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 13	100.00 1	99.85 26

Gipuma		99.03 69	99.16 54	98.64 191	99.94 2	98.51 104	99.32 23	99.75 38	99.58 29	98.60 225	99.62 37	98.22 87	99.51 351	97.70 157	99.73 153	97.89 383
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 26	99.31 36	99.53 37	99.91 3	98.98 69	99.63 7	99.58 66	99.44 42	99.78 33	99.76 12	96.39 211	99.92 55	99.44 44	99.92 58	99.68 63

pmmvs6		99.67 3	99.70 3	99.60 14	99.90 4	99.27 26	99.53 8	99.76 35	99.64 19	99.84 25	99.83 4	99.50 9	99.87 115	99.36 46	99.92 58	99.64 74

PS-MVSNAJss		99.46 14	99.49 13	99.35 72	99.90 4	98.15 131	99.20 45	99.65 56	99.48 34	99.92 8	99.71 19	98.07 100	99.96 12	99.53 38	100.00 1	99.93 11

testf1		99.25 37	99.16 54	99.51 46	99.89 6	99.63 4	98.71 99	99.69 46	98.90 111	99.43 87	99.35 93	98.86 31	99.67 283	97.81 148	99.81 107	99.24 237

APD_test2		99.25 37	99.16 54	99.51 46	99.89 6	99.63 4	98.71 99	99.69 46	98.90 111	99.43 87	99.35 93	98.86 31	99.67 283	97.81 148	99.81 107	99.24 237

ANet_high		99.57 7	99.67 5	99.28 88	99.89 6	98.09 138	99.14 54	99.93 5	99.82 5	99.93 6	99.81 6	99.17 19	99.94 39	99.31 49	100.00 1	99.82 31

anonymousdsp		99.51 11	99.47 18	99.62 9	99.88 9	99.08 67	99.34 20	99.69 46	98.93 109	99.65 53	99.72 18	98.93 29	99.95 24	99.11 63	100.00 1	99.82 31

v7n		99.53 9	99.57 10	99.41 62	99.88 9	98.54 102	99.45 11	99.61 62	99.66 17	99.68 47	99.66 29	98.44 68	99.95 24	99.73 24	99.96 27	99.75 52

mvs_tets		99.63 5	99.67 5	99.49 51	99.88 9	98.61 94	99.34 20	99.71 42	99.27 63	99.90 13	99.74 15	99.68 4	99.97 5	99.55 37	99.99 5	99.88 19

test_fmvsmconf0.01_n		99.57 7	99.63 7	99.36 66	99.87 12	98.13 134	98.08 170	99.95 1	99.45 40	99.98 2	99.75 13	99.80 1	99.97 5	99.82 9	99.99 5	99.99 2

jajsoiax		99.58 6	99.61 8	99.48 53	99.87 12	98.61 94	99.28 37	99.66 55	99.09 91	99.89 16	99.68 22	99.53 7	99.97 5	99.50 41	99.99 5	99.87 20

test_djsdf		99.52 10	99.51 12	99.53 37	99.86 14	98.74 84	99.39 17	99.56 80	99.11 81	99.70 43	99.73 17	99.00 24	99.97 5	99.26 53	99.98 12	99.89 16

MIMVSNet1		99.38 25	99.32 34	99.55 27	99.86 14	99.19 41	99.41 14	99.59 64	99.59 27	99.71 41	99.57 46	97.12 171	99.90 70	99.21 58	99.87 84	99.54 121

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 25	99.85 16	99.11 63	99.90 1	99.78 33	99.63 21	99.78 33	99.67 27	99.48 10	99.81 195	99.30 50	99.97 20	99.77 43
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 19	99.69 5	99.58 66	99.90 3	99.86 20	99.78 10	99.58 6	99.95 24	99.00 72	99.95 34	99.78 40

SixPastTwentyTwo		98.75 107	98.62 118	99.16 108	99.83 18	97.96 158	99.28 37	98.20 334	99.37 50	99.70 43	99.65 33	92.65 314	99.93 46	99.04 69	99.84 93	99.60 87

Baseline_NR-MVSNet		98.98 76	98.86 86	99.36 66	99.82 19	98.55 99	97.47 260	99.57 73	99.37 50	99.21 131	99.61 40	96.76 195	99.83 171	98.06 132	99.83 100	99.71 55

pm-mvs1		99.44 16	99.48 15	99.33 81	99.80 20	98.63 91	99.29 33	99.63 58	99.30 60	99.65 53	99.60 42	99.16 21	99.82 181	99.07 66	99.83 100	99.56 110

TransMVSNet (Re)		99.44 16	99.47 18	99.36 66	99.80 20	98.58 97	99.27 39	99.57 73	99.39 48	99.75 37	99.62 37	99.17 19	99.83 171	99.06 67	99.62 201	99.66 68

K. test v3		98.00 205	97.66 229	99.03 133	99.79 22	97.56 190	99.19 49	92.47 416	99.62 24	99.52 70	99.66 29	89.61 340	99.96 12	99.25 55	99.81 107	99.56 110

test_fmvsmconf0.1_n		99.49 12	99.54 11	99.34 75	99.78 23	98.11 135	97.77 217	99.90 11	99.33 55	99.97 3	99.66 29	99.71 3	99.96 12	99.79 16	99.99 5	99.96 8

APD_test1		98.83 94	98.66 112	99.34 75	99.78 23	99.47 9	98.42 136	99.45 121	98.28 158	98.98 161	99.19 130	97.76 124	99.58 326	96.57 240	99.55 228	98.97 285

test_vis3_rt		99.14 52	99.17 52	99.07 123	99.78 23	98.38 111	98.92 79	99.94 2	97.80 195	99.91 12	99.67 27	97.15 170	98.91 409	99.76 20	99.56 224	99.92 12

EGC-MVSNET		85.24 396	80.54 399	99.34 75	99.77 26	99.20 38	99.08 58	99.29 193	12.08 434	20.84 435	99.42 80	97.55 142	99.85 136	97.08 192	99.72 161	98.96 287

Anonymous20240521		98.69 118	98.87 83	98.16 255	99.77 26	95.11 297	99.08 58	99.44 125	99.34 54	99.33 107	99.55 54	94.10 290	99.94 39	99.25 55	99.96 27	99.42 176

FC-MVSNet-test		99.27 34	99.25 45	99.34 75	99.77 26	98.37 113	99.30 32	99.57 73	99.61 26	99.40 95	99.50 64	97.12 171	99.85 136	99.02 71	99.94 42	99.80 36

test_vis1_n		98.31 177	98.50 134	97.73 288	99.76 29	94.17 322	98.68 102	99.91 9	96.31 302	99.79 32	99.57 46	92.85 310	99.42 370	99.79 16	99.84 93	99.60 87

test_fmvs3		99.12 58	99.41 22	98.25 247	99.76 29	95.07 298	99.05 64	99.94 2	97.78 197	99.82 27	99.84 3	98.56 59	99.71 263	99.96 1	99.96 27	99.97 4

XXY-MVS		99.14 52	99.15 59	99.10 117	99.76 29	97.74 179	98.85 87	99.62 59	98.48 142	99.37 100	99.49 70	98.75 41	99.86 123	98.20 122	99.80 118	99.71 55

