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 82	99.16 64	98.64 219	99.94 2	98.51 113	99.32 27	99.75 43	99.58 39	98.60 268	99.62 41	98.22 105	99.51 397	97.70 190	99.73 181	97.89 430
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 30	99.31 43	99.53 39	99.91 3	98.98 72	99.63 7	99.58 89	99.44 54	99.78 40	99.76 15	96.39 249	99.92 65	99.44 55	99.92 69	99.68 71

FE-MVSNET1		99.51 14	99.54 14	99.43 68	99.90 4	98.85 86	99.33 26	99.79 36	99.47 48	99.51 93	99.75 16	99.10 24	99.84 174	99.14 76	99.91 78	99.59 107

pmmvs6		99.67 3	99.70 3	99.60 16	99.90 4	99.27 28	99.53 9	99.76 40	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 18	99.49 17	99.35 81	99.90 4	98.15 140	99.20 49	99.65 70	99.48 45	99.92 8	99.71 23	98.07 120	99.96 14	99.53 48	100.00 1	99.93 11

testf1		99.25 42	99.16 64	99.51 49	99.89 7	99.63 4	98.71 105	99.69 55	98.90 134	99.43 107	99.35 106	98.86 35	99.67 321	97.81 177	99.81 130	99.24 278

APD_test2		99.25 42	99.16 64	99.51 49	99.89 7	99.63 4	98.71 105	99.69 55	98.90 134	99.43 107	99.35 106	98.86 35	99.67 321	97.81 177	99.81 130	99.24 278

ANet_high		99.57 10	99.67 6	99.28 97	99.89 7	98.09 147	99.14 58	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 22	99.62 10	99.88 10	99.08 70	99.34 23	99.69 55	98.93 130	99.65 64	99.72 22	98.93 33	99.95 26	99.11 79	100.00 1	99.82 36

v7n		99.53 12	99.57 13	99.41 71	99.88 10	98.54 111	99.45 14	99.61 79	99.66 24	99.68 58	99.66 33	98.44 79	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 10	98.61 103	99.34 23	99.71 48	99.27 75	99.90 14	99.74 19	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 75	99.87 13	98.13 143	98.08 188	99.95 1	99.45 52	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 13	98.61 103	99.28 41	99.66 66	99.09 109	99.89 18	99.68 26	99.53 7	99.97 7	99.50 51	99.99 5	99.87 22

test_djsdf		99.52 13	99.51 16	99.53 39	99.86 15	98.74 93	99.39 20	99.56 105	99.11 99	99.70 52	99.73 21	99.00 28	99.97 7	99.26 66	99.98 12	99.89 16

MIMVSNet1		99.38 29	99.32 41	99.55 29	99.86 15	99.19 43	99.41 17	99.59 87	99.59 37	99.71 50	99.57 50	97.12 204	99.90 81	99.21 71	99.87 99	99.54 143

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 27	99.85 17	99.11 65	99.90 1	99.78 37	99.63 29	99.78 40	99.67 31	99.48 10	99.81 223	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 18	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 89	99.95 38	99.78 47

SixPastTwentyTwo		98.75 131	98.62 146	99.16 119	99.83 19	97.96 167	99.28 41	98.20 377	99.37 62	99.70 52	99.65 37	92.65 355	99.93 54	99.04 86	99.84 113	99.60 100

sc_t1		99.62 7	99.66 8	99.53 39	99.82 20	99.09 69	99.50 11	99.63 74	99.88 4	99.86 24	99.80 11	99.03 25	99.89 97	99.48 53	99.93 56	99.60 100

Baseline_NR-MVSNet		98.98 90	98.86 108	99.36 75	99.82 20	98.55 108	97.47 295	99.57 96	99.37 62	99.21 161	99.61 44	96.76 231	99.83 193	98.06 155	99.83 120	99.71 63

pm-mvs1		99.44 20	99.48 19	99.33 90	99.80 22	98.63 100	99.29 37	99.63 74	99.30 72	99.65 64	99.60 46	99.16 22	99.82 206	99.07 82	99.83 120	99.56 130

TransMVSNet (Re)		99.44 20	99.47 22	99.36 75	99.80 22	98.58 106	99.27 43	99.57 96	99.39 60	99.75 45	99.62 41	99.17 20	99.83 193	99.06 84	99.62 240	99.66 78

K. test v3		98.00 249	97.66 274	99.03 146	99.79 24	97.56 203	99.19 53	92.47 463	99.62 33	99.52 88	99.66 33	89.61 386	99.96 14	99.25 68	99.81 130	99.56 130

test_fmvsmconf0.1_n		99.49 16	99.54 14	99.34 84	99.78 25	98.11 144	97.77 245	99.90 11	99.33 67	99.97 3	99.66 33	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 84	99.78 25	99.47 9	98.42 150	99.45 153	98.28 187	98.98 197	99.19 150	97.76 152	99.58 371	96.57 286	99.55 267	98.97 332

test_vis3_rt		99.14 64	99.17 62	99.07 136	99.78 25	98.38 120	98.92 83	99.94 2	97.80 233	99.91 12	99.67 31	97.15 203	98.91 456	99.76 23	99.56 263	99.92 12

EGC-MVSNET		85.24 442	80.54 445	99.34 84	99.77 28	99.20 40	99.08 62	99.29 233	12.08 481	20.84 482	99.42 91	97.55 171	99.85 156	97.08 234	99.72 189	98.96 334

Anonymous20240521		98.69 144	98.87 104	98.16 295	99.77 28	95.11 336	99.08 62	99.44 161	99.34 66	99.33 131	99.55 58	94.10 330	99.94 42	99.25 68	99.96 28	99.42 208

FC-MVSNet-test		99.27 39	99.25 54	99.34 84	99.77 28	98.37 122	99.30 36	99.57 96	99.61 35	99.40 116	99.50 70	97.12 204	99.85 156	99.02 88	99.94 50	99.80 42

test_vis1_n		98.31 213	98.50 166	97.73 329	99.76 31	94.17 364	98.68 108	99.91 9	96.31 347	99.79 39	99.57 50	92.85 351	99.42 417	99.79 19	99.84 113	99.60 100

test_fmvs3		99.12 71	99.41 27	98.25 283	99.76 31	95.07 337	99.05 68	99.94 2	97.78 236	99.82 34	99.84 3	98.56 69	99.71 297	99.96 1	99.96 28	99.97 4

XXY-MVS		99.14 64	99.15 69	99.10 129	99.76 31	97.74 192	98.85 93	99.62 76	98.48 170	99.37 121	99.49 76	98.75 47	99.86 143	98.20 145	99.80 141	99.71 63

TDRefinement		99.42 25	99.38 30	99.55 29	99.76 31	99.33 21	99.68 6	99.71 48	99.38 61	99.53 83	99.61 44	98.64 57	99.80 232	98.24 140	99.84 113	99.52 155

fmvsm_s_conf0.1_n_a		99.17 54	99.30 46	98.80 184	99.75 35	96.59 269	97.97 218	99.86 16	98.22 190	99.88 21	99.71 23	98.59 63	99.84 174	99.73 28	99.98 12	99.98 3

tt0805		98.69 144	98.62 146	98.90 172	99.75 35	99.30 23	99.15 57	96.97 414	98.86 139	98.87 230	97.62 392	98.63 59	98.96 453	99.41 57	98.29 405	98.45 396

test_vis1_n_1920		98.40 196	98.92 97	96.81 391	99.74 37	90.76 442	98.15 176	99.91 9	98.33 178	99.89 18	99.55 58	95.07 301	99.88 115	99.76 23	99.93 56	99.79 44

FOURS1					99.73 38	99.67 3	99.43 15	99.54 114	99.43 56	99.26 149

PEN-MVS		99.41 26	99.34 37	99.62 10	99.73 38	99.14 58	99.29 37	99.54 114	99.62 33	99.56 74	99.42 91	98.16 114	99.96 14	98.78 104	99.93 56	99.77 50

lessismore_v0				98.97 158	99.73 38	97.53 205		86.71 478		99.37 121	99.52 69	89.93 382	99.92 65	98.99 90	99.72 189	99.44 199

SteuartSystems-ACMMP		98.79 124	98.54 159	99.54 32	99.73 38	99.16 49	98.23 166	99.31 217	97.92 224	98.90 219	98.90 236	98.00 126	99.88 115	96.15 318	99.72 189	99.58 116
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 234	98.15 226	98.22 289	99.73 38	95.15 333	97.36 309	99.68 61	94.45 404	98.99 196	99.27 125	96.87 220	99.94 42	97.13 231	99.91 78	99.57 124

Vis-MVSNet		99.34 31	99.36 34	99.27 100	99.73 38	98.26 129	99.17 54	99.78 37	99.11 99	99.27 145	99.48 77	98.82 38	99.95 26	98.94 93	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 44	98.98 72	99.51 10	99.85 18	99.86 6	99.88 21	99.82 5	99.02 27	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 44	96.08 294	98.74 98	98.64 357	99.74 13	99.67 60	99.24 138	94.57 316	99.95 26	99.11 79	99.24 329	99.82 36

test_f		98.67 153	98.87 104	98.05 304	99.72 44	95.59 309	98.51 134	99.81 31	96.30 349	99.78 40	99.82 5	96.14 260	98.63 463	99.82 12	99.93 56	99.95 9

ACMH	96.65 7	99.25 42	99.24 55	99.26 102	99.72 44	98.38 120	99.07 65	99.55 109	98.30 182	99.65 64	99.45 86	99.22 17	99.76 268	98.44 130	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 48	98.94 79	99.54 8	99.83 25	99.87 5	99.89 18	99.82 5	98.75 47	99.90 81	99.54 44	99.95 38	99.59 107

fmvsm_s_conf0.1_n		99.16 58	99.33 39	98.64 219	99.71 48	96.10 289	97.87 231	99.85 18	98.56 166	99.90 14	99.68 26	98.69 53	99.85 156	99.72 30	99.98 12	99.97 4

PS-CasMVS		99.40 27	99.33 39	99.62 10	99.71 48	99.10 66	99.29 37	99.53 118	99.53 42	99.46 102	99.41 95	98.23 102	99.95 26	98.89 98	99.95 38	99.81 40

DTE-MVSNet		99.43 24	99.35 35	99.66 7	99.71 48	99.30 23	99.31 31	99.51 124	99.64 27	99.56 74	99.46 82	98.23 102	99.97 7	98.78 104	99.93 56	99.72 62

WR-MVS_H		99.33 32	99.22 56	99.65 8	99.71 48	99.24 31	99.32 27	99.55 109	99.46 51	99.50 95	99.34 110	97.30 193	99.93 54	98.90 96	99.93 56	99.77 50

HPM-MVS_fast		99.01 84	98.82 112	99.57 22	99.71 48	99.35 17	99.00 73	99.50 127	97.33 281	98.94 214	98.86 246	98.75 47	99.82 206	97.53 202	99.71 198	99.56 130

ACMH+	96.62 9	99.08 78	99.00 89	99.33 90	99.71 48	98.83 88	98.60 120	99.58 89	99.11 99	99.53 83	99.18 154	98.81 39	99.67 321	96.71 272	99.77 158	99.50 162

PMVS	91.26 20	97.86 263	97.94 250	97.65 336	99.71 48	97.94 169	98.52 129	98.68 353	98.99 122	97.52 361	99.35 106	97.41 186	98.18 469	91.59 432	99.67 219	96.82 458
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FE-MVSNET2		99.15 59	99.22 56	98.94 162	99.70 56	97.49 206	98.62 117	99.67 65	98.85 142	99.34 128	99.54 64	98.47 73	99.81 223	98.93 94	99.91 78	99.51 158

KinetiMVS		99.03 82	99.02 85	99.03 146	99.70 56	97.48 209	98.43 147	99.29 233	99.70 16	99.60 71	99.07 183	96.13 261	99.94 42	99.42 56	99.87 99	99.68 71

FIs		99.14 64	99.09 77	99.29 96	99.70 56	98.28 128	99.13 59	99.52 123	99.48 45	99.24 155	99.41 95	96.79 228	99.82 206	98.69 114	99.88 95	99.76 56

VPNet		98.87 106	98.83 111	99.01 150	99.70 56	97.62 201	98.43 147	99.35 198	99.47 48	99.28 143	99.05 191	96.72 234	99.82 206	98.09 152	99.36 308	99.59 107

fmvsm_s_conf0.1_n_2		99.20 52	99.38 30	98.65 217	99.69 60	96.08 294	97.49 290	99.90 11	99.53 42	99.88 21	99.64 38	98.51 72	99.90 81	99.83 10	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 210	98.68 134	97.27 367	99.69 60	92.29 416	98.03 199	99.85 18	97.62 246	99.96 4	99.62 41	93.98 331	99.74 281	99.52 50	99.86 106	99.79 44

MP-MVS-pluss		98.57 170	98.23 214	99.60 16	99.69 60	99.35 17	97.16 330	99.38 184	94.87 394	98.97 201	98.99 213	98.01 125	99.88 115	97.29 218	99.70 205	99.58 116
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 47	99.32 41	98.96 159	99.68 63	97.35 217	98.84 95	99.48 136	99.69 18	99.63 67	99.68 26	99.03 25	99.96 14	97.97 165	99.92 69	99.57 124

sd_testset		99.28 38	99.31 43	99.19 113	99.68 63	98.06 156	99.41 17	99.30 225	99.69 18	99.63 67	99.68 26	99.25 16	99.96 14	97.25 221	99.92 69	99.57 124

test_fmvs1_n		98.09 240	98.28 205	97.52 353	99.68 63	93.47 395	98.63 115	99.93 5	95.41 382	99.68 58	99.64 38	91.88 365	99.48 404	99.82 12	99.87 99	99.62 90

CHOSEN 1792x2688		97.49 292	97.14 307	98.54 247	99.68 63	96.09 292	96.50 366	99.62 76	91.58 442	98.84 233	98.97 220	92.36 357	99.88 115	96.76 265	99.95 38	99.67 76

tfpnnormal		98.90 101	98.90 99	98.91 169	99.67 67	97.82 184	99.00 73	99.44 161	99.45 52	99.51 93	99.24 138	98.20 109	99.86 143	95.92 327	99.69 208	99.04 319

