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		99.43 1	99.49 1	99.24 1	99.95 1	98.13 1	99.37 1	99.57 1	99.82 1	99.86 1	99.85 1	99.52 1	99.73 1	97.58 1	99.94 1	99.85 1

LTVRE_ROB	93.87 1	97.93 2	98.16 2	97.26 24	98.81 24	93.86 27	99.07 2	98.98 3	97.01 12	98.92 5	98.78 15	95.22 33	98.61 153	96.85 2	99.77 10	99.31 27
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
TDRefinement		97.68 3	97.60 5	97.93 2	99.02 11	95.95 5	98.61 3	98.81 4	97.41 9	97.28 43	98.46 26	94.62 50	98.84 115	94.64 17	99.53 34	98.99 52

test_normal		97.36 4	97.99 3	95.47 74	98.84 21	87.46 113	98.44 4	98.44 8	94.63 36	99.24 2	99.44 2	97.00 6	99.30 57	95.97 8	99.87 3	99.66 6

UA-Net		97.35 5	97.24 12	97.69 5	98.22 64	93.87 26	98.42 5	98.19 29	96.95 13	95.46 114	99.23 5	93.45 64	99.57 13	95.34 13	99.89 2	99.63 10

OurMVSNet-221017-0		96.80 13	96.75 19	96.96 33	99.03 10	91.85 53	97.98 6	98.01 53	94.15 45	98.93 4	99.07 6	88.07 165	99.57 13	95.86 10	99.69 15	99.46 18

UniMVSNet_ETH3D		97.13 7	97.72 4	95.35 77	99.51 2	87.38 116	97.70 7	97.54 93	98.16 2	98.94 3	99.33 3	97.84 4	99.08 78	90.73 107	99.73 14	99.59 13

HPM-MVS		96.81 12	96.62 23	97.36 22	98.89 18	93.53 34	97.51 8	98.44 8	92.35 75	95.95 96	96.41 121	96.71 9	99.42 26	93.99 30	99.36 55	99.13 39
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EPP-MVSNet		93.91 116	93.68 122	94.59 106	98.08 71	85.55 154	97.44 9	94.03 230	94.22 44	94.94 135	96.19 138	82.07 229	99.57 13	87.28 177	98.89 100	98.65 89

LS3D		96.11 46	95.83 56	96.95 34	94.75 230	94.20 14	97.34 10	97.98 56	97.31 10	95.32 118	96.77 99	93.08 76	99.20 68	91.79 89	98.16 170	97.44 170

HPM-MVS_fast		97.01 8	96.89 16	97.39 20	99.12 7	93.92 24	97.16 11	98.17 33	93.11 63	96.48 70	97.36 70	96.92 7	99.34 51	94.31 22	99.38 54	98.92 65

MVSFormer		92.18 165	92.23 155	92.04 194	94.74 231	80.06 217	97.15 12	97.37 102	88.98 152	88.83 260	92.79 248	77.02 262	99.60 8	96.41 4	96.75 228	96.46 206

test_djsdf		96.62 22	96.49 26	97.01 30	98.55 39	91.77 55	97.15 12	97.37 102	88.98 152	98.26 21	98.86 11	93.35 69	99.60 8	96.41 4	99.45 42	99.66 6

IS-MVSNet		94.49 99	94.35 103	94.92 91	98.25 63	86.46 135	97.13 14	94.31 225	96.24 23	96.28 81	96.36 129	82.88 220	99.35 49	88.19 158	99.52 36	98.96 58

Anonymous20231211		96.60 24	97.13 13	95.00 89	97.46 108	86.35 140	97.11 15	98.24 25	97.58 7	98.72 9	98.97 8	93.15 75	99.15 72	93.18 57	99.74 13	99.50 17

anonymousdsp		96.74 16	96.42 27	97.68 7	98.00 77	94.03 21	96.97 16	97.61 88	87.68 180	98.45 19	98.77 16	94.20 57	99.50 19	96.70 3	99.40 52	99.53 15

ACMMP		96.61 23	96.34 31	97.43 17	98.61 32	93.88 25	96.95 17	98.18 30	92.26 78	96.33 74	96.84 97	95.10 38	99.40 35	93.47 45	99.33 58	99.02 49
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
APDe-MVS		96.46 31	96.64 22	95.93 57	97.68 96	89.38 81	96.90 18	98.41 12	92.52 70	97.43 38	97.92 41	95.11 37	99.50 19	94.45 19	99.30 62	98.92 65

v7n		96.82 10	97.31 11	95.33 79	98.54 41	86.81 127	96.83 19	98.07 42	96.59 19	98.46 18	98.43 28	92.91 80	99.52 17	96.25 6	99.76 11	99.65 9

CP-MVS		96.44 34	96.08 44	97.54 9	98.29 59	94.62 10	96.80 20	98.08 39	92.67 68	95.08 131	96.39 126	94.77 47	99.42 26	93.17 58	99.44 44	98.58 98

COLMAP_ROB	91.06 5	96.75 15	96.62 23	97.13 26	98.38 54	94.31 12	96.79 21	98.32 15	96.69 16	96.86 56	97.56 55	95.48 23	98.77 132	90.11 125	99.44 44	98.31 112
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
WR-MVS_H		96.60 24	97.05 15	95.24 82	99.02 11	86.44 136	96.78 22	98.08 39	97.42 8	98.48 17	97.86 45	91.76 104	99.63 6	94.23 25	99.84 4	99.66 6

pmmvs6		96.80 13	97.36 10	95.15 86	99.12 7	87.82 111	96.68 23	97.86 67	96.10 25	98.14 23	99.28 4	97.94 3	98.21 189	91.38 102	99.69 15	99.42 19

3Dnovator	92.54 3	94.80 89	94.90 83	94.47 113	95.47 210	87.06 122	96.63 24	97.28 116	91.82 93	94.34 154	97.41 64	90.60 136	98.65 151	92.47 76	98.11 176	97.70 155

PS-CasMVS		96.69 19	97.43 6	94.49 112	99.13 5	84.09 170	96.61 25	97.97 59	97.91 5	98.64 14	98.13 32	95.24 32	99.65 3	93.39 51	99.84 4	99.72 2

abl_6		97.31 6	97.12 14	97.86 3	98.54 41	95.32 7	96.61 25	98.35 14	95.81 30	97.55 33	97.44 63	96.51 10	99.40 35	94.06 29	99.23 70	98.85 74

mvs_tets		96.83 9	96.71 20	97.17 25	98.83 22	92.51 44	96.58 27	97.61 88	87.57 182	98.80 8	98.90 10	96.50 11	99.59 12	96.15 7	99.47 38	99.40 21

PEN-MVS		96.69 19	97.39 9	94.61 101	99.16 3	84.50 162	96.54 28	98.05 45	98.06 4	98.64 14	98.25 31	95.01 43	99.65 3	92.95 66	99.83 6	99.68 4

DTE-MVSNet		96.74 16	97.43 6	94.67 99	99.13 5	84.68 161	96.51 29	97.94 65	98.14 3	98.67 13	98.32 29	95.04 40	99.69 2	93.27 54	99.82 8	99.62 11

XVS		96.49 28	96.18 37	97.44 15	98.56 36	93.99 22	96.50 30	97.95 62	94.58 37	94.38 151	96.49 115	94.56 51	99.39 40	93.57 39	99.05 86	98.93 61

X-MVStestdata		90.70 189	88.45 222	97.44 15	98.56 36	93.99 22	96.50 30	97.95 62	94.58 37	94.38 151	26.89 333	94.56 51	99.39 40	93.57 39	99.05 86	98.93 61

mPP-MVS		96.46 31	96.05 46	97.69 5	98.62 30	94.65 9	96.45 32	97.74 80	92.59 69	95.47 112	96.68 108	94.50 53	99.42 26	93.10 61	99.26 67	98.99 52

QAPM		92.88 144	92.77 142	93.22 154	95.82 192	83.31 178	96.45 32	97.35 109	83.91 224	93.75 163	96.77 99	89.25 154	98.88 106	84.56 212	97.02 221	97.49 168

jajsoiax		96.59 26	96.42 27	97.12 27	98.76 26	92.49 45	96.44 34	97.42 100	86.96 191	98.71 11	98.72 18	95.36 27	99.56 16	95.92 9	99.45 42	99.32 26

Gipuma		95.31 71	95.80 58	93.81 135	97.99 80	90.91 65	96.42 35	97.95 62	96.69 16	91.78 216	98.85 13	91.77 103	95.49 289	91.72 91	99.08 82	95.02 254
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MSP-MVS		95.34 68	94.63 95	97.48 12	98.67 27	94.05 18	96.41 36	98.18 30	91.26 109	95.12 127	95.15 179	86.60 194	99.50 19	93.43 50	96.81 225	98.89 67

TSAR-MVS + MP.		94.96 80	94.75 89	95.57 71	98.86 20	88.69 91	96.37 37	96.81 146	85.23 210	94.75 142	97.12 82	91.85 102	99.40 35	93.45 46	98.33 150	98.62 94
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
ACMH	88.36 12	96.59 26	97.43 6	94.07 124	98.56 36	85.33 156	96.33 38	98.30 18	94.66 35	98.72 9	98.30 30	97.51 5	98.00 203	94.87 14	99.59 26	98.86 71
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
region2R		96.41 35	96.09 43	97.38 21	98.62 30	93.81 31	96.32 39	97.96 60	92.26 78	95.28 121	96.57 113	95.02 42	99.41 31	93.63 38	99.11 81	98.94 60

APD-MVS_3200maxsize		96.82 10	96.65 21	97.32 23	97.95 81	93.82 29	96.31 40	98.25 22	95.51 31	96.99 54	97.05 86	95.63 19	99.39 40	93.31 53	98.88 102	98.75 83

CP-MVSNet		96.19 44	96.80 18	94.38 118	98.99 13	83.82 174	96.31 40	97.53 94	97.60 6	98.34 20	97.52 58	91.98 100	99.63 6	93.08 63	99.81 9	99.70 3

HFP-MVS		96.39 37	96.17 39	97.04 28	98.51 45	93.37 35	96.30 42	97.98 56	92.35 75	95.63 107	96.47 116	95.37 25	99.27 62	93.78 34	99.14 78	98.48 102

ACMMPR		96.46 31	96.14 40	97.41 19	98.60 33	93.82 29	96.30 42	97.96 60	92.35 75	95.57 110	96.61 111	94.93 46	99.41 31	93.78 34	99.15 77	99.00 50