TDRefinement		99.42 21	99.38 25	99.55 27	99.76 29	99.33 20	99.68 6	99.71 42	99.38 49	99.53 68	99.61 40	98.64 49	99.80 202	98.24 119	99.84 93	99.52 132

fmvsm_s_conf0.1_n_a		99.17 47	99.30 39	98.80 165	99.75 33	96.59 244	97.97 192	99.86 16	98.22 161	99.88 18	99.71 19	98.59 55	99.84 154	99.73 24	99.98 12	99.98 3

tt0805		98.69 118	98.62 118	98.90 155	99.75 33	99.30 21	99.15 53	96.97 369	98.86 115	98.87 190	97.62 345	98.63 51	98.96 406	99.41 45	98.29 358	98.45 349

test_vis1_n_1920		98.40 164	98.92 78	96.81 344	99.74 35	90.76 395	98.15 160	99.91 9	98.33 149	99.89 16	99.55 54	95.07 261	99.88 97	99.76 20	99.93 47	99.79 37

FOURS1					99.73 36	99.67 3	99.43 12	99.54 88	99.43 44	99.26 123

PEN-MVS		99.41 22	99.34 31	99.62 9	99.73 36	99.14 56	99.29 33	99.54 88	99.62 24	99.56 60	99.42 80	98.16 95	99.96 12	98.78 86	99.93 47	99.77 43

lessismore_v0				98.97 142	99.73 36	97.53 192		86.71 431		99.37 100	99.52 63	89.93 338	99.92 55	98.99 73	99.72 161	99.44 169

SteuartSystems-ACMMP		98.79 100	98.54 129	99.54 30	99.73 36	99.16 47	98.23 150	99.31 177	97.92 186	98.90 181	98.90 204	98.00 106	99.88 97	96.15 272	99.72 161	99.58 99
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 195	98.15 186	98.22 250	99.73 36	95.15 294	97.36 268	99.68 51	94.45 357	98.99 160	99.27 111	96.87 185	99.94 39	97.13 189	99.91 67	99.57 104

Vis-MVSNet		99.34 27	99.36 28	99.27 91	99.73 36	98.26 120	99.17 50	99.78 33	99.11 81	99.27 119	99.48 71	98.82 34	99.95 24	98.94 76	99.93 47	99.59 93
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
SSC-MVS		98.71 111	98.74 96	98.62 197	99.72 42	96.08 262	98.74 92	98.64 314	99.74 10	99.67 49	99.24 121	94.57 276	99.95 24	99.11 63	99.24 282	99.82 31

test_f		98.67 126	98.87 83	98.05 264	99.72 42	95.59 274	98.51 123	99.81 28	96.30 304	99.78 33	99.82 5	96.14 221	98.63 416	99.82 9	99.93 47	99.95 9

ACMH	96.65 7	99.25 37	99.24 46	99.26 93	99.72 42	98.38 111	99.07 61	99.55 84	98.30 153	99.65 53	99.45 77	99.22 16	99.76 238	98.44 110	99.77 134	99.64 74
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.1_n		99.16 50	99.33 32	98.64 191	99.71 45	96.10 257	97.87 204	99.85 18	98.56 138	99.90 13	99.68 22	98.69 46	99.85 136	99.72 26	99.98 12	99.97 4

PS-CasMVS		99.40 23	99.33 32	99.62 9	99.71 45	99.10 64	99.29 33	99.53 91	99.53 31	99.46 82	99.41 84	98.23 84	99.95 24	98.89 80	99.95 34	99.81 34

DTE-MVSNet		99.43 20	99.35 29	99.66 7	99.71 45	99.30 21	99.31 27	99.51 95	99.64 19	99.56 60	99.46 73	98.23 84	99.97 5	98.78 86	99.93 47	99.72 54

WR-MVS_H		99.33 28	99.22 47	99.65 8	99.71 45	99.24 29	99.32 23	99.55 84	99.46 39	99.50 76	99.34 97	97.30 160	99.93 46	98.90 78	99.93 47	99.77 43

HPM-MVS_fast		99.01 70	98.82 89	99.57 20	99.71 45	99.35 16	99.00 69	99.50 97	97.33 240	98.94 176	98.86 214	98.75 41	99.82 181	97.53 167	99.71 166	99.56 110

ACMH+	96.62 9	99.08 65	99.00 71	99.33 81	99.71 45	98.83 79	98.60 109	99.58 66	99.11 81	99.53 68	99.18 134	98.81 35	99.67 283	96.71 229	99.77 134	99.50 138

PMVS	91.26 20	97.86 218	97.94 208	97.65 292	99.71 45	97.94 160	98.52 118	98.68 310	98.99 102	97.52 315	99.35 93	97.41 155	98.18 422	91.59 386	99.67 187	96.82 411
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FIs		99.14 52	99.09 64	99.29 87	99.70 52	98.28 119	99.13 55	99.52 94	99.48 34	99.24 128	99.41 84	96.79 192	99.82 181	98.69 96	99.88 81	99.76 48

VPNet		98.87 89	98.83 88	99.01 136	99.70 52	97.62 188	98.43 134	99.35 158	99.47 37	99.28 117	99.05 165	96.72 198	99.82 181	98.09 129	99.36 262	99.59 93

fmvsm_s_conf0.1_n_2		99.20 45	99.38 25	98.65 189	99.69 54	96.08 262	97.49 257	99.90 11	99.53 31	99.88 18	99.64 34	98.51 62	99.90 70	99.83 8	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 174	98.68 109	97.27 321	99.69 54	92.29 370	98.03 178	99.85 18	97.62 206	99.96 4	99.62 37	93.98 291	99.74 250	99.52 40	99.86 88	99.79 37

MP-MVS-pluss		98.57 140	98.23 176	99.60 14	99.69 54	99.35 16	97.16 286	99.38 145	94.87 347	98.97 165	98.99 183	98.01 105	99.88 97	97.29 177	99.70 173	99.58 99
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 41	99.32 34	98.96 143	99.68 57	97.35 201	98.84 89	99.48 106	99.69 13	99.63 56	99.68 22	99.03 23	99.96 12	97.97 139	99.92 58	99.57 104

sd_testset		99.28 33	99.31 36	99.19 104	99.68 57	98.06 147	99.41 14	99.30 185	99.69 13	99.63 56	99.68 22	99.25 15	99.96 12	97.25 180	99.92 58	99.57 104

test_fmvs1_n		98.09 199	98.28 168	97.52 307	99.68 57	93.47 349	98.63 105	99.93 5	95.41 335	99.68 47	99.64 34	91.88 323	99.48 358	99.82 9	99.87 84	99.62 78

CHOSEN 1792x2688		97.49 247	97.14 262	98.54 215	99.68 57	96.09 260	96.50 319	99.62 59	91.58 395	98.84 193	98.97 189	92.36 316	99.88 97	96.76 222	99.95 34	99.67 66

tfpnnormal		98.90 86	98.90 80	98.91 152	99.67 61	97.82 171	99.00 69	99.44 125	99.45 40	99.51 75	99.24 121	98.20 90	99.86 123	95.92 281	99.69 176	99.04 272

MTAPA		98.88 88	98.64 115	99.61 12	99.67 61	99.36 15	98.43 134	99.20 216	98.83 119	98.89 183	98.90 204	96.98 181	99.92 55	97.16 184	99.70 173	99.56 110

test_fmvsmvis_n_1920		99.26 36	99.49 13	98.54 215	99.66 63	96.97 224	98.00 184	99.85 18	99.24 65	99.92 8	99.50 64	99.39 12	99.95 24	99.89 3	99.98 12	98.71 326

mvs5depth		99.30 30	99.59 9	98.44 228	99.65 64	95.35 286	99.82 3	99.94 2	99.83 4	99.42 90	99.94 2	98.13 98	99.96 12	99.63 31	99.96 27	100.00 1

fmvsm_l_conf0.5_n_a		99.19 46	99.27 42	98.94 146	99.65 64	97.05 220	97.80 213	99.76 35	98.70 123	99.78 33	99.11 150	98.79 39	99.95 24	99.85 5	99.96 27	99.83 28

