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		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 8	99.98 1	99.99 1	99.96 1	99.77 1	100.00 1	99.81 8	100.00 1	99.85 12

Gipuma		99.03 51	99.16 36	98.64 174	99.94 2	98.51 102	99.32 23	99.75 22	99.58 23	98.60 200	99.62 30	98.22 65	99.51 313	97.70 129	99.73 132	97.89 336
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 21	99.31 26	99.53 34	99.91 3	98.98 65	99.63 6	99.58 45	99.44 34	99.78 18	99.76 10	96.39 186	99.92 44	99.44 26	99.92 45	99.68 43

pmmvs6		99.67 3	99.70 3	99.60 11	99.90 4	99.27 22	99.53 7	99.76 21	99.64 13	99.84 14	99.83 3	99.50 5	99.87 93	99.36 28	99.92 45	99.64 52

PS-MVSNAJss		99.46 12	99.49 10	99.35 69	99.90 4	98.15 129	99.20 45	99.65 36	99.48 29	99.92 6	99.71 16	98.07 77	99.96 11	99.53 20	100.00 1	99.93 4

testf1		99.25 30	99.16 36	99.51 43	99.89 6	99.63 3	98.71 91	99.69 27	98.90 93	99.43 65	99.35 77	98.86 25	99.67 253	97.81 121	99.81 90	99.24 212

APD_test2		99.25 30	99.16 36	99.51 43	99.89 6	99.63 3	98.71 91	99.69 27	98.90 93	99.43 65	99.35 77	98.86 25	99.67 253	97.81 121	99.81 90	99.24 212

ANet_high		99.57 7	99.67 5	99.28 83	99.89 6	98.09 133	99.14 54	99.93 3	99.82 3	99.93 4	99.81 5	99.17 15	99.94 30	99.31 31	100.00 1	99.82 15

anonymousdsp		99.51 10	99.47 13	99.62 6	99.88 9	99.08 63	99.34 20	99.69 27	98.93 91	99.65 35	99.72 15	98.93 23	99.95 20	99.11 43	100.00 1	99.82 15

v7n		99.53 8	99.57 8	99.41 60	99.88 9	98.54 100	99.45 10	99.61 41	99.66 12	99.68 30	99.66 24	98.44 50	99.95 20	99.73 13	99.96 18	99.75 31

mvs_tets		99.63 5	99.67 5	99.49 48	99.88 9	98.61 92	99.34 20	99.71 24	99.27 52	99.90 9	99.74 12	99.68 2	99.97 4	99.55 19	99.99 5	99.88 7

RRT_MVS		99.09 46	98.94 58	99.55 23	99.87 12	98.82 78	99.48 9	98.16 306	99.49 28	99.59 42	99.65 26	94.79 247	99.95 20	99.45 25	99.96 18	99.88 7

jajsoiax		99.58 6	99.61 7	99.48 51	99.87 12	98.61 92	99.28 37	99.66 35	99.09 76	99.89 11	99.68 18	99.53 4	99.97 4	99.50 22	99.99 5	99.87 9

test_djsdf		99.52 9	99.51 9	99.53 34	99.86 14	98.74 82	99.39 17	99.56 59	99.11 66	99.70 26	99.73 14	99.00 19	99.97 4	99.26 34	99.98 10	99.89 6

MIMVSNet1		99.38 20	99.32 24	99.55 23	99.86 14	99.19 37	99.41 13	99.59 43	99.59 21	99.71 24	99.57 38	97.12 146	99.90 57	99.21 39	99.87 68	99.54 97

bld_raw_dy_0_64		99.07 49	99.00 53	99.29 81	99.85 16	98.18 126	99.11 58	99.40 114	99.33 46	99.38 76	99.44 64	95.21 230	99.97 4	99.31 31	99.98 10	99.73 33

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 21	99.85 16	99.11 59	99.90 1	99.78 19	99.63 15	99.78 18	99.67 22	99.48 6	99.81 167	99.30 33	99.97 14	99.77 24
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
UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 18	99.34 15	99.69 4	99.58 45	99.90 2	99.86 13	99.78 8	99.58 3	99.95 20	99.00 51	99.95 22	99.78 22

mvsmamba		99.24 34	99.15 41	99.49 48	99.83 19	98.85 74	99.41 13	99.55 63	99.54 25	99.40 72	99.52 50	95.86 213	99.91 52	99.32 30	99.95 22	99.70 40

SixPastTwentyTwo		98.75 87	98.62 95	99.16 103	99.83 19	97.96 153	99.28 37	98.20 303	99.37 41	99.70 26	99.65 26	92.65 285	99.93 35	99.04 48	99.84 76	99.60 63

Baseline_NR-MVSNet		98.98 57	98.86 66	99.36 64	99.82 21	98.55 97	97.47 230	99.57 52	99.37 41	99.21 109	99.61 33	96.76 170	99.83 144	98.06 105	99.83 83	99.71 35

pm-mvs1		99.44 13	99.48 12	99.33 76	99.80 22	98.63 89	99.29 33	99.63 37	99.30 50	99.65 35	99.60 35	99.16 17	99.82 154	99.07 45	99.83 83	99.56 86

TransMVSNet (Re)		99.44 13	99.47 13	99.36 64	99.80 22	98.58 95	99.27 39	99.57 52	99.39 39	99.75 21	99.62 30	99.17 15	99.83 144	99.06 46	99.62 177	99.66 47

K. test v3		98.00 179	97.66 201	99.03 128	99.79 24	97.56 183	99.19 49	92.47 370	99.62 18	99.52 52	99.66 24	89.61 307	99.96 11	99.25 36	99.81 90	99.56 86

APD_test1		98.83 75	98.66 89	99.34 72	99.78 25	99.47 6	98.42 127	99.45 98	98.28 128	98.98 139	99.19 106	97.76 99	99.58 292	96.57 206	99.55 203	98.97 256

test_vis3_rt		99.14 39	99.17 34	99.07 118	99.78 25	98.38 109	98.92 76	99.94 1	97.80 162	99.91 8	99.67 22	97.15 145	98.91 366	99.76 11	99.56 200	99.92 5

EGC-MVSNET		85.24 348	80.54 351	99.34 72	99.77 27	99.20 34	99.08 59	99.29 166	12.08 384	20.84 385	99.42 67	97.55 117	99.85 114	97.08 161	99.72 139	98.96 258

Anonymous20240521		98.69 97	98.87 63	98.16 227	99.77 27	95.11 269	99.08 59	99.44 102	99.34 45	99.33 86	99.55 43	94.10 263	99.94 30	99.25 36	99.96 18	99.42 150

FC-MVSNet-test		99.27 27	99.25 30	99.34 72	99.77 27	98.37 111	99.30 32	99.57 52	99.61 20	99.40 72	99.50 52	97.12 146	99.85 114	99.02 50	99.94 30	99.80 18

test_vis1_n		98.31 151	98.50 110	97.73 259	99.76 30	94.17 293	98.68 94	99.91 6	96.31 260	99.79 17	99.57 38	92.85 282	99.42 329	99.79 9	99.84 76	99.60 63

test_fmvs3		99.12 44	99.41 16	98.25 219	99.76 30	95.07 270	99.05 65	99.94 1	97.78 164	99.82 15	99.84 2	98.56 44	99.71 234	99.96 1	99.96 18	99.97 1

XXY-MVS		99.14 39	99.15 41	99.10 112	99.76 30	97.74 173	98.85 82	99.62 38	98.48 115	99.37 79	99.49 56	98.75 31	99.86 102	98.20 98	99.80 100	99.71 35

TDRefinement		99.42 16	99.38 18	99.55 23	99.76 30	99.33 16	99.68 5	99.71 24	99.38 40	99.53 50	99.61 33	98.64 37	99.80 174	98.24 95	99.84 76	99.52 107

tt0805		98.69 97	98.62 95	98.90 145	99.75 34	99.30 17	99.15 53	96.97 336	98.86 96	98.87 166	97.62 313	98.63 39	98.96 363	99.41 27	98.29 321	98.45 312

test_vis1_n_1920		98.40 140	98.92 60	96.81 311	99.74 35	90.76 355	98.15 150	99.91 6	98.33 120	99.89 11	99.55 43	95.07 235	99.88 76	99.76 11	99.93 34	99.79 19

FOURS1					99.73 36	99.67 2	99.43 11	99.54 68	99.43 36	99.26 101

PEN-MVS		99.41 17	99.34 22	99.62 6	99.73 36	99.14 52	99.29 33	99.54 68	99.62 18	99.56 43	99.42 67	98.16 73	99.96 11	98.78 62	99.93 34	99.77 24

lessismore_v0				98.97 135	99.73 36	97.53 185		86.71 383		99.37 79	99.52 50	89.93 305	99.92 44	98.99 52	99.72 139	99.44 143

SteuartSystems-ACMMP		98.79 80	98.54 105	99.54 27	99.73 36	99.16 43	98.23 141	99.31 150	97.92 153	98.90 156	98.90 177	98.00 83	99.88 76	96.15 237	99.72 139	99.58 75
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 168	98.15 160	98.22 222	99.73 36	95.15 266	97.36 236	99.68 32	94.45 309	98.99 138	99.27 92	96.87 160	99.94 30	97.13 158	99.91 53	99.57 80

Vis-MVSNet		99.34 22	99.36 19	99.27 86	99.73 36	98.26 118	99.17 50	99.78 19	99.11 66	99.27 97	99.48 57	98.82 28	99.95 20	98.94 54	99.93 34	99.59 69
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_f		98.67 105	98.87 63	98.05 236	99.72 42	95.59 249	98.51 114	99.81 17	96.30 262	99.78 18	99.82 4	96.14 195	98.63 371	99.82 6	99.93 34	99.95 2

ACMH	96.65 7	99.25 30	99.24 31	99.26 88	99.72 42	98.38 109	99.07 62	99.55 63	98.30 123	99.65 35	99.45 63	99.22 12	99.76 209	98.44 86	99.77 114	99.64 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PS-CasMVS		99.40 18	99.33 23	99.62 6	99.71 44	99.10 60	99.29 33	99.53 71	99.53 26	99.46 60	99.41 70	98.23 62	99.95 20	98.89 58	99.95 22	99.81 17

DTE-MVSNet		99.43 15	99.35 20	99.66 4	99.71 44	99.30 17	99.31 27	99.51 75	99.64 13	99.56 43	99.46 59	98.23 62	99.97 4	98.78 62	99.93 34	99.72 34

WR-MVS_H		99.33 23	99.22 32	99.65 5	99.71 44	99.24 25	99.32 23	99.55 63	99.46 32	99.50 56	99.34 81	97.30 135	99.93 35	98.90 56	99.93 34	99.77 24

HPM-MVS_fast		99.01 52	98.82 69	99.57 16	99.71 44	99.35 12	99.00 69	99.50 77	97.33 205	98.94 152	98.86 187	98.75 31	99.82 154	97.53 136	99.71 144	99.56 86

ACMH+	96.62 9	99.08 48	99.00 53	99.33 76	99.71 44	98.83 76	98.60 101	99.58 45	99.11 66	99.53 50	99.18 109	98.81 29	99.67 253	96.71 198	99.77 114	99.50 112

PMVS	91.26 20	97.86 190	97.94 179	97.65 263	99.71 44	97.94 155	98.52 110	98.68 281	98.99 85	97.52 284	99.35 77	97.41 130	98.18 375	91.59 344	99.67 163	96.82 363
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FIs		99.14 39	99.09 46	99.29 81	99.70 50	98.28 117	99.13 55	99.52 74	99.48 29	99.24 106	99.41 70	96.79 167	99.82 154	98.69 71	99.88 65	99.76 28