3Dnovator+	92.74 2	95.86 52	95.77 59	96.13 49	96.81 132	90.79 68	96.30 42	97.82 73	96.13 24	94.74 143	97.23 76	91.33 113	99.16 71	93.25 55	98.30 155	98.46 104

MIMVSNet1		95.52 61	95.45 66	95.72 66	99.14 4	89.02 85	96.23 45	96.87 145	93.73 53	97.87 26	98.49 25	90.73 133	99.05 83	86.43 190	99.60 24	99.10 44

SR-MVS		96.70 18	96.42 27	97.54 9	98.05 72	94.69 8	96.13 46	98.07 42	95.17 32	96.82 58	96.73 105	95.09 39	99.43 25	92.99 65	98.71 121	98.50 101

MP-MVS		96.14 45	95.68 61	97.51 11	98.81 24	94.06 16	96.10 47	97.78 79	92.73 65	93.48 169	96.72 106	94.23 56	99.42 26	91.99 83	99.29 63	99.05 47
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
GBi-Net		93.21 134	92.96 137	93.97 127	95.40 212	84.29 163	95.99 48	96.56 158	88.63 159	95.10 128	98.53 22	81.31 236	98.98 93	86.74 181	98.38 143	98.65 89

test1		93.21 134	92.96 137	93.97 127	95.40 212	84.29 163	95.99 48	96.56 158	88.63 159	95.10 128	98.53 22	81.31 236	98.98 93	86.74 181	98.38 143	98.65 89

FMVSNet1		94.84 86	95.13 79	93.97 127	97.60 99	84.29 163	95.99 48	96.56 158	92.38 72	97.03 53	98.53 22	90.12 143	98.98 93	88.78 151	99.16 76	98.65 89

RPSCF		95.58 60	94.89 84	97.62 8	97.58 100	96.30 4	95.97 51	97.53 94	92.42 71	93.41 170	97.78 46	91.21 119	97.77 220	91.06 104	97.06 219	98.80 78

SixPastTwentyTwo		94.91 81	95.21 76	93.98 126	98.52 44	83.19 181	95.93 52	94.84 211	94.86 34	98.49 16	98.74 17	81.45 234	99.60 8	94.69 16	99.39 53	99.15 37

ambc				92.98 159	96.88 129	83.01 185	95.92 53	96.38 167		96.41 71	97.48 61	88.26 161	97.80 216	89.96 130	98.93 99	98.12 124

FC-MVSNet-test		95.32 69	95.88 53	93.62 138	98.49 50	81.77 194	95.90 54	98.32 15	93.93 50	97.53 34	97.56 55	88.48 158	99.40 35	92.91 67	99.83 6	99.68 4

MTAPA		96.65 21	96.38 30	97.47 13	98.95 15	94.05 18	95.88 55	97.62 85	94.46 41	96.29 78	96.94 88	93.56 62	99.37 46	94.29 23	99.42 46	98.99 52

CPTT-MVS		94.74 90	94.12 111	96.60 41	98.15 68	93.01 39	95.84 56	97.66 83	89.21 151	93.28 176	95.46 169	88.89 156	98.98 93	89.80 132	98.82 111	97.80 151

ab-mvs		92.40 159	92.62 148	91.74 200	97.02 123	81.65 196	95.84 56	95.50 199	86.95 192	92.95 189	97.56 55	90.70 134	97.50 233	79.63 258	97.43 210	96.06 222

nrg030		96.32 39	96.55 25	95.62 69	97.83 85	88.55 97	95.77 58	98.29 21	92.68 66	98.03 25	97.91 43	95.13 36	98.95 100	93.85 32	99.49 37	99.36 24

SteuartSystems-ACMMP		96.40 36	96.30 32	96.71 39	98.63 29	91.96 51	95.70 59	98.01 53	93.34 61	96.64 65	96.57 113	94.99 44	99.36 48	93.48 44	99.34 56	98.82 76
Skip Steuart: Steuart Systems R&D Blog.
OpenMVS	89.45 8	92.27 164	92.13 158	92.68 172	94.53 240	84.10 169	95.70 59	97.03 129	82.44 237	91.14 226	96.42 120	88.47 159	98.38 177	85.95 194	97.47 209	95.55 244

GST-MVS		96.24 42	95.99 49	97.00 31	98.65 28	92.71 43	95.69 61	98.01 53	92.08 83	95.74 103	96.28 133	95.22 33	99.42 26	93.17 58	99.06 83	98.88 69

ACMH+	88.43 11	96.48 29	96.82 17	95.47 74	98.54 41	89.06 84	95.65 62	98.61 6	96.10 25	98.16 22	97.52 58	96.90 8	98.62 152	90.30 119	99.60 24	98.72 87

canonicalmvs		94.59 95	94.69 91	94.30 119	95.60 207	87.03 124	95.59 63	98.24 25	91.56 103	95.21 126	92.04 263	94.95 45	98.66 149	91.45 100	97.57 206	97.20 183

PS-MVSNAJss		96.01 49	96.04 47	95.89 60	98.82 23	88.51 99	95.57 64	97.88 66	88.72 158	98.81 7	98.86 11	90.77 129	99.60 8	95.43 12	99.53 34	99.57 14

PMVS	87.21 14	94.97 79	95.33 71	93.91 131	98.97 14	97.16 2	95.54 65	95.85 186	96.47 20	93.40 172	97.46 62	95.31 29	95.47 290	86.18 193	98.78 116	89.11 317
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
VDDNet		94.03 114	94.27 108	93.31 150	98.87 19	82.36 189	95.51 66	91.78 268	97.19 11	96.32 75	98.60 19	84.24 212	98.75 133	87.09 178	98.83 110	98.81 77

pm-mvs1		95.43 64	95.94 50	93.93 130	98.38 54	85.08 158	95.46 67	97.12 126	91.84 91	97.28 43	98.46 26	95.30 30	97.71 225	90.17 123	99.42 46	98.99 52

Vis-MVSNet		95.50 62	95.48 65	95.56 72	98.11 69	89.40 80	95.35 68	98.22 27	92.36 74	94.11 155	98.07 33	92.02 96	99.44 23	93.38 52	97.67 202	97.85 146
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test0726					98.51 45	86.69 130	95.34 69	98.18 30	91.85 89	97.63 31	97.37 67	95.58 20

FIs		94.90 82	95.35 69	93.55 141	98.28 60	81.76 195	95.33 70	98.14 36	93.05 64	97.07 48	97.18 79	87.65 172	99.29 58	91.72 91	99.69 15	99.61 12

PGM-MVS		96.32 39	95.94 50	97.43 17	98.59 35	93.84 28	95.33 70	98.30 18	91.40 106	95.76 101	96.87 94	95.26 31	99.45 22	92.77 68	99.21 72	99.00 50

LPG-MVS_test		96.38 38	96.23 35	96.84 37	98.36 57	92.13 48	95.33 70	98.25 22	91.78 94	97.07 48	97.22 77	96.38 12	99.28 60	92.07 81	99.59 26	99.11 41

AllTest		94.88 84	94.51 98	96.00 52	98.02 75	92.17 46	95.26 73	98.43 10	90.48 127	95.04 132	96.74 103	92.54 88	97.86 211	85.11 204	98.98 93	97.98 132

DVP-MVS		95.82 53	96.18 37	94.72 98	98.51 45	86.69 130	95.20 74	97.00 131	91.85 89	97.40 41	97.35 71	95.58 20	99.34 51	93.44 48	99.31 60	98.13 123

test_0728_SECOND				94.88 92	98.55 39	86.72 129	95.20 74	98.22 27					99.38 45	93.44 48	99.31 60	98.53 100

Anonymous20240529		95.50 62	95.83 56	94.50 110	97.33 113	85.93 148	95.19 76	96.77 150	96.64 18	97.61 32	98.05 34	93.23 72	98.79 124	88.60 154	99.04 89	98.78 80

#test#		95.89 50	95.51 64	97.04 28	98.51 45	93.37 35	95.14 77	97.98 56	89.34 147	95.63 107	96.47 116	95.37 25	99.27 62	91.99 83	99.14 78	98.48 102

SMA-MVS		95.77 54	95.54 63	96.47 47	98.27 61	91.19 61	95.09 78	97.79 78	86.48 194	97.42 40	97.51 60	94.47 55	99.29 58	93.55 41	99.29 63	98.93 61

NR-MVSNet		95.28 72	95.28 74	95.26 81	97.75 88	87.21 120	95.08 79	97.37 102	93.92 51	97.65 30	95.90 148	90.10 146	99.33 56	90.11 125	99.66 20	99.26 29

TransMVSNet (Re)		95.27 74	96.04 47	92.97 160	98.37 56	81.92 193	95.07 80	96.76 151	93.97 49	97.77 27	98.57 20	95.72 17	97.90 206	88.89 149	99.23 70	99.08 45

UGNet		93.08 137	92.50 151	94.79 96	93.87 255	87.99 107	95.07 80	94.26 227	90.64 124	87.33 284	97.67 51	86.89 189	98.49 167	88.10 161	98.71 121	97.91 139
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
tttt0517		89.81 210	88.90 217	92.55 179	97.00 124	79.73 228	95.03 82	83.65 320	89.88 139	95.30 119	94.79 198	53.64 331	99.39 40	91.99 83	98.79 115	98.54 99

LFMVS		91.33 181	91.16 182	91.82 197	96.27 162	79.36 233	95.01 83	85.61 308	96.04 28	94.82 140	97.06 85	72.03 279	98.46 173	84.96 207	98.70 123	97.65 159

CSCG		94.69 92	94.75 89	94.52 109	97.55 102	87.87 109	95.01 83	97.57 91	92.68 66	96.20 86	93.44 235	91.92 101	98.78 128	89.11 147	99.24 69	96.92 190

GG-mvs-BLEND				83.24 307	85.06 332	71.03 304	94.99 85	65.55 335		74.09 331	75.51 330	44.57 338	94.46 303	59.57 328	87.54 317	84.24 324

EU-MVSNet		87.39 251	86.71 253	89.44 251	93.40 260	76.11 272	94.93 86	90.00 276	57.17 329	95.71 105	97.37 67	64.77 304	97.68 227	92.67 73	94.37 275	94.52 265