WB-MVS		98.52 153	98.55 127	98.43 229	99.65 64	95.59 274	98.52 118	98.77 300	99.65 18	99.52 70	99.00 182	94.34 282	99.93 46	98.65 98	98.83 330	99.76 48

CP-MVSNet		99.21 43	99.09 64	99.56 25	99.65 64	98.96 74	99.13 55	99.34 164	99.42 45	99.33 107	99.26 116	97.01 179	99.94 39	98.74 91	99.93 47	99.79 37

HPM-MVS		98.79 100	98.53 130	99.59 18	99.65 64	99.29 23	99.16 51	99.43 131	96.74 284	98.61 223	98.38 291	98.62 52	99.87 115	96.47 252	99.67 187	99.59 93
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 135	98.36 158	99.42 60	99.65 64	99.42 11	98.55 114	99.57 73	97.72 200	98.90 181	99.26 116	96.12 223	99.52 346	95.72 292	99.71 166	99.32 218

fmvsm_l_conf0.5_n		99.21 43	99.28 41	99.02 135	99.64 70	97.28 205	97.82 209	99.76 35	98.73 120	99.82 27	99.09 157	98.81 35	99.95 24	99.86 4	99.96 27	99.83 28

test_fmvsmconf_n		99.44 16	99.48 15	99.31 86	99.64 70	98.10 137	97.68 229	99.84 21	99.29 61	99.92 8	99.57 46	99.60 5	99.96 12	99.74 23	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 132	98.49 138	99.06 129	99.64 70	97.90 162	98.51 123	98.94 265	96.96 271	99.24 128	98.89 210	97.83 117	99.81 195	96.88 212	99.49 247	99.48 152
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 96	98.72 100	99.12 113	99.64 70	98.54 102	97.98 189	99.68 51	97.62 206	99.34 106	99.18 134	97.54 143	99.77 232	97.79 150	99.74 150	99.04 272

KD-MVS_self_test		99.25 37	99.18 51	99.44 59	99.63 74	99.06 68	98.69 101	99.54 88	99.31 58	99.62 59	99.53 60	97.36 158	99.86 123	99.24 57	99.71 166	99.39 189

EU-MVSNet		97.66 235	98.50 134	95.13 386	99.63 74	85.84 417	98.35 142	98.21 333	98.23 160	99.54 64	99.46 73	95.02 262	99.68 280	98.24 119	99.87 84	99.87 20

HyFIR lowres test		97.19 273	96.60 297	98.96 143	99.62 76	97.28 205	95.17 383	99.50 97	94.21 362	99.01 158	98.32 299	86.61 358	99.99 2	97.10 191	99.84 93	99.60 87

fmvsm_l_conf0.5_n_3		99.45 15	99.48 15	99.34 75	99.59 77	98.21 128	97.82 209	99.84 21	99.41 47	99.92 8	99.41 84	99.51 8	99.95 24	99.84 7	99.97 20	99.87 20

mmtdpeth		99.30 30	99.42 21	98.92 151	99.58 78	96.89 231	99.48 10	99.92 7	99.92 2	98.26 260	99.80 9	98.33 77	99.91 64	99.56 36	99.95 34	99.97 4

ACMMP_NAP		98.75 107	98.48 139	99.57 20	99.58 78	99.29 23	97.82 209	99.25 205	96.94 273	98.78 200	99.12 149	98.02 104	99.84 154	97.13 189	99.67 187	99.59 93

nrg030		99.40 23	99.35 29	99.54 30	99.58 78	99.13 59	98.98 72	99.48 106	99.68 15	99.46 82	99.26 116	98.62 52	99.73 255	99.17 61	99.92 58	99.76 48

VDDNet		98.21 190	97.95 206	99.01 136	99.58 78	97.74 179	99.01 67	97.29 360	99.67 16	98.97 165	99.50 64	90.45 335	99.80 202	97.88 145	99.20 290	99.48 152

COLMAP_ROB	96.50 10	98.99 73	98.85 87	99.41 62	99.58 78	99.10 64	98.74 92	99.56 80	99.09 91	99.33 107	99.19 130	98.40 70	99.72 262	95.98 279	99.76 146	99.42 176
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 28	99.45 20	98.99 138	99.57 83	97.73 181	97.93 193	99.83 24	99.22 66	99.93 6	99.30 105	99.42 11	99.96 12	99.85 5	99.99 5	99.29 227

ZNCC-MVS		98.68 123	98.40 151	99.54 30	99.57 83	99.21 32	98.46 131	99.29 193	97.28 246	98.11 272	98.39 289	98.00 106	99.87 115	96.86 215	99.64 195	99.55 117

MSP-MVS		98.40 164	98.00 201	99.61 12	99.57 83	99.25 28	98.57 112	99.35 158	97.55 217	99.31 115	97.71 338	94.61 275	99.88 97	96.14 273	99.19 293	99.70 60
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		98.32 175	98.39 154	98.13 256	99.57 83	95.54 277	97.78 215	99.49 104	97.37 237	99.19 133	97.65 342	98.96 26	99.49 355	96.50 251	98.99 318	99.34 211

MP-MVS		98.46 158	98.09 191	99.54 30	99.57 83	99.22 31	98.50 125	99.19 220	97.61 209	97.58 309	98.66 252	97.40 156	99.88 97	94.72 318	99.60 208	99.54 121
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 111	98.46 143	99.47 56	99.57 83	98.97 70	98.23 150	99.48 106	96.60 289	99.10 143	99.06 158	98.71 44	99.83 171	95.58 299	99.78 128	99.62 78

LGP-MVS_train				99.47 56	99.57 83	98.97 70		99.48 106	96.60 289	99.10 143	99.06 158	98.71 44	99.83 171	95.58 299	99.78 128	99.62 78

IS-MVSNet		98.19 192	97.90 212	99.08 121	99.57 83	97.97 155	99.31 27	98.32 329	99.01 101	98.98 161	99.03 169	91.59 325	99.79 215	95.49 301	99.80 118	99.48 152

dcpmvs_2		98.78 102	99.11 60	97.78 278	99.56 91	93.67 344	99.06 62	99.86 16	99.50 33	99.66 50	99.26 116	97.21 168	99.99 2	98.00 137	99.91 67	99.68 63

test_0402		98.76 106	98.71 103	98.93 148	99.56 91	98.14 133	98.45 133	99.34 164	99.28 62	98.95 169	98.91 201	98.34 76	99.79 215	95.63 296	99.91 67	98.86 304

EPP-MVSNet		98.30 178	98.04 197	99.07 123	99.56 91	97.83 168	99.29 33	98.07 340	99.03 99	98.59 227	99.13 148	92.16 319	99.90 70	96.87 213	99.68 181	99.49 142

ACMMP		98.75 107	98.50 134	99.52 42	99.56 91	99.16 47	98.87 84	99.37 149	97.16 261	98.82 197	99.01 179	97.71 127	99.87 115	96.29 264	99.69 176	99.54 121
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 60	99.20 50	98.78 171	99.55 95	96.59 244	97.79 214	99.82 27	98.21 162	99.81 30	99.53 60	98.46 66	99.84 154	99.70 28	99.97 20	99.90 15

fmvsm_s_conf0.5_n		99.09 61	99.26 44	98.61 200	99.55 95	96.09 260	97.74 223	99.81 28	98.55 139	99.85 22	99.55 54	98.60 54	99.84 154	99.69 30	99.98 12	99.89 16