VPNet		98.87 70	98.83 68	99.01 130	99.70 50	97.62 182	98.43 125	99.35 132	99.47 31	99.28 95	99.05 137	96.72 173	99.82 154	98.09 103	99.36 237	99.59 69

test_cas_vis1_n_1920		98.33 148	98.68 86	97.27 289	99.69 52	92.29 336	98.03 165	99.85 12	97.62 174	99.96 2	99.62 30	93.98 264	99.74 221	99.52 21	99.86 71	99.79 19

MP-MVS-pluss		98.57 118	98.23 150	99.60 11	99.69 52	99.35 12	97.16 252	99.38 119	94.87 299	98.97 143	98.99 154	98.01 82	99.88 76	97.29 146	99.70 149	99.58 75
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 35	99.32 24	98.96 136	99.68 54	97.35 194	98.84 84	99.48 86	99.69 8	99.63 38	99.68 18	99.03 18	99.96 11	97.97 112	99.92 45	99.57 80

sd_testset		99.28 26	99.31 26	99.19 99	99.68 54	98.06 142	99.41 13	99.30 158	99.69 8	99.63 38	99.68 18	99.25 11	99.96 11	97.25 149	99.92 45	99.57 80

test_fmvs1_n		98.09 173	98.28 144	97.52 276	99.68 54	93.47 316	98.63 97	99.93 3	95.41 288	99.68 30	99.64 28	91.88 294	99.48 318	99.82 6	99.87 68	99.62 56

CHOSEN 1792x2688		97.49 217	97.14 233	98.54 193	99.68 54	96.09 238	96.50 283	99.62 38	91.58 347	98.84 170	98.97 160	92.36 287	99.88 76	96.76 191	99.95 22	99.67 46

tfpnnormal		98.90 67	98.90 62	98.91 143	99.67 58	97.82 166	99.00 69	99.44 102	99.45 33	99.51 55	99.24 99	98.20 68	99.86 102	95.92 246	99.69 152	99.04 244

MTAPA		98.88 69	98.64 92	99.61 9	99.67 58	99.36 11	98.43 125	99.20 189	98.83 100	98.89 158	98.90 177	96.98 156	99.92 44	97.16 153	99.70 149	99.56 86

test_fmvsmvis_n_1920		99.26 29	99.49 10	98.54 193	99.66 60	96.97 214	98.00 171	99.85 12	99.24 54	99.92 6	99.50 52	99.39 8	99.95 20	99.89 3	99.98 10	98.71 295

CP-MVSNet		99.21 36	99.09 46	99.56 21	99.65 61	98.96 70	99.13 55	99.34 138	99.42 37	99.33 86	99.26 94	97.01 154	99.94 30	98.74 66	99.93 34	99.79 19

HPM-MVS		98.79 80	98.53 106	99.59 15	99.65 61	99.29 19	99.16 51	99.43 108	96.74 244	98.61 198	98.38 259	98.62 40	99.87 93	96.47 218	99.67 163	99.59 69
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 113	98.36 134	99.42 58	99.65 61	99.42 7	98.55 106	99.57 52	97.72 168	98.90 156	99.26 94	96.12 197	99.52 309	95.72 257	99.71 144	99.32 193

TSAR-MVS + MP.		98.63 111	98.49 114	99.06 124	99.64 64	97.90 157	98.51 114	98.94 240	96.96 233	99.24 106	98.89 183	97.83 93	99.81 167	96.88 181	99.49 222	99.48 126
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 76	98.72 78	99.12 108	99.64 64	98.54 100	97.98 174	99.68 32	97.62 174	99.34 85	99.18 109	97.54 118	99.77 204	97.79 123	99.74 129	99.04 244

KD-MVS_self_test		99.25 30	99.18 33	99.44 57	99.63 66	99.06 64	98.69 93	99.54 68	99.31 48	99.62 41	99.53 48	97.36 133	99.86 102	99.24 38	99.71 144	99.39 165

EU-MVSNet		97.66 207	98.50 110	95.13 343	99.63 66	85.84 372	98.35 133	98.21 302	98.23 130	99.54 46	99.46 59	95.02 236	99.68 250	98.24 95	99.87 68	99.87 9

HyFIR lowres test		97.19 241	96.60 266	98.96 136	99.62 68	97.28 198	95.17 335	99.50 77	94.21 314	99.01 136	98.32 267	86.61 325	99.99 2	97.10 160	99.84 76	99.60 63

ACMMP_NAP		98.75 87	98.48 115	99.57 16	99.58 69	99.29 19	97.82 191	99.25 178	96.94 235	98.78 177	99.12 124	98.02 81	99.84 130	97.13 158	99.67 163	99.59 69

nrg030		99.40 18	99.35 20	99.54 27	99.58 69	99.13 55	98.98 72	99.48 86	99.68 10	99.46 60	99.26 94	98.62 40	99.73 226	99.17 42	99.92 45	99.76 28

VDDNet		98.21 163	97.95 177	99.01 130	99.58 69	97.74 173	99.01 67	97.29 329	99.67 11	98.97 143	99.50 52	90.45 302	99.80 174	97.88 118	99.20 262	99.48 126

COLMAP_ROB	96.50 10	98.99 54	98.85 67	99.41 60	99.58 69	99.10 60	98.74 86	99.56 59	99.09 76	99.33 86	99.19 106	98.40 52	99.72 233	95.98 244	99.76 125	99.42 150
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvsm_n_1920		99.33 23	99.45 15	98.99 132	99.57 73	97.73 175	97.93 177	99.83 15	99.22 55	99.93 4	99.30 88	99.42 7	99.96 11	99.85 4	99.99 5	99.29 202

ZNCC-MVS		98.68 102	98.40 127	99.54 27	99.57 73	99.21 28	98.46 122	99.29 166	97.28 211	98.11 243	98.39 257	98.00 83	99.87 93	96.86 184	99.64 171	99.55 93

MSP-MVS		98.40 140	98.00 174	99.61 9	99.57 73	99.25 24	98.57 104	99.35 132	97.55 183	99.31 94	97.71 306	94.61 250	99.88 76	96.14 238	99.19 265	99.70 40
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
testgi		98.32 149	98.39 130	98.13 228	99.57 73	95.54 251	97.78 193	99.49 84	97.37 202	99.19 111	97.65 310	98.96 21	99.49 315	96.50 217	98.99 289	99.34 186

MP-MVS		98.46 134	98.09 165	99.54 27	99.57 73	99.22 27	98.50 116	99.19 193	97.61 177	97.58 278	98.66 223	97.40 131	99.88 76	94.72 281	99.60 184	99.54 97
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 91	98.46 119	99.47 54	99.57 73	98.97 66	98.23 141	99.48 86	96.60 249	99.10 121	99.06 130	98.71 34	99.83 144	95.58 264	99.78 110	99.62 56

LGP-MVS_train				99.47 54	99.57 73	98.97 66		99.48 86	96.60 249	99.10 121	99.06 130	98.71 34	99.83 144	95.58 264	99.78 110	99.62 56

IS-MVSNet		98.19 165	97.90 183	99.08 116	99.57 73	97.97 150	99.31 27	98.32 298	99.01 84	98.98 139	99.03 141	91.59 295	99.79 187	95.49 266	99.80 100	99.48 126

dcpmvs_2		98.78 82	99.11 43	97.78 251	99.56 81	93.67 313	99.06 63	99.86 11	99.50 27	99.66 32	99.26 94	97.21 143	99.99 2	98.00 110	99.91 53	99.68 43

test_0402		98.76 86	98.71 80	98.93 140	99.56 81	98.14 131	98.45 124	99.34 138	99.28 51	98.95 146	98.91 174	98.34 58	99.79 187	95.63 261	99.91 53	98.86 274

EPP-MVSNet		98.30 152	98.04 171	99.07 118	99.56 81	97.83 163	99.29 33	98.07 310	99.03 82	98.59 202	99.13 122	92.16 290	99.90 57	96.87 182	99.68 157	99.49 116

ACMMP		98.75 87	98.50 110	99.52 39	99.56 81	99.16 43	98.87 79	99.37 123	97.16 225	98.82 174	99.01 151	97.71 102	99.87 93	96.29 229	99.69 152	99.54 97
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
FMVSNet1		99.17 37	99.17 34	99.17 100	99.55 85	98.24 120	99.20 45	99.44 102	99.21 57	99.43 65	99.55 43	97.82 96	99.86 102	98.42 88	99.89 64	99.41 153

Vis-MVSNet (Re-imp)		97.46 219	97.16 230	98.34 212	99.55 85	96.10 236	98.94 74	98.44 293	98.32 122	98.16 237	98.62 232	88.76 312	99.73 226	93.88 307	99.79 105	99.18 226

ACMM	96.08 12	98.91 65	98.73 76	99.48 51	99.55 85	99.14 52	98.07 159	99.37 123	97.62 174	99.04 132	98.96 163	98.84 27	99.79 187	97.43 140	99.65 169	99.49 116
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 94	98.97 57	97.89 244	99.54 88	94.05 295	98.55 106	99.92 5	96.78 242	99.72 22	99.78 8	96.60 178	99.67 253	99.91 2	99.90 60	99.94 3

mPP-MVS		98.64 109	98.34 137	99.54 27	99.54 88	99.17 39	98.63 97	99.24 183	97.47 189	98.09 245	98.68 218	97.62 111	99.89 67	96.22 232	99.62 177	99.57 80

XVG-ACMP-BASELINE		98.56 119	98.34 137	99.22 96	99.54 88	98.59 94	97.71 201	99.46 95	97.25 214	98.98 139	98.99 154	97.54 118	99.84 130	95.88 247	99.74 129	99.23 214

region2R		98.69 97	98.40 127	99.54 27	99.53 91	99.17 39	98.52 110	99.31 150	97.46 194	98.44 219	98.51 244	97.83 93	99.88 76	96.46 219	99.58 193	99.58 75

PGM-MVS		98.66 106	98.37 133	99.55 23	99.53 91	99.18 38	98.23 141	99.49 84	97.01 232	98.69 187	98.88 184	98.00 83	99.89 67	95.87 250	99.59 188	99.58 75

Patchmatch-RL test		97.26 234	97.02 237	97.99 240	99.52 93	95.53 252	96.13 301	99.71 24	97.47 189	99.27 97	99.16 115	84.30 346	99.62 277	97.89 115	99.77 114	98.81 281

ACMMPR		98.70 94	98.42 125	99.54 27	99.52 93	99.14 52	98.52 110	99.31 150	97.47 189	98.56 207	98.54 240	97.75 100	99.88 76	96.57 206	99.59 188	99.58 75

GST-MVS		98.61 114	98.30 142	99.52 39	99.51 95	99.20 34	98.26 139	99.25 178	97.44 197	98.67 189	98.39 257	97.68 103	99.85 114	96.00 242	99.51 214	99.52 107

Anonymous20231206		98.21 163	98.21 151	98.20 223	99.51 95	95.43 257	98.13 151	99.32 145	96.16 265	98.93 153	98.82 196	96.00 203	99.83 144	97.32 145	99.73 132	99.36 180

ACMP	95.32 15	98.41 138	98.09 165	99.36 64	99.51 95	98.79 80	97.68 204	99.38 119	95.76 278	98.81 176	98.82 196	98.36 54	99.82 154	94.75 278	99.77 114	99.48 126
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DVP-MVS		98.77 85	98.52 107	99.52 39	99.50 98	99.21 28	98.02 167	98.84 262	97.97 148	99.08 123	99.02 142	97.61 112	99.88 76	96.99 168	99.63 174	99.48 126
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				99.60 11	99.50 98	99.23 26	98.02 167	99.32 145					99.88 76	96.99 168	99.63 174	99.68 43

test0726					99.50 98	99.21 28	98.17 149	99.35 132	97.97 148	99.26 101	99.06 130	97.61 112