MTMP							94.82 87	54.62 337

PHI-MVS		94.34 104	93.80 116	95.95 54	95.65 203	91.67 57	94.82 87	97.86 67	87.86 175	93.04 186	94.16 217	91.58 107	98.78 128	90.27 120	98.96 97	97.41 171

testtj		94.81 88	94.42 99	96.01 51	97.23 115	90.51 69	94.77 89	97.85 70	91.29 108	94.92 137	95.66 160	91.71 105	99.40 35	88.07 162	98.25 160	98.11 125

gg-mvs-nofinetune		82.10 289	81.02 292	85.34 294	87.46 323	71.04 303	94.74 90	67.56 334	96.44 21	79.43 326	98.99 7	45.24 337	96.15 279	67.18 320	92.17 301	88.85 318

ACMM	88.83 9	96.30 41	96.07 45	96.97 32	98.39 53	92.95 41	94.74 90	98.03 50	90.82 119	97.15 46	96.85 95	96.25 14	99.00 92	93.10 61	99.33 58	98.95 59
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SD-MVS		95.19 75	95.73 60	93.55 141	96.62 140	88.88 90	94.67 92	98.05 45	91.26 109	97.25 45	96.40 122	95.42 24	94.36 306	92.72 72	99.19 73	97.40 174
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
API-MVS		91.52 176	91.61 169	91.26 215	94.16 246	86.26 143	94.66 93	94.82 212	91.17 112	92.13 211	91.08 276	90.03 149	97.06 252	79.09 265	97.35 213	90.45 315

v10		94.68 93	95.27 75	92.90 165	96.57 142	80.15 213	94.65 94	97.57 91	90.68 123	97.43 38	98.00 37	88.18 162	99.15 72	94.84 15	99.55 33	99.41 20

v8		94.65 94	95.29 73	92.74 170	96.65 137	79.77 227	94.59 95	97.17 122	91.86 88	97.47 37	97.93 40	88.16 163	99.08 78	94.32 21	99.47 38	99.38 22

APD-MVS		95.00 78	94.69 91	95.93 57	97.38 110	90.88 66	94.59 95	97.81 74	89.22 150	95.46 114	96.17 140	93.42 67	99.34 51	89.30 139	98.87 105	97.56 166
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
VPA-MVSNet		95.14 76	95.67 62	93.58 140	97.76 87	83.15 182	94.58 97	97.58 90	93.39 60	97.05 52	98.04 35	93.25 71	98.51 166	89.75 133	99.59 26	99.08 45

ACMMP_NAP		96.21 43	96.12 42	96.49 46	98.90 17	91.42 58	94.57 98	98.03 50	90.42 130	96.37 73	97.35 71	95.68 18	99.25 64	94.44 20	99.34 56	98.80 78

HQP_MVS		94.26 108	93.93 113	95.23 83	97.71 92	88.12 104	94.56 99	97.81 74	91.74 98	93.31 173	95.59 161	86.93 186	98.95 100	89.26 143	98.51 136	98.60 96

plane_prior2							94.56 99		91.74 98

tfpnnormal		94.27 107	94.87 85	92.48 181	97.71 92	80.88 208	94.55 101	95.41 201	93.70 54	96.67 64	97.72 49	91.40 111	98.18 193	87.45 173	99.18 75	98.36 108

XVG-ACMP-BASELINE		95.68 57	95.34 70	96.69 40	98.40 52	93.04 38	94.54 102	98.05 45	90.45 129	96.31 76	96.76 101	92.91 80	98.72 138	91.19 103	99.42 46	98.32 110

DP-MVS		95.62 58	95.84 55	94.97 90	97.16 118	88.62 94	94.54 102	97.64 84	96.94 14	96.58 68	97.32 74	93.07 77	98.72 138	90.45 112	98.84 107	97.57 164

MIMVSNet		87.13 259	86.54 256	88.89 261	96.05 177	76.11 272	94.39 104	88.51 281	81.37 242	88.27 273	96.75 102	72.38 277	95.52 287	65.71 323	95.47 252	95.03 253

K. test v3		93.37 126	93.27 134	93.66 137	98.05 72	82.62 187	94.35 105	86.62 297	96.05 27	97.51 35	98.85 13	76.59 266	99.65 3	93.21 56	98.20 168	98.73 86

Vis-MVSNet (Re-imp)		90.42 193	90.16 196	91.20 219	97.66 98	77.32 263	94.33 106	87.66 291	91.20 111	92.99 187	95.13 181	75.40 269	98.28 183	77.86 270	99.19 73	97.99 131

ANet_high		94.83 87	96.28 33	90.47 232	96.65 137	73.16 293	94.33 106	98.74 5	96.39 22	98.09 24	98.93 9	93.37 68	98.70 145	90.38 115	99.68 18	99.53 15

ACMP	88.15 13	95.71 56	95.43 68	96.54 43	98.17 67	91.73 56	94.24 108	98.08 39	89.46 145	96.61 67	96.47 116	95.85 16	99.12 76	90.45 112	99.56 32	98.77 82
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MAR-MVS		90.32 199	88.87 218	94.66 100	94.82 226	91.85 53	94.22 109	94.75 215	80.91 243	87.52 282	88.07 305	86.63 193	97.87 210	76.67 281	96.21 239	94.25 271
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
FMVSNet2		92.78 147	92.73 146	92.95 162	95.40 212	81.98 192	94.18 110	95.53 198	88.63 159	96.05 93	97.37 67	81.31 236	98.81 122	87.38 176	98.67 125	98.06 126

9.14			94.81 86		97.49 105		94.11 111	98.37 13	87.56 183	95.38 116	96.03 144	94.66 49	99.08 78	90.70 108	98.97 96

HPM-MVS++		95.02 77	94.39 100	96.91 35	97.88 83	93.58 33	94.09 112	96.99 133	91.05 114	92.40 201	95.22 178	91.03 126	99.25 64	92.11 78	98.69 124	97.90 140

HY-MVS	82.50 18	86.81 263	85.93 263	89.47 250	93.63 258	77.93 254	94.02 113	91.58 270	75.68 280	83.64 306	93.64 229	77.40 259	97.42 239	71.70 306	92.07 302	93.05 294

Effi-MVS+-dtu		93.90 117	92.60 149	97.77 4	94.74 231	96.67 3	94.00 114	95.41 201	89.94 136	91.93 215	92.13 261	90.12 143	98.97 97	87.68 169	97.48 208	97.67 158

Effi-MVS+		92.79 146	92.74 144	92.94 163	95.10 220	83.30 179	94.00 114	97.53 94	91.36 107	89.35 256	90.65 285	94.01 59	98.66 149	87.40 175	95.30 257	96.88 193

VDD-MVS		94.37 101	94.37 102	94.40 117	97.49 105	86.07 146	93.97 116	93.28 241	94.49 40	96.24 82	97.78 46	87.99 168	98.79 124	88.92 148	99.14 78	98.34 109

EPNet		89.80 211	88.25 226	94.45 115	83.91 334	86.18 144	93.87 117	87.07 295	91.16 113	80.64 323	94.72 200	78.83 247	98.89 105	85.17 199	98.89 100	98.28 114
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepC-MVS	91.39 4	95.43 64	95.33 71	95.71 67	97.67 97	90.17 70	93.86 118	98.02 52	87.35 184	96.22 84	97.99 38	94.48 54	99.05 83	92.73 71	99.68 18	97.93 136
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LCM-MVSNet-Re		94.20 111	94.58 96	93.04 156	95.91 188	83.13 183	93.79 119	99.19 2	92.00 84	98.84 6	98.04 35	93.64 61	99.02 89	81.28 241	98.54 132	96.96 189

TranMVSNet+NR-MVSNet		96.07 48	96.26 34	95.50 73	98.26 62	87.69 112	93.75 120	97.86 67	95.96 29	97.48 36	97.14 81	95.33 28	99.44 23	90.79 106	99.76 11	99.38 22

PAPM_NR		91.03 184	90.81 188	91.68 203	96.73 135	81.10 205	93.72 121	96.35 168	88.19 169	88.77 266	92.12 262	85.09 208	97.25 246	82.40 231	93.90 281	96.68 198

zzz-MVS		96.47 30	96.14 40	97.47 13	98.95 15	94.05 18	93.69 122	97.62 85	94.46 41	96.29 78	96.94 88	93.56 62	99.37 46	94.29 23	99.42 46	98.99 52

baseline		94.26 108	94.80 87	92.64 173	96.08 175	80.99 206	93.69 122	98.04 49	90.80 120	94.89 138	96.32 130	93.19 73	98.48 171	91.68 94	98.51 136	98.43 106

MVS_0304		90.96 185	90.15 198	93.37 147	93.17 264	87.06 122	93.62 124	92.43 259	89.60 144	82.25 314	95.50 168	82.56 226	97.83 214	84.41 214	97.83 194	95.22 248

CS-MVS		92.54 157	92.31 154	93.23 153	95.89 190	84.07 171	93.58 125	98.48 7	88.60 162	90.41 237	86.23 316	92.00 97	99.35 49	87.54 171	98.06 180	96.26 214

F-COLMAP		92.28 163	91.06 183	95.95 54	97.52 103	91.90 52	93.53 126	97.18 121	83.98 223	88.70 268	94.04 220	88.41 160	98.55 163	80.17 252	95.99 241	97.39 175

FMVSNet5		87.82 241	86.56 255	91.62 204	92.31 278	79.81 226	93.49 127	94.81 214	83.26 226	91.36 220	96.93 90	52.77 333	97.49 235	76.07 285	98.03 184	97.55 167

DPE-MVS		95.89 50	95.88 53	95.92 59	97.93 82	89.83 75	93.46 128	98.30 18	92.37 73	97.75 28	96.95 87	95.14 35	99.51 18	91.74 90	99.28 66	98.41 107

alignmvs		93.26 131	92.85 140	94.50 110	95.70 199	87.45 114	93.45 129	95.76 188	91.58 102	95.25 123	92.42 257	81.96 231	98.72 138	91.61 95	97.87 192	97.33 179

114514_t		90.51 191	89.80 201	92.63 175	98.00 77	82.24 190	93.40 130	97.29 114	65.84 320	89.40 255	94.80 197	86.99 184	98.75 133	83.88 217	98.61 128	96.89 192

DeepC-MVS_fast	89.96 7	93.73 119	93.44 129	94.60 105	96.14 172	87.90 108	93.36 131	97.14 123	85.53 209	93.90 161	95.45 170	91.30 115	98.59 157	89.51 136	98.62 127	97.31 180
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS-pluss		96.08 47	95.92 52	96.57 42	99.06 9	91.21 60	93.25 132	98.32 15	87.89 174	96.86 56	97.38 66	95.55 22	99.39 40	95.47 11	99.47 38	99.11 41
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
test_0402		95.73 55	96.22 36	94.26 120	98.19 66	85.77 151	93.24 133	97.24 118	96.88 15	97.69 29	97.77 48	94.12 58	99.13 75	91.54 99	99.29 63	97.88 142

