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.

APDe-MVS		99.02 3	98.84 2	99.55 6	99.57 33	98.96 12	99.39 6	98.93 37	97.38 26	99.41 11	99.54 1	96.66 13	99.84 53	98.86 1	99.85 3	99.87 1

CANet		98.05 57	97.76 63	98.90 71	98.73 130	97.27 91	98.35 181	98.78 95	97.37 28	97.72 118	98.96 93	91.53 140	99.92 21	98.79 2	99.65 58	99.51 89

DROMVSNet		98.12 56	98.02 52	98.42 101	98.25 169	97.23 96	99.49 2	98.42 179	96.55 66	98.68 57	98.70 121	93.82 101	99.01 200	98.79 2	99.48 90	99.03 152

Regformer-4		98.64 14	98.53 11	98.99 63	99.43 57	97.37 87	98.40 176	98.79 92	97.46 21	99.09 30	99.31 35	95.86 42	99.80 80	98.64 4	99.76 32	99.79 10

VDD-MVS		95.82 160	95.23 171	97.61 160	98.84 124	93.98 234	98.68 133	97.40 297	95.02 137	97.95 103	99.34 31	74.37 348	99.78 96	98.64 4	96.80 185	99.08 149

EI-MVSNet-Vis-set		98.47 38	98.39 19	98.69 78	99.46 51	96.49 127	98.30 192	98.69 118	97.21 38	98.84 46	99.36 26	95.41 54	99.78 96	98.62 6	99.65 58	99.80 9

Regformer-3		98.59 20	98.50 14	98.86 73	99.43 57	97.05 102	98.40 176	98.68 121	97.43 22	99.06 31	99.31 35	95.80 43	99.77 101	98.62 6	99.76 32	99.78 13

CS-MVS		97.94 63	97.90 59	98.06 127	98.04 189	96.85 111	99.04 54	98.39 185	96.17 79	98.50 71	98.29 167	94.60 82	99.02 197	98.61 8	99.43 97	98.30 197

EI-MVSNet-UG-set		98.41 41	98.34 28	98.61 83	99.45 55	96.32 135	98.28 195	98.68 121	97.17 41	98.74 53	99.37 22	95.25 66	99.79 92	98.57 9	99.54 84	99.73 36

CHOSEN 280x420		97.18 108	97.18 91	97.20 177	98.81 126	93.27 261	95.78 336	99.15 18	95.25 124	96.79 158	98.11 182	92.29 117	99.07 189	98.56 10	99.85 3	99.25 127

xiu_mvs_v1_base_debu		97.60 80	97.56 71	97.72 149	98.35 158	95.98 145	97.86 244	98.51 161	97.13 44	99.01 35	98.40 152	91.56 136	99.80 80	98.53 11	98.68 129	97.37 224

xiu_mvs_v1_base		97.60 80	97.56 71	97.72 149	98.35 158	95.98 145	97.86 244	98.51 161	97.13 44	99.01 35	98.40 152	91.56 136	99.80 80	98.53 11	98.68 129	97.37 224

xiu_mvs_v1_base_debi		97.60 80	97.56 71	97.72 149	98.35 158	95.98 145	97.86 244	98.51 161	97.13 44	99.01 35	98.40 152	91.56 136	99.80 80	98.53 11	98.68 129	97.37 224

VNet		97.79 70	97.40 83	98.96 67	98.88 119	97.55 81	98.63 142	98.93 37	96.74 57	99.02 34	98.84 107	90.33 164	99.83 56	98.53 11	96.66 189	99.50 91

MSLP-MVS++		98.56 28	98.57 8	98.55 87	99.26 85	96.80 112	98.71 126	99.05 24	97.28 31	98.84 46	99.28 40	96.47 18	99.40 155	98.52 15	99.70 51	99.47 98

TSAR-MVS + GP.		98.38 43	98.24 41	98.81 74	99.22 94	97.25 95	98.11 220	98.29 207	97.19 40	98.99 38	99.02 80	96.22 20	99.67 122	98.52 15	98.56 137	99.51 89

DVP-MVS		99.03 2	98.83 3	99.63 3	99.72 12	99.25 2	98.97 70	98.58 147	97.62 11	99.45 9	99.46 9	97.42 6	99.94 3	98.47 17	99.81 10	99.69 51
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
test_0728_THIRD									97.32 29	99.45 9	99.46 9	97.88 1	99.94 3	98.47 17	99.86 1	99.85 2

test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 70	98.88 49					99.94 3	98.47 17	99.81 10	99.84 4

SED-MVS		99.09 1	98.91 1	99.63 3	99.71 20	99.24 4	99.02 60	98.87 55	97.65 9	99.73 1	99.48 6	97.53 4	99.94 3	98.43 20	99.81 10	99.70 48

test_241102_TWO								98.87 55	97.65 9	99.53 8	99.48 6	97.34 8	99.94 3	98.43 20	99.80 17	99.83 5

Regformer-1		98.66 12	98.51 13	99.12 57	99.35 60	97.81 74	98.37 178	98.76 99	97.49 17	99.20 22	99.21 48	96.08 29	99.79 92	98.42 22	99.73 43	99.75 28

DELS-MVS		98.40 42	98.20 44	98.99 63	99.00 110	97.66 76	97.75 253	98.89 46	97.71 8	98.33 82	98.97 87	94.97 74	99.88 43	98.42 22	99.76 32	99.42 108
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
Regformer-2		98.69 11	98.52 12	99.19 43	99.35 60	98.01 62	98.37 178	98.81 76	97.48 18	99.21 21	99.21 48	96.13 27	99.80 80	98.40 24	99.73 43	99.75 28

alignmvs		97.56 86	97.07 96	99.01 62	98.66 139	98.37 41	98.83 98	98.06 252	96.74 57	98.00 100	97.65 224	90.80 155	99.48 150	98.37 25	96.56 193	99.19 133

IU-MVS					99.71 20	99.23 6		98.64 137	95.28 122	99.63 4				98.35 26	99.81 10	99.83 5

TSAR-MVS + MP.		98.78 6	98.62 7	99.24 40	99.69 25	98.28 48	99.14 38	98.66 132	96.84 53	99.56 5	99.31 35	96.34 19	99.70 115	98.32 27	99.73 43	99.73 36
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CS-MVS-test		97.78 71	97.68 66	98.09 124	97.94 195	97.19 98	98.95 74	98.37 189	95.98 87	97.99 101	97.84 207	94.50 88	99.11 182	98.30 28	99.28 108	97.97 207

DeepPCF-MVS	96.37 2	97.93 65	98.48 17	96.30 247	99.00 110	89.54 317	97.43 270	98.87 55	98.16 2	99.26 18	99.38 21	96.12 28	99.64 126	98.30 28	99.77 26	99.72 40

canonicalmvs		97.67 76	97.23 89	98.98 65	98.70 135	98.38 35	99.34 12	98.39 185	96.76 56	97.67 121	97.40 245	92.26 118	99.49 146	98.28 30	96.28 205	99.08 149

SD-MVS		98.64 14	98.68 5	98.53 91	99.33 65	98.36 42	98.90 82	98.85 64	97.28 31	99.72 3	99.39 14	96.63 15	97.60 323	98.17 31	99.85 3	99.64 70
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
diffmvs		97.58 84	97.40 83	98.13 120	98.32 166	95.81 163	98.06 223	98.37 189	96.20 78	98.74 53	98.89 101	91.31 145	99.25 164	98.16 32	98.52 138	99.34 112

casdiffmvs		97.63 79	97.41 82	98.28 108	98.33 164	96.14 142	98.82 101	98.32 197	96.38 73	97.95 103	99.21 48	91.23 147	99.23 167	98.12 33	98.37 146	99.48 96

baseline		97.64 78	97.44 81	98.25 112	98.35 158	96.20 139	99.00 64	98.32 197	96.33 75	98.03 93	99.17 56	91.35 143	99.16 173	98.10 34	98.29 151	99.39 109

MP-MVS-pluss		98.31 52	97.92 58	99.49 9	99.72 12	98.88 14	98.43 172	98.78 95	94.10 170	97.69 120	99.42 12	95.25 66	99.92 21	98.09 35	99.80 17	99.67 61
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SMA-MVS		98.58 23	98.25 38	99.56 5	99.51 39	99.04 11	98.95 74	98.80 87	93.67 200	99.37 13	99.52 3	96.52 17	99.89 35	98.06 36	99.81 10	99.76 26
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
CNVR-MVS		98.78 6	98.56 9	99.45 14	99.32 68	98.87 15	98.47 166	98.81 76	97.72 6	98.76 52	99.16 61	97.05 10	99.78 96	98.06 36	99.66 57	99.69 51

MVS_111021_HR		98.47 38	98.34 28	98.88 72	99.22 94	97.32 88	97.91 237	99.58 3	97.20 39	98.33 82	99.00 85	95.99 35	99.64 126	98.05 38	99.76 32	99.69 51

VDDNet		95.36 184	94.53 201	97.86 137	98.10 184	95.13 188	98.85 94	97.75 269	90.46 300	98.36 80	99.39 14	73.27 350	99.64 126	97.98 39	96.58 192	98.81 169

hse-mvs3		96.17 145	95.62 154	97.81 142	99.03 108	94.45 219	98.64 141	98.75 102	97.48 18	98.67 59	98.72 120	89.76 171	99.86 49	97.95 40	81.59 342	99.11 144

hse-mvs2		95.71 164	95.30 169	96.93 195	98.50 150	93.53 251	98.36 180	98.10 238	97.48 18	98.67 59	97.99 191	89.76 171	99.02 197	97.95 40	80.91 346	98.22 199

MCST-MVS		98.65 13	98.37 21	99.48 10	99.60 31	98.87 15	98.41 175	98.68 121	97.04 48	98.52 70	98.80 111	96.78 12	99.83 56	97.93 42	99.61 67	99.74 33

zzz-MVS		98.55 30	98.25 38	99.46 12	99.76 1	98.64 22	98.55 156	98.74 104	97.27 35	98.02 94	99.39 14	94.81 77	99.96 1	97.91 43	99.79 19	99.77 20

MTAPA		98.58 23	98.29 35	99.46 12	99.76 1	98.64 22	98.90 82	98.74 104	97.27 35	98.02 94	99.39 14	94.81 77	99.96 1	97.91 43	99.79 19	99.77 20

MVS_111021_LR		98.34 48	98.23 42	98.67 80	99.27 83	96.90 108	97.95 233	99.58 3	97.14 43	98.44 76	99.01 84	95.03 73	99.62 131	97.91 43	99.75 38	99.50 91

ACMMP_NAP		98.61 17	98.30 34	99.55 6	99.62 30	98.95 13	98.82 101	98.81 76	95.80 94	99.16 26	99.47 8	95.37 57	99.92 21	97.89 46	99.75 38	99.79 10

PS-MVSNAJ		97.73 73	97.77 62	97.62 159	98.68 138	95.58 168	97.34 279	98.51 161	97.29 30	98.66 63	97.88 202	94.51 85	99.90 33	97.87 47	99.17 112	97.39 222

test1172		98.56 28	98.35 24	99.16 50	99.53 36	97.94 66	99.09 48	98.83 68	96.52 67	99.05 32	99.34 31	95.34 59	99.82 64	97.86 48	99.64 62	99.73 36