AllTest		98.44 136	98.20 152	99.16 103	99.50 98	98.55 97	98.25 140	99.58 45	96.80 240	98.88 162	99.06 130	97.65 106	99.57 294	94.45 288	99.61 182	99.37 174

TestCases				99.16 103	99.50 98	98.55 97		99.58 45	96.80 240	98.88 162	99.06 130	97.65 106	99.57 294	94.45 288	99.61 182	99.37 174

XVG-OURS		98.53 127	98.34 137	99.11 110	99.50 98	98.82 78	95.97 305	99.50 77	97.30 209	99.05 130	98.98 158	99.35 9	99.32 341	95.72 257	99.68 157	99.18 226

EG-PatchMatch MVS		98.99 54	99.01 52	98.94 139	99.50 98	97.47 187	98.04 164	99.59 43	98.15 141	99.40 72	99.36 76	98.58 43	99.76 209	98.78 62	99.68 157	99.59 69

SED-MVS		98.91 65	98.72 78	99.49 48	99.49 105	99.17 39	98.10 156	99.31 150	98.03 145	99.66 32	99.02 142	98.36 54	99.88 76	96.91 174	99.62 177	99.41 153

IU-MVS					99.49 105	99.15 47		98.87 253	92.97 332	99.41 69				96.76 191	99.62 177	99.66 47

test_241102_ONE					99.49 105	99.17 39		99.31 150	97.98 147	99.66 32	98.90 177	98.36 54	99.48 318

UA-Net		99.47 11	99.40 17	99.70 2	99.49 105	99.29 19	99.80 3	99.72 23	99.82 3	99.04 132	99.81 5	98.05 80	99.96 11	98.85 59	99.99 5	99.86 11

HFP-MVS		98.71 91	98.44 122	99.51 43	99.49 105	99.16 43	98.52 110	99.31 150	97.47 189	98.58 204	98.50 248	97.97 87	99.85 114	96.57 206	99.59 188	99.53 104

VPA-MVSNet		99.30 25	99.30 28	99.28 83	99.49 105	98.36 114	99.00 69	99.45 98	99.63 15	99.52 52	99.44 64	98.25 60	99.88 76	99.09 44	99.84 76	99.62 56

XVG-OURS-SEG-HR		98.49 131	98.28 144	99.14 106	99.49 105	98.83 76	96.54 281	99.48 86	97.32 207	99.11 118	98.61 234	99.33 10	99.30 344	96.23 231	98.38 318	99.28 204

114514_t		96.50 276	95.77 283	98.69 171	99.48 112	97.43 191	97.84 190	99.55 63	81.42 378	96.51 330	98.58 237	95.53 221	99.67 253	93.41 319	99.58 193	98.98 253

IterMVS-LS		98.55 123	98.70 83	98.09 229	99.48 112	94.73 278	97.22 248	99.39 117	98.97 87	99.38 76	99.31 87	96.00 203	99.93 35	98.58 76	99.97 14	99.60 63
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v8		99.01 52	99.16 36	98.57 185	99.47 114	96.31 233	98.90 77	99.47 93	99.03 82	99.52 52	99.57 38	96.93 157	99.81 167	99.60 15	99.98 10	99.60 63

XVS		98.72 90	98.45 120	99.53 34	99.46 115	99.21 28	98.65 95	99.34 138	98.62 107	97.54 282	98.63 230	97.50 124	99.83 144	96.79 187	99.53 209	99.56 86

X-MVStestdata		94.32 318	92.59 336	99.53 34	99.46 115	99.21 28	98.65 95	99.34 138	98.62 107	97.54 282	45.85 382	97.50 124	99.83 144	96.79 187	99.53 209	99.56 86

test20.03		98.78 82	98.77 74	98.78 160	99.46 115	97.20 204	97.78 193	99.24 183	99.04 81	99.41 69	98.90 177	97.65 106	99.76 209	97.70 129	99.79 105	99.39 165

CSCG		98.68 102	98.50 110	99.20 97	99.45 118	98.63 89	98.56 105	99.57 52	97.87 157	98.85 167	98.04 288	97.66 105	99.84 130	96.72 196	99.81 90	99.13 234

GeoE		99.05 50	98.99 56	99.25 91	99.44 119	98.35 115	98.73 88	99.56 59	98.42 116	98.91 155	98.81 198	98.94 22	99.91 52	98.35 90	99.73 132	99.49 116

v148		98.45 135	98.60 100	98.00 239	99.44 119	94.98 271	97.44 232	99.06 221	98.30 123	99.32 92	98.97 160	96.65 176	99.62 277	98.37 89	99.85 72	99.39 165

v10		98.97 58	99.11 43	98.55 190	99.44 119	96.21 235	98.90 77	99.55 63	98.73 101	99.48 57	99.60 35	96.63 177	99.83 144	99.70 14	99.99 5	99.61 62

V42		98.78 82	98.78 73	98.76 163	99.44 119	97.04 211	98.27 138	99.19 193	97.87 157	99.25 105	99.16 115	96.84 161	99.78 198	99.21 39	99.84 76	99.46 135

MDA-MVSNet-bldmvs		97.94 183	97.91 182	98.06 234	99.44 119	94.96 272	96.63 279	99.15 209	98.35 118	98.83 171	99.11 125	94.31 256	99.85 114	96.60 203	98.72 304	99.37 174

casdiffmvs_mvg		99.12 44	99.16 36	98.99 132	99.43 124	97.73 175	98.00 171	99.62 38	99.22 55	99.55 45	99.22 102	98.93 23	99.75 216	98.66 73	99.81 90	99.50 112
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test1111		96.49 277	96.82 249	95.52 337	99.42 125	87.08 369	99.22 42	87.14 382	99.11 66	99.46 60	99.58 37	88.69 313	99.86 102	98.80 61	99.95 22	99.62 56

v2v482		98.56 119	98.62 95	98.37 210	99.42 125	95.81 246	97.58 218	99.16 204	97.90 155	99.28 95	99.01 151	95.98 207	99.79 187	99.33 29	99.90 60	99.51 109

OPM-MVS		98.56 119	98.32 141	99.25 91	99.41 127	98.73 85	97.13 254	99.18 197	97.10 228	98.75 183	98.92 173	98.18 69	99.65 269	96.68 200	99.56 200	99.37 174
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 175	98.08 168	98.04 237	99.41 127	94.59 284	94.59 353	99.40 114	97.50 186	98.82 174	98.83 193	96.83 163	99.84 130	97.50 138	99.81 90	99.71 35

test_one_0601					99.39 129	99.20 34		99.31 150	98.49 114	98.66 191	99.02 142	97.64 109

mvsany_test3		98.87 70	98.92 60	98.74 170	99.38 130	96.94 217	98.58 103	99.10 216	96.49 253	99.96 2	99.81 5	98.18 69	99.45 324	98.97 53	99.79 105	99.83 14

patch_mono-2		98.51 130	98.63 93	98.17 225	99.38 130	94.78 275	97.36 236	99.69 27	98.16 140	98.49 215	99.29 89	97.06 149	99.97 4	98.29 94	99.91 53	99.76 28

test2506		92.39 341	91.89 344	93.89 354	99.38 130	82.28 383	99.32 23	66.03 390	99.08 78	98.77 180	99.57 38	66.26 387	99.84 130	98.71 69	99.95 22	99.54 97

ECVR-MVS		96.42 279	96.61 264	95.85 329	99.38 130	88.18 365	99.22 42	86.00 384	99.08 78	99.36 81	99.57 38	88.47 318	99.82 154	98.52 82	99.95 22	99.54 97

casdiffmvs		98.95 61	99.00 53	98.81 153	99.38 130	97.33 195	97.82 191	99.57 52	99.17 64	99.35 83	99.17 113	98.35 57	99.69 241	98.46 85	99.73 132	99.41 153
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		98.96 60	99.02 51	98.76 163	99.38 130	97.26 199	98.49 117	99.50 77	98.86 96	99.19 111	99.06 130	98.23 62	99.69 241	98.71 69	99.76 125	99.33 191

TranMVSNet+NR-MVSNet		99.17 37	99.07 49	99.46 56	99.37 136	98.87 73	98.39 129	99.42 111	99.42 37	99.36 81	99.06 130	98.38 53	99.95 20	98.34 91	99.90 60	99.57 80

tttt0517		95.64 299	94.98 308	97.64 265	99.36 137	93.81 309	98.72 89	90.47 378	98.08 144	98.67 189	98.34 264	73.88 379	99.92 44	97.77 124	99.51 214	99.20 219

test_part2					99.36 137	99.10 60				99.05 130

v1144		98.60 115	98.66 89	98.41 206	99.36 137	95.90 242	97.58 218	99.34 138	97.51 185	99.27 97	99.15 119	96.34 191	99.80 174	99.47 24	99.93 34	99.51 109

CP-MVS		98.70 94	98.42 125	99.52 39	99.36 137	99.12 57	98.72 89	99.36 127	97.54 184	98.30 229	98.40 256	97.86 92	99.89 67	96.53 215	99.72 139	99.56 86

Test_1112_low_res		96.99 257	96.55 268	98.31 215	99.35 141	95.47 255	95.84 316	99.53 71	91.51 349	96.80 320	98.48 251	91.36 297	99.83 144	96.58 204	99.53 209	99.62 56

DeepC-MVS	97.60 4	98.97 58	98.93 59	99.10 112	99.35 141	97.98 149	98.01 170	99.46 95	97.56 182	99.54 46	99.50 52	98.97 20	99.84 130	98.06 105	99.92 45	99.49 116
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 233	96.86 245	98.58 183	99.34 143	96.32 232	96.75 273	99.58 45	93.14 330	96.89 315	97.48 320	92.11 291	99.86 102	96.91 174	99.54 205	99.57 80

SF-MVS		98.53 127	98.27 146	99.32 78	99.31 144	98.75 81	98.19 145	99.41 112	96.77 243	98.83 171	98.90 177	97.80 97	99.82 154	95.68 260	99.52 212	99.38 172

CPTT-MVS		97.84 196	97.36 220	99.27 86	99.31 144	98.46 105	98.29 136	99.27 172	94.90 298	97.83 262	98.37 260	94.90 238	99.84 130	93.85 309	99.54 205	99.51 109

UnsupCasMVSNet_eth		97.89 186	97.60 206	98.75 166	99.31 144	97.17 207	97.62 212	99.35 132	98.72 102	98.76 182	98.68 218	92.57 286	99.74 221	97.76 128	95.60 369	99.34 186

pmmvs-eth3d		98.47 133	98.34 137	98.86 147	99.30 147	97.76 171	97.16 252	99.28 169	95.54 281	99.42 68	99.19 106	97.27 138	99.63 275	97.89 115	99.97 14	99.20 219

Anonymous20231211		99.27 27	99.27 29	99.26 88	99.29 148	98.18 126	99.49 8	99.51 75	99.70 7	99.80 16	99.68 18	96.84 161	99.83 144	99.21 39	99.91 53	99.77 24

UnsupCasMVSNet_bld		97.30 231	96.92 241	98.45 202	99.28 149	96.78 224	96.20 299	99.27 172	95.42 285	98.28 231	98.30 268	93.16 273	99.71 234	94.99 273	97.37 346	98.87 273

EC-MVSNet		99.09 46	99.05 50	99.20 97	99.28 149	98.93 71	99.24 41	99.84 14	99.08 78	98.12 242	98.37 260	98.72 33	99.90 57	99.05 47	99.77 114	98.77 289

