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 13	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 16	100.00 1	99.85 30

Gipuma		99.03 81	99.16 63	98.64 219	99.94 2	98.51 112	99.32 26	99.75 42	99.58 39	98.60 269	99.62 40	98.22 105	99.51 399	97.70 190	99.73 181	97.89 432
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 29	99.31 42	99.53 39	99.91 3	98.98 72	99.63 7	99.58 89	99.44 53	99.78 40	99.76 15	96.39 250	99.92 65	99.44 55	99.92 69	99.68 71

pmmvs6		99.67 3	99.70 3	99.60 16	99.90 4	99.27 28	99.53 9	99.76 39	99.64 27	99.84 30	99.83 4	99.50 9	99.87 134	99.36 58	99.92 69	99.64 84

PS-MVSNAJss		99.46 17	99.49 16	99.35 80	99.90 4	98.15 139	99.20 48	99.65 69	99.48 45	99.92 8	99.71 22	98.07 120	99.96 14	99.53 48	100.00 1	99.93 11

testf1		99.25 41	99.16 63	99.51 49	99.89 6	99.63 4	98.71 104	99.69 54	98.90 133	99.43 106	99.35 105	98.86 34	99.67 322	97.81 177	99.81 130	99.24 279

APD_test2		99.25 41	99.16 63	99.51 49	99.89 6	99.63 4	98.71 104	99.69 54	98.90 133	99.43 106	99.35 105	98.86 34	99.67 322	97.81 177	99.81 130	99.24 279

ANet_high		99.57 10	99.67 6	99.28 96	99.89 6	98.09 146	99.14 57	99.93 5	99.82 8	99.93 6	99.81 8	99.17 20	99.94 42	99.31 62	100.00 1	99.82 36

anonymousdsp		99.51 14	99.47 21	99.62 10	99.88 9	99.08 70	99.34 23	99.69 54	98.93 129	99.65 64	99.72 21	98.93 32	99.95 26	99.11 78	100.00 1	99.82 36

v7n		99.53 12	99.57 13	99.41 70	99.88 9	98.54 110	99.45 14	99.61 78	99.66 24	99.68 58	99.66 32	98.44 78	99.95 26	99.73 28	99.96 28	99.75 60

mvs_tets		99.63 6	99.67 6	99.49 55	99.88 9	98.61 102	99.34 23	99.71 47	99.27 74	99.90 14	99.74 18	99.68 4	99.97 7	99.55 43	99.99 5	99.88 20

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 74	99.87 12	98.13 142	98.08 187	99.95 1	99.45 51	99.98 2	99.75 16	99.80 1	99.97 7	99.82 12	99.99 5	99.99 2

jajsoiax		99.58 9	99.61 11	99.48 57	99.87 12	98.61 102	99.28 40	99.66 65	99.09 108	99.89 18	99.68 25	99.53 7	99.97 7	99.50 51	99.99 5	99.87 22

test_djsdf		99.52 13	99.51 15	99.53 39	99.86 14	98.74 92	99.39 20	99.56 105	99.11 98	99.70 52	99.73 20	99.00 27	99.97 7	99.26 66	99.98 12	99.89 16

MIMVSNet1		99.38 28	99.32 40	99.55 29	99.86 14	99.19 43	99.41 17	99.59 87	99.59 37	99.71 50	99.57 49	97.12 205	99.90 81	99.21 71	99.87 98	99.54 142

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 27	99.85 16	99.11 65	99.90 1	99.78 36	99.63 29	99.78 40	99.67 30	99.48 10	99.81 222	99.30 63	99.97 21	99.77 50
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 17	99.34 20	99.69 5	99.58 89	99.90 3	99.86 24	99.78 13	99.58 6	99.95 26	99.00 88	99.95 38	99.78 47

SixPastTwentyTwo		98.75 131	98.62 146	99.16 118	99.83 18	97.96 166	99.28 40	98.20 379	99.37 61	99.70 52	99.65 36	92.65 356	99.93 54	99.04 85	99.84 112	99.60 100

sc_t1		99.62 7	99.66 8	99.53 39	99.82 19	99.09 69	99.50 11	99.63 73	99.88 4	99.86 24	99.80 11	99.03 24	99.89 97	99.48 53	99.93 56	99.60 100

Baseline_NR-MVSNet		98.98 89	98.86 108	99.36 74	99.82 19	98.55 107	97.47 295	99.57 96	99.37 61	99.21 160	99.61 43	96.76 232	99.83 192	98.06 154	99.83 119	99.71 63

pm-mvs1		99.44 19	99.48 18	99.33 89	99.80 21	98.63 99	99.29 36	99.63 73	99.30 71	99.65 64	99.60 45	99.16 22	99.82 205	99.07 81	99.83 119	99.56 129

TransMVSNet (Re)		99.44 19	99.47 21	99.36 74	99.80 21	98.58 105	99.27 42	99.57 96	99.39 59	99.75 45	99.62 40	99.17 20	99.83 192	99.06 83	99.62 240	99.66 78

K. test v3		98.00 250	97.66 275	99.03 145	99.79 23	97.56 202	99.19 52	92.47 465	99.62 33	99.52 88	99.66 32	89.61 388	99.96 14	99.25 68	99.81 130	99.56 129

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 83	99.78 24	98.11 143	97.77 244	99.90 11	99.33 66	99.97 3	99.66 32	99.71 3	99.96 14	99.79 19	99.99 5	99.96 8

APD_test1		98.83 115	98.66 139	99.34 83	99.78 24	99.47 9	98.42 149	99.45 154	98.28 187	98.98 197	99.19 150	97.76 152	99.58 373	96.57 288	99.55 267	98.97 334

test_vis3_rt		99.14 63	99.17 61	99.07 135	99.78 24	98.38 119	98.92 82	99.94 2	97.80 233	99.91 12	99.67 30	97.15 204	98.91 458	99.76 23	99.56 263	99.92 12

EGC-MVSNET		85.24 444	80.54 447	99.34 83	99.77 27	99.20 40	99.08 61	99.29 234	12.08 483	20.84 484	99.42 90	97.55 171	99.85 156	97.08 236	99.72 189	98.96 336

Anonymous20240521		98.69 144	98.87 104	98.16 296	99.77 27	95.11 338	99.08 61	99.44 162	99.34 65	99.33 130	99.55 57	94.10 331	99.94 42	99.25 68	99.96 28	99.42 208

FC-MVSNet-test		99.27 38	99.25 53	99.34 83	99.77 27	98.37 121	99.30 35	99.57 96	99.61 35	99.40 115	99.50 69	97.12 205	99.85 156	99.02 87	99.94 50	99.80 42

test_vis1_n		98.31 214	98.50 166	97.73 331	99.76 30	94.17 366	98.68 107	99.91 9	96.31 349	99.79 39	99.57 49	92.85 352	99.42 419	99.79 19	99.84 112	99.60 100

test_fmvs3		99.12 70	99.41 26	98.25 284	99.76 30	95.07 339	99.05 67	99.94 2	97.78 236	99.82 34	99.84 3	98.56 68	99.71 297	99.96 1	99.96 28	99.97 4

XXY-MVS		99.14 63	99.15 68	99.10 128	99.76 30	97.74 191	98.85 92	99.62 75	98.48 170	99.37 120	99.49 75	98.75 46	99.86 143	98.20 144	99.80 141	99.71 63

TDRefinement		99.42 24	99.38 29	99.55 29	99.76 30	99.33 21	99.68 6	99.71 47	99.38 60	99.53 83	99.61 43	98.64 56	99.80 231	98.24 139	99.84 112	99.52 154

fmvsm_s_conf0.1_n_a		99.17 53	99.30 45	98.80 184	99.75 34	96.59 270	97.97 217	99.86 16	98.22 190	99.88 21	99.71 22	98.59 62	99.84 174	99.73 28	99.98 12	99.98 3

tt0805		98.69 144	98.62 146	98.90 171	99.75 34	99.30 23	99.15 56	96.97 416	98.86 138	98.87 230	97.62 394	98.63 58	98.96 455	99.41 57	98.29 407	98.45 398

test_vis1_n_1920		98.40 197	98.92 96	96.81 393	99.74 36	90.76 444	98.15 175	99.91 9	98.33 178	99.89 18	99.55 57	95.07 302	99.88 115	99.76 23	99.93 56	99.79 44

FOURS1					99.73 37	99.67 3	99.43 15	99.54 114	99.43 55	99.26 148

PEN-MVS		99.41 25	99.34 36	99.62 10	99.73 37	99.14 58	99.29 36	99.54 114	99.62 33	99.56 74	99.42 90	98.16 114	99.96 14	98.78 103	99.93 56	99.77 50

lessismore_v0				98.97 157	99.73 37	97.53 204		86.71 480		99.37 120	99.52 68	89.93 384	99.92 65	98.99 89	99.72 189	99.44 199

SteuartSystems-ACMMP		98.79 124	98.54 159	99.54 32	99.73 37	99.16 49	98.23 165	99.31 218	97.92 224	98.90 219	98.90 237	98.00 126	99.88 115	96.15 320	99.72 189	99.58 115
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 235	98.15 227	98.22 290	99.73 37	95.15 335	97.36 309	99.68 60	94.45 406	98.99 196	99.27 125	96.87 221	99.94 42	97.13 233	99.91 78	99.57 123

Vis-MVSNet		99.34 30	99.36 33	99.27 99	99.73 37	98.26 128	99.17 53	99.78 36	99.11 98	99.27 144	99.48 76	98.82 37	99.95 26	98.94 92	99.93 56	99.59 107
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
tt0320-xc		99.64 5	99.68 5	99.50 54	99.72 43	98.98 72	99.51 10	99.85 18	99.86 6	99.88 21	99.82 5	99.02 26	99.90 81	99.54 44	99.95 38	99.61 98

SSC-MVS		98.71 135	98.74 119	98.62 225	99.72 43	96.08 295	98.74 97	98.64 359	99.74 13	99.67 60	99.24 138	94.57 317	99.95 26	99.11 78	99.24 331	99.82 36

test_f		98.67 153	98.87 104	98.05 306	99.72 43	95.59 310	98.51 133	99.81 31	96.30 351	99.78 40	99.82 5	96.14 261	98.63 465	99.82 12	99.93 56	99.95 9

ACMH	96.65 7	99.25 41	99.24 54	99.26 101	99.72 43	98.38 119	99.07 64	99.55 109	98.30 182	99.65 64	99.45 85	99.22 17	99.76 267	98.44 129	99.77 158	99.64 84
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		99.61 8	99.65 9	99.48 57	99.71 47	98.94 79	99.54 8	99.83 25	99.87 5	99.89 18	99.82 5	98.75 46	99.90 81	99.54 44	99.95 38	99.59 107

fmvsm_s_conf0.1_n		99.16 57	99.33 38	98.64 219	99.71 47	96.10 290	97.87 230	99.85 18	98.56 166	99.90 14	99.68 25	98.69 52	99.85 156	99.72 30	99.98 12	99.97 4

PS-CasMVS		99.40 26	99.33 38	99.62 10	99.71 47	99.10 66	99.29 36	99.53 118	99.53 42	99.46 101	99.41 94	98.23 102	99.95 26	98.89 97	99.95 38	99.81 40

DTE-MVSNet		99.43 23	99.35 34	99.66 7	99.71 47	99.30 23	99.31 30	99.51 124	99.64 27	99.56 74	99.46 81	98.23 102	99.97 7	98.78 103	99.93 56	99.72 62

WR-MVS_H		99.33 31	99.22 55	99.65 8	99.71 47	99.24 31	99.32 26	99.55 109	99.46 50	99.50 94	99.34 109	97.30 193	99.93 54	98.90 95	99.93 56	99.77 50

HPM-MVS_fast		99.01 83	98.82 112	99.57 22	99.71 47	99.35 17	99.00 72	99.50 127	97.33 282	98.94 214	98.86 247	98.75 46	99.82 205	97.53 202	99.71 198	99.56 129

ACMH+	96.62 9	99.08 77	99.00 88	99.33 89	99.71 47	98.83 87	98.60 119	99.58 89	99.11 98	99.53 83	99.18 154	98.81 38	99.67 322	96.71 274	99.77 158	99.50 162

PMVS	91.26 20	97.86 264	97.94 251	97.65 338	99.71 47	97.94 168	98.52 128	98.68 355	98.99 121	97.52 363	99.35 105	97.41 186	98.18 471	91.59 434	99.67 219	96.82 460
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FE-MVSNET2		99.15 58	99.22 55	98.94 161	99.70 55	97.49 205	98.62 116	99.67 64	98.85 141	99.34 127	99.54 63	98.47 72	99.81 222	98.93 93	99.91 78	99.51 158

KinetiMVS		99.03 81	99.02 84	99.03 145	99.70 55	97.48 208	98.43 146	99.29 234	99.70 16	99.60 71	99.07 183	96.13 262	99.94 42	99.42 56	99.87 98	99.68 71

FIs		99.14 63	99.09 76	99.29 95	99.70 55	98.28 127	99.13 58	99.52 123	99.48 45	99.24 154	99.41 94	96.79 229	99.82 205	98.69 113	99.88 94	99.76 56

VPNet		98.87 105	98.83 111	99.01 149	99.70 55	97.62 200	98.43 146	99.35 199	99.47 48	99.28 142	99.05 191	96.72 235	99.82 205	98.09 151	99.36 310	99.59 107

fmvsm_s_conf0.1_n_2		99.20 51	99.38 29	98.65 217	99.69 59	96.08 295	97.49 290	99.90 11	99.53 42	99.88 21	99.64 37	98.51 71	99.90 81	99.83 10	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 211	98.68 134	97.27 369	99.69 59	92.29 418	98.03 198	99.85 18	97.62 246	99.96 4	99.62 40	93.98 332	99.74 281	99.52 50	99.86 105	99.79 44

MP-MVS-pluss		98.57 170	98.23 215	99.60 16	99.69 59	99.35 17	97.16 331	99.38 185	94.87 396	98.97 201	98.99 213	98.01 125	99.88 115	97.29 220	99.70 205	99.58 115
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 46	99.32 40	98.96 158	99.68 62	97.35 216	98.84 94	99.48 137	99.69 18	99.63 67	99.68 25	99.03 24	99.96 14	97.97 165	99.92 69	99.57 123

sd_testset		99.28 37	99.31 42	99.19 112	99.68 62	98.06 155	99.41 17	99.30 226	99.69 18	99.63 67	99.68 25	99.25 16	99.96 14	97.25 223	99.92 69	99.57 123

test_fmvs1_n		98.09 241	98.28 206	97.52 355	99.68 62	93.47 397	98.63 114	99.93 5	95.41 384	99.68 58	99.64 37	91.88 367	99.48 406	99.82 12	99.87 98	99.62 90