FMVSNet1		99.17 47	99.17 52	99.17 105	99.55 95	98.24 122	99.20 45	99.44 125	99.21 68	99.43 87	99.55 54	97.82 120	99.86 123	98.42 112	99.89 79	99.41 179

Vis-MVSNet (Re-imp)		97.46 249	97.16 259	98.34 240	99.55 95	96.10 257	98.94 77	98.44 323	98.32 151	98.16 266	98.62 261	88.76 345	99.73 255	93.88 344	99.79 123	99.18 252

ACMM	96.08 12	98.91 84	98.73 98	99.48 53	99.55 95	99.14 56	98.07 172	99.37 149	97.62 206	99.04 154	98.96 192	98.84 33	99.79 215	97.43 171	99.65 193	99.49 142
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 115	98.97 75	97.89 271	99.54 100	94.05 325	98.55 114	99.92 7	96.78 282	99.72 39	99.78 10	96.60 203	99.67 283	99.91 2	99.90 73	99.94 10

mPP-MVS		98.64 130	98.34 161	99.54 30	99.54 100	99.17 43	98.63 105	99.24 210	97.47 224	98.09 274	98.68 247	97.62 136	99.89 83	96.22 267	99.62 201	99.57 104

XVG-ACMP-BASELINE		98.56 141	98.34 161	99.22 101	99.54 100	98.59 96	97.71 226	99.46 117	97.25 249	98.98 161	98.99 183	97.54 143	99.84 154	95.88 282	99.74 150	99.23 239

region2R		98.69 118	98.40 151	99.54 30	99.53 103	99.17 43	98.52 118	99.31 177	97.46 229	98.44 245	98.51 275	97.83 117	99.88 97	96.46 253	99.58 217	99.58 99

PGM-MVS		98.66 127	98.37 157	99.55 27	99.53 103	99.18 42	98.23 150	99.49 104	97.01 270	98.69 211	98.88 211	98.00 106	99.89 83	95.87 285	99.59 212	99.58 99

Patchmatch-RL test		97.26 266	97.02 267	97.99 268	99.52 105	95.53 278	96.13 344	99.71 42	97.47 224	99.27 119	99.16 140	84.30 379	99.62 308	97.89 142	99.77 134	98.81 312

ACMMPR		98.70 115	98.42 149	99.54 30	99.52 105	99.14 56	98.52 118	99.31 177	97.47 224	98.56 232	98.54 270	97.75 125	99.88 97	96.57 240	99.59 212	99.58 99

GST-MVS		98.61 136	98.30 166	99.52 42	99.51 107	99.20 38	98.26 148	99.25 205	97.44 232	98.67 214	98.39 289	97.68 128	99.85 136	96.00 277	99.51 239	99.52 132

Anonymous20231206		98.21 190	98.21 177	98.20 251	99.51 107	95.43 284	98.13 162	99.32 172	96.16 307	98.93 177	98.82 223	96.00 228	99.83 171	97.32 176	99.73 153	99.36 205

ACMP	95.32 15	98.41 162	98.09 191	99.36 66	99.51 107	98.79 82	97.68 229	99.38 145	95.76 322	98.81 199	98.82 223	98.36 72	99.82 181	94.75 315	99.77 134	99.48 152
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DVP-MVS		98.77 105	98.52 131	99.52 42	99.50 110	99.21 32	98.02 180	98.84 289	97.97 180	99.08 145	99.02 170	97.61 137	99.88 97	96.99 199	99.63 198	99.48 152
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 14	99.50 110	99.23 30	98.02 180	99.32 172					99.88 97	96.99 199	99.63 198	99.68 63

test0726					99.50 110	99.21 32	98.17 158	99.35 158	97.97 180	99.26 123	99.06 158	97.61 137

AllTest		98.44 160	98.20 178	99.16 108	99.50 110	98.55 99	98.25 149	99.58 66	96.80 280	98.88 186	99.06 158	97.65 131	99.57 328	94.45 325	99.61 206	99.37 198

TestCases				99.16 108	99.50 110	98.55 99		99.58 66	96.80 280	98.88 186	99.06 158	97.65 131	99.57 328	94.45 325	99.61 206	99.37 198

XVG-OURS		98.53 149	98.34 161	99.11 115	99.50 110	98.82 81	95.97 350	99.50 97	97.30 244	99.05 152	98.98 187	99.35 13	99.32 384	95.72 292	99.68 181	99.18 252

EG-PatchMatch MVS		98.99 73	99.01 70	98.94 146	99.50 110	97.47 194	98.04 177	99.59 64	98.15 173	99.40 95	99.36 92	98.58 58	99.76 238	98.78 86	99.68 181	99.59 93

fmvsm_s_conf0.5_n_2		99.14 52	99.31 36	98.63 195	99.49 117	96.08 262	97.38 265	99.81 28	99.48 34	99.84 25	99.57 46	98.46 66	99.89 83	99.82 9	99.97 20	99.91 13

SED-MVS		98.91 84	98.72 100	99.49 51	99.49 117	99.17 43	98.10 168	99.31 177	98.03 176	99.66 50	99.02 170	98.36 72	99.88 97	96.91 205	99.62 201	99.41 179

IU-MVS					99.49 117	99.15 51		98.87 280	92.97 380	99.41 92				96.76 222	99.62 201	99.66 68

test_241102_ONE					99.49 117	99.17 43		99.31 177	97.98 179	99.66 50	98.90 204	98.36 72	99.48 358

UA-Net		99.47 13	99.40 23	99.70 2	99.49 117	99.29 23	99.80 4	99.72 40	99.82 5	99.04 154	99.81 6	98.05 103	99.96 12	98.85 82	99.99 5	99.86 24

HFP-MVS		98.71 111	98.44 146	99.51 46	99.49 117	99.16 47	98.52 118	99.31 177	97.47 224	98.58 229	98.50 279	97.97 110	99.85 136	96.57 240	99.59 212	99.53 129

VPA-MVSNet		99.30 30	99.30 39	99.28 88	99.49 117	98.36 116	99.00 69	99.45 121	99.63 21	99.52 70	99.44 78	98.25 82	99.88 97	99.09 65	99.84 93	99.62 78

XVG-OURS-SEG-HR		98.49 155	98.28 168	99.14 111	99.49 117	98.83 79	96.54 315	99.48 106	97.32 242	99.11 140	98.61 263	99.33 14	99.30 387	96.23 266	98.38 354	99.28 229

114514_t		96.50 306	95.77 314	98.69 185	99.48 125	97.43 198	97.84 208	99.55 84	81.42 427	96.51 367	98.58 267	95.53 248	99.67 283	93.41 357	99.58 217	98.98 282

IterMVS-LS		98.55 145	98.70 106	98.09 257	99.48 125	94.73 306	97.22 281	99.39 143	98.97 105	99.38 98	99.31 104	96.00 228	99.93 46	98.58 101	99.97 20	99.60 87
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_5		99.07 67	99.10 62	98.99 138	99.47 127	97.22 210	97.40 263	99.83 24	97.61 209	99.85 22	99.30 105	98.80 37	99.95 24	99.71 27	99.90 73	99.78 40

v8		99.01 70	99.16 54	98.57 207	99.47 127	96.31 254	98.90 80	99.47 114	99.03 99	99.52 70	99.57 46	96.93 182	99.81 195	99.60 32	99.98 12	99.60 87

