High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

LCM-MVSNet		99.86 1	99.86 1	99.87 1	99.99 1	99.77 1	99.77 1	99.80 1	99.97 1	99.97 1	99.95 1	99.74 1	99.98 1	99.56 1	100.00 1	99.85 3

pmmvs6		99.07 4	99.24 4	98.56 49	99.81 2	96.38 64	98.87 9	99.30 11	99.01 16	99.63 9	99.66 3	99.27 2	99.68 126	97.75 30	99.89 22	99.62 25

UniMVSNet_ETH3D		99.12 3	99.28 3	98.65 43	99.77 3	96.34 66	99.18 5	99.20 16	99.67 2	99.73 3	99.65 4	99.15 3	99.86 20	97.22 47	99.92 14	99.77 8

XVG-OURS-SEG-HR		97.38 101	97.07 115	98.30 68	99.01 96	97.41 36	94.66 244	99.02 52	95.20 165	98.15 106	97.52 186	98.83 4	98.43 339	94.87 159	96.41 331	99.07 162

ACMH	93.61 9	98.44 22	98.76 13	97.51 130	99.43 34	93.54 181	98.23 40	99.05 43	97.40 74	99.37 18	99.08 37	98.79 5	99.47 195	97.74 31	99.71 55	99.50 45
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvs_tets		98.90 5	98.94 6	98.75 33	99.69 8	96.48 62	98.54 20	99.22 13	96.23 113	99.71 4	99.48 7	98.77 6	99.93 2	98.89 3	99.95 5	99.84 5

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 38	99.71 7	96.99 46	99.69 2	99.57 5	99.02 15	99.62 10	99.36 14	98.53 7	99.52 182	98.58 12	99.95 5	99.66 22
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
TransMVSNet (Re)		98.38 25	98.67 17	97.51 130	99.51 24	93.39 185	98.20 45	98.87 87	98.23 36	99.48 12	99.27 19	98.47 8	99.55 173	96.52 69	99.53 102	99.60 26

pm-mvs1		98.47 21	98.67 17	97.86 104	99.52 23	94.58 140	98.28 37	99.00 60	97.57 62	99.27 24	99.22 22	98.32 9	99.50 187	97.09 55	99.75 46	99.50 45

jajsoiax		98.77 9	98.79 12	98.74 35	99.66 10	96.48 62	98.45 27	99.12 28	95.83 140	99.67 6	99.37 12	98.25 10	99.92 4	98.77 5	99.94 8	99.82 6

ACMH+	93.58 10	98.23 32	98.31 29	97.98 96	99.39 39	95.22 118	97.55 82	99.20 16	98.21 37	99.25 25	98.51 76	98.21 11	99.40 219	94.79 163	99.72 52	99.32 101

HPM-MVS_fast		98.32 27	98.13 33	98.88 24	99.54 21	97.48 32	98.35 30	99.03 50	95.88 135	97.88 138	98.22 110	98.15 12	99.74 76	96.50 71	99.62 70	99.42 81

wuyk23d		93.25 276	95.20 193	87.40 352	96.07 323	95.38 105	97.04 113	94.97 316	95.33 160	99.70 5	98.11 121	98.14 13	91.94 370	77.76 363	99.68 61	74.89 370

ACMM	93.33 11	98.05 42	97.79 56	98.85 25	99.15 74	97.55 27	96.68 132	98.83 106	95.21 164	98.36 79	98.13 117	98.13 14	99.62 152	96.04 87	99.54 99	99.39 86
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS		98.11 38	97.83 54	98.92 22	99.42 36	97.46 33	98.57 17	99.05 43	95.43 158	97.41 166	97.50 188	97.98 15	99.79 40	95.58 117	99.57 87	99.50 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testgi		96.07 170	96.50 151	94.80 273	99.26 50	87.69 290	95.96 168	98.58 160	95.08 171	98.02 124	96.25 274	97.92 16	97.60 359	88.68 305	98.74 249	99.11 155

LPG-MVS_test		97.94 53	97.67 67	98.74 35	99.15 74	97.02 44	97.09 110	99.02 52	95.15 168	98.34 82	98.23 107	97.91 17	99.70 110	94.41 178	99.73 49	99.50 45

LGP-MVS_train				98.74 35	99.15 74	97.02 44		99.02 52	95.15 168	98.34 82	98.23 107	97.91 17	99.70 110	94.41 178	99.73 49	99.50 45

abl_6		98.42 23	98.19 32	99.09 3	99.16 71	98.10 6	97.73 73	99.11 29	97.76 51	98.62 52	98.27 103	97.88 19	99.80 39	95.67 108	99.50 116	99.38 88

SED-MVS		97.94 53	97.90 46	98.07 88	99.22 59	95.35 108	96.79 123	98.83 106	96.11 119	99.08 31	98.24 105	97.87 20	99.72 87	95.44 125	99.51 112	99.14 143

test_241102_ONE					99.22 59	95.35 108		98.83 106	96.04 124	99.08 31	98.13 117	97.87 20	99.33 240

SD-MVS		97.37 102	97.70 63	96.35 207	98.14 192	95.13 122	96.54 135	98.92 76	95.94 131	99.19 28	98.08 123	97.74 22	95.06 368	95.24 138	99.54 99	98.87 198
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
DeepC-MVS	95.41 4	97.82 70	97.70 63	98.16 80	98.78 114	95.72 85	96.23 152	99.02 52	93.92 212	98.62 52	98.99 42	97.69 23	99.62 152	96.18 81	99.87 24	99.15 140
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
nrg030		98.54 18	98.62 21	98.32 65	99.22 59	95.66 91	97.90 61	99.08 37	98.31 33	99.02 34	98.74 59	97.68 24	99.61 158	97.77 29	99.85 28	99.70 18

ANet_high		98.31 28	98.94 6	96.41 206	99.33 45	89.64 251	97.92 60	99.56 6	99.27 6	99.66 8	99.50 6	97.67 25	99.83 29	97.55 37	99.98 2	99.77 8

canonicalmvs		97.23 112	97.21 107	97.30 154	97.65 255	94.39 146	97.84 64	99.05 43	97.42 70	96.68 208	93.85 331	97.63 26	99.33 240	96.29 78	98.47 268	98.18 267

GeoE		97.75 75	97.70 63	97.89 101	98.88 106	94.53 141	97.10 109	98.98 66	95.75 144	97.62 149	97.59 180	97.61 27	99.77 54	96.34 77	99.44 134	99.36 96

TranMVSNet+NR-MVSNet		98.33 26	98.30 31	98.43 57	99.07 88	95.87 81	96.73 130	99.05 43	98.67 24	98.84 42	98.45 80	97.58 28	99.88 18	96.45 73	99.86 25	99.54 38

cdsmvs_eth3d_5k		24.22 341	32.30 344	0.00 359	0.00 382	0.00 383	0.00 370	98.10 220	0.00 377	0.00 378	95.06 311	97.54 29	0.00 378	0.00 376	0.00 376	0.00 374

ACMP	92.54 13	97.47 95	97.10 112	98.55 50	99.04 94	96.70 53	96.24 151	98.89 79	93.71 216	97.97 129	97.75 166	97.44 30	99.63 144	93.22 219	99.70 58	99.32 101
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_djsdf		98.73 11	98.74 16	98.69 40	99.63 12	96.30 68	98.67 13	99.02 52	96.50 101	99.32 20	99.44 10	97.43 31	99.92 4	98.73 7	99.95 5	99.86 2

TDRefinement		98.90 5	98.86 8	99.02 9	99.54 21	98.06 8	99.34 4	99.44 9	98.85 20	99.00 36	99.20 23	97.42 32	99.59 160	97.21 49	99.76 42	99.40 84

anonymousdsp		98.72 14	98.63 19	98.99 13	99.62 13	97.29 39	98.65 16	99.19 18	95.62 148	99.35 19	99.37 12	97.38 33	99.90 13	98.59 11	99.91 17	99.77 8

PS-CasMVS		98.73 11	98.85 10	98.39 60	99.55 19	95.47 102	98.49 24	99.13 27	99.22 8	99.22 27	98.96 45	97.35 34	99.92 4	97.79 28	99.93 10	99.79 7

COLMAP_ROB	94.48 6	98.25 31	98.11 34	98.64 44	99.21 66	97.35 37	97.96 56	99.16 20	98.34 32	98.78 45	98.52 75	97.32 35	99.45 202	94.08 193	99.67 62	99.13 146
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
EG-PatchMatch MVS		97.69 79	97.79 56	97.40 148	99.06 89	93.52 182	95.96 168	98.97 70	94.55 192	98.82 43	98.76 58	97.31 36	99.29 251	97.20 51	99.44 134	99.38 88

XXY-MVS		97.54 89	97.70 63	97.07 166	99.46 30	92.21 209	97.22 102	99.00 60	94.93 179	98.58 58	98.92 48	97.31 36	99.41 217	94.44 176	99.43 142	99.59 27

PEN-MVS		98.75 10	98.85 10	98.44 56	99.58 15	95.67 90	98.45 27	99.15 24	99.33 5	99.30 21	99.00 41	97.27 38	99.92 4	97.64 34	99.92 14	99.75 13

DTE-MVSNet		98.79 8	98.86 8	98.59 47	99.55 19	96.12 73	98.48 26	99.10 31	99.36 4	99.29 23	99.06 39	97.27 38	99.93 2	97.71 32	99.91 17	99.70 18

ZNCC-MVS		97.92 57	97.62 77	98.83 26	99.32 47	97.24 41	97.45 89	98.84 99	95.76 142	96.93 196	97.43 194	97.26 40	99.79 40	96.06 84	99.53 102	99.45 69

MP-MVS-pluss		97.69 79	97.36 95	98.70 39	99.50 27	96.84 49	95.38 201	98.99 63	92.45 252	98.11 110	98.31 90	97.25 41	99.77 54	96.60 65	99.62 70	99.48 59
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		97.89 62	97.63 75	98.67 41	99.35 43	96.84 49	96.36 143	98.79 116	95.07 172	97.88 138	98.35 86	97.24 42	99.72 87	96.05 86	99.58 84	99.45 69

Effi-MVS+		96.19 166	96.01 169	96.71 186	97.43 272	92.19 212	96.12 157	99.10 31	95.45 156	93.33 321	94.71 318	97.23 43	99.56 169	93.21 220	97.54 305	98.37 244

PGM-MVS		97.88 63	97.52 85	98.96 16	99.20 67	97.62 22	97.09 110	99.06 41	95.45 156	97.55 151	97.94 145	97.11 44	99.78 44	94.77 166	99.46 129	99.48 59

test_0728_THIRD									96.62 93	98.40 73	98.28 99	97.10 45	99.71 101	95.70 104	99.62 70	99.58 28

APD-MVS_3200maxsize		98.13 37	97.90 46	98.79 31	98.79 112	97.31 38	97.55 82	98.92 76	97.72 55	98.25 94	98.13 117	97.10 45	99.75 66	95.44 125	99.24 190	99.32 101

OPM-MVS		97.54 89	97.25 102	98.41 58	99.11 84	96.61 57	95.24 214	98.46 170	94.58 191	98.10 113	98.07 125	97.09 47	99.39 224	95.16 144	99.44 134	99.21 129
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HFP-MVS		97.94 53	97.64 73	98.83 26	99.15 74	97.50 30	97.59 79	98.84 99	96.05 122	97.49 157	97.54 183	97.07 48	99.70 110	95.61 114	99.46 129	99.30 107