CHOSEN 1792x2688		97.49 293	97.14 308	98.54 248	99.68 62	96.09 293	96.50 367	99.62 75	91.58 444	98.84 233	98.97 220	92.36 358	99.88 115	96.76 267	99.95 38	99.67 76

tfpnnormal		98.90 100	98.90 98	98.91 168	99.67 66	97.82 183	99.00 72	99.44 162	99.45 51	99.51 93	99.24 138	98.20 109	99.86 143	95.92 329	99.69 208	99.04 321

MTAPA		98.88 104	98.64 142	99.61 14	99.67 66	99.36 16	98.43 146	99.20 258	98.83 143	98.89 222	98.90 237	96.98 215	99.92 65	97.16 228	99.70 205	99.56 129

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 248	99.66 68	96.97 249	98.00 205	99.85 18	99.24 76	99.92 8	99.50 69	99.39 12	99.95 26	99.89 3	99.98 12	98.71 375

mvs5depth		99.30 34	99.59 12	98.44 262	99.65 69	95.35 327	99.82 3	99.94 2	99.83 7	99.42 110	99.94 2	98.13 117	99.96 14	99.63 36	99.96 28	100.00 1

fmvsm_l_conf0.5_n_a		99.19 52	99.27 48	98.94 161	99.65 69	97.05 244	97.80 239	99.76 39	98.70 148	99.78 40	99.11 173	98.79 42	99.95 26	99.85 6	99.96 28	99.83 33

WB-MVS		98.52 184	98.55 157	98.43 263	99.65 69	95.59 310	98.52 128	98.77 344	99.65 26	99.52 88	99.00 211	94.34 323	99.93 54	98.65 115	98.83 379	99.76 56

CP-MVSNet		99.21 48	99.09 76	99.56 27	99.65 69	98.96 78	99.13 58	99.34 205	99.42 56	99.33 130	99.26 131	97.01 213	99.94 42	98.74 108	99.93 56	99.79 44

HPM-MVS		98.79 124	98.53 161	99.59 20	99.65 69	99.29 25	99.16 54	99.43 168	96.74 329	98.61 267	98.38 338	98.62 59	99.87 134	96.47 300	99.67 219	99.59 107
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 162	98.36 192	99.42 68	99.65 69	99.42 11	98.55 124	99.57 96	97.72 240	98.90 219	99.26 131	96.12 264	99.52 394	95.72 340	99.71 198	99.32 255

NormalMVS		98.26 221	97.97 248	99.15 121	99.64 75	97.83 178	98.28 159	99.43 168	99.24 76	98.80 241	98.85 250	89.76 386	99.94 42	98.04 156	99.67 219	99.68 71

lecture		99.25 41	99.12 71	99.62 10	99.64 75	99.40 12	98.89 87	99.51 124	99.19 88	99.37 120	99.25 136	98.36 83	99.88 115	98.23 141	99.67 219	99.59 107

fmvsm_l_conf0.5_n		99.21 48	99.28 47	99.02 148	99.64 75	97.28 223	97.82 235	99.76 39	98.73 145	99.82 34	99.09 181	98.81 38	99.95 26	99.86 4	99.96 28	99.83 33

test_fmvsmconf_n		99.44 19	99.48 18	99.31 94	99.64 75	98.10 145	97.68 258	99.84 22	99.29 72	99.92 8	99.57 49	99.60 5	99.96 14	99.74 27	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 159	98.49 171	99.06 141	99.64 75	97.90 172	98.51 133	98.94 309	96.96 313	99.24 154	98.89 243	97.83 144	99.81 222	96.88 257	99.49 289	99.48 180
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 118	98.72 123	99.12 124	99.64 75	98.54 110	97.98 213	99.68 60	97.62 246	99.34 127	99.18 154	97.54 173	99.77 261	97.79 179	99.74 178	99.04 321

Elysia		99.15 58	99.14 69	99.18 113	99.63 81	97.92 169	98.50 135	99.43 168	99.67 21	99.70 52	99.13 169	96.66 238	99.98 4	99.54 44	99.96 28	99.64 84

StellarMVS		99.15 58	99.14 69	99.18 113	99.63 81	97.92 169	98.50 135	99.43 168	99.67 21	99.70 52	99.13 169	96.66 238	99.98 4	99.54 44	99.96 28	99.64 84

KD-MVS_self_test		99.25 41	99.18 60	99.44 66	99.63 81	99.06 71	98.69 106	99.54 114	99.31 69	99.62 70	99.53 65	97.36 190	99.86 143	99.24 70	99.71 198	99.39 221

EU-MVSNet		97.66 281	98.50 166	95.13 435	99.63 81	85.84 466	98.35 155	98.21 378	98.23 189	99.54 79	99.46 81	95.02 303	99.68 318	98.24 139	99.87 98	99.87 22

HyFIR lowres test		97.19 320	96.60 344	98.96 158	99.62 85	97.28 223	95.17 432	99.50 127	94.21 411	99.01 191	98.32 346	86.61 406	99.99 2	97.10 235	99.84 112	99.60 100

fmvsm_l_conf0.5_n_9		99.32 33	99.43 24	98.98 155	99.59 86	97.18 235	97.44 299	99.83 25	99.56 40	99.91 12	99.34 109	99.36 13	99.93 54	99.83 10	99.98 12	99.85 30

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 83	99.59 86	98.21 136	97.82 235	99.84 22	99.41 58	99.92 8	99.41 94	99.51 8	99.95 26	99.84 9	99.97 21	99.87 22

MED-MVS test				99.45 64	99.58 88	98.93 80	98.68 107	99.60 80	96.46 342	99.53 83	98.77 270		99.83 192	96.67 277	99.64 230	99.58 115

MED-MVS		98.90 100	98.72 123	99.45 64	99.58 88	98.93 80	98.68 107	99.60 80	98.14 208	99.53 83	98.77 270	97.87 141	99.83 192	96.67 277	99.64 230	99.58 115

TestfortrainingZip a		98.95 93	98.72 123	99.64 9	99.58 88	99.32 22	98.68 107	99.60 80	96.46 342	99.53 83	98.77 270	97.87 141	99.83 192	98.39 132	99.64 230	99.77 50

FE-MVSNET		98.59 167	98.50 166	98.87 172	99.58 88	97.30 221	98.08 187	99.74 43	96.94 315	98.97 201	99.10 176	96.94 217	99.74 281	97.33 218	99.86 105	99.55 136

mmtdpeth		99.30 34	99.42 25	98.92 167	99.58 88	96.89 257	99.48 13	99.92 7	99.92 2	98.26 305	99.80 11	98.33 89	99.91 74	99.56 41	99.95 38	99.97 4

ACMMP_NAP		98.75 131	98.48 172	99.57 22	99.58 88	99.29 25	97.82 235	99.25 247	96.94 315	98.78 243	99.12 172	98.02 124	99.84 174	97.13 233	99.67 219	99.59 107

nrg030		99.40 26	99.35 34	99.54 32	99.58 88	99.13 61	98.98 75	99.48 137	99.68 20	99.46 101	99.26 131	98.62 59	99.73 288	99.17 75	99.92 69	99.76 56

VDDNet		98.21 228	97.95 249	99.01 149	99.58 88	97.74 191	99.01 70	97.29 407	99.67 21	98.97 201	99.50 69	90.45 381	99.80 231	97.88 172	99.20 339	99.48 180

COLMAP_ROB	96.50 10	98.99 86	98.85 110	99.41 70	99.58 88	99.10 66	98.74 97	99.56 105	99.09 108	99.33 130	99.19 150	98.40 80	99.72 296	95.98 327	99.76 173	99.42 208
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 31	99.45 23	98.99 151	99.57 97	97.73 193	97.93 219	99.83 25	99.22 79	99.93 6	99.30 119	99.42 11	99.96 14	99.85 6	99.99 5	99.29 265

ZNCC-MVS		98.68 150	98.40 184	99.54 32	99.57 97	99.21 34	98.46 143	99.29 234	97.28 288	98.11 317	98.39 336	98.00 126	99.87 134	96.86 260	99.64 230	99.55 136

MSP-MVS		98.40 197	98.00 243	99.61 14	99.57 97	99.25 30	98.57 122	99.35 199	97.55 257	99.31 138	97.71 387	94.61 316	99.88 115	96.14 321	99.19 342	99.70 68
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		98.32 212	98.39 187	98.13 297	99.57 97	95.54 313	97.78 241	99.49 135	97.37 279	99.19 162	97.65 391	98.96 29	99.49 403	96.50 299	98.99 367	99.34 246

MP-MVS		98.46 190	98.09 232	99.54 32	99.57 97	99.22 33	98.50 135	99.19 262	97.61 249	97.58 357	98.66 298	97.40 187	99.88 115	94.72 366	99.60 247	99.54 142
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 135	98.46 176	99.47 61	99.57 97	98.97 74	98.23 165	99.48 137	96.60 334	99.10 173	99.06 184	98.71 50	99.83 192	95.58 347	99.78 152	99.62 90

LGP-MVS_train				99.47 61	99.57 97	98.97 74		99.48 137	96.60 334	99.10 173	99.06 184	98.71 50	99.83 192	95.58 347	99.78 152	99.62 90

IS-MVSNet		98.19 231	97.90 257	99.08 133	99.57 97	97.97 163	99.31 30	98.32 374	99.01 120	98.98 197	99.03 195	91.59 369	99.79 244	95.49 349	99.80 141	99.48 180

viewdifsd2359ckpt11		98.84 112	99.04 81	98.24 286	99.56 105	95.51 315	97.38 304	99.70 52	99.16 93	99.57 72	99.40 97	98.26 98	99.71 297	98.55 124	99.82 124	99.50 162

viewmsd2359difaftdt		98.84 112	99.04 81	98.24 286	99.56 105	95.51 315	97.38 304	99.70 52	99.16 93	99.57 72	99.40 97	98.26 98	99.71 297	98.55 124	99.82 124	99.50 162

dcpmvs_2		98.78 126	99.11 72	97.78 321	99.56 105	93.67 392	99.06 65	99.86 16	99.50 44	99.66 61	99.26 131	97.21 201	99.99 2	98.00 161	99.91 78	99.68 71

test_0402		98.76 130	98.71 128	98.93 164	99.56 105	98.14 141	98.45 145	99.34 205	99.28 73	98.95 207	98.91 234	98.34 88	99.79 244	95.63 344	99.91 78	98.86 353

EPP-MVSNet		98.30 215	98.04 239	99.07 135	99.56 105	97.83 178	99.29 36	98.07 385	99.03 118	98.59 271	99.13 169	92.16 362	99.90 81	96.87 258	99.68 213	99.49 169

ACMMP		98.75 131	98.50 166	99.52 45	99.56 105	99.16 49	98.87 88	99.37 189	97.16 303	98.82 237	99.01 207	97.71 155	99.87 134	96.29 312	99.69 208	99.54 142
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
fmvsm_s_conf0.5_n_a		99.10 72	99.20 59	98.78 191	99.55 111	96.59 270	97.79 240	99.82 30	98.21 192	99.81 37	99.53 65	98.46 76	99.84 174	99.70 33	99.97 21	99.90 15

fmvsm_s_conf0.5_n		99.09 73	99.26 51	98.61 229	99.55 111	96.09 293	97.74 251	99.81 31	98.55 167	99.85 27	99.55 57	98.60 61	99.84 174	99.69 35	99.98 12	99.89 16

FMVSNet1		99.17 53	99.17 61	99.17 115	99.55 111	98.24 130	99.20 48	99.44 162	99.21 81	99.43 106	99.55 57	97.82 147	99.86 143	98.42 131	99.89 92	99.41 211

Vis-MVSNet (Re-imp)		97.46 295	97.16 305	98.34 275	99.55 111	96.10 290	98.94 80	98.44 368	98.32 180	98.16 311	98.62 307	88.76 393	99.73 288	93.88 392	99.79 147	99.18 299

ACMM	96.08 12	98.91 98	98.73 121	99.48 57	99.55 111	99.14 58	98.07 191	99.37 189	97.62 246	99.04 187	98.96 223	98.84 36	99.79 244	97.43 212	99.65 228	99.49 169
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 140	98.97 92	97.89 314	99.54 116	94.05 369	98.55 124	99.92 7	96.78 327	99.72 48	99.78 13	96.60 242	99.67 322	99.91 2	99.90 86	99.94 10

mPP-MVS		98.64 157	98.34 195	99.54 32	99.54 116	99.17 45	98.63 114	99.24 252	97.47 265	98.09 319	98.68 293	97.62 164	99.89 97	96.22 315	99.62 240	99.57 123

XVG-ACMP-BASELINE		98.56 171	98.34 195	99.22 109	99.54 116	98.59 104	97.71 254	99.46 150	97.25 291	98.98 197	98.99 213	97.54 173	99.84 174	95.88 330	99.74 178	99.23 281

viewmacassd2359aftdt		98.86 109	98.87 104	98.83 177	99.53 119	97.32 220	97.70 256	99.64 71	98.22 190	99.25 152	99.27 125	98.40 80	99.61 359	97.98 164	99.87 98	99.55 136

region2R		98.69 144	98.40 184	99.54 32	99.53 119	99.17 45	98.52 128	99.31 218	97.46 270	98.44 290	98.51 321	97.83 144	99.88 115	96.46 301	99.58 256	99.58 115

PGM-MVS		98.66 154	98.37 191	99.55 29	99.53 119	99.18 44	98.23 165	99.49 135	97.01 312	98.69 254	98.88 244	98.00 126	99.89 97	95.87 333	99.59 251	99.58 115

E4		98.87 105	98.88 101	98.81 181	99.52 122	97.23 226	97.62 269	99.61 78	98.58 161	99.18 166	99.33 112	98.29 92	99.69 308	97.99 163	99.83 119	99.52 154

Patchmatch-RL test		97.26 313	97.02 314	97.99 310	99.52 122	95.53 314	96.13 392	99.71 47	97.47 265	99.27 144	99.16 160	84.30 427	99.62 352	97.89 169	99.77 158	98.81 361

ACMMPR		98.70 140	98.42 182	99.54 32	99.52 122	99.14 58	98.52 128	99.31 218	97.47 265	98.56 277	98.54 316	97.75 153	99.88 115	96.57 288	99.59 251	99.58 115

fmvsm_s_conf0.5_n_9		99.17 53	99.38 29	98.53 250	99.51 125	95.82 305	97.62 269	99.78 36	99.72 15	99.90 14	99.48 76	98.66 54	99.89 97	99.85 6	99.93 56	99.89 16

