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 26	98.81 28	93.86 31	99.07 2	98.98 6	97.01 13	98.92 4	98.78 14	95.22 40	98.61 170	96.85 3	99.77 9	99.31 28
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 4	97.93 2	99.02 12	95.95 8	98.61 3	98.81 8	97.41 10	97.28 56	98.46 30	94.62 62	98.84 129	94.64 34	99.53 38	98.99 56

DVP-MVS++		95.93 52	96.34 34	94.70 112	96.54 179	86.66 154	98.45 4	98.22 36	93.26 71	97.54 40	97.36 94	93.12 95	99.38 55	93.88 48	98.68 155	98.04 156

FOURS1					99.21 3	94.68 12	98.45 4	98.81 8	97.73 6	98.27 20

UA-Net		97.35 4	97.24 11	97.69 4	98.22 74	93.87 30	98.42 6	98.19 39	96.95 14	95.46 144	99.23 4	93.45 82	99.57 14	95.34 30	99.89 2	99.63 9

OurMVSNet-221017-0		96.80 12	96.75 17	96.96 35	99.03 11	91.85 57	97.98 7	98.01 72	94.15 51	98.93 3	99.07 5	88.07 188	99.57 14	95.86 15	99.69 14	99.46 18

UniMVSNet_ETH3D		97.13 5	97.72 3	95.35 84	99.51 2	87.38 134	97.70 8	97.54 112	98.16 2	98.94 2	99.33 2	97.84 4	99.08 94	90.73 141	99.73 13	99.59 13

tt0805		95.42 76	95.93 57	93.86 152	98.75 32	88.47 117	97.68 9	94.29 270	96.48 21	95.38 147	93.63 283	94.89 55	97.94 234	95.38 28	96.92 269	95.17 302

HPM-MVS		96.81 11	96.62 22	97.36 23	98.89 20	93.53 38	97.51 10	98.44 16	92.35 88	95.95 116	96.41 162	96.71 8	99.42 33	93.99 47	99.36 60	99.13 41
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RRT_MVS		95.41 77	95.20 92	96.05 55	98.86 22	88.92 104	97.49 11	94.48 266	93.12 73	97.94 27	98.54 25	81.19 271	99.63 6	95.48 24	99.69 14	99.60 12

EPP-MVSNet		93.91 137	93.68 144	94.59 122	98.08 82	85.55 185	97.44 12	94.03 275	94.22 50	94.94 171	96.19 181	82.07 260	99.57 14	87.28 227	98.89 126	98.65 107

LS3D		96.11 47	95.83 63	96.95 36	94.75 276	94.20 19	97.34 13	97.98 75	97.31 11	95.32 152	96.77 139	93.08 97	99.20 80	91.79 117	98.16 206	97.44 214

HPM-MVS_fast		97.01 6	96.89 14	97.39 21	99.12 8	93.92 28	97.16 14	98.17 45	93.11 74	96.48 90	97.36 94	96.92 6	99.34 63	94.31 40	99.38 59	98.92 72

MVSFormer		92.18 189	92.23 181	92.04 220	94.74 277	80.06 258	97.15 15	97.37 123	88.98 174	88.83 319	92.79 304	77.02 304	99.60 9	96.41 9	96.75 276	96.46 259

test_djsdf		96.62 23	96.49 26	97.01 32	98.55 45	91.77 59	97.15 15	97.37 123	88.98 174	98.26 22	98.86 10	93.35 87	99.60 9	96.41 9	99.45 47	99.66 6

mvsmamba		95.61 65	95.40 81	96.22 51	98.44 60	89.86 84	97.14 17	97.45 120	91.25 128	97.49 44	98.14 39	83.49 241	99.45 27	95.52 22	99.66 21	99.36 24

IS-MVSNet		94.49 112	94.35 123	94.92 102	98.25 73	86.46 159	97.13 18	94.31 269	96.24 25	96.28 101	96.36 170	82.88 249	99.35 60	88.19 207	99.52 41	98.96 64

Anonymous20231211		96.60 25	97.13 12	95.00 100	97.46 130	86.35 164	97.11 19	98.24 34	97.58 8	98.72 8	98.97 7	93.15 94	99.15 84	93.18 80	99.74 12	99.50 17

anonymousdsp		96.74 17	96.42 29	97.68 6	98.00 91	94.03 25	96.97 20	97.61 107	87.68 205	98.45 18	98.77 15	94.20 72	99.50 21	96.70 5	99.40 57	99.53 15

ACMMP		96.61 24	96.34 34	97.43 18	98.61 38	93.88 29	96.95 21	98.18 41	92.26 91	96.33 95	96.84 137	95.10 46	99.40 46	93.47 65	99.33 66	99.02 53
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 21	95.93 62	97.68 116	89.38 95	96.90 22	98.41 19	92.52 83	97.43 48	97.92 58	95.11 45	99.50 21	94.45 36	99.30 71	98.92 72
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
EGC-MVSNET		80.97 350	75.73 363	96.67 42	98.85 24	94.55 15	96.83 23	96.60 184	2.44 399	5.32 400	98.25 37	92.24 115	98.02 226	91.85 115	99.21 90	97.45 212

v7n		96.82 9	97.31 10	95.33 86	98.54 48	86.81 148	96.83 23	98.07 60	96.59 20	98.46 17	98.43 32	92.91 102	99.52 19	96.25 12	99.76 10	99.65 8

CP-MVS		96.44 34	96.08 49	97.54 11	98.29 68	94.62 14	96.80 25	98.08 57	92.67 81	95.08 167	96.39 167	94.77 58	99.42 33	93.17 81	99.44 50	98.58 119

COLMAP_ROB	91.06 5	96.75 16	96.62 22	97.13 28	98.38 63	94.31 17	96.79 26	98.32 24	96.69 17	96.86 75	97.56 76	95.48 27	98.77 146	90.11 164	99.44 50	98.31 135
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 25	97.05 13	95.24 92	99.02 12	86.44 160	96.78 27	98.08 57	97.42 9	98.48 16	97.86 62	91.76 128	99.63 6	94.23 42	99.84 3	99.66 6

FE-MVS		89.06 259	88.29 266	91.36 242	94.78 274	79.57 273	96.77 28	90.99 324	84.87 254	92.96 236	96.29 174	60.69 378	98.80 139	80.18 309	97.11 260	95.71 289

CS-MVS		95.77 59	95.58 73	96.37 50	96.84 160	91.72 61	96.73 29	99.06 5	94.23 49	92.48 252	94.79 245	93.56 79	99.49 24	93.47 65	99.05 106	97.89 176

pmmvs6		96.80 12	97.36 9	95.15 97	99.12 8	87.82 129	96.68 30	97.86 85	96.10 27	98.14 24	99.28 3	97.94 3	98.21 209	91.38 129	99.69 14	99.42 19

3Dnovator	92.54 3	94.80 101	94.90 101	94.47 129	95.47 254	87.06 142	96.63 31	97.28 137	91.82 110	94.34 191	97.41 88	90.60 158	98.65 167	92.47 100	98.11 210	97.70 196

PS-CasMVS		96.69 20	97.43 5	94.49 128	99.13 6	84.09 205	96.61 32	97.97 77	97.91 5	98.64 13	98.13 41	95.24 38	99.65 3	93.39 72	99.84 3	99.72 2

mvs_tets		96.83 8	96.71 18	97.17 27	98.83 25	92.51 48	96.58 33	97.61 107	87.57 207	98.80 7	98.90 9	96.50 9	99.59 13	96.15 13	99.47 43	99.40 21

PEN-MVS		96.69 20	97.39 8	94.61 118	99.16 4	84.50 195	96.54 34	98.05 64	98.06 4	98.64 13	98.25 37	95.01 51	99.65 3	92.95 89	99.83 5	99.68 4

DTE-MVSNet		96.74 17	97.43 5	94.67 113	99.13 6	84.68 194	96.51 35	97.94 83	98.14 3	98.67 12	98.32 34	95.04 48	99.69 2	93.27 77	99.82 7	99.62 10

XVS		96.49 29	96.18 42	97.44 16	98.56 42	93.99 26	96.50 36	97.95 80	94.58 43	94.38 189	96.49 157	94.56 64	99.39 49	93.57 58	99.05 106	98.93 68

X-MVStestdata		90.70 214	88.45 261	97.44 16	98.56 42	93.99 26	96.50 36	97.95 80	94.58 43	94.38 189	26.89 397	94.56 64	99.39 49	93.57 58	99.05 106	98.93 68

EC-MVSNet		95.44 72	95.62 71	94.89 103	96.93 154	87.69 131	96.48 38	99.14 4	93.93 56	92.77 243	94.52 255	93.95 76	99.49 24	93.62 57	99.22 89	97.51 209

mPP-MVS		96.46 31	96.05 51	97.69 4	98.62 36	94.65 13	96.45 39	97.74 98	92.59 82	95.47 142	96.68 149	94.50 66	99.42 33	93.10 83	99.26 82	98.99 56

QAPM		92.88 166	92.77 167	93.22 176	95.82 236	83.31 212	96.45 39	97.35 129	83.91 264	93.75 206	96.77 139	89.25 177	98.88 121	84.56 268	97.02 263	97.49 210

jajsoiax		96.59 27	96.42 29	97.12 29	98.76 31	92.49 49	96.44 41	97.42 121	86.96 216	98.71 10	98.72 17	95.36 32	99.56 17	95.92 14	99.45 47	99.32 27

Gipuma		95.31 84	95.80 65	93.81 155	97.99 94	90.91 70	96.42 42	97.95 80	96.69 17	91.78 272	98.85 12	91.77 126	95.49 336	91.72 119	99.08 102	95.02 308
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MSP-MVS		95.34 80	94.63 115	97.48 14	98.67 33	94.05 23	96.41 43	98.18 41	91.26 126	95.12 163	95.15 228	86.60 217	99.50 21	93.43 71	96.81 273	98.89 75
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
SR-MVS-dyc-post		96.84 7	96.60 24	97.56 10	98.07 83	95.27 9	96.37 44	98.12 51	95.66 33	97.00 68	97.03 123	94.85 56	99.42 33	93.49 62	98.84 133	98.00 161

RE-MVS-def			96.66 19		98.07 83	95.27 9	96.37 44	98.12 51	95.66 33	97.00 68	97.03 123	95.40 29		93.49 62	98.84 133	98.00 161

TSAR-MVS + MP.		94.96 95	94.75 107	95.57 78	98.86 22	88.69 108	96.37 44	96.81 171	85.23 244	94.75 179	97.12 116	91.85 124	99.40 46	93.45 67	98.33 189	98.62 116
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		95.32 81	95.10 96	95.96 58	96.86 158	90.75 74	96.33 47	99.20 2	93.99 53	91.03 285	93.73 281	93.52 81	99.55 18	91.81 116	99.45 47	97.58 203

ACMH	88.36 12	96.59 27	97.43 5	94.07 141	98.56 42	85.33 188	96.33 47	98.30 27	94.66 42	98.72 8	98.30 35	97.51 5	98.00 228	94.87 31	99.59 28	98.86 78
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
region2R		96.41 36	96.09 47	97.38 22	98.62 36	93.81 35	96.32 49	97.96 78	92.26 91	95.28 155	96.57 155	95.02 50	99.41 39	93.63 56	99.11 101	98.94 66

testf1		96.77 14	96.49 26	97.60 8	99.01 14	96.70 3	96.31 50	98.33 22	94.96 38	97.30 54	97.93 55	96.05 16	97.90 235	89.32 180	99.23 86	98.19 144

APD_test2		96.77 14	96.49 26	97.60 8	99.01 14	96.70 3	96.31 50	98.33 22	94.96 38	97.30 54	97.93 55	96.05 16	97.90 235	89.32 180	99.23 86	98.19 144

APD-MVS_3200maxsize		96.82 9	96.65 20	97.32 25	97.95 95	93.82 33	96.31 50	98.25 31	95.51 35	96.99 70	97.05 122	95.63 23	99.39 49	93.31 74	98.88 128	98.75 92

CP-MVSNet		96.19 45	96.80 16	94.38 133	98.99 16	83.82 208	96.31 50	97.53 114	97.60 7	98.34 19	97.52 81	91.98 122	99.63 6	93.08 85	99.81 8	99.70 3