MSLP-MVS++		93.25 133	93.88 114	91.37 211	96.34 156	82.81 186	93.11 134	97.74 80	89.37 146	94.08 157	95.29 177	90.40 141	96.35 277	90.35 117	98.25 160	94.96 255

baseline1		87.62 246	87.31 240	88.54 267	94.71 235	74.27 287	93.10 135	88.20 285	86.20 198	92.18 210	93.04 243	73.21 275	95.52 287	79.32 262	85.82 319	95.83 232

plane_prior						88.12 104	93.01 136		88.98 152						98.06 180

thres100view900		87.35 252	86.89 249	88.72 264	96.14 172	73.09 294	93.00 137	85.31 311	92.13 82	93.26 178	90.96 278	63.42 310	98.28 183	71.27 309	96.54 232	94.79 258

Patchmtry		90.11 203	89.92 200	90.66 229	90.35 303	77.00 267	92.96 138	92.81 248	90.25 133	94.74 143	96.93 90	67.11 289	97.52 232	85.17 199	98.98 93	97.46 169

LF4IMVS		92.72 149	92.02 160	94.84 94	95.65 203	91.99 50	92.92 139	96.60 157	85.08 215	92.44 199	93.62 230	86.80 190	96.35 277	86.81 180	98.25 160	96.18 218

UniMVSNet (Re)		95.32 69	95.15 78	95.80 62	97.79 86	88.91 87	92.91 140	98.07 42	93.46 59	96.31 76	95.97 147	90.14 142	99.34 51	92.11 78	99.64 22	99.16 36

TAPA-MVS	88.58 10	92.49 158	91.75 168	94.73 97	96.50 145	89.69 76	92.91 140	97.68 82	78.02 270	92.79 192	94.10 218	90.85 127	97.96 205	84.76 210	98.16 170	96.54 199
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
testing_2		94.03 114	94.38 101	93.00 158	96.79 134	81.41 201	92.87 142	96.96 134	85.88 205	97.06 51	97.92 41	91.18 123	98.71 144	91.72 91	99.04 89	98.87 70

thisisatest0530		88.69 230	87.52 238	92.20 186	96.33 157	79.36 233	92.81 143	84.01 319	86.44 195	93.67 166	92.68 252	53.62 332	99.25 64	89.65 135	98.45 139	98.00 130

ETV-MVS		92.35 161	92.03 159	93.30 151	95.81 194	83.97 172	92.80 144	98.17 33	87.71 178	89.79 250	87.56 306	91.17 124	99.18 70	87.97 164	97.27 214	96.77 196

thres600view7		87.66 244	87.10 247	89.36 254	96.05 177	73.17 292	92.72 145	85.31 311	91.89 87	93.29 175	90.97 277	63.42 310	98.39 175	73.23 297	96.99 222	96.51 201

wuyk23d		87.83 240	90.79 189	78.96 315	90.46 302	88.63 93	92.72 145	90.67 274	91.65 101	98.68 12	97.64 52	96.06 15	77.53 333	59.84 327	99.41 51	70.73 330

V42		93.43 125	93.58 125	92.97 160	95.34 216	81.22 203	92.67 147	96.49 163	87.25 186	96.20 86	96.37 128	87.32 178	98.85 114	92.39 77	98.21 166	98.85 74

OPM-MVS		95.61 59	95.45 66	96.08 50	98.49 50	91.00 63	92.65 148	97.33 110	90.05 135	96.77 61	96.85 95	95.04 40	98.56 161	92.77 68	99.06 83	98.70 88

DU-MVS		95.28 72	95.12 80	95.75 65	97.75 88	88.59 95	92.58 149	97.81 74	93.99 47	96.80 59	95.90 148	90.10 146	99.41 31	91.60 96	99.58 30	99.26 29

FMVSNet3		90.78 188	90.32 195	92.16 190	93.03 269	79.92 222	92.54 150	94.95 208	86.17 200	95.10 128	96.01 145	69.97 283	98.75 133	86.74 181	98.38 143	97.82 149

MVS_Test		92.57 156	93.29 131	90.40 234	93.53 259	75.85 275	92.52 151	96.96 134	88.73 157	92.35 204	96.70 107	90.77 129	98.37 180	92.53 75	95.49 251	96.99 188

CR-MVSNet		87.89 238	87.12 246	90.22 239	91.01 294	78.93 241	92.52 151	92.81 248	73.08 294	89.10 257	96.93 90	67.11 289	97.64 228	88.80 150	92.70 297	94.08 272

RPMNet		89.30 217	89.00 213	90.22 239	91.01 294	78.93 241	92.52 151	87.85 290	91.91 86	89.10 257	96.89 93	68.84 284	97.64 228	90.17 123	92.70 297	94.08 272

XVG-OURS-SEG-HR		95.38 66	95.00 82	96.51 44	98.10 70	94.07 15	92.46 154	98.13 38	90.69 122	93.75 163	96.25 136	98.03 2	97.02 253	92.08 80	95.55 249	98.45 105

EI-MVSNet-Vis-set		94.36 102	94.28 106	94.61 101	92.55 276	85.98 147	92.44 155	94.69 218	93.70 54	96.12 91	95.81 154	91.24 117	98.86 112	93.76 37	98.22 165	98.98 57

Anonymous202405211		92.58 154	92.50 151	92.83 168	96.55 143	83.22 180	92.43 156	91.64 269	94.10 46	95.59 109	96.64 109	81.88 233	97.50 233	85.12 203	98.52 134	97.77 152

EI-MVSNet-UG-set		94.35 103	94.27 108	94.59 106	92.46 277	85.87 149	92.42 157	94.69 218	93.67 58	96.13 90	95.84 153	91.20 120	98.86 112	93.78 34	98.23 163	99.03 48

Regformer-3		94.28 106	94.23 110	94.46 114	92.78 274	86.28 142	92.39 158	94.70 217	93.69 57	95.97 94	95.56 166	91.34 112	98.48 171	93.45 46	98.14 172	98.62 94

Regformer-4		94.90 82	94.67 93	95.59 70	92.78 274	89.02 85	92.39 158	95.91 183	94.50 39	96.41 71	95.56 166	92.10 95	99.01 91	94.23 25	98.14 172	98.74 84

NCCC		94.08 113	93.54 127	95.70 68	96.49 146	89.90 74	92.39 158	96.91 141	90.64 124	92.33 207	94.60 203	90.58 137	98.96 98	90.21 122	97.70 200	98.23 116

casdiffmvs		94.32 105	94.80 87	92.85 167	96.05 177	81.44 200	92.35 161	98.05 45	91.53 104	95.75 102	96.80 98	93.35 69	98.49 167	91.01 105	98.32 152	98.64 93

EIA-MVS		92.99 141	92.74 144	93.72 136	95.86 191	86.30 141	92.33 162	97.84 71	91.70 100	92.81 191	86.17 317	92.22 92	99.19 69	88.03 163	97.73 196	95.66 240

EI-MVSNet		92.99 141	93.26 135	92.19 187	92.12 283	79.21 238	92.32 163	94.67 220	91.77 96	95.24 124	95.85 150	87.14 182	98.49 167	91.99 83	98.26 158	98.86 71

CVMVSNet		85.16 270	84.72 268	86.48 286	92.12 283	70.19 307	92.32 163	88.17 287	56.15 330	90.64 233	95.85 150	67.97 287	96.69 264	88.78 151	90.52 310	92.56 300

OMC-MVS		94.22 110	93.69 121	95.81 61	97.25 114	91.27 59	92.27 165	97.40 101	87.10 190	94.56 147	95.42 172	93.74 60	98.11 197	86.62 185	98.85 106	98.06 126

PM-MVS		93.33 127	92.67 147	95.33 79	96.58 141	94.06 16	92.26 166	92.18 261	85.92 204	96.22 84	96.61 111	85.64 206	95.99 282	90.35 117	98.23 163	95.93 227

UniMVSNet_NR-MVSNet		95.35 67	95.21 76	95.76 64	97.69 95	88.59 95	92.26 166	97.84 71	94.91 33	96.80 59	95.78 157	90.42 138	99.41 31	91.60 96	99.58 30	99.29 28

AdaColmap		91.63 173	91.36 177	92.47 182	95.56 208	86.36 139	92.24 168	96.27 170	88.88 156	89.90 246	92.69 251	91.65 106	98.32 181	77.38 277	97.64 203	92.72 299

mvs-test1		93.07 139	91.80 166	96.89 36	94.74 231	95.83 6	92.17 169	95.41 201	89.94 136	89.85 247	90.59 286	90.12 143	98.88 106	87.68 169	95.66 247	95.97 225

PVSNet_Blended_VisFu		91.63 173	91.20 180	92.94 163	97.73 91	83.95 173	92.14 170	97.46 98	78.85 266	92.35 204	94.98 189	84.16 213	99.08 78	86.36 191	96.77 227	95.79 234

Baseline_NR-MVSNet		94.47 100	95.09 81	92.60 177	98.50 49	80.82 209	92.08 171	96.68 154	93.82 52	96.29 78	98.56 21	90.10 146	97.75 223	90.10 127	99.66 20	99.24 31

Fast-Effi-MVS+-dtu		92.77 148	92.16 156	94.58 108	94.66 237	88.25 102	92.05 172	96.65 155	89.62 143	90.08 241	91.23 273	92.56 87	98.60 155	86.30 192	96.27 238	96.90 191

save fliter					97.46 108	88.05 106	92.04 173	97.08 127	87.63 181

PatchT		87.51 248	88.17 230	85.55 291	90.64 297	66.91 316	92.02 174	86.09 301	92.20 80	89.05 259	97.16 80	64.15 306	96.37 276	89.21 146	92.98 295	93.37 291

EG-PatchMatch MVS		94.54 98	94.67 93	94.14 122	97.87 84	86.50 132	92.00 175	96.74 152	88.16 170	96.93 55	97.61 53	93.04 78	97.90 206	91.60 96	98.12 175	98.03 128

v144192		93.20 136	93.54 127	92.16 190	96.05 177	78.26 251	91.95 176	97.14 123	84.98 217	95.96 95	96.11 141	87.08 183	99.04 86	93.79 33	98.84 107	99.17 35