AstraMVS		98.16 237	98.07 237	98.41 265	99.51 125	95.86 302	98.00 205	95.14 448	98.97 124	99.43 106	99.24 138	93.25 340	99.84 174	99.21 71	99.87 98	99.54 142

fmvsm_s_conf0.5_n_8		99.13 67	99.26 51	98.74 204	99.51 125	96.44 282	97.65 264	99.65 69	99.66 24	99.78 40	99.48 76	97.92 134	99.93 54	99.72 30	99.95 38	99.87 22

GST-MVS		98.61 163	98.30 203	99.52 45	99.51 125	99.20 40	98.26 163	99.25 247	97.44 273	98.67 257	98.39 336	97.68 156	99.85 156	96.00 325	99.51 279	99.52 154

Anonymous20231206		98.21 228	98.21 216	98.20 291	99.51 125	95.43 324	98.13 177	99.32 213	96.16 355	98.93 215	98.82 260	96.00 269	99.83 192	97.32 219	99.73 181	99.36 239

ACMP	95.32 15	98.41 194	98.09 232	99.36 74	99.51 125	98.79 90	97.68 258	99.38 185	95.76 371	98.81 239	98.82 260	98.36 83	99.82 205	94.75 363	99.77 158	99.48 180
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 203	98.20 217	98.98 155	99.50 131	97.49 205	97.78 241	97.69 394	98.75 144	99.49 95	99.25 136	92.30 360	99.94 42	99.14 76	99.88 94	99.50 162

DVP-MVS		98.77 129	98.52 162	99.52 45	99.50 131	99.21 34	98.02 201	98.84 333	97.97 218	99.08 175	99.02 196	97.61 166	99.88 115	96.99 244	99.63 237	99.48 180
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 16	99.50 131	99.23 32	98.02 201	99.32 213					99.88 115	96.99 244	99.63 237	99.68 71

test0726					99.50 131	99.21 34	98.17 173	99.35 199	97.97 218	99.26 148	99.06 184	97.61 166

AllTest		98.44 192	98.20 217	99.16 118	99.50 131	98.55 107	98.25 164	99.58 89	96.80 325	98.88 226	99.06 184	97.65 159	99.57 375	94.45 373	99.61 245	99.37 232

TestCases				99.16 118	99.50 131	98.55 107		99.58 89	96.80 325	98.88 226	99.06 184	97.65 159	99.57 375	94.45 373	99.61 245	99.37 232

XVG-OURS		98.53 180	98.34 195	99.11 126	99.50 131	98.82 89	95.97 398	99.50 127	97.30 286	99.05 185	98.98 218	99.35 14	99.32 433	95.72 340	99.68 213	99.18 299

EG-PatchMatch MVS		98.99 86	99.01 86	98.94 161	99.50 131	97.47 209	98.04 196	99.59 87	98.15 207	99.40 115	99.36 104	98.58 67	99.76 267	98.78 103	99.68 213	99.59 107

fmvsm_s_conf0.5_n_2		99.14 63	99.31 42	98.63 223	99.49 139	96.08 295	97.38 304	99.81 31	99.48 45	99.84 30	99.57 49	98.46 76	99.89 97	99.82 12	99.97 21	99.91 13

SED-MVS		98.91 98	98.72 123	99.49 55	99.49 139	99.17 45	98.10 184	99.31 218	98.03 214	99.66 61	99.02 196	98.36 83	99.88 115	96.91 250	99.62 240	99.41 211

IU-MVS					99.49 139	99.15 53		98.87 324	92.97 429	99.41 112				96.76 267	99.62 240	99.66 78

test_241102_ONE					99.49 139	99.17 45		99.31 218	97.98 217	99.66 61	98.90 237	98.36 83	99.48 406

UA-Net		99.47 16	99.40 27	99.70 2	99.49 139	99.29 25	99.80 4	99.72 45	99.82 8	99.04 187	99.81 8	98.05 123	99.96 14	98.85 99	99.99 5	99.86 28

HFP-MVS		98.71 135	98.44 179	99.51 49	99.49 139	99.16 49	98.52 128	99.31 218	97.47 265	98.58 273	98.50 325	97.97 130	99.85 156	96.57 288	99.59 251	99.53 151

VPA-MVSNet		99.30 34	99.30 45	99.28 96	99.49 139	98.36 124	99.00 72	99.45 154	99.63 29	99.52 88	99.44 86	98.25 100	99.88 115	99.09 80	99.84 112	99.62 90

XVG-OURS-SEG-HR		98.49 187	98.28 206	99.14 122	99.49 139	98.83 87	96.54 363	99.48 137	97.32 284	99.11 170	98.61 309	99.33 15	99.30 436	96.23 314	98.38 403	99.28 268

fmvsm_s_conf0.5_n_11		99.21 48	99.34 36	98.80 184	99.48 147	96.56 275	97.97 217	99.69 54	99.63 29	99.84 30	99.54 63	98.21 107	99.94 42	99.76 23	99.95 38	99.88 20

114514_t		96.50 353	95.77 362	98.69 212	99.48 147	97.43 213	97.84 234	99.55 109	81.42 476	96.51 416	98.58 313	95.53 289	99.67 322	93.41 405	99.58 256	98.98 331

IterMVS-LS		98.55 175	98.70 131	98.09 299	99.48 147	94.73 349	97.22 325	99.39 183	98.97 124	99.38 118	99.31 118	96.00 269	99.93 54	98.58 118	99.97 21	99.60 100
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_10		99.15 58	99.27 48	98.78 191	99.47 150	96.56 275	97.75 250	99.71 47	99.60 36	99.74 47	99.44 86	97.96 131	99.95 26	99.86 4	99.94 50	99.82 36

fmvsm_s_conf0.5_n_5		99.07 79	99.10 74	98.99 151	99.47 150	97.22 229	97.40 301	99.83 25	97.61 249	99.85 27	99.30 119	98.80 40	99.95 26	99.71 32	99.90 86	99.78 47

v8		99.01 83	99.16 63	98.57 236	99.47 150	96.31 287	98.90 83	99.47 146	99.03 118	99.52 88	99.57 49	96.93 218	99.81 222	99.60 37	99.98 12	99.60 100

SSC-MVS3.2		98.53 180	98.79 115	97.74 328	99.46 153	93.62 395	96.45 369	99.34 205	99.33 66	98.93 215	98.70 289	97.90 135	99.90 81	99.12 77	99.92 69	99.69 70

fmvsm_s_conf0.5_n_3		99.22 47	99.37 32	98.78 191	99.46 153	96.58 273	97.65 264	99.72 45	99.47 48	99.86 24	99.50 69	98.94 30	99.89 97	99.75 26	99.97 21	99.86 28

XVS		98.72 134	98.45 177	99.53 39	99.46 153	99.21 34	98.65 112	99.34 205	98.62 155	97.54 361	98.63 305	97.50 179	99.83 192	96.79 263	99.53 273	99.56 129

X-MVStestdata		94.32 402	92.59 421	99.53 39	99.46 153	99.21 34	98.65 112	99.34 205	98.62 155	97.54 361	45.85 481	97.50 179	99.83 192	96.79 263	99.53 273	99.56 129

test20.03		98.78 126	98.77 118	98.78 191	99.46 153	97.20 232	97.78 241	99.24 252	99.04 117	99.41 112	98.90 237	97.65 159	99.76 267	97.70 190	99.79 147	99.39 221

guyue		98.01 249	97.93 253	98.26 282	99.45 158	95.48 319	98.08 187	96.24 431	98.89 135	99.34 127	99.14 167	91.32 373	99.82 205	99.07 81	99.83 119	99.48 180

CSCG		98.68 150	98.50 166	99.20 110	99.45 158	98.63 99	98.56 123	99.57 96	97.87 228	98.85 231	98.04 367	97.66 158	99.84 174	96.72 272	99.81 130	99.13 310

GeoE		99.05 80	98.99 90	99.25 104	99.44 160	98.35 125	98.73 101	99.56 105	98.42 173	98.91 218	98.81 263	98.94 30	99.91 74	98.35 134	99.73 181	99.49 169

v148		98.45 191	98.60 151	98.00 309	99.44 160	94.98 341	97.44 299	99.06 288	98.30 182	99.32 136	98.97 220	96.65 240	99.62 352	98.37 133	99.85 107	99.39 221

v10		98.97 90	99.11 72	98.55 243	99.44 160	96.21 289	98.90 83	99.55 109	98.73 145	99.48 96	99.60 45	96.63 241	99.83 192	99.70 33	99.99 5	99.61 98

V42		98.78 126	98.78 117	98.76 198	99.44 160	97.04 245	98.27 162	99.19 262	97.87 228	99.25 152	99.16 160	96.84 222	99.78 255	99.21 71	99.84 112	99.46 190

MDA-MVSNet-bldmvs		97.94 255	97.91 256	98.06 304	99.44 160	94.96 342	96.63 359	99.15 278	98.35 176	98.83 234	99.11 173	94.31 324	99.85 156	96.60 285	98.72 385	99.37 232

viewdifsd2359ckpt07		98.71 135	98.86 108	98.26 282	99.43 165	95.65 309	97.20 326	99.66 65	99.20 83	99.29 140	99.01 207	98.29 92	99.73 288	97.92 168	99.75 177	99.39 221

casdiffmvs_mvg		99.12 70	99.16 63	98.99 151	99.43 165	97.73 193	98.00 205	99.62 75	99.22 79	99.55 77	99.22 144	98.93 32	99.75 275	98.66 114	99.81 130	99.50 162
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SSM_0404		98.90 100	99.01 86	98.57 236	99.42 167	96.59 270	98.13 177	99.66 65	99.09 108	99.30 139	99.02 196	98.79 42	99.89 97	97.87 174	99.80 141	99.23 281

test1111		96.49 354	96.82 328	95.52 428	99.42 167	87.08 463	99.22 45	87.14 479	99.11 98	99.46 101	99.58 47	88.69 394	99.86 143	98.80 101	99.95 38	99.62 90

v2v482		98.56 171	98.62 146	98.37 272	99.42 167	95.81 306	97.58 278	99.16 273	97.90 226	99.28 142	99.01 207	95.98 274	99.79 244	99.33 60	99.90 86	99.51 158

OPM-MVS		98.56 171	98.32 201	99.25 104	99.41 170	98.73 95	97.13 333	99.18 266	97.10 306	98.75 249	98.92 231	98.18 110	99.65 342	96.68 276	99.56 263	99.37 232
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 243	98.08 235	98.04 307	99.41 170	94.59 355	94.59 450	99.40 181	97.50 262	98.82 237	98.83 257	96.83 224	99.84 174	97.50 205	99.81 130	99.71 63

E2		98.70 140	98.68 134	98.73 206	99.40 172	97.10 242	97.48 291	99.57 96	98.09 211	99.00 192	99.20 147	97.90 135	99.67 322	97.73 188	99.77 158	99.43 203

E3		98.69 144	98.68 134	98.73 206	99.40 172	97.10 242	97.48 291	99.57 96	98.09 211	99.00 192	99.20 147	97.90 135	99.67 322	97.73 188	99.77 158	99.43 203

test_one_0601					99.39 174	99.20 40		99.31 218	98.49 169	98.66 259	99.02 196	97.64 162

mvsany_test3		98.87 105	98.92 96	98.74 204	99.38 175	96.94 253	98.58 121	99.10 283	96.49 339	99.96 4	99.81 8	98.18 110	99.45 414	98.97 90	99.79 147	99.83 33

patch_mono-2		98.51 185	98.63 144	98.17 294	99.38 175	94.78 346	97.36 309	99.69 54	98.16 202	98.49 286	99.29 122	97.06 208	99.97 7	98.29 138	99.91 78	99.76 56

test2506		92.39 433	91.89 435	93.89 449	99.38 175	82.28 480	99.32 26	66.03 487	99.08 112	98.77 246	99.57 49	66.26 474	99.84 174	98.71 111	99.95 38	99.54 142

ECVR-MVS		96.42 356	96.61 342	95.85 420	99.38 175	88.18 458	99.22 45	86.00 481	99.08 112	99.36 123	99.57 49	88.47 399	99.82 205	98.52 126	99.95 38	99.54 142

casdiffmvs		98.95 93	99.00 88	98.81 181	99.38 175	97.33 218	97.82 235	99.57 96	99.17 92	99.35 125	99.17 158	98.35 87	99.69 308	98.46 128	99.73 181	99.41 211
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 92	99.02 84	98.76 198	99.38 175	97.26 225	98.49 138	99.50 127	98.86 138	99.19 162	99.06 184	98.23 102	99.69 308	98.71 111	99.76 173	99.33 252

TranMVSNet+NR-MVSNet		99.17 53	99.07 79	99.46 63	99.37 181	98.87 85	98.39 151	99.42 174	99.42 56	99.36 123	99.06 184	98.38 82	99.95 26	98.34 135	99.90 86	99.57 123

fmvsm_s_conf0.5_n_6		99.08 77	99.21 58	98.69 212	99.36 182	96.51 277	97.62 269	99.68 60	98.43 172	99.85 27	99.10 176	99.12 23	99.88 115	99.77 22	99.92 69	99.67 76

tttt0517		95.64 381	94.98 391	97.64 341	99.36 182	93.81 387	98.72 102	90.47 473	98.08 213	98.67 257	98.34 343	73.88 460	99.92 65	97.77 181	99.51 279	99.20 291

test_part2					99.36 182	99.10 66				99.05 185

v1144		98.60 165	98.66 139	98.41 265	99.36 182	95.90 300	97.58 278	99.34 205	97.51 261	99.27 144	99.15 164	96.34 255	99.80 231	99.47 54	99.93 56	99.51 158

CP-MVS		98.70 140	98.42 182	99.52 45	99.36 182	99.12 63	98.72 102	99.36 193	97.54 259	98.30 299	98.40 335	97.86 143	99.89 97	96.53 297	99.72 189	99.56 129

diffmvs_AUTHOR		98.50 186	98.59 153	98.23 289	99.35 187	95.48 319	96.61 360	99.60 80	98.37 174	98.90 219	99.00 211	97.37 189	99.76 267	98.22 142	99.85 107	99.46 190

Test_1112_low_res		96.99 335	96.55 346	98.31 278	99.35 187	95.47 322	95.84 410	99.53 118	91.51 446	96.80 403	98.48 328	91.36 372	99.83 192	96.58 286	99.53 273	99.62 90