HFP-MVS		96.39 38	96.17 44	97.04 31	98.51 51	93.37 39	96.30 54	97.98 75	92.35 88	95.63 134	96.47 158	95.37 30	99.27 74	93.78 52	99.14 99	98.48 125

ACMMPR		96.46 31	96.14 45	97.41 20	98.60 39	93.82 33	96.30 54	97.96 78	92.35 88	95.57 137	96.61 153	94.93 54	99.41 39	93.78 52	99.15 98	99.00 54

3Dnovator+	92.74 2	95.86 57	95.77 66	96.13 53	96.81 163	90.79 73	96.30 54	97.82 90	96.13 26	94.74 180	97.23 106	91.33 135	99.16 83	93.25 78	98.30 192	98.46 126

MIMVSNet1		95.52 69	95.45 77	95.72 73	99.14 5	89.02 102	96.23 57	96.87 167	93.73 60	97.87 28	98.49 29	90.73 155	99.05 99	86.43 243	99.60 26	99.10 47

test2506		85.42 317	84.57 320	87.96 325	97.81 103	66.53 379	96.14 58	56.35 402	89.04 172	93.55 213	98.10 42	42.88 402	98.68 163	88.09 211	99.18 94	98.67 105

SR-MVS		96.70 19	96.42 29	97.54 11	98.05 85	94.69 11	96.13 59	98.07 60	95.17 37	96.82 77	96.73 146	95.09 47	99.43 32	92.99 88	98.71 151	98.50 122

MP-MVS		96.14 46	95.68 69	97.51 13	98.81 28	94.06 21	96.10 60	97.78 96	92.73 78	93.48 214	96.72 147	94.23 71	99.42 33	91.99 110	99.29 74	99.05 51
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		96.42 35	96.20 41	97.07 30	98.80 30	92.79 46	96.08 61	98.16 48	91.74 115	95.34 151	96.36 170	95.68 21	99.44 29	94.41 38	99.28 79	98.97 62

FA-MVS(test-final)		91.81 194	91.85 192	91.68 231	94.95 267	79.99 262	96.00 62	93.44 287	87.80 200	94.02 199	97.29 102	77.60 295	98.45 189	88.04 213	97.49 245	96.61 251

GBi-Net		93.21 156	92.96 162	93.97 144	95.40 256	84.29 198	95.99 63	96.56 188	88.63 182	95.10 164	98.53 26	81.31 267	98.98 107	86.74 233	98.38 183	98.65 107

test1		93.21 156	92.96 162	93.97 144	95.40 256	84.29 198	95.99 63	96.56 188	88.63 182	95.10 164	98.53 26	81.31 267	98.98 107	86.74 233	98.38 183	98.65 107

FMVSNet1		94.84 99	95.13 94	93.97 144	97.60 120	84.29 198	95.99 63	96.56 188	92.38 85	97.03 67	98.53 26	90.12 166	98.98 107	88.78 199	99.16 97	98.65 107

RPSCF		95.58 68	94.89 102	97.62 7	97.58 122	96.30 7	95.97 66	97.53 114	92.42 84	93.41 215	97.78 63	91.21 140	97.77 253	91.06 132	97.06 261	98.80 86

SixPastTwentyTwo		94.91 96	95.21 90	93.98 143	98.52 50	83.19 217	95.93 67	94.84 256	94.86 41	98.49 15	98.74 16	81.45 265	99.60 9	94.69 33	99.39 58	99.15 39

ambc				92.98 180	96.88 156	83.01 221	95.92 68	96.38 198		96.41 92	97.48 86	88.26 184	97.80 248	89.96 169	98.93 125	98.12 151

FC-MVSNet-test		95.32 81	95.88 59	93.62 159	98.49 58	81.77 234	95.90 69	98.32 24	93.93 56	97.53 42	97.56 76	88.48 181	99.40 46	92.91 90	99.83 5	99.68 4

MTAPA		96.65 22	96.38 33	97.47 15	98.95 18	94.05 23	95.88 70	97.62 105	94.46 47	96.29 99	96.94 129	93.56 79	99.37 57	94.29 41	99.42 52	98.99 56

CPTT-MVS		94.74 102	94.12 131	96.60 43	98.15 78	93.01 42	95.84 71	97.66 102	89.21 171	93.28 221	95.46 215	88.89 179	98.98 107	89.80 171	98.82 139	97.80 187

ab-mvs		92.40 182	92.62 174	91.74 227	97.02 148	81.65 236	95.84 71	95.50 236	86.95 217	92.95 237	97.56 76	90.70 156	97.50 270	79.63 317	97.43 249	96.06 274

bld_raw_dy_0_64		94.27 120	94.15 130	94.65 116	98.55 45	86.28 166	95.80 73	95.55 233	88.41 188	97.09 61	98.08 44	78.69 285	98.87 125	95.63 17	99.53 38	98.81 84

nrg030		96.32 40	96.55 25	95.62 76	97.83 102	88.55 115	95.77 74	98.29 30	92.68 79	98.03 26	97.91 59	95.13 43	98.95 114	93.85 50	99.49 42	99.36 24

ECVR-MVS		90.12 236	90.16 230	90.00 288	97.81 103	72.68 355	95.76 75	78.54 393	89.04 172	95.36 150	98.10 42	70.51 334	98.64 168	87.10 229	99.18 94	98.67 105

SteuartSystems-ACMMP		96.40 37	96.30 36	96.71 40	98.63 35	91.96 55	95.70 76	98.01 72	93.34 70	96.64 85	96.57 155	94.99 52	99.36 58	93.48 64	99.34 64	98.82 82
Skip Steuart: Steuart Systems R&D Blog.
OpenMVS	89.45 8	92.27 187	92.13 185	92.68 195	94.53 286	84.10 204	95.70 76	97.03 153	82.44 285	91.14 283	96.42 161	88.47 182	98.38 194	85.95 248	97.47 247	95.55 297

GST-MVS		96.24 43	95.99 54	97.00 33	98.65 34	92.71 47	95.69 78	98.01 72	92.08 96	95.74 129	96.28 176	95.22 40	99.42 33	93.17 81	99.06 103	98.88 77

ACMH+	88.43 11	96.48 30	96.82 15	95.47 81	98.54 48	89.06 101	95.65 79	98.61 12	96.10 27	98.16 23	97.52 81	96.90 7	98.62 169	90.30 155	99.60 26	98.72 97

APD_test1		95.91 53	95.42 80	97.36 23	98.82 26	96.62 6	95.64 80	97.64 103	93.38 69	95.89 121	97.23 106	93.35 87	97.66 263	88.20 206	98.66 159	97.79 188

test1111		90.39 225	90.61 221	89.74 292	98.04 88	71.50 361	95.59 81	79.72 390	89.41 164	95.94 117	98.14 39	70.79 333	98.81 136	88.52 204	99.32 68	98.90 74

canonicalmvs		94.59 108	94.69 111	94.30 134	95.60 251	87.03 143	95.59 81	98.24 34	91.56 121	95.21 161	92.04 321	94.95 53	98.66 165	91.45 127	97.57 243	97.20 228

SF-MVS		95.88 56	95.88 59	95.87 68	98.12 79	89.65 87	95.58 83	98.56 14	91.84 107	96.36 94	96.68 149	94.37 70	99.32 69	92.41 101	99.05 106	98.64 112

PS-MVSNAJss		96.01 50	96.04 52	95.89 67	98.82 26	88.51 116	95.57 84	97.88 84	88.72 180	98.81 6	98.86 10	90.77 151	99.60 9	95.43 27	99.53 38	99.57 14

PMVS	87.21 14	94.97 94	95.33 85	93.91 149	98.97 17	97.16 2	95.54 85	95.85 220	96.47 22	93.40 217	97.46 87	95.31 35	95.47 337	86.18 247	98.78 144	89.11 377
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
VDDNet		94.03 131	94.27 127	93.31 173	98.87 21	82.36 229	95.51 86	91.78 318	97.19 12	96.32 96	98.60 22	84.24 237	98.75 147	87.09 230	98.83 138	98.81 84

pm-mvs1		95.43 73	95.94 55	93.93 148	98.38 63	85.08 191	95.46 87	97.12 148	91.84 107	97.28 56	98.46 30	95.30 36	97.71 260	90.17 162	99.42 52	98.99 56

Vis-MVSNet		95.50 70	95.48 76	95.56 79	98.11 80	89.40 94	95.35 88	98.22 36	92.36 87	94.11 192	98.07 45	92.02 120	99.44 29	93.38 73	97.67 239	97.85 181
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test0726					98.51 51	86.69 152	95.34 89	98.18 41	91.85 104	97.63 35	97.37 91	95.58 24

FIs		94.90 97	95.35 83	93.55 162	98.28 69	81.76 235	95.33 90	98.14 49	93.05 76	97.07 63	97.18 111	87.65 195	99.29 70	91.72 119	99.69 14	99.61 11

PGM-MVS		96.32 40	95.94 55	97.43 18	98.59 41	93.84 32	95.33 90	98.30 27	91.40 124	95.76 126	96.87 134	95.26 37	99.45 27	92.77 91	99.21 90	99.00 54

LPG-MVS_test		96.38 39	96.23 39	96.84 38	98.36 66	92.13 52	95.33 90	98.25 31	91.78 111	97.07 63	97.22 108	96.38 12	99.28 72	92.07 108	99.59 28	99.11 44

AllTest		94.88 98	94.51 117	96.00 56	98.02 89	92.17 50	95.26 93	98.43 17	90.48 145	95.04 168	96.74 144	92.54 111	97.86 243	85.11 260	98.98 114	97.98 165

SED-MVS		96.00 51	96.41 32	94.76 109	98.51 51	86.97 144	95.21 94	98.10 54	91.95 98	97.63 35	97.25 104	96.48 10	99.35 60	93.29 75	99.29 74	97.95 169

OPU-MVS				95.15 97	96.84 160	89.43 92	95.21 94				95.66 207	93.12 95	98.06 221	86.28 246	98.61 161	97.95 169

DVP-MVS		95.82 58	96.18 42	94.72 111	98.51 51	86.69 152	95.20 96	97.00 155	91.85 104	97.40 52	97.35 97	95.58 24	99.34 63	93.44 68	99.31 69	98.13 150
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_SECOND				94.88 104	98.55 45	86.72 151	95.20 96	98.22 36					99.38 55	93.44 68	99.31 69	98.53 121

Anonymous20240529		95.50 70	95.83 63	94.50 126	97.33 136	85.93 174	95.19 98	96.77 175	96.64 19	97.61 38	98.05 46	93.23 91	98.79 140	88.60 203	99.04 111	98.78 88

SMA-MVS		95.77 59	95.54 74	96.47 49	98.27 70	91.19 66	95.09 99	97.79 95	86.48 219	97.42 50	97.51 84	94.47 69	99.29 70	93.55 60	99.29 74	98.93 68
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
NR-MVSNet		95.28 85	95.28 88	95.26 90	97.75 107	87.21 138	95.08 100	97.37 123	93.92 58	97.65 34	95.90 193	90.10 168	99.33 68	90.11 164	99.66 21	99.26 30

TransMVSNet (Re)		95.27 87	96.04 52	92.97 181	98.37 65	81.92 233	95.07 101	96.76 176	93.97 55	97.77 31	98.57 23	95.72 20	97.90 235	88.89 197	99.23 86	99.08 48

UGNet		93.08 159	92.50 177	94.79 108	93.87 301	87.99 125	95.07 101	94.26 272	90.64 142	87.33 346	97.67 69	86.89 211	98.49 183	88.10 210	98.71 151	97.91 173
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		89.81 246	88.90 255	92.55 203	97.00 149	79.73 270	95.03 103	83.65 377	89.88 156	95.30 153	94.79 245	53.64 390	99.39 49	91.99 110	98.79 143	98.54 120

LFMVS		91.33 205	91.16 210	91.82 224	96.27 202	79.36 277	95.01 104	85.61 365	96.04 30	94.82 176	97.06 121	72.03 329	98.46 188	84.96 263	98.70 153	97.65 200