#test#		97.62 83	97.22 106	98.83 26	99.15 74	97.50 30	96.81 122	98.84 99	94.25 201	97.49 157	97.54 183	97.07 48	99.70 110	94.37 181	99.46 129	99.30 107

DVP-MVS		97.78 73	97.65 70	98.16 80	99.24 54	95.51 97	96.74 126	98.23 200	95.92 132	98.40 73	98.28 99	97.06 50	99.71 101	95.48 121	99.52 107	99.26 120
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test0726					99.24 54	95.51 97	96.89 119	98.89 79	95.92 132	98.64 51	98.31 90	97.06 50

casdiffmvs		97.50 92	97.81 55	96.56 197	98.51 148	91.04 231	95.83 176	99.09 36	97.23 79	98.33 86	98.30 94	97.03 52	99.37 230	96.58 67	99.38 155	99.28 115

SteuartSystems-ACMMP		98.02 44	97.76 60	98.79 31	99.43 34	97.21 43	97.15 105	98.90 78	96.58 97	98.08 116	97.87 154	97.02 53	99.76 59	95.25 137	99.59 82	99.40 84
Skip Steuart: Steuart Systems R&D Blog.
PC_three_1452									87.24 308	98.37 76	97.44 193	97.00 54	96.78 365	92.01 233	99.25 187	99.21 129

DROMVSNet		97.90 61	97.94 45	97.79 108	98.66 129	95.14 121	98.31 34	99.66 3	97.57 62	95.95 243	97.01 230	96.99 55	99.82 30	97.66 33	99.64 67	98.39 242

DVP-MVS++		97.96 47	97.90 46	98.12 85	97.75 244	95.40 103	99.03 7	98.89 79	96.62 93	98.62 52	98.30 94	96.97 56	99.75 66	95.70 104	99.25 187	99.21 129

OPU-MVS				97.64 121	98.01 203	95.27 113	96.79 123				97.35 205	96.97 56	98.51 336	91.21 253	99.25 187	99.14 143

RE-MVS-def			97.88 50		98.81 109	98.05 9	97.55 82	98.86 90	97.77 48	98.20 99	98.07 125	96.94 58		95.49 118	99.20 192	99.26 120

APDe-MVS		98.14 34	98.03 40	98.47 55	98.72 120	96.04 76	98.07 52	99.10 31	95.96 129	98.59 57	98.69 63	96.94 58	99.81 33	96.64 63	99.58 84	99.57 32

test_one_0601					99.05 93	95.50 100		98.87 87	97.21 80	98.03 122	98.30 94	96.93 60

GST-MVS		97.82 70	97.49 89	98.81 29	99.23 56	97.25 40	97.16 104	98.79 116	95.96 129	97.53 152	97.40 196	96.93 60	99.77 54	95.04 153	99.35 164	99.42 81

test_241102_TWO								98.83 106	96.11 119	98.62 52	98.24 105	96.92 62	99.72 87	95.44 125	99.49 120	99.49 53

LCM-MVSNet-Re		97.33 105	97.33 97	97.32 153	98.13 195	93.79 171	96.99 116	99.65 4	96.74 91	99.47 13	98.93 47	96.91 63	99.84 26	90.11 283	99.06 217	98.32 251

VPA-MVSNet		98.27 29	98.46 24	97.70 116	99.06 89	93.80 170	97.76 69	99.00 60	98.40 30	99.07 33	98.98 43	96.89 64	99.75 66	97.19 52	99.79 38	99.55 37

ACMMP		98.05 42	97.75 62	98.93 21	99.23 56	97.60 23	98.09 51	98.96 71	95.75 144	97.91 134	98.06 130	96.89 64	99.76 59	95.32 133	99.57 87	99.43 80
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
CS-MVS		98.08 39	98.01 41	98.29 70	98.46 158	96.58 59	98.53 22	99.69 2	98.07 41	96.04 239	97.18 216	96.88 66	99.86 20	97.48 40	99.74 48	98.43 239

PMVS	89.60 17	96.71 143	96.97 120	95.95 226	99.51 24	97.81 17	97.42 93	97.49 261	97.93 45	95.95 243	98.58 69	96.88 66	96.91 362	89.59 291	99.36 159	93.12 362
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
region2R		97.92 57	97.59 80	98.92 22	99.22 59	97.55 27	97.60 78	98.84 99	96.00 127	97.22 170	97.62 178	96.87 68	99.76 59	95.48 121	99.43 142	99.46 64

CP-MVS		97.92 57	97.56 83	98.99 13	98.99 97	97.82 16	97.93 58	98.96 71	96.11 119	96.89 199	97.45 192	96.85 69	99.78 44	95.19 140	99.63 69	99.38 88

DPE-MVS		97.64 81	97.35 96	98.50 52	98.85 107	96.18 70	95.21 216	98.99 63	95.84 139	98.78 45	98.08 123	96.84 70	99.81 33	93.98 200	99.57 87	99.52 42
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_0402		97.84 67	97.97 42	97.47 138	99.19 69	94.07 159	96.71 131	98.73 129	98.66 25	98.56 59	98.41 82	96.84 70	99.69 118	94.82 161	99.81 33	98.64 221

ACMMPR		97.95 51	97.62 77	98.94 18	99.20 67	97.56 26	97.59 79	98.83 106	96.05 122	97.46 163	97.63 177	96.77 72	99.76 59	95.61 114	99.46 129	99.49 53

Vis-MVSNet		98.27 29	98.34 28	98.07 88	99.33 45	95.21 120	98.04 53	99.46 8	97.32 76	97.82 146	99.11 34	96.75 73	99.86 20	97.84 25	99.36 159	99.15 140
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Fast-Effi-MVS+		95.49 191	95.07 199	96.75 184	97.67 254	92.82 197	94.22 260	98.60 157	91.61 263	93.42 319	92.90 341	96.73 74	99.70 110	92.60 226	97.89 289	97.74 294

baseline		97.44 97	97.78 59	96.43 203	98.52 147	90.75 238	96.84 120	99.03 50	96.51 100	97.86 142	98.02 134	96.67 75	99.36 232	97.09 55	99.47 126	99.19 133

SR-MVS		98.00 46	97.66 68	99.01 11	98.77 116	97.93 11	97.38 95	98.83 106	97.32 76	98.06 118	97.85 155	96.65 76	99.77 54	95.00 156	99.11 208	99.32 101

tfpnnormal		97.72 77	97.97 42	96.94 172	99.26 50	92.23 208	97.83 65	98.45 171	98.25 35	99.13 30	98.66 65	96.65 76	99.69 118	93.92 202	99.62 70	98.91 188

DeepPCF-MVS	94.58 5	96.90 126	96.43 153	98.31 67	97.48 266	97.23 42	92.56 311	98.60 157	92.84 247	98.54 60	97.40 196	96.64 78	98.78 310	94.40 180	99.41 151	98.93 183

MVS_111021_LR		96.82 133	96.55 144	97.62 122	98.27 173	95.34 110	93.81 281	98.33 191	94.59 190	96.56 214	96.63 254	96.61 79	98.73 315	94.80 162	99.34 167	98.78 207

Gipuma		98.07 41	98.31 29	97.36 151	99.76 5	96.28 69	98.51 23	99.10 31	98.76 23	96.79 201	99.34 17	96.61 79	98.82 306	96.38 75	99.50 116	96.98 316
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test1172		98.08 39	97.76 60	99.05 6	98.78 114	98.07 7	97.41 94	98.85 94	97.57 62	98.15 106	97.96 140	96.60 81	99.76 59	95.30 134	99.18 197	99.33 100

SR-MVS-dyc-post		98.14 34	97.84 52	99.02 9	98.81 109	98.05 9	97.55 82	98.86 90	97.77 48	98.20 99	98.07 125	96.60 81	99.76 59	95.49 118	99.20 192	99.26 120

MVS_111021_HR		96.73 140	96.54 146	97.27 155	98.35 166	93.66 178	93.42 291	98.36 186	94.74 183	96.58 212	96.76 247	96.54 83	98.99 291	94.87 159	99.27 185	99.15 140

SMA-MVS		97.48 94	97.11 111	98.60 46	98.83 108	96.67 54	96.74 126	98.73 129	91.61 263	98.48 66	98.36 85	96.53 84	99.68 126	95.17 142	99.54 99	99.45 69
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
v7n		98.73 11	98.99 5	97.95 97	99.64 11	94.20 156	98.67 13	99.14 26	99.08 10	99.42 15	99.23 21	96.53 84	99.91 12	99.27 2	99.93 10	99.73 15

mPP-MVS		97.91 60	97.53 84	99.04 7	99.22 59	97.87 15	97.74 71	98.78 120	96.04 124	97.10 180	97.73 169	96.53 84	99.78 44	95.16 144	99.50 116	99.46 64

XVS		97.96 47	97.63 75	98.94 18	99.15 74	97.66 20	97.77 67	98.83 106	97.42 70	96.32 225	97.64 176	96.49 87	99.72 87	95.66 110	99.37 156	99.45 69

X-MVStestdata		92.86 280	90.83 305	98.94 18	99.15 74	97.66 20	97.77 67	98.83 106	97.42 70	96.32 225	36.50 372	96.49 87	99.72 87	95.66 110	99.37 156	99.45 69

9.14			96.69 135		98.53 146		96.02 163	98.98 66	93.23 229	97.18 174	97.46 191	96.47 89	99.62 152	92.99 223	99.32 176

UA-Net		98.88 7	98.76 13	99.22 2	99.11 84	97.89 14	99.47 3	99.32 10	99.08 10	97.87 141	99.67 2	96.47 89	99.92 4	97.88 23	99.98 2	99.85 3

xxxxxxxxxxxxxcwj		97.24 111	97.03 118	97.89 101	98.48 154	94.71 134	94.53 249	99.07 40	95.02 175	97.83 144	97.88 152	96.44 91	99.72 87	94.59 173	99.39 153	99.25 124

SF-MVS		97.60 85	97.39 93	98.22 76	98.93 102	95.69 87	97.05 112	99.10 31	95.32 161	97.83 144	97.88 152	96.44 91	99.72 87	94.59 173	99.39 153	99.25 124

xiu_mvs_v1_base_debu		95.62 186	95.96 173	94.60 280	98.01 203	88.42 271	93.99 272	98.21 201	92.98 241	95.91 245	94.53 321	96.39 93	99.72 87	95.43 128	98.19 276	95.64 346

xiu_mvs_v1_base		95.62 186	95.96 173	94.60 280	98.01 203	88.42 271	93.99 272	98.21 201	92.98 241	95.91 245	94.53 321	96.39 93	99.72 87	95.43 128	98.19 276	95.64 346

xiu_mvs_v1_base_debi		95.62 186	95.96 173	94.60 280	98.01 203	88.42 271	93.99 272	98.21 201	92.98 241	95.91 245	94.53 321	96.39 93	99.72 87	95.43 128	98.19 276	95.64 346

ETV-MVS		96.13 169	95.90 176	96.82 180	97.76 242	93.89 165	95.40 199	98.95 73	95.87 136	95.58 259	91.00 362	96.36 96	99.72 87	93.36 214	98.83 241	96.85 323

MP-MVS		97.64 81	97.18 108	99.00 12	99.32 47	97.77 18	97.49 88	98.73 129	96.27 110	95.59 258	97.75 166	96.30 97	99.78 44	93.70 210	99.48 124	99.45 69
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TinyColmap		96.00 175	96.34 156	94.96 264	97.90 215	87.91 283	94.13 267	98.49 168	94.41 194	98.16 104	97.76 163	96.29 98	98.68 322	90.52 276	99.42 145	98.30 255