VNet		92.67 151	92.96 137	91.79 198	96.27 162	80.15 213	91.95 176	94.98 207	92.19 81	94.52 149	96.07 142	87.43 176	97.39 242	84.83 208	98.38 143	97.83 147

1314		86.46 264	86.33 260	86.87 285	91.65 288	74.54 282	91.94 178	94.10 229	74.28 286	84.78 298	87.33 310	83.03 219	95.00 299	78.72 266	91.16 308	91.06 312

1121		90.26 200	89.23 207	93.34 148	97.15 120	87.40 115	91.94 178	94.39 223	67.88 315	91.02 227	94.91 192	86.91 188	98.59 157	81.17 244	97.71 199	94.02 277

MVS		84.98 272	84.30 271	87.01 283	91.03 293	77.69 259	91.94 178	94.16 228	59.36 328	84.23 302	87.50 308	85.66 204	96.80 261	71.79 304	93.05 294	86.54 322

tfpn200view9		87.05 260	86.52 257	88.67 265	95.77 195	72.94 295	91.89 181	86.00 303	90.84 117	92.61 195	89.80 290	63.93 307	98.28 183	71.27 309	96.54 232	94.79 258

thres400		87.20 256	86.52 257	89.24 258	95.77 195	72.94 295	91.89 181	86.00 303	90.84 117	92.61 195	89.80 290	63.93 307	98.28 183	71.27 309	96.54 232	96.51 201

v1921920		93.26 131	93.61 124	92.19 187	96.04 181	78.31 250	91.88 183	97.24 118	85.17 211	96.19 88	96.19 138	86.76 191	99.05 83	94.18 27	98.84 107	99.22 32

Regformer-1		94.55 97	94.33 104	95.19 84	92.83 272	88.54 98	91.87 184	95.84 187	93.99 47	95.95 96	95.04 186	92.00 97	98.79 124	93.14 60	98.31 153	98.23 116

Regformer-2		94.86 85	94.55 97	95.77 63	92.83 272	89.98 72	91.87 184	96.40 165	94.38 43	96.19 88	95.04 186	92.47 91	99.04 86	93.49 43	98.31 153	98.28 114

XXY-MVS		92.58 154	93.16 136	90.84 228	97.75 88	79.84 223	91.87 184	96.22 175	85.94 203	95.53 111	97.68 50	92.69 85	94.48 302	83.21 222	97.51 207	98.21 118

IterMVS-LS		93.78 118	94.28 106	92.27 184	96.27 162	79.21 238	91.87 184	96.78 148	91.77 96	96.57 69	97.07 84	87.15 181	98.74 136	91.99 83	99.03 92	98.86 71
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1144		93.50 122	93.81 115	92.57 178	96.28 161	79.61 230	91.86 188	96.96 134	86.95 192	95.91 99	96.32 130	87.65 172	98.96 98	93.51 42	98.88 102	99.13 39

v1192		93.49 123	93.78 117	92.62 176	96.16 171	79.62 229	91.83 189	97.22 120	86.07 201	96.10 92	96.38 127	87.22 179	99.02 89	94.14 28	98.88 102	99.22 32

v1240		93.29 128	93.71 120	92.06 193	96.01 182	77.89 256	91.81 190	97.37 102	85.12 213	96.69 63	96.40 122	86.67 192	99.07 82	94.51 18	98.76 118	99.22 32

CNVR-MVS		94.58 96	94.29 105	95.46 76	96.94 126	89.35 82	91.81 190	96.80 147	89.66 142	93.90 161	95.44 171	92.80 84	98.72 138	92.74 70	98.52 134	98.32 110

v2v482		93.29 128	93.63 123	92.29 183	96.35 155	78.82 244	91.77 192	96.28 169	88.45 164	95.70 106	96.26 135	86.02 201	98.90 103	93.02 64	98.81 113	99.14 38

EPNet_dtu		85.63 268	84.37 270	89.40 253	86.30 328	74.33 286	91.64 193	88.26 283	84.84 219	72.96 332	89.85 288	71.27 281	97.69 226	76.60 282	97.62 204	96.18 218
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PLC	85.34 15	90.40 194	88.92 215	94.85 93	96.53 144	90.02 71	91.58 194	96.48 164	80.16 249	86.14 290	92.18 259	85.73 203	98.25 187	76.87 280	94.61 272	96.30 212
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
VPNet		93.08 137	93.76 118	91.03 222	98.60 33	75.83 277	91.51 195	95.62 191	91.84 91	95.74 103	97.10 83	89.31 153	98.32 181	85.07 206	99.06 83	98.93 61

XVG-OURS		94.72 91	94.12 111	96.50 45	98.00 77	94.23 13	91.48 196	98.17 33	90.72 121	95.30 119	96.47 116	87.94 169	96.98 254	91.41 101	97.61 205	98.30 113

HQP-NCC					96.36 152		91.37 197		87.16 187	88.81 262

ACMP_Plane					96.36 152		91.37 197		87.16 187	88.81 262

HQP-MVS		92.09 166	91.49 174	93.88 132	96.36 152	84.89 159	91.37 197	97.31 111	87.16 187	88.81 262	93.40 236	84.76 209	98.60 155	86.55 187	97.73 196	98.14 122

MCST-MVS		92.91 143	92.51 150	94.10 123	97.52 103	85.72 152	91.36 200	97.13 125	80.33 248	92.91 190	94.24 213	91.23 118	98.72 138	89.99 129	97.93 189	97.86 144

v148		92.87 145	93.29 131	91.62 204	96.25 165	77.72 258	91.28 201	95.05 205	89.69 141	95.93 98	96.04 143	87.34 177	98.38 177	90.05 128	97.99 186	98.78 80

tpmvs		84.22 276	83.97 274	84.94 297	87.09 325	65.18 322	91.21 202	88.35 282	82.87 233	85.21 293	90.96 278	65.24 302	96.75 262	79.60 261	85.25 320	92.90 296

CANet		92.38 160	91.99 161	93.52 145	93.82 257	83.46 177	91.14 203	97.00 131	89.81 140	86.47 288	94.04 220	87.90 170	99.21 67	89.50 137	98.27 157	97.90 140

CNLPA		91.72 171	91.20 180	93.26 152	96.17 170	91.02 62	91.14 203	95.55 197	90.16 134	90.87 228	93.56 233	86.31 197	94.40 305	79.92 257	97.12 218	94.37 268

DP-MVS Recon		92.31 162	91.88 163	93.60 139	97.18 117	86.87 126	91.10 205	97.37 102	84.92 218	92.08 212	94.08 219	88.59 157	98.20 190	83.50 219	98.14 172	95.73 236

OpenMVS_ROB	85.12 16	89.52 214	89.05 211	90.92 226	94.58 239	81.21 204	91.10 205	93.41 240	77.03 277	93.41 170	93.99 224	83.23 217	97.80 216	79.93 256	94.80 267	93.74 284

TSAR-MVS + GP.		93.07 139	92.41 153	95.06 88	95.82 192	90.87 67	90.97 207	92.61 255	88.04 171	94.61 146	93.79 228	88.08 164	97.81 215	89.41 138	98.39 142	96.50 204

MVP-Stereo		90.07 206	88.92 215	93.54 143	96.31 159	86.49 133	90.93 208	95.59 195	79.80 250	91.48 218	95.59 161	80.79 240	97.39 242	78.57 268	91.19 307	96.76 197
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MVSTER		89.32 216	88.75 219	91.03 222	90.10 305	76.62 269	90.85 209	94.67 220	82.27 238	95.24 124	95.79 155	61.09 319	98.49 167	90.49 111	98.26 158	97.97 135

pmmvs-eth3d		91.54 175	90.73 191	93.99 125	95.76 197	87.86 110	90.83 210	93.98 232	78.23 269	94.02 159	96.22 137	82.62 225	96.83 260	86.57 186	98.33 150	97.29 181

CANet_DTU		89.85 209	89.17 209	91.87 196	92.20 281	80.02 220	90.79 211	95.87 185	86.02 202	82.53 313	91.77 266	80.01 243	98.57 160	85.66 196	97.70 200	97.01 187

test_prior4						89.91 73	90.74 212

TinyColmap		92.00 168	92.76 143	89.71 248	95.62 206	77.02 266	90.72 213	96.17 177	87.70 179	95.26 122	96.29 132	92.54 88	96.45 271	81.77 236	98.77 117	95.66 240

CDPH-MVS		92.67 151	91.83 164	95.18 85	96.94 126	88.46 100	90.70 214	97.07 128	77.38 273	92.34 206	95.08 184	92.67 86	98.88 106	85.74 195	98.57 129	98.20 119

DSMNet-mixed		82.21 288	81.56 286	84.16 303	89.57 310	70.00 309	90.65 215	77.66 332	54.99 331	83.30 309	97.57 54	77.89 257	90.50 325	66.86 321	95.54 250	91.97 305

TEST9					96.45 148	89.46 77	90.60 216	96.92 139	79.09 262	90.49 234	94.39 209	91.31 114	98.88 106

train_agg		92.71 150	91.83 164	95.35 77	96.45 148	89.46 77	90.60 216	96.92 139	79.37 257	90.49 234	94.39 209	91.20 120	98.88 106	88.66 153	98.43 140	97.72 154

DI_MVS_plusplus_test		91.42 180	91.41 175	91.46 208	95.34 216	79.06 240	90.58 218	93.74 234	82.59 234	94.69 145	94.76 199	86.54 195	98.44 174	87.93 166	96.49 236	96.87 194

PatchmatchNet		85.22 269	84.64 269	86.98 284	89.51 311	69.83 310	90.52 219	87.34 293	78.87 265	87.22 285	92.74 250	66.91 291	96.53 267	81.77 236	86.88 318	94.58 264
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test_8					96.37 150	89.14 83	90.51 220	96.89 142	79.37 257	90.42 236	94.36 211	91.20 120	98.82 117

test_yl		90.11 203	89.73 204	91.26 215	94.09 249	79.82 224	90.44 221	92.65 253	90.90 115	93.19 181	93.30 238	73.90 272	98.03 199	82.23 232	96.87 223	95.93 227