DeepC-MVS	97.60 4	98.97 90	98.93 95	99.10 128	99.35 187	97.98 162	98.01 204	99.46 150	97.56 255	99.54 79	99.50 69	98.97 28	99.84 174	98.06 154	99.92 69	99.49 169
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 312	96.86 324	98.58 233	99.34 190	96.32 286	96.75 352	99.58 89	93.14 427	96.89 398	97.48 401	92.11 364	99.86 143	96.91 250	99.54 269	99.57 123

reproduce_model		99.15 58	98.97 92	99.67 4	99.33 191	99.44 10	98.15 175	99.47 146	99.12 97	99.52 88	99.32 117	98.31 90	99.90 81	97.78 180	99.73 181	99.66 78

MVSMamba_PlusPlus		98.83 115	98.98 91	98.36 273	99.32 192	96.58 273	98.90 83	99.41 178	99.75 11	98.72 252	99.50 69	96.17 260	99.94 42	99.27 65	99.78 152	98.57 391

fmvsm_s_conf0.5_n_4		99.01 83	99.22 55	98.38 269	99.31 193	95.48 319	97.56 280	99.73 44	98.87 136	99.75 45	99.27 125	98.80 40	99.86 143	99.80 17	99.90 86	99.81 40

SF-MVS		98.53 180	98.27 209	99.32 91	99.31 193	98.75 91	98.19 169	99.41 178	96.77 328	98.83 234	98.90 237	97.80 149	99.82 205	95.68 343	99.52 276	99.38 230

CPTT-MVS		97.84 270	97.36 294	99.27 99	99.31 193	98.46 115	98.29 158	99.27 241	94.90 395	97.83 341	98.37 339	94.90 305	99.84 174	93.85 394	99.54 269	99.51 158

UnsupCasMVSNet_eth		97.89 259	97.60 280	98.75 200	99.31 193	97.17 237	97.62 269	99.35 199	98.72 147	98.76 248	98.68 293	92.57 357	99.74 281	97.76 185	95.60 465	99.34 246

fmvsm_s_conf0.5_n_7		98.83 115	99.04 81	98.20 291	99.30 197	94.83 344	97.23 321	99.36 193	98.64 150	99.84 30	99.43 89	98.10 119	99.91 74	99.56 41	99.96 28	99.87 22

pmmvs-eth3d		98.47 189	98.34 195	98.86 174	99.30 197	97.76 189	97.16 331	99.28 238	95.54 377	99.42 110	99.19 150	97.27 196	99.63 349	97.89 169	99.97 21	99.20 291

mamv4		99.44 19	99.39 28	99.58 21	99.30 197	99.74 2	99.04 68	99.81 31	99.77 10	99.82 34	99.57 49	97.82 147	99.98 4	99.53 48	99.89 92	99.01 325

viewcassd2359sk11		98.55 175	98.51 163	98.67 215	99.29 200	96.99 248	97.39 302	99.54 114	97.73 238	98.81 239	99.08 182	97.55 171	99.66 335	97.52 204	99.67 219	99.36 239

SymmetryMVS		98.05 245	97.71 270	99.09 132	99.29 200	97.83 178	98.28 159	97.64 399	99.24 76	98.80 241	98.85 250	89.76 386	99.94 42	98.04 156	99.50 287	99.49 169

Anonymous20231211		99.27 38	99.27 48	99.26 101	99.29 200	98.18 137	99.49 12	99.51 124	99.70 16	99.80 38	99.68 25	96.84 222	99.83 192	99.21 71	99.91 78	99.77 50

viewmanbaseed2359cas		98.58 169	98.54 159	98.70 210	99.28 203	97.13 241	97.47 295	99.55 109	97.55 257	98.96 206	98.92 231	97.77 151	99.59 366	97.59 198	99.77 158	99.39 221

UnsupCasMVSNet_bld		97.30 310	96.92 320	98.45 260	99.28 203	96.78 264	96.20 386	99.27 241	95.42 381	98.28 303	98.30 347	93.16 343	99.71 297	94.99 357	97.37 441	98.87 352

EC-MVSNet		99.09 73	99.05 80	99.20 110	99.28 203	98.93 80	99.24 44	99.84 22	99.08 112	98.12 316	98.37 339	98.72 49	99.90 81	99.05 84	99.77 158	98.77 369

mamba_0408		98.80 122	98.88 101	98.55 243	99.27 206	96.50 278	98.00 205	99.60 80	98.93 129	99.22 157	98.84 255	98.59 62	99.89 97	97.74 186	99.72 189	99.27 269

SSM_04072		98.80 122	98.88 101	98.56 241	99.27 206	96.50 278	98.00 205	99.60 80	98.93 129	99.22 157	98.84 255	98.59 62	99.90 81	97.74 186	99.72 189	99.27 269

SSM_0407		98.86 109	98.96 94	98.55 243	99.27 206	96.50 278	98.04 196	99.66 65	99.09 108	99.22 157	99.02 196	98.79 42	99.87 134	97.87 174	99.72 189	99.27 269

reproduce-ours		99.09 73	98.90 98	99.67 4	99.27 206	99.49 6	98.00 205	99.42 174	99.05 115	99.48 96	99.27 125	98.29 92	99.89 97	97.61 195	99.71 198	99.62 90

our_new_method		99.09 73	98.90 98	99.67 4	99.27 206	99.49 6	98.00 205	99.42 174	99.05 115	99.48 96	99.27 125	98.29 92	99.89 97	97.61 195	99.71 198	99.62 90

DPE-MVS		98.59 167	98.26 210	99.57 22	99.27 206	99.15 53	97.01 336	99.39 183	97.67 242	99.44 105	98.99 213	97.53 175	99.89 97	95.40 351	99.68 213	99.66 78
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 269	98.18 222	96.87 389	99.27 206	91.16 438	95.53 420	99.25 247	99.10 105	99.41 112	99.35 105	93.10 345	99.96 14	98.65 115	99.94 50	99.49 169

v1192		98.60 165	98.66 139	98.41 265	99.27 206	95.88 301	97.52 285	99.36 193	97.41 274	99.33 130	99.20 147	96.37 253	99.82 205	99.57 39	99.92 69	99.55 136

N_pmnet		97.63 283	97.17 304	98.99 151	99.27 206	97.86 175	95.98 397	93.41 462	95.25 386	99.47 100	98.90 237	95.63 286	99.85 156	96.91 250	99.73 181	99.27 269

viewdifsd2359ckpt13		98.39 203	98.29 205	98.70 210	99.26 215	97.19 233	97.51 287	99.48 137	96.94 315	98.58 273	98.82 260	97.47 184	99.55 382	97.21 225	99.33 315	99.34 246

FPMVS		93.44 419	92.23 426	97.08 377	99.25 216	97.86 175	95.61 417	97.16 411	92.90 431	93.76 464	98.65 300	75.94 458	95.66 478	79.30 476	97.49 434	97.73 442

ME-MVS		98.61 163	98.33 200	99.44 66	99.24 217	98.93 80	97.45 297	99.06 288	98.14 208	99.06 177	98.77 270	96.97 216	99.82 205	96.67 277	99.64 230	99.58 115

new-patchmatchnet		98.35 206	98.74 119	97.18 372	99.24 217	92.23 420	96.42 373	99.48 137	98.30 182	99.69 56	99.53 65	97.44 185	99.82 205	98.84 100	99.77 158	99.49 169

MCST-MVS		98.00 250	97.63 278	99.10 128	99.24 217	98.17 138	96.89 345	98.73 352	95.66 372	97.92 332	97.70 389	97.17 203	99.66 335	96.18 319	99.23 334	99.47 188

UniMVSNet (Re)		98.87 105	98.71 128	99.35 80	99.24 217	98.73 95	97.73 253	99.38 185	98.93 129	99.12 169	98.73 279	96.77 230	99.86 143	98.63 117	99.80 141	99.46 190

jason		97.45 297	97.35 295	97.76 325	99.24 217	93.93 381	95.86 407	98.42 370	94.24 410	98.50 285	98.13 357	94.82 309	99.91 74	97.22 224	99.73 181	99.43 203
jason: jason.
IterMVS		97.73 275	98.11 231	96.57 399	99.24 217	90.28 447	95.52 422	99.21 256	98.86 138	99.33 130	99.33 112	93.11 344	99.94 42	98.49 127	99.94 50	99.48 180
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 175	98.62 146	98.32 276	99.22 223	95.58 312	97.51 287	99.45 154	97.16 303	99.45 104	99.24 138	96.12 264	99.85 156	99.60 37	99.88 94	99.55 136

ITE_SJBPF				98.87 172	99.22 223	98.48 114		99.35 199	97.50 262	98.28 303	98.60 311	97.64 162	99.35 429	93.86 393	99.27 326	98.79 367

h-mvs33		97.77 273	97.33 297	99.10 128	99.21 225	97.84 177	98.35 155	98.57 362	99.11 98	98.58 273	99.02 196	88.65 397	99.96 14	98.11 149	96.34 457	99.49 169

v144192		98.54 178	98.57 155	98.45 260	99.21 225	95.98 298	97.63 268	99.36 193	97.15 305	99.32 136	99.18 154	95.84 281	99.84 174	99.50 51	99.91 78	99.54 142

APDe-MVS		98.99 86	98.79 115	99.60 16	99.21 225	99.15 53	98.87 88	99.48 137	97.57 253	99.35 125	99.24 138	97.83 144	99.89 97	97.88 172	99.70 205	99.75 60
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 96	98.81 114	99.28 96	99.21 225	98.45 116	98.46 143	99.33 211	99.63 29	99.48 96	99.15 164	97.23 199	99.75 275	97.17 227	99.66 227	99.63 89

SR-MVS-dyc-post		98.81 120	98.55 157	99.57 22	99.20 229	99.38 13	98.48 141	99.30 226	98.64 150	98.95 207	98.96 223	97.49 182	99.86 143	96.56 292	99.39 306	99.45 195

RE-MVS-def			98.58 154		99.20 229	99.38 13	98.48 141	99.30 226	98.64 150	98.95 207	98.96 223	97.75 153		96.56 292	99.39 306	99.45 195

v1921920		98.54 178	98.60 151	98.38 269	99.20 229	95.76 308	97.56 280	99.36 193	97.23 297	99.38 118	99.17 158	96.02 267	99.84 174	99.57 39	99.90 86	99.54 142

E3new		98.41 194	98.34 195	98.62 225	99.19 232	96.90 256	97.32 312	99.50 127	97.40 276	98.63 262	98.92 231	97.21 201	99.65 342	97.34 216	99.52 276	99.31 259

thisisatest0530		95.27 388	94.45 399	97.74 328	99.19 232	94.37 359	97.86 231	90.20 474	97.17 302	98.22 306	97.65 391	73.53 461	99.90 81	96.90 255	99.35 312	98.95 337

Anonymous20240529		98.93 96	98.87 104	99.12 124	99.19 232	98.22 135	99.01 70	98.99 306	99.25 75	99.54 79	99.37 100	97.04 209	99.80 231	97.89 169	99.52 276	99.35 244

APD-MVS_3200maxsize		98.84 112	98.61 150	99.53 39	99.19 232	99.27 28	98.49 138	99.33 211	98.64 150	99.03 190	98.98 218	97.89 139	99.85 156	96.54 296	99.42 303	99.46 190

HQP_MVS		97.99 253	97.67 272	98.93 164	99.19 232	97.65 197	97.77 244	99.27 241	98.20 196	97.79 344	97.98 371	94.90 305	99.70 304	94.42 375	99.51 279	99.45 195

plane_prior7					99.19 232	97.87 174

ab-mvs		98.41 194	98.36 192	98.59 232	99.19 232	97.23 226	99.32 26	98.81 338	97.66 243	98.62 265	99.40 97	96.82 225	99.80 231	95.88 330	99.51 279	98.75 372

F-COLMAP		97.30 310	96.68 337	99.14 122	99.19 232	98.39 118	97.27 320	99.30 226	92.93 430	96.62 409	98.00 369	95.73 284	99.68 318	92.62 421	98.46 402	99.35 244

viewdifsd2359ckpt09		98.13 238	97.92 254	98.77 196	99.18 240	97.35 216	97.29 316	99.53 118	95.81 369	98.09 319	98.47 329	96.34 255	99.66 335	97.02 240	99.51 279	99.29 265

SR-MVS		98.71 135	98.43 180	99.57 22	99.18 240	99.35 17	98.36 154	99.29 234	98.29 185	98.88 226	98.85 250	97.53 175	99.87 134	96.14 321	99.31 319	99.48 180

UniMVSNet_NR-MVSNet		98.86 109	98.68 134	99.40 72	99.17 242	98.74 92	97.68 258	99.40 181	99.14 96	99.06 177	98.59 312	96.71 236	99.93 54	98.57 120	99.77 158	99.53 151

LF4IMVS		97.90 257	97.69 271	98.52 251	99.17 242	97.66 196	97.19 330	99.47 146	96.31 349	97.85 340	98.20 354	96.71 236	99.52 394	94.62 367	99.72 189	98.38 408

SMA-MVS		98.40 197	98.03 240	99.51 49	99.16 244	99.21 34	98.05 194	99.22 255	94.16 412	98.98 197	99.10 176	97.52 177	99.79 244	96.45 302	99.64 230	99.53 151
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		98.82 118	98.63 144	99.39 73	99.16 244	98.74 92	97.54 283	99.25 247	98.84 142	99.06 177	98.76 276	96.76 232	99.93 54	98.57 120	99.77 158	99.50 162

NR-MVSNet		98.95 93	98.82 112	99.36 74	99.16 244	98.72 97	99.22 45	99.20 258	99.10 105	99.72 48	98.76 276	96.38 252	99.86 143	98.00 161	99.82 124	99.50 162

MVS_111021_LR		98.30 215	98.12 230	98.83 177	99.16 244	98.03 157	96.09 394	99.30 226	97.58 252	98.10 318	98.24 350	98.25 100	99.34 430	96.69 275	99.65 228	99.12 311

DSMNet-mixed		97.42 300	97.60 280	96.87 389	99.15 248	91.46 427	98.54 126	99.12 280	92.87 432	97.58 357	99.63 39	96.21 259	99.90 81	95.74 339	99.54 269	99.27 269

D2MVS		97.84 270	97.84 261	97.83 317	99.14 249	94.74 348	96.94 340	98.88 322	95.84 368	98.89 222	98.96 223	94.40 321	99.69 308	97.55 199	99.95 38	99.05 317

pmmvs5		97.64 282	97.49 286	98.08 302	99.14 249	95.12 337	96.70 355	99.05 292	93.77 419	98.62 265	98.83 257	93.23 341	99.75 275	98.33 137	99.76 173	99.36 239