DPE-MVS		98.59 117	98.26 147	99.57 16	99.27 151	99.15 47	97.01 257	99.39 117	97.67 170	99.44 64	98.99 154	97.53 120	99.89 67	95.40 268	99.68 157	99.66 47
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 195	98.18 155	96.87 307	99.27 151	91.16 353	95.53 324	99.25 178	99.10 73	99.41 69	99.35 77	93.10 275	99.96 11	98.65 74	99.94 30	99.49 116

v1192		98.60 115	98.66 89	98.41 206	99.27 151	95.88 243	97.52 224	99.36 127	97.41 198	99.33 86	99.20 105	96.37 189	99.82 154	99.57 17	99.92 45	99.55 93

N_pmnet		97.63 209	97.17 229	98.99 132	99.27 151	97.86 160	95.98 304	93.41 367	95.25 290	99.47 59	98.90 177	95.63 218	99.85 114	96.91 174	99.73 132	99.27 205

FPMVS		93.44 333	92.23 338	97.08 296	99.25 155	97.86 160	95.61 321	97.16 331	92.90 334	93.76 372	98.65 225	75.94 376	95.66 381	79.30 380	97.49 341	97.73 346

new-patchmatchnet		98.35 146	98.74 75	97.18 292	99.24 156	92.23 338	96.42 288	99.48 86	98.30 123	99.69 28	99.53 48	97.44 129	99.82 154	98.84 60	99.77 114	99.49 116

MCST-MVS		98.00 179	97.63 204	99.10 112	99.24 156	98.17 128	96.89 266	98.73 279	95.66 279	97.92 254	97.70 308	97.17 144	99.66 264	96.18 236	99.23 258	99.47 133

UniMVSNet (Re)		98.87 70	98.71 80	99.35 69	99.24 156	98.73 85	97.73 200	99.38 119	98.93 91	99.12 117	98.73 209	96.77 168	99.86 102	98.63 75	99.80 100	99.46 135

jason		97.45 221	97.35 221	97.76 255	99.24 156	93.93 303	95.86 313	98.42 294	94.24 313	98.50 214	98.13 278	94.82 242	99.91 52	97.22 150	99.73 132	99.43 147
jason: jason.
IterMVS		97.73 201	98.11 164	96.57 315	99.24 156	90.28 356	95.52 326	99.21 187	98.86 96	99.33 86	99.33 83	93.11 274	99.94 30	98.49 84	99.94 30	99.48 126
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 123	98.62 95	98.32 213	99.22 161	95.58 250	97.51 226	99.45 98	97.16 225	99.45 63	99.24 99	96.12 197	99.85 114	99.60 15	99.88 65	99.55 93

ITE_SJBPF				98.87 146	99.22 161	98.48 104		99.35 132	97.50 186	98.28 231	98.60 235	97.64 109	99.35 337	93.86 308	99.27 252	98.79 287

h-mvs33		97.77 199	97.33 223	99.10 112	99.21 163	97.84 162	98.35 133	98.57 287	99.11 66	98.58 204	99.02 142	88.65 316	99.96 11	98.11 101	96.34 361	99.49 116

v144192		98.54 125	98.57 103	98.45 202	99.21 163	95.98 240	97.63 211	99.36 127	97.15 227	99.32 92	99.18 109	95.84 214	99.84 130	99.50 22	99.91 53	99.54 97

APDe-MVS		98.99 54	98.79 72	99.60 11	99.21 163	99.15 47	98.87 79	99.48 86	97.57 180	99.35 83	99.24 99	97.83 93	99.89 67	97.88 118	99.70 149	99.75 31

DP-MVS		98.93 63	98.81 71	99.28 83	99.21 163	98.45 106	98.46 122	99.33 143	99.63 15	99.48 57	99.15 119	97.23 141	99.75 216	97.17 152	99.66 168	99.63 55

SR-MVS-dyc-post		98.81 78	98.55 104	99.57 16	99.20 167	99.38 8	98.48 120	99.30 158	98.64 103	98.95 146	98.96 163	97.49 127	99.86 102	96.56 210	99.39 233	99.45 139

RE-MVS-def			98.58 102		99.20 167	99.38 8	98.48 120	99.30 158	98.64 103	98.95 146	98.96 163	97.75 100		96.56 210	99.39 233	99.45 139

v1921920		98.54 125	98.60 100	98.38 209	99.20 167	95.76 248	97.56 220	99.36 127	97.23 220	99.38 76	99.17 113	96.02 201	99.84 130	99.57 17	99.90 60	99.54 97

thisisatest0530		95.27 306	94.45 315	97.74 257	99.19 170	94.37 287	97.86 188	90.20 379	97.17 224	98.22 233	97.65 310	73.53 380	99.90 57	96.90 179	99.35 239	98.95 259

Anonymous20240529		98.93 63	98.87 63	99.12 108	99.19 170	98.22 125	99.01 67	98.99 238	99.25 53	99.54 46	99.37 73	97.04 150	99.80 174	97.89 115	99.52 212	99.35 184

APD-MVS_3200maxsize		98.84 74	98.61 99	99.53 34	99.19 170	99.27 22	98.49 117	99.33 143	98.64 103	99.03 135	98.98 158	97.89 90	99.85 114	96.54 214	99.42 230	99.46 135

HQP_MVS		97.99 182	97.67 198	98.93 140	99.19 170	97.65 179	97.77 195	99.27 172	98.20 134	97.79 265	97.98 291	94.90 238	99.70 237	94.42 290	99.51 214	99.45 139

plane_prior7					99.19 170	97.87 159

ab-mvs		98.41 138	98.36 134	98.59 182	99.19 170	97.23 200	99.32 23	98.81 267	97.66 171	98.62 196	99.40 72	96.82 164	99.80 174	95.88 247	99.51 214	98.75 292

F-COLMAP		97.30 231	96.68 258	99.14 106	99.19 170	98.39 108	97.27 244	99.30 158	92.93 333	96.62 325	98.00 289	95.73 216	99.68 250	92.62 333	98.46 317	99.35 184

SR-MVS		98.71 91	98.43 123	99.57 16	99.18 177	99.35 12	98.36 132	99.29 166	98.29 126	98.88 162	98.85 190	97.53 120	99.87 93	96.14 238	99.31 245	99.48 126

UniMVSNet_NR-MVSNet		98.86 73	98.68 86	99.40 62	99.17 178	98.74 82	97.68 204	99.40 114	99.14 65	99.06 125	98.59 236	96.71 174	99.93 35	98.57 78	99.77 114	99.53 104

LF4IMVS		97.90 184	97.69 197	98.52 195	99.17 178	97.66 178	97.19 251	99.47 93	96.31 260	97.85 261	98.20 275	96.71 174	99.52 309	94.62 282	99.72 139	98.38 317

SMA-MVS		98.40 140	98.03 172	99.51 43	99.16 180	99.21 28	98.05 162	99.22 186	94.16 315	98.98 139	99.10 127	97.52 122	99.79 187	96.45 220	99.64 171	99.53 104
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
DU-MVS		98.82 76	98.63 93	99.39 63	99.16 180	98.74 82	97.54 222	99.25 178	98.84 99	99.06 125	98.76 206	96.76 170	99.93 35	98.57 78	99.77 114	99.50 112

NR-MVSNet		98.95 61	98.82 69	99.36 64	99.16 180	98.72 87	99.22 42	99.20 189	99.10 73	99.72 22	98.76 206	96.38 188	99.86 102	98.00 110	99.82 86	99.50 112

MVS_111021_LR		98.30 152	98.12 163	98.83 150	99.16 180	98.03 144	96.09 302	99.30 158	97.58 179	98.10 244	98.24 271	98.25 60	99.34 338	96.69 199	99.65 169	99.12 235

DSMNet-mixed		97.42 223	97.60 206	96.87 307	99.15 184	91.46 344	98.54 108	99.12 212	92.87 335	97.58 278	99.63 29	96.21 194	99.90 57	95.74 256	99.54 205	99.27 205

D2MVS		97.84 196	97.84 188	97.83 247	99.14 185	94.74 277	96.94 261	98.88 251	95.84 276	98.89 158	98.96 163	94.40 254	99.69 241	97.55 133	99.95 22	99.05 240

pmmvs5		97.64 208	97.49 212	98.08 232	99.14 185	95.12 268	96.70 276	99.05 224	93.77 322	98.62 196	98.83 193	93.23 271	99.75 216	98.33 93	99.76 125	99.36 180

CS-MVS-test		99.13 42	99.09 46	99.26 88	99.13 187	98.97 66	99.31 27	99.88 9	99.44 34	98.16 237	98.51 244	98.64 37	99.93 35	98.91 55	99.85 72	98.88 272

VDD-MVS		98.56 119	98.39 130	99.07 118	99.13 187	98.07 139	98.59 102	97.01 334	99.59 21	99.11 118	99.27 92	94.82 242	99.79 187	98.34 91	99.63 174	99.34 186

save fliter					99.11 189	97.97 150	96.53 282	99.02 232	98.24 129

APD-MVS		98.10 170	97.67 198	99.42 58	99.11 189	98.93 71	97.76 197	99.28 169	94.97 296	98.72 186	98.77 204	97.04 150	99.85 114	93.79 310	99.54 205	99.49 116
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 97	98.71 80	98.62 178	99.10 191	96.37 230	97.23 245	98.87 253	99.20 59	99.19 111	98.99 154	97.30 135	99.85 114	98.77 65	99.79 105	99.65 51

EI-MVSNet		98.40 140	98.51 108	98.04 237	99.10 191	94.73 278	97.20 249	98.87 253	98.97 87	99.06 125	99.02 142	96.00 203	99.80 174	98.58 76	99.82 86	99.60 63

CVMVSNet		96.25 284	97.21 228	93.38 360	99.10 191	80.56 386	97.20 249	98.19 305	96.94 235	99.00 137	99.02 142	89.50 309	99.80 174	96.36 225	99.59 188	99.78 22

EI-MVSNet-Vis-set		98.68 102	98.70 83	98.63 177	99.09 194	96.40 229	97.23 245	98.86 258	99.20 59	99.18 115	98.97 160	97.29 137	99.85 114	98.72 68	99.78 110	99.64 52

HPM-MVS++		98.10 170	97.64 203	99.48 51	99.09 194	99.13 55	97.52 224	98.75 276	97.46 194	96.90 314	97.83 301	96.01 202	99.84 130	95.82 254	99.35 239	99.46 135

DP-MVS Recon		97.33 229	96.92 241	98.57 185	99.09 194	97.99 146	96.79 269	99.35 132	93.18 329	97.71 269	98.07 286	95.00 237	99.31 342	93.97 303	99.13 273	98.42 316

MVS_111021_HR		98.25 160	98.08 168	98.75 166	99.09 194	97.46 188	95.97 305	99.27 172	97.60 178	97.99 252	98.25 270	98.15 75	99.38 335	96.87 182	99.57 197	99.42 150

9.14			97.78 190		99.07 198		97.53 223	99.32 145	95.53 282	98.54 211	98.70 215	97.58 114	99.76 209	94.32 295	99.46 224

PAPM_NR		96.82 264	96.32 274	98.30 216	99.07 198	96.69 226	97.48 228	98.76 273	95.81 277	96.61 326	96.47 345	94.12 262	99.17 355	90.82 356	97.78 338	99.06 239

TAMVS		98.24 161	98.05 170	98.80 155	99.07 198	97.18 206	97.88 184	98.81 267	96.66 248	99.17 116	99.21 103	94.81 244	99.77 204	96.96 172	99.88 65	99.44 143