Fast-Effi-MVS+-dtu		96.44 157	96.12 164	97.39 149	97.18 289	94.39 146	95.46 193	98.73 129	96.03 126	94.72 275	94.92 315	96.28 99	99.69 118	93.81 205	97.98 284	98.09 269

OMC-MVS		96.48 155	96.00 170	97.91 100	98.30 168	96.01 79	94.86 236	98.60 157	91.88 260	97.18 174	97.21 215	96.11 100	99.04 285	90.49 279	99.34 167	98.69 218

xiu_mvs_v2_base		94.22 248	94.63 223	92.99 317	97.32 283	84.84 329	92.12 319	97.84 239	91.96 258	94.17 289	93.43 332	96.07 101	99.71 101	91.27 250	97.48 308	94.42 355

CSCG		97.40 100	97.30 98	97.69 118	98.95 99	94.83 129	97.28 98	98.99 63	96.35 109	98.13 109	95.95 291	95.99 102	99.66 137	94.36 184	99.73 49	98.59 227

PHI-MVS		96.96 122	96.53 147	98.25 74	97.48 266	96.50 61	96.76 125	98.85 94	93.52 219	96.19 234	96.85 238	95.94 103	99.42 208	93.79 206	99.43 142	98.83 201

TSAR-MVS + MP.		97.42 98	97.23 105	98.00 95	99.38 40	95.00 125	97.63 77	98.20 204	93.00 240	98.16 104	98.06 130	95.89 104	99.72 87	95.67 108	99.10 210	99.28 115
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
XVG-ACMP-BASELINE		97.58 87	97.28 101	98.49 53	99.16 71	96.90 48	96.39 140	98.98 66	95.05 173	98.06 118	98.02 134	95.86 105	99.56 169	94.37 181	99.64 67	99.00 171

AllTest		97.20 113	96.92 124	98.06 90	99.08 86	96.16 71	97.14 107	99.16 20	94.35 197	97.78 147	98.07 125	95.84 106	99.12 274	91.41 247	99.42 145	98.91 188

TestCases				98.06 90	99.08 86	96.16 71		99.16 20	94.35 197	97.78 147	98.07 125	95.84 106	99.12 274	91.41 247	99.42 145	98.91 188

APD-MVS		97.00 117	96.53 147	98.41 58	98.55 144	96.31 67	96.32 146	98.77 121	92.96 245	97.44 165	97.58 182	95.84 106	99.74 76	91.96 234	99.35 164	99.19 133
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
pcd_1.5k_mvsjas		7.98 344	10.65 347	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	95.82 109	0.00 378	0.00 376	0.00 376	0.00 374

PS-MVSNAJss		98.53 19	98.63 19	98.21 79	99.68 9	94.82 130	98.10 50	99.21 14	96.91 86	99.75 2	99.45 9	95.82 109	99.92 4	98.80 4	99.96 4	99.89 1

PS-MVSNAJ		94.10 254	94.47 233	93.00 316	97.35 276	84.88 328	91.86 323	97.84 239	91.96 258	94.17 289	92.50 348	95.82 109	99.71 101	91.27 250	97.48 308	94.40 356

3Dnovator	96.53 2	97.61 84	97.64 73	97.50 133	97.74 247	93.65 179	98.49 24	98.88 85	96.86 88	97.11 179	98.55 73	95.82 109	99.73 82	95.94 95	99.42 145	99.13 146

zzz-MVS		98.01 45	97.66 68	99.06 4	99.44 32	97.90 12	95.66 184	98.73 129	97.69 58	97.90 135	97.96 140	95.81 113	99.82 30	96.13 82	99.61 76	99.45 69

MTAPA		98.14 34	97.84 52	99.06 4	99.44 32	97.90 12	97.25 99	98.73 129	97.69 58	97.90 135	97.96 140	95.81 113	99.82 30	96.13 82	99.61 76	99.45 69

DP-MVS		97.87 64	97.89 49	97.81 107	98.62 135	94.82 130	97.13 108	98.79 116	98.98 17	98.74 48	98.49 77	95.80 115	99.49 189	95.04 153	99.44 134	99.11 155

Anonymous20240529		97.96 47	98.04 39	97.71 114	98.69 127	94.28 153	97.86 63	98.31 194	98.79 22	99.23 26	98.86 53	95.76 116	99.61 158	95.49 118	99.36 159	99.23 127

LS3D		97.77 74	97.50 88	98.57 48	96.24 313	97.58 25	98.45 27	98.85 94	98.58 27	97.51 154	97.94 145	95.74 117	99.63 144	95.19 140	98.97 222	98.51 233

EIA-MVS		96.04 172	95.77 180	96.85 178	97.80 230	92.98 194	96.12 157	99.16 20	94.65 186	93.77 302	91.69 356	95.68 118	99.67 131	94.18 189	98.85 239	97.91 287

CNVR-MVS		96.92 124	96.55 144	98.03 94	98.00 207	95.54 95	94.87 235	98.17 210	94.60 188	96.38 222	97.05 226	95.67 119	99.36 232	95.12 150	99.08 212	99.19 133

CLD-MVS		95.47 194	95.07 199	96.69 188	98.27 173	92.53 202	91.36 329	98.67 147	91.22 271	95.78 252	94.12 329	95.65 120	98.98 293	90.81 262	99.72 52	98.57 228
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Anonymous20231211		98.55 17	98.76 13	97.94 98	98.79 112	94.37 148	98.84 10	99.15 24	99.37 3	99.67 6	99.43 11	95.61 121	99.72 87	98.12 16	99.86 25	99.73 15

EGC-MVSNET		83.08 338	77.93 341	98.53 51	99.57 16	97.55 27	98.33 33	98.57 161	4.71 374	10.38 375	98.90 50	95.60 122	99.50 187	95.69 106	99.61 76	98.55 231

Regformer-2		97.41 99	97.24 104	97.93 99	97.21 287	94.72 133	94.85 237	98.27 195	97.74 52	98.11 110	97.50 188	95.58 123	99.69 118	96.57 68	99.31 178	99.37 95

ITE_SJBPF				97.85 105	98.64 130	96.66 55		98.51 167	95.63 147	97.22 170	97.30 210	95.52 124	98.55 333	90.97 257	98.90 231	98.34 250

CS-MVS-test		96.62 149	96.59 139	96.69 188	97.88 217	93.16 190	97.21 103	99.53 7	95.61 149	93.72 304	95.33 306	95.49 125	99.69 118	95.37 132	99.19 196	97.22 310

Regformer-4		97.53 91	97.47 91	97.71 114	97.35 276	93.91 164	95.26 211	98.14 216	97.97 44	98.34 82	97.89 150	95.49 125	99.71 101	97.41 42	99.42 145	99.51 44

DeepC-MVS_fast	94.34 7	96.74 138	96.51 150	97.44 144	97.69 250	94.15 157	96.02 163	98.43 174	93.17 235	97.30 168	97.38 202	95.48 127	99.28 253	93.74 207	99.34 167	98.88 196
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
WR-MVS_H		98.65 15	98.62 21	98.75 33	99.51 24	96.61 57	98.55 19	99.17 19	99.05 13	99.17 29	98.79 55	95.47 128	99.89 16	97.95 21	99.91 17	99.75 13

FMVSNet1		97.95 51	98.08 35	97.56 125	99.14 82	93.67 175	98.23 40	98.66 149	97.41 73	99.00 36	99.19 24	95.47 128	99.73 82	95.83 102	99.76 42	99.30 107

MIMVSNet1		98.51 20	98.45 26	98.67 41	99.72 6	96.71 52	98.76 11	98.89 79	98.49 28	99.38 17	99.14 33	95.44 130	99.84 26	96.47 72	99.80 36	99.47 62

CP-MVSNet		98.42 23	98.46 24	98.30 68	99.46 30	95.22 118	98.27 39	98.84 99	99.05 13	99.01 35	98.65 67	95.37 131	99.90 13	97.57 36	99.91 17	99.77 8

Regformer-1		97.27 108	97.16 109	97.61 123	97.21 287	93.86 167	94.85 237	98.04 230	97.62 61	98.03 122	97.50 188	95.34 132	99.63 144	96.52 69	99.31 178	99.35 98

segment_acmp												95.34 132

CDPH-MVS		95.45 196	94.65 220	97.84 106	98.28 171	94.96 126	93.73 283	98.33 191	85.03 333	95.44 260	96.60 255	95.31 134	99.44 205	90.01 285	99.13 204	99.11 155

3Dnovator+	96.13 3	97.73 76	97.59 80	98.15 83	98.11 197	95.60 93	98.04 53	98.70 139	98.13 39	96.93 196	98.45 80	95.30 135	99.62 152	95.64 112	98.96 223	99.24 126

MVS_Test		96.27 162	96.79 132	94.73 276	96.94 298	86.63 306	96.18 154	98.33 191	94.94 177	96.07 238	98.28 99	95.25 136	99.26 256	97.21 49	97.90 288	98.30 255

XVG-OURS		97.12 114	96.74 133	98.26 71	98.99 97	97.45 34	93.82 279	99.05 43	95.19 166	98.32 87	97.70 172	95.22 137	98.41 340	94.27 186	98.13 279	98.93 183

MCST-MVS		96.24 163	95.80 178	97.56 125	98.75 117	94.13 158	94.66 244	98.17 210	90.17 281	96.21 233	96.10 284	95.14 138	99.43 207	94.13 192	98.85 239	99.13 146

EI-MVSNet-Vis-set		97.32 106	97.39 93	97.11 163	97.36 275	92.08 215	95.34 204	97.65 253	97.74 52	98.29 92	98.11 121	95.05 139	99.68 126	97.50 39	99.50 116	99.56 35

Regformer-3		97.25 110	97.29 99	97.11 163	97.35 276	92.32 206	95.26 211	97.62 258	97.67 60	98.17 103	97.89 150	95.05 139	99.56 169	97.16 53	99.42 145	99.46 64

EI-MVSNet-UG-set		97.32 106	97.40 92	97.09 165	97.34 280	92.01 217	95.33 205	97.65 253	97.74 52	98.30 91	98.14 116	95.04 141	99.69 118	97.55 37	99.52 107	99.58 28

KD-MVS_self_test		97.86 66	98.07 36	97.25 158	99.22 59	92.81 198	97.55 82	98.94 74	97.10 82	98.85 41	98.88 51	95.03 142	99.67 131	97.39 44	99.65 65	99.26 120

ZD-MVS					98.43 160	95.94 80		98.56 162	90.72 275	96.66 209	97.07 224	95.02 143	99.74 76	91.08 254	98.93 229

DELS-MVS		96.17 167	96.23 159	95.99 222	97.55 263	90.04 245	92.38 316	98.52 165	94.13 205	96.55 216	97.06 225	94.99 144	99.58 162	95.62 113	99.28 183	98.37 244
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
ab-mvs		96.59 150	96.59 139	96.60 192	98.64 130	92.21 209	98.35 30	97.67 249	94.45 193	96.99 191	98.79 55	94.96 145	99.49 189	90.39 280	99.07 214	98.08 270

ETH3D-3000-0.1		96.89 128	96.46 152	98.16 80	98.62 135	95.69 87	95.96 168	98.98 66	93.36 224	97.04 187	97.31 209	94.93 146	99.63 144	92.60 226	99.34 167	99.17 136