MTAPA		98.88 105	98.64 142	99.61 14	99.67 67	99.36 16	98.43 147	99.20 257	98.83 144	98.89 222	98.90 236	96.98 214	99.92 65	97.16 226	99.70 205	99.56 130

test_fmvsmvis_n_1920		99.26 41	99.49 17	98.54 247	99.66 69	96.97 249	98.00 206	99.85 18	99.24 77	99.92 8	99.50 70	99.39 12	99.95 26	99.89 3	99.98 12	98.71 373

mvs5depth		99.30 35	99.59 12	98.44 261	99.65 70	95.35 325	99.82 3	99.94 2	99.83 7	99.42 111	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 53	99.27 49	98.94 162	99.65 70	97.05 244	97.80 240	99.76 40	98.70 149	99.78 40	99.11 173	98.79 43	99.95 26	99.85 6	99.96 28	99.83 33

WB-MVS		98.52 184	98.55 157	98.43 262	99.65 70	95.59 309	98.52 129	98.77 342	99.65 26	99.52 88	99.00 211	94.34 322	99.93 54	98.65 116	98.83 377	99.76 56

CP-MVSNet		99.21 49	99.09 77	99.56 27	99.65 70	98.96 78	99.13 59	99.34 204	99.42 57	99.33 131	99.26 131	97.01 212	99.94 42	98.74 109	99.93 56	99.79 44

HPM-MVS		98.79 124	98.53 161	99.59 20	99.65 70	99.29 25	99.16 55	99.43 167	96.74 327	98.61 266	98.38 337	98.62 60	99.87 134	96.47 298	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 69	99.65 70	99.42 11	98.55 125	99.57 96	97.72 240	98.90 219	99.26 131	96.12 263	99.52 392	95.72 338	99.71 198	99.32 255

NormalMVS		98.26 220	97.97 247	99.15 122	99.64 76	97.83 179	98.28 160	99.43 167	99.24 77	98.80 241	98.85 249	89.76 384	99.94 42	98.04 157	99.67 219	99.68 71

lecture		99.25 42	99.12 72	99.62 10	99.64 76	99.40 12	98.89 88	99.51 124	99.19 89	99.37 121	99.25 136	98.36 84	99.88 115	98.23 142	99.67 219	99.59 107

fmvsm_l_conf0.5_n		99.21 49	99.28 48	99.02 149	99.64 76	97.28 224	97.82 236	99.76 40	98.73 146	99.82 34	99.09 181	98.81 39	99.95 26	99.86 4	99.96 28	99.83 33

test_fmvsmconf_n		99.44 20	99.48 19	99.31 95	99.64 76	98.10 146	97.68 259	99.84 22	99.29 73	99.92 8	99.57 50	99.60 5	99.96 14	99.74 27	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 159	98.49 171	99.06 142	99.64 76	97.90 173	98.51 134	98.94 307	96.96 312	99.24 155	98.89 242	97.83 144	99.81 223	96.88 255	99.49 288	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	99.12 125	99.64 76	98.54 111	97.98 214	99.68 61	97.62 246	99.34 128	99.18 154	97.54 173	99.77 262	97.79 179	99.74 178	99.04 319

Elysia		99.15 59	99.14 70	99.18 114	99.63 82	97.92 170	98.50 136	99.43 167	99.67 21	99.70 52	99.13 169	96.66 237	99.98 4	99.54 44	99.96 28	99.64 84

StellarMVS		99.15 59	99.14 70	99.18 114	99.63 82	97.92 170	98.50 136	99.43 167	99.67 21	99.70 52	99.13 169	96.66 237	99.98 4	99.54 44	99.96 28	99.64 84

KD-MVS_self_test		99.25 42	99.18 61	99.44 66	99.63 82	99.06 71	98.69 107	99.54 114	99.31 70	99.62 70	99.53 66	97.36 190	99.86 143	99.24 70	99.71 198	99.39 221

EU-MVSNet		97.66 280	98.50 166	95.13 433	99.63 82	85.84 464	98.35 156	98.21 376	98.23 189	99.54 79	99.46 82	95.02 302	99.68 317	98.24 140	99.87 99	99.87 22

HyFIR lowres test		97.19 318	96.60 342	98.96 159	99.62 86	97.28 224	95.17 431	99.50 127	94.21 409	99.01 191	98.32 345	86.61 404	99.99 2	97.10 233	99.84 113	99.60 100

fmvsm_l_conf0.5_n_9		99.32 34	99.43 25	98.98 156	99.59 87	97.18 235	97.44 299	99.83 25	99.56 40	99.91 12	99.34 110	99.36 13	99.93 54	99.83 10	99.98 12	99.85 30

fmvsm_l_conf0.5_n_3		99.45 19	99.48 19	99.34 84	99.59 87	98.21 137	97.82 236	99.84 22	99.41 59	99.92 8	99.41 95	99.51 8	99.95 26	99.84 9	99.97 21	99.87 22

MED-MVS test				99.45 64	99.58 89	98.93 80	98.68 108	99.60 80	96.46 340	99.53 83	98.77 269		99.83 193	96.67 275	99.64 230	99.58 116

MED-MVS		98.90 101	98.72 123	99.45 64	99.58 89	98.93 80	98.68 108	99.60 80	98.14 208	99.53 83	98.77 269	97.87 141	99.83 193	96.67 275	99.64 230	99.58 116

TestfortrainingZip a		98.95 94	98.72 123	99.64 9	99.58 89	99.32 22	98.68 108	99.60 80	96.46 340	99.53 83	98.77 269	97.87 141	99.83 193	98.39 133	99.64 230	99.77 50

FE-MVSNET		98.59 167	98.50 166	98.87 173	99.58 89	97.30 222	98.08 188	99.74 44	96.94 314	98.97 201	99.10 176	96.94 216	99.74 281	97.33 216	99.86 106	99.55 137

mmtdpeth		99.30 35	99.42 26	98.92 168	99.58 89	96.89 256	99.48 13	99.92 7	99.92 2	98.26 304	99.80 11	98.33 90	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 89	99.29 25	97.82 236	99.25 246	96.94 314	98.78 243	99.12 172	98.02 124	99.84 174	97.13 231	99.67 219	99.59 107

nrg030		99.40 27	99.35 35	99.54 32	99.58 89	99.13 61	98.98 76	99.48 136	99.68 20	99.46 102	99.26 131	98.62 60	99.73 288	99.17 75	99.92 69	99.76 56

VDDNet		98.21 227	97.95 248	99.01 150	99.58 89	97.74 192	99.01 71	97.29 405	99.67 21	98.97 201	99.50 70	90.45 379	99.80 232	97.88 172	99.20 337	99.48 180

COLMAP_ROB	96.50 10	98.99 87	98.85 110	99.41 71	99.58 89	99.10 66	98.74 98	99.56 105	99.09 109	99.33 131	99.19 150	98.40 81	99.72 296	95.98 325	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 32	99.45 24	98.99 152	99.57 98	97.73 194	97.93 220	99.83 25	99.22 80	99.93 6	99.30 119	99.42 11	99.96 14	99.85 6	99.99 5	99.29 264

ZNCC-MVS		98.68 150	98.40 184	99.54 32	99.57 98	99.21 34	98.46 144	99.29 233	97.28 287	98.11 316	98.39 335	98.00 126	99.87 134	96.86 258	99.64 230	99.55 137

MSP-MVS		98.40 196	98.00 242	99.61 14	99.57 98	99.25 30	98.57 123	99.35 198	97.55 257	99.31 139	97.71 385	94.61 315	99.88 115	96.14 319	99.19 340	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		98.32 211	98.39 187	98.13 296	99.57 98	95.54 312	97.78 242	99.49 134	97.37 278	99.19 163	97.65 389	98.96 30	99.49 401	96.50 297	98.99 365	99.34 246

MP-MVS		98.46 190	98.09 231	99.54 32	99.57 98	99.22 33	98.50 136	99.19 261	97.61 249	97.58 355	98.66 297	97.40 187	99.88 115	94.72 364	99.60 247	99.54 143
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 98	98.97 74	98.23 166	99.48 136	96.60 332	99.10 173	99.06 184	98.71 51	99.83 193	95.58 345	99.78 152	99.62 90

LGP-MVS_train				99.47 61	99.57 98	98.97 74		99.48 136	96.60 332	99.10 173	99.06 184	98.71 51	99.83 193	95.58 345	99.78 152	99.62 90

IS-MVSNet		98.19 230	97.90 256	99.08 134	99.57 98	97.97 164	99.31 31	98.32 372	99.01 121	98.98 197	99.03 195	91.59 367	99.79 245	95.49 347	99.80 141	99.48 180

viewdifsd2359ckpt11		98.84 112	99.04 82	98.24 285	99.56 106	95.51 314	97.38 304	99.70 53	99.16 94	99.57 72	99.40 98	98.26 98	99.71 297	98.55 125	99.82 124	99.50 162

viewmsd2359difaftdt		98.84 112	99.04 82	98.24 285	99.56 106	95.51 314	97.38 304	99.70 53	99.16 94	99.57 72	99.40 98	98.26 98	99.71 297	98.55 125	99.82 124	99.50 162

dcpmvs_2		98.78 126	99.11 73	97.78 319	99.56 106	93.67 390	99.06 66	99.86 16	99.50 44	99.66 61	99.26 131	97.21 201	99.99 2	98.00 162	99.91 78	99.68 71

test_0402		98.76 130	98.71 128	98.93 165	99.56 106	98.14 142	98.45 146	99.34 204	99.28 74	98.95 207	98.91 233	98.34 89	99.79 245	95.63 342	99.91 78	98.86 351

EPP-MVSNet		98.30 214	98.04 238	99.07 136	99.56 106	97.83 179	99.29 37	98.07 383	99.03 119	98.59 270	99.13 169	92.16 361	99.90 81	96.87 256	99.68 213	99.49 169

ACMMP		98.75 131	98.50 166	99.52 45	99.56 106	99.16 49	98.87 89	99.37 188	97.16 302	98.82 237	99.01 207	97.71 155	99.87 134	96.29 310	99.69 208	99.54 143
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 73	99.20 60	98.78 191	99.55 112	96.59 269	97.79 241	99.82 30	98.21 192	99.81 37	99.53 66	98.46 77	99.84 174	99.70 33	99.97 21	99.90 15

fmvsm_s_conf0.5_n		99.09 74	99.26 52	98.61 228	99.55 112	96.09 292	97.74 252	99.81 31	98.55 167	99.85 27	99.55 58	98.60 62	99.84 174	99.69 35	99.98 12	99.89 16

FMVSNet1		99.17 54	99.17 62	99.17 116	99.55 112	98.24 131	99.20 49	99.44 161	99.21 82	99.43 107	99.55 58	97.82 147	99.86 143	98.42 132	99.89 93	99.41 211

Vis-MVSNet (Re-imp)		97.46 294	97.16 304	98.34 274	99.55 112	96.10 289	98.94 81	98.44 366	98.32 180	98.16 310	98.62 306	88.76 391	99.73 288	93.88 390	99.79 147	99.18 298

ACMM	96.08 12	98.91 99	98.73 121	99.48 57	99.55 112	99.14 58	98.07 192	99.37 188	97.62 246	99.04 187	98.96 223	98.84 37	99.79 245	97.43 211	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 93	97.89 312	99.54 117	94.05 367	98.55 125	99.92 7	96.78 325	99.72 48	99.78 13	96.60 241	99.67 321	99.91 2	99.90 87	99.94 10

mPP-MVS		98.64 157	98.34 195	99.54 32	99.54 117	99.17 45	98.63 115	99.24 251	97.47 265	98.09 318	98.68 292	97.62 164	99.89 97	96.22 313	99.62 240	99.57 124

XVG-ACMP-BASELINE		98.56 171	98.34 195	99.22 110	99.54 117	98.59 105	97.71 255	99.46 149	97.25 290	98.98 197	98.99 213	97.54 173	99.84 174	95.88 328	99.74 178	99.23 280

viewmacassd2359aftdt		98.86 109	98.87 104	98.83 178	99.53 120	97.32 221	97.70 257	99.64 72	98.22 190	99.25 153	99.27 125	98.40 81	99.61 357	97.98 164	99.87 99	99.55 137

region2R		98.69 144	98.40 184	99.54 32	99.53 120	99.17 45	98.52 129	99.31 217	97.46 270	98.44 289	98.51 320	97.83 144	99.88 115	96.46 299	99.58 256	99.58 116

PGM-MVS		98.66 154	98.37 191	99.55 29	99.53 120	99.18 44	98.23 166	99.49 134	97.01 311	98.69 254	98.88 243	98.00 126	99.89 97	95.87 331	99.59 251	99.58 116

Patchmatch-RL test		97.26 311	97.02 312	97.99 308	99.52 123	95.53 313	96.13 391	99.71 48	97.47 265	99.27 145	99.16 160	84.30 425	99.62 350	97.89 169	99.77 158	98.81 359

ACMMPR		98.70 140	98.42 182	99.54 32	99.52 123	99.14 58	98.52 129	99.31 217	97.47 265	98.56 276	98.54 315	97.75 153	99.88 115	96.57 286	99.59 251	99.58 116

fmvsm_s_conf0.5_n_9		99.17 54	99.38 30	98.53 249	99.51 125	95.82 304	97.62 270	99.78 37	99.72 15	99.90 14	99.48 77	98.66 55	99.89 97	99.85 6	99.93 56	99.89 16

AstraMVS		98.16 236	98.07 236	98.41 264	99.51 125	95.86 301	98.00 206	95.14 446	98.97 125	99.43 107	99.24 138	93.25 339	99.84 174	99.21 71	99.87 99	99.54 143

fmvsm_s_conf0.5_n_8		99.13 68	99.26 52	98.74 204	99.51 125	96.44 281	97.65 265	99.65 70	99.66 24	99.78 40	99.48 77	97.92 134	99.93 54	99.72 30	99.95 38	99.87 22

GST-MVS		98.61 163	98.30 202	99.52 45	99.51 125	99.20 40	98.26 164	99.25 246	97.44 273	98.67 257	98.39 335	97.68 156	99.85 156	96.00 323	99.51 278	99.52 155

Anonymous20231206		98.21 227	98.21 215	98.20 290	99.51 125	95.43 323	98.13 178	99.32 212	96.16 353	98.93 215	98.82 259	96.00 268	99.83 193	97.32 217	99.73 181	99.36 239