SPE-MVS-test		99.13 67	99.09 76	99.26 101	99.13 251	98.97 74	99.31 30	99.88 14	99.44 53	98.16 311	98.51 321	98.64 56	99.93 54	98.91 94	99.85 107	98.88 351

VDD-MVS		98.56 171	98.39 187	99.07 135	99.13 251	98.07 152	98.59 120	97.01 414	99.59 37	99.11 170	99.27 125	94.82 309	99.79 244	98.34 135	99.63 237	99.34 246

save fliter					99.11 253	97.97 163	96.53 365	99.02 300	98.24 188

APD-MVS		98.10 239	97.67 272	99.42 68	99.11 253	98.93 80	97.76 247	99.28 238	94.97 393	98.72 252	98.77 270	97.04 209	99.85 156	93.79 395	99.54 269	99.49 169
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 144	98.71 128	98.62 225	99.10 255	96.37 284	97.23 321	98.87 324	99.20 83	99.19 162	98.99 213	97.30 193	99.85 156	98.77 106	99.79 147	99.65 83

EI-MVSNet		98.40 197	98.51 163	98.04 307	99.10 255	94.73 349	97.20 326	98.87 324	98.97 124	99.06 177	99.02 196	96.00 269	99.80 231	98.58 118	99.82 124	99.60 100

CVMVSNet		96.25 362	97.21 303	93.38 456	99.10 255	80.56 484	97.20 326	98.19 381	96.94 315	99.00 192	99.02 196	89.50 390	99.80 231	96.36 308	99.59 251	99.78 47

EI-MVSNet-Vis-set		98.68 150	98.70 131	98.63 223	99.09 258	96.40 283	97.23 321	98.86 329	99.20 83	99.18 166	98.97 220	97.29 195	99.85 156	98.72 110	99.78 152	99.64 84

HPM-MVS++		98.10 239	97.64 277	99.48 57	99.09 258	99.13 61	97.52 285	98.75 349	97.46 270	96.90 397	97.83 381	96.01 268	99.84 174	95.82 337	99.35 312	99.46 190

DP-MVS Recon		97.33 308	96.92 320	98.57 236	99.09 258	97.99 159	96.79 348	99.35 199	93.18 426	97.71 348	98.07 365	95.00 304	99.31 434	93.97 388	99.13 350	98.42 405

MVS_111021_HR		98.25 224	98.08 235	98.75 200	99.09 258	97.46 210	95.97 398	99.27 241	97.60 251	97.99 329	98.25 349	98.15 116	99.38 425	96.87 258	99.57 260	99.42 208

BP-MVS1		97.40 302	96.97 316	98.71 209	99.07 262	96.81 260	98.34 157	97.18 409	98.58 161	98.17 308	98.61 309	84.01 429	99.94 42	98.97 90	99.78 152	99.37 232

9.14			97.78 263		99.07 262		97.53 284	99.32 213	95.53 378	98.54 281	98.70 289	97.58 168	99.76 267	94.32 380	99.46 292

PAPM_NR		96.82 342	96.32 353	98.30 279	99.07 262	96.69 268	97.48 291	98.76 346	95.81 369	96.61 410	96.47 427	94.12 330	99.17 447	90.82 448	97.78 428	99.06 316

TAMVS		98.24 225	98.05 238	98.80 184	99.07 262	97.18 235	97.88 227	98.81 338	96.66 333	99.17 168	99.21 145	94.81 311	99.77 261	96.96 248	99.88 94	99.44 199

CLD-MVS		97.49 293	97.16 305	98.48 257	99.07 262	97.03 246	94.71 443	99.21 256	94.46 404	98.06 322	97.16 413	97.57 169	99.48 406	94.46 372	99.78 152	98.95 337
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 67	99.10 74	99.24 106	99.06 267	99.15 53	99.36 22	99.88 14	99.36 64	98.21 307	98.46 330	98.68 53	99.93 54	99.03 86	99.85 107	98.64 384

thres100view900		94.19 405	93.67 410	95.75 423	99.06 267	91.35 431	98.03 198	94.24 457	98.33 178	97.40 373	94.98 457	79.84 445	99.62 352	83.05 469	98.08 419	96.29 464

thres600view7		94.45 400	93.83 407	96.29 407	99.06 267	91.53 426	97.99 212	94.24 457	98.34 177	97.44 371	95.01 455	79.84 445	99.67 322	84.33 467	98.23 408	97.66 445

plane_prior1					99.05 270

YYNet1		97.60 284	97.67 272	97.39 365	99.04 271	93.04 404	95.27 429	98.38 373	97.25 291	98.92 217	98.95 227	95.48 293	99.73 288	96.99 244	98.74 383	99.41 211

MDA-MVSNet_test_wron		97.60 284	97.66 275	97.41 364	99.04 271	93.09 400	95.27 429	98.42 370	97.26 290	98.88 226	98.95 227	95.43 294	99.73 288	97.02 240	98.72 385	99.41 211

MIMVSNet		96.62 349	96.25 357	97.71 332	99.04 271	94.66 352	99.16 54	96.92 420	97.23 297	97.87 337	99.10 176	86.11 412	99.65 342	91.65 432	99.21 338	98.82 356

FE-MVSNET3		97.37 304	97.13 309	98.11 298	99.03 274	95.40 325	94.47 453	98.99 306	96.87 321	97.97 330	97.81 382	92.12 363	99.75 275	97.49 210	99.43 302	99.16 306

icg_test_0407_2		98.20 230	98.38 189	97.65 338	99.03 274	94.03 372	95.78 412	99.45 154	98.16 202	99.06 177	98.71 282	98.27 96	99.68 318	97.50 205	99.45 294	99.22 286

IMVS_0407		98.39 203	98.64 142	97.66 336	99.03 274	94.03 372	98.10 184	99.45 154	98.16 202	99.06 177	98.71 282	98.27 96	99.71 297	97.50 205	99.45 294	99.22 286

IMVS_0404		98.07 243	98.20 217	97.69 333	99.03 274	94.03 372	96.67 356	99.45 154	98.16 202	98.03 326	98.71 282	96.80 228	99.82 205	97.50 205	99.45 294	99.22 286

IMVS_0403		98.34 207	98.56 156	97.66 336	99.03 274	94.03 372	97.98 213	99.45 154	98.16 202	98.89 222	98.71 282	97.90 135	99.74 281	97.50 205	99.45 294	99.22 286

PatchMatch-RL		97.24 316	96.78 331	98.61 229	99.03 274	97.83 178	96.36 376	99.06 288	93.49 424	97.36 377	97.78 383	95.75 283	99.49 403	93.44 404	98.77 382	98.52 393

viewmambaseed2359dif		98.19 231	98.26 210	97.99 310	99.02 280	95.03 340	96.59 362	99.53 118	96.21 352	99.00 192	98.99 213	97.62 164	99.61 359	97.62 194	99.72 189	99.33 252

GDP-MVS		97.50 290	97.11 310	98.67 215	99.02 280	96.85 258	98.16 174	99.71 47	98.32 180	98.52 284	98.54 316	83.39 433	99.95 26	98.79 102	99.56 263	99.19 296

ZD-MVS					99.01 282	98.84 86		99.07 287	94.10 414	98.05 324	98.12 359	96.36 254	99.86 143	92.70 420	99.19 342

CDPH-MVS		97.26 313	96.66 340	99.07 135	99.00 283	98.15 139	96.03 396	99.01 303	91.21 450	97.79 344	97.85 380	96.89 220	99.69 308	92.75 418	99.38 309	99.39 221

diffmvs		98.22 226	98.24 214	98.17 294	99.00 283	95.44 323	96.38 375	99.58 89	97.79 235	98.53 282	98.50 325	96.76 232	99.74 281	97.95 167	99.64 230	99.34 246
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		98.40 197	98.19 221	99.03 145	99.00 283	97.65 197	96.85 346	98.94 309	98.57 163	98.89 222	98.50 325	95.60 287	99.85 156	97.54 201	99.85 107	99.59 107

plane_prior6					98.99 286	97.70 195						94.90 305

xiu_mvs_v1_base_debu		97.86 264	98.17 223	96.92 386	98.98 287	93.91 382	96.45 369	99.17 270	97.85 230	98.41 293	97.14 415	98.47 72	99.92 65	98.02 158	99.05 356	96.92 457

xiu_mvs_v1_base		97.86 264	98.17 223	96.92 386	98.98 287	93.91 382	96.45 369	99.17 270	97.85 230	98.41 293	97.14 415	98.47 72	99.92 65	98.02 158	99.05 356	96.92 457

xiu_mvs_v1_base_debi		97.86 264	98.17 223	96.92 386	98.98 287	93.91 382	96.45 369	99.17 270	97.85 230	98.41 293	97.14 415	98.47 72	99.92 65	98.02 158	99.05 356	96.92 457

MVP-Stereo		98.08 242	97.92 254	98.57 236	98.96 290	96.79 261	97.90 225	99.18 266	96.41 345	98.46 288	98.95 227	95.93 278	99.60 362	96.51 298	98.98 370	99.31 259
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 197	98.68 134	97.54 353	98.96 290	97.99 159	97.88 227	99.36 193	98.20 196	99.63 67	99.04 193	98.76 45	95.33 480	96.56 292	99.74 178	99.31 259
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				98.91 168	98.94 292	97.76 189		98.76 346	87.58 467	96.75 405	98.10 361	94.80 312	99.78 255	92.73 419	99.00 365	99.20 291

USDC		97.41 301	97.40 290	97.44 362	98.94 292	93.67 392	95.17 432	99.53 118	94.03 416	98.97 201	99.10 176	95.29 296	99.34 430	95.84 336	99.73 181	99.30 263

tfpn200view9		94.03 409	93.44 412	95.78 422	98.93 294	91.44 429	97.60 275	94.29 455	97.94 222	97.10 383	94.31 464	79.67 447	99.62 352	83.05 469	98.08 419	96.29 464

testdata				98.09 299	98.93 294	95.40 325		98.80 340	90.08 458	97.45 370	98.37 339	95.26 297	99.70 304	93.58 400	98.95 373	99.17 303

thres400		94.14 407	93.44 412	96.24 410	98.93 294	91.44 429	97.60 275	94.29 455	97.94 222	97.10 383	94.31 464	79.67 447	99.62 352	83.05 469	98.08 419	97.66 445

TAPA-MVS	96.21 11	96.63 348	95.95 359	98.65 217	98.93 294	98.09 146	96.93 342	99.28 238	83.58 473	98.13 315	97.78 383	96.13 262	99.40 421	93.52 401	99.29 324	98.45 398
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 298	96.93 254	95.54 419	98.78 343	85.72 470	96.86 400	98.11 360	94.43 319			99.10 355	99.23 281

PVSNet_BlendedMVS		97.55 289	97.53 283	97.60 345	98.92 298	93.77 389	96.64 358	99.43 168	94.49 402	97.62 353	99.18 154	96.82 225	99.67 322	94.73 364	99.93 56	99.36 239

PVSNet_Blended		96.88 338	96.68 337	97.47 360	98.92 298	93.77 389	94.71 443	99.43 168	90.98 452	97.62 353	97.36 409	96.82 225	99.67 322	94.73 364	99.56 263	98.98 331

MSDG		97.71 277	97.52 284	98.28 281	98.91 301	96.82 259	94.42 454	99.37 189	97.65 244	98.37 298	98.29 348	97.40 187	99.33 432	94.09 386	99.22 335	98.68 382

Anonymous202405211		97.90 257	97.50 285	99.08 133	98.90 302	98.25 129	98.53 127	96.16 432	98.87 136	99.11 170	98.86 247	90.40 382	99.78 255	97.36 215	99.31 319	99.19 296

原ACMM1				98.35 274	98.90 302	96.25 288		98.83 337	92.48 436	96.07 427	98.10 361	95.39 295	99.71 297	92.61 422	98.99 367	99.08 313

GBi-Net		98.65 155	98.47 174	99.17 115	98.90 302	98.24 130	99.20 48	99.44 162	98.59 158	98.95 207	99.55 57	94.14 327	99.86 143	97.77 181	99.69 208	99.41 211

test1		98.65 155	98.47 174	99.17 115	98.90 302	98.24 130	99.20 48	99.44 162	98.59 158	98.95 207	99.55 57	94.14 327	99.86 143	97.77 181	99.69 208	99.41 211

FMVSNet2		98.49 187	98.40 184	98.75 200	98.90 302	97.14 240	98.61 118	99.13 279	98.59 158	99.19 162	99.28 123	94.14 327	99.82 205	97.97 165	99.80 141	99.29 265

OMC-MVS		97.88 261	97.49 286	99.04 144	98.89 307	98.63 99	96.94 340	99.25 247	95.02 391	98.53 282	98.51 321	97.27 196	99.47 409	93.50 403	99.51 279	99.01 325

VortexMVS		97.98 254	98.31 202	97.02 380	98.88 308	91.45 428	98.03 198	99.47 146	98.65 149	99.55 77	99.47 79	91.49 371	99.81 222	99.32 61	99.91 78	99.80 42

MVSFormer		98.26 221	98.43 180	97.77 322	98.88 308	93.89 385	99.39 20	99.56 105	99.11 98	98.16 311	98.13 357	93.81 335	99.97 7	99.26 66	99.57 260	99.43 203

lupinMVS		97.06 328	96.86 324	97.65 338	98.88 308	93.89 385	95.48 423	97.97 387	93.53 422	98.16 311	97.58 395	93.81 335	99.91 74	96.77 266	99.57 260	99.17 303

dmvs_re		95.98 370	95.39 380	97.74 328	98.86 311	97.45 211	98.37 153	95.69 444	97.95 220	96.56 411	95.95 436	90.70 379	97.68 474	88.32 457	96.13 461	98.11 420

DELS-MVS		98.27 219	98.20 217	98.48 257	98.86 311	96.70 267	95.60 418	99.20 258	97.73 238	98.45 289	98.71 282	97.50 179	99.82 205	98.21 143	99.59 251	98.93 342
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		97.89 259	97.98 245	97.60 345	98.86 311	94.35 360	96.21 385	99.44 162	97.45 272	99.06 177	98.88 244	97.99 129	99.28 440	94.38 379	99.58 256	99.18 299

LCM-MVSNet-Re		98.64 157	98.48 172	99.11 126	98.85 314	98.51 112	98.49 138	99.83 25	98.37 174	99.69 56	99.46 81	98.21 107	99.92 65	94.13 385	99.30 322	98.91 346

pmmvs4		97.58 287	97.28 298	98.51 252	98.84 315	96.93 254	95.40 427	98.52 365	93.60 421	98.61 267	98.65 300	95.10 301	99.60 362	96.97 247	99.79 147	98.99 330