DCV-MVSNet		90.11 203	89.73 204	91.26 215	94.09 249	79.82 224	90.44 221	92.65 253	90.90 115	93.19 181	93.30 238	73.90 272	98.03 199	82.23 232	96.87 223	95.93 227

tpm2		81.46 291	80.35 297	84.80 298	89.90 306	65.14 323	90.44 221	85.36 310	65.82 321	82.05 317	92.44 255	57.94 324	96.69 264	70.71 312	88.49 315	92.56 300

agg_prior1		92.60 153	91.76 167	95.10 87	96.20 167	88.89 88	90.37 224	96.88 143	79.67 254	90.21 238	94.41 207	91.30 115	98.78 128	88.46 155	98.37 148	97.64 160

CostFormer		83.09 281	82.21 283	85.73 290	89.27 313	67.01 315	90.35 225	86.47 298	70.42 306	83.52 308	93.23 241	61.18 318	96.85 259	77.21 278	88.26 316	93.34 292

TAMVS		90.16 202	89.05 211	93.49 146	96.49 146	86.37 138	90.34 226	92.55 256	80.84 246	92.99 187	94.57 205	81.94 232	98.20 190	73.51 295	98.21 166	95.90 230

EPMVS		81.17 295	80.37 296	83.58 305	85.58 330	65.08 324	90.31 227	71.34 333	77.31 275	85.80 292	91.30 272	59.38 322	92.70 318	79.99 253	82.34 327	92.96 295

CMPMVS	68.83 22	87.28 253	85.67 265	92.09 192	88.77 317	85.42 155	90.31 227	94.38 224	70.02 308	88.00 276	93.30 238	73.78 274	94.03 310	75.96 287	96.54 232	96.83 195
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_post1							90.21 229				5.85 337	65.36 300	96.00 281	79.61 259

test_prior3		93.29 128	92.85 140	94.61 101	95.95 185	87.23 118	90.21 229	97.36 107	89.33 148	90.77 229	94.81 194	90.41 139	98.68 147	88.21 156	98.55 130	97.93 136

test_prior2							90.21 229		89.33 148	90.77 229	94.81 194	90.41 139		88.21 156	98.55 130

MVS_111021_LR		93.66 120	93.28 133	94.80 95	96.25 165	90.95 64	90.21 229	95.43 200	87.91 172	93.74 165	94.40 208	92.88 82	96.38 275	90.39 114	98.28 156	97.07 184

WR-MVS		93.49 123	93.72 119	92.80 169	97.57 101	80.03 219	90.14 233	95.68 190	93.70 54	96.62 66	95.39 175	87.21 180	99.04 86	87.50 172	99.64 22	99.33 25

tpmrst		82.85 284	82.93 281	82.64 308	87.65 319	58.99 332	90.14 233	87.90 289	75.54 281	83.93 303	91.63 269	66.79 294	95.36 293	81.21 243	81.54 328	93.57 290

PVSNet_BlendedMVS		90.35 197	89.96 199	91.54 207	94.81 227	78.80 246	90.14 233	96.93 137	79.43 256	88.68 269	95.06 185	86.27 198	98.15 195	80.27 249	98.04 183	97.68 157

BH-untuned		90.68 190	90.90 184	90.05 245	95.98 183	79.57 231	90.04 236	94.94 209	87.91 172	94.07 158	93.00 244	87.76 171	97.78 219	79.19 264	95.17 260	92.80 297

新几何2							90.02 237

旧先验2							90.00 238		68.65 312	92.71 194			96.52 268	85.15 201

无先验							89.94 239	95.75 189	70.81 305				98.59 157	81.17 244		94.81 257

xiu_mvs_v1_base_debu		91.47 177	91.52 171	91.33 212	95.69 200	81.56 197	89.92 240	96.05 180	83.22 227	91.26 222	90.74 280	91.55 108	98.82 117	89.29 140	95.91 242	93.62 287

xiu_mvs_v1_base		91.47 177	91.52 171	91.33 212	95.69 200	81.56 197	89.92 240	96.05 180	83.22 227	91.26 222	90.74 280	91.55 108	98.82 117	89.29 140	95.91 242	93.62 287

xiu_mvs_v1_base_debi		91.47 177	91.52 171	91.33 212	95.69 200	81.56 197	89.92 240	96.05 180	83.22 227	91.26 222	90.74 280	91.55 108	98.82 117	89.29 140	95.91 242	93.62 287

DWT-MVSNet_test		80.74 297	79.18 302	85.43 293	87.51 322	66.87 317	89.87 243	86.01 302	74.20 288	80.86 322	80.62 327	48.84 335	96.68 266	81.54 238	83.14 326	92.75 298

mvs_anonymous		90.37 196	91.30 179	87.58 279	92.17 282	68.00 313	89.84 244	94.73 216	83.82 225	93.22 180	97.40 65	87.54 174	97.40 241	87.94 165	95.05 262	97.34 178

test20.03		90.80 187	90.85 187	90.63 230	95.63 205	79.24 236	89.81 245	92.87 247	89.90 138	94.39 150	96.40 122	85.77 202	95.27 297	73.86 294	99.05 86	97.39 175

1112_ss		88.42 233	87.41 239	91.45 209	96.69 136	80.99 206	89.72 246	96.72 153	73.37 292	87.00 286	90.69 283	77.38 260	98.20 190	81.38 240	93.72 284	95.15 250

UnsupCasMVSNet_eth		90.33 198	90.34 194	90.28 236	94.64 238	80.24 211	89.69 247	95.88 184	85.77 207	93.94 160	95.69 159	81.99 230	92.98 317	84.21 215	91.30 306	97.62 162

MG-MVS		89.54 213	89.80 201	88.76 263	94.88 223	72.47 299	89.60 248	92.44 258	85.82 206	89.48 254	95.98 146	82.85 221	97.74 224	81.87 235	95.27 258	96.08 221

Patchmatch-test		86.10 266	86.01 262	86.38 288	90.63 298	74.22 288	89.57 249	86.69 296	85.73 208	89.81 249	92.83 246	65.24 302	91.04 323	77.82 273	95.78 246	93.88 281

Anonymous20231206		88.77 228	88.29 225	90.20 242	96.31 159	78.81 245	89.56 250	93.49 239	74.26 287	92.38 202	95.58 164	82.21 227	95.43 292	72.07 303	98.75 120	96.34 210

DeepPCF-MVS	90.46 6	94.20 111	93.56 126	96.14 48	95.96 184	92.96 40	89.48 251	97.46 98	85.14 212	96.23 83	95.42 172	93.19 73	98.08 198	90.37 116	98.76 118	97.38 177

SCA		87.43 250	87.21 243	88.10 274	92.01 285	71.98 301	89.43 252	88.11 288	82.26 239	88.71 267	92.83 246	78.65 249	97.59 230	79.61 259	93.30 288	94.75 260

testgi		90.38 195	91.34 178	87.50 280	97.49 105	71.54 302	89.43 252	95.16 204	88.38 166	94.54 148	94.68 202	92.88 82	93.09 316	71.60 307	97.85 193	97.88 142

JIA-IIPM		85.08 271	83.04 279	91.19 220	87.56 320	86.14 145	89.40 254	84.44 318	88.98 152	82.20 315	97.95 39	56.82 327	96.15 279	76.55 283	83.45 324	91.30 310

原ACMM2							89.34 255

tpm		84.38 275	84.08 273	85.30 296	90.47 301	63.43 329	89.34 255	85.63 307	77.24 276	87.62 280	95.03 188	61.00 320	97.30 245	79.26 263	91.09 309	95.16 249

MVS_111021_HR		93.63 121	93.42 130	94.26 120	96.65 137	86.96 125	89.30 257	96.23 173	88.36 167	93.57 168	94.60 203	93.45 64	97.77 220	90.23 121	98.38 143	98.03 128

tpm cat1		80.61 299	79.46 301	84.07 304	88.78 316	65.06 325	89.26 258	88.23 284	62.27 326	81.90 319	89.66 296	62.70 315	95.29 296	71.72 305	80.60 329	91.86 308

CDS-MVSNet		89.55 212	88.22 229	93.53 144	95.37 215	86.49 133	89.26 258	93.59 236	79.76 252	91.15 225	92.31 258	77.12 261	98.38 177	77.51 275	97.92 190	95.71 237
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Fast-Effi-MVS+		91.28 182	90.86 186	92.53 180	95.45 211	82.53 188	89.25 260	96.52 162	85.00 216	89.91 245	88.55 302	92.94 79	98.84 115	84.72 211	95.44 253	96.22 216

BH-RMVSNet		90.47 192	90.44 193	90.56 231	95.21 219	78.65 248	89.15 261	93.94 233	88.21 168	92.74 193	94.22 214	86.38 196	97.88 208	78.67 267	95.39 255	95.14 251

thres200		85.85 267	85.18 267	87.88 277	94.44 241	72.52 298	89.08 262	86.21 299	88.57 163	91.44 219	88.40 303	64.22 305	98.00 203	68.35 317	95.88 245	93.12 293

PatchFormer-LS_test		82.62 285	81.71 285	85.32 295	87.92 318	67.31 314	89.03 263	88.20 285	77.58 272	83.79 304	80.50 328	60.96 321	96.42 272	83.86 218	83.59 323	92.23 303

USDC		89.02 221	89.08 210	88.84 262	95.07 221	74.50 284	88.97 264	96.39 166	73.21 293	93.27 177	96.28 133	82.16 228	96.39 274	77.55 274	98.80 114	95.62 243

testdata1							88.96 265		88.44 165

pmmvs5		87.87 239	87.14 245	90.07 244	93.26 263	76.97 268	88.89 266	92.18 261	73.71 291	88.36 271	93.89 226	76.86 265	96.73 263	80.32 248	96.81 225	96.51 201

test222					96.95 125	85.27 157	88.83 267	93.61 235	65.09 322	90.74 231	94.85 193	84.62 211			97.36 212	93.91 279

baseline2		83.38 279	81.54 288	88.90 260	91.38 290	72.84 297	88.78 268	81.22 326	78.97 263	79.82 325	87.56 306	61.73 317	97.80 216	74.30 292	90.05 312	96.05 223

diffmvs		91.74 170	91.93 162	91.15 221	93.06 267	78.17 252	88.77 269	97.51 97	86.28 197	92.42 200	93.96 225	88.04 166	97.46 236	90.69 109	96.67 230	97.82 149

MDTV_nov1_ep13			83.88 275		89.42 312	61.52 330	88.74 270	87.41 292	73.99 289	84.96 297	94.01 223	65.25 301	95.53 286	78.02 269	93.16 290

D2MVS		89.93 207	89.60 206	90.92 226	94.03 251	78.40 249	88.69 271	94.85 210	78.96 264	93.08 183	95.09 183	74.57 270	96.94 255	88.19 158	98.96 97	97.41 171