CLD-MVS		97.49 217	97.16 230	98.48 199	99.07 198	97.03 212	94.71 346	99.21 187	94.46 307	98.06 247	97.16 332	97.57 115	99.48 318	94.46 287	99.78 110	98.95 259
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CS-MVS		99.13 42	99.10 45	99.24 93	99.06 202	99.15 47	99.36 19	99.88 9	99.36 44	98.21 234	98.46 252	98.68 36	99.93 35	99.03 49	99.85 72	98.64 304

thres100view900		94.19 321	93.67 325	95.75 332	99.06 202	91.35 347	98.03 165	94.24 363	98.33 120	97.40 293	94.98 369	79.84 362	99.62 277	83.05 373	98.08 333	96.29 367

thres600view7		94.45 316	93.83 322	96.29 320	99.06 202	91.53 343	97.99 173	94.24 363	98.34 119	97.44 291	95.01 367	79.84 362	99.67 253	84.33 371	98.23 322	97.66 349

plane_prior1					99.05 205

YYNet1		97.60 210	97.67 198	97.39 285	99.04 206	93.04 323	95.27 332	98.38 297	97.25 214	98.92 154	98.95 167	95.48 225	99.73 226	96.99 168	98.74 302	99.41 153

MDA-MVSNet_test_wron		97.60 210	97.66 201	97.41 284	99.04 206	93.09 319	95.27 332	98.42 294	97.26 213	98.88 162	98.95 167	95.43 226	99.73 226	97.02 165	98.72 304	99.41 153

MIMVSNet		96.62 271	96.25 278	97.71 260	99.04 206	94.66 281	99.16 51	96.92 340	97.23 220	97.87 258	99.10 127	86.11 331	99.65 269	91.65 342	99.21 261	98.82 277

PatchMatch-RL		97.24 237	96.78 252	98.61 180	99.03 209	97.83 163	96.36 291	99.06 221	93.49 327	97.36 296	97.78 302	95.75 215	99.49 315	93.44 318	98.77 301	98.52 308

ZD-MVS					99.01 210	98.84 75		99.07 220	94.10 317	98.05 249	98.12 280	96.36 190	99.86 102	92.70 332	99.19 265

CDPH-MVS		97.26 234	96.66 261	99.07 118	99.00 211	98.15 129	96.03 303	99.01 235	91.21 353	97.79 265	97.85 300	96.89 159	99.69 241	92.75 330	99.38 236	99.39 165

diffmvs		98.22 162	98.24 149	98.17 225	99.00 211	95.44 256	96.38 290	99.58 45	97.79 163	98.53 212	98.50 248	96.76 170	99.74 221	97.95 114	99.64 171	99.34 186
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WR-MVS		98.40 140	98.19 154	99.03 128	99.00 211	97.65 179	96.85 267	98.94 240	98.57 112	98.89 158	98.50 248	95.60 219	99.85 114	97.54 135	99.85 72	99.59 69

plane_prior6					98.99 214	97.70 177						94.90 238

xiu_mvs_v1_base_debu		97.86 190	98.17 156	96.92 304	98.98 215	93.91 304	96.45 285	99.17 201	97.85 159	98.41 222	97.14 334	98.47 47	99.92 44	98.02 107	99.05 279	96.92 360

xiu_mvs_v1_base		97.86 190	98.17 156	96.92 304	98.98 215	93.91 304	96.45 285	99.17 201	97.85 159	98.41 222	97.14 334	98.47 47	99.92 44	98.02 107	99.05 279	96.92 360

xiu_mvs_v1_base_debi		97.86 190	98.17 156	96.92 304	98.98 215	93.91 304	96.45 285	99.17 201	97.85 159	98.41 222	97.14 334	98.47 47	99.92 44	98.02 107	99.05 279	96.92 360

MVP-Stereo		98.08 174	97.92 181	98.57 185	98.96 218	96.79 221	97.90 182	99.18 197	96.41 256	98.46 217	98.95 167	95.93 210	99.60 284	96.51 216	98.98 291	99.31 197
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 140	98.68 86	97.54 274	98.96 218	97.99 146	97.88 184	99.36 127	98.20 134	99.63 38	99.04 139	98.76 30	95.33 383	96.56 210	99.74 129	99.31 197
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
新几何1				98.91 143	98.94 220	97.76 171		98.76 273	87.58 370	96.75 321	98.10 282	94.80 245	99.78 198	92.73 331	99.00 288	99.20 219

USDC		97.41 224	97.40 216	97.44 282	98.94 220	93.67 313	95.17 335	99.53 71	94.03 319	98.97 143	99.10 127	95.29 228	99.34 338	95.84 253	99.73 132	99.30 200

tfpn200view9		94.03 325	93.44 327	95.78 331	98.93 222	91.44 345	97.60 215	94.29 361	97.94 151	97.10 301	94.31 375	79.67 364	99.62 277	83.05 373	98.08 333	96.29 367

testdata				98.09 229	98.93 222	95.40 258		98.80 269	90.08 361	97.45 290	98.37 260	95.26 229	99.70 237	93.58 314	98.95 293	99.17 230

thres400		94.14 323	93.44 327	96.24 322	98.93 222	91.44 345	97.60 215	94.29 361	97.94 151	97.10 301	94.31 375	79.67 364	99.62 277	83.05 373	98.08 333	97.66 349

TAPA-MVS	96.21 11	96.63 270	95.95 281	98.65 173	98.93 222	98.09 133	96.93 263	99.28 169	83.58 376	98.13 241	97.78 302	96.13 196	99.40 331	93.52 315	99.29 250	98.45 312
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 226	96.93 218	95.54 323	98.78 272	85.72 373	96.86 317	98.11 281	94.43 252			99.10 278	99.23 214

PVSNet_BlendedMVS		97.55 214	97.53 209	97.60 267	98.92 226	93.77 311	96.64 278	99.43 108	94.49 305	97.62 274	99.18 109	96.82 164	99.67 253	94.73 279	99.93 34	99.36 180

PVSNet_Blended		96.88 260	96.68 258	97.47 280	98.92 226	93.77 311	94.71 346	99.43 108	90.98 355	97.62 274	97.36 328	96.82 164	99.67 253	94.73 279	99.56 200	98.98 253

MSDG		97.71 203	97.52 210	98.28 218	98.91 229	96.82 220	94.42 356	99.37 123	97.65 172	98.37 227	98.29 269	97.40 131	99.33 340	94.09 301	99.22 259	98.68 302

Anonymous202405211		97.90 184	97.50 211	99.08 116	98.90 230	98.25 119	98.53 109	96.16 348	98.87 95	99.11 118	98.86 187	90.40 303	99.78 198	97.36 143	99.31 245	99.19 224

原ACMM1				98.35 211	98.90 230	96.25 234		98.83 266	92.48 339	96.07 340	98.10 282	95.39 227	99.71 234	92.61 334	98.99 289	99.08 237

GBi-Net		98.65 107	98.47 117	99.17 100	98.90 230	98.24 120	99.20 45	99.44 102	98.59 109	98.95 146	99.55 43	94.14 259	99.86 102	97.77 124	99.69 152	99.41 153

test1		98.65 107	98.47 117	99.17 100	98.90 230	98.24 120	99.20 45	99.44 102	98.59 109	98.95 146	99.55 43	94.14 259	99.86 102	97.77 124	99.69 152	99.41 153

FMVSNet2		98.49 131	98.40 127	98.75 166	98.90 230	97.14 210	98.61 100	99.13 211	98.59 109	99.19 111	99.28 90	94.14 259	99.82 154	97.97 112	99.80 100	99.29 202

OMC-MVS		97.88 188	97.49 212	99.04 127	98.89 235	98.63 89	96.94 261	99.25 178	95.02 294	98.53 212	98.51 244	97.27 138	99.47 321	93.50 317	99.51 214	99.01 248

MVSFormer		98.26 158	98.43 123	97.77 252	98.88 236	93.89 307	99.39 17	99.56 59	99.11 66	98.16 237	98.13 278	93.81 267	99.97 4	99.26 34	99.57 197	99.43 147

lupinMVS		97.06 250	96.86 245	97.65 263	98.88 236	93.89 307	95.48 327	97.97 312	93.53 325	98.16 237	97.58 314	93.81 267	99.91 52	96.77 190	99.57 197	99.17 230

dmvs_re		95.98 290	95.39 298	97.74 257	98.86 238	97.45 189	98.37 131	95.69 355	97.95 150	96.56 327	95.95 353	90.70 300	97.68 377	88.32 363	96.13 365	98.11 327

DELS-MVS		98.27 156	98.20 152	98.48 199	98.86 238	96.70 225	95.60 322	99.20 189	97.73 166	98.45 218	98.71 212	97.50 124	99.82 154	98.21 97	99.59 188	98.93 264
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
TinyColmap		97.89 186	97.98 175	97.60 267	98.86 238	94.35 288	96.21 298	99.44 102	97.45 196	99.06 125	98.88 184	97.99 86	99.28 348	94.38 294	99.58 193	99.18 226

LCM-MVSNet-Re		98.64 109	98.48 115	99.11 110	98.85 241	98.51 102	98.49 117	99.83 15	98.37 117	99.69 28	99.46 59	98.21 67	99.92 44	94.13 300	99.30 248	98.91 268

pmmvs4		97.58 213	97.28 224	98.51 196	98.84 242	96.93 218	95.40 330	98.52 290	93.60 324	98.61 198	98.65 225	95.10 234	99.60 284	96.97 171	99.79 105	98.99 252

NP-MVS					98.84 242	97.39 193					96.84 337

sss		97.21 239	96.93 239	98.06 234	98.83 244	95.22 264	96.75 273	98.48 292	94.49 305	97.27 297	97.90 297	92.77 283	99.80 174	96.57 206	99.32 243	99.16 233

PVSNet	93.40 17	95.67 297	95.70 286	95.57 336	98.83 244	88.57 361	92.50 373	97.72 317	92.69 337	96.49 333	96.44 346	93.72 270	99.43 327	93.61 312	99.28 251	98.71 295

MVE	83.40 22	92.50 340	91.92 343	94.25 350	98.83 244	91.64 342	92.71 372	83.52 386	95.92 274	86.46 383	95.46 363	95.20 231	95.40 382	80.51 378	98.64 311	95.73 375
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
MVS_0304		98.10 170	97.88 185	98.76 163	98.82 247	96.50 227	97.90 182	91.35 376	99.56 24	98.32 228	99.13 122	96.06 199	99.93 35	99.84 5	99.97 14	99.85 12

ambc				98.24 221	98.82 247	95.97 241	98.62 99	99.00 237		99.27 97	99.21 103	96.99 155	99.50 314	96.55 213	99.50 221	99.26 208

旧先验1					98.82 247	97.45 189		98.76 273			98.34 264	95.50 224			99.01 287	99.23 214

test_vis1_rt		97.75 200	97.72 196	97.83 247	98.81 250	96.35 231	97.30 240	99.69 27	94.61 303	97.87 258	98.05 287	96.26 193	98.32 374	98.74 66	98.18 325	98.82 277

WTY-MVS		96.67 268	96.27 277	97.87 245	98.81 250	94.61 283	96.77 271	97.92 314	94.94 297	97.12 300	97.74 305	91.11 298	99.82 154	93.89 306	98.15 329	99.18 226

3Dnovator+	97.89 3	98.69 97	98.51 108	99.24 93	98.81 250	98.40 107	99.02 66	99.19 193	98.99 85	98.07 246	99.28 90	97.11 148	99.84 130	96.84 185	99.32 243	99.47 133

QAPM		97.31 230	96.81 251	98.82 151	98.80 253	97.49 186	99.06 63	99.19 193	90.22 359	97.69 271	99.16 115	96.91 158	99.90 57	90.89 355	99.41 231	99.07 238