ACMP	95.32 15	98.41 194	98.09 231	99.36 75	99.51 125	98.79 91	97.68 259	99.38 184	95.76 369	98.81 239	98.82 259	98.36 84	99.82 206	94.75 361	99.77 158	99.48 180
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 202	98.20 216	98.98 156	99.50 131	97.49 206	97.78 242	97.69 392	98.75 145	99.49 96	99.25 136	92.30 359	99.94 42	99.14 76	99.88 95	99.50 162

DVP-MVS		98.77 129	98.52 162	99.52 45	99.50 131	99.21 34	98.02 202	98.84 331	97.97 218	99.08 175	99.02 196	97.61 166	99.88 115	96.99 242	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	98.02 202	99.32 212					99.88 115	96.99 242	99.63 237	99.68 71

test0726					99.50 131	99.21 34	98.17 174	99.35 198	97.97 218	99.26 149	99.06 184	97.61 166

AllTest		98.44 192	98.20 216	99.16 119	99.50 131	98.55 108	98.25 165	99.58 89	96.80 323	98.88 226	99.06 184	97.65 159	99.57 373	94.45 371	99.61 245	99.37 232

TestCases				99.16 119	99.50 131	98.55 108		99.58 89	96.80 323	98.88 226	99.06 184	97.65 159	99.57 373	94.45 371	99.61 245	99.37 232

XVG-OURS		98.53 180	98.34 195	99.11 127	99.50 131	98.82 90	95.97 397	99.50 127	97.30 285	99.05 185	98.98 218	99.35 14	99.32 431	95.72 338	99.68 213	99.18 298

EG-PatchMatch MVS		98.99 87	99.01 87	98.94 162	99.50 131	97.47 210	98.04 197	99.59 87	98.15 207	99.40 116	99.36 105	98.58 68	99.76 268	98.78 104	99.68 213	99.59 107

fmvsm_s_conf0.5_n_2		99.14 64	99.31 43	98.63 223	99.49 139	96.08 294	97.38 304	99.81 31	99.48 45	99.84 30	99.57 50	98.46 77	99.89 97	99.82 12	99.97 21	99.91 13

SED-MVS		98.91 99	98.72 123	99.49 55	99.49 139	99.17 45	98.10 185	99.31 217	98.03 214	99.66 61	99.02 196	98.36 84	99.88 115	96.91 248	99.62 240	99.41 211

IU-MVS					99.49 139	99.15 53		98.87 322	92.97 427	99.41 113				96.76 265	99.62 240	99.66 78

test_241102_ONE					99.49 139	99.17 45		99.31 217	97.98 217	99.66 61	98.90 236	98.36 84	99.48 404

UA-Net		99.47 17	99.40 28	99.70 2	99.49 139	99.29 25	99.80 4	99.72 46	99.82 8	99.04 187	99.81 8	98.05 123	99.96 14	98.85 100	99.99 5	99.86 28

HFP-MVS		98.71 135	98.44 179	99.51 49	99.49 139	99.16 49	98.52 129	99.31 217	97.47 265	98.58 272	98.50 324	97.97 130	99.85 156	96.57 286	99.59 251	99.53 152

VPA-MVSNet		99.30 35	99.30 46	99.28 97	99.49 139	98.36 125	99.00 73	99.45 153	99.63 29	99.52 88	99.44 87	98.25 100	99.88 115	99.09 81	99.84 113	99.62 90

XVG-OURS-SEG-HR		98.49 187	98.28 205	99.14 123	99.49 139	98.83 88	96.54 362	99.48 136	97.32 283	99.11 170	98.61 308	99.33 15	99.30 434	96.23 312	98.38 401	99.28 267

fmvsm_s_conf0.5_n_11		99.21 49	99.34 37	98.80 184	99.48 147	96.56 274	97.97 218	99.69 55	99.63 29	99.84 30	99.54 64	98.21 107	99.94 42	99.76 23	99.95 38	99.88 20

114514_t		96.50 351	95.77 360	98.69 212	99.48 147	97.43 214	97.84 235	99.55 109	81.42 474	96.51 414	98.58 312	95.53 288	99.67 321	93.41 403	99.58 256	98.98 329

IterMVS-LS		98.55 175	98.70 131	98.09 297	99.48 147	94.73 347	97.22 324	99.39 182	98.97 125	99.38 119	99.31 118	96.00 268	99.93 54	98.58 119	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 59	99.27 49	98.78 191	99.47 150	96.56 274	97.75 251	99.71 48	99.60 36	99.74 47	99.44 87	97.96 131	99.95 26	99.86 4	99.94 50	99.82 36

fmvsm_s_conf0.5_n_5		99.07 80	99.10 75	98.99 152	99.47 150	97.22 229	97.40 301	99.83 25	97.61 249	99.85 27	99.30 119	98.80 41	99.95 26	99.71 32	99.90 87	99.78 47

v8		99.01 84	99.16 64	98.57 235	99.47 150	96.31 286	98.90 84	99.47 145	99.03 119	99.52 88	99.57 50	96.93 217	99.81 223	99.60 37	99.98 12	99.60 100

SSC-MVS3.2		98.53 180	98.79 115	97.74 326	99.46 153	93.62 393	96.45 368	99.34 204	99.33 67	98.93 215	98.70 288	97.90 135	99.90 81	99.12 78	99.92 69	99.69 70

fmvsm_s_conf0.5_n_3		99.22 48	99.37 33	98.78 191	99.46 153	96.58 272	97.65 265	99.72 46	99.47 48	99.86 24	99.50 70	98.94 31	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	98.65 113	99.34 204	98.62 156	97.54 359	98.63 304	97.50 179	99.83 193	96.79 261	99.53 273	99.56 130

X-MVStestdata		94.32 400	92.59 419	99.53 39	99.46 153	99.21 34	98.65 113	99.34 204	98.62 156	97.54 359	45.85 479	97.50 179	99.83 193	96.79 261	99.53 273	99.56 130

test20.03		98.78 126	98.77 118	98.78 191	99.46 153	97.20 232	97.78 242	99.24 251	99.04 118	99.41 113	98.90 236	97.65 159	99.76 268	97.70 190	99.79 147	99.39 221

guyue		98.01 248	97.93 252	98.26 281	99.45 158	95.48 318	98.08 188	96.24 429	98.89 136	99.34 128	99.14 167	91.32 371	99.82 206	99.07 82	99.83 120	99.48 180

CSCG		98.68 150	98.50 166	99.20 111	99.45 158	98.63 100	98.56 124	99.57 96	97.87 228	98.85 231	98.04 366	97.66 158	99.84 174	96.72 270	99.81 130	99.13 308

GeoE		99.05 81	98.99 91	99.25 105	99.44 160	98.35 126	98.73 102	99.56 105	98.42 173	98.91 218	98.81 262	98.94 31	99.91 74	98.35 135	99.73 181	99.49 169

v148		98.45 191	98.60 151	98.00 307	99.44 160	94.98 339	97.44 299	99.06 287	98.30 182	99.32 137	98.97 220	96.65 239	99.62 350	98.37 134	99.85 108	99.39 221

v10		98.97 91	99.11 73	98.55 242	99.44 160	96.21 288	98.90 84	99.55 109	98.73 146	99.48 97	99.60 46	96.63 240	99.83 193	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	98.27 163	99.19 261	97.87 228	99.25 153	99.16 160	96.84 221	99.78 256	99.21 71	99.84 113	99.46 190

MDA-MVSNet-bldmvs		97.94 254	97.91 255	98.06 302	99.44 160	94.96 340	96.63 358	99.15 277	98.35 176	98.83 234	99.11 173	94.31 323	99.85 156	96.60 283	98.72 383	99.37 232

viewdifsd2359ckpt07		98.71 135	98.86 108	98.26 281	99.43 165	95.65 308	97.20 325	99.66 66	99.20 84	99.29 141	99.01 207	98.29 93	99.73 288	97.92 168	99.75 177	99.39 221

casdiffmvs_mvg		99.12 71	99.16 64	98.99 152	99.43 165	97.73 194	98.00 206	99.62 76	99.22 80	99.55 77	99.22 144	98.93 33	99.75 276	98.66 115	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		98.90 101	99.01 87	98.57 235	99.42 167	96.59 269	98.13 178	99.66 66	99.09 109	99.30 140	99.02 196	98.79 43	99.89 97	97.87 174	99.80 141	99.23 280

test1111		96.49 352	96.82 326	95.52 426	99.42 167	87.08 461	99.22 46	87.14 477	99.11 99	99.46 102	99.58 48	88.69 392	99.86 143	98.80 102	99.95 38	99.62 90

v2v482		98.56 171	98.62 146	98.37 271	99.42 167	95.81 305	97.58 278	99.16 272	97.90 226	99.28 143	99.01 207	95.98 273	99.79 245	99.33 60	99.90 87	99.51 158

OPM-MVS		98.56 171	98.32 200	99.25 105	99.41 170	98.73 96	97.13 332	99.18 265	97.10 305	98.75 249	98.92 231	98.18 110	99.65 341	96.68 274	99.56 263	99.37 232
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 242	98.08 234	98.04 305	99.41 170	94.59 353	94.59 449	99.40 180	97.50 262	98.82 237	98.83 256	96.83 223	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	99.67 321	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	99.67 321	97.73 188	99.77 158	99.43 203

test_one_0601					99.39 174	99.20 40		99.31 217	98.49 169	98.66 259	99.02 196	97.64 162

mvsany_test3		98.87 106	98.92 97	98.74 204	99.38 175	96.94 253	98.58 122	99.10 282	96.49 337	99.96 4	99.81 8	98.18 110	99.45 412	98.97 91	99.79 147	99.83 33

patch_mono-2		98.51 185	98.63 144	98.17 293	99.38 175	94.78 344	97.36 309	99.69 55	98.16 202	98.49 285	99.29 122	97.06 207	99.97 7	98.29 139	99.91 78	99.76 56

test2506		92.39 431	91.89 433	93.89 447	99.38 175	82.28 478	99.32 27	66.03 485	99.08 113	98.77 246	99.57 50	66.26 472	99.84 174	98.71 112	99.95 38	99.54 143

ECVR-MVS		96.42 354	96.61 340	95.85 418	99.38 175	88.18 456	99.22 46	86.00 479	99.08 113	99.36 124	99.57 50	88.47 397	99.82 206	98.52 127	99.95 38	99.54 143

casdiffmvs		98.95 94	99.00 89	98.81 182	99.38 175	97.33 219	97.82 236	99.57 96	99.17 93	99.35 126	99.17 158	98.35 88	99.69 308	98.46 129	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 93	99.02 85	98.76 198	99.38 175	97.26 226	98.49 139	99.50 127	98.86 139	99.19 163	99.06 184	98.23 102	99.69 308	98.71 112	99.76 173	99.33 252

TranMVSNet+NR-MVSNet		99.17 54	99.07 80	99.46 63	99.37 181	98.87 85	98.39 152	99.42 173	99.42 57	99.36 124	99.06 184	98.38 83	99.95 26	98.34 136	99.90 87	99.57 124

fmvsm_s_conf0.5_n_6		99.08 78	99.21 59	98.69 212	99.36 182	96.51 276	97.62 270	99.68 61	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		95.64 379	94.98 389	97.64 339	99.36 182	93.81 385	98.72 103	90.47 471	98.08 213	98.67 257	98.34 342	73.88 458	99.92 65	97.77 181	99.51 278	99.20 290

test_part2					99.36 182	99.10 66				99.05 185

v1144		98.60 165	98.66 139	98.41 264	99.36 182	95.90 299	97.58 278	99.34 204	97.51 261	99.27 145	99.15 164	96.34 254	99.80 232	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	98.72 103	99.36 192	97.54 259	98.30 298	98.40 334	97.86 143	99.89 97	96.53 295	99.72 189	99.56 130

diffmvs_AUTHOR		98.50 186	98.59 153	98.23 288	99.35 187	95.48 318	96.61 359	99.60 80	98.37 174	98.90 219	99.00 211	97.37 189	99.76 268	98.22 143	99.85 108	99.46 190

Test_1112_low_res		96.99 333	96.55 344	98.31 277	99.35 187	95.47 321	95.84 409	99.53 118	91.51 444	96.80 401	98.48 327	91.36 370	99.83 193	96.58 284	99.53 273	99.62 90

DeepC-MVS	97.60 4	98.97 91	98.93 96	99.10 129	99.35 187	97.98 163	98.01 205	99.46 149	97.56 255	99.54 79	99.50 70	98.97 29	99.84 174	98.06 155	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		97.29 310	96.86 322	98.58 232	99.34 190	96.32 285	96.75 351	99.58 89	93.14 425	96.89 396	97.48 399	92.11 362	99.86 143	96.91 248	99.54 269	99.57 124

reproduce_model		99.15 59	98.97 93	99.67 4	99.33 191	99.44 10	98.15 176	99.47 145	99.12 98	99.52 88	99.32 117	98.31 91	99.90 81	97.78 180	99.73 181	99.66 78

MVSMamba_PlusPlus		98.83 115	98.98 92	98.36 272	99.32 192	96.58 272	98.90 84	99.41 177	99.75 11	98.72 252	99.50 70	96.17 259	99.94 42	99.27 65	99.78 152	98.57 389

fmvsm_s_conf0.5_n_4		99.01 84	99.22 56	98.38 268	99.31 193	95.48 318	97.56 280	99.73 45	98.87 137	99.75 45	99.27 125	98.80 41	99.86 143	99.80 17	99.90 87	99.81 40

SF-MVS		98.53 180	98.27 208	99.32 92	99.31 193	98.75 92	98.19 170	99.41 177	96.77 326	98.83 234	98.90 236	97.80 149	99.82 206	95.68 341	99.52 276	99.38 230

CPTT-MVS		97.84 269	97.36 293	99.27 100	99.31 193	98.46 116	98.29 159	99.27 240	94.90 393	97.83 339	98.37 338	94.90 304	99.84 174	93.85 392	99.54 269	99.51 158