CSCG		94.69 105	94.75 107	94.52 125	97.55 124	87.87 127	95.01 104	97.57 110	92.68 79	96.20 107	93.44 289	91.92 123	98.78 143	89.11 191	99.24 85	96.92 239

GG-mvs-BLEND				83.24 364	85.06 395	71.03 363	94.99 106	65.55 400		74.09 394	75.51 394	44.57 397	94.46 352	59.57 392	87.54 381	84.24 387

EU-MVSNet		87.39 297	86.71 301	89.44 296	93.40 308	76.11 326	94.93 107	90.00 332	57.17 393	95.71 132	97.37 91	64.77 361	97.68 262	92.67 96	94.37 330	94.52 324

KD-MVS_self_test		94.10 129	94.73 110	92.19 212	97.66 118	79.49 275	94.86 108	97.12 148	89.59 162	96.87 74	97.65 70	90.40 162	98.34 199	89.08 192	99.35 61	98.75 92

MTMP							94.82 109	54.62 403

PHI-MVS		94.34 118	93.80 138	95.95 59	95.65 247	91.67 62	94.82 109	97.86 85	87.86 199	93.04 233	94.16 266	91.58 130	98.78 143	90.27 157	98.96 121	97.41 215

gg-mvs-nofinetune		82.10 343	81.02 345	85.34 349	87.46 385	71.04 362	94.74 111	67.56 399	96.44 23	79.43 389	98.99 6	45.24 396	96.15 322	67.18 384	92.17 363	88.85 378

ACMM	88.83 9	96.30 42	96.07 50	96.97 34	98.39 62	92.95 44	94.74 111	98.03 69	90.82 137	97.15 59	96.85 135	96.25 14	99.00 106	93.10 83	99.33 66	98.95 65
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SD-MVS		95.19 88	95.73 67	93.55 162	96.62 174	88.88 107	94.67 113	98.05 64	91.26 126	97.25 58	96.40 163	95.42 28	94.36 355	92.72 95	99.19 92	97.40 218
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		91.52 201	91.61 196	91.26 247	94.16 292	86.26 167	94.66 114	94.82 257	91.17 130	92.13 267	91.08 334	90.03 171	97.06 294	79.09 324	97.35 253	90.45 375

v10		94.68 106	95.27 89	92.90 187	96.57 176	80.15 254	94.65 115	97.57 110	90.68 141	97.43 48	98.00 51	88.18 185	99.15 84	94.84 32	99.55 37	99.41 20

v8		94.65 107	95.29 87	92.74 192	96.65 170	79.77 269	94.59 116	97.17 143	91.86 103	97.47 47	97.93 55	88.16 186	99.08 94	94.32 39	99.47 43	99.38 22

APD-MVS		95.00 93	94.69 111	95.93 62	97.38 132	90.88 71	94.59 116	97.81 91	89.22 170	95.46 144	96.17 184	93.42 85	99.34 63	89.30 182	98.87 131	97.56 206
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
VPA-MVSNet		95.14 89	95.67 70	93.58 161	97.76 106	83.15 218	94.58 118	97.58 109	93.39 68	97.05 66	98.04 48	93.25 90	98.51 182	89.75 174	99.59 28	99.08 48

ACMMP_NAP		96.21 44	96.12 46	96.49 48	98.90 19	91.42 63	94.57 119	98.03 69	90.42 148	96.37 93	97.35 97	95.68 21	99.25 75	94.44 37	99.34 64	98.80 86

HQP_MVS		94.26 122	93.93 134	95.23 93	97.71 112	88.12 122	94.56 120	97.81 91	91.74 115	93.31 218	95.59 209	86.93 209	98.95 114	89.26 186	98.51 173	98.60 117

plane_prior2							94.56 120		91.74 115

tfpnnormal		94.27 120	94.87 103	92.48 205	97.71 112	80.88 249	94.55 122	95.41 240	93.70 61	96.67 84	97.72 66	91.40 134	98.18 213	87.45 223	99.18 94	98.36 131

XVG-ACMP-BASELINE		95.68 63	95.34 84	96.69 41	98.40 61	93.04 41	94.54 123	98.05 64	90.45 147	96.31 97	96.76 141	92.91 102	98.72 152	91.19 130	99.42 52	98.32 133

DP-MVS		95.62 64	95.84 62	94.97 101	97.16 144	88.62 111	94.54 123	97.64 103	96.94 15	96.58 88	97.32 101	93.07 98	98.72 152	90.45 147	98.84 133	97.57 204

MIMVSNet		87.13 305	86.54 304	88.89 307	96.05 221	76.11 326	94.39 125	88.51 337	81.37 292	88.27 334	96.75 143	72.38 326	95.52 334	65.71 387	95.47 303	95.03 307

K. test v3		93.37 149	93.27 159	93.66 158	98.05 85	82.62 225	94.35 126	86.62 355	96.05 29	97.51 43	98.85 12	76.59 311	99.65 3	93.21 79	98.20 204	98.73 96

MVS_0304		93.92 136	93.68 144	94.64 117	95.94 231	85.83 178	94.34 127	88.14 343	92.98 77	91.09 284	97.68 67	86.73 214	99.36 58	96.64 7	99.59 28	98.72 97

Vis-MVSNet (Re-imp)		90.42 222	90.16 230	91.20 251	97.66 118	77.32 309	94.33 128	87.66 348	91.20 129	92.99 234	95.13 230	75.40 316	98.28 202	77.86 329	99.19 92	97.99 164

ANet_high		94.83 100	96.28 37	90.47 273	96.65 170	73.16 350	94.33 128	98.74 11	96.39 24	98.09 25	98.93 8	93.37 86	98.70 159	90.38 150	99.68 18	99.53 15

iter_conf_final		90.23 232	89.32 245	92.95 183	94.65 283	81.46 240	94.32 130	95.40 242	85.61 238	92.84 239	95.37 224	54.58 387	99.13 88	92.16 104	98.94 124	98.25 139

MM				95.22 94		87.21 138	94.31 131	90.92 326	94.48 46	92.80 241	97.52 81	85.27 230	99.49 24	96.58 8	99.57 35	98.97 62

test_fmvsmconf0.01_n		95.90 54	96.09 47	95.31 89	97.30 137	89.21 97	94.24 132	98.76 10	86.25 223	97.56 39	98.66 18	95.73 19	98.44 190	97.35 2	98.99 113	98.27 138

ACMP	88.15 13	95.71 62	95.43 79	96.54 45	98.17 77	91.73 60	94.24 132	98.08 57	89.46 163	96.61 87	96.47 158	95.85 18	99.12 91	90.45 147	99.56 36	98.77 91
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MAR-MVS		90.32 230	88.87 256	94.66 115	94.82 271	91.85 57	94.22 134	94.75 260	80.91 296	87.52 344	88.07 367	86.63 216	97.87 242	76.67 340	96.21 287	94.25 330
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
FMVSNet2		92.78 170	92.73 171	92.95 183	95.40 256	81.98 232	94.18 135	95.53 235	88.63 182	96.05 113	97.37 91	81.31 267	98.81 136	87.38 226	98.67 157	98.06 153

fmvsm_s_conf0.1_n_a		94.26 122	94.37 121	93.95 147	97.36 134	85.72 181	94.15 136	95.44 237	83.25 270	95.51 139	98.05 46	92.54 111	97.19 288	95.55 21	97.46 248	98.94 66

Anonymous20240521		92.86 168	93.57 150	90.74 267	96.57 176	75.50 333	94.15 136	95.60 226	89.38 165	95.90 120	97.90 61	80.39 275	97.96 232	92.60 98	99.68 18	98.75 92

GeoE		94.55 110	94.68 113	94.15 137	97.23 139	85.11 190	94.14 138	97.34 130	88.71 181	95.26 156	95.50 214	94.65 61	99.12 91	90.94 136	98.40 179	98.23 140

9.14			94.81 104		97.49 127		94.11 139	98.37 20	87.56 208	95.38 147	96.03 189	94.66 60	99.08 94	90.70 142	98.97 119

HPM-MVS++		95.02 92	94.39 119	96.91 37	97.88 99	93.58 37	94.09 140	96.99 157	91.05 132	92.40 257	95.22 227	91.03 147	99.25 75	92.11 105	98.69 154	97.90 174

HY-MVS	82.50 18	86.81 309	85.93 311	89.47 295	93.63 305	77.93 299	94.02 141	91.58 321	75.68 334	83.64 370	93.64 282	77.40 298	97.42 276	71.70 368	92.07 364	93.05 355

Effi-MVS+-dtu		93.90 138	92.60 175	97.77 3	94.74 277	96.67 5	94.00 142	95.41 240	89.94 154	91.93 271	92.13 319	90.12 166	98.97 111	87.68 220	97.48 246	97.67 199

Effi-MVS+		92.79 169	92.74 169	92.94 185	95.10 264	83.30 213	94.00 142	97.53 114	91.36 125	89.35 315	90.65 343	94.01 75	98.66 165	87.40 225	95.30 309	96.88 243

VDD-MVS		94.37 115	94.37 121	94.40 132	97.49 127	86.07 172	93.97 144	93.28 289	94.49 45	96.24 103	97.78 63	87.99 191	98.79 140	88.92 195	99.14 99	98.34 132

h-mvs33		92.89 165	91.99 188	95.58 77	96.97 150	90.55 76	93.94 145	94.01 278	89.23 168	93.95 201	96.19 181	76.88 307	99.14 86	91.02 133	95.71 297	97.04 235

EPNet		89.80 247	88.25 269	94.45 130	83.91 397	86.18 169	93.87 146	87.07 353	91.16 131	80.64 386	94.72 247	78.83 283	98.89 120	85.17 255	98.89 126	98.28 137
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvs3		92.42 181	92.40 180	92.46 207	93.80 304	87.28 136	93.86 147	97.05 152	76.86 330	96.25 102	98.66 18	82.87 250	91.26 373	95.44 26	96.83 272	98.82 82

DeepC-MVS	91.39 4	95.43 73	95.33 85	95.71 74	97.67 117	90.17 80	93.86 147	98.02 71	87.35 209	96.22 105	97.99 53	94.48 68	99.05 99	92.73 94	99.68 18	97.93 171
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		94.20 126	94.58 116	93.04 178	95.91 232	83.13 219	93.79 149	99.19 3	92.00 97	98.84 5	98.04 48	93.64 78	99.02 104	81.28 298	98.54 169	96.96 238

TranMVSNet+NR-MVSNet		96.07 49	96.26 38	95.50 80	98.26 71	87.69 131	93.75 150	97.86 85	95.96 32	97.48 46	97.14 114	95.33 34	99.44 29	90.79 139	99.76 10	99.38 22

fmvsm_s_conf0.1_n		94.19 128	94.41 118	93.52 167	97.22 141	84.37 196	93.73 151	95.26 245	84.45 259	95.76 126	98.00 51	91.85 124	97.21 285	95.62 18	97.82 231	98.98 60

PAPM_NR		91.03 209	90.81 216	91.68 231	96.73 165	81.10 246	93.72 152	96.35 199	88.19 192	88.77 325	92.12 320	85.09 233	97.25 283	82.40 287	93.90 339	96.68 250

baseline		94.26 122	94.80 105	92.64 196	96.08 219	80.99 247	93.69 153	98.04 68	90.80 138	94.89 174	96.32 172	93.19 92	98.48 187	91.68 121	98.51 173	98.43 128

dcpmvs_2		93.96 134	95.01 99	90.82 265	97.60 120	74.04 345	93.68 154	98.85 7	89.80 158	97.82 29	97.01 126	91.14 145	99.21 78	90.56 145	98.59 164	99.19 36

fmvsm_s_conf0.5_n_a		94.02 132	94.08 133	93.84 153	96.72 166	85.73 180	93.65 155	95.23 246	83.30 268	95.13 162	97.56 76	92.22 116	97.17 289	95.51 23	97.41 250	98.64 112

F-COLMAP		92.28 186	91.06 211	95.95 59	97.52 125	91.90 56	93.53 156	97.18 142	83.98 263	88.70 327	94.04 269	88.41 183	98.55 179	80.17 310	95.99 291	97.39 219

test_fmvsmconf0.1_n		95.61 65	95.72 68	95.26 90	96.85 159	89.20 98	93.51 157	98.60 13	85.68 235	97.42 50	98.30 35	95.34 33	98.39 191	96.85 3	98.98 114	98.19 144