VNet		98.42 137	98.30 142	98.79 157	98.79 254	97.29 197	98.23 141	98.66 282	99.31 48	98.85 167	98.80 199	94.80 245	99.78 198	98.13 100	99.13 273	99.31 197

DPM-MVS		96.32 281	95.59 291	98.51 196	98.76 255	97.21 203	94.54 355	98.26 300	91.94 344	96.37 334	97.25 330	93.06 277	99.43 327	91.42 347	98.74 302	98.89 269

3Dnovator	98.27 2	98.81 78	98.73 76	99.05 125	98.76 255	97.81 168	99.25 40	99.30 158	98.57 112	98.55 209	99.33 83	97.95 88	99.90 57	97.16 153	99.67 163	99.44 143

PLC	94.65 16	96.51 274	95.73 285	98.85 148	98.75 257	97.91 156	96.42 288	99.06 221	90.94 356	95.59 346	97.38 326	94.41 253	99.59 288	90.93 353	98.04 336	99.05 240
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 262	96.75 254	97.08 296	98.74 258	93.33 317	96.71 275	98.26 300	96.72 245	98.44 219	97.37 327	95.20 231	99.47 321	91.89 339	97.43 344	98.44 314

hse-mvs2		97.46 219	97.07 234	98.64 174	98.73 259	97.33 195	97.45 231	97.64 322	99.11 66	98.58 204	97.98 291	88.65 316	99.79 187	98.11 101	97.39 345	98.81 281

CDS-MVSNet		97.69 204	97.35 221	98.69 171	98.73 259	97.02 213	96.92 265	98.75 276	95.89 275	98.59 202	98.67 220	92.08 292	99.74 221	96.72 196	99.81 90	99.32 193
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EIA-MVS		98.00 179	97.74 193	98.80 155	98.72 261	98.09 133	98.05 162	99.60 42	97.39 200	96.63 324	95.55 360	97.68 103	99.80 174	96.73 195	99.27 252	98.52 308

LFMVS		97.20 240	96.72 255	98.64 174	98.72 261	96.95 216	98.93 75	94.14 365	99.74 6	98.78 177	99.01 151	84.45 343	99.73 226	97.44 139	99.27 252	99.25 209

new_pmnet		96.99 257	96.76 253	97.67 261	98.72 261	94.89 273	95.95 309	98.20 303	92.62 338	98.55 209	98.54 240	94.88 241	99.52 309	93.96 304	99.44 229	98.59 307

Fast-Effi-MVS+		97.67 206	97.38 218	98.57 185	98.71 264	97.43 191	97.23 245	99.45 98	94.82 300	96.13 337	96.51 342	98.52 46	99.91 52	96.19 234	98.83 299	98.37 319

TEST9					98.71 264	98.08 137	95.96 307	99.03 229	91.40 350	95.85 343	97.53 316	96.52 181	99.76 209

train_agg		97.10 246	96.45 271	99.07 118	98.71 264	98.08 137	95.96 307	99.03 229	91.64 345	95.85 343	97.53 316	96.47 183	99.76 209	93.67 311	99.16 268	99.36 180

TSAR-MVS + GP.		98.18 166	97.98 175	98.77 162	98.71 264	97.88 158	96.32 293	98.66 282	96.33 258	99.23 108	98.51 244	97.48 128	99.40 331	97.16 153	99.46 224	99.02 247

FA-MVS(test-final)		96.99 257	96.82 249	97.50 278	98.70 268	94.78 275	99.34 20	96.99 335	95.07 293	98.48 216	99.33 83	88.41 319	99.65 269	96.13 240	98.92 296	98.07 330

AUN-MVS		96.24 285	95.45 294	98.60 181	98.70 268	97.22 202	97.38 234	97.65 320	95.95 273	95.53 353	97.96 295	82.11 358	99.79 187	96.31 227	97.44 343	98.80 286

our_test_3		97.39 225	97.73 195	96.34 319	98.70 268	89.78 358	94.61 352	98.97 239	96.50 252	99.04 132	98.85 190	95.98 207	99.84 130	97.26 148	99.67 163	99.41 153

ppachtmachnet_test		97.50 215	97.74 193	96.78 313	98.70 268	91.23 352	94.55 354	99.05 224	96.36 257	99.21 109	98.79 201	96.39 186	99.78 198	96.74 193	99.82 86	99.34 186

PCF-MVS	92.86 18	94.36 317	93.00 334	98.42 205	98.70 268	97.56 183	93.16 371	99.11 214	79.59 379	97.55 281	97.43 323	92.19 289	99.73 226	79.85 379	99.45 226	97.97 335
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ETV-MVS		98.03 176	97.86 187	98.56 189	98.69 273	98.07 139	97.51 226	99.50 77	98.10 142	97.50 286	95.51 361	98.41 51	99.88 76	96.27 230	99.24 257	97.71 348

test_prior				98.95 138	98.69 273	97.95 154		99.03 229					99.59 288			99.30 200

agg_prior					98.68 275	97.99 146		99.01 235		95.59 346			99.77 204

test_8					98.67 276	98.01 145	95.91 312	99.02 232	91.64 345	95.79 345	97.50 319	96.47 183	99.76 209

HQP-NCC					98.67 276		96.29 294		96.05 268	95.55 349

ACMP_Plane					98.67 276		96.29 294		96.05 268	95.55 349

CNVR-MVS		98.17 168	97.87 186	99.07 118	98.67 276	98.24 120	97.01 257	98.93 242	97.25 214	97.62 274	98.34 264	97.27 138	99.57 294	96.42 221	99.33 242	99.39 165

HQP-MVS		97.00 256	96.49 270	98.55 190	98.67 276	96.79 221	96.29 294	99.04 227	96.05 268	95.55 349	96.84 337	93.84 265	99.54 303	92.82 327	99.26 255	99.32 193

test_fmvs1		97.72 202	97.94 179	97.07 298	98.66 281	92.39 333	97.68 204	99.81 17	95.20 292	99.54 46	99.44 64	91.56 296	99.41 330	99.78 10	99.77 114	99.40 162

thres200		93.72 330	93.14 332	95.46 340	98.66 281	91.29 349	96.61 280	94.63 359	97.39 200	96.83 318	93.71 377	79.88 361	99.56 297	82.40 376	98.13 330	95.54 376

wuyk23d		96.06 287	97.62 205	91.38 363	98.65 283	98.57 96	98.85 82	96.95 338	96.86 239	99.90 9	99.16 115	99.18 14	98.40 373	89.23 361	99.77 114	77.18 381

NCCC		97.86 190	97.47 215	99.05 125	98.61 284	98.07 139	96.98 259	98.90 248	97.63 173	97.04 305	97.93 296	95.99 206	99.66 264	95.31 269	98.82 300	99.43 147

DeepC-MVS_fast	96.85 6	98.30 152	98.15 160	98.75 166	98.61 284	97.23 200	97.76 197	99.09 218	97.31 208	98.75 183	98.66 223	97.56 116	99.64 272	96.10 241	99.55 203	99.39 165
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
thisisatest0515		94.12 324	93.16 331	96.97 302	98.60 286	92.90 324	93.77 367	90.61 377	94.10 317	96.91 311	95.87 356	74.99 378	99.80 174	94.52 285	99.12 276	98.20 323

GA-MVS		95.86 293	95.32 301	97.49 279	98.60 286	94.15 294	93.83 366	97.93 313	95.49 283	96.68 322	97.42 324	83.21 351	99.30 344	96.22 232	98.55 316	99.01 248

dmvs_testset		92.94 337	92.21 339	95.13 343	98.59 288	90.99 354	97.65 209	92.09 373	96.95 234	94.00 369	93.55 378	92.34 288	96.97 380	72.20 382	92.52 378	97.43 356

OPU-MVS				98.82 151	98.59 288	98.30 116	98.10 156				98.52 243	98.18 69	98.75 370	94.62 282	99.48 223	99.41 153

MSLP-MVS++		98.02 177	98.14 162	97.64 265	98.58 290	95.19 265	97.48 228	99.23 185	97.47 189	97.90 256	98.62 232	97.04 150	98.81 369	97.55 133	99.41 231	98.94 263

test12				98.93 140	98.58 290	97.83 163		98.66 282		96.53 328		95.51 223	99.69 241		99.13 273	99.27 205

CL-MVSNet_self_test		97.44 222	97.22 227	98.08 232	98.57 292	95.78 247	94.30 359	98.79 270	96.58 251	98.60 200	98.19 276	94.74 249	99.64 272	96.41 222	98.84 298	98.82 277

PS-MVSNAJ		97.08 249	97.39 217	96.16 326	98.56 293	92.46 331	95.24 334	98.85 261	97.25 214	97.49 287	95.99 352	98.07 77	99.90 57	96.37 223	98.67 310	96.12 372

CNLPA		97.17 243	96.71 256	98.55 190	98.56 293	98.05 143	96.33 292	98.93 242	96.91 237	97.06 304	97.39 325	94.38 255	99.45 324	91.66 341	99.18 267	98.14 326

xiu_mvs_v2_base		97.16 244	97.49 212	96.17 324	98.54 295	92.46 331	95.45 328	98.84 262	97.25 214	97.48 288	96.49 343	98.31 59	99.90 57	96.34 226	98.68 309	96.15 371

alignmvs		97.35 227	96.88 244	98.78 160	98.54 295	98.09 133	97.71 201	97.69 319	99.20 59	97.59 277	95.90 355	88.12 321	99.55 300	98.18 99	98.96 292	98.70 298

FE-MVS		95.66 298	94.95 310	97.77 252	98.53 297	95.28 261	99.40 16	96.09 350	93.11 331	97.96 253	99.26 94	79.10 369	99.77 204	92.40 336	98.71 306	98.27 321

iter_conf_final		97.10 246	96.65 263	98.45 202	98.53 297	96.08 239	98.30 135	99.11 214	98.10 142	98.85 167	98.95 167	79.38 367	99.87 93	98.68 72	99.91 53	99.40 162

Effi-MVS+		98.02 177	97.82 189	98.62 178	98.53 297	97.19 205	97.33 238	99.68 32	97.30 209	96.68 322	97.46 322	98.56 44	99.80 174	96.63 202	98.20 324	98.86 274

baseline1		95.96 291	95.44 295	97.52 276	98.51 300	93.99 301	98.39 129	96.09 350	98.21 131	98.40 226	97.76 304	86.88 323	99.63 275	95.42 267	89.27 381	98.95 259

MVS_Test		98.18 166	98.36 134	97.67 261	98.48 301	94.73 278	98.18 146	99.02 232	97.69 169	98.04 250	99.11 125	97.22 142	99.56 297	98.57 78	98.90 297	98.71 295

BH-RMVSNet		96.83 262	96.58 267	97.58 269	98.47 302	94.05 295	96.67 277	97.36 325	96.70 247	97.87 258	97.98 291	95.14 233	99.44 326	90.47 357	98.58 315	99.25 209

canonicalmvs		98.34 147	98.26 147	98.58 183	98.46 303	97.82 166	98.96 73	99.46 95	99.19 63	97.46 289	95.46 363	98.59 42	99.46 323	98.08 104	98.71 306	98.46 310

MVS-HIRNet		94.32 318	95.62 289	90.42 364	98.46 303	75.36 387	96.29 294	89.13 381	95.25 290	95.38 355	99.75 11	92.88 280	99.19 354	94.07 302	99.39 233	96.72 365

PHI-MVS		98.29 155	97.95 177	99.34 72	98.44 305	99.16 43	98.12 153	99.38 119	96.01 271	98.06 247	98.43 254	97.80 97	99.67 253	95.69 259	99.58 193	99.20 219