UnsupCasMVSNet_eth		97.89 258	97.60 279	98.75 200	99.31 193	97.17 237	97.62 270	99.35 198	98.72 148	98.76 248	98.68 292	92.57 356	99.74 281	97.76 185	95.60 463	99.34 246

fmvsm_s_conf0.5_n_7		98.83 115	99.04 82	98.20 290	99.30 197	94.83 342	97.23 320	99.36 192	98.64 151	99.84 30	99.43 90	98.10 119	99.91 74	99.56 41	99.96 28	99.87 22

pmmvs-eth3d		98.47 189	98.34 195	98.86 175	99.30 197	97.76 190	97.16 330	99.28 237	95.54 375	99.42 111	99.19 150	97.27 196	99.63 347	97.89 169	99.97 21	99.20 290

mamv4		99.44 20	99.39 29	99.58 21	99.30 197	99.74 2	99.04 69	99.81 31	99.77 10	99.82 34	99.57 50	97.82 147	99.98 4	99.53 48	99.89 93	99.01 323

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	99.66 334	97.52 204	99.67 219	99.36 239

SymmetryMVS		98.05 244	97.71 269	99.09 133	99.29 200	97.83 179	98.28 160	97.64 397	99.24 77	98.80 241	98.85 249	89.76 384	99.94 42	98.04 157	99.50 286	99.49 169

Anonymous20231211		99.27 39	99.27 49	99.26 102	99.29 200	98.18 138	99.49 12	99.51 124	99.70 16	99.80 38	99.68 26	96.84 221	99.83 193	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	99.59 364	97.59 198	99.77 158	99.39 221

UnsupCasMVSNet_bld		97.30 308	96.92 318	98.45 259	99.28 203	96.78 263	96.20 385	99.27 240	95.42 379	98.28 302	98.30 346	93.16 342	99.71 297	94.99 355	97.37 439	98.87 350

EC-MVSNet		99.09 74	99.05 81	99.20 111	99.28 203	98.93 80	99.24 45	99.84 22	99.08 113	98.12 315	98.37 338	98.72 50	99.90 81	99.05 85	99.77 158	98.77 367

mamba_0408		98.80 122	98.88 102	98.55 242	99.27 206	96.50 277	98.00 206	99.60 80	98.93 130	99.22 158	98.84 254	98.59 63	99.89 97	97.74 186	99.72 189	99.27 268

SSM_04072		98.80 122	98.88 102	98.56 240	99.27 206	96.50 277	98.00 206	99.60 80	98.93 130	99.22 158	98.84 254	98.59 63	99.90 81	97.74 186	99.72 189	99.27 268

SSM_0407		98.86 109	98.96 95	98.55 242	99.27 206	96.50 277	98.04 197	99.66 66	99.09 109	99.22 158	99.02 196	98.79 43	99.87 134	97.87 174	99.72 189	99.27 268

reproduce-ours		99.09 74	98.90 99	99.67 4	99.27 206	99.49 6	98.00 206	99.42 173	99.05 116	99.48 97	99.27 125	98.29 93	99.89 97	97.61 195	99.71 198	99.62 90

our_new_method		99.09 74	98.90 99	99.67 4	99.27 206	99.49 6	98.00 206	99.42 173	99.05 116	99.48 97	99.27 125	98.29 93	99.89 97	97.61 195	99.71 198	99.62 90

DPE-MVS		98.59 167	98.26 209	99.57 22	99.27 206	99.15 53	97.01 335	99.39 182	97.67 242	99.44 106	98.99 213	97.53 175	99.89 97	95.40 349	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		97.85 268	98.18 221	96.87 387	99.27 206	91.16 436	95.53 419	99.25 246	99.10 106	99.41 113	99.35 106	93.10 344	99.96 14	98.65 116	99.94 50	99.49 169

v1192		98.60 165	98.66 139	98.41 264	99.27 206	95.88 300	97.52 285	99.36 192	97.41 274	99.33 131	99.20 147	96.37 252	99.82 206	99.57 39	99.92 69	99.55 137

N_pmnet		97.63 282	97.17 303	98.99 152	99.27 206	97.86 176	95.98 396	93.41 460	95.25 384	99.47 101	98.90 236	95.63 285	99.85 156	96.91 248	99.73 181	99.27 268

viewdifsd2359ckpt13		98.39 202	98.29 204	98.70 210	99.26 215	97.19 233	97.51 287	99.48 136	96.94 314	98.58 272	98.82 259	97.47 184	99.55 380	97.21 223	99.33 313	99.34 246

FPMVS		93.44 417	92.23 424	97.08 375	99.25 216	97.86 176	95.61 416	97.16 409	92.90 429	93.76 462	98.65 299	75.94 456	95.66 476	79.30 474	97.49 432	97.73 440

ME-MVS		98.61 163	98.33 199	99.44 66	99.24 217	98.93 80	97.45 297	99.06 287	98.14 208	99.06 177	98.77 269	96.97 215	99.82 206	96.67 275	99.64 230	99.58 116

new-patchmatchnet		98.35 205	98.74 119	97.18 370	99.24 217	92.23 418	96.42 372	99.48 136	98.30 182	99.69 56	99.53 66	97.44 185	99.82 206	98.84 101	99.77 158	99.49 169

MCST-MVS		98.00 249	97.63 277	99.10 129	99.24 217	98.17 139	96.89 344	98.73 350	95.66 370	97.92 330	97.70 387	97.17 202	99.66 334	96.18 317	99.23 332	99.47 188

UniMVSNet (Re)		98.87 106	98.71 128	99.35 81	99.24 217	98.73 96	97.73 254	99.38 184	98.93 130	99.12 169	98.73 278	96.77 229	99.86 143	98.63 118	99.80 141	99.46 190

jason		97.45 296	97.35 294	97.76 323	99.24 217	93.93 379	95.86 406	98.42 368	94.24 408	98.50 284	98.13 356	94.82 308	99.91 74	97.22 222	99.73 181	99.43 203
jason: jason.
IterMVS		97.73 274	98.11 230	96.57 397	99.24 217	90.28 445	95.52 421	99.21 255	98.86 139	99.33 131	99.33 113	93.11 343	99.94 42	98.49 128	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	98.32 275	99.22 223	95.58 311	97.51 287	99.45 153	97.16 302	99.45 105	99.24 138	96.12 263	99.85 156	99.60 37	99.88 95	99.55 137

ITE_SJBPF				98.87 173	99.22 223	98.48 115		99.35 198	97.50 262	98.28 302	98.60 310	97.64 162	99.35 427	93.86 391	99.27 324	98.79 365

h-mvs33		97.77 272	97.33 296	99.10 129	99.21 225	97.84 178	98.35 156	98.57 360	99.11 99	98.58 272	99.02 196	88.65 395	99.96 14	98.11 150	96.34 455	99.49 169

v144192		98.54 178	98.57 155	98.45 259	99.21 225	95.98 297	97.63 269	99.36 192	97.15 304	99.32 137	99.18 154	95.84 280	99.84 174	99.50 51	99.91 78	99.54 143

APDe-MVS		98.99 87	98.79 115	99.60 16	99.21 225	99.15 53	98.87 89	99.48 136	97.57 253	99.35 126	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 97	98.81 114	99.28 97	99.21 225	98.45 117	98.46 144	99.33 210	99.63 29	99.48 97	99.15 164	97.23 199	99.75 276	97.17 225	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	98.48 142	99.30 225	98.64 151	98.95 207	98.96 223	97.49 182	99.86 143	96.56 290	99.39 304	99.45 195

RE-MVS-def			98.58 154		99.20 229	99.38 13	98.48 142	99.30 225	98.64 151	98.95 207	98.96 223	97.75 153		96.56 290	99.39 304	99.45 195

v1921920		98.54 178	98.60 151	98.38 268	99.20 229	95.76 307	97.56 280	99.36 192	97.23 296	99.38 119	99.17 158	96.02 266	99.84 174	99.57 39	99.90 87	99.54 143

thisisatest0530		95.27 386	94.45 397	97.74 326	99.19 232	94.37 357	97.86 232	90.20 472	97.17 301	98.22 305	97.65 389	73.53 459	99.90 81	96.90 253	99.35 310	98.95 335

Anonymous20240529		98.93 97	98.87 104	99.12 125	99.19 232	98.22 136	99.01 71	98.99 305	99.25 76	99.54 79	99.37 101	97.04 208	99.80 232	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	98.49 139	99.33 210	98.64 151	99.03 190	98.98 218	97.89 139	99.85 156	96.54 294	99.42 301	99.46 190

HQP_MVS		97.99 252	97.67 271	98.93 165	99.19 232	97.65 198	97.77 245	99.27 240	98.20 196	97.79 342	97.98 370	94.90 304	99.70 304	94.42 373	99.51 278	99.45 195

plane_prior7					99.19 232	97.87 175

ab-mvs		98.41 194	98.36 192	98.59 231	99.19 232	97.23 227	99.32 27	98.81 336	97.66 243	98.62 264	99.40 98	96.82 224	99.80 232	95.88 328	99.51 278	98.75 370

F-COLMAP		97.30 308	96.68 335	99.14 123	99.19 232	98.39 119	97.27 319	99.30 225	92.93 428	96.62 407	98.00 368	95.73 283	99.68 317	92.62 419	98.46 400	99.35 244

viewdifsd2359ckpt09		98.13 237	97.92 253	98.77 196	99.18 239	97.35 217	97.29 315	99.53 118	95.81 367	98.09 318	98.47 328	96.34 254	99.66 334	97.02 238	99.51 278	99.29 264

SR-MVS		98.71 135	98.43 180	99.57 22	99.18 239	99.35 17	98.36 155	99.29 233	98.29 185	98.88 226	98.85 249	97.53 175	99.87 134	96.14 319	99.31 317	99.48 180

UniMVSNet_NR-MVSNet		98.86 109	98.68 134	99.40 73	99.17 241	98.74 93	97.68 259	99.40 180	99.14 97	99.06 177	98.59 311	96.71 235	99.93 54	98.57 121	99.77 158	99.53 152

LF4IMVS		97.90 256	97.69 270	98.52 250	99.17 241	97.66 197	97.19 329	99.47 145	96.31 347	97.85 338	98.20 353	96.71 235	99.52 392	94.62 365	99.72 189	98.38 406

SMA-MVS		98.40 196	98.03 239	99.51 49	99.16 243	99.21 34	98.05 195	99.22 254	94.16 410	98.98 197	99.10 176	97.52 177	99.79 245	96.45 300	99.64 230	99.53 152
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 74	99.16 243	98.74 93	97.54 283	99.25 246	98.84 143	99.06 177	98.76 275	96.76 231	99.93 54	98.57 121	99.77 158	99.50 162

NR-MVSNet		98.95 94	98.82 112	99.36 75	99.16 243	98.72 98	99.22 46	99.20 257	99.10 106	99.72 48	98.76 275	96.38 251	99.86 143	98.00 162	99.82 124	99.50 162

MVS_111021_LR		98.30 214	98.12 229	98.83 178	99.16 243	98.03 158	96.09 393	99.30 225	97.58 252	98.10 317	98.24 349	98.25 100	99.34 428	96.69 273	99.65 228	99.12 309

DSMNet-mixed		97.42 299	97.60 279	96.87 387	99.15 247	91.46 425	98.54 127	99.12 279	92.87 430	97.58 355	99.63 40	96.21 258	99.90 81	95.74 337	99.54 269	99.27 268

D2MVS		97.84 269	97.84 260	97.83 315	99.14 248	94.74 346	96.94 339	98.88 320	95.84 366	98.89 222	98.96 223	94.40 320	99.69 308	97.55 199	99.95 38	99.05 315

pmmvs5		97.64 281	97.49 285	98.08 300	99.14 248	95.12 335	96.70 354	99.05 291	93.77 417	98.62 264	98.83 256	93.23 340	99.75 276	98.33 138	99.76 173	99.36 239

SPE-MVS-test		99.13 68	99.09 77	99.26 102	99.13 250	98.97 74	99.31 31	99.88 14	99.44 54	98.16 310	98.51 320	98.64 57	99.93 54	98.91 95	99.85 108	98.88 349

VDD-MVS		98.56 171	98.39 187	99.07 136	99.13 250	98.07 153	98.59 121	97.01 412	99.59 37	99.11 170	99.27 125	94.82 308	99.79 245	98.34 136	99.63 237	99.34 246

save fliter					99.11 252	97.97 164	96.53 364	99.02 299	98.24 188

APD-MVS		98.10 238	97.67 271	99.42 69	99.11 252	98.93 80	97.76 248	99.28 237	94.97 391	98.72 252	98.77 269	97.04 208	99.85 156	93.79 393	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	99.10 254	96.37 283	97.23 320	98.87 322	99.20 84	99.19 163	98.99 213	97.30 193	99.85 156	98.77 107	99.79 147	99.65 83

EI-MVSNet		98.40 196	98.51 163	98.04 305	99.10 254	94.73 347	97.20 325	98.87 322	98.97 125	99.06 177	99.02 196	96.00 268	99.80 232	98.58 119	99.82 124	99.60 100

CVMVSNet		96.25 360	97.21 302	93.38 454	99.10 254	80.56 482	97.20 325	98.19 379	96.94 314	99.00 192	99.02 196	89.50 388	99.80 232	96.36 306	99.59 251	99.78 47

EI-MVSNet-Vis-set		98.68 150	98.70 131	98.63 223	99.09 257	96.40 282	97.23 320	98.86 327	99.20 84	99.18 167	98.97 220	97.29 195	99.85 156	98.72 111	99.78 152	99.64 84

HPM-MVS++		98.10 238	97.64 276	99.48 57	99.09 257	99.13 61	97.52 285	98.75 347	97.46 270	96.90 395	97.83 380	96.01 267	99.84 174	95.82 335	99.35 310	99.46 190

DP-MVS Recon		97.33 306	96.92 318	98.57 235	99.09 257	97.99 160	96.79 347	99.35 198	93.18 424	97.71 346	98.07 364	95.00 303	99.31 432	93.97 386	99.13 348	98.42 403

MVS_111021_HR		98.25 223	98.08 234	98.75 200	99.09 257	97.46 211	95.97 397	99.27 240	97.60 251	97.99 328	98.25 348	98.15 116	99.38 423	96.87 256	99.57 260	99.42 208

BP-MVS1		97.40 301	96.97 314	98.71 209	99.07 261	96.81 259	98.34 158	97.18 407	98.58 162	98.17 307	98.61 308	84.01 427	99.94 42	98.97 91	99.78 152	99.37 232

9.14			97.78 262		99.07 261		97.53 284	99.32 212	95.53 376	98.54 280	98.70 288	97.58 168	99.76 268	94.32 378	99.46 291