FMVSNet5		87.82 286	86.56 303	91.62 233	92.31 324	79.81 268	93.49 158	94.81 259	83.26 269	91.36 277	96.93 130	52.77 392	97.49 272	76.07 344	98.03 217	97.55 207

DPE-MVS		95.89 55	95.88 59	95.92 64	97.93 96	89.83 85	93.46 159	98.30 27	92.37 86	97.75 32	96.95 128	95.14 42	99.51 20	91.74 118	99.28 79	98.41 129
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
alignmvs		93.26 153	92.85 166	94.50 126	95.70 243	87.45 133	93.45 160	95.76 221	91.58 120	95.25 158	92.42 315	81.96 262	98.72 152	91.61 122	97.87 229	97.33 223

test_fmvsmvis_n_1920		95.08 91	95.40 81	94.13 139	96.66 169	87.75 130	93.44 161	98.49 15	85.57 240	98.27 20	97.11 117	94.11 74	97.75 256	96.26 11	98.72 149	96.89 241

114514_t		90.51 219	89.80 239	92.63 198	98.00 91	82.24 230	93.40 162	97.29 135	65.84 384	89.40 314	94.80 244	86.99 207	98.75 147	83.88 273	98.61 161	96.89 241

fmvsm_s_conf0.5_n		94.00 133	94.20 129	93.42 171	96.69 167	84.37 196	93.38 163	95.13 248	84.50 258	95.40 146	97.55 80	91.77 126	97.20 286	95.59 19	97.79 232	98.69 104

DeepC-MVS_fast	89.96 7	93.73 141	93.44 154	94.60 121	96.14 214	87.90 126	93.36 164	97.14 145	85.53 241	93.90 204	95.45 216	91.30 137	98.59 174	89.51 177	98.62 160	97.31 224
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 48	95.92 58	96.57 44	99.06 10	91.21 65	93.25 165	98.32 24	87.89 198	96.86 75	97.38 90	95.55 26	99.39 49	95.47 25	99.47 43	99.11 44
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
test_0402		95.73 61	96.22 40	94.26 135	98.19 76	85.77 179	93.24 166	97.24 139	96.88 16	97.69 33	97.77 65	94.12 73	99.13 88	91.54 126	99.29 74	97.88 177

test_fmvsmconf_n		95.43 73	95.50 75	95.22 94	96.48 186	89.19 99	93.23 167	98.36 21	85.61 238	96.92 73	98.02 50	95.23 39	98.38 194	96.69 6	98.95 123	98.09 152

test_fmvsm_n_1920		94.72 103	94.74 109	94.67 113	96.30 200	88.62 111	93.19 168	98.07 60	85.63 237	97.08 62	97.35 97	90.86 148	97.66 263	95.70 16	98.48 176	97.74 194

sd_testset		93.94 135	94.39 119	92.61 200	97.93 96	83.24 214	93.17 169	95.04 250	93.65 65	95.51 139	98.63 20	94.49 67	95.89 329	81.72 294	99.35 61	98.70 101

MSLP-MVS++		93.25 155	93.88 135	91.37 241	96.34 195	82.81 224	93.11 170	97.74 98	89.37 166	94.08 194	95.29 226	90.40 162	96.35 319	90.35 152	98.25 197	94.96 309

baseline1		87.62 291	87.31 286	88.54 314	94.71 280	74.27 343	93.10 171	88.20 341	86.20 224	92.18 266	93.04 297	73.21 323	95.52 334	79.32 321	85.82 384	95.83 284

plane_prior						88.12 122	93.01 172		88.98 174						98.06 214

thres100view900		87.35 298	86.89 297	88.72 310	96.14 214	73.09 351	93.00 173	85.31 368	92.13 95	93.26 223	90.96 336	63.42 367	98.28 202	71.27 371	96.54 281	94.79 317

Patchmtry		90.11 237	89.92 236	90.66 269	90.35 362	77.00 313	92.96 174	92.81 296	90.25 151	94.74 180	96.93 130	67.11 345	97.52 269	85.17 255	98.98 114	97.46 211

LF4IMVS		92.72 172	92.02 187	94.84 106	95.65 247	91.99 54	92.92 175	96.60 184	85.08 250	92.44 255	93.62 284	86.80 212	96.35 319	86.81 232	98.25 197	96.18 270

UniMVSNet (Re)		95.32 81	95.15 93	95.80 70	97.79 105	88.91 105	92.91 176	98.07 60	93.46 67	96.31 97	95.97 192	90.14 165	99.34 63	92.11 105	99.64 24	99.16 38

TAPA-MVS	88.58 10	92.49 179	91.75 195	94.73 110	96.50 183	89.69 86	92.91 176	97.68 101	78.02 323	92.79 242	94.10 267	90.85 149	97.96 232	84.76 266	98.16 206	96.54 252
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
thisisatest0530		88.69 273	87.52 284	92.20 211	96.33 196	79.36 277	92.81 178	84.01 376	86.44 220	93.67 209	92.68 308	53.62 391	99.25 75	89.65 176	98.45 177	98.00 161

EIA-MVS		92.35 184	92.03 186	93.30 174	95.81 238	83.97 206	92.80 179	98.17 45	87.71 203	89.79 309	87.56 368	91.17 144	99.18 82	87.97 215	97.27 254	96.77 247

iter_conf05		88.94 266	88.09 276	91.50 238	92.74 319	76.97 316	92.80 179	95.92 217	82.82 279	93.65 210	95.37 224	49.41 394	99.13 88	90.82 138	99.28 79	98.40 130

thres600view7		87.66 289	87.10 295	89.36 299	96.05 221	73.17 349	92.72 181	85.31 368	91.89 102	93.29 220	90.97 335	63.42 367	98.39 191	73.23 359	96.99 268	96.51 254

wuyk23d		87.83 285	90.79 217	78.96 374	90.46 361	88.63 110	92.72 181	90.67 329	91.65 119	98.68 11	97.64 71	96.06 15	77.53 396	59.84 391	99.41 56	70.73 394

test_fmvs2		90.62 218	90.40 227	91.29 246	91.93 338	85.46 186	92.70 183	96.48 194	74.44 343	94.91 173	97.59 74	75.52 315	90.57 375	93.44 68	96.56 280	97.84 182

V42		93.43 148	93.58 149	92.97 181	95.34 260	81.22 244	92.67 184	96.49 193	87.25 211	96.20 107	96.37 169	87.32 201	98.85 128	92.39 102	98.21 202	98.85 81

casdiffmvs_mvg		95.10 90	95.62 71	93.53 165	96.25 205	83.23 215	92.66 185	98.19 39	93.06 75	97.49 44	97.15 113	94.78 57	98.71 158	92.27 103	98.72 149	98.65 107
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
OPM-MVS		95.61 65	95.45 77	96.08 54	98.49 58	91.00 68	92.65 186	97.33 131	90.05 153	96.77 80	96.85 135	95.04 48	98.56 177	92.77 91	99.06 103	98.70 101
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
test_vis1_n		89.01 262	89.01 251	89.03 304	92.57 321	82.46 228	92.62 187	96.06 211	73.02 353	90.40 295	95.77 203	74.86 317	89.68 381	90.78 140	94.98 315	94.95 310

DU-MVS		95.28 85	95.12 95	95.75 72	97.75 107	88.59 113	92.58 188	97.81 91	93.99 53	96.80 78	95.90 193	90.10 168	99.41 39	91.60 123	99.58 33	99.26 30

FMVSNet3		90.78 212	90.32 229	92.16 216	93.03 316	79.92 264	92.54 189	94.95 253	86.17 226	95.10 164	96.01 190	69.97 336	98.75 147	86.74 233	98.38 183	97.82 185

hse-mvs2		92.24 188	91.20 207	95.38 83	96.16 211	90.65 75	92.52 190	92.01 316	89.23 168	93.95 201	92.99 299	76.88 307	98.69 161	91.02 133	96.03 289	96.81 245

MVS_Test		92.57 178	93.29 156	90.40 276	93.53 307	75.85 329	92.52 190	96.96 158	88.73 179	92.35 260	96.70 148	90.77 151	98.37 198	92.53 99	95.49 302	96.99 237

CR-MVSNet		87.89 283	87.12 294	90.22 281	91.01 353	78.93 284	92.52 190	92.81 296	73.08 352	89.10 316	96.93 130	67.11 345	97.64 265	88.80 198	92.70 357	94.08 331

RPMNet		90.31 231	90.14 233	90.81 266	91.01 353	78.93 284	92.52 190	98.12 51	91.91 101	89.10 316	96.89 133	68.84 338	99.41 39	90.17 162	92.70 357	94.08 331

fmvsm_l_conf0.5_n		93.79 139	93.81 136	93.73 156	96.16 211	86.26 167	92.46 194	96.72 178	81.69 291	95.77 125	97.11 117	90.83 150	97.82 246	95.58 20	97.99 221	97.11 230

XVG-OURS-SEG-HR		95.38 78	95.00 100	96.51 46	98.10 81	94.07 20	92.46 194	98.13 50	90.69 140	93.75 206	96.25 179	98.03 2	97.02 295	92.08 107	95.55 300	98.45 127

EI-MVSNet-Vis-set		94.36 116	94.28 125	94.61 118	92.55 322	85.98 173	92.44 196	94.69 262	93.70 61	96.12 111	95.81 198	91.24 138	98.86 126	93.76 55	98.22 201	98.98 60

Anonymous202405211		92.58 176	92.50 177	92.83 190	96.55 178	83.22 216	92.43 197	91.64 320	94.10 52	95.59 136	96.64 151	81.88 264	97.50 270	85.12 259	98.52 171	97.77 190

AUN-MVS		90.05 241	88.30 265	95.32 88	96.09 218	90.52 77	92.42 198	92.05 315	82.08 288	88.45 331	92.86 301	65.76 355	98.69 161	88.91 196	96.07 288	96.75 249

EI-MVSNet-UG-set		94.35 117	94.27 127	94.59 122	92.46 323	85.87 176	92.42 198	94.69 262	93.67 64	96.13 110	95.84 197	91.20 141	98.86 126	93.78 52	98.23 199	99.03 52

NCCC		94.08 130	93.54 152	95.70 75	96.49 184	89.90 83	92.39 200	96.91 164	90.64 142	92.33 263	94.60 252	90.58 159	98.96 112	90.21 161	97.70 237	98.23 140

casdiffmvs		94.32 119	94.80 105	92.85 189	96.05 221	81.44 241	92.35 201	98.05 64	91.53 122	95.75 128	96.80 138	93.35 87	98.49 183	91.01 135	98.32 191	98.64 112
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ETV-MVS		92.99 162	92.74 169	93.72 157	95.86 234	86.30 165	92.33 202	97.84 88	91.70 118	92.81 240	86.17 378	92.22 116	99.19 81	88.03 214	97.73 234	95.66 293

fmvsm_l_conf0.5_n_a		93.59 144	93.63 146	93.49 169	96.10 217	85.66 183	92.32 203	96.57 187	81.32 293	95.63 134	97.14 114	90.19 164	97.73 259	95.37 29	98.03 217	97.07 231

EI-MVSNet		92.99 162	93.26 160	92.19 212	92.12 332	79.21 282	92.32 203	94.67 264	91.77 113	95.24 159	95.85 195	87.14 205	98.49 183	91.99 110	98.26 195	98.86 78

CVMVSNet		85.16 319	84.72 317	86.48 340	92.12 332	70.19 366	92.32 203	88.17 342	56.15 394	90.64 291	95.85 195	67.97 343	96.69 307	88.78 199	90.52 373	92.56 360

test_fmvs1_n		88.73 272	88.38 263	89.76 291	92.06 334	82.53 226	92.30 206	96.59 186	71.14 362	92.58 249	95.41 221	68.55 339	89.57 383	91.12 131	95.66 298	97.18 229