SSC-MVS3.2		98.53 149	98.79 92	97.74 285	99.46 129	93.62 347	96.45 321	99.34 164	99.33 55	98.93 177	98.70 243	97.90 113	99.90 70	99.12 62	99.92 58	99.69 62

fmvsm_s_conf0.5_n_3		99.22 42	99.37 27	98.78 171	99.46 129	96.58 246	97.65 235	99.72 40	99.47 37	99.86 20	99.50 64	98.94 27	99.89 83	99.75 22	99.97 20	99.86 24

XVS		98.72 110	98.45 144	99.53 37	99.46 129	99.21 32	98.65 103	99.34 164	98.62 128	97.54 313	98.63 259	97.50 149	99.83 171	96.79 218	99.53 234	99.56 110

X-MVStestdata		94.32 354	92.59 373	99.53 37	99.46 129	99.21 32	98.65 103	99.34 164	98.62 128	97.54 313	45.85 432	97.50 149	99.83 171	96.79 218	99.53 234	99.56 110

test20.03		98.78 102	98.77 95	98.78 171	99.46 129	97.20 213	97.78 215	99.24 210	99.04 98	99.41 92	98.90 204	97.65 131	99.76 238	97.70 157	99.79 123	99.39 189

CSCG		98.68 123	98.50 134	99.20 102	99.45 134	98.63 91	98.56 113	99.57 73	97.87 190	98.85 191	98.04 320	97.66 130	99.84 154	96.72 227	99.81 107	99.13 261

GeoE		99.05 68	98.99 73	99.25 96	99.44 135	98.35 117	98.73 96	99.56 80	98.42 145	98.91 180	98.81 225	98.94 27	99.91 64	98.35 114	99.73 153	99.49 142

v148		98.45 159	98.60 123	98.00 267	99.44 135	94.98 299	97.44 262	99.06 246	98.30 153	99.32 113	98.97 189	96.65 201	99.62 308	98.37 113	99.85 89	99.39 189

v10		98.97 77	99.11 60	98.55 212	99.44 135	96.21 256	98.90 80	99.55 84	98.73 120	99.48 77	99.60 42	96.63 202	99.83 171	99.70 28	99.99 5	99.61 86

V42		98.78 102	98.78 94	98.76 176	99.44 135	97.04 221	98.27 147	99.19 220	97.87 190	99.25 127	99.16 140	96.84 186	99.78 226	99.21 58	99.84 93	99.46 161

MDA-MVSNet-bldmvs		97.94 209	97.91 211	98.06 262	99.44 135	94.96 300	96.63 313	99.15 236	98.35 147	98.83 194	99.11 150	94.31 283	99.85 136	96.60 237	98.72 336	99.37 198

casdiffmvs_mvg		99.12 58	99.16 54	98.99 138	99.43 140	97.73 181	98.00 184	99.62 59	99.22 66	99.55 63	99.22 126	98.93 29	99.75 245	98.66 97	99.81 107	99.50 138
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test1111		96.49 307	96.82 281	95.52 379	99.42 141	87.08 414	99.22 42	87.14 430	99.11 81	99.46 82	99.58 44	88.69 346	99.86 123	98.80 84	99.95 34	99.62 78

v2v482		98.56 141	98.62 118	98.37 237	99.42 141	95.81 271	97.58 246	99.16 231	97.90 188	99.28 117	99.01 179	95.98 233	99.79 215	99.33 48	99.90 73	99.51 135

OPM-MVS		98.56 141	98.32 165	99.25 96	99.41 143	98.73 87	97.13 288	99.18 224	97.10 264	98.75 206	98.92 200	98.18 91	99.65 299	96.68 231	99.56 224	99.37 198
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 201	98.08 194	98.04 265	99.41 143	94.59 312	94.59 401	99.40 141	97.50 221	98.82 197	98.83 220	96.83 188	99.84 154	97.50 169	99.81 107	99.71 55

test_one_0601					99.39 145	99.20 38		99.31 177	98.49 141	98.66 216	99.02 170	97.64 134

mvsany_test3		98.87 89	98.92 78	98.74 182	99.38 146	96.94 228	98.58 111	99.10 241	96.49 294	99.96 4	99.81 6	98.18 91	99.45 365	98.97 74	99.79 123	99.83 28

patch_mono-2		98.51 154	98.63 116	98.17 253	99.38 146	94.78 303	97.36 268	99.69 46	98.16 172	98.49 241	99.29 108	97.06 174	99.97 5	98.29 118	99.91 67	99.76 48

test2506		92.39 385	91.89 387	93.89 400	99.38 146	82.28 431	99.32 23	66.03 438	99.08 93	98.77 203	99.57 46	66.26 426	99.84 154	98.71 94	99.95 34	99.54 121

ECVR-MVS		96.42 309	96.61 295	95.85 371	99.38 146	88.18 409	99.22 42	86.00 432	99.08 93	99.36 102	99.57 46	88.47 351	99.82 181	98.52 107	99.95 34	99.54 121

casdiffmvs		98.95 80	99.00 71	98.81 163	99.38 146	97.33 202	97.82 209	99.57 73	99.17 77	99.35 104	99.17 138	98.35 75	99.69 271	98.46 109	99.73 153	99.41 179
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 79	99.02 69	98.76 176	99.38 146	97.26 207	98.49 126	99.50 97	98.86 115	99.19 133	99.06 158	98.23 84	99.69 271	98.71 94	99.76 146	99.33 216

TranMVSNet+NR-MVSNet		99.17 47	99.07 67	99.46 58	99.37 152	98.87 77	98.39 138	99.42 134	99.42 45	99.36 102	99.06 158	98.38 71	99.95 24	98.34 115	99.90 73	99.57 104

fmvsm_s_conf0.5_n_6		99.08 65	99.21 49	98.69 185	99.36 153	96.51 248	97.62 239	99.68 51	98.43 144	99.85 22	99.10 153	99.12 22	99.88 97	99.77 19	99.92 58	99.67 66

tttt0517		95.64 333	94.98 343	97.64 294	99.36 153	93.81 339	98.72 97	90.47 424	98.08 175	98.67 214	98.34 296	73.88 412	99.92 55	97.77 152	99.51 239	99.20 244

test_part2					99.36 153	99.10 64				99.05 152

v1144		98.60 137	98.66 112	98.41 231	99.36 153	95.90 267	97.58 246	99.34 164	97.51 220	99.27 119	99.15 144	96.34 216	99.80 202	99.47 43	99.93 47	99.51 135

CP-MVS		98.70 115	98.42 149	99.52 42	99.36 153	99.12 61	98.72 97	99.36 153	97.54 218	98.30 254	98.40 288	97.86 116	99.89 83	96.53 249	99.72 161	99.56 110

Test_1112_low_res		96.99 288	96.55 299	98.31 243	99.35 158	95.47 282	95.84 362	99.53 91	91.51 397	96.80 355	98.48 282	91.36 327	99.83 171	96.58 238	99.53 234	99.62 78

DeepC-MVS	97.60 4	98.97 77	98.93 77	99.10 117	99.35 158	97.98 154	98.01 183	99.46 117	97.56 215	99.54 64	99.50 64	98.97 25	99.84 154	98.06 132	99.92 58	99.49 142
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 265	96.86 277	98.58 204	99.34 160	96.32 253	96.75 307	99.58 66	93.14 378	96.89 350	97.48 352	92.11 320	99.86 123	96.91 205	99.54 230	99.57 104

reproduce_model		99.15 51	98.97 75	99.67 4	99.33 161	99.44 10	98.15 160	99.47 114	99.12 80	99.52 70	99.32 103	98.31 78	99.90 70	97.78 151	99.73 153	99.66 68