XVS		98.70 9	98.49 16	99.34 23	99.70 23	98.35 43	99.29 16	98.88 49	97.40 23	98.46 72	99.20 52	95.90 40	99.89 35	97.85 49	99.74 41	99.78 13

X-MVStestdata		94.06 267	92.30 287	99.34 23	99.70 23	98.35 43	99.29 16	98.88 49	97.40 23	98.46 72	43.50 364	95.90 40	99.89 35	97.85 49	99.74 41	99.78 13

xiu_mvs_v2_base		97.66 77	97.70 65	97.56 163	98.61 144	95.46 174	97.44 268	98.46 171	97.15 42	98.65 64	98.15 179	94.33 92	99.80 80	97.84 51	98.66 133	97.41 220

DeepC-MVS	95.98 3	97.88 66	97.58 69	98.77 75	99.25 86	96.93 106	98.83 98	98.75 102	96.96 51	96.89 152	99.50 4	90.46 161	99.87 44	97.84 51	99.76 32	99.52 85
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSP-MVS		98.74 8	98.55 10	99.29 31	99.75 3	98.23 49	99.26 20	98.88 49	97.52 15	99.41 11	98.78 113	96.00 34	99.79 92	97.79 53	99.59 71	99.85 2
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
CP-MVS		98.57 26	98.36 22	99.19 43	99.66 27	97.86 68	99.34 12	98.87 55	95.96 89	98.60 67	99.13 64	96.05 32	99.94 3	97.77 54	99.86 1	99.77 20

SteuartSystems-ACMMP		98.90 5	98.75 4	99.36 21	99.22 94	98.43 33	99.10 47	98.87 55	97.38 26	99.35 14	99.40 13	97.78 3	99.87 44	97.77 54	99.85 3	99.78 13
Skip Steuart: Steuart Systems R&D Blog.
APD-MVS_3200maxsize		98.53 34	98.33 32	99.15 53	99.50 41	97.92 67	99.15 37	98.81 76	96.24 76	99.20 22	99.37 22	95.30 62	99.80 80	97.73 56	99.67 54	99.72 40

SR-MVS-dyc-post		98.54 32	98.35 24	99.13 54	99.49 45	97.86 68	99.11 44	98.80 87	96.49 68	99.17 24	99.35 28	95.34 59	99.82 64	97.72 57	99.65 58	99.71 44

RE-MVS-def			98.34 28		99.49 45	97.86 68	99.11 44	98.80 87	96.49 68	99.17 24	99.35 28	95.29 63		97.72 57	99.65 58	99.71 44

xxxxxxxxxxxxxcwj		98.70 9	98.50 14	99.30 30	99.46 51	98.38 35	98.21 201	98.52 158	97.95 3	99.32 15	99.39 14	96.22 20	99.84 53	97.72 57	99.73 43	99.67 61

SF-MVS		98.59 20	98.32 33	99.41 16	99.54 35	98.71 18	99.04 54	98.81 76	95.12 131	99.32 15	99.39 14	96.22 20	99.84 53	97.72 57	99.73 43	99.67 61

LFMVS		95.86 157	94.98 183	98.47 96	98.87 120	96.32 135	98.84 97	96.02 334	93.40 210	98.62 65	99.20 52	74.99 344	99.63 129	97.72 57	97.20 179	99.46 102

SR-MVS		98.57 26	98.35 24	99.24 40	99.53 36	98.18 53	99.09 48	98.82 70	96.58 63	99.10 29	99.32 33	95.39 55	99.82 64	97.70 62	99.63 64	99.72 40

PHI-MVS		98.34 48	98.06 49	99.18 47	99.15 101	98.12 58	99.04 54	99.09 20	93.32 213	98.83 48	99.10 69	96.54 16	99.83 56	97.70 62	99.76 32	99.59 80

HPM-MVS		98.36 45	98.10 48	99.13 54	99.74 7	97.82 72	99.53 1	98.80 87	94.63 155	98.61 66	98.97 87	95.13 70	99.77 101	97.65 64	99.83 9	99.79 10
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
DPE-MVS		98.92 4	98.67 6	99.65 2	99.58 32	99.20 7	98.42 174	98.91 43	97.58 14	99.54 7	99.46 9	97.10 9	99.94 3	97.64 65	99.84 8	99.83 5
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ETV-MVS		97.96 59	97.81 61	98.40 103	98.42 154	97.27 91	98.73 121	98.55 152	96.84 53	98.38 79	97.44 242	95.39 55	99.35 158	97.62 66	98.89 120	98.58 186

HFP-MVS		98.63 16	98.40 18	99.32 28	99.72 12	98.29 46	99.23 23	98.96 32	96.10 85	98.94 39	99.17 56	96.06 30	99.92 21	97.62 66	99.78 23	99.75 28

ACMMPR		98.59 20	98.36 22	99.29 31	99.74 7	98.15 56	99.23 23	98.95 34	96.10 85	98.93 43	99.19 55	95.70 44	99.94 3	97.62 66	99.79 19	99.78 13

jason		97.32 101	97.08 95	98.06 127	97.45 233	95.59 167	97.87 243	97.91 263	94.79 146	98.55 69	98.83 108	91.12 148	99.23 167	97.58 69	99.60 68	99.34 112
jason: jason.
lupinMVS		97.44 93	97.22 90	98.12 122	98.07 185	95.76 164	97.68 257	97.76 268	94.50 160	98.79 49	98.61 130	92.34 115	99.30 161	97.58 69	99.59 71	99.31 118

HPM-MVS_fast		98.38 43	98.13 46	99.12 57	99.75 3	97.86 68	99.44 5	98.82 70	94.46 162	98.94 39	99.20 52	95.16 69	99.74 107	97.58 69	99.85 3	99.77 20

ZNCC-MVS		98.49 36	98.20 44	99.35 22	99.73 11	98.39 34	99.19 33	98.86 61	95.77 95	98.31 84	99.10 69	95.46 51	99.93 15	97.57 72	99.81 10	99.74 33

region2R		98.61 17	98.38 20	99.29 31	99.74 7	98.16 55	99.23 23	98.93 37	96.15 80	98.94 39	99.17 56	95.91 39	99.94 3	97.55 73	99.79 19	99.78 13

DeepC-MVS_fast	96.70 1	98.55 30	98.34 28	99.18 47	99.25 86	98.04 60	98.50 163	98.78 95	97.72 6	98.92 44	99.28 40	95.27 64	99.82 64	97.55 73	99.77 26	99.69 51
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HPM-MVS++		98.58 23	98.25 38	99.55 6	99.50 41	99.08 9	98.72 125	98.66 132	97.51 16	98.15 85	98.83 108	95.70 44	99.92 21	97.53 75	99.67 54	99.66 65

nrg030		96.28 142	95.72 146	97.96 134	96.90 269	98.15 56	99.39 6	98.31 199	95.47 110	94.42 219	98.35 158	92.09 125	98.69 234	97.50 76	89.05 302	97.04 232

CSCG		97.85 68	97.74 64	98.20 115	99.67 26	95.16 184	99.22 27	99.32 7	93.04 224	97.02 145	98.92 99	95.36 58	99.91 30	97.43 77	99.64 62	99.52 85

mPP-MVS		98.51 35	98.26 37	99.25 39	99.75 3	98.04 60	99.28 18	98.81 76	96.24 76	98.35 81	99.23 45	95.46 51	99.94 3	97.42 78	99.81 10	99.77 20

mvs_anonymous		96.70 125	96.53 123	97.18 179	98.19 176	93.78 239	98.31 190	98.19 218	94.01 175	94.47 213	98.27 171	92.08 126	98.46 257	97.39 79	97.91 160	99.31 118

EIA-MVS		97.75 72	97.58 69	98.27 109	98.38 156	96.44 129	99.01 62	98.60 140	95.88 91	97.26 134	97.53 235	94.97 74	99.33 160	97.38 80	99.20 110	99.05 151

NCCC		98.61 17	98.35 24	99.38 17	99.28 82	98.61 24	98.45 167	98.76 99	97.82 5	98.45 75	98.93 97	96.65 14	99.83 56	97.38 80	99.41 99	99.71 44

VPA-MVSNet		95.75 162	95.11 177	97.69 153	97.24 244	97.27 91	98.94 77	99.23 12	95.13 130	95.51 190	97.32 248	85.73 258	98.91 213	97.33 82	89.55 294	96.89 248

OPU-MVS				99.37 20	99.24 92	99.05 10	99.02 60				99.16 61	97.81 2	99.37 157	97.24 83	99.73 43	99.70 48

3Dnovator	94.51 5	97.46 89	96.93 102	99.07 60	97.78 204	97.64 77	99.35 11	99.06 22	97.02 49	93.75 251	99.16 61	89.25 182	99.92 21	97.22 84	99.75 38	99.64 70

#test#		98.54 32	98.27 36	99.32 28	99.72 12	98.29 46	98.98 69	98.96 32	95.65 102	98.94 39	99.17 56	96.06 30	99.92 21	97.21 85	99.78 23	99.75 28

ACMMP		98.23 54	97.95 56	99.09 59	99.74 7	97.62 79	99.03 57	99.41 6	95.98 87	97.60 128	99.36 26	94.45 90	99.93 15	97.14 86	98.85 124	99.70 48
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
PVSNet_Blended_VisFu		97.70 75	97.46 79	98.44 98	99.27 83	95.91 158	98.63 142	99.16 17	94.48 161	97.67 121	98.88 102	92.80 110	99.91 30	97.11 87	99.12 113	99.50 91

mvs_tets		95.41 180	95.00 181	96.65 213	95.58 321	94.42 221	99.00 64	98.55 152	95.73 97	93.21 269	98.38 155	83.45 297	98.63 241	97.09 88	94.00 233	96.91 245

GST-MVS		98.43 40	98.12 47	99.34 23	99.72 12	98.38 35	99.09 48	98.82 70	95.71 98	98.73 55	99.06 78	95.27 64	99.93 15	97.07 89	99.63 64	99.72 40

9.14			98.06 49		99.47 48		98.71 126	98.82 70	94.36 164	99.16 26	99.29 39	96.05 32	99.81 71	97.00 90	99.71 50

EPNet		97.28 102	96.87 105	98.51 92	94.98 331	96.14 142	98.90 82	97.02 314	98.28 1	95.99 186	99.11 67	91.36 142	99.89 35	96.98 91	99.19 111	99.50 91
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HyFIR lowres test		96.90 119	96.49 124	98.14 118	99.33 65	95.56 169	97.38 273	99.65 2	92.34 249	97.61 127	98.20 176	89.29 181	99.10 186	96.97 92	97.60 173	99.77 20

3Dnovator+	94.38 6	97.43 94	96.78 109	99.38 17	97.83 202	98.52 27	99.37 8	98.71 114	97.09 47	92.99 277	99.13 64	89.36 179	99.89 35	96.97 92	99.57 75	99.71 44

abl_6		98.30 53	98.03 51	99.13 54	99.56 34	97.76 75	99.13 41	98.82 70	96.14 81	99.26 18	99.37 22	93.33 104	99.93 15	96.96 94	99.67 54	99.69 51

jajsoiax		95.45 176	95.03 180	96.73 207	95.42 328	94.63 210	99.14 38	98.52 158	95.74 96	93.22 268	98.36 157	83.87 293	98.65 240	96.95 95	94.04 231	96.91 245