MSLP-MVS++		96.42 159	96.71 134	95.57 241	97.82 225	90.56 242	95.71 179	98.84 99	94.72 184	96.71 207	97.39 200	94.91 147	98.10 354	95.28 135	99.02 219	98.05 279

QAPM		95.88 179	95.57 187	96.80 181	97.90 215	91.84 221	98.18 47	98.73 129	88.41 297	96.42 220	98.13 117	94.73 148	99.75 66	88.72 303	98.94 227	98.81 203

RPSCF		97.87 64	97.51 86	98.95 17	99.15 74	98.43 3	97.56 81	99.06 41	96.19 116	98.48 66	98.70 62	94.72 149	99.24 259	94.37 181	99.33 174	99.17 136

DU-MVS		97.79 72	97.60 79	98.36 62	98.73 118	95.78 83	95.65 187	98.87 87	97.57 62	98.31 89	97.83 157	94.69 150	99.85 23	97.02 58	99.71 55	99.46 64

Baseline_NR-MVSNet		97.72 77	97.79 56	97.50 133	99.56 17	93.29 186	95.44 194	98.86 90	98.20 38	98.37 76	99.24 20	94.69 150	99.55 173	95.98 93	99.79 38	99.65 23

TEST9					97.84 222	95.23 115	93.62 285	98.39 182	86.81 313	93.78 300	95.99 286	94.68 152	99.52 182

UniMVSNet (Re)		97.83 68	97.65 70	98.35 64	98.80 111	95.86 82	95.92 172	99.04 49	97.51 67	98.22 98	97.81 161	94.68 152	99.78 44	97.14 54	99.75 46	99.41 83

agg_prior1		95.39 198	94.60 225	97.75 111	97.80 230	94.96 126	93.39 293	98.36 186	87.20 309	93.49 314	95.97 289	94.65 154	99.53 178	91.69 244	98.86 237	98.77 210

UniMVSNet_NR-MVSNet		97.83 68	97.65 70	98.37 61	98.72 120	95.78 83	95.66 184	99.02 52	98.11 40	98.31 89	97.69 174	94.65 154	99.85 23	97.02 58	99.71 55	99.48 59

VPNet		97.26 109	97.49 89	96.59 193	99.47 29	90.58 240	96.27 147	98.53 164	97.77 48	98.46 69	98.41 82	94.59 156	99.68 126	94.61 169	99.29 182	99.52 42

train_agg		95.46 195	94.66 219	97.88 103	97.84 222	95.23 115	93.62 285	98.39 182	87.04 311	93.78 300	95.99 286	94.58 157	99.52 182	91.76 242	98.90 231	98.89 192

test_8					97.81 226	95.07 124	93.54 288	98.38 184	87.04 311	93.71 305	95.96 290	94.58 157	99.52 182

API-MVS		95.09 211	95.01 203	95.31 252	96.61 304	94.02 161	96.83 121	97.18 271	95.60 150	95.79 250	94.33 326	94.54 159	98.37 345	85.70 332	98.52 265	93.52 359

Test By Simon												94.51 160

MSDG		95.33 200	95.13 196	95.94 228	97.40 274	91.85 220	91.02 340	98.37 185	95.30 162	96.31 227	95.99 286	94.51 160	98.38 343	89.59 291	97.65 302	97.60 301

TSAR-MVS + GP.		96.47 156	96.12 164	97.49 136	97.74 247	95.23 115	94.15 264	96.90 282	93.26 228	98.04 121	96.70 250	94.41 162	98.89 301	94.77 166	99.14 200	98.37 244

NR-MVSNet		97.96 47	97.86 51	98.26 71	98.73 118	95.54 95	98.14 48	98.73 129	97.79 47	99.42 15	97.83 157	94.40 163	99.78 44	95.91 97	99.76 42	99.46 64

AdaColmap		95.11 209	94.62 224	96.58 194	97.33 282	94.45 145	94.92 233	98.08 223	93.15 236	93.98 298	95.53 303	94.34 164	99.10 279	85.69 333	98.61 261	96.20 340

FC-MVSNet-test		98.16 33	98.37 27	97.56 125	99.49 28	93.10 192	98.35 30	99.21 14	98.43 29	98.89 39	98.83 54	94.30 165	99.81 33	97.87 24	99.91 17	99.77 8

Effi-MVS+-dtu		96.81 134	96.09 166	98.99 13	96.90 300	98.69 2	96.42 139	98.09 221	95.86 137	95.15 266	95.54 302	94.26 166	99.81 33	94.06 194	98.51 267	98.47 236

mvs-test1		96.20 165	95.50 189	98.32 65	96.90 300	98.16 5	95.07 224	98.09 221	95.86 137	93.63 308	94.32 327	94.26 166	99.71 101	94.06 194	97.27 316	97.07 313

ambc				96.56 197	98.23 179	91.68 224	97.88 62	98.13 218		98.42 72	98.56 72	94.22 168	99.04 285	94.05 197	99.35 164	98.95 177

test20.03		96.58 151	96.61 138	96.48 201	98.49 152	91.72 223	95.68 183	97.69 248	96.81 89	98.27 93	97.92 148	94.18 169	98.71 317	90.78 264	99.66 64	99.00 171

HPM-MVS++		96.99 118	96.38 154	98.81 29	98.64 130	97.59 24	95.97 167	98.20 204	95.51 154	95.06 267	96.53 259	94.10 170	99.70 110	94.29 185	99.15 199	99.13 146

testtj		96.69 144	96.13 163	98.36 62	98.46 158	96.02 78	96.44 138	98.70 139	94.26 200	96.79 201	97.13 218	94.07 171	99.75 66	90.53 275	98.80 243	99.31 106

ETH3D cwj APD-0.16		96.23 164	95.61 186	98.09 87	97.91 213	95.65 92	94.94 232	98.74 127	91.31 269	96.02 241	97.08 223	94.05 172	99.69 118	91.51 246	98.94 227	98.93 183

PM-MVS		97.36 104	97.10 112	98.14 84	98.91 104	96.77 51	96.20 153	98.63 155	93.82 213	98.54 60	98.33 88	93.98 173	99.05 284	95.99 92	99.45 133	98.61 226

OpenMVS	94.22 8	95.48 193	95.20 193	96.32 209	97.16 290	91.96 218	97.74 71	98.84 99	87.26 307	94.36 286	98.01 136	93.95 174	99.67 131	90.70 270	98.75 248	97.35 309

v8		97.60 85	98.06 38	96.23 213	98.71 123	89.44 255	97.43 92	98.82 114	97.29 78	98.74 48	99.10 35	93.86 175	99.68 126	98.61 10	99.94 8	99.56 35

diffmvs		96.04 172	96.23 159	95.46 248	97.35 276	88.03 282	93.42 291	99.08 37	94.09 207	96.66 209	96.93 234	93.85 176	99.29 251	96.01 91	98.67 254	99.06 164

NCCC		96.52 153	95.99 171	98.10 86	97.81 226	95.68 89	95.00 230	98.20 204	95.39 159	95.40 262	96.36 270	93.81 177	99.45 202	93.55 213	98.42 269	99.17 136

TAPA-MVS	93.32 12	94.93 216	94.23 240	97.04 168	98.18 185	94.51 142	95.22 215	98.73 129	81.22 350	96.25 231	95.95 291	93.80 178	98.98 293	89.89 287	98.87 235	97.62 299
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
FIs		97.93 56	98.07 36	97.48 137	99.38 40	92.95 195	98.03 55	99.11 29	98.04 43	98.62 52	98.66 65	93.75 179	99.78 44	97.23 46	99.84 29	99.73 15

OurMVSNet-221017-0		98.61 16	98.61 23	98.63 45	99.77 3	96.35 65	99.17 6	99.05 43	98.05 42	99.61 11	99.52 5	93.72 180	99.88 18	98.72 9	99.88 23	99.65 23

test_prior3		95.91 177	95.39 190	97.46 141	97.79 236	94.26 154	93.33 296	98.42 177	94.21 202	94.02 295	96.25 274	93.64 181	99.34 237	91.90 236	98.96 223	98.79 205

test_prior2							93.33 296		94.21 202	94.02 295	96.25 274	93.64 181		91.90 236	98.96 223

旧先验1					97.80 230	93.87 166		97.75 244			97.04 227	93.57 183			98.68 253	98.72 215

v10		97.55 88	97.97 42	96.31 210	98.60 138	89.64 251	97.44 90	99.02 52	96.60 95	98.72 50	99.16 30	93.48 184	99.72 87	98.76 6	99.92 14	99.58 28

v148		96.58 151	96.97 120	95.42 249	98.63 134	87.57 291	95.09 221	97.90 234	95.91 134	98.24 96	97.96 140	93.42 185	99.39 224	96.04 87	99.52 107	99.29 114

V42		97.04 116	97.16 109	96.68 190	98.59 140	91.05 230	96.33 145	98.36 186	94.60 188	97.99 125	98.30 94	93.32 186	99.62 152	97.40 43	99.53 102	99.38 88

new-patchmatchnet		95.67 185	96.58 141	92.94 319	97.48 266	80.21 354	92.96 302	98.19 209	94.83 181	98.82 43	98.79 55	93.31 187	99.51 186	95.83 102	99.04 218	99.12 151

test12				97.46 141	97.61 258	94.07 159		97.78 243		93.57 312		93.31 187	99.42 208		98.78 245	98.89 192

UGNet		96.81 134	96.56 143	97.58 124	96.64 303	93.84 169	97.75 70	97.12 274	96.47 104	93.62 309	98.88 51	93.22 189	99.53 178	95.61 114	99.69 59	99.36 96
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
pmmvs-eth3d		96.49 154	96.18 162	97.42 146	98.25 176	94.29 150	94.77 241	98.07 227	89.81 284	97.97 129	98.33 88	93.11 190	99.08 281	95.46 124	99.84 29	98.89 192

v1144		96.84 129	97.08 114	96.13 219	98.42 161	89.28 258	95.41 198	98.67 147	94.21 202	97.97 129	98.31 90	93.06 191	99.65 139	98.06 19	99.62 70	99.45 69

PVSNet_BlendedMVS		95.02 215	94.93 206	95.27 253	97.79 236	87.40 295	94.14 266	98.68 144	88.94 292	94.51 282	98.01 136	93.04 192	99.30 247	89.77 289	99.49 120	99.11 155

PVSNet_Blended		93.96 258	93.65 257	94.91 265	97.79 236	87.40 295	91.43 328	98.68 144	84.50 338	94.51 282	94.48 324	93.04 192	99.30 247	89.77 289	98.61 261	98.02 282

mvs_anonymous		95.36 199	96.07 168	93.21 311	96.29 311	81.56 349	94.60 246	97.66 251	93.30 227	96.95 195	98.91 49	93.03 194	99.38 227	96.60 65	97.30 315	98.69 218

v1192		96.83 132	97.06 116	96.15 218	98.28 171	89.29 257	95.36 202	98.77 121	93.73 215	98.11 110	98.34 87	93.02 195	99.67 131	98.35 14	99.58 84	99.50 45

F-COLMAP		95.30 202	94.38 237	98.05 93	98.64 130	96.04 76	95.61 190	98.66 149	89.00 291	93.22 322	96.40 267	92.90 196	99.35 235	87.45 322	97.53 306	98.77 210

WR-MVS		96.90 126	96.81 129	97.16 160	98.56 143	92.20 211	94.33 253	98.12 219	97.34 75	98.20 99	97.33 207	92.81 197	99.75 66	94.79 163	99.81 33	99.54 38

v1240		96.74 138	97.02 119	95.91 229	98.18 185	88.52 270	95.39 200	98.88 85	93.15 236	98.46 69	98.40 84	92.80 198	99.71 101	98.45 13	99.49 120	99.49 53