MVSMamba_PlusPlus		98.83 94	98.98 74	98.36 238	99.32 162	96.58 246	98.90 80	99.41 138	99.75 8	98.72 209	99.50 64	96.17 220	99.94 39	99.27 52	99.78 128	98.57 342

fmvsm_s_conf0.5_n_4		99.01 70	99.22 47	98.38 234	99.31 163	95.48 281	97.56 248	99.73 39	98.87 113	99.75 37	99.27 111	98.80 37	99.86 123	99.80 14	99.90 73	99.81 34

SF-MVS		98.53 149	98.27 171	99.32 83	99.31 163	98.75 83	98.19 154	99.41 138	96.77 283	98.83 194	98.90 204	97.80 122	99.82 181	95.68 295	99.52 237	99.38 196

CPTT-MVS		97.84 224	97.36 248	99.27 91	99.31 163	98.46 107	98.29 145	99.27 199	94.90 346	97.83 293	98.37 292	94.90 264	99.84 154	93.85 346	99.54 230	99.51 135

UnsupCasMVSNet_eth		97.89 213	97.60 234	98.75 178	99.31 163	97.17 216	97.62 239	99.35 158	98.72 122	98.76 205	98.68 247	92.57 315	99.74 250	97.76 156	95.60 416	99.34 211

pmmvs-eth3d		98.47 157	98.34 161	98.86 157	99.30 167	97.76 177	97.16 286	99.28 196	95.54 328	99.42 90	99.19 130	97.27 163	99.63 305	97.89 142	99.97 20	99.20 244

mamv4		99.44 16	99.39 24	99.58 19	99.30 167	99.74 2	99.04 65	99.81 28	99.77 7	99.82 27	99.57 46	97.82 120	99.98 4	99.53 38	99.89 79	99.01 276

Anonymous20231211		99.27 34	99.27 42	99.26 93	99.29 169	98.18 129	99.49 9	99.51 95	99.70 12	99.80 31	99.68 22	96.84 186	99.83 171	99.21 58	99.91 67	99.77 43

UnsupCasMVSNet_bld		97.30 263	96.92 273	98.45 226	99.28 170	96.78 238	96.20 338	99.27 199	95.42 332	98.28 258	98.30 300	93.16 301	99.71 263	94.99 309	97.37 392	98.87 303

EC-MVSNet		99.09 61	99.05 68	99.20 102	99.28 170	98.93 75	99.24 41	99.84 21	99.08 93	98.12 271	98.37 292	98.72 43	99.90 70	99.05 68	99.77 134	98.77 320

reproduce-ours		99.09 61	98.90 80	99.67 4	99.27 172	99.49 6	98.00 184	99.42 134	99.05 96	99.48 77	99.27 111	98.29 80	99.89 83	97.61 161	99.71 166	99.62 78

our_new_method		99.09 61	98.90 80	99.67 4	99.27 172	99.49 6	98.00 184	99.42 134	99.05 96	99.48 77	99.27 111	98.29 80	99.89 83	97.61 161	99.71 166	99.62 78

DPE-MVS		98.59 139	98.26 172	99.57 20	99.27 172	99.15 51	97.01 291	99.39 143	97.67 202	99.44 86	98.99 183	97.53 145	99.89 83	95.40 303	99.68 181	99.66 68
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 223	98.18 181	96.87 340	99.27 172	91.16 389	95.53 371	99.25 205	99.10 88	99.41 92	99.35 93	93.10 303	99.96 12	98.65 98	99.94 42	99.49 142

v1192		98.60 137	98.66 112	98.41 231	99.27 172	95.88 268	97.52 253	99.36 153	97.41 233	99.33 107	99.20 129	96.37 214	99.82 181	99.57 34	99.92 58	99.55 117

N_pmnet		97.63 237	97.17 258	98.99 138	99.27 172	97.86 165	95.98 349	93.41 413	95.25 337	99.47 81	98.90 204	95.63 245	99.85 136	96.91 205	99.73 153	99.27 230

FPMVS		93.44 371	92.23 378	97.08 329	99.25 178	97.86 165	95.61 368	97.16 364	92.90 382	93.76 415	98.65 254	75.94 410	95.66 429	79.30 428	97.49 385	97.73 393

new-patchmatchnet		98.35 170	98.74 96	97.18 324	99.24 179	92.23 372	96.42 325	99.48 106	98.30 153	99.69 45	99.53 60	97.44 154	99.82 181	98.84 83	99.77 134	99.49 142

MCST-MVS		98.00 205	97.63 232	99.10 117	99.24 179	98.17 130	96.89 300	98.73 307	95.66 323	97.92 284	97.70 340	97.17 169	99.66 294	96.18 271	99.23 285	99.47 159

UniMVSNet (Re)		98.87 89	98.71 103	99.35 72	99.24 179	98.73 87	97.73 225	99.38 145	98.93 109	99.12 139	98.73 237	96.77 193	99.86 123	98.63 100	99.80 118	99.46 161

jason		97.45 251	97.35 249	97.76 282	99.24 179	93.93 333	95.86 359	98.42 325	94.24 361	98.50 240	98.13 310	94.82 268	99.91 64	97.22 181	99.73 153	99.43 173
jason: jason.
IterMVS		97.73 229	98.11 190	96.57 350	99.24 179	90.28 398	95.52 373	99.21 214	98.86 115	99.33 107	99.33 99	93.11 302	99.94 39	98.49 108	99.94 42	99.48 152
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 145	98.62 118	98.32 241	99.22 184	95.58 276	97.51 255	99.45 121	97.16 261	99.45 85	99.24 121	96.12 223	99.85 136	99.60 32	99.88 81	99.55 117

ITE_SJBPF				98.87 156	99.22 184	98.48 106		99.35 158	97.50 221	98.28 258	98.60 265	97.64 134	99.35 380	93.86 345	99.27 277	98.79 318

h-mvs33		97.77 227	97.33 251	99.10 117	99.21 186	97.84 167	98.35 142	98.57 317	99.11 81	98.58 229	99.02 170	88.65 349	99.96 12	98.11 127	96.34 408	99.49 142

v144192		98.54 147	98.57 126	98.45 226	99.21 186	95.98 265	97.63 238	99.36 153	97.15 263	99.32 113	99.18 134	95.84 240	99.84 154	99.50 41	99.91 67	99.54 121

APDe-MVS		98.99 73	98.79 92	99.60 14	99.21 186	99.15 51	98.87 84	99.48 106	97.57 213	99.35 104	99.24 121	97.83 117	99.89 83	97.88 145	99.70 173	99.75 52
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 82	98.81 91	99.28 88	99.21 186	98.45 108	98.46 131	99.33 170	99.63 21	99.48 77	99.15 144	97.23 166	99.75 245	97.17 183	99.66 192	99.63 77

SR-MVS-dyc-post		98.81 98	98.55 127	99.57 20	99.20 190	99.38 12	98.48 129	99.30 185	98.64 124	98.95 169	98.96 192	97.49 152	99.86 123	96.56 244	99.39 258	99.45 165