NP-MVS					98.84 315	97.39 215					96.84 418

sss		97.21 318	96.93 318	98.06 304	98.83 317	95.22 333	96.75 352	98.48 367	94.49 402	97.27 379	97.90 377	92.77 353	99.80 231	96.57 288	99.32 317	99.16 306

PVSNet	93.40 17	95.67 379	95.70 365	95.57 427	98.83 317	88.57 454	92.50 471	97.72 392	92.69 434	96.49 419	96.44 428	93.72 338	99.43 417	93.61 398	99.28 325	98.71 375

MVE	83.40 22	92.50 432	91.92 434	94.25 443	98.83 317	91.64 425	92.71 470	83.52 483	95.92 366	86.46 481	95.46 449	95.20 298	95.40 479	80.51 474	98.64 394	95.73 472
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 413	93.91 405	93.39 455	98.82 320	81.72 482	97.76 247	95.28 446	98.60 157	96.54 412	96.66 422	65.85 477	99.62 352	96.65 281	98.99 367	98.82 356

ambc				98.24 286	98.82 320	95.97 299	98.62 116	99.00 305		99.27 144	99.21 145	96.99 214	99.50 400	96.55 295	99.50 287	99.26 275

旧先验1					98.82 320	97.45 211		98.76 346			98.34 343	95.50 292			99.01 364	99.23 281

test_vis1_rt		97.75 274	97.72 269	97.83 317	98.81 323	96.35 285	97.30 315	99.69 54	94.61 400	97.87 337	98.05 366	96.26 258	98.32 468	98.74 108	98.18 411	98.82 356

WTY-MVS		96.67 346	96.27 356	97.87 315	98.81 323	94.61 354	96.77 350	97.92 389	94.94 394	97.12 382	97.74 386	91.11 375	99.82 205	93.89 391	98.15 415	99.18 299

3Dnovator+	97.89 3	98.69 144	98.51 163	99.24 106	98.81 323	98.40 117	99.02 69	99.19 262	98.99 121	98.07 321	99.28 123	97.11 207	99.84 174	96.84 261	99.32 317	99.47 188

QAPM		97.31 309	96.81 330	98.82 179	98.80 326	97.49 205	99.06 65	99.19 262	90.22 456	97.69 350	99.16 160	96.91 219	99.90 81	90.89 447	99.41 304	99.07 315

VNet		98.42 193	98.30 203	98.79 188	98.79 327	97.29 222	98.23 165	98.66 356	99.31 69	98.85 231	98.80 264	94.80 312	99.78 255	98.13 148	99.13 350	99.31 259

DPM-MVS		96.32 358	95.59 371	98.51 252	98.76 328	97.21 231	94.54 452	98.26 376	91.94 441	96.37 420	97.25 411	93.06 347	99.43 417	91.42 437	98.74 383	98.89 348

3Dnovator	98.27 2	98.81 120	98.73 121	99.05 142	98.76 328	97.81 186	99.25 43	99.30 226	98.57 163	98.55 279	99.33 112	97.95 132	99.90 81	97.16 228	99.67 219	99.44 199

PLC	94.65 16	96.51 351	95.73 364	98.85 175	98.75 330	97.91 171	96.42 373	99.06 288	90.94 453	95.59 433	97.38 407	94.41 320	99.59 366	90.93 445	98.04 424	99.05 317
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 340	96.75 333	97.08 377	98.74 331	93.33 398	96.71 354	98.26 376	96.72 330	98.44 290	97.37 408	95.20 298	99.47 409	91.89 427	97.43 438	98.44 401

hse-mvs2		97.46 295	97.07 311	98.64 219	98.73 332	97.33 218	97.45 297	97.64 399	99.11 98	98.58 273	97.98 371	88.65 397	99.79 244	98.11 149	97.39 440	98.81 361

CDS-MVSNet		97.69 278	97.35 295	98.69 212	98.73 332	97.02 247	96.92 344	98.75 349	95.89 367	98.59 271	98.67 295	92.08 365	99.74 281	96.72 272	99.81 130	99.32 255
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 360	95.83 361	97.64 341	98.72 334	94.30 361	98.87 88	98.77 344	97.80 233	96.53 413	98.02 368	97.34 191	99.47 409	76.93 478	99.48 290	99.16 306

EIA-MVS		98.00 250	97.74 266	98.80 184	98.72 334	98.09 146	98.05 194	99.60 80	97.39 277	96.63 408	95.55 444	97.68 156	99.80 231	96.73 271	99.27 326	98.52 393

LFMVS		97.20 319	96.72 334	98.64 219	98.72 334	96.95 252	98.93 81	94.14 459	99.74 13	98.78 243	99.01 207	84.45 424	99.73 288	97.44 211	99.27 326	99.25 276

new_pmnet		96.99 335	96.76 332	97.67 334	98.72 334	94.89 343	95.95 402	98.20 379	92.62 435	98.55 279	98.54 316	94.88 308	99.52 394	93.96 389	99.44 301	98.59 390

Fast-Effi-MVS+		97.67 280	97.38 292	98.57 236	98.71 338	97.43 213	97.23 321	99.45 154	94.82 397	96.13 424	96.51 424	98.52 70	99.91 74	96.19 317	98.83 379	98.37 410

TEST9					98.71 338	98.08 150	95.96 400	99.03 297	91.40 447	95.85 430	97.53 397	96.52 245	99.76 267

train_agg		97.10 325	96.45 350	99.07 135	98.71 338	98.08 150	95.96 400	99.03 297	91.64 442	95.85 430	97.53 397	96.47 247	99.76 267	93.67 397	99.16 345	99.36 239

TSAR-MVS + GP.		98.18 233	97.98 245	98.77 196	98.71 338	97.88 173	96.32 379	98.66 356	96.33 347	99.23 156	98.51 321	97.48 183	99.40 421	97.16 228	99.46 292	99.02 324

FA-MVS(test-final)		96.99 335	96.82 328	97.50 357	98.70 342	94.78 346	99.34 23	96.99 415	95.07 390	98.48 287	99.33 112	88.41 400	99.65 342	96.13 323	98.92 376	98.07 423

AUN-MVS		96.24 364	95.45 376	98.60 231	98.70 342	97.22 229	97.38 304	97.65 397	95.95 365	95.53 440	97.96 375	82.11 441	99.79 244	96.31 310	97.44 437	98.80 366

our_test_3		97.39 303	97.73 268	96.34 405	98.70 342	89.78 450	94.61 449	98.97 308	96.50 338	99.04 187	98.85 250	95.98 274	99.84 174	97.26 222	99.67 219	99.41 211

ppachtmachnet_test		97.50 290	97.74 266	96.78 395	98.70 342	91.23 437	94.55 451	99.05 292	96.36 346	99.21 160	98.79 266	96.39 250	99.78 255	96.74 269	99.82 124	99.34 246

PCF-MVS	92.86 18	94.36 401	93.00 419	98.42 264	98.70 342	97.56 202	93.16 469	99.11 282	79.59 477	97.55 360	97.43 404	92.19 361	99.73 288	79.85 475	99.45 294	97.97 429
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 256	98.02 241	97.58 347	98.69 347	94.10 368	98.13 177	98.90 318	97.95 220	97.32 378	99.58 47	95.95 277	98.75 463	96.41 304	99.22 335	99.87 22

ETV-MVS		98.03 246	97.86 260	98.56 241	98.69 347	98.07 152	97.51 287	99.50 127	98.10 210	97.50 365	95.51 445	98.41 79	99.88 115	96.27 313	99.24 331	97.71 444

test_prior				98.95 160	98.69 347	97.95 167		99.03 297					99.59 366			99.30 263

mvsmamba		97.57 288	97.26 299	98.51 252	98.69 347	96.73 266	98.74 97	97.25 408	97.03 311	97.88 336	99.23 143	90.95 376	99.87 134	96.61 284	99.00 365	98.91 346

agg_prior					98.68 351	97.99 159		99.01 303		95.59 433			99.77 261

test_8					98.67 352	98.01 158	95.91 406	99.02 300	91.64 442	95.79 432	97.50 400	96.47 247	99.76 267

HQP-NCC					98.67 352		96.29 381		96.05 358	95.55 436

ACMP_Plane					98.67 352		96.29 381		96.05 358	95.55 436

CNVR-MVS		98.17 235	97.87 259	99.07 135	98.67 352	98.24 130	97.01 336	98.93 312	97.25 291	97.62 353	98.34 343	97.27 196	99.57 375	96.42 303	99.33 315	99.39 221

HQP-MVS		97.00 334	96.49 349	98.55 243	98.67 352	96.79 261	96.29 381	99.04 295	96.05 358	95.55 436	96.84 418	93.84 333	99.54 388	92.82 415	99.26 329	99.32 255

MM		98.22 226	97.99 244	98.91 168	98.66 357	96.97 249	97.89 226	94.44 453	99.54 41	98.95 207	99.14 167	93.50 339	99.92 65	99.80 17	99.96 28	99.85 30

test_fmvs1		97.72 276	97.94 251	97.07 379	98.66 357	92.39 415	97.68 258	99.81 31	95.20 389	99.54 79	99.44 86	91.56 370	99.41 420	99.78 21	99.77 158	99.40 220

balanced_conf03		98.63 159	98.72 123	98.38 269	98.66 357	96.68 269	98.90 83	99.42 174	98.99 121	98.97 201	99.19 150	95.81 282	99.85 156	98.77 106	99.77 158	98.60 387

thres200		93.72 415	93.14 417	95.46 431	98.66 357	91.29 433	96.61 360	94.63 452	97.39 277	96.83 401	93.71 467	79.88 444	99.56 378	82.40 472	98.13 416	95.54 473

wuyk23d		96.06 366	97.62 279	91.38 460	98.65 361	98.57 106	98.85 92	96.95 418	96.86 323	99.90 14	99.16 160	99.18 19	98.40 467	89.23 455	99.77 158	77.18 480

NCCC		97.86 264	97.47 289	99.05 142	98.61 362	98.07 152	96.98 338	98.90 318	97.63 245	97.04 387	97.93 376	95.99 273	99.66 335	95.31 352	98.82 381	99.43 203

DeepC-MVS_fast	96.85 6	98.30 215	98.15 227	98.75 200	98.61 362	97.23 226	97.76 247	99.09 285	97.31 285	98.75 249	98.66 298	97.56 170	99.64 346	96.10 324	99.55 267	99.39 221
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 417	92.09 428	97.75 326	98.60 364	94.40 358	97.32 312	95.26 447	97.56 255	96.79 404	95.50 446	53.57 485	99.77 261	95.26 353	98.97 371	99.08 313

thisisatest0515		94.12 408	93.16 416	96.97 384	98.60 364	92.90 405	93.77 465	90.61 472	94.10 414	96.91 394	95.87 439	74.99 459	99.80 231	94.52 370	99.12 353	98.20 416

GA-MVS		95.86 373	95.32 383	97.49 358	98.60 364	94.15 367	93.83 464	97.93 388	95.49 379	96.68 406	97.42 405	83.21 434	99.30 436	96.22 315	98.55 400	99.01 325

dmvs_testset		92.94 427	92.21 427	95.13 435	98.59 367	90.99 440	97.65 264	92.09 468	96.95 314	94.00 460	93.55 468	92.34 359	96.97 477	72.20 479	92.52 475	97.43 452

OPU-MVS				98.82 179	98.59 367	98.30 126	98.10 184				98.52 320	98.18 110	98.75 463	94.62 367	99.48 290	99.41 211

MSLP-MVS++		98.02 247	98.14 229	97.64 341	98.58 369	95.19 334	97.48 291	99.23 254	97.47 265	97.90 334	98.62 307	97.04 209	98.81 461	97.55 199	99.41 304	98.94 341

test12				98.93 164	98.58 369	97.83 178		98.66 356		96.53 413		95.51 291	99.69 308		99.13 350	99.27 269

CL-MVSNet_self_test		97.44 298	97.22 302	98.08 302	98.57 371	95.78 307	94.30 457	98.79 341	96.58 336	98.60 269	98.19 355	94.74 315	99.64 346	96.41 304	98.84 378	98.82 356

PS-MVSNAJ		97.08 327	97.39 291	96.16 416	98.56 372	92.46 413	95.24 431	98.85 332	97.25 291	97.49 366	95.99 435	98.07 120	99.90 81	96.37 306	98.67 393	96.12 469

CNLPA		97.17 322	96.71 335	98.55 243	98.56 372	98.05 156	96.33 378	98.93 312	96.91 319	97.06 386	97.39 406	94.38 322	99.45 414	91.66 431	99.18 344	98.14 419

xiu_mvs_v2_base		97.16 323	97.49 286	96.17 414	98.54 374	92.46 413	95.45 424	98.84 333	97.25 291	97.48 367	96.49 425	98.31 90	99.90 81	96.34 309	98.68 392	96.15 468

alignmvs		97.35 306	96.88 323	98.78 191	98.54 374	98.09 146	97.71 254	97.69 394	99.20 83	97.59 356	95.90 438	88.12 402	99.55 382	98.18 145	98.96 372	98.70 378

FE-MVS		95.66 380	94.95 393	97.77 322	98.53 376	95.28 330	99.40 19	96.09 435	93.11 428	97.96 331	99.26 131	79.10 451	99.77 261	92.40 424	98.71 387	98.27 414

Effi-MVS+		98.02 247	97.82 262	98.62 225	98.53 376	97.19 233	97.33 311	99.68 60	97.30 286	96.68 406	97.46 403	98.56 68	99.80 231	96.63 282	98.20 410	98.86 353

baseline1		95.96 371	95.44 377	97.52 355	98.51 378	93.99 379	98.39 151	96.09 435	98.21 192	98.40 297	97.76 385	86.88 404	99.63 349	95.42 350	89.27 478	98.95 337

MVS_Test		98.18 233	98.36 192	97.67 334	98.48 379	94.73 349	98.18 170	99.02 300	97.69 241	98.04 325	99.11 173	97.22 200	99.56 378	98.57 120	98.90 377	98.71 375

MGCFI-Net		98.34 207	98.28 206	98.51 252	98.47 380	97.59 201	98.96 77	99.48 137	99.18 91	97.40 373	95.50 446	98.66 54	99.50 400	98.18 145	98.71 387	98.44 401