ET-MVSNet_ETH3D		94.13 260	92.98 275	97.58 161	98.22 172	96.20 139	97.31 282	95.37 342	94.53 157	79.56 353	97.63 228	86.51 244	97.53 326	96.91 96	90.74 279	99.02 154

MVSFormer		97.57 85	97.49 77	97.84 138	98.07 185	95.76 164	99.47 3	98.40 183	94.98 138	98.79 49	98.83 108	92.34 115	98.41 269	96.91 96	99.59 71	99.34 112

test_djsdf		96.00 151	95.69 151	96.93 195	95.72 317	95.49 173	99.47 3	98.40 183	94.98 138	94.58 209	97.86 204	89.16 185	98.41 269	96.91 96	94.12 230	96.88 249

test_prior3		98.22 55	97.90 59	99.19 43	99.31 70	98.22 50	97.80 249	98.84 65	96.12 83	97.89 110	98.69 122	95.96 36	99.70 115	96.89 99	99.60 68	99.65 67

test_prior2							97.80 249		96.12 83	97.89 110	98.69 122	95.96 36		96.89 99	99.60 68

EPP-MVSNet		97.46 89	97.28 87	97.99 131	98.64 141	95.38 176	99.33 15	98.31 199	93.61 203	97.19 136	99.07 77	94.05 96	99.23 167	96.89 99	98.43 145	99.37 111

PS-MVSNAJss		96.43 135	96.26 131	96.92 198	95.84 315	95.08 190	99.16 36	98.50 166	95.87 92	93.84 247	98.34 162	94.51 85	98.61 242	96.88 102	93.45 246	97.06 231

PVSNet_BlendedMVS		96.73 124	96.60 119	97.12 183	99.25 86	95.35 179	98.26 198	99.26 8	94.28 165	97.94 105	97.46 239	92.74 111	99.81 71	96.88 102	93.32 249	96.20 315

PVSNet_Blended		97.38 98	97.12 92	98.14 118	99.25 86	95.35 179	97.28 284	99.26 8	93.13 221	97.94 105	98.21 175	92.74 111	99.81 71	96.88 102	99.40 101	99.27 125

Effi-MVS+		97.12 111	96.69 115	98.39 104	98.19 176	96.72 116	97.37 275	98.43 178	93.71 193	97.65 124	98.02 187	92.20 122	99.25 164	96.87 105	97.79 165	99.19 133

CHOSEN 1792x2688		97.12 111	96.80 106	98.08 125	99.30 75	94.56 217	98.05 224	99.71 1	93.57 204	97.09 139	98.91 100	88.17 211	99.89 35	96.87 105	99.56 80	99.81 8

test_yl		97.22 104	96.78 109	98.54 89	98.73 130	96.60 121	98.45 167	98.31 199	94.70 148	98.02 94	98.42 150	90.80 155	99.70 115	96.81 107	96.79 186	99.34 112

DCV-MVSNet		97.22 104	96.78 109	98.54 89	98.73 130	96.60 121	98.45 167	98.31 199	94.70 148	98.02 94	98.42 150	90.80 155	99.70 115	96.81 107	96.79 186	99.34 112

ETH3D-3000-0.1		98.35 46	98.00 54	99.38 17	99.47 48	98.68 21	98.67 136	98.84 65	94.66 154	99.11 28	99.25 43	95.46 51	99.81 71	96.80 109	99.73 43	99.63 73

PGM-MVS		98.49 36	98.23 42	99.27 38	99.72 12	98.08 59	98.99 66	99.49 5	95.43 112	99.03 33	99.32 33	95.56 47	99.94 3	96.80 109	99.77 26	99.78 13

RRT_test8_iter05		94.56 233	94.19 220	95.67 272	97.60 216	91.34 291	98.93 79	98.42 179	94.75 147	93.39 263	97.87 203	79.00 322	98.61 242	96.78 111	90.99 277	97.07 230

XVG-OURS-SEG-HR		96.51 133	96.34 127	97.02 188	98.77 128	93.76 240	97.79 251	98.50 166	95.45 111	96.94 147	99.09 74	87.87 221	99.55 142	96.76 112	95.83 215	97.74 213

MP-MVS		98.33 50	98.01 53	99.28 35	99.75 3	98.18 53	99.22 27	98.79 92	96.13 82	97.92 108	99.23 45	94.54 84	99.94 3	96.74 113	99.78 23	99.73 36
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
agg_prior1		97.95 62	97.51 76	99.28 35	99.30 75	98.38 35	97.81 248	98.72 110	93.16 220	97.57 129	98.66 127	96.14 26	99.81 71	96.63 114	99.56 80	99.66 65

train_agg		97.97 58	97.52 74	99.33 27	99.31 70	98.50 29	97.92 235	98.73 108	92.98 226	97.74 116	98.68 124	96.20 23	99.80 80	96.59 115	99.57 75	99.68 57

MVSTER		96.06 148	95.72 146	97.08 186	98.23 171	95.93 156	98.73 121	98.27 208	94.86 144	95.07 195	98.09 183	88.21 209	98.54 250	96.59 115	93.46 244	96.79 258

bset_n11_16_dypcd		94.89 213	94.27 216	96.76 205	94.41 338	95.15 186	95.67 337	95.64 341	95.53 106	94.65 207	97.52 236	87.10 234	98.29 285	96.58 117	91.35 269	96.83 256

UGNet		96.78 123	96.30 129	98.19 117	98.24 170	95.89 160	98.88 89	98.93 37	97.39 25	96.81 156	97.84 207	82.60 299	99.90 33	96.53 118	99.49 88	98.79 170
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
APD-MVS		98.35 46	98.00 54	99.42 15	99.51 39	98.72 17	98.80 108	98.82 70	94.52 159	99.23 20	99.25 43	95.54 49	99.80 80	96.52 119	99.77 26	99.74 33
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
VPNet		94.99 205	94.19 220	97.40 171	97.16 253	96.57 123	98.71 126	98.97 30	95.67 100	94.84 201	98.24 174	80.36 314	98.67 238	96.46 120	87.32 322	96.96 237

ETH3D cwj APD-0.16		97.96 59	97.52 74	99.29 31	99.05 105	98.52 27	98.33 184	98.68 121	93.18 218	98.68 57	99.13 64	94.62 81	99.83 56	96.45 121	99.55 83	99.52 85

sss		97.39 97	96.98 101	98.61 83	98.60 145	96.61 120	98.22 200	98.93 37	93.97 178	98.01 98	98.48 144	91.98 128	99.85 50	96.45 121	98.15 153	99.39 109

MVS_Test		97.28 102	97.00 99	98.13 120	98.33 164	95.97 150	98.74 117	98.07 247	94.27 166	98.44 76	98.07 184	92.48 113	99.26 163	96.43 123	98.19 152	99.16 138

FIs		96.51 133	96.12 135	97.67 155	97.13 255	97.54 82	99.36 9	99.22 14	95.89 90	94.03 239	98.35 158	91.98 128	98.44 260	96.40 124	92.76 256	97.01 233

test9_res														96.39 125	99.57 75	99.69 51

Anonymous20240529		95.10 199	94.22 218	97.75 147	99.01 109	94.26 228	98.87 91	98.83 68	85.79 341	96.64 161	98.97 87	78.73 323	99.85 50	96.27 126	94.89 219	99.12 143

PMMVS		96.60 127	96.33 128	97.41 169	97.90 198	93.93 235	97.35 278	98.41 181	92.84 233	97.76 114	97.45 241	91.10 150	99.20 170	96.26 127	97.91 160	99.11 144

CLD-MVS		95.62 170	95.34 164	96.46 237	97.52 226	93.75 242	97.27 285	98.46 171	95.53 106	94.42 219	98.00 190	86.21 251	98.97 202	96.25 128	94.37 220	96.66 277
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Anonymous202405211		95.28 189	94.49 203	97.67 155	99.00 110	93.75 242	98.70 130	97.04 311	90.66 296	96.49 172	98.80 111	78.13 328	99.83 56	96.21 129	95.36 218	99.44 105

RRT_MVS		96.04 149	95.53 155	97.56 163	97.07 259	97.32 88	98.57 153	98.09 243	95.15 129	95.02 197	98.44 147	88.20 210	98.58 248	96.17 130	93.09 253	96.79 258

ZD-MVS					99.46 51	98.70 19		98.79 92	93.21 217	98.67 59	98.97 87	95.70 44	99.83 56	96.07 131	99.58 74

HQP_MVS		96.14 146	95.90 142	96.85 201	97.42 234	94.60 215	98.80 108	98.56 150	97.28 31	95.34 191	98.28 168	87.09 235	99.03 194	96.07 131	94.27 222	96.92 240

plane_prior5								98.56 150					99.03 194	96.07 131	94.27 222	96.92 240

CPTT-MVS		97.72 74	97.32 86	98.92 69	99.64 28	97.10 101	99.12 43	98.81 76	92.34 249	98.09 88	99.08 76	93.01 108	99.92 21	96.06 134	99.77 26	99.75 28

DP-MVS Recon		97.86 67	97.46 79	99.06 61	99.53 36	98.35 43	98.33 184	98.89 46	92.62 238	98.05 90	98.94 96	95.34 59	99.65 124	96.04 135	99.42 98	99.19 133

FC-MVSNet-test		96.42 136	96.05 137	97.53 165	96.95 264	97.27 91	99.36 9	99.23 12	95.83 93	93.93 241	98.37 156	92.00 127	98.32 278	96.02 136	92.72 257	97.00 234

Vis-MVSNet		97.42 95	97.11 93	98.34 106	98.66 139	96.23 138	99.22 27	99.00 27	96.63 62	98.04 92	99.21 48	88.05 216	99.35 158	96.01 137	99.21 109	99.45 104
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ab-mvs		96.42 136	95.71 149	98.55 87	98.63 142	96.75 115	97.88 242	98.74 104	93.84 184	96.54 169	98.18 178	85.34 266	99.75 105	95.93 138	96.35 199	99.15 139

WTY-MVS		97.37 99	96.92 103	98.72 77	98.86 121	96.89 110	98.31 190	98.71 114	95.26 123	97.67 121	98.56 138	92.21 121	99.78 96	95.89 139	96.85 184	99.48 96

XVG-OURS		96.55 132	96.41 125	96.99 189	98.75 129	93.76 240	97.50 267	98.52 158	95.67 100	96.83 153	99.30 38	88.95 195	99.53 143	95.88 140	96.26 206	97.69 216

agg_prior2														95.87 141	99.57 75	99.68 57

UniMVSNet_NR-MVSNet		95.71 164	95.15 174	97.40 171	96.84 272	96.97 104	98.74 117	99.24 10	95.16 128	93.88 244	97.72 219	91.68 133	98.31 280	95.81 142	87.25 323	96.92 240

DU-MVS		95.42 178	94.76 191	97.40 171	96.53 287	96.97 104	98.66 139	98.99 29	95.43 112	93.88 244	97.69 220	88.57 201	98.31 280	95.81 142	87.25 323	96.92 240

testtj		98.33 50	97.95 56	99.47 11	99.49 45	98.70 19	98.83 98	98.86 61	95.48 109	98.91 45	99.17 56	95.48 50	99.93 15	95.80 144	99.53 85	99.76 26