MVE	73.61 22	86.48 336	85.92 338	88.18 350	96.23 315	85.28 322	81.78 368	75.79 374	86.01 318	82.53 370	91.88 353	92.74 199	87.47 373	71.42 370	94.86 348	91.78 364
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DP-MVS Recon		95.55 189	95.13 196	96.80 181	98.51 148	93.99 163	94.60 246	98.69 142	90.20 280	95.78 252	96.21 277	92.73 200	98.98 293	90.58 274	98.86 237	97.42 306

CANet		95.86 180	95.65 183	96.49 200	96.41 309	90.82 235	94.36 252	98.41 179	94.94 177	92.62 335	96.73 248	92.68 201	99.71 101	95.12 150	99.60 80	98.94 179

v1921920		96.72 141	96.96 122	95.99 222	98.21 180	88.79 267	95.42 196	98.79 116	93.22 230	98.19 102	98.26 104	92.68 201	99.70 110	98.34 15	99.55 96	99.49 53

BH-untuned		94.69 229	94.75 217	94.52 285	97.95 212	87.53 292	94.07 269	97.01 278	93.99 209	97.10 180	95.65 298	92.65 203	98.95 298	87.60 318	96.74 325	97.09 312

LF4IMVS		96.07 170	95.63 184	97.36 151	98.19 182	95.55 94	95.44 194	98.82 114	92.29 254	95.70 256	96.55 257	92.63 204	98.69 319	91.75 243	99.33 174	97.85 289

v2v482		96.78 136	97.06 116	95.95 226	98.57 142	88.77 268	95.36 202	98.26 197	95.18 167	97.85 143	98.23 107	92.58 205	99.63 144	97.80 27	99.69 59	99.45 69

EI-MVSNet		96.63 148	96.93 123	95.74 235	97.26 285	88.13 280	95.29 209	97.65 253	96.99 83	97.94 132	98.19 112	92.55 206	99.58 162	96.91 61	99.56 90	99.50 45

IterMVS-LS		96.92 124	97.29 99	95.79 233	98.51 148	88.13 280	95.10 219	98.66 149	96.99 83	98.46 69	98.68 64	92.55 206	99.74 76	96.91 61	99.79 38	99.50 45
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
VDD-MVS		97.37 102	97.25 102	97.74 112	98.69 127	94.50 144	97.04 113	95.61 309	98.59 26	98.51 62	98.72 60	92.54 208	99.58 162	96.02 89	99.49 120	99.12 151

MVS		90.02 313	89.20 320	92.47 326	94.71 346	86.90 303	95.86 173	96.74 289	64.72 370	90.62 346	92.77 343	92.54 208	98.39 342	79.30 358	95.56 343	92.12 363

v144192		96.69 144	96.90 126	96.03 221	98.25 176	88.92 262	95.49 192	98.77 121	93.05 238	98.09 114	98.29 98	92.51 210	99.70 110	98.11 17	99.56 90	99.47 62

原ACMM1				96.58 194	98.16 189	92.12 213		98.15 215	85.90 321	93.49 314	96.43 264	92.47 211	99.38 227	87.66 317	98.62 260	98.23 262

VNet		96.84 129	96.83 128	96.88 176	98.06 198	92.02 216	96.35 144	97.57 260	97.70 57	97.88 138	97.80 162	92.40 212	99.54 176	94.73 168	98.96 223	99.08 160

114514_t		93.96 258	93.22 265	96.19 216	99.06 89	90.97 233	95.99 165	98.94 74	73.88 368	93.43 318	96.93 234	92.38 213	99.37 230	89.09 298	99.28 183	98.25 261

CPTT-MVS		96.69 144	96.08 167	98.49 53	98.89 105	96.64 56	97.25 99	98.77 121	92.89 246	96.01 242	97.13 218	92.23 214	99.67 131	92.24 231	99.34 167	99.17 136

MSP-MVS		97.45 96	96.92 124	99.03 8	99.26 50	97.70 19	97.66 74	98.89 79	95.65 146	98.51 62	96.46 263	92.15 215	99.81 33	95.14 147	98.58 264	99.58 28
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
MAR-MVS		94.21 250	93.03 267	97.76 110	96.94 298	97.44 35	96.97 117	97.15 272	87.89 305	92.00 340	92.73 345	92.14 216	99.12 274	83.92 346	97.51 307	96.73 330
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
PVSNet_Blended_VisFu		95.95 176	95.80 178	96.42 204	99.28 49	90.62 239	95.31 207	99.08 37	88.40 298	96.97 194	98.17 115	92.11 217	99.78 44	93.64 211	99.21 191	98.86 199

BH-RMVSNet		94.56 237	94.44 236	94.91 265	97.57 259	87.44 294	93.78 282	96.26 294	93.69 217	96.41 221	96.50 262	92.10 218	99.00 289	85.96 330	97.71 296	98.31 253

新几何1				97.25 158	98.29 169	94.70 137		97.73 245	77.98 361	94.83 274	96.67 252	92.08 219	99.45 202	88.17 312	98.65 258	97.61 300

testdata				95.70 238	98.16 189	90.58 240		97.72 246	80.38 353	95.62 257	97.02 228	92.06 220	98.98 293	89.06 300	98.52 265	97.54 302

YYNet1		94.73 224	94.84 211	94.41 288	97.47 270	85.09 326	90.29 346	95.85 304	92.52 249	97.53 152	97.76 163	91.97 221	99.18 265	93.31 216	96.86 321	98.95 177

Anonymous20231206		95.27 203	95.06 201	95.88 230	98.72 120	89.37 256	95.70 180	97.85 237	88.00 303	96.98 193	97.62 178	91.95 222	99.34 237	89.21 296	99.53 102	98.94 179

MS-PatchMatch		94.83 220	94.91 208	94.57 283	96.81 302	87.10 300	94.23 259	97.34 266	88.74 295	97.14 176	97.11 221	91.94 223	98.23 350	92.99 223	97.92 286	98.37 244

1121		94.26 246	93.26 263	97.27 155	98.26 175	94.73 132	95.86 173	97.71 247	77.96 362	94.53 281	96.71 249	91.93 224	99.40 219	87.71 314	98.64 259	97.69 297

MDA-MVSNet_test_wron		94.73 224	94.83 213	94.42 287	97.48 266	85.15 324	90.28 347	95.87 303	92.52 249	97.48 160	97.76 163	91.92 225	99.17 269	93.32 215	96.80 324	98.94 179

HQP_MVS		96.66 147	96.33 157	97.68 119	98.70 125	94.29 150	96.50 136	98.75 125	96.36 107	96.16 235	96.77 245	91.91 226	99.46 198	92.59 228	99.20 192	99.28 115

plane_prior6					98.38 163	94.37 148						91.91 226

ETH3 D test6400		94.77 223	93.87 254	97.47 138	98.12 196	93.73 173	94.56 248	98.70 139	85.45 328	94.70 277	95.93 293	91.77 228	99.63 144	86.45 328	99.14 200	99.05 166

MVP-Stereo		95.69 183	95.28 192	96.92 173	98.15 191	93.03 193	95.64 189	98.20 204	90.39 278	96.63 211	97.73 169	91.63 229	99.10 279	91.84 240	97.31 314	98.63 223
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchMatch-RL		94.61 235	93.81 255	97.02 170	98.19 182	95.72 85	93.66 284	97.23 268	88.17 301	94.94 272	95.62 300	91.43 230	98.57 330	87.36 323	97.68 299	96.76 329

MDA-MVSNet-bldmvs		95.69 183	95.67 182	95.74 235	98.48 154	88.76 269	92.84 303	97.25 267	96.00 127	97.59 150	97.95 144	91.38 231	99.46 198	93.16 221	96.35 332	98.99 174

PAPR		92.22 291	91.27 297	95.07 260	95.73 332	88.81 266	91.97 322	97.87 236	85.80 322	90.91 345	92.73 345	91.16 232	98.33 347	79.48 357	95.76 341	98.08 270

1314		92.38 288	92.30 284	92.64 323	95.42 339	85.15 324	95.86 173	96.97 280	85.40 329	90.62 346	93.06 339	91.12 233	97.80 357	86.74 326	95.49 344	94.97 353

ppachtmachnet_test		94.49 241	94.84 211	93.46 305	96.16 319	82.10 345	90.59 343	97.48 263	90.53 277	97.01 190	97.59 180	91.01 234	99.36 232	93.97 201	99.18 197	98.94 179

PLC	91.02 16	94.05 257	92.90 269	97.51 130	98.00 207	95.12 123	94.25 257	98.25 198	86.17 317	91.48 343	95.25 307	91.01 234	99.19 264	85.02 341	96.69 326	98.22 263
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test222					98.17 187	93.24 188	92.74 308	97.61 259	75.17 366	94.65 278	96.69 251	90.96 236			98.66 256	97.66 298

CL-MVSNet_self_test		95.04 212	94.79 216	95.82 232	97.51 265	89.79 249	91.14 337	96.82 285	93.05 238	96.72 206	96.40 267	90.82 237	99.16 270	91.95 235	98.66 256	98.50 234

USDC		94.56 237	94.57 230	94.55 284	97.78 240	86.43 309	92.75 306	98.65 154	85.96 319	96.91 198	97.93 147	90.82 237	98.74 314	90.71 269	99.59 82	98.47 236

PCF-MVS	89.43 18	92.12 294	90.64 308	96.57 196	97.80 230	93.48 183	89.88 353	98.45 171	74.46 367	96.04 239	95.68 297	90.71 239	99.31 244	73.73 366	99.01 221	96.91 320
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PAPM_NR		94.61 235	94.17 244	95.96 224	98.36 165	91.23 228	95.93 171	97.95 231	92.98 241	93.42 319	94.43 325	90.53 240	98.38 343	87.60 318	96.29 333	98.27 259

our_test_3		94.20 252	94.58 228	93.07 313	96.16 319	81.20 351	90.42 345	96.84 283	90.72 275	97.14 176	97.13 218	90.47 241	99.11 277	94.04 198	98.25 275	98.91 188

OpenMVS_ROB	91.80 14	93.64 267	93.05 266	95.42 249	97.31 284	91.21 229	95.08 223	96.68 291	81.56 347	96.88 200	96.41 265	90.44 242	99.25 258	85.39 337	97.67 300	95.80 344

HQP2-MVS												90.33 243

N_pmnet		95.18 206	94.23 240	98.06 90	97.85 218	96.55 60	92.49 312	91.63 346	89.34 287	98.09 114	97.41 195	90.33 243	99.06 283	91.58 245	99.31 178	98.56 229

HQP-MVS		95.17 208	94.58 228	96.92 173	97.85 218	92.47 203	94.26 254	98.43 174	93.18 232	92.86 327	95.08 309	90.33 243	99.23 261	90.51 277	98.74 249	99.05 166

CNLPA		95.04 212	94.47 233	96.75 184	97.81 226	95.25 114	94.12 268	97.89 235	94.41 194	94.57 279	95.69 296	90.30 246	98.35 346	86.72 327	98.76 247	96.64 332

PMMVS		92.39 287	91.08 299	96.30 211	93.12 365	92.81 198	90.58 344	95.96 301	79.17 358	91.85 342	92.27 349	90.29 247	98.66 324	89.85 288	96.68 327	97.43 305