PAPM_NR		96.82 340	96.32 351	98.30 278	99.07 261	96.69 267	97.48 291	98.76 344	95.81 367	96.61 408	96.47 425	94.12 329	99.17 445	90.82 446	97.78 426	99.06 314

TAMVS		98.24 224	98.05 237	98.80 184	99.07 261	97.18 235	97.88 228	98.81 336	96.66 331	99.17 168	99.21 145	94.81 310	99.77 262	96.96 246	99.88 95	99.44 199

CLD-MVS		97.49 292	97.16 304	98.48 256	99.07 261	97.03 246	94.71 442	99.21 255	94.46 402	98.06 321	97.16 411	97.57 169	99.48 404	94.46 370	99.78 152	98.95 335
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 68	99.10 75	99.24 107	99.06 266	99.15 53	99.36 22	99.88 14	99.36 65	98.21 306	98.46 329	98.68 54	99.93 54	99.03 87	99.85 108	98.64 382

thres100view900		94.19 403	93.67 408	95.75 421	99.06 266	91.35 429	98.03 199	94.24 455	98.33 178	97.40 371	94.98 455	79.84 443	99.62 350	83.05 467	98.08 417	96.29 462

thres600view7		94.45 398	93.83 405	96.29 405	99.06 266	91.53 424	97.99 213	94.24 455	98.34 177	97.44 369	95.01 453	79.84 443	99.67 321	84.33 465	98.23 406	97.66 443

plane_prior1					99.05 269

YYNet1		97.60 283	97.67 271	97.39 363	99.04 270	93.04 402	95.27 428	98.38 371	97.25 290	98.92 217	98.95 227	95.48 292	99.73 288	96.99 242	98.74 381	99.41 211

MDA-MVSNet_test_wron		97.60 283	97.66 274	97.41 362	99.04 270	93.09 398	95.27 428	98.42 368	97.26 289	98.88 226	98.95 227	95.43 293	99.73 288	97.02 238	98.72 383	99.41 211

MIMVSNet		96.62 347	96.25 355	97.71 330	99.04 270	94.66 350	99.16 55	96.92 418	97.23 296	97.87 335	99.10 176	86.11 410	99.65 341	91.65 430	99.21 336	98.82 354

icg_test_0407_2		98.20 229	98.38 189	97.65 336	99.03 273	94.03 370	95.78 411	99.45 153	98.16 202	99.06 177	98.71 281	98.27 96	99.68 317	97.50 205	99.45 293	99.22 285

IMVS_0407		98.39 202	98.64 142	97.66 334	99.03 273	94.03 370	98.10 185	99.45 153	98.16 202	99.06 177	98.71 281	98.27 96	99.71 297	97.50 205	99.45 293	99.22 285

IMVS_0404		98.07 242	98.20 216	97.69 331	99.03 273	94.03 370	96.67 355	99.45 153	98.16 202	98.03 325	98.71 281	96.80 227	99.82 206	97.50 205	99.45 293	99.22 285

IMVS_0403		98.34 206	98.56 156	97.66 334	99.03 273	94.03 370	97.98 214	99.45 153	98.16 202	98.89 222	98.71 281	97.90 135	99.74 281	97.50 205	99.45 293	99.22 285

PatchMatch-RL		97.24 314	96.78 329	98.61 228	99.03 273	97.83 179	96.36 375	99.06 287	93.49 422	97.36 375	97.78 381	95.75 282	99.49 401	93.44 402	98.77 380	98.52 391

viewmambaseed2359dif		98.19 230	98.26 209	97.99 308	99.02 278	95.03 338	96.59 361	99.53 118	96.21 350	99.00 192	98.99 213	97.62 164	99.61 357	97.62 194	99.72 189	99.33 252

GDP-MVS		97.50 289	97.11 308	98.67 215	99.02 278	96.85 257	98.16 175	99.71 48	98.32 180	98.52 283	98.54 315	83.39 431	99.95 26	98.79 103	99.56 263	99.19 295

ZD-MVS					99.01 280	98.84 87		99.07 286	94.10 412	98.05 323	98.12 358	96.36 253	99.86 143	92.70 418	99.19 340

CDPH-MVS		97.26 311	96.66 338	99.07 136	99.00 281	98.15 140	96.03 395	99.01 302	91.21 448	97.79 342	97.85 379	96.89 219	99.69 308	92.75 416	99.38 307	99.39 221

diffmvs		98.22 225	98.24 213	98.17 293	99.00 281	95.44 322	96.38 374	99.58 89	97.79 235	98.53 281	98.50 324	96.76 231	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		98.40 196	98.19 220	99.03 146	99.00 281	97.65 198	96.85 345	98.94 307	98.57 163	98.89 222	98.50 324	95.60 286	99.85 156	97.54 201	99.85 108	99.59 107

plane_prior6					98.99 284	97.70 196						94.90 304

xiu_mvs_v1_base_debu		97.86 263	98.17 222	96.92 384	98.98 285	93.91 380	96.45 368	99.17 269	97.85 230	98.41 292	97.14 413	98.47 73	99.92 65	98.02 159	99.05 354	96.92 455

xiu_mvs_v1_base		97.86 263	98.17 222	96.92 384	98.98 285	93.91 380	96.45 368	99.17 269	97.85 230	98.41 292	97.14 413	98.47 73	99.92 65	98.02 159	99.05 354	96.92 455

xiu_mvs_v1_base_debi		97.86 263	98.17 222	96.92 384	98.98 285	93.91 380	96.45 368	99.17 269	97.85 230	98.41 292	97.14 413	98.47 73	99.92 65	98.02 159	99.05 354	96.92 455

MVP-Stereo		98.08 241	97.92 253	98.57 235	98.96 288	96.79 260	97.90 226	99.18 265	96.41 343	98.46 287	98.95 227	95.93 277	99.60 360	96.51 296	98.98 368	99.31 259
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 196	98.68 134	97.54 351	98.96 288	97.99 160	97.88 228	99.36 192	98.20 196	99.63 67	99.04 193	98.76 46	95.33 478	96.56 290	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				98.91 169	98.94 290	97.76 190		98.76 344	87.58 465	96.75 403	98.10 360	94.80 311	99.78 256	92.73 417	99.00 363	99.20 290

USDC		97.41 300	97.40 289	97.44 360	98.94 290	93.67 390	95.17 431	99.53 118	94.03 414	98.97 201	99.10 176	95.29 295	99.34 428	95.84 334	99.73 181	99.30 262

tfpn200view9		94.03 407	93.44 410	95.78 420	98.93 292	91.44 427	97.60 275	94.29 453	97.94 222	97.10 381	94.31 462	79.67 445	99.62 350	83.05 467	98.08 417	96.29 462

testdata				98.09 297	98.93 292	95.40 324		98.80 338	90.08 456	97.45 368	98.37 338	95.26 296	99.70 304	93.58 398	98.95 371	99.17 302

thres400		94.14 405	93.44 410	96.24 408	98.93 292	91.44 427	97.60 275	94.29 453	97.94 222	97.10 381	94.31 462	79.67 445	99.62 350	83.05 467	98.08 417	97.66 443

TAPA-MVS	96.21 11	96.63 346	95.95 357	98.65 217	98.93 292	98.09 147	96.93 341	99.28 237	83.58 471	98.13 314	97.78 381	96.13 261	99.40 419	93.52 399	99.29 322	98.45 396
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 296	96.93 254	95.54 418	98.78 341	85.72 468	96.86 398	98.11 359	94.43 318			99.10 353	99.23 280

PVSNet_BlendedMVS		97.55 288	97.53 282	97.60 343	98.92 296	93.77 387	96.64 357	99.43 167	94.49 400	97.62 351	99.18 154	96.82 224	99.67 321	94.73 362	99.93 56	99.36 239

PVSNet_Blended		96.88 336	96.68 335	97.47 358	98.92 296	93.77 387	94.71 442	99.43 167	90.98 450	97.62 351	97.36 407	96.82 224	99.67 321	94.73 362	99.56 263	98.98 329

MSDG		97.71 276	97.52 283	98.28 280	98.91 299	96.82 258	94.42 452	99.37 188	97.65 244	98.37 297	98.29 347	97.40 187	99.33 430	94.09 384	99.22 333	98.68 380

Anonymous202405211		97.90 256	97.50 284	99.08 134	98.90 300	98.25 130	98.53 128	96.16 430	98.87 137	99.11 170	98.86 246	90.40 380	99.78 256	97.36 214	99.31 317	99.19 295

原ACMM1				98.35 273	98.90 300	96.25 287		98.83 335	92.48 434	96.07 425	98.10 360	95.39 294	99.71 297	92.61 420	98.99 365	99.08 311

GBi-Net		98.65 155	98.47 174	99.17 116	98.90 300	98.24 131	99.20 49	99.44 161	98.59 159	98.95 207	99.55 58	94.14 326	99.86 143	97.77 181	99.69 208	99.41 211

test1		98.65 155	98.47 174	99.17 116	98.90 300	98.24 131	99.20 49	99.44 161	98.59 159	98.95 207	99.55 58	94.14 326	99.86 143	97.77 181	99.69 208	99.41 211

FMVSNet2		98.49 187	98.40 184	98.75 200	98.90 300	97.14 240	98.61 119	99.13 278	98.59 159	99.19 163	99.28 123	94.14 326	99.82 206	97.97 165	99.80 141	99.29 264

OMC-MVS		97.88 260	97.49 285	99.04 145	98.89 305	98.63 100	96.94 339	99.25 246	95.02 389	98.53 281	98.51 320	97.27 196	99.47 407	93.50 401	99.51 278	99.01 323

VortexMVS		97.98 253	98.31 201	97.02 378	98.88 306	91.45 426	98.03 199	99.47 145	98.65 150	99.55 77	99.47 80	91.49 369	99.81 223	99.32 61	99.91 78	99.80 42

MVSFormer		98.26 220	98.43 180	97.77 320	98.88 306	93.89 383	99.39 20	99.56 105	99.11 99	98.16 310	98.13 356	93.81 334	99.97 7	99.26 66	99.57 260	99.43 203

lupinMVS		97.06 326	96.86 322	97.65 336	98.88 306	93.89 383	95.48 422	97.97 385	93.53 420	98.16 310	97.58 393	93.81 334	99.91 74	96.77 264	99.57 260	99.17 302

dmvs_re		95.98 368	95.39 378	97.74 326	98.86 309	97.45 212	98.37 154	95.69 442	97.95 220	96.56 409	95.95 434	90.70 377	97.68 472	88.32 455	96.13 459	98.11 418

DELS-MVS		98.27 218	98.20 216	98.48 256	98.86 309	96.70 266	95.60 417	99.20 257	97.73 238	98.45 288	98.71 281	97.50 179	99.82 206	98.21 144	99.59 251	98.93 340
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		97.89 258	97.98 244	97.60 343	98.86 309	94.35 358	96.21 384	99.44 161	97.45 272	99.06 177	98.88 243	97.99 129	99.28 438	94.38 377	99.58 256	99.18 298

LCM-MVSNet-Re		98.64 157	98.48 172	99.11 127	98.85 312	98.51 113	98.49 139	99.83 25	98.37 174	99.69 56	99.46 82	98.21 107	99.92 65	94.13 383	99.30 320	98.91 344

pmmvs4		97.58 286	97.28 297	98.51 251	98.84 313	96.93 254	95.40 426	98.52 363	93.60 419	98.61 266	98.65 299	95.10 300	99.60 360	96.97 245	99.79 147	98.99 328

NP-MVS					98.84 313	97.39 216					96.84 416

sss		97.21 316	96.93 316	98.06 302	98.83 315	95.22 331	96.75 351	98.48 365	94.49 400	97.27 377	97.90 376	92.77 352	99.80 232	96.57 286	99.32 315	99.16 305

PVSNet	93.40 17	95.67 377	95.70 363	95.57 425	98.83 315	88.57 452	92.50 469	97.72 390	92.69 432	96.49 417	96.44 426	93.72 337	99.43 415	93.61 396	99.28 323	98.71 373

MVE	83.40 22	92.50 430	91.92 432	94.25 441	98.83 315	91.64 423	92.71 468	83.52 481	95.92 364	86.46 479	95.46 447	95.20 297	95.40 477	80.51 472	98.64 392	95.73 470
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 411	93.91 403	93.39 453	98.82 318	81.72 480	97.76 248	95.28 444	98.60 158	96.54 410	96.66 420	65.85 475	99.62 350	96.65 279	98.99 365	98.82 354

ambc				98.24 285	98.82 318	95.97 298	98.62 117	99.00 304		99.27 145	99.21 145	96.99 213	99.50 398	96.55 293	99.50 286	99.26 274

旧先验1					98.82 318	97.45 212		98.76 344			98.34 342	95.50 291			99.01 362	99.23 280

test_vis1_rt		97.75 273	97.72 268	97.83 315	98.81 321	96.35 284	97.30 314	99.69 55	94.61 398	97.87 335	98.05 365	96.26 257	98.32 466	98.74 109	98.18 409	98.82 354

WTY-MVS		96.67 344	96.27 354	97.87 313	98.81 321	94.61 352	96.77 349	97.92 387	94.94 392	97.12 380	97.74 384	91.11 373	99.82 206	93.89 389	98.15 413	99.18 298

3Dnovator+	97.89 3	98.69 144	98.51 163	99.24 107	98.81 321	98.40 118	99.02 70	99.19 261	98.99 122	98.07 320	99.28 123	97.11 206	99.84 174	96.84 259	99.32 315	99.47 188

QAPM		97.31 307	96.81 328	98.82 180	98.80 324	97.49 206	99.06 66	99.19 261	90.22 454	97.69 348	99.16 160	96.91 218	99.90 81	90.89 445	99.41 302	99.07 313

VNet		98.42 193	98.30 202	98.79 188	98.79 325	97.29 223	98.23 166	98.66 354	99.31 70	98.85 231	98.80 263	94.80 311	99.78 256	98.13 149	99.13 348	99.31 259

DPM-MVS		96.32 356	95.59 369	98.51 251	98.76 326	97.21 231	94.54 451	98.26 374	91.94 439	96.37 418	97.25 409	93.06 346	99.43 415	91.42 435	98.74 381	98.89 346