OMC-MVS		94.22 125	93.69 143	95.81 69	97.25 138	91.27 64	92.27 207	97.40 122	87.10 215	94.56 184	95.42 218	93.74 77	98.11 218	86.62 237	98.85 132	98.06 153

PM-MVS		93.33 150	92.67 173	95.33 86	96.58 175	94.06 21	92.26 208	92.18 309	85.92 230	96.22 105	96.61 153	85.64 228	95.99 328	90.35 152	98.23 199	95.93 279

UniMVSNet_NR-MVSNet		95.35 79	95.21 90	95.76 71	97.69 115	88.59 113	92.26 208	97.84 88	94.91 40	96.80 78	95.78 202	90.42 160	99.41 39	91.60 123	99.58 33	99.29 29

AdaColmap		91.63 198	91.36 204	92.47 206	95.56 252	86.36 163	92.24 210	96.27 201	88.88 178	89.90 306	92.69 307	91.65 129	98.32 200	77.38 336	97.64 240	92.72 359

PVSNet_Blended_VisFu		91.63 198	91.20 207	92.94 185	97.73 110	83.95 207	92.14 211	97.46 118	78.85 319	92.35 260	94.98 236	84.16 238	99.08 94	86.36 244	96.77 275	95.79 286

Baseline_NR-MVSNet		94.47 113	95.09 97	92.60 201	98.50 57	80.82 250	92.08 212	96.68 180	93.82 59	96.29 99	98.56 24	90.10 168	97.75 256	90.10 166	99.66 21	99.24 32

Fast-Effi-MVS+-dtu		92.77 171	92.16 182	94.58 124	94.66 282	88.25 120	92.05 213	96.65 182	89.62 161	90.08 301	91.23 331	92.56 110	98.60 172	86.30 245	96.27 286	96.90 240

save fliter					97.46 130	88.05 124	92.04 214	97.08 150	87.63 206

PatchT		87.51 294	88.17 274	85.55 347	90.64 356	66.91 376	92.02 215	86.09 359	92.20 93	89.05 318	97.16 112	64.15 363	96.37 318	89.21 189	92.98 355	93.37 350

EG-PatchMatch MVS		94.54 111	94.67 114	94.14 138	97.87 101	86.50 156	92.00 216	96.74 177	88.16 194	96.93 72	97.61 73	93.04 99	97.90 235	91.60 123	98.12 209	98.03 159

v144192		93.20 158	93.54 152	92.16 216	96.05 221	78.26 296	91.95 217	97.14 145	84.98 252	95.96 115	96.11 185	87.08 206	99.04 102	93.79 51	98.84 133	99.17 37

VNet		92.67 174	92.96 162	91.79 225	96.27 202	80.15 254	91.95 217	94.98 252	92.19 94	94.52 186	96.07 187	87.43 199	97.39 279	84.83 264	98.38 183	97.83 183

1314		86.46 311	86.33 308	86.87 338	91.65 345	74.54 338	91.94 219	94.10 274	74.28 344	84.78 363	87.33 372	83.03 248	95.00 346	78.72 325	91.16 370	91.06 372

MVS		84.98 321	84.30 322	87.01 335	91.03 352	77.69 305	91.94 219	94.16 273	59.36 392	84.23 367	87.50 370	85.66 226	96.80 304	71.79 366	93.05 354	86.54 385

SDMVSNet		94.43 114	95.02 98	92.69 194	97.93 96	82.88 223	91.92 221	95.99 216	93.65 65	95.51 139	98.63 20	94.60 63	96.48 312	87.57 221	99.35 61	98.70 101

tfpn200view9		87.05 306	86.52 305	88.67 311	95.77 239	72.94 352	91.89 222	86.00 360	90.84 135	92.61 247	89.80 347	63.93 364	98.28 202	71.27 371	96.54 281	94.79 317

thres400		87.20 302	86.52 305	89.24 303	95.77 239	72.94 352	91.89 222	86.00 360	90.84 135	92.61 247	89.80 347	63.93 364	98.28 202	71.27 371	96.54 281	96.51 254

v1921920		93.26 153	93.61 148	92.19 212	96.04 225	78.31 295	91.88 224	97.24 139	85.17 246	96.19 109	96.19 181	86.76 213	99.05 99	94.18 43	98.84 133	99.22 33

XXY-MVS		92.58 176	93.16 161	90.84 264	97.75 107	79.84 265	91.87 225	96.22 206	85.94 229	95.53 138	97.68 67	92.69 108	94.48 351	83.21 277	97.51 244	98.21 142

IterMVS-LS		93.78 140	94.28 125	92.27 209	96.27 202	79.21 282	91.87 225	96.78 173	91.77 113	96.57 89	97.07 120	87.15 204	98.74 150	91.99 110	99.03 112	98.86 78
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1144		93.50 145	93.81 136	92.57 202	96.28 201	79.61 272	91.86 227	96.96 158	86.95 217	95.91 119	96.32 172	87.65 195	98.96 112	93.51 61	98.88 128	99.13 41

v1192		93.49 146	93.78 139	92.62 199	96.16 211	79.62 271	91.83 228	97.22 141	86.07 227	96.10 112	96.38 168	87.22 202	99.02 104	94.14 44	98.88 128	99.22 33

v1240		93.29 151	93.71 142	92.06 219	96.01 226	77.89 301	91.81 229	97.37 123	85.12 248	96.69 83	96.40 163	86.67 215	99.07 98	94.51 35	98.76 146	99.22 33

CNVR-MVS		94.58 109	94.29 124	95.46 82	96.94 152	89.35 96	91.81 229	96.80 172	89.66 160	93.90 204	95.44 217	92.80 106	98.72 152	92.74 93	98.52 171	98.32 133

v2v482		93.29 151	93.63 146	92.29 208	96.35 194	78.82 289	91.77 231	96.28 200	88.45 186	95.70 133	96.26 178	86.02 223	98.90 118	93.02 86	98.81 141	99.14 40

EPNet_dtu		85.63 315	84.37 321	89.40 298	86.30 390	74.33 342	91.64 232	88.26 339	84.84 255	72.96 395	89.85 345	71.27 332	97.69 261	76.60 341	97.62 241	96.18 270
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PLC	85.34 15	90.40 223	88.92 253	94.85 105	96.53 182	90.02 81	91.58 233	96.48 194	80.16 302	86.14 352	92.18 317	85.73 225	98.25 207	76.87 339	94.61 326	96.30 265
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
VPNet		93.08 159	93.76 140	91.03 255	98.60 39	75.83 331	91.51 234	95.62 225	91.84 107	95.74 129	97.10 119	89.31 176	98.32 200	85.07 262	99.06 103	98.93 68

XVG-OURS		94.72 103	94.12 131	96.50 47	98.00 91	94.23 18	91.48 235	98.17 45	90.72 139	95.30 153	96.47 158	87.94 192	96.98 296	91.41 128	97.61 242	98.30 136

HQP-NCC					96.36 191		91.37 236		87.16 212	88.81 321

ACMP_Plane					96.36 191		91.37 236		87.16 212	88.81 321

HQP-MVS		92.09 190	91.49 201	93.88 150	96.36 191	84.89 192	91.37 236	97.31 132	87.16 212	88.81 321	93.40 290	84.76 234	98.60 172	86.55 240	97.73 234	98.14 149

MCST-MVS		92.91 164	92.51 176	94.10 140	97.52 125	85.72 181	91.36 239	97.13 147	80.33 301	92.91 238	94.24 262	91.23 139	98.72 152	89.99 168	97.93 226	97.86 179

v148		92.87 167	93.29 156	91.62 233	96.25 205	77.72 304	91.28 240	95.05 249	89.69 159	95.93 118	96.04 188	87.34 200	98.38 194	90.05 167	97.99 221	98.78 88

tpmvs		84.22 327	83.97 325	84.94 352	87.09 387	65.18 383	91.21 241	88.35 338	82.87 278	85.21 356	90.96 336	65.24 359	96.75 305	79.60 320	85.25 385	92.90 357

CANet		92.38 183	91.99 188	93.52 167	93.82 303	83.46 211	91.14 242	97.00 155	89.81 157	86.47 350	94.04 269	87.90 193	99.21 78	89.50 178	98.27 194	97.90 174

CNLPA		91.72 196	91.20 207	93.26 175	96.17 210	91.02 67	91.14 242	95.55 233	90.16 152	90.87 286	93.56 287	86.31 219	94.40 354	79.92 316	97.12 259	94.37 327

DP-MVS Recon		92.31 185	91.88 191	93.60 160	97.18 143	86.87 147	91.10 244	97.37 123	84.92 253	92.08 268	94.08 268	88.59 180	98.20 210	83.50 274	98.14 208	95.73 288

OpenMVS_ROB	85.12 16	89.52 250	89.05 249	90.92 260	94.58 285	81.21 245	91.10 244	93.41 288	77.03 329	93.41 215	93.99 273	83.23 245	97.80 248	79.93 314	94.80 321	93.74 342

TSAR-MVS + GP.		93.07 161	92.41 179	95.06 99	95.82 236	90.87 72	90.97 246	92.61 304	88.04 195	94.61 183	93.79 280	88.08 187	97.81 247	89.41 179	98.39 182	96.50 257

MVP-Stereo		90.07 240	88.92 253	93.54 164	96.31 198	86.49 157	90.93 247	95.59 230	79.80 303	91.48 275	95.59 209	80.79 272	97.39 279	78.57 327	91.19 369	96.76 248
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MVSTER		89.32 254	88.75 257	91.03 255	90.10 365	76.62 321	90.85 248	94.67 264	82.27 286	95.24 159	95.79 199	61.09 376	98.49 183	90.49 146	98.26 195	97.97 168

pmmvs-eth3d		91.54 200	90.73 219	93.99 142	95.76 241	87.86 128	90.83 249	93.98 279	78.23 322	94.02 199	96.22 180	82.62 256	96.83 303	86.57 238	98.33 189	97.29 225

CANet_DTU		89.85 245	89.17 247	91.87 222	92.20 329	80.02 261	90.79 250	95.87 219	86.02 228	82.53 377	91.77 324	80.01 276	98.57 176	85.66 252	97.70 237	97.01 236

SSC-MVS		90.16 234	92.96 162	81.78 368	97.88 99	48.48 400	90.75 251	87.69 347	96.02 31	96.70 82	97.63 72	85.60 229	97.80 248	85.73 251	98.60 163	99.06 50

test_prior4						89.91 82	90.74 252

TinyColmap		92.00 192	92.76 168	89.71 293	95.62 250	77.02 312	90.72 253	96.17 209	87.70 204	95.26 156	96.29 174	92.54 111	96.45 314	81.77 292	98.77 145	95.66 293

CDPH-MVS		92.67 174	91.83 193	95.18 96	96.94 152	88.46 118	90.70 254	97.07 151	77.38 325	92.34 262	95.08 233	92.67 109	98.88 121	85.74 250	98.57 166	98.20 143

test_vis1_n_1920		89.45 251	89.85 238	88.28 320	93.59 306	76.71 320	90.67 255	97.78 96	79.67 307	90.30 298	96.11 185	76.62 310	92.17 369	90.31 154	93.57 344	95.96 277

DSMNet-mixed		82.21 340	81.56 339	84.16 359	89.57 371	70.00 370	90.65 256	77.66 395	54.99 395	83.30 373	97.57 75	77.89 294	90.50 377	66.86 385	95.54 301	91.97 364

TEST9					96.45 187	89.46 90	90.60 257	96.92 162	79.09 315	90.49 292	94.39 258	91.31 136	98.88 121

train_agg		92.71 173	91.83 193	95.35 84	96.45 187	89.46 90	90.60 257	96.92 162	79.37 310	90.49 292	94.39 258	91.20 141	98.88 121	88.66 202	98.43 178	97.72 195

PatchmatchNet		85.22 318	84.64 318	86.98 336	89.51 372	69.83 371	90.52 259	87.34 351	78.87 318	87.22 347	92.74 306	66.91 347	96.53 309	81.77 292	86.88 382	94.58 323
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test_8					96.37 189	89.14 100	90.51 260	96.89 165	79.37 310	90.42 294	94.36 260	91.20 141	98.82 131

test_yl		90.11 237	89.73 242	91.26 247	94.09 295	79.82 266	90.44 261	92.65 301	90.90 133	93.19 228	93.30 292	73.90 320	98.03 223	82.23 288	96.87 270	95.93 279