UniMVSNet (Re)		95.78 161	95.19 173	97.58 161	96.99 263	97.47 84	98.79 112	99.18 16	95.60 103	93.92 242	97.04 273	91.68 133	98.48 254	95.80 144	87.66 318	96.79 258

cascas		94.63 228	93.86 243	96.93 195	96.91 268	94.27 227	96.00 333	98.51 161	85.55 342	94.54 210	96.23 314	84.20 286	98.87 220	95.80 144	96.98 183	97.66 217

Effi-MVS+-dtu		96.29 140	96.56 120	95.51 275	97.89 199	90.22 310	98.80 108	98.10 238	96.57 64	96.45 175	96.66 298	90.81 153	98.91 213	95.72 147	97.99 158	97.40 221

mvs-test1		96.60 127	96.68 117	96.37 242	97.89 199	91.81 281	98.56 154	98.10 238	96.57 64	96.52 171	97.94 196	90.81 153	99.45 153	95.72 147	98.01 157	97.86 210

LPG-MVS_test		95.62 170	95.34 164	96.47 234	97.46 229	93.54 249	98.99 66	98.54 154	94.67 152	94.36 221	98.77 115	85.39 263	99.11 182	95.71 149	94.15 228	96.76 262

LGP-MVS_train				96.47 234	97.46 229	93.54 249		98.54 154	94.67 152	94.36 221	98.77 115	85.39 263	99.11 182	95.71 149	94.15 228	96.76 262

旧先验2							97.57 265		91.30 284	98.67 59			99.80 80	95.70 151

LCM-MVSNet-Re		95.22 192	95.32 167	94.91 293	98.18 178	87.85 341	98.75 114	95.66 340	95.11 132	88.96 329	96.85 291	90.26 166	97.65 321	95.65 152	98.44 143	99.22 129

anonymousdsp		95.42 178	94.91 186	96.94 194	95.10 330	95.90 159	99.14 38	98.41 181	93.75 188	93.16 270	97.46 239	87.50 229	98.41 269	95.63 153	94.03 232	96.50 301

CDPH-MVS		97.94 63	97.49 77	99.28 35	99.47 48	98.44 31	97.91 237	98.67 129	92.57 241	98.77 51	98.85 105	95.93 38	99.72 109	95.56 154	99.69 52	99.68 57

CostFormer		94.95 209	94.73 193	95.60 274	97.28 242	89.06 324	97.53 266	96.89 322	89.66 316	96.82 155	96.72 296	86.05 254	98.95 210	95.53 155	96.13 211	98.79 170

ACMM	93.85 9	95.69 167	95.38 162	96.61 218	97.61 215	93.84 238	98.91 81	98.44 175	95.25 124	94.28 225	98.47 145	86.04 256	99.12 179	95.50 156	93.95 235	96.87 251
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	93.49 10	95.34 186	94.98 183	96.43 239	97.67 211	93.48 253	98.73 121	98.44 175	94.94 143	92.53 290	98.53 139	84.50 280	99.14 177	95.48 157	94.00 233	96.66 277
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
tttt0517		96.07 147	95.51 157	97.78 144	98.41 155	94.84 201	99.28 18	94.33 353	94.26 167	97.64 125	98.64 129	84.05 288	99.47 151	95.34 158	97.60 173	99.03 152

TAMVS		97.02 114	96.79 108	97.70 152	98.06 187	95.31 181	98.52 158	98.31 199	93.95 179	97.05 144	98.61 130	93.49 103	98.52 252	95.33 159	97.81 164	99.29 123

BP-MVS														95.30 160

HQP-MVS		95.72 163	95.40 158	96.69 211	97.20 248	94.25 229	98.05 224	98.46 171	96.43 70	94.45 214	97.73 217	86.75 241	98.96 206	95.30 160	94.18 226	96.86 253

thisisatest0530		96.01 150	95.36 163	97.97 132	98.38 156	95.52 172	98.88 89	94.19 355	94.04 172	97.64 125	98.31 165	83.82 295	99.46 152	95.29 162	97.70 170	98.93 163

WR-MVS		95.15 196	94.46 206	97.22 176	96.67 282	96.45 128	98.21 201	98.81 76	94.15 168	93.16 270	97.69 220	87.51 227	98.30 282	95.29 162	88.62 308	96.90 247

tpmrst		95.63 169	95.69 151	95.44 279	97.54 223	88.54 332	96.97 301	97.56 279	93.50 206	97.52 131	96.93 286	89.49 175	99.16 173	95.25 164	96.42 198	98.64 182

CDS-MVSNet		96.99 115	96.69 115	97.90 136	98.05 188	95.98 145	98.20 204	98.33 196	93.67 200	96.95 146	98.49 143	93.54 102	98.42 262	95.24 165	97.74 168	99.31 118
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
OPM-MVS		95.69 167	95.33 166	96.76 205	96.16 304	94.63 210	98.43 172	98.39 185	96.64 61	95.02 197	98.78 113	85.15 268	99.05 190	95.21 166	94.20 225	96.60 282

OMC-MVS		97.55 87	97.34 85	98.20 115	99.33 65	95.92 157	98.28 195	98.59 142	95.52 108	97.97 102	99.10 69	93.28 106	99.49 146	95.09 167	98.88 121	99.19 133

UniMVSNet_ETH3D		94.24 253	93.33 269	96.97 192	97.19 251	93.38 258	98.74 117	98.57 148	91.21 290	93.81 248	98.58 135	72.85 351	98.77 231	95.05 168	93.93 236	98.77 172

CANet_DTU		96.96 116	96.55 121	98.21 114	98.17 180	96.07 144	97.98 231	98.21 215	97.24 37	97.13 138	98.93 97	86.88 240	99.91 30	95.00 169	99.37 103	98.66 180

UA-Net		97.96 59	97.62 67	98.98 65	98.86 121	97.47 84	98.89 86	99.08 21	96.67 60	98.72 56	99.54 1	93.15 107	99.81 71	94.87 170	98.83 125	99.65 67

114514_t		96.93 117	96.27 130	98.92 69	99.50 41	97.63 78	98.85 94	98.90 44	84.80 344	97.77 113	99.11 67	92.84 109	99.66 123	94.85 171	99.77 26	99.47 98

Anonymous20231211		94.10 263	93.26 272	96.61 218	99.11 104	94.28 226	99.01 62	98.88 49	86.43 335	92.81 280	97.57 232	81.66 305	98.68 237	94.83 172	89.02 304	96.88 249

XXY-MVS		95.20 194	94.45 208	97.46 166	96.75 277	96.56 124	98.86 93	98.65 136	93.30 215	93.27 267	98.27 171	84.85 273	98.87 220	94.82 173	91.26 273	96.96 237

MG-MVS		97.81 69	97.60 68	98.44 98	99.12 103	95.97 150	97.75 253	98.78 95	96.89 52	98.46 72	99.22 47	93.90 100	99.68 121	94.81 174	99.52 87	99.67 61

test_part1		94.82 215	93.82 245	97.82 141	98.84 124	97.82 72	99.03 57	98.81 76	92.31 253	92.51 292	97.89 201	81.96 302	98.67 238	94.80 175	88.24 311	96.98 235

EI-MVSNet		95.96 152	95.83 144	96.36 243	97.93 196	93.70 246	98.12 218	98.27 208	93.70 195	95.07 195	99.02 80	92.23 120	98.54 250	94.68 176	93.46 244	96.84 254

thisisatest0515		95.61 172	94.89 187	97.76 146	98.15 181	95.15 186	96.77 317	94.41 351	92.95 228	97.18 137	97.43 243	84.78 274	99.45 153	94.63 177	97.73 169	98.68 177

IterMVS-LS		95.46 174	95.21 172	96.22 250	98.12 182	93.72 245	98.32 189	98.13 232	93.71 193	94.26 226	97.31 249	92.24 119	98.10 297	94.63 177	90.12 285	96.84 254
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.25 144	95.73 145	97.79 143	97.13 255	95.55 171	98.19 208	98.59 142	93.47 207	92.03 303	97.82 212	91.33 144	99.49 146	94.62 179	98.44 143	98.32 196

baseline1		95.84 158	95.12 176	98.01 130	98.49 152	95.98 145	98.73 121	97.03 312	95.37 117	96.22 179	98.19 177	89.96 169	99.16 173	94.60 180	87.48 319	98.90 165

IS-MVSNet		97.22 104	96.88 104	98.25 112	98.85 123	96.36 133	99.19 33	97.97 257	95.39 114	97.23 135	98.99 86	91.11 149	98.93 211	94.60 180	98.59 135	99.47 98

NR-MVSNet		94.98 207	94.16 223	97.44 167	96.53 287	97.22 97	98.74 117	98.95 34	94.96 140	89.25 328	97.69 220	89.32 180	98.18 291	94.59 182	87.40 321	96.92 240

IB-MVS	91.98 17	93.27 280	91.97 291	97.19 178	97.47 228	93.41 256	97.09 296	95.99 335	93.32 213	92.47 294	95.73 324	78.06 329	99.53 143	94.59 182	82.98 337	98.62 183
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
DWT-MVSNet_test		94.82 215	94.36 213	96.20 251	97.35 239	90.79 302	98.34 182	96.57 333	92.91 230	95.33 193	96.44 308	82.00 301	99.12 179	94.52 184	95.78 216	98.70 175

HY-MVS	93.96 8	96.82 122	96.23 133	98.57 85	98.46 153	97.00 103	98.14 215	98.21 215	93.95 179	96.72 159	97.99 191	91.58 135	99.76 103	94.51 185	96.54 194	98.95 162

D2MVS		95.18 195	95.08 178	95.48 276	97.10 257	92.07 277	98.30 192	99.13 19	94.02 174	92.90 278	96.73 295	89.48 176	98.73 233	94.48 186	93.60 243	95.65 328

Baseline_NR-MVSNet		94.35 246	93.81 246	95.96 260	96.20 300	94.05 233	98.61 145	96.67 331	91.44 277	93.85 246	97.60 229	88.57 201	98.14 294	94.39 187	86.93 326	95.68 327

AdaColmap		97.15 110	96.70 114	98.48 95	99.16 99	96.69 117	98.01 228	98.89 46	94.44 163	96.83 153	98.68 124	90.69 158	99.76 103	94.36 188	99.29 107	98.98 158

AUN-MVS		94.53 236	93.73 254	96.92 198	98.50 150	93.52 252	98.34 182	98.10 238	93.83 186	95.94 188	97.98 193	85.59 261	99.03 194	94.35 189	80.94 345	98.22 199

1112_ss		96.63 126	96.00 140	98.50 93	98.56 146	96.37 132	98.18 212	98.10 238	92.92 229	94.84 201	98.43 148	92.14 123	99.58 134	94.35 189	96.51 195	99.56 84

CP-MVSNet		94.94 211	94.30 215	96.83 202	96.72 279	95.56 169	99.11 44	98.95 34	93.89 181	92.42 296	97.90 199	87.19 233	98.12 296	94.32 191	88.21 312	96.82 257