3Dnovator	98.27 2	98.81 120	98.73 121	99.05 143	98.76 326	97.81 187	99.25 44	99.30 225	98.57 163	98.55 278	99.33 113	97.95 132	99.90 81	97.16 226	99.67 219	99.44 199

PLC	94.65 16	96.51 349	95.73 362	98.85 176	98.75 328	97.91 172	96.42 372	99.06 287	90.94 451	95.59 431	97.38 405	94.41 319	99.59 364	90.93 443	98.04 422	99.05 315
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 338	96.75 331	97.08 375	98.74 329	93.33 396	96.71 353	98.26 374	96.72 328	98.44 289	97.37 406	95.20 297	99.47 407	91.89 425	97.43 436	98.44 399

hse-mvs2		97.46 294	97.07 309	98.64 219	98.73 330	97.33 219	97.45 297	97.64 397	99.11 99	98.58 272	97.98 370	88.65 395	99.79 245	98.11 150	97.39 438	98.81 359

CDS-MVSNet		97.69 277	97.35 294	98.69 212	98.73 330	97.02 247	96.92 343	98.75 347	95.89 365	98.59 270	98.67 294	92.08 363	99.74 281	96.72 270	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		96.28 358	95.83 359	97.64 339	98.72 332	94.30 359	98.87 89	98.77 342	97.80 233	96.53 411	98.02 367	97.34 191	99.47 407	76.93 476	99.48 289	99.16 305

EIA-MVS		98.00 249	97.74 265	98.80 184	98.72 332	98.09 147	98.05 195	99.60 80	97.39 276	96.63 406	95.55 442	97.68 156	99.80 232	96.73 269	99.27 324	98.52 391

LFMVS		97.20 317	96.72 332	98.64 219	98.72 332	96.95 252	98.93 82	94.14 457	99.74 13	98.78 243	99.01 207	84.45 422	99.73 288	97.44 210	99.27 324	99.25 275

new_pmnet		96.99 333	96.76 330	97.67 332	98.72 332	94.89 341	95.95 401	98.20 377	92.62 433	98.55 278	98.54 315	94.88 307	99.52 392	93.96 387	99.44 300	98.59 388

Fast-Effi-MVS+		97.67 279	97.38 291	98.57 235	98.71 336	97.43 214	97.23 320	99.45 153	94.82 395	96.13 422	96.51 422	98.52 71	99.91 74	96.19 315	98.83 377	98.37 408

TEST9					98.71 336	98.08 151	95.96 399	99.03 296	91.40 445	95.85 428	97.53 395	96.52 244	99.76 268

train_agg		97.10 323	96.45 348	99.07 136	98.71 336	98.08 151	95.96 399	99.03 296	91.64 440	95.85 428	97.53 395	96.47 246	99.76 268	93.67 395	99.16 343	99.36 239

TSAR-MVS + GP.		98.18 232	97.98 244	98.77 196	98.71 336	97.88 174	96.32 378	98.66 354	96.33 345	99.23 157	98.51 320	97.48 183	99.40 419	97.16 226	99.46 291	99.02 322

FA-MVS(test-final)		96.99 333	96.82 326	97.50 355	98.70 340	94.78 344	99.34 23	96.99 413	95.07 388	98.48 286	99.33 113	88.41 398	99.65 341	96.13 321	98.92 374	98.07 421

AUN-MVS		96.24 362	95.45 374	98.60 230	98.70 340	97.22 229	97.38 304	97.65 395	95.95 363	95.53 438	97.96 374	82.11 439	99.79 245	96.31 308	97.44 435	98.80 364

our_test_3		97.39 302	97.73 267	96.34 403	98.70 340	89.78 448	94.61 448	98.97 306	96.50 336	99.04 187	98.85 249	95.98 273	99.84 174	97.26 220	99.67 219	99.41 211

ppachtmachnet_test		97.50 289	97.74 265	96.78 393	98.70 340	91.23 435	94.55 450	99.05 291	96.36 344	99.21 161	98.79 265	96.39 249	99.78 256	96.74 267	99.82 124	99.34 246

PCF-MVS	92.86 18	94.36 399	93.00 417	98.42 263	98.70 340	97.56 203	93.16 467	99.11 281	79.59 475	97.55 358	97.43 402	92.19 360	99.73 288	79.85 473	99.45 293	97.97 427
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 255	98.02 240	97.58 345	98.69 345	94.10 366	98.13 178	98.90 316	97.95 220	97.32 376	99.58 48	95.95 276	98.75 461	96.41 302	99.22 333	99.87 22

ETV-MVS		98.03 245	97.86 259	98.56 240	98.69 345	98.07 153	97.51 287	99.50 127	98.10 210	97.50 363	95.51 443	98.41 80	99.88 115	96.27 311	99.24 329	97.71 442

test_prior				98.95 161	98.69 345	97.95 168		99.03 296					99.59 364			99.30 262

mvsmamba		97.57 287	97.26 298	98.51 251	98.69 345	96.73 265	98.74 98	97.25 406	97.03 310	97.88 334	99.23 143	90.95 374	99.87 134	96.61 282	99.00 363	98.91 344

agg_prior					98.68 349	97.99 160		99.01 302		95.59 431			99.77 262

test_8					98.67 350	98.01 159	95.91 405	99.02 299	91.64 440	95.79 430	97.50 398	96.47 246	99.76 268

HQP-NCC					98.67 350		96.29 380		96.05 356	95.55 434

ACMP_Plane					98.67 350		96.29 380		96.05 356	95.55 434

CNVR-MVS		98.17 234	97.87 258	99.07 136	98.67 350	98.24 131	97.01 335	98.93 310	97.25 290	97.62 351	98.34 342	97.27 196	99.57 373	96.42 301	99.33 313	99.39 221

HQP-MVS		97.00 332	96.49 347	98.55 242	98.67 350	96.79 260	96.29 380	99.04 294	96.05 356	95.55 434	96.84 416	93.84 332	99.54 386	92.82 413	99.26 327	99.32 255

MM		98.22 225	97.99 243	98.91 169	98.66 355	96.97 249	97.89 227	94.44 451	99.54 41	98.95 207	99.14 167	93.50 338	99.92 65	99.80 17	99.96 28	99.85 30

test_fmvs1		97.72 275	97.94 250	97.07 377	98.66 355	92.39 413	97.68 259	99.81 31	95.20 387	99.54 79	99.44 87	91.56 368	99.41 418	99.78 21	99.77 158	99.40 220

balanced_conf03		98.63 159	98.72 123	98.38 268	98.66 355	96.68 268	98.90 84	99.42 173	98.99 122	98.97 201	99.19 150	95.81 281	99.85 156	98.77 107	99.77 158	98.60 385

thres200		93.72 413	93.14 415	95.46 429	98.66 355	91.29 431	96.61 359	94.63 450	97.39 276	96.83 399	93.71 465	79.88 442	99.56 376	82.40 470	98.13 414	95.54 471

wuyk23d		96.06 364	97.62 278	91.38 458	98.65 359	98.57 107	98.85 93	96.95 416	96.86 321	99.90 14	99.16 160	99.18 19	98.40 465	89.23 453	99.77 158	77.18 478

NCCC		97.86 263	97.47 288	99.05 143	98.61 360	98.07 153	96.98 337	98.90 316	97.63 245	97.04 385	97.93 375	95.99 272	99.66 334	95.31 350	98.82 379	99.43 203

DeepC-MVS_fast	96.85 6	98.30 214	98.15 226	98.75 200	98.61 360	97.23 227	97.76 248	99.09 284	97.31 284	98.75 249	98.66 297	97.56 170	99.64 344	96.10 322	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		93.51 415	92.09 426	97.75 324	98.60 362	94.40 356	97.32 312	95.26 445	97.56 255	96.79 402	95.50 444	53.57 483	99.77 262	95.26 351	98.97 369	99.08 311

thisisatest0515		94.12 406	93.16 414	96.97 382	98.60 362	92.90 403	93.77 463	90.61 470	94.10 412	96.91 392	95.87 437	74.99 457	99.80 232	94.52 368	99.12 351	98.20 414

GA-MVS		95.86 371	95.32 381	97.49 356	98.60 362	94.15 365	93.83 462	97.93 386	95.49 377	96.68 404	97.42 403	83.21 432	99.30 434	96.22 313	98.55 398	99.01 323

dmvs_testset		92.94 425	92.21 425	95.13 433	98.59 365	90.99 438	97.65 265	92.09 466	96.95 313	94.00 458	93.55 466	92.34 358	96.97 475	72.20 477	92.52 473	97.43 450

OPU-MVS				98.82 180	98.59 365	98.30 127	98.10 185				98.52 319	98.18 110	98.75 461	94.62 365	99.48 289	99.41 211

MSLP-MVS++		98.02 246	98.14 228	97.64 339	98.58 367	95.19 332	97.48 291	99.23 253	97.47 265	97.90 332	98.62 306	97.04 208	98.81 459	97.55 199	99.41 302	98.94 339

test12				98.93 165	98.58 367	97.83 179		98.66 354		96.53 411		95.51 290	99.69 308		99.13 348	99.27 268

CL-MVSNet_self_test		97.44 297	97.22 301	98.08 300	98.57 369	95.78 306	94.30 455	98.79 339	96.58 334	98.60 268	98.19 354	94.74 314	99.64 344	96.41 302	98.84 376	98.82 354

PS-MVSNAJ		97.08 325	97.39 290	96.16 414	98.56 370	92.46 411	95.24 430	98.85 330	97.25 290	97.49 364	95.99 433	98.07 120	99.90 81	96.37 304	98.67 391	96.12 467

CNLPA		97.17 320	96.71 333	98.55 242	98.56 370	98.05 157	96.33 377	98.93 310	96.91 318	97.06 384	97.39 404	94.38 321	99.45 412	91.66 429	99.18 342	98.14 417

xiu_mvs_v2_base		97.16 321	97.49 285	96.17 412	98.54 372	92.46 411	95.45 423	98.84 331	97.25 290	97.48 365	96.49 423	98.31 91	99.90 81	96.34 307	98.68 390	96.15 466

alignmvs		97.35 304	96.88 321	98.78 191	98.54 372	98.09 147	97.71 255	97.69 392	99.20 84	97.59 354	95.90 436	88.12 400	99.55 380	98.18 146	98.96 370	98.70 376

FE-MVS		95.66 378	94.95 391	97.77 320	98.53 374	95.28 328	99.40 19	96.09 433	93.11 426	97.96 329	99.26 131	79.10 449	99.77 262	92.40 422	98.71 385	98.27 412

Effi-MVS+		98.02 246	97.82 261	98.62 225	98.53 374	97.19 233	97.33 311	99.68 61	97.30 285	96.68 404	97.46 401	98.56 69	99.80 232	96.63 280	98.20 408	98.86 351

baseline1		95.96 369	95.44 375	97.52 353	98.51 376	93.99 377	98.39 152	96.09 433	98.21 192	98.40 296	97.76 383	86.88 402	99.63 347	95.42 348	89.27 476	98.95 335

MVS_Test		98.18 232	98.36 192	97.67 332	98.48 377	94.73 347	98.18 171	99.02 299	97.69 241	98.04 324	99.11 173	97.22 200	99.56 376	98.57 121	98.90 375	98.71 373

MGCFI-Net		98.34 206	98.28 205	98.51 251	98.47 378	97.59 202	98.96 78	99.48 136	99.18 92	97.40 371	95.50 444	98.66 55	99.50 398	98.18 146	98.71 385	98.44 399

BH-RMVSNet		96.83 338	96.58 343	97.58 345	98.47 378	94.05 367	96.67 355	97.36 401	96.70 330	97.87 335	97.98 370	95.14 299	99.44 414	90.47 448	98.58 397	99.25 275

sasdasda		98.34 206	98.26 209	98.58 232	98.46 380	97.82 184	98.96 78	99.46 149	99.19 89	97.46 366	95.46 447	98.59 63	99.46 410	98.08 153	98.71 385	98.46 393

canonicalmvs		98.34 206	98.26 209	98.58 232	98.46 380	97.82 184	98.96 78	99.46 149	99.19 89	97.46 366	95.46 447	98.59 63	99.46 410	98.08 153	98.71 385	98.46 393

MVS-HIRNet		94.32 400	95.62 366	90.42 459	98.46 380	75.36 483	96.29 380	89.13 474	95.25 384	95.38 440	99.75 16	92.88 349	99.19 444	94.07 385	99.39 304	96.72 460

PHI-MVS		98.29 217	97.95 248	99.34 84	98.44 383	99.16 49	98.12 182	99.38 184	96.01 360	98.06 321	98.43 332	97.80 149	99.67 321	95.69 340	99.58 256	99.20 290

DVP-MVS++		98.90 101	98.70 131	99.51 49	98.43 384	99.15 53	99.43 15	99.32 212	98.17 199	99.26 149	99.02 196	98.18 110	99.88 115	97.07 235	99.45 293	99.49 169

MSC_two_6792asdad				99.32 92	98.43 384	98.37 122		98.86 327					99.89 97	97.14 229	99.60 247	99.71 63

No_MVS				99.32 92	98.43 384	98.37 122		98.86 327					99.89 97	97.14 229	99.60 247	99.71 63

Fast-Effi-MVS+-dtu		98.27 218	98.09 231	98.81 182	98.43 384	98.11 144	97.61 274	99.50 127	98.64 151	97.39 373	97.52 397	98.12 118	99.95 26	96.90 253	98.71 385	98.38 406

OpenMVS_ROB	95.38 14	95.84 373	95.18 386	97.81 317	98.41 388	97.15 239	97.37 308	98.62 358	83.86 470	98.65 260	98.37 338	94.29 324	99.68 317	88.41 454	98.62 395	96.60 461

DeepPCF-MVS	96.93 5	98.32 211	98.01 241	99.23 109	98.39 389	98.97 74	95.03 435	99.18 265	96.88 319	99.33 131	98.78 267	98.16 114	99.28 438	96.74 267	99.62 240	99.44 199

Patchmatch-test		96.55 348	96.34 350	97.17 372	98.35 390	93.06 399	98.40 151	97.79 388	97.33 281	98.41 292	98.67 294	83.68 430	99.69 308	95.16 353	99.31 317	98.77 367

AdaColmap		97.14 322	96.71 333	98.46 258	98.34 391	97.80 188	96.95 338	98.93 310	95.58 374	96.92 390	97.66 388	95.87 279	99.53 388	90.97 442	99.14 346	98.04 422