TR-MVS		87.70 242	87.17 244	89.27 256	94.11 248	79.26 235	88.69 271	91.86 267	81.94 240	90.69 232	89.79 292	82.82 222	97.42 239	72.65 301	91.98 303	91.14 311

PatchMatch-RL		89.18 218	88.02 233	92.64 173	95.90 189	92.87 42	88.67 273	91.06 272	80.34 247	90.03 243	91.67 268	83.34 215	94.42 304	76.35 284	94.84 266	90.64 314

PAPR		87.65 245	86.77 252	90.27 237	92.85 271	77.38 262	88.56 274	96.23 173	76.82 279	84.98 296	89.75 294	86.08 200	97.16 249	72.33 302	93.35 287	96.26 214

MDTV_nov1_ep13_2view						42.48 337	88.45 275		67.22 317	83.56 307		66.80 292		72.86 300		94.06 274

jason		89.17 219	88.32 224	91.70 202	95.73 198	80.07 216	88.10 276	93.22 242	71.98 298	90.09 240	92.79 248	78.53 252	98.56 161	87.43 174	97.06 219	96.46 206
jason: jason.
BH-w/o		87.21 255	87.02 248	87.79 278	94.77 229	77.27 264	87.90 277	93.21 244	81.74 241	89.99 244	88.39 304	83.47 214	96.93 257	71.29 308	92.43 299	89.15 316

MS-PatchMatch		88.05 237	87.75 234	88.95 259	93.28 261	77.93 254	87.88 278	92.49 257	75.42 282	92.57 197	93.59 232	80.44 242	94.24 309	81.28 241	92.75 296	94.69 263

DELS-MVS		92.05 167	92.16 156	91.72 201	94.44 241	80.13 215	87.62 279	97.25 117	87.34 185	92.22 209	93.18 242	89.54 152	98.73 137	89.67 134	98.20 168	96.30 212
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
ADS-MVSNet2		84.01 277	82.20 284	89.41 252	89.04 314	76.37 271	87.57 280	90.98 273	72.71 296	84.46 299	92.45 253	68.08 285	96.48 270	70.58 313	83.97 321	95.38 246

ADS-MVSNet		82.25 287	81.55 287	84.34 302	89.04 314	65.30 321	87.57 280	85.13 315	72.71 296	84.46 299	92.45 253	68.08 285	92.33 319	70.58 313	83.97 321	95.38 246

IterMVS-SCA-FT		91.65 172	91.55 170	91.94 195	93.89 254	79.22 237	87.56 282	93.51 238	91.53 104	95.37 117	96.62 110	78.65 249	98.90 103	91.89 88	94.95 263	97.70 155

IterMVS		90.18 201	90.16 196	90.21 241	93.15 265	75.98 274	87.56 282	92.97 246	86.43 196	94.09 156	96.40 122	78.32 253	97.43 238	87.87 167	94.69 270	97.23 182
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Test_1112_low_res		87.50 249	86.58 254	90.25 238	96.80 133	77.75 257	87.53 284	96.25 171	69.73 309	86.47 288	93.61 231	75.67 268	97.88 208	79.95 254	93.20 289	95.11 252

UnsupCasMVSNet_bld		88.50 232	88.03 232	89.90 246	95.52 209	78.88 243	87.39 285	94.02 231	79.32 260	93.06 184	94.02 222	80.72 241	94.27 307	75.16 290	93.08 293	96.54 199

lupinMVS		88.34 234	87.31 240	91.45 209	94.74 231	80.06 217	87.23 286	92.27 260	71.10 302	88.83 260	91.15 274	77.02 262	98.53 164	86.67 184	96.75 228	95.76 235

pmmvs4		88.95 224	87.70 236	92.70 171	94.30 244	85.60 153	87.22 287	92.16 263	74.62 285	89.75 252	94.19 215	77.97 256	96.41 273	82.71 226	96.36 237	96.09 220

WTY-MVS		86.93 262	86.50 259	88.24 272	94.96 222	74.64 280	87.19 288	92.07 266	78.29 268	88.32 272	91.59 270	78.06 255	94.27 307	74.88 291	93.15 291	95.80 233

ET-MVSNet_ETH3D		86.15 265	84.27 272	91.79 198	93.04 268	81.28 202	87.17 289	86.14 300	79.57 255	83.65 305	88.66 300	57.10 325	98.18 193	87.74 168	95.40 254	95.90 230

MVS-HIRNet		78.83 304	80.60 295	73.51 318	93.07 266	47.37 335	87.10 290	78.00 331	68.94 311	77.53 328	97.26 75	71.45 280	94.62 300	63.28 326	88.74 314	78.55 329

xiu_mvs_v2_base		89.00 222	89.19 208	88.46 270	94.86 225	74.63 281	86.97 291	95.60 192	80.88 244	87.83 278	88.62 301	91.04 125	98.81 122	82.51 230	94.38 274	91.93 306

DPM-MVS		89.35 215	88.40 223	92.18 189	96.13 174	84.20 167	86.96 292	96.15 178	75.40 283	87.36 283	91.55 271	83.30 216	98.01 202	82.17 234	96.62 231	94.32 270

dp		79.28 302	78.62 304	81.24 311	85.97 329	56.45 333	86.91 293	85.26 313	72.97 295	81.45 321	89.17 299	56.01 329	95.45 291	73.19 298	76.68 330	91.82 309

sss		87.23 254	86.82 250	88.46 270	93.96 252	77.94 253	86.84 294	92.78 251	77.59 271	87.61 281	91.83 265	78.75 248	91.92 320	77.84 271	94.20 279	95.52 245

CLD-MVS		91.82 169	91.41 175	93.04 156	96.37 150	83.65 176	86.82 295	97.29 114	84.65 221	92.27 208	89.67 295	92.20 93	97.85 213	83.95 216	99.47 38	97.62 162
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PS-MVSNAJ		88.86 226	88.99 214	88.48 269	94.88 223	74.71 279	86.69 296	95.60 192	80.88 244	87.83 278	87.37 309	90.77 129	98.82 117	82.52 229	94.37 275	91.93 306

PVSNet_Blended		88.74 229	88.16 231	90.46 233	94.81 227	78.80 246	86.64 297	96.93 137	74.67 284	88.68 269	89.18 298	86.27 198	98.15 195	80.27 249	96.00 240	94.44 267

MSDG		90.82 186	90.67 192	91.26 215	94.16 246	83.08 184	86.63 298	96.19 176	90.60 126	91.94 214	91.89 264	89.16 155	95.75 284	80.96 247	94.51 273	94.95 256

PCF-MVS	84.52 17	89.12 220	87.71 235	93.34 148	96.06 176	85.84 150	86.58 299	97.31 111	68.46 313	93.61 167	93.89 226	87.51 175	98.52 165	67.85 318	98.11 176	95.66 240
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Patchmatch-RL test		88.81 227	88.52 221	89.69 249	95.33 218	79.94 221	86.22 300	92.71 252	78.46 267	95.80 100	94.18 216	66.25 297	95.33 295	89.22 145	98.53 133	93.78 282

FPMVS		84.50 274	83.28 277	88.16 273	96.32 158	94.49 11	85.76 301	85.47 309	83.09 230	85.20 294	94.26 212	63.79 309	86.58 330	63.72 325	91.88 305	83.40 325

IB-MVS	77.21 19	83.11 280	81.05 291	89.29 255	91.15 292	75.85 275	85.66 302	86.00 303	79.70 253	82.02 318	86.61 312	48.26 336	98.39 175	77.84 271	92.22 300	93.63 286
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
MDA-MVSNet-bldmvs		91.04 183	90.88 185	91.55 206	94.68 236	80.16 212	85.49 303	92.14 264	90.41 131	94.93 136	95.79 155	85.10 207	96.93 257	85.15 201	94.19 280	97.57 164

new-patchmatchnet		88.97 223	90.79 189	83.50 306	94.28 245	55.83 334	85.34 304	93.56 237	86.18 199	95.47 112	95.73 158	83.10 218	96.51 269	85.40 198	98.06 180	98.16 120

HyFIR lowres test		87.19 257	85.51 266	92.24 185	97.12 122	80.51 210	85.03 305	96.06 179	66.11 319	91.66 217	92.98 245	70.12 282	99.14 74	75.29 289	95.23 259	97.07 184

pmmvs3		80.83 296	78.96 303	86.45 287	87.23 324	77.48 261	84.87 306	82.31 323	63.83 324	85.03 295	89.50 297	49.66 334	93.10 315	73.12 299	95.10 261	88.78 320

test0.0.03 1		82.48 286	81.47 289	85.48 292	89.70 307	73.57 291	84.73 307	81.64 325	83.07 231	88.13 275	86.61 312	62.86 313	89.10 329	66.24 322	90.29 311	93.77 283

N_pmnet		88.90 225	87.25 242	93.83 134	94.40 243	93.81 31	84.73 307	87.09 294	79.36 259	93.26 178	92.43 256	79.29 246	91.68 321	77.50 276	97.22 216	96.00 224

GA-MVS		87.70 242	86.82 250	90.31 235	93.27 262	77.22 265	84.72 309	92.79 250	85.11 214	89.82 248	90.07 287	66.80 292	97.76 222	84.56 212	94.27 278	95.96 226

ppachtmachnet_test		88.61 231	88.64 220	88.50 268	91.76 286	70.99 305	84.59 310	92.98 245	79.30 261	92.38 202	93.53 234	79.57 245	97.45 237	86.50 189	97.17 217	97.07 184

CHOSEN 1792x2688		87.19 257	85.92 264	91.00 225	97.13 121	79.41 232	84.51 311	95.60 192	64.14 323	90.07 242	94.81 194	78.26 254	97.14 250	73.34 296	95.38 256	96.46 206

thisisatest0515		84.72 273	82.99 280	89.90 246	92.96 270	75.33 278	84.36 312	83.42 321	77.37 274	88.27 273	86.65 311	53.94 330	98.72 138	82.56 228	97.40 211	95.67 239

cascas		87.02 261	86.28 261	89.25 257	91.56 289	76.45 270	84.33 313	96.78 148	71.01 303	86.89 287	85.91 318	81.35 235	96.94 255	83.09 223	95.60 248	94.35 269

new_pmnet		81.22 293	81.01 293	81.86 310	90.92 296	70.15 308	84.03 314	80.25 330	70.83 304	85.97 291	89.78 293	67.93 288	84.65 331	67.44 319	91.90 304	90.78 313