RE-MVS-def			98.58 125		99.20 190	99.38 12	98.48 129	99.30 185	98.64 124	98.95 169	98.96 192	97.75 125		96.56 244	99.39 258	99.45 165

v1921920		98.54 147	98.60 123	98.38 234	99.20 190	95.76 273	97.56 248	99.36 153	97.23 255	99.38 98	99.17 138	96.02 226	99.84 154	99.57 34	99.90 73	99.54 121

thisisatest0530		95.27 340	94.45 351	97.74 285	99.19 193	94.37 316	97.86 205	90.20 425	97.17 260	98.22 261	97.65 342	73.53 413	99.90 70	96.90 210	99.35 264	98.95 288

Anonymous20240529		98.93 82	98.87 83	99.12 113	99.19 193	98.22 127	99.01 67	98.99 263	99.25 64	99.54 64	99.37 88	97.04 175	99.80 202	97.89 142	99.52 237	99.35 209

APD-MVS_3200maxsize		98.84 93	98.61 122	99.53 37	99.19 193	99.27 26	98.49 126	99.33 170	98.64 124	99.03 157	98.98 187	97.89 114	99.85 136	96.54 248	99.42 255	99.46 161

HQP_MVS		97.99 208	97.67 226	98.93 148	99.19 193	97.65 185	97.77 217	99.27 199	98.20 166	97.79 296	97.98 323	94.90 264	99.70 267	94.42 327	99.51 239	99.45 165

plane_prior7					99.19 193	97.87 164

ab-mvs		98.41 162	98.36 158	98.59 203	99.19 193	97.23 208	99.32 23	98.81 294	97.66 203	98.62 221	99.40 87	96.82 189	99.80 202	95.88 282	99.51 239	98.75 323

F-COLMAP		97.30 263	96.68 290	99.14 111	99.19 193	98.39 110	97.27 277	99.30 185	92.93 381	96.62 361	98.00 321	95.73 243	99.68 280	92.62 373	98.46 353	99.35 209

SR-MVS		98.71 111	98.43 147	99.57 20	99.18 200	99.35 16	98.36 141	99.29 193	98.29 156	98.88 186	98.85 217	97.53 145	99.87 115	96.14 273	99.31 270	99.48 152

UniMVSNet_NR-MVSNet		98.86 92	98.68 109	99.40 64	99.17 201	98.74 84	97.68 229	99.40 141	99.14 79	99.06 147	98.59 266	96.71 199	99.93 46	98.57 103	99.77 134	99.53 129

LF4IMVS		97.90 211	97.69 225	98.52 217	99.17 201	97.66 184	97.19 285	99.47 114	96.31 302	97.85 292	98.20 307	96.71 199	99.52 346	94.62 319	99.72 161	98.38 359

SMA-MVS		98.40 164	98.03 198	99.51 46	99.16 203	99.21 32	98.05 175	99.22 213	94.16 363	98.98 161	99.10 153	97.52 147	99.79 215	96.45 254	99.64 195	99.53 129
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 96	98.63 116	99.39 65	99.16 203	98.74 84	97.54 251	99.25 205	98.84 118	99.06 147	98.76 234	96.76 195	99.93 46	98.57 103	99.77 134	99.50 138

NR-MVSNet		98.95 80	98.82 89	99.36 66	99.16 203	98.72 89	99.22 42	99.20 216	99.10 88	99.72 39	98.76 234	96.38 213	99.86 123	98.00 137	99.82 103	99.50 138

MVS_111021_LR		98.30 178	98.12 189	98.83 160	99.16 203	98.03 149	96.09 346	99.30 185	97.58 212	98.10 273	98.24 303	98.25 82	99.34 381	96.69 230	99.65 193	99.12 262

DSMNet-mixed		97.42 254	97.60 234	96.87 340	99.15 207	91.46 379	98.54 116	99.12 238	92.87 383	97.58 309	99.63 36	96.21 219	99.90 70	95.74 291	99.54 230	99.27 230

D2MVS		97.84 224	97.84 216	97.83 274	99.14 208	94.74 305	96.94 295	98.88 278	95.84 320	98.89 183	98.96 192	94.40 280	99.69 271	97.55 164	99.95 34	99.05 268

pmmvs5		97.64 236	97.49 240	98.08 260	99.14 208	95.12 296	96.70 310	99.05 249	93.77 370	98.62 221	98.83 220	93.23 299	99.75 245	98.33 117	99.76 146	99.36 205

SPE-MVS-test		99.13 56	99.09 64	99.26 93	99.13 210	98.97 70	99.31 27	99.88 14	99.44 42	98.16 266	98.51 275	98.64 49	99.93 46	98.91 77	99.85 89	98.88 302

VDD-MVS		98.56 141	98.39 154	99.07 123	99.13 210	98.07 144	98.59 110	97.01 367	99.59 27	99.11 140	99.27 111	94.82 268	99.79 215	98.34 115	99.63 198	99.34 211

save fliter					99.11 212	97.97 155	96.53 317	99.02 257	98.24 159

APD-MVS		98.10 197	97.67 226	99.42 60	99.11 212	98.93 75	97.76 220	99.28 196	94.97 344	98.72 209	98.77 232	97.04 175	99.85 136	93.79 347	99.54 230	99.49 142
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 118	98.71 103	98.62 197	99.10 214	96.37 251	97.23 278	98.87 280	99.20 70	99.19 133	98.99 183	97.30 160	99.85 136	98.77 89	99.79 123	99.65 73

EI-MVSNet		98.40 164	98.51 132	98.04 265	99.10 214	94.73 306	97.20 282	98.87 280	98.97 105	99.06 147	99.02 170	96.00 228	99.80 202	98.58 101	99.82 103	99.60 87

CVMVSNet		96.25 314	97.21 257	93.38 407	99.10 214	80.56 435	97.20 282	98.19 336	96.94 273	99.00 159	99.02 170	89.50 342	99.80 202	96.36 260	99.59 212	99.78 40

EI-MVSNet-Vis-set		98.68 123	98.70 106	98.63 195	99.09 217	96.40 250	97.23 278	98.86 285	99.20 70	99.18 137	98.97 189	97.29 162	99.85 136	98.72 93	99.78 128	99.64 74

HPM-MVS++		98.10 197	97.64 231	99.48 53	99.09 217	99.13 59	97.52 253	98.75 304	97.46 229	96.90 349	97.83 333	96.01 227	99.84 154	95.82 289	99.35 264	99.46 161

DP-MVS Recon		97.33 261	96.92 273	98.57 207	99.09 217	97.99 151	96.79 303	99.35 158	93.18 377	97.71 300	98.07 318	95.00 263	99.31 385	93.97 340	99.13 301	98.42 356

MVS_111021_HR		98.25 186	98.08 194	98.75 178	99.09 217	97.46 195	95.97 350	99.27 199	97.60 211	97.99 282	98.25 302	98.15 97	99.38 376	96.87 213	99.57 221	99.42 176

BP-MVS1		97.40 256	96.97 269	98.71 184	99.07 221	96.81 234	98.34 144	97.18 362	98.58 134	98.17 263	98.61 263	84.01 381	99.94 39	98.97 74	99.78 128	99.37 198

9.14			97.78 218		99.07 221		97.53 252	99.32 172	95.53 329	98.54 236	98.70 243	97.58 139	99.76 238	94.32 332	99.46 249

PAPM_NR		96.82 295	96.32 306	98.30 244	99.07 221	96.69 242	97.48 258	98.76 301	95.81 321	96.61 362	96.47 378	94.12 289	99.17 398	90.82 400	97.78 379	99.06 267

TAMVS		98.24 187	98.05 196	98.80 165	99.07 221	97.18 215	97.88 201	98.81 294	96.66 288	99.17 138	99.21 127	94.81 270	99.77 232	96.96 203	99.88 81	99.44 169