TR-MVS		92.54 285	92.20 285	93.57 303	96.49 307	86.66 305	93.51 289	94.73 318	89.96 283	94.95 271	93.87 330	90.24 248	98.61 327	81.18 355	94.88 347	95.45 350

MVS_0304		95.50 190	95.05 202	96.84 179	96.28 312	93.12 191	97.00 115	96.16 295	95.03 174	89.22 357	97.70 172	90.16 249	99.48 192	94.51 175	99.34 167	97.93 286

TAMVS		95.49 191	94.94 204	97.16 160	98.31 167	93.41 184	95.07 224	96.82 285	91.09 272	97.51 154	97.82 160	89.96 250	99.42 208	88.42 308	99.44 134	98.64 221

DPM-MVS		93.68 265	92.77 276	96.42 204	97.91 213	92.54 201	91.17 336	97.47 264	84.99 334	93.08 324	94.74 317	89.90 251	99.00 289	87.54 320	98.09 281	97.72 295

PMMVS2		93.66 266	94.07 246	92.45 327	97.57 259	80.67 353	86.46 362	96.00 299	93.99 209	97.10 180	97.38 202	89.90 251	97.82 356	88.76 302	99.47 126	98.86 199

BH-w/o		92.14 293	91.94 287	92.73 322	97.13 291	85.30 320	92.46 313	95.64 306	89.33 288	94.21 288	92.74 344	89.60 253	98.24 349	81.68 353	94.66 349	94.66 354

Anonymous20240521		97.07 115	97.51 86	95.76 234	99.35 43	88.18 277	97.78 66	98.40 181	97.11 81	98.34 82	99.04 40	89.58 254	99.79 40	98.09 18	99.93 10	99.30 107

UnsupCasMVSNet_bld		94.72 228	94.26 239	96.08 220	98.62 135	90.54 243	93.38 294	98.05 229	90.30 279	97.02 189	96.80 244	89.54 255	99.16 270	88.44 307	96.18 334	98.56 229

MG-MVS		94.08 256	94.00 249	94.32 290	97.09 292	85.89 314	93.19 300	95.96 301	92.52 249	94.93 273	97.51 187	89.54 255	98.77 311	87.52 321	97.71 296	98.31 253

UnsupCasMVSNet_eth		95.91 177	95.73 181	96.44 202	98.48 154	91.52 226	95.31 207	98.45 171	95.76 142	97.48 160	97.54 183	89.53 257	98.69 319	94.43 177	94.61 350	99.13 146

GBi-Net		96.99 118	96.80 130	97.56 125	97.96 209	93.67 175	98.23 40	98.66 149	95.59 151	97.99 125	99.19 24	89.51 258	99.73 82	94.60 170	99.44 134	99.30 107

test1		96.99 118	96.80 130	97.56 125	97.96 209	93.67 175	98.23 40	98.66 149	95.59 151	97.99 125	99.19 24	89.51 258	99.73 82	94.60 170	99.44 134	99.30 107

FMVSNet2		96.72 141	96.67 137	96.87 177	97.96 209	91.88 219	97.15 105	98.06 228	95.59 151	98.50 64	98.62 68	89.51 258	99.65 139	94.99 157	99.60 80	99.07 162

pmmvs4		94.82 221	94.19 243	96.70 187	97.42 273	92.75 200	92.09 321	96.76 287	86.80 314	95.73 255	97.22 214	89.28 261	98.89 301	93.28 217	99.14 200	98.46 238

cascas		91.89 297	91.35 295	93.51 304	94.27 352	85.60 316	88.86 358	98.61 156	79.32 357	92.16 339	91.44 358	89.22 262	98.12 353	90.80 263	97.47 310	96.82 326

DSMNet-mixed		92.19 292	91.83 289	93.25 309	96.18 318	83.68 339	96.27 147	93.68 327	76.97 365	92.54 336	99.18 27	89.20 263	98.55 333	83.88 347	98.60 263	97.51 303

c3_l		95.20 205	95.32 191	94.83 272	96.19 317	86.43 309	91.83 324	98.35 190	93.47 221	97.36 167	97.26 212	88.69 264	99.28 253	95.41 131	99.36 159	98.78 207

CANet_DTU		94.65 233	94.21 242	95.96 224	95.90 325	89.68 250	93.92 276	97.83 241	93.19 231	90.12 352	95.64 299	88.52 265	99.57 168	93.27 218	99.47 126	98.62 224

EPP-MVSNet		96.84 129	96.58 141	97.65 120	99.18 70	93.78 172	98.68 12	96.34 293	97.91 46	97.30 168	98.06 130	88.46 266	99.85 23	93.85 204	99.40 152	99.32 101

SixPastTwentyTwo		97.49 93	97.57 82	97.26 157	99.56 17	92.33 205	98.28 37	96.97 280	98.30 34	99.45 14	99.35 16	88.43 267	99.89 16	98.01 20	99.76 42	99.54 38

miper_ehance_all_eth		94.69 229	94.70 218	94.64 277	95.77 330	86.22 311	91.32 333	98.24 199	91.67 262	97.05 186	96.65 253	88.39 268	99.22 263	94.88 158	98.34 271	98.49 235

IS-MVSNet		96.93 123	96.68 136	97.70 116	99.25 53	94.00 162	98.57 17	96.74 289	98.36 31	98.14 108	97.98 139	88.23 269	99.71 101	93.10 222	99.72 52	99.38 88

jason		94.39 244	94.04 248	95.41 251	98.29 169	87.85 286	92.74 308	96.75 288	85.38 330	95.29 263	96.15 279	88.21 270	99.65 139	94.24 187	99.34 167	98.74 212
jason: jason.
IterMVS-SCA-FT		95.86 180	96.19 161	94.85 270	97.68 251	85.53 317	92.42 314	97.63 257	96.99 83	98.36 79	98.54 74	87.94 271	99.75 66	97.07 57	99.08 212	99.27 119

SCA		93.38 273	93.52 259	92.96 318	96.24 313	81.40 350	93.24 298	94.00 324	91.58 265	94.57 279	96.97 231	87.94 271	99.42 208	89.47 293	97.66 301	98.06 276

sss		94.22 248	93.72 256	95.74 235	97.71 249	89.95 247	93.84 278	96.98 279	88.38 299	93.75 303	95.74 295	87.94 271	98.89 301	91.02 256	98.10 280	98.37 244

IterMVS		95.42 197	95.83 177	94.20 293	97.52 264	83.78 338	92.41 315	97.47 264	95.49 155	98.06 118	98.49 77	87.94 271	99.58 162	96.02 89	99.02 219	99.23 127
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		94.10 254	93.41 261	96.18 217	99.16 71	90.04 245	92.15 318	98.68 144	79.90 355	96.22 232	97.83 157	87.92 275	99.42 208	89.18 297	99.65 65	99.08 160

VDDNet		96.98 121	96.84 127	97.41 147	99.40 38	93.26 187	97.94 57	95.31 315	99.26 7	98.39 75	99.18 27	87.85 276	99.62 152	95.13 149	99.09 211	99.35 98

pmmvs5		94.63 234	94.34 238	95.50 245	97.63 257	88.34 274	94.02 270	97.13 273	87.15 310	95.22 265	97.15 217	87.50 277	99.27 255	93.99 199	99.26 186	98.88 196

D2MVS		95.18 206	95.17 195	95.21 255	97.76 242	87.76 289	94.15 264	97.94 232	89.77 285	96.99 191	97.68 175	87.45 278	99.14 272	95.03 155	99.81 33	98.74 212

PVSNet	86.72 19	91.10 305	90.97 302	91.49 334	97.56 261	78.04 359	87.17 361	94.60 320	84.65 336	92.34 337	92.20 350	87.37 279	98.47 337	85.17 340	97.69 298	97.96 284

Anonymous202405211		96.34 160	95.98 172	97.43 145	98.25 176	93.85 168	96.74 126	94.41 322	97.72 55	98.37 76	98.03 133	87.15 280	99.53 178	94.06 194	99.07 214	98.92 187

MVSFormer		96.14 168	96.36 155	95.49 246	97.68 251	87.81 287	98.67 13	99.02 52	96.50 101	94.48 284	96.15 279	86.90 281	99.92 4	98.73 7	99.13 204	98.74 212

lupinMVS		93.77 261	93.28 262	95.24 254	97.68 251	87.81 287	92.12 319	96.05 297	84.52 337	94.48 284	95.06 311	86.90 281	99.63 144	93.62 212	99.13 204	98.27 259

eth_miper_zixun_eth		94.89 218	94.93 206	94.75 275	95.99 324	86.12 312	91.35 330	98.49 168	93.40 222	97.12 178	97.25 213	86.87 283	99.35 235	95.08 152	98.82 242	98.78 207

WTY-MVS		93.55 269	93.00 268	95.19 256	97.81 226	87.86 284	93.89 277	96.00 299	89.02 290	94.07 293	95.44 305	86.27 284	99.33 240	87.69 316	96.82 322	98.39 242

CDS-MVSNet		94.88 219	94.12 245	97.14 162	97.64 256	93.57 180	93.96 275	97.06 277	90.05 282	96.30 228	96.55 257	86.10 285	99.47 195	90.10 284	99.31 178	98.40 240
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
1112_ss		94.12 253	93.42 260	96.23 213	98.59 140	90.85 234	94.24 258	98.85 94	85.49 325	92.97 325	94.94 313	86.01 286	99.64 142	91.78 241	97.92 286	98.20 265

miper_enhance_ethall		93.14 278	92.78 275	94.20 293	93.65 359	85.29 321	89.97 349	97.85 237	85.05 332	96.15 237	94.56 320	85.74 287	99.14 272	93.74 207	98.34 271	98.17 268

new_pmnet		92.34 289	91.69 292	94.32 290	96.23 315	89.16 260	92.27 317	92.88 335	84.39 340	95.29 263	96.35 271	85.66 288	96.74 366	84.53 344	97.56 304	97.05 314

alignmvs		96.01 174	95.52 188	97.50 133	97.77 241	94.71 134	96.07 159	96.84 283	97.48 68	96.78 205	94.28 328	85.50 289	99.40 219	96.22 79	98.73 252	98.40 240

lessismore_v0				97.05 167	99.36 42	92.12 213		84.07 370		98.77 47	98.98 43	85.36 290	99.74 76	97.34 45	99.37 156	99.30 107

HY-MVS	91.43 15	92.58 284	91.81 290	94.90 267	96.49 307	88.87 264	97.31 96	94.62 319	85.92 320	90.50 349	96.84 239	85.05 291	99.40 219	83.77 349	95.78 340	96.43 337

EPNet		93.72 263	92.62 280	97.03 169	87.61 377	92.25 207	96.27 147	91.28 349	96.74 91	87.65 363	97.39 200	85.00 292	99.64 142	92.14 232	99.48 124	99.20 132
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_lstm_enhance		94.81 222	94.80 215	94.85 270	96.16 319	86.45 308	91.14 337	98.20 204	93.49 220	97.03 188	97.37 204	84.97 293	99.26 256	95.28 135	99.56 90	98.83 201

Test_1112_low_res		93.53 270	92.86 270	95.54 244	98.60 138	88.86 265	92.75 306	98.69 142	82.66 344	92.65 332	96.92 236	84.75 294	99.56 169	90.94 258	97.76 292	98.19 266

MVS-HIRNet		88.40 328	90.20 313	82.99 353	97.01 294	60.04 377	93.11 301	85.61 369	84.45 339	88.72 359	99.09 36	84.72 295	98.23 350	82.52 352	96.59 329	90.69 368