BH-RMVSNet		96.83 340	96.58 345	97.58 347	98.47 380	94.05 369	96.67 356	97.36 403	96.70 332	97.87 337	97.98 371	95.14 300	99.44 416	90.47 450	98.58 399	99.25 276

sasdasda		98.34 207	98.26 210	98.58 233	98.46 382	97.82 183	98.96 77	99.46 150	99.19 88	97.46 368	95.46 449	98.59 62	99.46 412	98.08 152	98.71 387	98.46 395

canonicalmvs		98.34 207	98.26 210	98.58 233	98.46 382	97.82 183	98.96 77	99.46 150	99.19 88	97.46 368	95.46 449	98.59 62	99.46 412	98.08 152	98.71 387	98.46 395

MVS-HIRNet		94.32 402	95.62 368	90.42 461	98.46 382	75.36 485	96.29 381	89.13 476	95.25 386	95.38 442	99.75 16	92.88 350	99.19 446	94.07 387	99.39 306	96.72 462

PHI-MVS		98.29 218	97.95 249	99.34 83	98.44 385	99.16 49	98.12 181	99.38 185	96.01 362	98.06 322	98.43 333	97.80 149	99.67 322	95.69 342	99.58 256	99.20 291

DVP-MVS++		98.90 100	98.70 131	99.51 49	98.43 386	99.15 53	99.43 15	99.32 213	98.17 199	99.26 148	99.02 196	98.18 110	99.88 115	97.07 237	99.45 294	99.49 169

MSC_two_6792asdad				99.32 91	98.43 386	98.37 121		98.86 329					99.89 97	97.14 231	99.60 247	99.71 63

No_MVS				99.32 91	98.43 386	98.37 121		98.86 329					99.89 97	97.14 231	99.60 247	99.71 63

Fast-Effi-MVS+-dtu		98.27 219	98.09 232	98.81 181	98.43 386	98.11 143	97.61 274	99.50 127	98.64 150	97.39 375	97.52 399	98.12 118	99.95 26	96.90 255	98.71 387	98.38 408

OpenMVS_ROB	95.38 14	95.84 375	95.18 388	97.81 319	98.41 390	97.15 239	97.37 308	98.62 360	83.86 472	98.65 260	98.37 339	94.29 325	99.68 318	88.41 456	98.62 397	96.60 463

DeepPCF-MVS	96.93 5	98.32 212	98.01 242	99.23 108	98.39 391	98.97 74	95.03 436	99.18 266	96.88 320	99.33 130	98.78 268	98.16 114	99.28 440	96.74 269	99.62 240	99.44 199

Patchmatch-test		96.55 350	96.34 352	97.17 374	98.35 392	93.06 401	98.40 150	97.79 390	97.33 282	98.41 293	98.67 295	83.68 432	99.69 308	95.16 355	99.31 319	98.77 369

AdaColmap		97.14 324	96.71 335	98.46 259	98.34 393	97.80 187	96.95 339	98.93 312	95.58 376	96.92 392	97.66 390	95.87 280	99.53 390	90.97 444	99.14 348	98.04 424

OpenMVS	96.65 7	97.09 326	96.68 337	98.32 276	98.32 394	97.16 238	98.86 91	99.37 189	89.48 460	96.29 422	99.15 164	96.56 243	99.90 81	92.90 412	99.20 339	97.89 432

MG-MVS		96.77 343	96.61 342	97.26 370	98.31 395	93.06 401	95.93 403	98.12 384	96.45 344	97.92 332	98.73 279	93.77 337	99.39 423	91.19 442	99.04 359	99.33 252

test_yl		96.69 344	96.29 354	97.90 312	98.28 396	95.24 331	97.29 316	97.36 403	98.21 192	98.17 308	97.86 378	86.27 408	99.55 382	94.87 361	98.32 404	98.89 348

DCV-MVSNet		96.69 344	96.29 354	97.90 312	98.28 396	95.24 331	97.29 316	97.36 403	98.21 192	98.17 308	97.86 378	86.27 408	99.55 382	94.87 361	98.32 404	98.89 348

CHOSEN 280x420		95.51 385	95.47 374	95.65 426	98.25 398	88.27 457	93.25 468	98.88 322	93.53 422	94.65 451	97.15 414	86.17 410	99.93 54	97.41 213	99.93 56	98.73 374

SCA		96.41 357	96.66 340	95.67 424	98.24 399	88.35 456	95.85 409	96.88 421	96.11 356	97.67 351	98.67 295	93.10 345	99.85 156	94.16 381	99.22 335	98.81 361

DeepMVS_CX				93.44 454	98.24 399	94.21 364		94.34 454	64.28 480	91.34 474	94.87 461	89.45 391	92.77 481	77.54 477	93.14 474	93.35 476

MS-PatchMatch		97.68 279	97.75 265	97.45 361	98.23 401	93.78 388	97.29 316	98.84 333	96.10 357	98.64 261	98.65 300	96.04 266	99.36 426	96.84 261	99.14 348	99.20 291

BH-w/o		95.13 391	94.89 395	95.86 419	98.20 402	91.31 432	95.65 416	97.37 402	93.64 420	96.52 415	95.70 442	93.04 348	99.02 452	88.10 458	95.82 464	97.24 455

mvs_anonymous		97.83 272	98.16 226	96.87 389	98.18 403	91.89 422	97.31 314	98.90 318	97.37 279	98.83 234	99.46 81	96.28 257	99.79 244	98.90 95	98.16 414	98.95 337

miper_lstm_enhance		97.18 321	97.16 305	97.25 371	98.16 404	92.85 406	95.15 434	99.31 218	97.25 291	98.74 251	98.78 268	90.07 383	99.78 255	97.19 226	99.80 141	99.11 312

RRT-MVS		97.88 261	97.98 245	97.61 344	98.15 405	93.77 389	98.97 76	99.64 71	99.16 93	98.69 254	99.42 90	91.60 368	99.89 97	97.63 193	98.52 401	99.16 306

ET-MVSNet_ETH3D		94.30 404	93.21 415	97.58 347	98.14 406	94.47 357	94.78 442	93.24 464	94.72 398	89.56 476	95.87 439	78.57 454	99.81 222	96.91 250	97.11 449	98.46 395

ADS-MVSNet2		95.43 386	94.98 391	96.76 396	98.14 406	91.74 423	97.92 222	97.76 391	90.23 454	96.51 416	98.91 234	85.61 415	99.85 156	92.88 413	96.90 450	98.69 379

ADS-MVSNet		95.24 389	94.93 394	96.18 413	98.14 406	90.10 449	97.92 222	97.32 406	90.23 454	96.51 416	98.91 234	85.61 415	99.74 281	92.88 413	96.90 450	98.69 379

c3_l		97.36 305	97.37 293	97.31 366	98.09 409	93.25 399	95.01 437	99.16 273	97.05 308	98.77 246	98.72 281	92.88 350	99.64 346	96.93 249	99.76 173	99.05 317

FMVSNet3		97.50 290	97.24 301	98.29 280	98.08 410	95.83 304	97.86 231	98.91 317	97.89 227	98.95 207	98.95 227	87.06 403	99.81 222	97.77 181	99.69 208	99.23 281

PAPM		91.88 441	90.34 444	96.51 400	98.06 411	92.56 411	92.44 472	97.17 410	86.35 468	90.38 475	96.01 434	86.61 406	99.21 445	70.65 481	95.43 466	97.75 441

Effi-MVS+-dtu		98.26 221	97.90 257	99.35 80	98.02 412	99.49 6	98.02 201	99.16 273	98.29 185	97.64 352	97.99 370	96.44 249	99.95 26	96.66 280	98.93 375	98.60 387

eth_miper_zixun_eth		97.23 317	97.25 300	97.17 374	98.00 413	92.77 408	94.71 443	99.18 266	97.27 289	98.56 277	98.74 278	91.89 366	99.69 308	97.06 239	99.81 130	99.05 317

HY-MVS	95.94 13	95.90 372	95.35 382	97.55 352	97.95 414	94.79 345	98.81 96	96.94 419	92.28 439	95.17 444	98.57 314	89.90 385	99.75 275	91.20 441	97.33 445	98.10 421

UGNet		98.53 180	98.45 177	98.79 188	97.94 415	96.96 251	99.08 61	98.54 363	99.10 105	96.82 402	99.47 79	96.55 244	99.84 174	98.56 123	99.94 50	99.55 136
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		96.47 355	95.70 365	98.79 188	97.92 416	99.12 63	98.28 159	98.60 361	92.16 440	95.54 439	96.17 432	94.77 314	99.52 394	89.62 453	98.23 408	97.72 443
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		96.86 339	96.55 346	97.79 320	97.91 417	94.21 364	97.56 280	98.87 324	97.49 264	99.06 177	99.05 191	80.72 442	99.80 231	98.44 129	99.82 124	99.37 232

API-MVS		97.04 330	96.91 322	97.42 363	97.88 418	98.23 134	98.18 170	98.50 366	97.57 253	97.39 375	96.75 420	96.77 230	99.15 449	90.16 451	99.02 363	94.88 474

myMVS_eth3d28		92.92 428	92.31 424	94.77 438	97.84 419	87.59 461	96.19 387	96.11 434	97.08 307	94.27 454	93.49 470	66.07 476	98.78 462	91.78 429	97.93 427	97.92 431

miper_ehance_all_eth		97.06 328	97.03 313	97.16 376	97.83 420	93.06 401	94.66 446	99.09 285	95.99 363	98.69 254	98.45 331	92.73 355	99.61 359	96.79 263	99.03 360	98.82 356

cl____		97.02 331	96.83 327	97.58 347	97.82 421	94.04 371	94.66 446	99.16 273	97.04 309	98.63 262	98.71 282	88.68 396	99.69 308	97.00 242	99.81 130	99.00 329

DIV-MVS_self_test		97.02 331	96.84 326	97.58 347	97.82 421	94.03 372	94.66 446	99.16 273	97.04 309	98.63 262	98.71 282	88.69 394	99.69 308	97.00 242	99.81 130	99.01 325

CANet		97.87 263	97.76 264	98.19 293	97.75 423	95.51 315	96.76 351	99.05 292	97.74 237	96.93 391	98.21 353	95.59 288	99.89 97	97.86 176	99.93 56	99.19 296

UBG		93.25 422	92.32 423	96.04 418	97.72 424	90.16 448	95.92 405	95.91 439	96.03 361	93.95 462	93.04 473	69.60 466	99.52 394	90.72 449	97.98 425	98.45 398

mvsany_test1		97.60 284	97.54 282	97.77 322	97.72 424	95.35 327	95.36 428	97.13 412	94.13 413	99.71 50	99.33 112	97.93 133	99.30 436	97.60 197	98.94 374	98.67 383

PVSNet_0	89.98 21	91.15 442	90.30 445	93.70 451	97.72 424	84.34 475	90.24 475	97.42 401	90.20 457	93.79 463	93.09 472	90.90 378	98.89 460	86.57 464	72.76 481	97.87 434

CR-MVSNet		96.28 360	95.95 359	97.28 368	97.71 427	94.22 362	98.11 182	98.92 315	92.31 438	96.91 394	99.37 100	85.44 418	99.81 222	97.39 214	97.36 443	97.81 437

RPMNet		97.02 331	96.93 318	97.30 367	97.71 427	94.22 362	98.11 182	99.30 226	99.37 61	96.91 394	99.34 109	86.72 405	99.87 134	97.53 202	97.36 443	97.81 437

ETVMVS		92.60 431	91.08 440	97.18 372	97.70 429	93.65 394	96.54 363	95.70 442	96.51 337	94.68 450	92.39 476	61.80 482	99.50 400	86.97 461	97.41 439	98.40 406

pmmvs3		95.03 393	94.40 400	96.93 385	97.70 429	92.53 412	95.08 435	97.71 393	88.57 464	97.71 348	98.08 364	79.39 449	99.82 205	96.19 317	99.11 354	98.43 403

baseline2		93.73 414	92.83 420	96.42 403	97.70 429	91.28 434	96.84 347	89.77 475	93.96 418	92.44 470	95.93 437	79.14 450	99.77 261	92.94 411	96.76 454	98.21 415

WBMVS		95.18 390	94.78 396	96.37 404	97.68 432	89.74 451	95.80 411	98.73 352	97.54 259	98.30 299	98.44 332	70.06 464	99.82 205	96.62 283	99.87 98	99.54 142

tpm		94.67 398	94.34 402	95.66 425	97.68 432	88.42 455	97.88 227	94.90 449	94.46 404	96.03 429	98.56 315	78.66 452	99.79 244	95.88 330	95.01 468	98.78 368

CANet_DTU		97.26 313	97.06 312	97.84 316	97.57 434	94.65 353	96.19 387	98.79 341	97.23 297	95.14 445	98.24 350	93.22 342	99.84 174	97.34 216	99.84 112	99.04 321

testing11		93.08 425	92.02 430	96.26 409	97.56 435	90.83 443	96.32 379	95.70 442	96.47 341	92.66 469	93.73 466	64.36 480	99.59 366	93.77 396	97.57 432	98.37 410

tpm2		93.09 424	92.58 422	94.62 440	97.56 435	86.53 464	97.66 262	95.79 441	86.15 469	94.07 459	98.23 352	75.95 457	99.53 390	90.91 446	96.86 453	97.81 437

testing91		93.32 420	92.27 425	96.47 402	97.54 437	91.25 435	96.17 391	96.76 423	97.18 301	93.65 465	93.50 469	65.11 479	99.63 349	93.04 410	97.45 436	98.53 392

TR-MVS		95.55 383	95.12 389	96.86 392	97.54 437	93.94 380	96.49 368	96.53 428	94.36 409	97.03 389	96.61 423	94.26 326	99.16 448	86.91 463	96.31 458	97.47 451

testing99		93.04 426	91.98 433	96.23 411	97.53 439	90.70 445	96.35 377	95.94 438	96.87 321	93.41 466	93.43 471	63.84 481	99.59 366	93.24 408	97.19 446	98.40 406

1314		95.74 377	95.60 369	96.17 414	97.53 439	92.75 409	98.07 191	98.31 375	91.22 449	94.25 455	96.68 421	95.53 289	99.03 451	91.64 433	97.18 447	96.74 461

CostFormer		93.97 410	93.78 408	94.51 441	97.53 439	85.83 467	97.98 213	95.96 437	89.29 462	94.99 447	98.63 305	78.63 453	99.62 352	94.54 369	96.50 455	98.09 422

FMVSNet5		96.01 368	95.20 387	98.41 265	97.53 439	96.10 290	98.74 97	99.50 127	97.22 300	98.03 326	99.04 193	69.80 465	99.88 115	97.27 221	99.71 198	99.25 276