PAPM		81.91 290	80.11 299	87.31 282	93.87 255	72.32 300	84.02 315	93.22 242	69.47 310	76.13 330	89.84 289	72.15 278	97.23 247	53.27 331	89.02 313	92.37 302

our_test_3		87.55 247	87.59 237	87.44 281	91.76 286	70.48 306	83.83 316	90.55 275	79.79 251	92.06 213	92.17 260	78.63 251	95.63 285	84.77 209	94.73 268	96.22 216

miper_lstm_enhance		89.90 208	89.80 201	90.19 243	91.37 291	77.50 260	83.82 317	95.00 206	84.84 219	93.05 185	94.96 190	76.53 267	95.20 298	89.96 130	98.67 125	97.86 144

test-LLR		83.58 278	83.17 278	84.79 299	89.68 308	66.86 318	83.08 318	84.52 316	83.07 231	82.85 311	84.78 321	62.86 313	93.49 313	82.85 224	94.86 264	94.03 275

TESTMET0.1,1		79.09 303	78.04 305	82.25 309	87.52 321	64.03 328	83.08 318	80.62 328	70.28 307	80.16 324	83.22 324	44.13 339	90.56 324	79.95 254	93.36 286	92.15 304

test-mter		81.21 294	80.01 300	84.79 299	89.68 308	66.86 318	83.08 318	84.52 316	73.85 290	82.85 311	84.78 321	43.66 340	93.49 313	82.85 224	94.86 264	94.03 275

test123		9.49 309	12.01 311	1.91 321	2.87 338	1.30 339	82.38 321	1.34 341	1.36 334	2.84 336	6.56 335	2.45 341	0.97 337	2.73 334	5.56 334	3.47 333

PMMVS		83.00 282	81.11 290	88.66 266	83.81 335	86.44 136	82.24 322	85.65 306	61.75 327	82.07 316	85.64 319	79.75 244	91.59 322	75.99 286	93.09 292	87.94 321

YYNet1		88.17 235	88.24 227	87.93 275	92.21 280	73.62 290	80.75 323	88.77 279	82.51 236	94.99 134	95.11 182	82.70 223	93.70 311	83.33 220	93.83 282	96.48 205

MDA-MVSNet_test_wron		88.16 236	88.23 228	87.93 275	92.22 279	73.71 289	80.71 324	88.84 278	82.52 235	94.88 139	95.14 180	82.70 223	93.61 312	83.28 221	93.80 283	96.46 206

testmvs		9.02 310	11.42 312	1.81 322	2.77 339	1.13 340	79.44 325	1.90 340	1.18 335	2.65 337	6.80 334	1.95 342	0.87 338	2.62 335	3.45 335	3.44 334

PVSNet	76.22 20	82.89 283	82.37 282	84.48 301	93.96 252	64.38 327	78.60 326	88.61 280	71.50 300	84.43 301	86.36 315	74.27 271	94.60 301	69.87 315	93.69 285	94.46 266

PVSNet_0	70.34 21	74.58 305	72.96 307	79.47 314	90.63 298	66.24 320	73.26 327	83.40 322	63.67 325	78.02 327	78.35 329	72.53 276	89.59 327	56.68 329	60.05 333	82.57 328

E-PMN		80.72 298	80.86 294	80.29 313	85.11 331	68.77 312	72.96 328	81.97 324	87.76 177	83.25 310	83.01 325	62.22 316	89.17 328	77.15 279	94.31 277	82.93 326

CHOSEN 280x420		80.04 301	77.97 306	86.23 289	90.13 304	74.53 283	72.87 329	89.59 277	66.38 318	76.29 329	85.32 320	56.96 326	95.36 293	69.49 316	94.72 269	88.79 319

EMVS		80.35 300	80.28 298	80.54 312	84.73 333	69.07 311	72.54 330	80.73 327	87.80 176	81.66 320	81.73 326	62.89 312	89.84 326	75.79 288	94.65 271	82.71 327

PMMVS2		81.31 292	83.44 276	74.92 317	90.52 300	46.49 336	69.19 331	85.23 314	84.30 222	87.95 277	94.71 201	76.95 264	84.36 332	64.07 324	98.09 178	93.89 280

tmp_tt		37.97 307	44.33 309	18.88 320	11.80 337	21.54 338	63.51 332	45.66 339	4.23 333	51.34 335	50.48 332	59.08 323	22.11 336	44.50 332	68.35 332	13.00 332

MVE	59.87 23	73.86 306	72.65 308	77.47 316	87.00 327	74.35 285	61.37 333	60.93 336	67.27 316	69.69 333	86.49 314	81.24 239	72.33 334	56.45 330	83.45 324	85.74 323
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_part1				0.00 323		0.00 341	0.00 334	98.14 36				0.00 343	0.00 339	0.00 336	0.00 336	0.00 335

cdsmvs_eth3d_5k		23.35 308	31.13 310	0.00 323	0.00 340	0.00 341	0.00 334	95.58 196	0.00 336	0.00 338	91.15 274	93.43 66	0.00 339	0.00 336	0.00 336	0.00 335

pcd_1.5k_mvsjas		7.56 311	10.09 313	0.00 323	0.00 340	0.00 341	0.00 334	0.00 342	0.00 336	0.00 338	0.00 338	90.77 129	0.00 339	0.00 336	0.00 336	0.00 335

sosnet-low-res		0.00 313	0.00 315	0.00 323	0.00 340	0.00 341	0.00 334	0.00 342	0.00 336	0.00 338	0.00 338	0.00 343	0.00 339	0.00 336	0.00 336	0.00 335

sosnet		0.00 313	0.00 315	0.00 323	0.00 340	0.00 341	0.00 334	0.00 342	0.00 336	0.00 338	0.00 338	0.00 343	0.00 339	0.00 336	0.00 336	0.00 335

uncertanet		0.00 313	0.00 315	0.00 323	0.00 340	0.00 341	0.00 334	0.00 342	0.00 336	0.00 338	0.00 338	0.00 343	0.00 339	0.00 336	0.00 336	0.00 335

Regformer		0.00 313	0.00 315	0.00 323	0.00 340	0.00 341	0.00 334	0.00 342	0.00 336	0.00 338	0.00 338	0.00 343	0.00 339	0.00 336	0.00 336	0.00 335

ab-mvs-re		7.56 311	10.08 314	0.00 323	0.00 340	0.00 341	0.00 334	0.00 342	0.00 336	0.00 338	90.69 283	0.00 343	0.00 339	0.00 336	0.00 336	0.00 335

uanet		0.00 313	0.00 315	0.00 323	0.00 340	0.00 341	0.00 334	0.00 342	0.00 336	0.00 338	0.00 338	0.00 343	0.00 339	0.00 336	0.00 336	0.00 335

save filter2										94.36 153	95.85 150	90.82 128	98.88 106	90.51 110	99.04 89	97.64 160

test_0728_THIRD									93.26 62	97.40 41	97.35 71	94.69 48	99.34 51	93.88 31	99.42 46	98.89 67

GSMVS																94.75 260

test_part2					98.21 65	89.41 79				96.72 62

sam_mvs1												66.64 295				94.75 260

sam_mvs												66.41 296

MTGPA								97.62 85

test_post											6.07 336	65.74 299	95.84 283

patchmatchnet-post											91.71 267	66.22 298	97.59 230

gm-plane-assit					87.08 326	59.33 331			71.22 301		83.58 323		97.20 248	73.95 293

test9_res														88.16 160	98.40 141	97.83 147

agg_prior2														87.06 179	98.36 149	97.98 132

agg_prior					96.20 167	88.89 88		96.88 143		90.21 238			98.78 128

TestCases				96.00 52	98.02 75	92.17 46		98.43 10	90.48 127	95.04 132	96.74 103	92.54 88	97.86 211	85.11 204	98.98 93	97.98 132

test_prior				94.61 101	95.95 185	87.23 118		97.36 107					98.68 147			97.93 136

新几何1				93.17 155	97.16 118	87.29 117		94.43 222	67.95 314	91.29 221	94.94 191	86.97 185	98.23 188	81.06 246	97.75 195	93.98 278

旧先验1					96.20 167	84.17 168		94.82 212			95.57 165	89.57 151			97.89 191	96.32 211

原ACMM1				92.87 166	96.91 128	84.22 166		97.01 130	76.84 278	89.64 253	94.46 206	88.00 167	98.70 145	81.53 239	98.01 185	95.70 238

testdata2													98.03 199	80.24 251

segment_acmp												92.14 94

testdata				91.03 222	96.87 130	82.01 191		94.28 226	71.55 299	92.46 198	95.42 172	85.65 205	97.38 244	82.64 227	97.27 214	93.70 285

test12				94.43 116	95.95 185	86.75 128		96.24 172		89.76 251		89.79 150	98.79 124		97.95 188	97.75 153

plane_prior7					97.71 92	88.68 92

plane_prior6					97.21 116	88.23 103						86.93 186

plane_prior5								97.81 74					98.95 100	89.26 143	98.51 136	98.60 96

plane_prior4											95.59 161

plane_prior3						88.43 101			90.35 132	93.31 173

plane_prior1					97.38 110

n2								0.00 342

nn								0.00 342

door-mid								92.13 265

lessismore_v0				93.87 133	98.05 72	83.77 175		80.32 329		97.13 47	97.91 43	77.49 258	99.11 77	92.62 74	98.08 179	98.74 84

LGP-MVS_train				96.84 37	98.36 57	92.13 48		98.25 22	91.78 94	97.07 48	97.22 77	96.38 12	99.28 60	92.07 81	99.59 26	99.11 41

test11								96.65 155

door								91.26 271

HQP5-MVS						84.89 159

BP-MVS														86.55 187

HQP4-MVS										88.81 262			98.61 153			98.15 121

HQP3-MVS								97.31 111							97.73 196

HQP2-MVS												84.76 209

NP-MVS					96.82 131	87.10 121					93.40 236

ACMMP++_ref															98.82 111

ACMMP++															99.25 68

Test By Simon												90.61 135

ITE_SJBPF				95.95 54	97.34 112	93.36 37		96.55 161	91.93 85	94.82 140	95.39 175	91.99 99	97.08 251	85.53 197	97.96 187	97.41 171

DeepMVS_CX				53.83 319	70.38 336	64.56 326		48.52 338	33.01 332	65.50 334	74.21 331	56.19 328	46.64 335	38.45 333	70.07 331	50.30 331

High-resolution multi-view benchmark