K. test v3		96.44 157	96.28 158	96.95 171	99.41 37	91.53 225	97.65 75	90.31 358	98.89 19	98.93 38	99.36 14	84.57 296	99.92 4	97.81 26	99.56 90	99.39 86

h-mvs33		96.29 161	95.63 184	98.26 71	98.50 151	96.11 74	96.90 118	97.09 275	96.58 97	97.21 172	98.19 112	84.14 297	99.78 44	95.89 98	96.17 335	98.89 192

hse-mvs2		95.77 182	95.09 198	97.79 108	97.84 222	95.51 97	95.66 184	95.43 314	96.58 97	97.21 172	96.16 278	84.14 297	99.54 176	95.89 98	96.92 318	98.32 251

DIV-MVS_self_test		94.73 224	94.64 221	95.01 262	95.86 326	87.00 301	91.33 331	98.08 223	93.34 225	97.10 180	97.34 206	84.02 299	99.31 244	95.15 146	99.55 96	98.72 215

cl____		94.73 224	94.64 221	95.01 262	95.85 327	87.00 301	91.33 331	98.08 223	93.34 225	97.10 180	97.33 207	84.01 300	99.30 247	95.14 147	99.56 90	98.71 217

Vis-MVSNet (Re-imp)		95.11 209	94.85 210	95.87 231	99.12 83	89.17 259	97.54 87	94.92 317	96.50 101	96.58 212	97.27 211	83.64 301	99.48 192	88.42 308	99.67 62	98.97 175

PVSNet_0	81.89 21	84.49 337	83.21 340	88.34 349	95.76 331	74.97 371	83.49 365	92.70 339	78.47 360	87.94 362	86.90 369	83.38 302	96.63 367	73.44 367	66.86 373	93.40 360

CMPMVS	73.10 23	92.74 282	91.39 294	96.77 183	93.57 361	94.67 138	94.21 261	97.67 249	80.36 354	93.61 310	96.60 255	82.85 303	97.35 360	84.86 342	98.78 245	98.29 258
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		94.25 247	94.47 233	93.60 302	98.14 192	82.60 343	97.24 101	92.72 338	85.08 331	98.48 66	98.94 46	82.59 304	98.76 313	97.47 41	99.53 102	99.44 79

bset_n11_16_dypcd		94.53 239	93.95 252	96.25 212	97.56 261	89.85 248	88.52 359	91.32 348	94.90 180	97.51 154	96.38 269	82.34 305	99.78 44	97.22 47	99.80 36	99.12 151

baseline1		93.14 278	92.64 279	94.62 279	97.34 280	87.20 299	96.67 133	93.02 333	94.71 185	96.51 217	95.83 294	81.64 306	98.60 329	90.00 286	88.06 365	98.07 272

test1111		94.53 239	94.81 214	93.72 299	99.06 89	81.94 348	98.31 34	83.87 371	96.37 106	98.49 65	99.17 29	81.49 307	99.73 82	96.64 63	99.86 25	99.49 53

CVMVSNet		92.33 290	92.79 273	90.95 338	97.26 285	75.84 368	95.29 209	92.33 341	81.86 345	96.27 229	98.19 112	81.44 308	98.46 338	94.23 188	98.29 274	98.55 231

EPNet_dtu		91.39 303	90.75 306	93.31 307	90.48 374	82.61 342	94.80 239	92.88 335	93.39 223	81.74 371	94.90 316	81.36 309	99.11 277	88.28 310	98.87 235	98.21 264
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ECVR-MVS		94.37 245	94.48 232	94.05 296	98.95 99	83.10 340	98.31 34	82.48 372	96.20 114	98.23 97	99.16 30	81.18 310	99.66 137	95.95 94	99.83 31	99.38 88

test_yl		94.40 242	94.00 249	95.59 239	96.95 296	89.52 253	94.75 242	95.55 311	96.18 117	96.79 201	96.14 281	81.09 311	99.18 265	90.75 265	97.77 290	98.07 272

DCV-MVSNet		94.40 242	94.00 249	95.59 239	96.95 296	89.52 253	94.75 242	95.55 311	96.18 117	96.79 201	96.14 281	81.09 311	99.18 265	90.75 265	97.77 290	98.07 272

MIMVSNet		93.42 271	92.86 270	95.10 259	98.17 187	88.19 276	98.13 49	93.69 325	92.07 255	95.04 270	98.21 111	80.95 313	99.03 288	81.42 354	98.06 282	98.07 272

PAPM		87.64 334	85.84 339	93.04 314	96.54 305	84.99 327	88.42 360	95.57 310	79.52 356	83.82 368	93.05 340	80.57 314	98.41 340	62.29 372	92.79 356	95.71 345

HyFIR lowres test		93.72 263	92.65 278	96.91 175	98.93 102	91.81 222	91.23 335	98.52 165	82.69 343	96.46 219	96.52 261	80.38 315	99.90 13	90.36 281	98.79 244	99.03 168

FMVSNet3		95.26 204	94.94 204	96.22 215	96.53 306	90.06 244	95.99 165	97.66 251	94.11 206	97.99 125	97.91 149	80.22 316	99.63 144	94.60 170	99.44 134	98.96 176

RPMNet		94.68 231	94.60 225	94.90 267	95.44 337	88.15 278	96.18 154	98.86 90	97.43 69	94.10 291	98.49 77	79.40 317	99.76 59	95.69 106	95.81 337	96.81 327

test_part1		96.77 137	96.53 147	97.47 138	98.04 199	92.92 196	97.93 58	98.85 94	98.83 21	99.30 21	99.07 38	79.25 318	99.79 40	97.59 35	99.93 10	99.69 20

LFMVS		95.32 201	94.88 209	96.62 191	98.03 200	91.47 227	97.65 75	90.72 355	99.11 9	97.89 137	98.31 90	79.20 319	99.48 192	93.91 203	99.12 207	98.93 183

ADS-MVSNet2		91.47 302	90.51 310	94.36 289	95.51 335	85.63 315	95.05 227	95.70 305	83.46 341	92.69 330	96.84 239	79.15 320	99.41 217	85.66 334	90.52 360	98.04 280

ADS-MVSNet		90.95 308	90.26 312	93.04 314	95.51 335	82.37 344	95.05 227	93.41 330	83.46 341	92.69 330	96.84 239	79.15 320	98.70 318	85.66 334	90.52 360	98.04 280

MDTV_nov1_ep13_2view						57.28 378	94.89 234		80.59 352	94.02 295		78.66 322		85.50 336		97.82 291

cl22		93.25 276	92.84 272	94.46 286	94.30 351	86.00 313	91.09 339	96.64 292	90.74 274	95.79 250	96.31 272	78.24 323	98.77 311	94.15 191	98.34 271	98.62 224

PatchmatchNet		91.98 296	91.87 288	92.30 329	94.60 348	79.71 355	95.12 218	93.59 329	89.52 286	93.61 310	97.02 228	77.94 324	99.18 265	90.84 261	94.57 352	98.01 283
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												77.80 325				98.06 276

CR-MVSNet		93.29 275	92.79 273	94.78 274	95.44 337	88.15 278	96.18 154	97.20 269	84.94 335	94.10 291	98.57 70	77.67 326	99.39 224	95.17 142	95.81 337	96.81 327

Patchmtry		95.03 214	94.59 227	96.33 208	94.83 345	90.82 235	96.38 142	97.20 269	96.59 96	97.49 157	98.57 70	77.67 326	99.38 227	92.95 225	99.62 70	98.80 204

tpmrst		90.31 311	90.61 309	89.41 345	94.06 356	72.37 374	95.06 226	93.69 325	88.01 302	92.32 338	96.86 237	77.45 328	98.82 306	91.04 255	87.01 367	97.04 315

sam_mvs												77.38 329

patchmatchnet-post											96.84 239	77.36 330	99.42 208

Patchmatch-RL test		94.66 232	94.49 231	95.19 256	98.54 145	88.91 263	92.57 310	98.74 127	91.46 266	98.32 87	97.75 166	77.31 331	98.81 308	96.06 84	99.61 76	97.85 289

tpmvs		90.79 309	90.87 303	90.57 341	92.75 369	76.30 366	95.79 177	93.64 328	91.04 273	91.91 341	96.26 273	77.19 332	98.86 305	89.38 295	89.85 363	96.56 335

test_post											10.87 375	76.83 333	99.07 282

Patchmatch-test		93.60 268	93.25 264	94.63 278	96.14 322	87.47 293	96.04 161	94.50 321	93.57 218	96.47 218	96.97 231	76.50 334	98.61 327	90.67 271	98.41 270	97.81 293

MDTV_nov1_ep13			91.28 296		94.31 350	73.51 372	94.80 239	93.16 332	86.75 315	93.45 317	97.40 196	76.37 335	98.55 333	88.85 301	96.43 330

EMVS		89.06 323	89.22 318	88.61 348	93.00 366	77.34 363	82.91 367	90.92 352	94.64 187	92.63 334	91.81 354	76.30 336	97.02 361	83.83 348	96.90 320	91.48 366

test_post1							94.98 231				10.37 376	76.21 337	99.04 285	89.47 293

GA-MVS		92.83 281	92.15 286	94.87 269	96.97 295	87.27 298	90.03 348	96.12 296	91.83 261	94.05 294	94.57 319	76.01 338	98.97 297	92.46 230	97.34 313	98.36 249

PatchT		93.75 262	93.57 258	94.29 292	95.05 343	87.32 297	96.05 160	92.98 334	97.54 66	94.25 287	98.72 60	75.79 339	99.24 259	95.92 96	95.81 337	96.32 338

E-PMN		89.52 321	89.78 315	88.73 347	93.14 364	77.61 361	83.26 366	92.02 342	94.82 182	93.71 305	93.11 334	75.31 340	96.81 363	85.81 331	96.81 323	91.77 365

DeepMVS_CX				77.17 354	90.94 373	85.28 322		74.08 377	52.51 371	80.87 372	88.03 368	75.25 341	70.63 374	59.23 373	84.94 369	75.62 369

AUN-MVS		93.95 260	92.69 277	97.74 112	97.80 230	95.38 105	95.57 191	95.46 313	91.26 270	92.64 333	96.10 284	74.67 342	99.55 173	93.72 209	96.97 317	98.30 255

CHOSEN 280x420		89.98 315	89.19 321	92.37 328	95.60 334	81.13 352	86.22 363	97.09 275	81.44 349	87.44 364	93.15 333	73.99 343	99.47 195	88.69 304	99.07 214	96.52 336

thres200		91.00 307	90.42 311	92.77 321	97.47 270	83.98 337	94.01 271	91.18 351	95.12 170	95.44 260	91.21 360	73.93 344	99.31 244	77.76 363	97.63 303	95.01 352

test-LLR		89.97 316	89.90 314	90.16 342	94.24 353	74.98 369	89.89 350	89.06 361	92.02 256	89.97 353	90.77 363	73.92 345	98.57 330	91.88 238	97.36 311	96.92 318

test0.0.03 1		90.11 312	89.21 319	92.83 320	93.89 357	86.87 304	91.74 325	88.74 363	92.02 256	94.71 276	91.14 361	73.92 345	94.48 369	83.75 350	92.94 355	97.16 311

tpm cat1		88.01 331	87.33 332	90.05 344	94.48 349	76.28 367	94.47 251	94.35 323	73.84 369	89.26 356	95.61 301	73.64 347	98.30 348	84.13 345	86.20 368	95.57 349

tfpn200view9		91.55 301	91.00 300	93.21 311	98.02 201	84.35 334	95.70 180	90.79 353	96.26 111	95.90 248	92.13 351	73.62 348	99.42 208	78.85 360	97.74 293	95.85 342

thres400		91.68 300	91.00 300	93.71 300	98.02 201	84.35 334	95.70 180	90.79 353	96.26 111	95.90 248	92.13 351	73.62 348	99.42 208	78.85 360	97.74 293	97.36 307

test_method		66.88 339	66.13 342	69.11 355	62.68 378	25.73 380	49.76 369	96.04 298	14.32 373	64.27 374	91.69 356	73.45 350	88.05 372	76.06 365	66.94 372	93.54 358

thres100view900		91.76 299	91.26 298	93.26 308	98.21 180	84.50 332	96.39 140	90.39 356	96.87 87	96.33 224	93.08 338	73.44 351	99.42 208	78.85 360	97.74 293	95.85 342

thres600view7		92.03 295	91.43 293	93.82 297	98.19 182	84.61 331	96.27 147	90.39 356	96.81 89	96.37 223	93.11 334	73.44 351	99.49 189	80.32 356	97.95 285	97.36 307