PMMVS		96.51 351	95.98 358	98.09 299	97.53 439	95.84 303	94.92 439	98.84 333	91.58 444	96.05 428	95.58 443	95.68 285	99.66 335	95.59 346	98.09 418	98.76 371

reproduce_monomvs		95.00 395	95.25 384	94.22 444	97.51 444	83.34 476	97.86 231	98.44 368	98.51 168	99.29 140	99.30 119	67.68 470	99.56 378	98.89 97	99.81 130	99.77 50

PAPR		95.29 387	94.47 398	97.75 326	97.50 445	95.14 336	94.89 440	98.71 354	91.39 448	95.35 443	95.48 448	94.57 317	99.14 450	84.95 466	97.37 441	98.97 334

testing222		91.96 439	90.37 443	96.72 397	97.47 446	92.59 410	96.11 393	94.76 450	96.83 324	92.90 468	92.87 474	57.92 483	99.55 382	86.93 462	97.52 433	98.00 428

PatchT		96.65 347	96.35 351	97.54 353	97.40 447	95.32 329	97.98 213	96.64 425	99.33 66	96.89 398	99.42 90	84.32 426	99.81 222	97.69 192	97.49 434	97.48 450

tpm cat1		93.29 421	93.13 418	93.75 450	97.39 448	84.74 470	97.39 302	97.65 397	83.39 474	94.16 456	98.41 334	82.86 437	99.39 423	91.56 435	95.35 467	97.14 456

PatchmatchNet		95.58 382	95.67 367	95.30 434	97.34 449	87.32 462	97.65 264	96.65 424	95.30 385	97.07 385	98.69 291	84.77 421	99.75 275	94.97 359	98.64 394	98.83 355
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 306	96.97 316	98.50 256	97.31 450	96.47 281	98.18 170	98.92 315	98.95 128	98.78 243	99.37 100	85.44 418	99.85 156	95.96 328	99.83 119	99.17 303

LS3D		98.63 159	98.38 189	99.36 74	97.25 451	99.38 13	99.12 60	99.32 213	99.21 81	98.44 290	98.88 244	97.31 192	99.80 231	96.58 286	99.34 314	98.92 343

IB-MVS	91.63 19	92.24 437	90.90 441	96.27 408	97.22 452	91.24 436	94.36 456	93.33 463	92.37 437	92.24 472	94.58 463	66.20 475	99.89 97	93.16 409	94.63 470	97.66 445
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
UWE-MVS		92.38 434	91.76 437	94.21 445	97.16 453	84.65 471	95.42 426	88.45 477	95.96 364	96.17 423	95.84 441	66.36 473	99.71 297	91.87 428	98.64 394	98.28 413

tpmrst		95.07 392	95.46 375	93.91 448	97.11 454	84.36 474	97.62 269	96.96 417	94.98 392	96.35 421	98.80 264	85.46 417	99.59 366	95.60 345	96.23 459	97.79 440

Syy-MVS		96.04 367	95.56 373	97.49 358	97.10 455	94.48 356	96.18 389	96.58 426	95.65 373	94.77 448	92.29 477	91.27 374	99.36 426	98.17 147	98.05 422	98.63 385

myMVS_eth3d		91.92 440	90.45 442	96.30 406	97.10 455	90.90 441	96.18 389	96.58 426	95.65 373	94.77 448	92.29 477	53.88 484	99.36 426	89.59 454	98.05 422	98.63 385

MDTV_nov1_ep13			95.22 386		97.06 457	83.20 477	97.74 251	96.16 432	94.37 408	96.99 390	98.83 257	83.95 430	99.53 390	93.90 390	97.95 426

MVS		93.19 423	92.09 428	96.50 401	96.91 458	94.03 372	98.07 191	98.06 386	68.01 479	94.56 453	96.48 426	95.96 276	99.30 436	83.84 468	96.89 452	96.17 466

E-PMN		94.17 406	94.37 401	93.58 452	96.86 459	85.71 468	90.11 477	97.07 413	98.17 199	97.82 343	97.19 412	84.62 423	98.94 456	89.77 452	97.68 431	96.09 470

JIA-IIPM		95.52 384	95.03 390	97.00 381	96.85 460	94.03 372	96.93 342	95.82 440	99.20 83	94.63 452	99.71 22	83.09 435	99.60 362	94.42 375	94.64 469	97.36 454

EMVS		93.83 412	94.02 404	93.23 457	96.83 461	84.96 469	89.77 478	96.32 430	97.92 224	97.43 372	96.36 431	86.17 410	98.93 457	87.68 459	97.73 430	95.81 471

cl22		95.79 376	95.39 380	96.98 383	96.77 462	92.79 407	94.40 455	98.53 364	94.59 401	97.89 335	98.17 356	82.82 438	99.24 442	96.37 306	99.03 360	98.92 343

WB-MVSnew		95.73 378	95.57 372	96.23 411	96.70 463	90.70 445	96.07 395	93.86 460	95.60 375	97.04 387	95.45 452	96.00 269	99.55 382	91.04 443	98.31 406	98.43 403

dp		93.47 418	93.59 411	93.13 458	96.64 464	81.62 483	97.66 262	96.42 429	92.80 433	96.11 425	98.64 303	78.55 455	99.59 366	93.31 406	92.18 477	98.16 418

MonoMVSNet		96.25 362	96.53 348	95.39 432	96.57 465	91.01 439	98.82 95	97.68 396	98.57 163	98.03 326	99.37 100	90.92 377	97.78 473	94.99 357	93.88 473	97.38 453

test-LLR		93.90 411	93.85 406	94.04 446	96.53 466	84.62 472	94.05 461	92.39 466	96.17 353	94.12 457	95.07 453	82.30 439	99.67 322	95.87 333	98.18 411	97.82 435

test-mter		92.33 436	91.76 437	94.04 446	96.53 466	84.62 472	94.05 461	92.39 466	94.00 417	94.12 457	95.07 453	65.63 478	99.67 322	95.87 333	98.18 411	97.82 435

TESTMET0.1,1		92.19 438	91.77 436	93.46 453	96.48 468	82.80 479	94.05 461	91.52 471	94.45 406	94.00 460	94.88 459	66.65 472	99.56 378	95.78 338	98.11 417	98.02 425

MGCNet		97.44 298	97.01 315	98.72 208	96.42 469	96.74 265	97.20 326	91.97 469	98.46 171	98.30 299	98.79 266	92.74 354	99.91 74	99.30 63	99.94 50	99.52 154

miper_enhance_ethall		96.01 368	95.74 363	96.81 393	96.41 470	92.27 419	93.69 466	98.89 321	91.14 451	98.30 299	97.35 410	90.58 380	99.58 373	96.31 310	99.03 360	98.60 387

tpmvs		95.02 394	95.25 384	94.33 442	96.39 471	85.87 465	98.08 187	96.83 422	95.46 380	95.51 441	98.69 291	85.91 413	99.53 390	94.16 381	96.23 459	97.58 448

CMPMVS	75.91 23	96.29 359	95.44 377	98.84 176	96.25 472	98.69 98	97.02 335	99.12 280	88.90 463	97.83 341	98.86 247	89.51 389	98.90 459	91.92 426	99.51 279	98.92 343
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 399	93.69 409	96.99 382	96.05 473	93.61 396	94.97 438	93.49 461	96.17 353	97.57 359	94.88 459	82.30 439	99.01 454	93.60 399	94.17 472	98.37 410

EPMVS		93.72 415	93.27 414	95.09 437	96.04 474	87.76 459	98.13 177	85.01 482	94.69 399	96.92 392	98.64 303	78.47 456	99.31 434	95.04 356	96.46 456	98.20 416

cascas		94.79 397	94.33 403	96.15 417	96.02 475	92.36 417	92.34 473	99.26 246	85.34 471	95.08 446	94.96 458	92.96 349	98.53 466	94.41 378	98.59 398	97.56 449

MVStest1		95.86 373	95.60 369	96.63 398	95.87 476	91.70 424	97.93 219	98.94 309	98.03 214	99.56 74	99.66 32	71.83 462	98.26 469	99.35 59	99.24 331	99.91 13

gg-mvs-nofinetune		92.37 435	91.20 439	95.85 420	95.80 477	92.38 416	99.31 30	81.84 484	99.75 11	91.83 473	99.74 18	68.29 467	99.02 452	87.15 460	97.12 448	96.16 467

gm-plane-assit					94.83 478	81.97 481			88.07 466		94.99 456		99.60 362	91.76 430

GG-mvs-BLEND				94.76 439	94.54 479	92.13 421	99.31 30	80.47 485		88.73 479	91.01 479	67.59 471	98.16 472	82.30 473	94.53 471	93.98 475

UWE-MVS-28		90.22 443	89.28 446	93.02 459	94.50 480	82.87 478	96.52 366	87.51 478	95.21 388	92.36 471	96.04 433	71.57 463	98.25 470	72.04 480	97.77 429	97.94 430

EPNet_dtu		94.93 396	94.78 396	95.38 433	93.58 481	87.68 460	96.78 349	95.69 444	97.35 281	89.14 478	98.09 363	88.15 401	99.49 403	94.95 360	99.30 322	98.98 331
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 447	75.95 450	77.12 464	92.39 482	67.91 488	90.16 476	59.44 489	82.04 475	89.42 477	94.67 462	49.68 486	81.74 482	48.06 482	77.66 480	81.72 478

KD-MVS_2432*1600		92.87 429	91.99 431	95.51 429	91.37 483	89.27 452	94.07 459	98.14 382	95.42 381	97.25 380	96.44 428	67.86 468	99.24 442	91.28 439	96.08 462	98.02 425

miper_refine_blended		92.87 429	91.99 431	95.51 429	91.37 483	89.27 452	94.07 459	98.14 382	95.42 381	97.25 380	96.44 428	67.86 468	99.24 442	91.28 439	96.08 462	98.02 425

EPNet		96.14 365	95.44 377	98.25 284	90.76 485	95.50 318	97.92 222	94.65 451	98.97 124	92.98 467	98.85 250	89.12 392	99.87 134	95.99 326	99.68 213	99.39 221
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 448	68.95 451	70.34 465	87.68 486	65.00 489	91.11 474	59.90 488	69.02 478	74.46 483	88.89 480	48.58 487	68.03 484	28.61 483	72.33 482	77.99 479

test_method		79.78 445	79.50 448	80.62 462	80.21 487	45.76 490	70.82 479	98.41 372	31.08 482	80.89 482	97.71 387	84.85 420	97.37 475	91.51 436	80.03 479	98.75 372

tmp_tt		78.77 446	78.73 449	78.90 463	58.45 488	74.76 487	94.20 458	78.26 486	39.16 481	86.71 480	92.82 475	80.50 443	75.19 483	86.16 465	92.29 476	86.74 477

testmvs		17.12 450	20.53 453	6.87 467	12.05 489	4.20 492	93.62 467	6.73 490	4.62 485	10.41 485	24.33 482	8.28 489	3.56 486	9.69 485	15.07 483	12.86 482

test123		17.04 451	20.11 454	7.82 466	10.25 490	4.91 491	94.80 441	4.47 491	4.93 484	10.00 486	24.28 483	9.69 488	3.64 485	10.14 484	12.43 484	14.92 481

mmdepth		0.00 454	0.00 457	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.00 486	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

monomultidepth		0.00 454	0.00 457	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.00 486	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

test_blank		0.00 454	0.00 457	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.00 486	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

eth-test2					0.00 491

eth-test					0.00 491

uanet_test		0.00 454	0.00 457	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.00 486	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

DCPMVS		0.00 454	0.00 457	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.00 486	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

cdsmvs_eth3d_5k		24.66 449	32.88 452	0.00 468	0.00 491	0.00 493	0.00 480	99.10 283	0.00 486	0.00 487	97.58 395	99.21 18	0.00 487	0.00 486	0.00 485	0.00 483

pcd_1.5k_mvsjas		8.17 452	10.90 455	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.00 486	98.07 120	0.00 487	0.00 486	0.00 485	0.00 483

sosnet-low-res		0.00 454	0.00 457	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.00 486	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

sosnet		0.00 454	0.00 457	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.00 486	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

uncertanet		0.00 454	0.00 457	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.00 486	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

Regformer		0.00 454	0.00 457	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.00 486	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

ab-mvs-re		8.12 453	10.83 456	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	97.48 401	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

uanet		0.00 454	0.00 457	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.00 486	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

TestfortrainingZip							98.68 107

WAC-MVS						90.90 441								91.37 438

PC_three_1452									93.27 425	99.40 115	98.54 316	98.22 105	97.00 476	95.17 354	99.45 294	99.49 169

test_241102_TWO								99.30 226	98.03 214	99.26 148	99.02 196	97.51 178	99.88 115	96.91 250	99.60 247	99.66 78

test_0728_THIRD									98.17 199	99.08 175	99.02 196	97.89 139	99.88 115	97.07 237	99.71 198	99.70 68

GSMVS																98.81 361

sam_mvs1												84.74 422				98.81 361

sam_mvs												84.29 428

MTGPA								99.20 258

test_post1							97.59 277				20.48 485	83.07 436	99.66 335	94.16 381

test_post											21.25 484	83.86 431	99.70 304

patchmatchnet-post											98.77 270	84.37 425	99.85 156

MTMP							97.93 219	91.91 470

test9_res														93.28 407	99.15 347	99.38 230

agg_prior2														92.50 423	99.16 345	99.37 232

test_prior4						97.97 163	95.86 407

test_prior2							95.74 414		96.48 340	96.11 425	97.63 393	95.92 279		94.16 381	99.20 339

旧先验2							95.76 413		88.56 465	97.52 363			99.66 335	94.48 371

新几何2							95.93 403

无先验							95.74 414	98.74 351	89.38 461				99.73 288	92.38 425		99.22 286

原ACMM2							95.53 420

testdata2													99.79 244	92.80 417

segment_acmp												97.02 212

testdata1							95.44 425		96.32 348

plane_prior5								99.27 241					99.70 304	94.42 375	99.51 279	99.45 195

plane_prior4											97.98 371

plane_prior3						97.78 188			97.41 274	97.79 344

plane_prior2							97.77 244		98.20 196

plane_prior						97.65 197	97.07 334		96.72 330						99.36 310

n2								0.00 492

nn								0.00 492

door-mid								99.57 96

test11								98.87 324

door								99.41 178

HQP5-MVS						96.79 261

BP-MVS														92.82 415

HQP4-MVS										95.56 435			99.54 388			99.32 255

HQP3-MVS								99.04 295							99.26 329

HQP2-MVS												93.84 333

MDTV_nov1_ep13_2view						74.92 486	97.69 257		90.06 459	97.75 347		85.78 414		93.52 401		98.69 379

ACMMP++_ref															99.77 158

ACMMP++															99.68 213

Test By Simon												96.52 245

High-resolution multi-view benchmark