CNLPA		97.45 92	97.03 97	98.73 76	99.05 105	97.44 86	98.07 222	98.53 156	95.32 120	96.80 157	98.53 139	93.32 105	99.72 109	94.31 192	99.31 106	99.02 154

testdata				98.26 111	99.20 97	95.36 177		98.68 121	91.89 264	98.60 67	99.10 69	94.44 91	99.82 64	94.27 193	99.44 96	99.58 82

PVSNet	91.96 18	96.35 138	96.15 134	96.96 193	99.17 98	92.05 278	96.08 329	98.68 121	93.69 196	97.75 115	97.80 214	88.86 196	99.69 120	94.26 194	99.01 115	99.15 139

miper_enhance_ethall		95.10 199	94.75 192	96.12 255	97.53 225	93.73 244	96.61 323	98.08 245	92.20 258	93.89 243	96.65 300	92.44 114	98.30 282	94.21 195	91.16 274	96.34 309

Test_1112_low_res		96.34 139	95.66 153	98.36 105	98.56 146	95.94 153	97.71 255	98.07 247	92.10 259	94.79 205	97.29 250	91.75 132	99.56 137	94.17 196	96.50 196	99.58 82

TranMVSNet+NR-MVSNet		95.14 197	94.48 204	97.11 184	96.45 292	96.36 133	99.03 57	99.03 25	95.04 136	93.58 254	97.93 197	88.27 208	98.03 304	94.13 197	86.90 328	96.95 239

API-MVS		97.41 96	97.25 88	97.91 135	98.70 135	96.80 112	98.82 101	98.69 118	94.53 157	98.11 87	98.28 168	94.50 88	99.57 135	94.12 198	99.49 88	97.37 224

ETH3 D test6400		97.59 83	97.01 98	99.34 23	99.40 59	98.56 25	98.20 204	98.81 76	91.63 272	98.44 76	98.85 105	93.98 99	99.82 64	94.11 199	99.69 52	99.64 70

cl-mvsnet2		94.68 223	94.19 220	96.13 254	98.11 183	93.60 247	96.94 303	98.31 199	92.43 246	93.32 266	96.87 290	86.51 244	98.28 287	94.10 200	91.16 274	96.51 299

PLC	95.07 4	97.20 107	96.78 109	98.44 98	99.29 78	96.31 137	98.14 215	98.76 99	92.41 247	96.39 176	98.31 165	94.92 76	99.78 96	94.06 201	98.77 128	99.23 128
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
XVG-ACMP-BASELINE		94.54 235	94.14 225	95.75 270	96.55 286	91.65 287	98.11 220	98.44 175	94.96 140	94.22 229	97.90 199	79.18 321	99.11 182	94.05 202	93.85 237	96.48 303

F-COLMAP		97.09 113	96.80 106	97.97 132	99.45 55	94.95 198	98.55 156	98.62 139	93.02 225	96.17 181	98.58 135	94.01 97	99.81 71	93.95 203	98.90 119	99.14 141

MDTV_nov1_ep13_2view						84.26 349	96.89 311		90.97 294	97.90 109		89.89 170		93.91 204		99.18 137

baseline2		95.11 198	94.52 202	96.87 200	96.65 283	93.56 248	98.27 197	94.10 357	93.45 208	92.02 304	97.43 243	87.45 231	99.19 171	93.88 205	97.41 177	97.87 209

原ACMM1				98.65 81	99.32 68	96.62 118		98.67 129	93.27 216	97.81 112	98.97 87	95.18 68	99.83 56	93.84 206	99.46 94	99.50 91

RPSCF		94.87 214	95.40 158	93.26 324	98.89 118	82.06 355	98.33 184	98.06 252	90.30 305	96.56 165	99.26 42	87.09 235	99.49 146	93.82 207	96.32 201	98.24 198

PAPM_NR		97.46 89	97.11 93	98.50 93	99.50 41	96.41 131	98.63 142	98.60 140	95.18 127	97.06 143	98.06 185	94.26 94	99.57 135	93.80 208	98.87 123	99.52 85

ACMH	92.88 16	94.55 234	93.95 237	96.34 245	97.63 214	93.26 262	98.81 107	98.49 170	93.43 209	89.74 323	98.53 139	81.91 303	99.08 188	93.69 209	93.30 250	96.70 271
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
miper_ehance_all_eth		95.01 203	94.69 195	95.97 259	97.70 210	93.31 260	97.02 299	98.07 247	92.23 255	93.51 259	96.96 282	91.85 130	98.15 293	93.68 210	91.16 274	96.44 306

MAR-MVS		96.91 118	96.40 126	98.45 97	98.69 137	96.90 108	98.66 139	98.68 121	92.40 248	97.07 142	97.96 194	91.54 139	99.75 105	93.68 210	98.92 118	98.69 176
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
Vis-MVSNet (Re-imp)		96.87 120	96.55 121	97.83 139	98.73 130	95.46 174	99.20 31	98.30 205	94.96 140	96.60 164	98.87 103	90.05 167	98.59 246	93.67 212	98.60 134	99.46 102

LS3D		97.16 109	96.66 118	98.68 79	98.53 149	97.19 98	98.93 79	98.90 44	92.83 234	95.99 186	99.37 22	92.12 124	99.87 44	93.67 212	99.57 75	98.97 159

PS-CasMVS		94.67 226	93.99 235	96.71 208	96.68 281	95.26 182	99.13 41	99.03 25	93.68 198	92.33 297	97.95 195	85.35 265	98.10 297	93.59 214	88.16 314	96.79 258

cl_fuxian		94.79 218	94.43 210	95.89 264	97.75 205	93.12 267	97.16 293	98.03 254	92.23 255	93.46 262	97.05 272	91.39 141	98.01 305	93.58 215	89.21 300	96.53 293

CVMVSNet		95.43 177	96.04 138	93.57 318	97.93 196	83.62 350	98.12 218	98.59 142	95.68 99	96.56 165	99.02 80	87.51 227	97.51 327	93.56 216	97.44 175	99.60 78

OurMVSNet-221017-0		94.21 254	94.00 233	94.85 296	95.60 320	89.22 322	98.89 86	97.43 295	95.29 121	92.18 300	98.52 142	82.86 298	98.59 246	93.46 217	91.76 265	96.74 264

eth_miper_zixun_eth		94.68 223	94.41 211	95.47 277	97.64 213	91.71 286	96.73 320	98.07 247	92.71 236	93.64 252	97.21 256	90.54 160	98.17 292	93.38 218	89.76 289	96.54 291

OpenMVS	93.04 13	95.83 159	95.00 181	98.32 107	97.18 252	97.32 88	99.21 30	98.97 30	89.96 310	91.14 311	99.05 79	86.64 243	99.92 21	93.38 218	99.47 91	97.73 214

无先验							97.58 264	98.72 110	91.38 278				99.87 44	93.36 220		99.60 78

1121		97.37 99	96.77 113	99.16 50	99.34 62	97.99 65	98.19 208	98.68 121	90.14 308	98.01 98	98.97 87	94.80 79	99.87 44	93.36 220	99.46 94	99.61 75

gm-plane-assit					95.88 313	87.47 342			89.74 315		96.94 285		99.19 171	93.32 222

WR-MVS_H		95.05 202	94.46 206	96.81 203	96.86 271	95.82 162	99.24 22	99.24 10	93.87 183	92.53 290	96.84 292	90.37 162	98.24 289	93.24 223	87.93 315	96.38 308

tpm		94.13 260	93.80 247	95.12 287	96.50 289	87.91 340	97.44 268	95.89 339	92.62 238	96.37 177	96.30 311	84.13 287	98.30 282	93.24 223	91.66 267	99.14 141

Fast-Effi-MVS+-dtu		95.87 156	95.85 143	95.91 262	97.74 208	91.74 285	98.69 132	98.15 229	95.56 105	94.92 199	97.68 223	88.98 193	98.79 229	93.19 225	97.78 166	97.20 228

pmmvs5		93.65 274	92.97 276	95.68 271	95.49 324	92.37 273	98.20 204	97.28 302	89.66 316	92.58 288	97.26 251	82.14 300	98.09 299	93.18 226	90.95 278	96.58 284

TESTMET0.1,1		94.18 258	93.69 257	95.63 273	96.92 266	89.12 323	96.91 306	94.78 348	93.17 219	94.88 200	96.45 307	78.52 324	98.92 212	93.09 227	98.50 140	98.85 166

test-LLR		95.10 199	94.87 188	95.80 267	96.77 274	89.70 314	96.91 306	95.21 343	95.11 132	94.83 203	95.72 326	87.71 223	98.97 202	93.06 228	98.50 140	98.72 173

test-mter		94.08 265	93.51 264	95.80 267	96.77 274	89.70 314	96.91 306	95.21 343	92.89 231	94.83 203	95.72 326	77.69 331	98.97 202	93.06 228	98.50 140	98.72 173

BH-untuned		95.95 153	95.72 146	96.65 213	98.55 148	92.26 274	98.23 199	97.79 267	93.73 191	94.62 208	98.01 189	88.97 194	99.00 201	93.04 230	98.51 139	98.68 177

EPMVS		94.99 205	94.48 204	96.52 230	97.22 246	91.75 284	97.23 286	91.66 361	94.11 169	97.28 133	96.81 293	85.70 259	98.84 223	93.04 230	97.28 178	98.97 159

pmmvs4		94.69 221	93.99 235	96.81 203	95.74 316	95.94 153	97.40 271	97.67 272	90.42 302	93.37 264	97.59 230	89.08 188	98.20 290	92.97 232	91.67 266	96.30 313

GeoE		96.58 131	96.07 136	98.10 123	98.35 158	95.89 160	99.34 12	98.12 233	93.12 222	96.09 182	98.87 103	89.71 173	98.97 202	92.95 233	98.08 156	99.43 106

v2v482		94.69 221	94.03 229	96.65 213	96.17 302	94.79 206	98.67 136	98.08 245	92.72 235	94.00 240	97.16 258	87.69 226	98.45 258	92.91 234	88.87 306	96.72 267

Fast-Effi-MVS+		96.28 142	95.70 150	98.03 129	98.29 168	95.97 150	98.58 148	98.25 213	91.74 267	95.29 194	97.23 254	91.03 152	99.15 176	92.90 235	97.96 159	98.97 159

V42		94.78 219	94.14 225	96.70 210	96.33 297	95.22 183	98.97 70	98.09 243	92.32 251	94.31 224	97.06 270	88.39 206	98.55 249	92.90 235	88.87 306	96.34 309

DP-MVS		96.59 129	95.93 141	98.57 85	99.34 62	96.19 141	98.70 130	98.39 185	89.45 319	94.52 211	99.35 28	91.85 130	99.85 50	92.89 237	98.88 121	99.68 57

TDRefinement		91.06 303	89.68 308	95.21 284	85.35 360	91.49 290	98.51 162	97.07 309	91.47 275	88.83 332	97.84 207	77.31 335	99.09 187	92.79 238	77.98 349	95.04 338