DCV-MVSNet		90.11 237	89.73 242	91.26 247	94.09 295	79.82 266	90.44 261	92.65 301	90.90 133	93.19 228	93.30 292	73.90 320	98.03 223	82.23 288	96.87 270	95.93 279

tpm2		81.46 345	80.35 352	84.80 353	89.90 366	65.14 384	90.44 261	85.36 367	65.82 385	82.05 380	92.44 313	57.94 381	96.69 307	70.71 375	88.49 379	92.56 360

test_fmvs1		87.59 292	87.27 288	88.54 314	88.32 380	81.26 243	90.43 264	95.72 223	70.55 368	91.70 273	94.63 250	68.13 340	89.42 384	90.59 144	95.34 308	94.94 312

test_vis3_rt		90.40 223	90.03 234	91.52 237	92.58 320	88.95 103	90.38 265	97.72 100	73.30 350	97.79 30	97.51 84	77.05 303	87.10 388	89.03 193	94.89 317	98.50 122

CostFormer		83.09 334	82.21 337	85.73 346	89.27 374	67.01 375	90.35 266	86.47 356	70.42 369	83.52 372	93.23 295	61.18 375	96.85 302	77.21 337	88.26 380	93.34 351

TAMVS		90.16 234	89.05 249	93.49 169	96.49 184	86.37 162	90.34 267	92.55 305	80.84 299	92.99 234	94.57 254	81.94 263	98.20 210	73.51 357	98.21 202	95.90 282

EPMVS		81.17 349	80.37 351	83.58 362	85.58 393	65.08 385	90.31 268	71.34 398	77.31 327	85.80 354	91.30 330	59.38 379	92.70 367	79.99 311	82.34 391	92.96 356

CMPMVS	68.83 22	87.28 299	85.67 313	92.09 218	88.77 378	85.42 187	90.31 268	94.38 268	70.02 371	88.00 337	93.30 292	73.78 322	94.03 359	75.96 346	96.54 281	96.83 244
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_post1							90.21 270				5.85 401	65.36 357	96.00 327	79.61 318

test_prior2							90.21 270		89.33 167	90.77 288	94.81 242	90.41 161		88.21 205	98.55 167

MVS_111021_LR		93.66 142	93.28 158	94.80 107	96.25 205	90.95 69	90.21 270	95.43 239	87.91 196	93.74 208	94.40 257	92.88 104	96.38 317	90.39 149	98.28 193	97.07 231

WR-MVS		93.49 146	93.72 141	92.80 191	97.57 123	80.03 260	90.14 273	95.68 224	93.70 61	96.62 86	95.39 222	87.21 203	99.04 102	87.50 222	99.64 24	99.33 26

tpmrst		82.85 337	82.93 333	82.64 365	87.65 382	58.99 396	90.14 273	87.90 346	75.54 336	83.93 368	91.63 327	66.79 350	95.36 340	81.21 300	81.54 392	93.57 349

PVSNet_BlendedMVS		90.35 228	89.96 235	91.54 236	94.81 272	78.80 291	90.14 273	96.93 160	79.43 309	88.68 328	95.06 234	86.27 220	98.15 216	80.27 306	98.04 216	97.68 198

BH-untuned		90.68 215	90.90 212	90.05 287	95.98 227	79.57 273	90.04 276	94.94 254	87.91 196	94.07 195	93.00 298	87.76 194	97.78 252	79.19 323	95.17 312	92.80 358

新几何2							90.02 277

旧先验2							90.00 278		68.65 376	92.71 245			96.52 310	85.15 257

无先验							89.94 279	95.75 222	70.81 366				98.59 174	81.17 301		94.81 315

xiu_mvs_v1_base_debu		91.47 202	91.52 198	91.33 243	95.69 244	81.56 237	89.92 280	96.05 213	83.22 271	91.26 279	90.74 338	91.55 131	98.82 131	89.29 183	95.91 292	93.62 346

xiu_mvs_v1_base		91.47 202	91.52 198	91.33 243	95.69 244	81.56 237	89.92 280	96.05 213	83.22 271	91.26 279	90.74 338	91.55 131	98.82 131	89.29 183	95.91 292	93.62 346

xiu_mvs_v1_base_debi		91.47 202	91.52 198	91.33 243	95.69 244	81.56 237	89.92 280	96.05 213	83.22 271	91.26 279	90.74 338	91.55 131	98.82 131	89.29 183	95.91 292	93.62 346

mvs_anonymous		90.37 227	91.30 206	87.58 330	92.17 331	68.00 374	89.84 283	94.73 261	83.82 266	93.22 227	97.40 89	87.54 197	97.40 278	87.94 216	95.05 314	97.34 222

test20.03		90.80 211	90.85 215	90.63 270	95.63 249	79.24 280	89.81 284	92.87 295	89.90 155	94.39 188	96.40 163	85.77 224	95.27 344	73.86 356	99.05 106	97.39 219

testing3		83.66 330	82.52 335	87.08 334	95.84 235	65.84 381	89.80 285	77.17 396	88.17 193	90.84 287	88.63 362	30.95 404	98.11 218	84.05 271	97.19 257	97.28 226

WB-MVS		89.44 252	92.15 184	81.32 369	97.73 110	48.22 401	89.73 286	87.98 345	95.24 36	96.05 113	96.99 127	85.18 231	96.95 297	82.45 286	97.97 223	98.78 88

1112_ss		88.42 276	87.41 285	91.45 239	96.69 167	80.99 247	89.72 287	96.72 178	73.37 349	87.00 348	90.69 341	77.38 299	98.20 210	81.38 297	93.72 342	95.15 304

UnsupCasMVSNet_eth		90.33 229	90.34 228	90.28 278	94.64 284	80.24 252	89.69 288	95.88 218	85.77 232	93.94 203	95.69 206	81.99 261	92.98 366	84.21 270	91.30 368	97.62 201

MG-MVS		89.54 249	89.80 239	88.76 309	94.88 268	72.47 357	89.60 289	92.44 307	85.82 231	89.48 313	95.98 191	82.85 251	97.74 258	81.87 291	95.27 310	96.08 273

Patchmatch-test		86.10 313	86.01 310	86.38 344	90.63 357	74.22 344	89.57 290	86.69 354	85.73 234	89.81 308	92.83 302	65.24 359	91.04 374	77.82 332	95.78 296	93.88 339

Anonymous20231206		88.77 270	88.29 266	90.20 283	96.31 198	78.81 290	89.56 291	93.49 286	74.26 345	92.38 258	95.58 212	82.21 257	95.43 339	72.07 365	98.75 148	96.34 263

dmvs_re		84.69 324	83.94 326	86.95 337	92.24 326	82.93 222	89.51 292	87.37 350	84.38 261	85.37 355	85.08 382	72.44 325	86.59 389	68.05 381	91.03 372	91.33 369

DeepPCF-MVS	90.46 6	94.20 126	93.56 151	96.14 52	95.96 228	92.96 43	89.48 293	97.46 118	85.14 247	96.23 104	95.42 218	93.19 92	98.08 220	90.37 151	98.76 146	97.38 221

test_cas_vis1_n_1920		88.25 279	88.27 268	88.20 322	92.19 330	78.92 286	89.45 294	95.44 237	75.29 340	93.23 226	95.65 208	71.58 330	90.23 379	88.05 212	93.55 345	95.44 299

SCA		87.43 296	87.21 290	88.10 324	92.01 336	71.98 359	89.43 295	88.11 344	82.26 287	88.71 326	92.83 302	78.65 286	97.59 266	79.61 318	93.30 348	94.75 319

testgi		90.38 226	91.34 205	87.50 331	97.49 127	71.54 360	89.43 295	95.16 247	88.38 189	94.54 185	94.68 249	92.88 104	93.09 365	71.60 369	97.85 230	97.88 177

JIA-IIPM		85.08 320	83.04 331	91.19 252	87.56 383	86.14 170	89.40 297	84.44 375	88.98 174	82.20 378	97.95 54	56.82 384	96.15 322	76.55 342	83.45 388	91.30 370

原ACMM2							89.34 298

tpm		84.38 326	84.08 324	85.30 350	90.47 360	63.43 390	89.34 298	85.63 364	77.24 328	87.62 342	95.03 235	61.00 377	97.30 282	79.26 322	91.09 371	95.16 303

MVS_111021_HR		93.63 143	93.42 155	94.26 135	96.65 170	86.96 146	89.30 300	96.23 204	88.36 190	93.57 212	94.60 252	93.45 82	97.77 253	90.23 160	98.38 183	98.03 159

tpm cat1		80.61 353	79.46 356	84.07 360	88.78 377	65.06 386	89.26 301	88.23 340	62.27 390	81.90 382	89.66 353	62.70 372	95.29 343	71.72 367	80.60 393	91.86 367

CDS-MVSNet		89.55 248	88.22 272	93.53 165	95.37 259	86.49 157	89.26 301	93.59 282	79.76 305	91.15 282	92.31 316	77.12 302	98.38 194	77.51 334	97.92 227	95.71 289
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Fast-Effi-MVS+		91.28 207	90.86 214	92.53 204	95.45 255	82.53 226	89.25 303	96.52 192	85.00 251	89.91 305	88.55 364	92.94 100	98.84 129	84.72 267	95.44 304	96.22 268

BH-RMVSNet		90.47 221	90.44 225	90.56 272	95.21 263	78.65 293	89.15 304	93.94 280	88.21 191	92.74 244	94.22 263	86.38 218	97.88 239	78.67 326	95.39 306	95.14 305

thres200		85.85 314	85.18 315	87.88 328	94.44 287	72.52 356	89.08 305	86.21 357	88.57 185	91.44 276	88.40 365	64.22 362	98.00 228	68.35 380	95.88 295	93.12 352

USDC		89.02 260	89.08 248	88.84 308	95.07 265	74.50 340	88.97 306	96.39 197	73.21 351	93.27 222	96.28 176	82.16 259	96.39 316	77.55 333	98.80 142	95.62 296

testdata1							88.96 307		88.44 187

pmmvs5		87.87 284	87.14 292	90.07 285	93.26 311	76.97 316	88.89 308	92.18 309	73.71 348	88.36 332	93.89 277	76.86 309	96.73 306	80.32 305	96.81 273	96.51 254

dmvs_testset		78.23 360	78.99 357	75.94 376	91.99 337	55.34 399	88.86 309	78.70 392	82.69 280	81.64 384	79.46 391	75.93 313	85.74 391	48.78 397	82.85 390	86.76 384

patch_mono-2		92.46 180	92.72 172	91.71 229	96.65 170	78.91 287	88.85 310	97.17 143	83.89 265	92.45 254	96.76 141	89.86 172	97.09 292	90.24 159	98.59 164	99.12 43

test222					96.95 151	85.27 189	88.83 311	93.61 281	65.09 386	90.74 289	94.85 241	84.62 236			97.36 252	93.91 337

baseline2		83.38 332	81.54 341	88.90 306	91.38 348	72.84 354	88.78 312	81.22 385	78.97 316	79.82 388	87.56 368	61.73 374	97.80 248	74.30 354	90.05 375	96.05 275

diffmvs		91.74 195	91.93 190	91.15 253	93.06 314	78.17 297	88.77 313	97.51 117	86.28 222	92.42 256	93.96 274	88.04 189	97.46 273	90.69 143	96.67 278	97.82 185
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MDTV_nov1_ep13			83.88 327		89.42 373	61.52 392	88.74 314	87.41 349	73.99 346	84.96 362	94.01 272	65.25 358	95.53 333	78.02 328	93.16 350

D2MVS		89.93 243	89.60 244	90.92 260	94.03 297	78.40 294	88.69 315	94.85 255	78.96 317	93.08 230	95.09 232	74.57 318	96.94 298	88.19 207	98.96 121	97.41 215

TR-MVS		87.70 287	87.17 291	89.27 301	94.11 294	79.26 279	88.69 315	91.86 317	81.94 289	90.69 290	89.79 349	82.82 252	97.42 276	72.65 363	91.98 365	91.14 371