DVP-MVS++		98.90 67	98.70 83	99.51 43	98.43 306	99.15 47	99.43 11	99.32 145	98.17 137	99.26 101	99.02 142	98.18 69	99.88 76	97.07 162	99.45 226	99.49 116

MSC_two_6792asdad				99.32 78	98.43 306	98.37 111		98.86 258					99.89 67	97.14 156	99.60 184	99.71 35

No_MVS				99.32 78	98.43 306	98.37 111		98.86 258					99.89 67	97.14 156	99.60 184	99.71 35

Fast-Effi-MVS+-dtu		98.27 156	98.09 165	98.81 153	98.43 306	98.11 132	97.61 214	99.50 77	98.64 103	97.39 294	97.52 318	98.12 76	99.95 20	96.90 179	98.71 306	98.38 317

OpenMVS_ROB	95.38 14	95.84 294	95.18 305	97.81 249	98.41 310	97.15 209	97.37 235	98.62 285	83.86 375	98.65 192	98.37 260	94.29 257	99.68 250	88.41 362	98.62 313	96.60 366

DeepPCF-MVS	96.93 5	98.32 149	98.01 173	99.23 95	98.39 311	98.97 66	95.03 339	99.18 197	96.88 238	99.33 86	98.78 202	98.16 73	99.28 348	96.74 193	99.62 177	99.44 143

Patchmatch-test		96.55 272	96.34 273	97.17 293	98.35 312	93.06 320	98.40 128	97.79 315	97.33 205	98.41 222	98.67 220	83.68 350	99.69 241	95.16 271	99.31 245	98.77 289

AdaColmap		97.14 245	96.71 256	98.46 201	98.34 313	97.80 169	96.95 260	98.93 242	95.58 280	96.92 309	97.66 309	95.87 212	99.53 305	90.97 352	99.14 271	98.04 331

OpenMVS	96.65 7	97.09 248	96.68 258	98.32 213	98.32 314	97.16 208	98.86 81	99.37 123	89.48 363	96.29 336	99.15 119	96.56 179	99.90 57	92.90 324	99.20 262	97.89 336

MG-MVS		96.77 265	96.61 264	97.26 290	98.31 315	93.06 320	95.93 310	98.12 309	96.45 255	97.92 254	98.73 209	93.77 269	99.39 333	91.19 351	99.04 282	99.33 191

test_yl		96.69 266	96.29 275	97.90 242	98.28 316	95.24 262	97.29 241	97.36 325	98.21 131	98.17 235	97.86 298	86.27 327	99.55 300	94.87 276	98.32 319	98.89 269

DCV-MVSNet		96.69 266	96.29 275	97.90 242	98.28 316	95.24 262	97.29 241	97.36 325	98.21 131	98.17 235	97.86 298	86.27 327	99.55 300	94.87 276	98.32 319	98.89 269

CHOSEN 280x420		95.51 303	95.47 292	95.65 335	98.25 318	88.27 364	93.25 370	98.88 251	93.53 325	94.65 361	97.15 333	86.17 329	99.93 35	97.41 141	99.93 34	98.73 294

SCA		96.41 280	96.66 261	95.67 333	98.24 319	88.35 363	95.85 315	96.88 341	96.11 266	97.67 272	98.67 220	93.10 275	99.85 114	94.16 296	99.22 259	98.81 281

DeepMVS_CX				93.44 359	98.24 319	94.21 291		94.34 360	64.28 381	91.34 377	94.87 373	89.45 310	92.77 384	77.54 381	93.14 377	93.35 379

MS-PatchMatch		97.68 205	97.75 192	97.45 281	98.23 321	93.78 310	97.29 241	98.84 262	96.10 267	98.64 193	98.65 225	96.04 200	99.36 336	96.84 185	99.14 271	99.20 219

BH-w/o		95.13 308	94.89 312	95.86 328	98.20 322	91.31 348	95.65 320	97.37 324	93.64 323	96.52 329	95.70 358	93.04 278	99.02 360	88.10 364	95.82 368	97.24 358

mvs_anonymous		97.83 198	98.16 159	96.87 307	98.18 323	91.89 340	97.31 239	98.90 248	97.37 202	98.83 171	99.46 59	96.28 192	99.79 187	98.90 56	98.16 328	98.95 259

miper_lstm_enhance		97.18 242	97.16 230	97.25 291	98.16 324	92.85 325	95.15 337	99.31 150	97.25 214	98.74 185	98.78 202	90.07 304	99.78 198	97.19 151	99.80 100	99.11 236

ET-MVSNet_ETH3D		94.30 320	93.21 330	97.58 269	98.14 325	94.47 286	94.78 345	93.24 369	94.72 301	89.56 379	95.87 356	78.57 372	99.81 167	96.91 174	97.11 353	98.46 310

ADS-MVSNet2		95.43 304	94.98 308	96.76 314	98.14 325	91.74 341	97.92 179	97.76 316	90.23 357	96.51 330	98.91 174	85.61 334	99.85 114	92.88 325	96.90 354	98.69 299

ADS-MVSNet		95.24 307	94.93 311	96.18 323	98.14 325	90.10 357	97.92 179	97.32 328	90.23 357	96.51 330	98.91 174	85.61 334	99.74 221	92.88 325	96.90 354	98.69 299

c3_l		97.36 226	97.37 219	97.31 286	98.09 328	93.25 318	95.01 340	99.16 204	97.05 229	98.77 180	98.72 211	92.88 280	99.64 272	96.93 173	99.76 125	99.05 240

FMVSNet3		97.50 215	97.24 226	98.29 217	98.08 329	95.83 245	97.86 188	98.91 247	97.89 156	98.95 146	98.95 167	87.06 322	99.81 167	97.77 124	99.69 152	99.23 214

PAPM		91.88 346	90.34 349	96.51 316	98.06 330	92.56 329	92.44 374	97.17 330	86.35 371	90.38 378	96.01 351	86.61 325	99.21 353	70.65 383	95.43 370	97.75 345

Effi-MVS+-dtu		98.26 158	97.90 183	99.35 69	98.02 331	99.49 5	98.02 167	99.16 204	98.29 126	97.64 273	97.99 290	96.44 185	99.95 20	96.66 201	98.93 295	98.60 305

eth_miper_zixun_eth		97.23 238	97.25 225	97.17 293	98.00 332	92.77 327	94.71 346	99.18 197	97.27 212	98.56 207	98.74 208	91.89 293	99.69 241	97.06 164	99.81 90	99.05 240

HY-MVS	95.94 13	95.90 292	95.35 300	97.55 273	97.95 333	94.79 274	98.81 85	96.94 339	92.28 342	95.17 357	98.57 238	89.90 306	99.75 216	91.20 350	97.33 350	98.10 328

UGNet		98.53 127	98.45 120	98.79 157	97.94 334	96.96 215	99.08 59	98.54 288	99.10 73	96.82 319	99.47 58	96.55 180	99.84 130	98.56 81	99.94 30	99.55 93
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
MAR-MVS		96.47 278	95.70 286	98.79 157	97.92 335	99.12 57	98.28 137	98.60 286	92.16 343	95.54 352	96.17 350	94.77 248	99.52 309	89.62 360	98.23 322	97.72 347
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
MVSTER		96.86 261	96.55 268	97.79 250	97.91 336	94.21 291	97.56 220	98.87 253	97.49 188	99.06 125	99.05 137	80.72 359	99.80 174	98.44 86	99.82 86	99.37 174

iter_conf05		96.54 273	96.07 279	97.92 241	97.90 337	94.50 285	97.87 187	99.14 210	97.73 166	98.89 158	98.95 167	75.75 377	99.87 93	98.50 83	99.92 45	99.40 162

API-MVS		97.04 252	96.91 243	97.42 283	97.88 338	98.23 124	98.18 146	98.50 291	97.57 180	97.39 294	96.75 339	96.77 168	99.15 357	90.16 358	99.02 286	94.88 377

miper_ehance_all_eth		97.06 250	97.03 236	97.16 295	97.83 339	93.06 320	94.66 349	99.09 218	95.99 272	98.69 187	98.45 253	92.73 284	99.61 283	96.79 187	99.03 283	98.82 277

cl____		97.02 253	96.83 248	97.58 269	97.82 340	94.04 297	94.66 349	99.16 204	97.04 230	98.63 194	98.71 212	88.68 315	99.69 241	97.00 166	99.81 90	99.00 251

DIV-MVS_self_test		97.02 253	96.84 247	97.58 269	97.82 340	94.03 298	94.66 349	99.16 204	97.04 230	98.63 194	98.71 212	88.69 313	99.69 241	97.00 166	99.81 90	99.01 248

CANet		97.87 189	97.76 191	98.19 224	97.75 342	95.51 253	96.76 272	99.05 224	97.74 165	96.93 308	98.21 274	95.59 220	99.89 67	97.86 120	99.93 34	99.19 224

mvsany_test1		97.60 210	97.54 208	97.77 252	97.72 343	95.35 259	95.36 331	97.13 332	94.13 316	99.71 24	99.33 83	97.93 89	99.30 344	97.60 132	98.94 294	98.67 303

PVSNet_0	89.98 21	91.15 347	90.30 350	93.70 356	97.72 343	84.34 380	90.24 376	97.42 323	90.20 360	93.79 371	93.09 379	90.90 299	98.89 368	86.57 368	72.76 383	97.87 338

CR-MVSNet		96.28 283	95.95 281	97.28 288	97.71 345	94.22 289	98.11 154	98.92 245	92.31 341	96.91 311	99.37 73	85.44 337	99.81 167	97.39 142	97.36 348	97.81 341

RPMNet		97.02 253	96.93 239	97.30 287	97.71 345	94.22 289	98.11 154	99.30 158	99.37 41	96.91 311	99.34 81	86.72 324	99.87 93	97.53 136	97.36 348	97.81 341

pmmvs3		95.03 310	94.40 316	96.93 303	97.70 347	92.53 330	95.08 338	97.71 318	88.57 367	97.71 269	98.08 285	79.39 366	99.82 154	96.19 234	99.11 277	98.43 315

baseline2		93.73 329	92.83 335	96.42 318	97.70 347	91.28 350	96.84 268	89.77 380	93.96 321	92.44 374	95.93 354	79.14 368	99.77 204	92.94 323	96.76 358	98.21 322

tpm		94.67 314	94.34 318	95.66 334	97.68 349	88.42 362	97.88 184	94.90 357	94.46 307	96.03 342	98.56 239	78.66 370	99.79 187	95.88 247	95.01 372	98.78 288

CANet_DTU		97.26 234	97.06 235	97.84 246	97.57 350	94.65 282	96.19 300	98.79 270	97.23 220	95.14 358	98.24 271	93.22 272	99.84 130	97.34 144	99.84 76	99.04 244

tpm2		93.09 336	92.58 337	94.62 347	97.56 351	86.53 370	97.66 207	95.79 354	86.15 372	94.07 368	98.23 273	75.95 375	99.53 305	90.91 354	96.86 357	97.81 341

TR-MVS		95.55 301	95.12 306	96.86 310	97.54 352	93.94 302	96.49 284	96.53 345	94.36 312	97.03 306	96.61 341	94.26 258	99.16 356	86.91 367	96.31 362	97.47 355

1314		95.74 296	95.60 290	96.17 324	97.53 353	92.75 328	98.07 159	98.31 299	91.22 352	94.25 364	96.68 340	95.53 221	99.03 359	91.64 343	97.18 351	96.74 364

CostFormer		93.97 326	93.78 323	94.51 348	97.53 353	85.83 373	97.98 174	95.96 352	89.29 365	94.99 360	98.63 230	78.63 371	99.62 277	94.54 284	96.50 359	98.09 329