ACMH+	92.99 14	94.30 249	93.77 250	95.88 265	97.81 203	92.04 279	98.71 126	98.37 189	93.99 177	90.60 317	98.47 145	80.86 311	99.05 190	92.75 239	92.40 259	96.55 290

cl-mvsnet____		94.51 238	94.01 232	96.02 256	97.58 218	93.40 257	97.05 297	97.96 259	91.73 269	92.76 282	97.08 266	89.06 189	98.13 295	92.61 240	90.29 284	96.52 296

cl-mvsnet1		94.52 237	94.03 229	95.99 257	97.57 222	93.38 258	97.05 297	97.94 260	91.74 267	92.81 280	97.10 260	89.12 186	98.07 301	92.60 241	90.30 283	96.53 293

DPM-MVS		97.55 87	96.99 100	99.23 42	99.04 107	98.55 26	97.17 292	98.35 193	94.85 145	97.93 107	98.58 135	95.07 72	99.71 114	92.60 241	99.34 104	99.43 106

test_post1							96.68 321				30.43 368	87.85 222	98.69 234	92.59 243

SCA		95.46 174	95.13 175	96.46 237	97.67 211	91.29 295	97.33 280	97.60 277	94.68 151	96.92 150	97.10 260	83.97 290	98.89 217	92.59 243	98.32 150	99.20 130

v148		94.29 250	93.76 252	95.91 262	96.10 305	92.93 269	98.58 148	97.97 257	92.59 240	93.47 261	96.95 284	88.53 204	98.32 278	92.56 245	87.06 325	96.49 302

PEN-MVS		94.42 243	93.73 254	96.49 232	96.28 298	94.84 201	99.17 35	99.00 27	93.51 205	92.23 299	97.83 211	86.10 253	97.90 313	92.55 246	86.92 327	96.74 264

Patchmatch-RL test		91.49 298	90.85 299	93.41 320	91.37 353	84.40 348	92.81 353	95.93 338	91.87 265	87.25 337	94.87 336	88.99 190	96.53 344	92.54 247	82.00 339	99.30 121

miper_lstm_enhance		94.33 247	94.07 228	95.11 288	97.75 205	90.97 299	97.22 287	98.03 254	91.67 271	92.76 282	96.97 280	90.03 168	97.78 319	92.51 248	89.64 291	96.56 288

IterMVS		94.09 264	93.85 244	94.80 299	97.99 192	90.35 309	97.18 290	98.12 233	93.68 198	92.46 295	97.34 246	84.05 288	97.41 328	92.51 248	91.33 270	96.62 280
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		94.11 262	93.87 242	94.85 296	97.98 194	90.56 307	97.18 290	98.11 236	93.75 188	92.58 288	97.48 238	83.97 290	97.41 328	92.48 250	91.30 271	96.58 284

tpm2		94.19 256	93.76 252	95.46 278	97.23 245	89.04 325	97.31 282	96.85 326	87.08 332	96.21 180	96.79 294	83.75 296	98.74 232	92.43 251	96.23 208	98.59 184

PVSNet_0	88.72 19	91.28 300	90.03 306	95.00 291	97.99 192	87.29 344	94.84 346	98.50 166	92.06 260	89.86 322	95.19 332	79.81 317	99.39 156	92.27 252	69.79 356	98.33 195

gg-mvs-nofinetune		92.21 294	90.58 301	97.13 182	96.75 277	95.09 189	95.85 334	89.40 364	85.43 343	94.50 212	81.98 358	80.80 312	98.40 275	92.16 253	98.33 149	97.88 208

pm-mvs1		93.94 270	93.06 274	96.59 221	96.49 290	95.16 184	98.95 74	98.03 254	92.32 251	91.08 312	97.84 207	84.54 279	98.41 269	92.16 253	86.13 334	96.19 316

K. test v3		92.55 291	91.91 293	94.48 308	95.64 319	89.24 321	99.07 51	94.88 347	94.04 172	86.78 339	97.59 230	77.64 334	97.64 322	92.08 255	89.43 297	96.57 286

GBi-Net		94.49 239	93.80 247	96.56 225	98.21 173	95.00 192	98.82 101	98.18 221	92.46 242	94.09 235	97.07 267	81.16 306	97.95 309	92.08 255	92.14 260	96.72 267

test1		94.49 239	93.80 247	96.56 225	98.21 173	95.00 192	98.82 101	98.18 221	92.46 242	94.09 235	97.07 267	81.16 306	97.95 309	92.08 255	92.14 260	96.72 267

FMVSNet3		94.97 208	94.26 217	97.11 184	98.18 178	96.62 118	98.56 154	98.26 212	93.67 200	94.09 235	97.10 260	84.25 283	98.01 305	92.08 255	92.14 260	96.70 271

PatchmatchNet		95.71 164	95.52 156	96.29 248	97.58 218	90.72 304	96.84 315	97.52 286	94.06 171	97.08 140	96.96 282	89.24 183	98.90 216	92.03 259	98.37 146	99.26 126
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
QAPM		96.29 140	95.40 158	98.96 67	97.85 201	97.60 80	99.23 23	98.93 37	89.76 314	93.11 274	99.02 80	89.11 187	99.93 15	91.99 260	99.62 66	99.34 112

新几何1				99.16 50	99.34 62	98.01 62		98.69 118	90.06 309	98.13 86	98.95 95	94.60 82	99.89 35	91.97 261	99.47 91	99.59 80

MDTV_nov1_ep13			95.40 158		97.48 227	88.34 335	96.85 314	97.29 301	93.74 190	97.48 132	97.26 251	89.18 184	99.05 190	91.92 262	97.43 176

EU-MVSNet		93.66 272	94.14 225	92.25 330	95.96 311	83.38 351	98.52 158	98.12 233	94.69 150	92.61 287	98.13 181	87.36 232	96.39 346	91.82 263	90.00 287	96.98 235

GA-MVS		94.81 217	94.03 229	97.14 181	97.15 254	93.86 237	96.76 318	97.58 278	94.00 176	94.76 206	97.04 273	80.91 309	98.48 254	91.79 264	96.25 207	99.09 146

PatchMatch-RL		96.59 129	96.03 139	98.27 109	99.31 70	96.51 126	97.91 237	99.06 22	93.72 192	96.92 150	98.06 185	88.50 205	99.65 124	91.77 265	99.00 116	98.66 180

v1144		94.59 231	93.92 238	96.60 220	96.21 299	94.78 207	98.59 146	98.14 231	91.86 266	94.21 230	97.02 275	87.97 217	98.41 269	91.72 266	89.57 292	96.61 281

v8		94.47 241	93.77 250	96.57 224	96.36 295	94.83 203	99.05 53	98.19 218	91.92 263	93.16 270	96.97 280	88.82 198	98.48 254	91.69 267	87.79 316	96.39 307

testdata2													99.89 35	91.65 268

BH-w/o		95.38 181	95.08 178	96.26 249	98.34 163	91.79 282	97.70 256	97.43 295	92.87 232	94.24 228	97.22 255	88.66 199	98.84 223	91.55 269	97.70 170	98.16 202

LF4IMVS		93.14 285	92.79 279	94.20 313	95.88 313	88.67 330	97.66 259	97.07 309	93.81 187	91.71 306	97.65 224	77.96 330	98.81 227	91.47 270	91.92 264	95.12 335

JIA-IIPM		93.35 277	92.49 284	95.92 261	96.48 291	90.65 305	95.01 342	96.96 316	85.93 339	96.08 183	87.33 355	87.70 225	98.78 230	91.35 271	95.58 217	98.34 194

FMVSNet2		94.47 241	93.61 260	97.04 187	98.21 173	96.43 130	98.79 112	98.27 208	92.46 242	93.50 260	97.09 264	81.16 306	98.00 307	91.09 272	91.93 263	96.70 271

v144192		94.39 245	93.70 256	96.48 233	96.06 307	94.35 225	98.58 148	98.16 228	91.45 276	94.33 223	97.02 275	87.50 229	98.45 258	91.08 273	89.11 301	96.63 279

tpmvs		94.60 229	94.36 213	95.33 282	97.46 229	88.60 331	96.88 312	97.68 271	91.29 285	93.80 249	96.42 309	88.58 200	99.24 166	91.06 274	96.04 213	98.17 201

LTVRE_ROB	92.95 15	94.60 229	93.90 240	96.68 212	97.41 237	94.42 221	98.52 158	98.59 142	91.69 270	91.21 310	98.35 158	84.87 272	99.04 193	91.06 274	93.44 247	96.60 282
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
PAPR		96.84 121	96.24 132	98.65 81	98.72 134	96.92 107	97.36 277	98.57 148	93.33 212	96.67 160	97.57 232	94.30 93	99.56 137	91.05 276	98.59 135	99.47 98

SixPastTwentyTwo		93.34 278	92.86 277	94.75 300	95.67 318	89.41 320	98.75 114	96.67 331	93.89 181	90.15 321	98.25 173	80.87 310	98.27 288	90.90 277	90.64 280	96.57 286

MVS_0304		92.81 288	92.01 290	95.23 283	97.46 229	91.33 293	98.17 213	98.81 76	91.13 292	93.80 249	95.68 329	66.08 357	98.06 302	90.79 278	96.13 211	96.32 312

COLMAP_ROB	93.27 12	95.33 187	94.87 188	96.71 208	99.29 78	93.24 263	98.58 148	98.11 236	89.92 311	93.57 255	99.10 69	86.37 249	99.79 92	90.78 279	98.10 155	97.09 229
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
pmmvs6		91.77 296	90.63 300	95.17 286	94.69 337	91.24 296	98.67 136	97.92 262	86.14 337	89.62 324	97.56 234	75.79 341	98.34 276	90.75 280	84.56 336	95.94 322

BH-RMVSNet		95.92 155	95.32 167	97.69 153	98.32 166	94.64 209	98.19 208	97.45 293	94.56 156	96.03 184	98.61 130	85.02 269	99.12 179	90.68 281	99.06 114	99.30 121

DTE-MVSNet		93.98 269	93.26 272	96.14 253	96.06 307	94.39 223	99.20 31	98.86 61	93.06 223	91.78 305	97.81 213	85.87 257	97.58 324	90.53 282	86.17 332	96.46 305

v10		94.29 250	93.55 262	96.51 231	96.39 294	94.80 205	98.99 66	98.19 218	91.35 281	93.02 276	96.99 278	88.09 214	98.41 269	90.50 283	88.41 310	96.33 311

ambc				89.49 335	86.66 358	75.78 358	92.66 354	96.72 328		86.55 341	92.50 349	46.01 362	97.90 313	90.32 284	82.09 338	94.80 342

lessismore_v0				94.45 311	94.93 333	88.44 334		91.03 362		86.77 340	97.64 226	76.23 339	98.42 262	90.31 285	85.64 335	96.51 299

v1192		94.32 248	93.58 261	96.53 229	96.10 305	94.45 219	98.50 163	98.17 226	91.54 274	94.19 231	97.06 270	86.95 239	98.43 261	90.14 286	89.57 292	96.70 271

MVS		94.67 226	93.54 263	98.08 125	96.88 270	96.56 124	98.19 208	98.50 166	78.05 353	92.69 285	98.02 187	91.07 151	99.63 129	90.09 287	98.36 148	98.04 204

ADS-MVSNet2		94.58 232	94.40 212	95.11 288	98.00 190	88.74 329	96.04 330	97.30 300	90.15 306	96.47 173	96.64 301	87.89 219	97.56 325	90.08 288	97.06 180	99.02 154