OpenMVS	96.65 7	97.09 324	96.68 335	98.32 275	98.32 392	97.16 238	98.86 92	99.37 188	89.48 458	96.29 420	99.15 164	96.56 242	99.90 81	92.90 410	99.20 337	97.89 430

MG-MVS		96.77 341	96.61 340	97.26 368	98.31 393	93.06 399	95.93 402	98.12 382	96.45 342	97.92 330	98.73 278	93.77 336	99.39 421	91.19 440	99.04 357	99.33 252

test_yl		96.69 342	96.29 352	97.90 310	98.28 394	95.24 329	97.29 315	97.36 401	98.21 192	98.17 307	97.86 377	86.27 406	99.55 380	94.87 359	98.32 402	98.89 346

DCV-MVSNet		96.69 342	96.29 352	97.90 310	98.28 394	95.24 329	97.29 315	97.36 401	98.21 192	98.17 307	97.86 377	86.27 406	99.55 380	94.87 359	98.32 402	98.89 346

CHOSEN 280x420		95.51 383	95.47 372	95.65 424	98.25 396	88.27 455	93.25 466	98.88 320	93.53 420	94.65 449	97.15 412	86.17 408	99.93 54	97.41 212	99.93 56	98.73 372

SCA		96.41 355	96.66 338	95.67 422	98.24 397	88.35 454	95.85 408	96.88 419	96.11 354	97.67 349	98.67 294	93.10 344	99.85 156	94.16 379	99.22 333	98.81 359

DeepMVS_CX				93.44 452	98.24 397	94.21 362		94.34 452	64.28 478	91.34 472	94.87 459	89.45 389	92.77 479	77.54 475	93.14 472	93.35 474

MS-PatchMatch		97.68 278	97.75 264	97.45 359	98.23 399	93.78 386	97.29 315	98.84 331	96.10 355	98.64 261	98.65 299	96.04 265	99.36 424	96.84 259	99.14 346	99.20 290

BH-w/o		95.13 389	94.89 393	95.86 417	98.20 400	91.31 430	95.65 415	97.37 400	93.64 418	96.52 413	95.70 440	93.04 347	99.02 450	88.10 456	95.82 462	97.24 453

mvs_anonymous		97.83 271	98.16 225	96.87 387	98.18 401	91.89 420	97.31 313	98.90 316	97.37 278	98.83 234	99.46 82	96.28 256	99.79 245	98.90 96	98.16 412	98.95 335

miper_lstm_enhance		97.18 319	97.16 304	97.25 369	98.16 402	92.85 404	95.15 433	99.31 217	97.25 290	98.74 251	98.78 267	90.07 381	99.78 256	97.19 224	99.80 141	99.11 310

RRT-MVS		97.88 260	97.98 244	97.61 342	98.15 403	93.77 387	98.97 77	99.64 72	99.16 94	98.69 254	99.42 91	91.60 366	99.89 97	97.63 193	98.52 399	99.16 305

ET-MVSNet_ETH3D		94.30 402	93.21 413	97.58 345	98.14 404	94.47 355	94.78 441	93.24 462	94.72 396	89.56 474	95.87 437	78.57 452	99.81 223	96.91 248	97.11 447	98.46 393

ADS-MVSNet2		95.43 384	94.98 389	96.76 394	98.14 404	91.74 421	97.92 223	97.76 389	90.23 452	96.51 414	98.91 233	85.61 413	99.85 156	92.88 411	96.90 448	98.69 377

ADS-MVSNet		95.24 387	94.93 392	96.18 411	98.14 404	90.10 447	97.92 223	97.32 404	90.23 452	96.51 414	98.91 233	85.61 413	99.74 281	92.88 411	96.90 448	98.69 377

c3_l		97.36 303	97.37 292	97.31 364	98.09 407	93.25 397	95.01 436	99.16 272	97.05 307	98.77 246	98.72 280	92.88 349	99.64 344	96.93 247	99.76 173	99.05 315

FMVSNet3		97.50 289	97.24 300	98.29 279	98.08 408	95.83 303	97.86 232	98.91 315	97.89 227	98.95 207	98.95 227	87.06 401	99.81 223	97.77 181	99.69 208	99.23 280

PAPM		91.88 439	90.34 442	96.51 398	98.06 409	92.56 409	92.44 470	97.17 408	86.35 466	90.38 473	96.01 432	86.61 404	99.21 443	70.65 479	95.43 464	97.75 439

Effi-MVS+-dtu		98.26 220	97.90 256	99.35 81	98.02 410	99.49 6	98.02 202	99.16 272	98.29 185	97.64 350	97.99 369	96.44 248	99.95 26	96.66 278	98.93 373	98.60 385

eth_miper_zixun_eth		97.23 315	97.25 299	97.17 372	98.00 411	92.77 406	94.71 442	99.18 265	97.27 288	98.56 276	98.74 277	91.89 364	99.69 308	97.06 237	99.81 130	99.05 315

HY-MVS	95.94 13	95.90 370	95.35 380	97.55 350	97.95 412	94.79 343	98.81 97	96.94 417	92.28 437	95.17 442	98.57 313	89.90 383	99.75 276	91.20 439	97.33 443	98.10 419

UGNet		98.53 180	98.45 177	98.79 188	97.94 413	96.96 251	99.08 62	98.54 361	99.10 106	96.82 400	99.47 80	96.55 243	99.84 174	98.56 124	99.94 50	99.55 137
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		96.47 353	95.70 363	98.79 188	97.92 414	99.12 63	98.28 160	98.60 359	92.16 438	95.54 437	96.17 430	94.77 313	99.52 392	89.62 451	98.23 406	97.72 441
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		96.86 337	96.55 344	97.79 318	97.91 415	94.21 362	97.56 280	98.87 322	97.49 264	99.06 177	99.05 191	80.72 440	99.80 232	98.44 130	99.82 124	99.37 232

API-MVS		97.04 328	96.91 320	97.42 361	97.88 416	98.23 135	98.18 171	98.50 364	97.57 253	97.39 373	96.75 418	96.77 229	99.15 447	90.16 449	99.02 361	94.88 472

myMVS_eth3d28		92.92 426	92.31 422	94.77 436	97.84 417	87.59 459	96.19 386	96.11 432	97.08 306	94.27 452	93.49 468	66.07 474	98.78 460	91.78 427	97.93 425	97.92 429

miper_ehance_all_eth		97.06 326	97.03 311	97.16 374	97.83 418	93.06 399	94.66 445	99.09 284	95.99 361	98.69 254	98.45 330	92.73 354	99.61 357	96.79 261	99.03 358	98.82 354

cl____		97.02 329	96.83 325	97.58 345	97.82 419	94.04 369	94.66 445	99.16 272	97.04 308	98.63 262	98.71 281	88.68 394	99.69 308	97.00 240	99.81 130	99.00 327

DIV-MVS_self_test		97.02 329	96.84 324	97.58 345	97.82 419	94.03 370	94.66 445	99.16 272	97.04 308	98.63 262	98.71 281	88.69 392	99.69 308	97.00 240	99.81 130	99.01 323

CANet		97.87 262	97.76 263	98.19 292	97.75 421	95.51 314	96.76 350	99.05 291	97.74 237	96.93 389	98.21 352	95.59 287	99.89 97	97.86 176	99.93 56	99.19 295

UBG		93.25 420	92.32 421	96.04 416	97.72 422	90.16 446	95.92 404	95.91 437	96.03 359	93.95 460	93.04 471	69.60 464	99.52 392	90.72 447	97.98 423	98.45 396

mvsany_test1		97.60 283	97.54 281	97.77 320	97.72 422	95.35 325	95.36 427	97.13 410	94.13 411	99.71 50	99.33 113	97.93 133	99.30 434	97.60 197	98.94 372	98.67 381

PVSNet_0	89.98 21	91.15 440	90.30 443	93.70 449	97.72 422	84.34 473	90.24 473	97.42 399	90.20 455	93.79 461	93.09 470	90.90 376	98.89 458	86.57 462	72.76 479	97.87 432

CR-MVSNet		96.28 358	95.95 357	97.28 366	97.71 425	94.22 360	98.11 183	98.92 313	92.31 436	96.91 392	99.37 101	85.44 416	99.81 223	97.39 213	97.36 441	97.81 435

RPMNet		97.02 329	96.93 316	97.30 365	97.71 425	94.22 360	98.11 183	99.30 225	99.37 62	96.91 392	99.34 110	86.72 403	99.87 134	97.53 202	97.36 441	97.81 435

ETVMVS		92.60 429	91.08 438	97.18 370	97.70 427	93.65 392	96.54 362	95.70 440	96.51 335	94.68 448	92.39 474	61.80 480	99.50 398	86.97 459	97.41 437	98.40 404

pmmvs3		95.03 391	94.40 398	96.93 383	97.70 427	92.53 410	95.08 434	97.71 391	88.57 462	97.71 346	98.08 363	79.39 447	99.82 206	96.19 315	99.11 352	98.43 401

baseline2		93.73 412	92.83 418	96.42 401	97.70 427	91.28 432	96.84 346	89.77 473	93.96 416	92.44 468	95.93 435	79.14 448	99.77 262	92.94 409	96.76 452	98.21 413

WBMVS		95.18 388	94.78 394	96.37 402	97.68 430	89.74 449	95.80 410	98.73 350	97.54 259	98.30 298	98.44 331	70.06 462	99.82 206	96.62 281	99.87 99	99.54 143

tpm		94.67 396	94.34 400	95.66 423	97.68 430	88.42 453	97.88 228	94.90 447	94.46 402	96.03 427	98.56 314	78.66 450	99.79 245	95.88 328	95.01 466	98.78 366

CANet_DTU		97.26 311	97.06 310	97.84 314	97.57 432	94.65 351	96.19 386	98.79 339	97.23 296	95.14 443	98.24 349	93.22 341	99.84 174	97.34 215	99.84 113	99.04 319

testing11		93.08 423	92.02 428	96.26 407	97.56 433	90.83 441	96.32 378	95.70 440	96.47 339	92.66 467	93.73 464	64.36 478	99.59 364	93.77 394	97.57 430	98.37 408

tpm2		93.09 422	92.58 420	94.62 438	97.56 433	86.53 462	97.66 263	95.79 439	86.15 467	94.07 457	98.23 351	75.95 455	99.53 388	90.91 444	96.86 451	97.81 435

testing91		93.32 418	92.27 423	96.47 400	97.54 435	91.25 433	96.17 390	96.76 421	97.18 300	93.65 463	93.50 467	65.11 477	99.63 347	93.04 408	97.45 434	98.53 390

TR-MVS		95.55 381	95.12 387	96.86 390	97.54 435	93.94 378	96.49 367	96.53 426	94.36 407	97.03 387	96.61 421	94.26 325	99.16 446	86.91 461	96.31 456	97.47 449

testing99		93.04 424	91.98 431	96.23 409	97.53 437	90.70 443	96.35 376	95.94 436	96.87 320	93.41 464	93.43 469	63.84 479	99.59 364	93.24 406	97.19 444	98.40 404

1314		95.74 375	95.60 367	96.17 412	97.53 437	92.75 407	98.07 192	98.31 373	91.22 447	94.25 453	96.68 419	95.53 288	99.03 449	91.64 431	97.18 445	96.74 459

CostFormer		93.97 408	93.78 406	94.51 439	97.53 437	85.83 465	97.98 214	95.96 435	89.29 460	94.99 445	98.63 304	78.63 451	99.62 350	94.54 367	96.50 453	98.09 420

FMVSNet5		96.01 366	95.20 385	98.41 264	97.53 437	96.10 289	98.74 98	99.50 127	97.22 299	98.03 325	99.04 193	69.80 463	99.88 115	97.27 219	99.71 198	99.25 275

PMMVS		96.51 349	95.98 356	98.09 297	97.53 437	95.84 302	94.92 438	98.84 331	91.58 442	96.05 426	95.58 441	95.68 284	99.66 334	95.59 344	98.09 416	98.76 369

reproduce_monomvs		95.00 393	95.25 382	94.22 442	97.51 442	83.34 474	97.86 232	98.44 366	98.51 168	99.29 141	99.30 119	67.68 468	99.56 376	98.89 98	99.81 130	99.77 50

PAPR		95.29 385	94.47 396	97.75 324	97.50 443	95.14 334	94.89 439	98.71 352	91.39 446	95.35 441	95.48 446	94.57 316	99.14 448	84.95 464	97.37 439	98.97 332

testing222		91.96 437	90.37 441	96.72 395	97.47 444	92.59 408	96.11 392	94.76 448	96.83 322	92.90 466	92.87 472	57.92 481	99.55 380	86.93 460	97.52 431	98.00 426

PatchT		96.65 345	96.35 349	97.54 351	97.40 445	95.32 327	97.98 214	96.64 423	99.33 67	96.89 396	99.42 91	84.32 424	99.81 223	97.69 192	97.49 432	97.48 448

tpm cat1		93.29 419	93.13 416	93.75 448	97.39 446	84.74 468	97.39 302	97.65 395	83.39 472	94.16 454	98.41 333	82.86 435	99.39 421	91.56 433	95.35 465	97.14 454

PatchmatchNet		95.58 380	95.67 365	95.30 432	97.34 447	87.32 460	97.65 265	96.65 422	95.30 383	97.07 383	98.69 290	84.77 419	99.75 276	94.97 357	98.64 392	98.83 353
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 304	96.97 314	98.50 255	97.31 448	96.47 280	98.18 171	98.92 313	98.95 129	98.78 243	99.37 101	85.44 416	99.85 156	95.96 326	99.83 120	99.17 302

LS3D		98.63 159	98.38 189	99.36 75	97.25 449	99.38 13	99.12 61	99.32 212	99.21 82	98.44 289	98.88 243	97.31 192	99.80 232	96.58 284	99.34 312	98.92 341

IB-MVS	91.63 19	92.24 435	90.90 439	96.27 406	97.22 450	91.24 434	94.36 454	93.33 461	92.37 435	92.24 470	94.58 461	66.20 473	99.89 97	93.16 407	94.63 468	97.66 443
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		92.38 432	91.76 435	94.21 443	97.16 451	84.65 469	95.42 425	88.45 475	95.96 362	96.17 421	95.84 439	66.36 471	99.71 297	91.87 426	98.64 392	98.28 411

tpmrst		95.07 390	95.46 373	93.91 446	97.11 452	84.36 472	97.62 270	96.96 415	94.98 390	96.35 419	98.80 263	85.46 415	99.59 364	95.60 343	96.23 457	97.79 438