FMVSNet5		96.01 288	95.20 304	98.41 206	97.53 353	96.10 236	98.74 86	99.50 77	97.22 223	98.03 251	99.04 139	69.80 381	99.88 76	97.27 147	99.71 144	99.25 209

PMMVS		96.51 274	95.98 280	98.09 229	97.53 353	95.84 244	94.92 342	98.84 262	91.58 347	96.05 341	95.58 359	95.68 217	99.66 264	95.59 263	98.09 332	98.76 291

PAPR		95.29 305	94.47 314	97.75 256	97.50 357	95.14 267	94.89 343	98.71 280	91.39 351	95.35 356	95.48 362	94.57 251	99.14 358	84.95 370	97.37 346	98.97 256

PatchT		96.65 269	96.35 272	97.54 274	97.40 358	95.32 260	97.98 174	96.64 344	99.33 46	96.89 315	99.42 67	84.32 345	99.81 167	97.69 131	97.49 341	97.48 354

tpm cat1		93.29 334	93.13 333	93.75 355	97.39 359	84.74 376	97.39 233	97.65 320	83.39 377	94.16 365	98.41 255	82.86 354	99.39 333	91.56 345	95.35 371	97.14 359

PatchmatchNet		95.58 300	95.67 288	95.30 342	97.34 360	87.32 368	97.65 209	96.65 343	95.30 289	97.07 303	98.69 216	84.77 340	99.75 216	94.97 274	98.64 311	98.83 276
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 227	96.97 238	98.50 198	97.31 361	96.47 228	98.18 146	98.92 245	98.95 90	98.78 177	99.37 73	85.44 337	99.85 114	95.96 245	99.83 83	99.17 230

LS3D		98.63 111	98.38 132	99.36 64	97.25 362	99.38 8	99.12 57	99.32 145	99.21 57	98.44 219	98.88 184	97.31 134	99.80 174	96.58 204	99.34 241	98.92 265

IB-MVS	91.63 19	92.24 344	90.90 348	96.27 321	97.22 363	91.24 351	94.36 358	93.33 368	92.37 340	92.24 375	94.58 374	66.20 388	99.89 67	93.16 322	94.63 374	97.66 349
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
tpmrst		95.07 309	95.46 293	93.91 353	97.11 364	84.36 379	97.62 212	96.96 337	94.98 295	96.35 335	98.80 199	85.46 336	99.59 288	95.60 262	96.23 363	97.79 344

MDTV_nov1_ep13			95.22 303		97.06 365	83.20 381	97.74 199	96.16 348	94.37 311	96.99 307	98.83 193	83.95 348	99.53 305	93.90 305	97.95 337

MVS		93.19 335	92.09 340	96.50 317	96.91 366	94.03 298	98.07 159	98.06 311	68.01 380	94.56 363	96.48 344	95.96 209	99.30 344	83.84 372	96.89 356	96.17 369

E-PMN		94.17 322	94.37 317	93.58 357	96.86 367	85.71 374	90.11 377	97.07 333	98.17 137	97.82 264	97.19 331	84.62 342	98.94 364	89.77 359	97.68 340	96.09 373

JIA-IIPM		95.52 302	95.03 307	97.00 299	96.85 368	94.03 298	96.93 263	95.82 353	99.20 59	94.63 362	99.71 16	83.09 352	99.60 284	94.42 290	94.64 373	97.36 357

EMVS		93.83 328	94.02 320	93.23 361	96.83 369	84.96 375	89.77 378	96.32 347	97.92 153	97.43 292	96.36 349	86.17 329	98.93 365	87.68 365	97.73 339	95.81 374

cl22		95.79 295	95.39 298	96.98 301	96.77 370	92.79 326	94.40 357	98.53 289	94.59 304	97.89 257	98.17 277	82.82 355	99.24 350	96.37 223	99.03 283	98.92 265

dp		93.47 332	93.59 326	93.13 362	96.64 371	81.62 385	97.66 207	96.42 346	92.80 336	96.11 338	98.64 228	78.55 373	99.59 288	93.31 320	92.18 380	98.16 325

test-LLR		93.90 327	93.85 321	94.04 351	96.53 372	84.62 377	94.05 363	92.39 371	96.17 263	94.12 366	95.07 365	82.30 356	99.67 253	95.87 250	98.18 325	97.82 339

test-mter		92.33 343	91.76 346	94.04 351	96.53 372	84.62 377	94.05 363	92.39 371	94.00 320	94.12 366	95.07 365	65.63 389	99.67 253	95.87 250	98.18 325	97.82 339

TESTMET0.1,1		92.19 345	91.77 345	93.46 358	96.48 374	82.80 382	94.05 363	91.52 375	94.45 309	94.00 369	94.88 371	66.65 386	99.56 297	95.78 255	98.11 331	98.02 332

miper_enhance_ethall		96.01 288	95.74 284	96.81 311	96.41 375	92.27 337	93.69 368	98.89 250	91.14 354	98.30 229	97.35 329	90.58 301	99.58 292	96.31 227	99.03 283	98.60 305

tpmvs		95.02 311	95.25 302	94.33 349	96.39 376	85.87 371	98.08 158	96.83 342	95.46 284	95.51 354	98.69 216	85.91 332	99.53 305	94.16 296	96.23 363	97.58 352

CMPMVS	75.91 23	96.29 282	95.44 295	98.84 149	96.25 377	98.69 88	97.02 256	99.12 212	88.90 366	97.83 262	98.86 187	89.51 308	98.90 367	91.92 338	99.51 214	98.92 265
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 315	93.69 324	96.99 300	96.05 378	93.61 315	94.97 341	93.49 366	96.17 263	97.57 280	94.88 371	82.30 356	99.01 362	93.60 313	94.17 376	98.37 319

EPMVS		93.72 330	93.27 329	95.09 345	96.04 379	87.76 366	98.13 151	85.01 385	94.69 302	96.92 309	98.64 228	78.47 374	99.31 342	95.04 272	96.46 360	98.20 323

cascas		94.79 313	94.33 319	96.15 327	96.02 380	92.36 335	92.34 375	99.26 177	85.34 374	95.08 359	94.96 370	92.96 279	98.53 372	94.41 293	98.59 314	97.56 353

gg-mvs-nofinetune		92.37 342	91.20 347	95.85 329	95.80 381	92.38 334	99.31 27	81.84 387	99.75 5	91.83 376	99.74 12	68.29 382	99.02 360	87.15 366	97.12 352	96.16 370

gm-plane-assit					94.83 382	81.97 384			88.07 369		94.99 368		99.60 284	91.76 340

GG-mvs-BLEND				94.76 346	94.54 383	92.13 339	99.31 27	80.47 388		88.73 381	91.01 381	67.59 385	98.16 376	82.30 377	94.53 375	93.98 378

EPNet_dtu		94.93 312	94.78 313	95.38 341	93.58 384	87.68 367	96.78 270	95.69 355	97.35 204	89.14 380	98.09 284	88.15 320	99.49 315	94.95 275	99.30 248	98.98 253
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
KD-MVS_2432*1600		92.87 338	91.99 341	95.51 338	91.37 385	89.27 359	94.07 361	98.14 307	95.42 285	97.25 298	96.44 346	67.86 383	99.24 350	91.28 348	96.08 366	98.02 332

miper_refine_blended		92.87 338	91.99 341	95.51 338	91.37 385	89.27 359	94.07 361	98.14 307	95.42 285	97.25 298	96.44 346	67.86 383	99.24 350	91.28 348	96.08 366	98.02 332

EPNet		96.14 286	95.44 295	98.25 219	90.76 387	95.50 254	97.92 179	94.65 358	98.97 87	92.98 373	98.85 190	89.12 311	99.87 93	95.99 243	99.68 157	99.39 165
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_method		79.78 349	79.50 352	80.62 365	80.21 388	45.76 390	70.82 379	98.41 296	31.08 383	80.89 384	97.71 306	84.85 339	97.37 378	91.51 346	80.03 382	98.75 292

tmp_tt		78.77 350	78.73 353	78.90 366	58.45 389	74.76 389	94.20 360	78.26 389	39.16 382	86.71 382	92.82 380	80.50 360	75.19 385	86.16 369	92.29 379	86.74 380

testmvs		17.12 352	20.53 355	6.87 368	12.05 390	4.20 392	93.62 369	6.73 391	4.62 386	10.41 386	24.33 383	8.28 391	3.56 387	9.69 385	15.07 384	12.86 383

test123		17.04 353	20.11 356	7.82 367	10.25 391	4.91 391	94.80 344	4.47 392	4.93 385	10.00 387	24.28 384	9.69 390	3.64 386	10.14 384	12.43 385	14.92 382

test_blank		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

eth-test2					0.00 392

eth-test					0.00 392

uanet_test		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

DCPMVS		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

cdsmvs_eth3d_5k		24.66 351	32.88 354	0.00 369	0.00 392	0.00 393	0.00 380	99.10 216	0.00 387	0.00 388	97.58 314	99.21 13	0.00 388	0.00 386	0.00 386	0.00 384

pcd_1.5k_mvsjas		8.17 354	10.90 357	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	98.07 77	0.00 388	0.00 386	0.00 386	0.00 384

sosnet-low-res		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

sosnet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uncertanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

Regformer		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

ab-mvs-re		8.12 355	10.83 358	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	97.48 320	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

PC_three_1452									93.27 328	99.40 72	98.54 240	98.22 65	97.00 379	95.17 270	99.45 226	99.49 116

test_241102_TWO								99.30 158	98.03 145	99.26 101	99.02 142	97.51 123	99.88 76	96.91 174	99.60 184	99.66 47

test_0728_THIRD									98.17 137	99.08 123	99.02 142	97.89 90	99.88 76	97.07 162	99.71 144	99.70 40

GSMVS																98.81 281

sam_mvs1												84.74 341				98.81 281

sam_mvs												84.29 347

MTGPA								99.20 189

test_post1							97.59 217				20.48 386	83.07 353	99.66 264	94.16 296

test_post											21.25 385	83.86 349	99.70 237

patchmatchnet-post											98.77 204	84.37 344	99.85 114

MTMP							97.93 177	91.91 374

test9_res														93.28 321	99.15 270	99.38 172

agg_prior2														92.50 335	99.16 268	99.37 174

test_prior4						97.97 150	95.86 313

test_prior2							95.74 318		96.48 254	96.11 338	97.63 312	95.92 211		94.16 296	99.20 262

旧先验2							95.76 317		88.56 368	97.52 284			99.66 264	94.48 286

新几何2							95.93 310

无先验							95.74 318	98.74 278	89.38 364				99.73 226	92.38 337		99.22 218

原ACMM2							95.53 324

testdata2													99.79 187	92.80 329

segment_acmp												97.02 153

testdata1							95.44 329		96.32 259

plane_prior5								99.27 172					99.70 237	94.42 290	99.51 214	99.45 139

plane_prior4											97.98 291

plane_prior3						97.78 170			97.41 198	97.79 265

plane_prior2							97.77 195		98.20 134

plane_prior						97.65 179	97.07 255		96.72 245						99.36 237

n2								0.00 393

nn								0.00 393

door-mid								99.57 52

test11								98.87 253

door								99.41 112

HQP5-MVS						96.79 221

BP-MVS														92.82 327

HQP4-MVS										95.56 348			99.54 303			99.32 193

HQP3-MVS								99.04 227							99.26 255

HQP2-MVS												93.84 265

MDTV_nov1_ep13_2view						74.92 388	97.69 203		90.06 362	97.75 268		85.78 333		93.52 315		98.69 299

ACMMP++_ref															99.77 114

ACMMP++															99.68 157

Test By Simon												96.52 181

High-resolution multi-view benchmark