ADS-MVSNet		95.00 204	94.45 208	96.63 216	98.00 190	91.91 280	96.04 330	97.74 270	90.15 306	96.47 173	96.64 301	87.89 219	98.96 206	90.08 288	97.06 180	99.02 154

MSDG		95.93 154	95.30 169	97.83 139	98.90 117	95.36 177	96.83 316	98.37 189	91.32 283	94.43 218	98.73 119	90.27 165	99.60 132	90.05 290	98.82 126	98.52 187

v1921920		94.20 255	93.47 266	96.40 241	95.98 310	94.08 232	98.52 158	98.15 229	91.33 282	94.25 227	97.20 257	86.41 248	98.42 262	90.04 291	89.39 298	96.69 276

dp		94.15 259	93.90 240	94.90 294	97.31 241	86.82 346	96.97 301	97.19 306	91.22 289	96.02 185	96.61 303	85.51 262	99.02 197	90.00 292	94.30 221	98.85 166

CMPMVS	66.06 21	89.70 313	89.67 309	89.78 334	93.19 347	76.56 357	97.00 300	98.35 193	80.97 350	81.57 351	97.75 216	74.75 345	98.61 242	89.85 293	93.63 241	94.17 345
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
TR-MVS		94.94 211	94.20 219	97.17 180	97.75 205	94.14 231	97.59 263	97.02 314	92.28 254	95.75 189	97.64 226	83.88 292	98.96 206	89.77 294	96.15 210	98.40 191

MS-PatchMatch		93.84 271	93.63 259	94.46 310	96.18 301	89.45 318	97.76 252	98.27 208	92.23 255	92.13 301	97.49 237	79.50 318	98.69 234	89.75 295	99.38 102	95.25 332

ITE_SJBPF				95.44 279	97.42 234	91.32 294		97.50 288	95.09 135	93.59 253	98.35 158	81.70 304	98.88 219	89.71 296	93.39 248	96.12 317

MVP-Stereo		94.28 252	93.92 238	95.35 281	94.95 332	92.60 272	97.97 232	97.65 273	91.61 273	90.68 316	97.09 264	86.32 250	98.42 262	89.70 297	99.34 104	95.02 339
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
AllTest		95.24 191	94.65 196	96.99 189	99.25 86	93.21 264	98.59 146	98.18 221	91.36 279	93.52 257	98.77 115	84.67 276	99.72 109	89.70 297	97.87 162	98.02 205

TestCases				96.99 189	99.25 86	93.21 264		98.18 221	91.36 279	93.52 257	98.77 115	84.67 276	99.72 109	89.70 297	97.87 162	98.02 205

GG-mvs-BLEND				96.59 221	96.34 296	94.98 195	96.51 326	88.58 365		93.10 275	94.34 342	80.34 315	98.05 303	89.53 300	96.99 182	96.74 264

USDC		93.33 279	92.71 280	95.21 284	96.83 273	90.83 301	96.91 306	97.50 288	93.84 184	90.72 315	98.14 180	77.69 331	98.82 226	89.51 301	93.21 252	95.97 321

v7n		94.19 256	93.43 267	96.47 234	95.90 312	94.38 224	99.26 20	98.34 195	91.99 261	92.76 282	97.13 259	88.31 207	98.52 252	89.48 302	87.70 317	96.52 296

PM-MVS		87.77 320	86.55 324	91.40 333	91.03 355	83.36 352	96.92 304	95.18 345	91.28 286	86.48 342	93.42 345	53.27 361	96.74 338	89.43 303	81.97 340	94.11 346

FMVSNet1		93.19 284	92.07 289	96.56 225	97.54 223	95.00 192	98.82 101	98.18 221	90.38 303	92.27 298	97.07 267	73.68 349	97.95 309	89.36 304	91.30 271	96.72 267

tpm cat1		93.36 276	92.80 278	95.07 290	97.58 218	87.97 339	96.76 318	97.86 265	82.17 349	93.53 256	96.04 320	86.13 252	99.13 178	89.24 305	95.87 214	98.10 203

UnsupCasMVSNet_eth		90.99 304	89.92 307	94.19 314	94.08 341	89.83 312	97.13 295	98.67 129	93.69 196	85.83 344	96.19 317	75.15 343	96.74 338	89.14 306	79.41 347	96.00 320

v1240		94.06 267	93.29 271	96.34 245	96.03 309	93.90 236	98.44 170	98.17 226	91.18 291	94.13 234	97.01 277	86.05 254	98.42 262	89.13 307	89.50 296	96.70 271

tmp_tt		68.90 330	66.97 332	74.68 345	50.78 370	59.95 366	87.13 358	83.47 368	38.80 365	62.21 361	96.23 314	64.70 358	76.91 366	88.91 308	30.49 364	87.19 356

pmmvs-eth3d		90.36 309	89.05 314	94.32 312	91.10 354	92.12 275	97.63 262	96.95 317	88.86 324	84.91 347	93.13 346	78.32 325	96.74 338	88.70 309	81.81 341	94.09 347

thres600view7		95.49 173	94.77 190	97.67 155	98.98 113	95.02 191	98.85 94	96.90 320	95.38 115	96.63 162	96.90 287	84.29 281	99.59 133	88.65 310	96.33 200	98.40 191

thres100view900		95.38 181	94.70 194	97.41 169	98.98 113	94.92 199	98.87 91	96.90 320	95.38 115	96.61 163	96.88 288	84.29 281	99.56 137	88.11 311	96.29 202	97.76 211

tfpn200view9		95.32 188	94.62 197	97.43 168	98.94 115	94.98 195	98.68 133	96.93 318	95.33 118	96.55 167	96.53 304	84.23 284	99.56 137	88.11 311	96.29 202	97.76 211

thres400		95.38 181	94.62 197	97.65 158	98.94 115	94.98 195	98.68 133	96.93 318	95.33 118	96.55 167	96.53 304	84.23 284	99.56 137	88.11 311	96.29 202	98.40 191

our_test_3		93.65 274	93.30 270	94.69 301	95.45 326	89.68 316	96.91 306	97.65 273	91.97 262	91.66 307	96.88 288	89.67 174	97.93 312	88.02 314	91.49 268	96.48 303

thres200		95.25 190	94.57 199	97.28 174	98.81 126	94.92 199	98.20 204	97.11 307	95.24 126	96.54 169	96.22 316	84.58 278	99.53 143	87.93 315	96.50 196	97.39 222

EG-PatchMatch MVS		91.13 302	90.12 305	94.17 315	94.73 336	89.00 326	98.13 217	97.81 266	89.22 322	85.32 346	96.46 306	67.71 354	98.42 262	87.89 316	93.82 238	95.08 337

CR-MVSNet		94.76 220	94.15 224	96.59 221	97.00 261	93.43 254	94.96 343	97.56 279	92.46 242	96.93 148	96.24 312	88.15 212	97.88 317	87.38 317	96.65 190	98.46 189

Patchmtry		93.22 282	92.35 286	95.84 266	96.77 274	93.09 268	94.66 348	97.56 279	87.37 331	92.90 278	96.24 312	88.15 212	97.90 313	87.37 318	90.10 286	96.53 293

test0.0.03 1		94.08 265	93.51 264	95.80 267	95.53 323	92.89 270	97.38 273	95.97 336	95.11 132	92.51 292	96.66 298	87.71 223	96.94 335	87.03 319	93.67 239	97.57 218

TinyColmap		92.31 293	91.53 294	94.65 303	96.92 266	89.75 313	96.92 304	96.68 330	90.45 301	89.62 324	97.85 206	76.06 340	98.81 227	86.74 320	92.51 258	95.41 330

MIMVSNet		93.26 281	92.21 288	96.41 240	97.73 209	93.13 266	95.65 338	97.03 312	91.27 287	94.04 238	96.06 319	75.33 342	97.19 331	86.56 321	96.23 208	98.92 164

TransMVSNet (Re)		92.67 290	91.51 295	96.15 252	96.58 285	94.65 208	98.90 82	96.73 327	90.86 295	89.46 327	97.86 204	85.62 260	98.09 299	86.45 322	81.12 343	95.71 326

DSMNet-mixed		92.52 292	92.58 283	92.33 329	94.15 340	82.65 353	98.30 192	94.26 354	89.08 323	92.65 286	95.73 324	85.01 270	95.76 348	86.24 323	97.76 167	98.59 184

testgi		93.06 286	92.45 285	94.88 295	96.43 293	89.90 311	98.75 114	97.54 285	95.60 103	91.63 308	97.91 198	74.46 347	97.02 333	86.10 324	93.67 239	97.72 215

YYNet1		90.70 307	89.39 310	94.62 304	94.79 335	90.65 305	97.20 288	97.46 291	87.54 330	72.54 357	95.74 323	86.51 244	96.66 342	86.00 325	86.76 330	96.54 291

MDA-MVSNet_test_wron		90.71 306	89.38 311	94.68 302	94.83 334	90.78 303	97.19 289	97.46 291	87.60 329	72.41 358	95.72 326	86.51 244	96.71 341	85.92 326	86.80 329	96.56 288

UnsupCasMVSNet_bld		87.17 321	85.12 325	93.31 323	91.94 351	88.77 328	94.92 345	98.30 205	84.30 346	82.30 350	90.04 352	63.96 359	97.25 330	85.85 327	74.47 355	93.93 350

EPNet_dtu		95.21 193	94.95 185	95.99 257	96.17 302	90.45 308	98.16 214	97.27 303	96.77 55	93.14 273	98.33 163	90.34 163	98.42 262	85.57 328	98.81 127	99.09 146
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		91.81 295	90.92 298	94.49 307	97.21 247	92.09 276	98.00 230	97.55 284	89.31 321	90.86 314	95.61 330	74.48 346	95.32 351	85.57 328	89.70 290	96.07 319

tfpnnormal		93.66 272	92.70 281	96.55 228	96.94 265	95.94 153	98.97 70	99.19 15	91.04 293	91.38 309	97.34 246	84.94 271	98.61 242	85.45 330	89.02 304	95.11 336

Patchmatch-test		94.42 243	93.68 258	96.63 216	97.60 216	91.76 283	94.83 347	97.49 290	89.45 319	94.14 233	97.10 260	88.99 190	98.83 225	85.37 331	98.13 154	99.29 123

ppachtmachnet_test		93.22 282	92.63 282	94.97 292	95.45 326	90.84 300	96.88 312	97.88 264	90.60 297	92.08 302	97.26 251	88.08 215	97.86 318	85.12 332	90.33 282	96.22 314

KD-MVS_2432*1600		89.61 315	87.96 319	94.54 305	94.06 342	91.59 288	95.59 339	97.63 275	89.87 312	88.95 330	94.38 340	78.28 326	96.82 336	84.83 333	68.05 357	95.21 333

miper_refine_blended		89.61 315	87.96 319	94.54 305	94.06 342	91.59 288	95.59 339	97.63 275	89.87 312	88.95 330	94.38 340	78.28 326	96.82 336	84.83 333	68.05 357	95.21 333