RRT_MVS		94.90 217	94.07 246	97.39 149	93.18 362	93.21 189	95.26 211	97.49 261	93.94 211	98.25 94	97.85 155	72.96 353	99.84 26	97.90 22	99.78 41	99.14 143

MVSTER		94.21 250	93.93 253	95.05 261	95.83 328	86.46 307	95.18 217	97.65 253	92.41 253	97.94 132	98.00 138	72.39 354	99.58 162	96.36 76	99.56 90	99.12 151

JIA-IIPM		91.79 298	90.69 307	95.11 258	93.80 358	90.98 232	94.16 263	91.78 345	96.38 105	90.30 351	99.30 18	72.02 355	98.90 299	88.28 310	90.17 362	95.45 350

tpm		91.08 306	90.85 304	91.75 333	95.33 340	78.09 358	95.03 229	91.27 350	88.75 294	93.53 313	97.40 196	71.24 356	99.30 247	91.25 252	93.87 353	97.87 288

baseline2		89.65 320	88.44 327	93.25 309	95.62 333	82.71 341	93.82 279	85.94 368	88.89 293	87.35 365	92.54 347	71.23 357	99.33 240	86.01 329	94.60 351	97.72 295

CostFormer		89.75 319	89.25 317	91.26 337	94.69 347	78.00 360	95.32 206	91.98 343	81.50 348	90.55 348	96.96 233	71.06 358	98.89 301	88.59 306	92.63 357	96.87 321

FPMVS		89.92 317	88.63 325	93.82 297	98.37 164	96.94 47	91.58 326	93.34 331	88.00 303	90.32 350	97.10 222	70.87 359	91.13 371	71.91 369	96.16 336	93.39 361

EPMVS		89.26 322	88.55 326	91.39 335	92.36 370	79.11 356	95.65 187	79.86 373	88.60 296	93.12 323	96.53 259	70.73 360	98.10 354	90.75 265	89.32 364	96.98 316

tmp_tt		57.23 340	62.50 343	41.44 356	34.77 379	49.21 379	83.93 364	60.22 380	15.31 372	71.11 373	79.37 371	70.09 361	44.86 375	64.76 371	82.93 371	30.25 371

ET-MVSNet_ETH3D		91.12 304	89.67 316	95.47 247	96.41 309	89.15 261	91.54 327	90.23 359	89.07 289	86.78 367	92.84 342	69.39 362	99.44 205	94.16 190	96.61 328	97.82 291

dp		88.08 330	88.05 328	88.16 351	92.85 367	68.81 376	94.17 262	92.88 335	85.47 326	91.38 344	96.14 281	68.87 363	98.81 308	86.88 325	83.80 370	96.87 321

tpm2		88.47 327	87.69 331	90.79 339	94.98 344	77.34 363	95.09 221	91.83 344	77.51 364	89.40 355	96.41 265	67.83 364	98.73 315	83.58 351	92.60 358	96.29 339

pmmvs3		90.00 314	88.90 324	93.32 306	94.20 355	85.34 319	91.25 334	92.56 340	78.59 359	93.82 299	95.17 308	67.36 365	98.69 319	89.08 299	98.03 283	95.92 341

thisisatest0515		90.43 310	89.18 322	94.17 295	97.07 293	85.44 318	89.75 354	87.58 364	88.28 300	93.69 307	91.72 355	65.27 366	99.58 162	90.59 273	98.67 254	97.50 304

tttt0517		93.31 274	92.56 281	95.57 241	98.71 123	87.86 284	97.44 90	87.17 366	95.79 141	97.47 162	96.84 239	64.12 367	99.81 33	96.20 80	99.32 176	99.02 170

thisisatest0530		92.71 283	91.76 291	95.56 243	98.42 161	88.23 275	96.03 162	87.35 365	94.04 208	96.56 214	95.47 304	64.03 368	99.77 54	94.78 165	99.11 208	98.68 220

FMVSNet5		93.39 272	92.35 283	96.50 199	95.83 328	90.81 237	97.31 96	98.27 195	92.74 248	96.27 229	98.28 99	62.23 369	99.67 131	90.86 260	99.36 159	99.03 168

DWT-MVSNet_test		87.92 332	86.77 336	91.39 335	93.18 362	78.62 357	95.10 219	91.42 347	85.58 324	88.00 361	88.73 367	60.60 370	98.90 299	90.60 272	87.70 366	96.65 331

IB-MVS	85.98 20	88.63 326	86.95 335	93.68 301	95.12 342	84.82 330	90.85 341	90.17 360	87.55 306	88.48 360	91.34 359	58.01 371	99.59 160	87.24 324	93.80 354	96.63 334
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
RRT_test8_iter05		92.46 286	92.52 282	92.29 330	95.33 340	77.43 362	95.73 178	98.55 163	94.41 194	97.46 163	97.72 171	57.44 372	99.74 76	96.92 60	99.14 200	99.69 20

gg-mvs-nofinetune		88.28 329	86.96 334	92.23 331	92.84 368	84.44 333	98.19 46	74.60 375	99.08 10	87.01 366	99.47 8	56.93 373	98.23 350	78.91 359	95.61 342	94.01 357

KD-MVS_2432*1600		88.93 324	87.74 329	92.49 324	88.04 375	81.99 346	89.63 355	95.62 307	91.35 267	95.06 267	93.11 334	56.58 374	98.63 325	85.19 338	95.07 345	96.85 323

miper_refine_blended		88.93 324	87.74 329	92.49 324	88.04 375	81.99 346	89.63 355	95.62 307	91.35 267	95.06 267	93.11 334	56.58 374	98.63 325	85.19 338	95.07 345	96.85 323

GG-mvs-BLEND				90.60 340	91.00 372	84.21 336	98.23 40	72.63 378		82.76 369	84.11 370	56.14 376	96.79 364	72.20 368	92.09 359	90.78 367

TESTMET0.1,1		87.20 335	86.57 337	89.07 346	93.62 360	72.84 373	89.89 350	87.01 367	85.46 327	89.12 358	90.20 365	56.00 377	97.72 358	90.91 259	96.92 318	96.64 332

test2506		89.86 318	89.16 323	91.97 332	98.95 99	76.83 365	98.54 20	61.07 379	96.20 114	97.07 185	99.16 30	55.19 378	99.69 118	96.43 74	99.83 31	99.38 88

test-mter		87.92 332	87.17 333	90.16 342	94.24 353	74.98 369	89.89 350	89.06 361	86.44 316	89.97 353	90.77 363	54.96 379	98.57 330	91.88 238	97.36 311	96.92 318

test123		12.59 342	15.49 345	3.87 357	6.07 380	2.55 381	90.75 342	2.59 382	2.52 375	5.20 377	13.02 374	4.96 380	1.85 377	5.20 374	9.09 374	7.23 372

testmvs		12.33 343	15.23 346	3.64 358	5.77 381	2.23 382	88.99 357	3.62 381	2.30 376	5.29 376	13.09 373	4.52 381	1.95 376	5.16 375	8.32 375	6.75 373

test_blank		0.00 346	0.00 349	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

uanet_test		0.00 346	0.00 349	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

sosnet-low-res		0.00 346	0.00 349	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

sosnet		0.00 346	0.00 349	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

uncertanet		0.00 346	0.00 349	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

Regformer		0.00 346	0.00 349	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

ab-mvs-re		7.91 345	10.55 348	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	94.94 313	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

uanet		0.00 346	0.00 349	0.00 359	0.00 382	0.00 383	0.00 370	0.00 383	0.00 377	0.00 378	0.00 377	0.00 382	0.00 378	0.00 376	0.00 376	0.00 374

FOURS1					99.59 14	98.20 4	99.03 7	99.25 12	98.96 18	98.87 40

MSC_two_6792asdad				98.22 76	97.75 244	95.34 110		98.16 213					99.75 66	95.87 100	99.51 112	99.57 32

No_MVS				98.22 76	97.75 244	95.34 110		98.16 213					99.75 66	95.87 100	99.51 112	99.57 32

eth-test2					0.00 382

eth-test					0.00 382

IU-MVS					99.22 59	95.40 103		98.14 216	85.77 323	98.36 79				95.23 139	99.51 112	99.49 53

save fliter					98.48 154	94.71 134	94.53 249	98.41 179	95.02 175

test_0728_SECOND				98.25 74	99.23 56	95.49 101	96.74 126	98.89 79					99.75 66	95.48 121	99.52 107	99.53 41

GSMVS																98.06 276

test_part2					99.03 95	96.07 75				98.08 116

MTGPA								98.73 129

MTMP							96.55 134	74.60 375

gm-plane-assit					91.79 371	71.40 375			81.67 346		90.11 366		98.99 291	84.86 342

test9_res														91.29 249	98.89 234	99.00 171

agg_prior2														90.34 282	98.90 231	99.10 159

agg_prior					97.80 230	94.96 126		98.36 186		93.49 314			99.53 178

test_prior4						95.38 105	93.61 287

test_prior				97.46 141	97.79 236	94.26 154		98.42 177					99.34 237			98.79 205

旧先验2							93.35 295		77.95 363	95.77 254			98.67 323	90.74 268

新几何2							93.43 290

无先验							93.20 299	97.91 233	80.78 351				99.40 219	87.71 314		97.94 285

原ACMM2							92.82 304

testdata2													99.46 198	87.84 313

testdata1							92.77 305		93.78 214

plane_prior7					98.70 125	94.67 138

plane_prior5								98.75 125					99.46 198	92.59 228	99.20 192	99.28 115

plane_prior4											96.77 245

plane_prior3						94.51 142			95.29 163	96.16 235

plane_prior2							96.50 136		96.36 107

plane_prior1					98.49 152

plane_prior						94.29 150	95.42 196		94.31 199						98.93 229

n2								0.00 383

nn								0.00 383

door-mid								98.17 210

test11								98.08 223

door								97.81 242

HQP5-MVS						92.47 203

HQP-NCC					97.85 218		94.26 254		93.18 232	92.86 327

ACMP_Plane					97.85 218		94.26 254		93.18 232	92.86 327

BP-MVS														90.51 277

HQP4-MVS										92.87 326			99.23 261			99.06 164

HQP3-MVS								98.43 174							98.74 249

NP-MVS					98.14 192	93.72 174					95.08 309

ACMMP++_ref															99.52 107

ACMMP++															99.55 96

High-resolution multi-view benchmark