PatchMatch-RL		89.18 255	88.02 278	92.64 196	95.90 233	92.87 45	88.67 317	91.06 323	80.34 300	90.03 303	91.67 326	83.34 243	94.42 353	76.35 343	94.84 320	90.64 374

PAPR		87.65 290	86.77 300	90.27 279	92.85 318	77.38 308	88.56 318	96.23 204	76.82 332	84.98 361	89.75 351	86.08 222	97.16 290	72.33 364	93.35 347	96.26 267

MDTV_nov1_ep13_2view						42.48 404	88.45 319		67.22 380	83.56 371		66.80 348		72.86 362		94.06 333

jason		89.17 256	88.32 264	91.70 230	95.73 242	80.07 257	88.10 320	93.22 290	71.98 358	90.09 300	92.79 304	78.53 289	98.56 177	87.43 224	97.06 261	96.46 259
jason: jason.
mvsany_test3		89.11 258	88.21 273	91.83 223	91.30 350	90.25 79	88.09 321	78.76 391	76.37 333	96.43 91	98.39 33	83.79 240	90.43 378	86.57 238	94.20 334	94.80 316

BH-w/o		87.21 301	87.02 296	87.79 329	94.77 275	77.27 310	87.90 322	93.21 292	81.74 290	89.99 304	88.39 366	83.47 242	96.93 300	71.29 370	92.43 361	89.15 376

MS-PatchMatch		88.05 282	87.75 280	88.95 305	93.28 309	77.93 299	87.88 323	92.49 306	75.42 337	92.57 250	93.59 286	80.44 274	94.24 358	81.28 298	92.75 356	94.69 322

DELS-MVS		92.05 191	92.16 182	91.72 228	94.44 287	80.13 256	87.62 324	97.25 138	87.34 210	92.22 265	93.18 296	89.54 175	98.73 151	89.67 175	98.20 204	96.30 265
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		84.01 328	82.20 338	89.41 297	89.04 375	76.37 325	87.57 325	90.98 325	72.71 356	84.46 364	92.45 311	68.08 341	96.48 312	70.58 376	83.97 386	95.38 300

ADS-MVSNet		82.25 339	81.55 340	84.34 358	89.04 375	65.30 382	87.57 325	85.13 372	72.71 356	84.46 364	92.45 311	68.08 341	92.33 368	70.58 376	83.97 386	95.38 300

IterMVS-SCA-FT		91.65 197	91.55 197	91.94 221	93.89 300	79.22 281	87.56 327	93.51 285	91.53 122	95.37 149	96.62 152	78.65 286	98.90 118	91.89 114	94.95 316	97.70 196

IterMVS		90.18 233	90.16 230	90.21 282	93.15 312	75.98 328	87.56 327	92.97 294	86.43 221	94.09 193	96.40 163	78.32 290	97.43 275	87.87 217	94.69 324	97.23 227
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Test_1112_low_res		87.50 295	86.58 302	90.25 280	96.80 164	77.75 303	87.53 329	96.25 202	69.73 373	86.47 350	93.61 285	75.67 314	97.88 239	79.95 312	93.20 349	95.11 306

c3_l		91.32 206	91.42 202	91.00 258	92.29 325	76.79 319	87.52 330	96.42 196	85.76 233	94.72 182	93.89 277	82.73 253	98.16 215	90.93 137	98.55 167	98.04 156

UnsupCasMVSNet_bld		88.50 275	88.03 277	89.90 289	95.52 253	78.88 288	87.39 331	94.02 277	79.32 313	93.06 231	94.02 271	80.72 273	94.27 356	75.16 349	93.08 353	96.54 252

lupinMVS		88.34 278	87.31 286	91.45 239	94.74 277	80.06 258	87.23 332	92.27 308	71.10 363	88.83 319	91.15 332	77.02 304	98.53 180	86.67 236	96.75 276	95.76 287

pmmvs4		88.95 265	87.70 282	92.70 193	94.30 290	85.60 184	87.22 333	92.16 311	74.62 342	89.75 311	94.19 264	77.97 293	96.41 315	82.71 281	96.36 285	96.09 272

WTY-MVS		86.93 308	86.50 307	88.24 321	94.96 266	74.64 336	87.19 334	92.07 314	78.29 321	88.32 333	91.59 328	78.06 292	94.27 356	74.88 350	93.15 351	95.80 285

ET-MVSNet_ETH3D		86.15 312	84.27 323	91.79 225	93.04 315	81.28 242	87.17 335	86.14 358	79.57 308	83.65 369	88.66 361	57.10 382	98.18 213	87.74 219	95.40 305	95.90 282

MVS-HIRNet		78.83 359	80.60 350	73.51 378	93.07 313	47.37 402	87.10 336	78.00 394	68.94 375	77.53 391	97.26 103	71.45 331	94.62 349	63.28 390	88.74 378	78.55 393

xiu_mvs_v2_base		89.00 263	89.19 246	88.46 318	94.86 270	74.63 337	86.97 337	95.60 226	80.88 297	87.83 339	88.62 363	91.04 146	98.81 136	82.51 285	94.38 329	91.93 365

DPM-MVS		89.35 253	88.40 262	92.18 215	96.13 216	84.20 202	86.96 338	96.15 210	75.40 338	87.36 345	91.55 329	83.30 244	98.01 227	82.17 290	96.62 279	94.32 329

eth_miper_zixun_eth		90.72 213	90.61 221	91.05 254	92.04 335	76.84 318	86.91 339	96.67 181	85.21 245	94.41 187	93.92 275	79.53 279	98.26 206	89.76 173	97.02 263	98.06 153

dp		79.28 357	78.62 359	81.24 370	85.97 392	56.45 397	86.91 339	85.26 370	72.97 354	81.45 385	89.17 360	56.01 386	95.45 338	73.19 360	76.68 394	91.82 368

sss		87.23 300	86.82 298	88.46 318	93.96 298	77.94 298	86.84 341	92.78 299	77.59 324	87.61 343	91.83 323	78.75 284	91.92 370	77.84 330	94.20 334	95.52 298

miper_ehance_all_eth		90.48 220	90.42 226	90.69 268	91.62 346	76.57 322	86.83 342	96.18 208	83.38 267	94.06 196	92.66 309	82.20 258	98.04 222	89.79 172	97.02 263	97.45 212

CLD-MVS		91.82 193	91.41 203	93.04 178	96.37 189	83.65 210	86.82 343	97.29 135	84.65 257	92.27 264	89.67 352	92.20 118	97.85 245	83.95 272	99.47 43	97.62 201
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
cl____		90.65 216	90.56 223	90.91 262	91.85 339	76.98 315	86.75 344	95.36 243	85.53 241	94.06 196	94.89 239	77.36 301	97.98 231	90.27 157	98.98 114	97.76 191

DIV-MVS_self_test		90.65 216	90.56 223	90.91 262	91.85 339	76.99 314	86.75 344	95.36 243	85.52 243	94.06 196	94.89 239	77.37 300	97.99 230	90.28 156	98.97 119	97.76 191

PS-MVSNAJ		88.86 268	88.99 252	88.48 317	94.88 268	74.71 335	86.69 346	95.60 226	80.88 297	87.83 339	87.37 371	90.77 151	98.82 131	82.52 284	94.37 330	91.93 365

PVSNet_Blended		88.74 271	88.16 275	90.46 275	94.81 272	78.80 291	86.64 347	96.93 160	74.67 341	88.68 328	89.18 359	86.27 220	98.15 216	80.27 306	96.00 290	94.44 326

MSDG		90.82 210	90.67 220	91.26 247	94.16 292	83.08 220	86.63 348	96.19 207	90.60 144	91.94 270	91.89 322	89.16 178	95.75 331	80.96 303	94.51 327	94.95 310

cl22		89.02 260	88.50 260	90.59 271	89.76 367	76.45 323	86.62 349	94.03 275	82.98 277	92.65 246	92.49 310	72.05 328	97.53 268	88.93 194	97.02 263	97.78 189

CL-MVSNet_self_test		90.04 242	89.90 237	90.47 273	95.24 262	77.81 302	86.60 350	92.62 303	85.64 236	93.25 225	93.92 275	83.84 239	96.06 326	79.93 314	98.03 217	97.53 208

PCF-MVS	84.52 17	89.12 257	87.71 281	93.34 172	96.06 220	85.84 177	86.58 351	97.31 132	68.46 377	93.61 211	93.89 277	87.51 198	98.52 181	67.85 382	98.11 210	95.66 293
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_f		86.65 310	87.13 293	85.19 351	90.28 363	86.11 171	86.52 352	91.66 319	69.76 372	95.73 131	97.21 110	69.51 337	81.28 395	89.15 190	94.40 328	88.17 381

Patchmatch-RL test		88.81 269	88.52 259	89.69 294	95.33 261	79.94 263	86.22 353	92.71 300	78.46 320	95.80 124	94.18 265	66.25 353	95.33 342	89.22 188	98.53 170	93.78 340

Syy-MVS		84.81 322	84.93 316	84.42 357	91.71 343	63.36 391	85.89 354	81.49 383	81.03 294	85.13 358	81.64 389	77.44 297	95.00 346	85.94 249	94.12 337	94.91 313

myMVS_eth3d		79.62 356	78.26 360	83.72 361	91.71 343	61.25 393	85.89 354	81.49 383	81.03 294	85.13 358	81.64 389	32.12 403	95.00 346	71.17 374	94.12 337	94.91 313

FPMVS		84.50 325	83.28 329	88.16 323	96.32 197	94.49 16	85.76 356	85.47 366	83.09 274	85.20 357	94.26 261	63.79 366	86.58 390	63.72 389	91.88 367	83.40 388

IB-MVS	77.21 19	83.11 333	81.05 344	89.29 300	91.15 351	75.85 329	85.66 357	86.00 360	79.70 306	82.02 381	86.61 374	48.26 395	98.39 191	77.84 330	92.22 362	93.63 345
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		91.04 208	90.88 213	91.55 235	94.68 281	80.16 253	85.49 358	92.14 312	90.41 149	94.93 172	95.79 199	85.10 232	96.93 300	85.15 257	94.19 336	97.57 204

test_vis1_rt		85.58 316	84.58 319	88.60 313	87.97 381	86.76 149	85.45 359	93.59 282	66.43 381	87.64 341	89.20 358	79.33 280	85.38 392	81.59 295	89.98 376	93.66 344

new-patchmatchnet		88.97 264	90.79 217	83.50 363	94.28 291	55.83 398	85.34 360	93.56 284	86.18 225	95.47 142	95.73 205	83.10 246	96.51 311	85.40 254	98.06 214	98.16 147

miper_enhance_ethall		88.42 276	87.87 279	90.07 285	88.67 379	75.52 332	85.10 361	95.59 230	75.68 334	92.49 251	89.45 355	78.96 282	97.88 239	87.86 218	97.02 263	96.81 245

HyFIR lowres test		87.19 303	85.51 314	92.24 210	97.12 147	80.51 251	85.03 362	96.06 211	66.11 383	91.66 274	92.98 300	70.12 335	99.14 86	75.29 348	95.23 311	97.07 231

pmmvs3		80.83 351	78.96 358	86.45 341	87.23 386	77.48 307	84.87 363	82.31 380	63.83 388	85.03 360	89.50 354	49.66 393	93.10 364	73.12 361	95.10 313	88.78 380

test0.0.03 1		82.48 338	81.47 342	85.48 348	89.70 368	73.57 348	84.73 364	81.64 382	83.07 275	88.13 336	86.61 374	62.86 370	89.10 386	66.24 386	90.29 374	93.77 341

N_pmnet		88.90 267	87.25 289	93.83 154	94.40 289	93.81 35	84.73 364	87.09 352	79.36 312	93.26 223	92.43 314	79.29 281	91.68 371	77.50 335	97.22 256	96.00 276

GA-MVS		87.70 287	86.82 298	90.31 277	93.27 310	77.22 311	84.72 366	92.79 298	85.11 249	89.82 307	90.07 344	66.80 348	97.76 255	84.56 268	94.27 333	95.96 277

ppachtmachnet_test		88.61 274	88.64 258	88.50 316	91.76 341	70.99 364	84.59 367	92.98 293	79.30 314	92.38 258	93.53 288	79.57 278	97.45 274	86.50 242	97.17 258	97.07 231