PCF-MVS	93.45 11	94.68 223	93.43 267	98.42 101	98.62 143	96.77 114	95.48 341	98.20 217	84.63 345	93.34 265	98.32 164	88.55 203	99.81 71	84.80 335	98.96 117	98.68 177
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_method		79.03 324	78.17 327	81.63 341	86.06 359	54.40 369	82.75 361	96.89 322	39.54 364	80.98 352	95.57 331	58.37 360	94.73 354	84.74 336	78.61 348	95.75 325

DIV-MVS_2432*1600		90.38 308	89.38 311	93.40 321	92.85 349	88.94 327	97.95 233	97.94 260	90.35 304	90.25 319	93.96 343	79.82 316	95.94 347	84.62 337	76.69 351	95.33 331

Anonymous20240521		91.18 301	90.44 302	93.42 319	93.70 345	88.47 333	98.94 77	97.56 279	88.46 326	89.56 326	95.08 335	77.15 337	96.97 334	83.92 338	89.55 294	94.82 341

MDA-MVSNet-bldmvs		89.97 312	88.35 317	94.83 298	95.21 329	91.34 291	97.64 260	97.51 287	88.36 327	71.17 359	96.13 318	79.22 320	96.63 343	83.65 339	86.27 331	96.52 296

MVS-HIRNet		89.46 317	88.40 316	92.64 327	97.58 218	82.15 354	94.16 352	93.05 360	75.73 355	90.90 313	82.52 357	79.42 319	98.33 277	83.53 340	98.68 129	97.43 219

new-patchmatchnet		88.50 319	87.45 322	91.67 332	90.31 356	85.89 347	97.16 293	97.33 299	89.47 318	83.63 349	92.77 347	76.38 338	95.06 353	82.70 341	77.29 350	94.06 348

PAPM		94.95 209	94.00 233	97.78 144	97.04 260	95.65 166	96.03 332	98.25 213	91.23 288	94.19 231	97.80 214	91.27 146	98.86 222	82.61 342	97.61 172	98.84 168

LCM-MVSNet		78.70 325	76.24 330	86.08 337	77.26 366	71.99 361	94.34 350	96.72 328	61.62 359	76.53 354	89.33 353	33.91 368	92.78 358	81.85 343	74.60 354	93.46 351

new_pmnet		90.06 311	89.00 315	93.22 325	94.18 339	88.32 336	96.42 328	96.89 322	86.19 336	85.67 345	93.62 344	77.18 336	97.10 332	81.61 344	89.29 299	94.23 344

pmmvs3		86.67 323	84.86 326	92.11 331	88.16 357	87.19 345	96.63 322	94.75 349	79.88 351	87.22 338	92.75 348	66.56 356	95.20 352	81.24 345	76.56 352	93.96 349

CL-MVSNet_2432*1600		90.11 310	89.14 313	93.02 326	91.86 352	88.23 337	96.51 326	98.07 247	90.49 298	90.49 318	94.41 338	84.75 275	95.34 350	80.79 346	74.95 353	95.50 329

N_pmnet		87.12 322	87.77 321	85.17 339	95.46 325	61.92 364	97.37 275	70.66 370	85.83 340	88.73 333	96.04 320	85.33 267	97.76 320	80.02 347	90.48 281	95.84 323

TAPA-MVS	93.98 7	95.35 185	94.56 200	97.74 148	99.13 102	94.83 203	98.33 184	98.64 137	86.62 333	96.29 178	98.61 130	94.00 98	99.29 162	80.00 348	99.41 99	99.09 146
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DeepMVS_CX				86.78 336	97.09 258	72.30 360		95.17 346	75.92 354	84.34 348	95.19 332	70.58 352	95.35 349	79.98 349	89.04 303	92.68 353

Anonymous20231206		91.66 297	91.10 297	93.33 322	94.02 344	87.35 343	98.58 148	97.26 304	90.48 299	90.16 320	96.31 310	83.83 294	96.53 344	79.36 350	89.90 288	96.12 317

test20.03		90.89 305	90.38 303	92.43 328	93.48 346	88.14 338	98.33 184	97.56 279	93.40 210	87.96 335	96.71 297	80.69 313	94.13 356	79.15 351	86.17 332	95.01 340

PatchT		93.06 286	91.97 291	96.35 244	96.69 280	92.67 271	94.48 349	97.08 308	86.62 333	97.08 140	92.23 350	87.94 218	97.90 313	78.89 352	96.69 188	98.49 188

MIMVSNet1		89.67 314	88.28 318	93.82 316	92.81 350	91.08 298	98.01 228	97.45 293	87.95 328	87.90 336	95.87 322	67.63 355	94.56 355	78.73 353	88.18 313	95.83 324

test_0402		91.32 299	90.27 304	94.48 308	96.60 284	91.12 297	98.50 163	97.22 305	86.10 338	88.30 334	96.98 279	77.65 333	97.99 308	78.13 354	92.94 255	94.34 343

OpenMVS_ROB	86.42 20	89.00 318	87.43 323	93.69 317	93.08 348	89.42 319	97.91 237	96.89 322	78.58 352	85.86 343	94.69 337	69.48 353	98.29 285	77.13 355	93.29 251	93.36 352

RPMNet		92.81 288	91.34 296	97.24 175	97.00 261	93.43 254	94.96 343	98.80 87	82.27 348	96.93 148	92.12 351	86.98 238	99.82 64	76.32 356	96.65 190	98.46 189

PMMVS2		77.95 327	75.44 331	85.46 338	82.54 361	74.95 359	94.23 351	93.08 359	72.80 356	74.68 355	87.38 354	36.36 367	91.56 359	73.95 357	63.94 359	89.87 354

FPMVS		77.62 328	77.14 328	79.05 343	79.25 364	60.97 365	95.79 335	95.94 337	65.96 357	67.93 360	94.40 339	37.73 366	88.88 361	68.83 358	88.46 309	87.29 355

Gipuma		78.40 326	76.75 329	83.38 340	95.54 322	80.43 356	79.42 362	97.40 297	64.67 358	73.46 356	80.82 359	45.65 363	93.14 357	66.32 359	87.43 320	76.56 360
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ANet_high		69.08 329	65.37 333	80.22 342	65.99 368	71.96 362	90.91 357	90.09 363	82.62 347	49.93 365	78.39 360	29.36 369	81.75 362	62.49 360	38.52 363	86.95 357

PMVS	61.03 23	65.95 331	63.57 335	73.09 346	57.90 369	51.22 370	85.05 360	93.93 358	54.45 360	44.32 366	83.57 356	13.22 370	89.15 360	58.68 361	81.00 344	78.91 359
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	62.14 22	63.28 334	59.38 337	74.99 344	74.33 367	65.47 363	85.55 359	80.50 369	52.02 362	51.10 364	75.00 363	10.91 373	80.50 363	51.60 362	53.40 360	78.99 358
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		64.94 332	64.25 334	67.02 347	82.28 362	59.36 367	91.83 356	85.63 366	52.69 361	60.22 362	77.28 361	41.06 365	80.12 364	46.15 363	41.14 361	61.57 362

EMVS		64.07 333	63.26 336	66.53 348	81.73 363	58.81 368	91.85 355	84.75 367	51.93 363	59.09 363	75.13 362	43.32 364	79.09 365	42.03 364	39.47 362	61.69 361

wuyk23d		30.17 335	30.18 339	30.16 349	78.61 365	43.29 371	66.79 363	14.21 371	17.31 366	14.82 369	11.93 369	11.55 372	41.43 367	37.08 365	19.30 365	5.76 365

test123		20.95 338	23.72 341	12.64 350	13.54 372	8.19 372	96.55 325	6.13 373	7.48 368	16.74 368	37.98 366	12.97 371	6.05 368	16.69 366	5.43 367	23.68 363

testmvs		21.48 337	24.95 340	11.09 351	14.89 371	6.47 373	96.56 324	9.87 372	7.55 367	17.93 367	39.02 365	9.43 374	5.90 369	16.56 367	12.72 366	20.91 364

uanet_test		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

cdsmvs_eth3d_5k		23.98 336	31.98 338	0.00 352	0.00 373	0.00 374	0.00 364	98.59 142	0.00 369	0.00 370	98.61 130	90.60 159	0.00 370	0.00 368	0.00 368	0.00 366

pcd_1.5k_mvsjas		7.88 340	10.50 343	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	94.51 85	0.00 370	0.00 368	0.00 368	0.00 366

sosnet-low-res		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

sosnet		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

uncertanet		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

Regformer		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

ab-mvs-re		8.20 339	10.94 342	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	98.43 148	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

uanet		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

eth-test2					0.00 373

eth-test					0.00 373

test_241102_ONE					99.71 20	99.24 4		98.87 55	97.62 11	99.73 1	99.39 14	97.53 4	99.74 107

save fliter					99.46 51	98.38 35	98.21 201	98.71 114	97.95 3

test0726					99.72 12	99.25 2	99.06 52	98.88 49	97.62 11	99.56 5	99.50 4	97.42 6

GSMVS																99.20 130

test_part2					99.63 29	99.18 8				99.27 17

sam_mvs1												89.45 177				99.20 130

sam_mvs												88.99 190

MTGPA								98.74 104

test_post											31.83 367	88.83 197	98.91 213

patchmatchnet-post											95.10 334	89.42 178	98.89 217

MTMP							98.89 86	94.14 356

TEST9					99.31 70	98.50 29	97.92 235	98.73 108	92.63 237	97.74 116	98.68 124	96.20 23	99.80 80

test_8					99.29 78	98.44 31	97.89 241	98.72 110	92.98 226	97.70 119	98.66 127	96.20 23	99.80 80

agg_prior					99.30 75	98.38 35		98.72 110		97.57 129			99.81 71

test_prior4						98.01 62	97.86 244

test_prior				99.19 43	99.31 70	98.22 50		98.84 65					99.70 115			99.65 67

新几何2							97.64 260

旧先验1					99.29 78	97.48 83		98.70 117			99.09 74	95.56 47			99.47 91	99.61 75

原ACMM2							97.67 258

test222					99.23 93	97.17 100	97.40 271	98.66 132	88.68 325	98.05 90	98.96 93	94.14 95			99.53 85	99.61 75

segment_acmp												96.85 11

testdata1							97.32 281		96.34 74

test12				99.18 47	99.16 99	98.19 52		98.53 156		98.07 89		95.13 70	99.72 109		99.56 80	99.63 73

plane_prior7					97.42 234	94.63 210

plane_prior6					97.35 239	94.61 213						87.09 235

plane_prior4											98.28 168

plane_prior3						94.61 213			97.02 49	95.34 191

plane_prior2							98.80 108		97.28 31

plane_prior1					97.37 238

plane_prior						94.60 215	98.44 170		96.74 57						94.22 224

n2								0.00 374

nn								0.00 374

door-mid								94.37 352

test11								98.66 132

door								94.64 350

HQP5-MVS						94.25 229

HQP-NCC					97.20 248		98.05 224		96.43 70	94.45 214

ACMP_Plane					97.20 248		98.05 224		96.43 70	94.45 214

HQP4-MVS										94.45 214			98.96 206			96.87 251

HQP3-MVS								98.46 171							94.18 226

HQP2-MVS												86.75 241

NP-MVS					97.28 242	94.51 218					97.73 217

ACMMP++_ref															92.97 254

ACMMP++															93.61 242

Test By Simon												94.64 80

High-resolution multi-view benchmark