Syy-MVS		96.04 365	95.56 371	97.49 356	97.10 453	94.48 354	96.18 388	96.58 424	95.65 371	94.77 446	92.29 475	91.27 372	99.36 424	98.17 148	98.05 420	98.63 383

myMVS_eth3d		91.92 438	90.45 440	96.30 404	97.10 453	90.90 439	96.18 388	96.58 424	95.65 371	94.77 446	92.29 475	53.88 482	99.36 424	89.59 452	98.05 420	98.63 383

MDTV_nov1_ep13			95.22 384		97.06 455	83.20 475	97.74 252	96.16 430	94.37 406	96.99 388	98.83 256	83.95 428	99.53 388	93.90 388	97.95 424

MVS		93.19 421	92.09 426	96.50 399	96.91 456	94.03 370	98.07 192	98.06 384	68.01 477	94.56 451	96.48 424	95.96 275	99.30 434	83.84 466	96.89 450	96.17 464

E-PMN		94.17 404	94.37 399	93.58 450	96.86 457	85.71 466	90.11 475	97.07 411	98.17 199	97.82 341	97.19 410	84.62 421	98.94 454	89.77 450	97.68 429	96.09 468

JIA-IIPM		95.52 382	95.03 388	97.00 379	96.85 458	94.03 370	96.93 341	95.82 438	99.20 84	94.63 450	99.71 23	83.09 433	99.60 360	94.42 373	94.64 467	97.36 452

EMVS		93.83 410	94.02 402	93.23 455	96.83 459	84.96 467	89.77 476	96.32 428	97.92 224	97.43 370	96.36 429	86.17 408	98.93 455	87.68 457	97.73 428	95.81 469

cl22		95.79 374	95.39 378	96.98 381	96.77 460	92.79 405	94.40 453	98.53 362	94.59 399	97.89 333	98.17 355	82.82 436	99.24 440	96.37 304	99.03 358	98.92 341

WB-MVSnew		95.73 376	95.57 370	96.23 409	96.70 461	90.70 443	96.07 394	93.86 458	95.60 373	97.04 385	95.45 450	96.00 268	99.55 380	91.04 441	98.31 404	98.43 401

dp		93.47 416	93.59 409	93.13 456	96.64 462	81.62 481	97.66 263	96.42 427	92.80 431	96.11 423	98.64 302	78.55 453	99.59 364	93.31 404	92.18 475	98.16 416

MonoMVSNet		96.25 360	96.53 346	95.39 430	96.57 463	91.01 437	98.82 96	97.68 394	98.57 163	98.03 325	99.37 101	90.92 375	97.78 471	94.99 355	93.88 471	97.38 451

test-LLR		93.90 409	93.85 404	94.04 444	96.53 464	84.62 470	94.05 459	92.39 464	96.17 351	94.12 455	95.07 451	82.30 437	99.67 321	95.87 331	98.18 409	97.82 433

test-mter		92.33 434	91.76 435	94.04 444	96.53 464	84.62 470	94.05 459	92.39 464	94.00 415	94.12 455	95.07 451	65.63 476	99.67 321	95.87 331	98.18 409	97.82 433

TESTMET0.1,1		92.19 436	91.77 434	93.46 451	96.48 466	82.80 477	94.05 459	91.52 469	94.45 404	94.00 458	94.88 457	66.65 470	99.56 376	95.78 336	98.11 415	98.02 423

MGCNet		97.44 297	97.01 313	98.72 208	96.42 467	96.74 264	97.20 325	91.97 467	98.46 171	98.30 298	98.79 265	92.74 353	99.91 74	99.30 63	99.94 50	99.52 155

miper_enhance_ethall		96.01 366	95.74 361	96.81 391	96.41 468	92.27 417	93.69 464	98.89 319	91.14 449	98.30 298	97.35 408	90.58 378	99.58 371	96.31 308	99.03 358	98.60 385

tpmvs		95.02 392	95.25 382	94.33 440	96.39 469	85.87 463	98.08 188	96.83 420	95.46 378	95.51 439	98.69 290	85.91 411	99.53 388	94.16 379	96.23 457	97.58 446

CMPMVS	75.91 23	96.29 357	95.44 375	98.84 177	96.25 470	98.69 99	97.02 334	99.12 279	88.90 461	97.83 339	98.86 246	89.51 387	98.90 457	91.92 424	99.51 278	98.92 341
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 397	93.69 407	96.99 380	96.05 471	93.61 394	94.97 437	93.49 459	96.17 351	97.57 357	94.88 457	82.30 437	99.01 452	93.60 397	94.17 470	98.37 408

EPMVS		93.72 413	93.27 412	95.09 435	96.04 472	87.76 457	98.13 178	85.01 480	94.69 397	96.92 390	98.64 302	78.47 454	99.31 432	95.04 354	96.46 454	98.20 414

cascas		94.79 395	94.33 401	96.15 415	96.02 473	92.36 415	92.34 471	99.26 245	85.34 469	95.08 444	94.96 456	92.96 348	98.53 464	94.41 376	98.59 396	97.56 447

MVStest1		95.86 371	95.60 367	96.63 396	95.87 474	91.70 422	97.93 220	98.94 307	98.03 214	99.56 74	99.66 33	71.83 460	98.26 467	99.35 59	99.24 329	99.91 13

gg-mvs-nofinetune		92.37 433	91.20 437	95.85 418	95.80 475	92.38 414	99.31 31	81.84 482	99.75 11	91.83 471	99.74 19	68.29 465	99.02 450	87.15 458	97.12 446	96.16 465

gm-plane-assit					94.83 476	81.97 479			88.07 464		94.99 454		99.60 360	91.76 428

GG-mvs-BLEND				94.76 437	94.54 477	92.13 419	99.31 31	80.47 483		88.73 477	91.01 477	67.59 469	98.16 470	82.30 471	94.53 469	93.98 473

UWE-MVS-28		90.22 441	89.28 444	93.02 457	94.50 478	82.87 476	96.52 365	87.51 476	95.21 386	92.36 469	96.04 431	71.57 461	98.25 468	72.04 478	97.77 427	97.94 428

EPNet_dtu		94.93 394	94.78 394	95.38 431	93.58 479	87.68 458	96.78 348	95.69 442	97.35 280	89.14 476	98.09 362	88.15 399	99.49 401	94.95 358	99.30 320	98.98 329
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 445	75.95 448	77.12 462	92.39 480	67.91 486	90.16 474	59.44 487	82.04 473	89.42 475	94.67 460	49.68 484	81.74 480	48.06 480	77.66 478	81.72 476

KD-MVS_2432*1600		92.87 427	91.99 429	95.51 427	91.37 481	89.27 450	94.07 457	98.14 380	95.42 379	97.25 378	96.44 426	67.86 466	99.24 440	91.28 437	96.08 460	98.02 423

miper_refine_blended		92.87 427	91.99 429	95.51 427	91.37 481	89.27 450	94.07 457	98.14 380	95.42 379	97.25 378	96.44 426	67.86 466	99.24 440	91.28 437	96.08 460	98.02 423

EPNet		96.14 363	95.44 375	98.25 283	90.76 483	95.50 317	97.92 223	94.65 449	98.97 125	92.98 465	98.85 249	89.12 390	99.87 134	95.99 324	99.68 213	99.39 221
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 446	68.95 449	70.34 463	87.68 484	65.00 487	91.11 472	59.90 486	69.02 476	74.46 481	88.89 478	48.58 485	68.03 482	28.61 481	72.33 480	77.99 477

test_method		79.78 443	79.50 446	80.62 460	80.21 485	45.76 488	70.82 477	98.41 370	31.08 480	80.89 480	97.71 385	84.85 418	97.37 473	91.51 434	80.03 477	98.75 370

tmp_tt		78.77 444	78.73 447	78.90 461	58.45 486	74.76 485	94.20 456	78.26 484	39.16 479	86.71 478	92.82 473	80.50 441	75.19 481	86.16 463	92.29 474	86.74 475

testmvs		17.12 448	20.53 451	6.87 465	12.05 487	4.20 490	93.62 465	6.73 488	4.62 483	10.41 483	24.33 480	8.28 487	3.56 484	9.69 483	15.07 481	12.86 480

test123		17.04 449	20.11 452	7.82 464	10.25 488	4.91 489	94.80 440	4.47 489	4.93 482	10.00 484	24.28 481	9.69 486	3.64 483	10.14 482	12.43 482	14.92 479

mmdepth		0.00 452	0.00 455	0.00 466	0.00 489	0.00 491	0.00 478	0.00 490	0.00 484	0.00 485	0.00 484	0.00 488	0.00 485	0.00 484	0.00 483	0.00 481

monomultidepth		0.00 452	0.00 455	0.00 466	0.00 489	0.00 491	0.00 478	0.00 490	0.00 484	0.00 485	0.00 484	0.00 488	0.00 485	0.00 484	0.00 483	0.00 481

test_blank		0.00 452	0.00 455	0.00 466	0.00 489	0.00 491	0.00 478	0.00 490	0.00 484	0.00 485	0.00 484	0.00 488	0.00 485	0.00 484	0.00 483	0.00 481

eth-test2					0.00 489

eth-test					0.00 489

uanet_test		0.00 452	0.00 455	0.00 466	0.00 489	0.00 491	0.00 478	0.00 490	0.00 484	0.00 485	0.00 484	0.00 488	0.00 485	0.00 484	0.00 483	0.00 481

DCPMVS		0.00 452	0.00 455	0.00 466	0.00 489	0.00 491	0.00 478	0.00 490	0.00 484	0.00 485	0.00 484	0.00 488	0.00 485	0.00 484	0.00 483	0.00 481

cdsmvs_eth3d_5k		24.66 447	32.88 450	0.00 466	0.00 489	0.00 491	0.00 478	99.10 282	0.00 484	0.00 485	97.58 393	99.21 18	0.00 485	0.00 484	0.00 483	0.00 481

pcd_1.5k_mvsjas		8.17 450	10.90 453	0.00 466	0.00 489	0.00 491	0.00 478	0.00 490	0.00 484	0.00 485	0.00 484	98.07 120	0.00 485	0.00 484	0.00 483	0.00 481

sosnet-low-res		0.00 452	0.00 455	0.00 466	0.00 489	0.00 491	0.00 478	0.00 490	0.00 484	0.00 485	0.00 484	0.00 488	0.00 485	0.00 484	0.00 483	0.00 481

sosnet		0.00 452	0.00 455	0.00 466	0.00 489	0.00 491	0.00 478	0.00 490	0.00 484	0.00 485	0.00 484	0.00 488	0.00 485	0.00 484	0.00 483	0.00 481

uncertanet		0.00 452	0.00 455	0.00 466	0.00 489	0.00 491	0.00 478	0.00 490	0.00 484	0.00 485	0.00 484	0.00 488	0.00 485	0.00 484	0.00 483	0.00 481

Regformer		0.00 452	0.00 455	0.00 466	0.00 489	0.00 491	0.00 478	0.00 490	0.00 484	0.00 485	0.00 484	0.00 488	0.00 485	0.00 484	0.00 483	0.00 481

ab-mvs-re		8.12 451	10.83 454	0.00 466	0.00 489	0.00 491	0.00 478	0.00 490	0.00 484	0.00 485	97.48 399	0.00 488	0.00 485	0.00 484	0.00 483	0.00 481

uanet		0.00 452	0.00 455	0.00 466	0.00 489	0.00 491	0.00 478	0.00 490	0.00 484	0.00 485	0.00 484	0.00 488	0.00 485	0.00 484	0.00 483	0.00 481

TestfortrainingZip							98.68 108

WAC-MVS						90.90 439								91.37 436

PC_three_1452									93.27 423	99.40 116	98.54 315	98.22 105	97.00 474	95.17 352	99.45 293	99.49 169

test_241102_TWO								99.30 225	98.03 214	99.26 149	99.02 196	97.51 178	99.88 115	96.91 248	99.60 247	99.66 78

test_0728_THIRD									98.17 199	99.08 175	99.02 196	97.89 139	99.88 115	97.07 235	99.71 198	99.70 68

GSMVS																98.81 359

sam_mvs1												84.74 420				98.81 359

sam_mvs												84.29 426

MTGPA								99.20 257

test_post1							97.59 277				20.48 483	83.07 434	99.66 334	94.16 379

test_post											21.25 482	83.86 429	99.70 304

patchmatchnet-post											98.77 269	84.37 423	99.85 156

MTMP							97.93 220	91.91 468

test9_res														93.28 405	99.15 345	99.38 230

agg_prior2														92.50 421	99.16 343	99.37 232

test_prior4						97.97 164	95.86 406

test_prior2							95.74 413		96.48 338	96.11 423	97.63 391	95.92 278		94.16 379	99.20 337

旧先验2							95.76 412		88.56 463	97.52 361			99.66 334	94.48 369

新几何2							95.93 402

无先验							95.74 413	98.74 349	89.38 459				99.73 288	92.38 423		99.22 285

原ACMM2							95.53 419

testdata2													99.79 245	92.80 415

segment_acmp												97.02 211

testdata1							95.44 424		96.32 346

plane_prior5								99.27 240					99.70 304	94.42 373	99.51 278	99.45 195

plane_prior4											97.98 370

plane_prior3						97.78 189			97.41 274	97.79 342

plane_prior2							97.77 245		98.20 196

plane_prior						97.65 198	97.07 333		96.72 328						99.36 308

n2								0.00 490

nn								0.00 490

door-mid								99.57 96

test11								98.87 322

door								99.41 177

HQP5-MVS						96.79 260

BP-MVS														92.82 413

HQP4-MVS										95.56 433			99.54 386			99.32 255

HQP3-MVS								99.04 294							99.26 327

HQP2-MVS												93.84 332

MDTV_nov1_ep13_2view						74.92 484	97.69 258		90.06 457	97.75 345		85.78 412		93.52 399		98.69 377

ACMMP++_ref															99.77 158

ACMMP++															99.68 213

Test By Simon												96.52 244

High-resolution multi-view benchmark