CHOSEN 1792x2688		87.19 303	85.92 312	91.00 258	97.13 146	79.41 276	84.51 368	95.60 226	64.14 387	90.07 302	94.81 242	78.26 291	97.14 291	73.34 358	95.38 307	96.46 259

thisisatest0515		84.72 323	82.99 332	89.90 289	92.96 317	75.33 334	84.36 369	83.42 378	77.37 326	88.27 334	86.65 373	53.94 389	98.72 152	82.56 283	97.40 251	95.67 292

cascas		87.02 307	86.28 309	89.25 302	91.56 347	76.45 323	84.33 370	96.78 173	71.01 364	86.89 349	85.91 379	81.35 266	96.94 298	83.09 278	95.60 299	94.35 328

new_pmnet		81.22 347	81.01 346	81.86 367	90.92 355	70.15 367	84.03 371	80.25 389	70.83 365	85.97 353	89.78 350	67.93 344	84.65 393	67.44 383	91.90 366	90.78 373

PAPM		81.91 344	80.11 354	87.31 333	93.87 301	72.32 358	84.02 372	93.22 290	69.47 374	76.13 393	89.84 346	72.15 327	97.23 284	53.27 395	89.02 377	92.37 362

our_test_3		87.55 293	87.59 283	87.44 332	91.76 341	70.48 365	83.83 373	90.55 330	79.79 304	92.06 269	92.17 318	78.63 288	95.63 332	84.77 265	94.73 322	96.22 268

miper_lstm_enhance		89.90 244	89.80 239	90.19 284	91.37 349	77.50 306	83.82 374	95.00 251	84.84 255	93.05 232	94.96 237	76.53 312	95.20 345	89.96 169	98.67 157	97.86 179

test-LLR		83.58 331	83.17 330	84.79 354	89.68 369	66.86 377	83.08 375	84.52 373	83.07 275	82.85 375	84.78 383	62.86 370	93.49 362	82.85 279	94.86 318	94.03 334

TESTMET0.1,1		79.09 358	78.04 361	82.25 366	87.52 384	64.03 389	83.08 375	80.62 387	70.28 370	80.16 387	83.22 386	44.13 398	90.56 376	79.95 312	93.36 346	92.15 363

test-mter		81.21 348	80.01 355	84.79 354	89.68 369	66.86 377	83.08 375	84.52 373	73.85 347	82.85 375	84.78 383	43.66 399	93.49 362	82.85 279	94.86 318	94.03 334

test123		9.49 366	12.01 369	1.91 382	2.87 404	1.30 407	82.38 378	1.34 407	1.36 400	2.84 401	6.56 399	2.45 405	0.97 401	2.73 400	5.56 399	3.47 397

PMMVS		83.00 335	81.11 343	88.66 312	83.81 398	86.44 160	82.24 379	85.65 363	61.75 391	82.07 379	85.64 380	79.75 277	91.59 372	75.99 345	93.09 352	87.94 382

KD-MVS_2432*1600		82.17 341	80.75 348	86.42 342	82.04 399	70.09 368	81.75 380	90.80 327	82.56 281	90.37 296	89.30 356	42.90 400	96.11 324	74.47 352	92.55 359	93.06 353

miper_refine_blended		82.17 341	80.75 348	86.42 342	82.04 399	70.09 368	81.75 380	90.80 327	82.56 281	90.37 296	89.30 356	42.90 400	96.11 324	74.47 352	92.55 359	93.06 353

mvsany_test1		83.91 329	82.93 333	86.84 339	86.18 391	85.93 174	81.11 382	75.03 397	70.80 367	88.57 330	94.63 250	83.08 247	87.38 387	80.39 304	86.57 383	87.21 383

YYNet1		88.17 280	88.24 270	87.93 326	92.21 328	73.62 347	80.75 383	88.77 335	82.51 284	94.99 170	95.11 231	82.70 254	93.70 360	83.33 275	93.83 340	96.48 258

MDA-MVSNet_test_wron		88.16 281	88.23 271	87.93 326	92.22 327	73.71 346	80.71 384	88.84 334	82.52 283	94.88 175	95.14 229	82.70 254	93.61 361	83.28 276	93.80 341	96.46 259

testmvs		9.02 367	11.42 370	1.81 383	2.77 405	1.13 408	79.44 385	1.90 406	1.18 401	2.65 402	6.80 398	1.95 406	0.87 402	2.62 401	3.45 400	3.44 398

PVSNet	76.22 20	82.89 336	82.37 336	84.48 356	93.96 298	64.38 388	78.60 386	88.61 336	71.50 360	84.43 366	86.36 377	74.27 319	94.60 350	69.87 378	93.69 343	94.46 325

PVSNet_0	70.34 21	74.58 361	72.96 364	79.47 373	90.63 357	66.24 380	73.26 387	83.40 379	63.67 389	78.02 390	78.35 393	72.53 324	89.59 382	56.68 393	60.05 397	82.57 391

E-PMN		80.72 352	80.86 347	80.29 372	85.11 394	68.77 373	72.96 388	81.97 381	87.76 202	83.25 374	83.01 387	62.22 373	89.17 385	77.15 338	94.31 332	82.93 389

CHOSEN 280x420		80.04 355	77.97 362	86.23 345	90.13 364	74.53 339	72.87 389	89.59 333	66.38 382	76.29 392	85.32 381	56.96 383	95.36 340	69.49 379	94.72 323	88.79 379

EMVS		80.35 354	80.28 353	80.54 371	84.73 396	69.07 372	72.54 390	80.73 386	87.80 200	81.66 383	81.73 388	62.89 369	89.84 380	75.79 347	94.65 325	82.71 390

PMMVS2		81.31 346	83.44 328	74.92 377	90.52 359	46.49 403	69.19 391	85.23 371	84.30 262	87.95 338	94.71 248	76.95 306	84.36 394	64.07 388	98.09 212	93.89 338

tmp_tt		37.97 364	44.33 367	18.88 381	11.80 403	21.54 405	63.51 392	45.66 405	4.23 398	51.34 398	50.48 396	59.08 380	22.11 400	44.50 398	68.35 396	13.00 396

MVE	59.87 23	73.86 362	72.65 365	77.47 375	87.00 389	74.35 341	61.37 393	60.93 401	67.27 379	69.69 396	86.49 376	81.24 270	72.33 397	56.45 394	83.45 388	85.74 386
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		50.44 363	48.94 366	54.93 379	39.68 402	12.38 406	28.59 394	90.09 331	6.82 397	41.10 399	78.41 392	54.41 388	70.69 398	50.12 396	51.26 398	81.72 392

test_blank		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet_test		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

DCPMVS		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

cdsmvs_eth3d_5k		23.35 365	31.13 368	0.00 384	0.00 406	0.00 409	0.00 395	95.58 232	0.00 402	0.00 403	91.15 332	93.43 84	0.00 403	0.00 402	0.00 401	0.00 399

pcd_1.5k_mvsjas		7.56 368	10.09 371	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	90.77 151	0.00 403	0.00 402	0.00 401	0.00 399

sosnet-low-res		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

sosnet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uncertanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

Regformer		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

ab-mvs-re		7.56 368	10.08 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	90.69 341	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

WAC-MVS						61.25 393								74.55 351

MSC_two_6792asdad				95.90 65	96.54 179	89.57 88		96.87 167					99.41 39	94.06 45	99.30 71	98.72 97

PC_three_1452									75.31 339	95.87 122	95.75 204	92.93 101	96.34 321	87.18 228	98.68 155	98.04 156

No_MVS				95.90 65	96.54 179	89.57 88		96.87 167					99.41 39	94.06 45	99.30 71	98.72 97

test_one_0601					98.26 71	87.14 140		98.18 41	94.25 48	96.99 70	97.36 94	95.13 43

eth-test2					0.00 406

eth-test					0.00 406

ZD-MVS					97.23 139	90.32 78		97.54 112	84.40 260	94.78 178	95.79 199	92.76 107	99.39 49	88.72 201	98.40 179

IU-MVS					98.51 51	86.66 154		96.83 170	72.74 355	95.83 123				93.00 87	99.29 74	98.64 112

test_241102_TWO								98.10 54	91.95 98	97.54 40	97.25 104	95.37 30	99.35 60	93.29 75	99.25 83	98.49 124

test_241102_ONE					98.51 51	86.97 144		98.10 54	91.85 104	97.63 35	97.03 123	96.48 10	98.95 114

test_0728_THIRD									93.26 71	97.40 52	97.35 97	94.69 59	99.34 63	93.88 48	99.42 52	98.89 75

GSMVS																94.75 319

test_part2					98.21 75	89.41 93				96.72 81

sam_mvs1												66.64 351				94.75 319

sam_mvs												66.41 352

MTGPA								97.62 105

test_post											6.07 400	65.74 356	95.84 330

patchmatchnet-post											91.71 325	66.22 354	97.59 266

gm-plane-assit					87.08 388	59.33 395			71.22 361		83.58 385		97.20 286	73.95 355

test9_res														88.16 209	98.40 179	97.83 183

agg_prior2														87.06 231	98.36 188	97.98 165

agg_prior					96.20 208	88.89 106		96.88 166		90.21 299			98.78 143

TestCases				96.00 56	98.02 89	92.17 50		98.43 17	90.48 145	95.04 168	96.74 144	92.54 111	97.86 243	85.11 260	98.98 114	97.98 165

test_prior				94.61 118	95.95 229	87.23 137		97.36 128					98.68 163			97.93 171

新几何1				93.17 177	97.16 144	87.29 135		94.43 267	67.95 378	91.29 278	94.94 238	86.97 208	98.23 208	81.06 302	97.75 233	93.98 336

旧先验1					96.20 208	84.17 203		94.82 257			95.57 213	89.57 174			97.89 228	96.32 264

原ACMM1				92.87 188	96.91 155	84.22 201		97.01 154	76.84 331	89.64 312	94.46 256	88.00 190	98.70 159	81.53 296	98.01 220	95.70 291

testdata2													98.03 223	80.24 308

segment_acmp												92.14 119

testdata				91.03 255	96.87 157	82.01 231		94.28 271	71.55 359	92.46 253	95.42 218	85.65 227	97.38 281	82.64 282	97.27 254	93.70 343

test12				94.43 131	95.95 229	86.75 150		96.24 203		89.76 310		89.79 173	98.79 140		97.95 225	97.75 193

plane_prior7					97.71 112	88.68 109

plane_prior6					97.21 142	88.23 121						86.93 209

plane_prior5								97.81 91					98.95 114	89.26 186	98.51 173	98.60 117

plane_prior4											95.59 209

plane_prior3						88.43 119			90.35 150	93.31 218

plane_prior1					97.38 132

n2								0.00 408

nn								0.00 408

door-mid								92.13 313

lessismore_v0				93.87 151	98.05 85	83.77 209		80.32 388		97.13 60	97.91 59	77.49 296	99.11 93	92.62 97	98.08 213	98.74 95

LGP-MVS_train				96.84 38	98.36 66	92.13 52		98.25 31	91.78 111	97.07 63	97.22 108	96.38 12	99.28 72	92.07 108	99.59 28	99.11 44

test11								96.65 182

door								91.26 322

HQP5-MVS						84.89 192

BP-MVS														86.55 240

HQP4-MVS										88.81 321			98.61 170			98.15 148

HQP3-MVS								97.31 132							97.73 234

HQP2-MVS												84.76 234

NP-MVS					96.82 162	87.10 141					93.40 290

ACMMP++_ref															98.82 139

ACMMP++															99.25 83

Test By Simon												90.61 157

ITE_SJBPF				95.95 59	97.34 135	93.36 40		96.55 191	91.93 100	94.82 176	95.39 222	91.99 121	97.08 293	85.53 253	97.96 224	97.41 215

DeepMVS_CX				53.83 380	70.38 401	64.56 387		48.52 404	33.01 396	65.50 397	74.21 395	56.19 385	46.64 399	38.45 399	70.07 395	50.30 395

High-resolution multi-view benchmark