CLD-MVS		97.49 247	97.16 259	98.48 223	99.07 221	97.03 222	94.71 394	99.21 214	94.46 355	98.06 276	97.16 364	97.57 140	99.48 358	94.46 324	99.78 128	98.95 288
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 56	99.10 62	99.24 98	99.06 226	99.15 51	99.36 19	99.88 14	99.36 53	98.21 262	98.46 283	98.68 47	99.93 46	99.03 70	99.85 89	98.64 335

thres100view900		94.19 357	93.67 362	95.75 374	99.06 226	91.35 382	98.03 178	94.24 408	98.33 149	97.40 325	94.98 408	79.84 397	99.62 308	83.05 421	98.08 370	96.29 415

thres600view7		94.45 352	93.83 359	96.29 358	99.06 226	91.53 378	97.99 188	94.24 408	98.34 148	97.44 323	95.01 406	79.84 397	99.67 283	84.33 419	98.23 359	97.66 396

plane_prior1					99.05 229

YYNet1		97.60 238	97.67 226	97.39 317	99.04 230	93.04 356	95.27 380	98.38 328	97.25 249	98.92 179	98.95 196	95.48 252	99.73 255	96.99 199	98.74 334	99.41 179

MDA-MVSNet_test_wron		97.60 238	97.66 229	97.41 316	99.04 230	93.09 352	95.27 380	98.42 325	97.26 248	98.88 186	98.95 196	95.43 253	99.73 255	97.02 196	98.72 336	99.41 179

MIMVSNet		96.62 302	96.25 310	97.71 289	99.04 230	94.66 309	99.16 51	96.92 373	97.23 255	97.87 289	99.10 153	86.11 364	99.65 299	91.65 384	99.21 289	98.82 307

PatchMatch-RL		97.24 269	96.78 284	98.61 200	99.03 233	97.83 168	96.36 328	99.06 246	93.49 375	97.36 329	97.78 334	95.75 242	99.49 355	93.44 356	98.77 333	98.52 344

GDP-MVS		97.50 244	97.11 263	98.67 188	99.02 234	96.85 232	98.16 159	99.71 42	98.32 151	98.52 239	98.54 270	83.39 385	99.95 24	98.79 85	99.56 224	99.19 249

ZD-MVS					99.01 235	98.84 78		99.07 245	94.10 365	98.05 278	98.12 312	96.36 215	99.86 123	92.70 372	99.19 293

CDPH-MVS		97.26 266	96.66 293	99.07 123	99.00 236	98.15 131	96.03 348	99.01 260	91.21 401	97.79 296	97.85 332	96.89 184	99.69 271	92.75 370	99.38 261	99.39 189

diffmvs		98.22 188	98.24 175	98.17 253	99.00 236	95.44 283	96.38 327	99.58 66	97.79 196	98.53 237	98.50 279	96.76 195	99.74 250	97.95 141	99.64 195	99.34 211
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WR-MVS		98.40 164	98.19 180	99.03 133	99.00 236	97.65 185	96.85 301	98.94 265	98.57 135	98.89 183	98.50 279	95.60 246	99.85 136	97.54 166	99.85 89	99.59 93

plane_prior6					98.99 239	97.70 183						94.90 264

xiu_mvs_v1_base_debu		97.86 218	98.17 182	96.92 337	98.98 240	93.91 334	96.45 321	99.17 228	97.85 192	98.41 248	97.14 366	98.47 63	99.92 55	98.02 134	99.05 307	96.92 408

xiu_mvs_v1_base		97.86 218	98.17 182	96.92 337	98.98 240	93.91 334	96.45 321	99.17 228	97.85 192	98.41 248	97.14 366	98.47 63	99.92 55	98.02 134	99.05 307	96.92 408

xiu_mvs_v1_base_debi		97.86 218	98.17 182	96.92 337	98.98 240	93.91 334	96.45 321	99.17 228	97.85 192	98.41 248	97.14 366	98.47 63	99.92 55	98.02 134	99.05 307	96.92 408

MVP-Stereo		98.08 200	97.92 210	98.57 207	98.96 243	96.79 235	97.90 199	99.18 224	96.41 298	98.46 243	98.95 196	95.93 237	99.60 316	96.51 250	98.98 321	99.31 222
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 164	98.68 109	97.54 305	98.96 243	97.99 151	97.88 201	99.36 153	98.20 166	99.63 56	99.04 167	98.76 40	95.33 431	96.56 244	99.74 150	99.31 222
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				98.91 152	98.94 245	97.76 177		98.76 301	87.58 418	96.75 357	98.10 314	94.80 271	99.78 226	92.73 371	99.00 316	99.20 244

USDC		97.41 255	97.40 244	97.44 314	98.94 245	93.67 344	95.17 383	99.53 91	94.03 367	98.97 165	99.10 153	95.29 255	99.34 381	95.84 288	99.73 153	99.30 225

tfpn200view9		94.03 361	93.44 364	95.78 373	98.93 247	91.44 380	97.60 243	94.29 406	97.94 184	97.10 335	94.31 415	79.67 399	99.62 308	83.05 421	98.08 370	96.29 415

testdata				98.09 257	98.93 247	95.40 285		98.80 296	90.08 409	97.45 322	98.37 292	95.26 256	99.70 267	93.58 352	98.95 324	99.17 256

thres400		94.14 359	93.44 364	96.24 361	98.93 247	91.44 380	97.60 243	94.29 406	97.94 184	97.10 335	94.31 415	79.67 399	99.62 308	83.05 421	98.08 370	97.66 396

TAPA-MVS	96.21 11	96.63 301	95.95 312	98.65 189	98.93 247	98.09 138	96.93 297	99.28 196	83.58 424	98.13 270	97.78 334	96.13 222	99.40 372	93.52 353	99.29 275	98.45 349
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 251	96.93 229	95.54 370	98.78 299	85.72 421	96.86 352	98.11 313	94.43 278			99.10 306	99.23 239

PVSNet_BlendedMVS		97.55 243	97.53 237	97.60 297	98.92 251	93.77 341	96.64 312	99.43 131	94.49 353	97.62 305	99.18 134	96.82 189	99.67 283	94.73 316	99.93 47	99.36 205

PVSNet_Blended		96.88 291	96.68 290	97.47 312	98.92 251	93.77 341	94.71 394	99.43 131	90.98 403	97.62 305	97.36 360	96.82 189	99.67 283	94.73 316	99.56 224	98.98 282

MSDG		97.71 231	97.52 238	98.28 246	98.91 254	96.82 233	94.42 404	99.37 149	97.65 204	98.37 253	98.29 301	97.40 156	99.33 383	94.09 338	99.22 286	98.68 333

Anonymous202405211		97.90 211	97.50 239	99.08 121	98.90 255	98.25 121	98.53 117	96.16 384	98.87 113	99.11 140	98.86 214	90.40 336	99.78 226	97.36 174	99.31 270	99.19 249

原ACMM1				98.35 239	98.90 255	96.25 255		98.83 293	92.48 387	96.07 378	98.10 314	95.39 254	99.71 263	92.61 374	98.99 318	99.08 264

GBi-Net		98.65 128	98.47 141	99.17 105	98.90 255	98.24 122	99.20 45	99.44 125	98.59 131	98.95 169	99.55 54	94.14 286	99.86 123	97.77 152	99.69 176	99.41 179

test1		98.65 128	98.47 141	99.17 105	98.90 255	98.24 122	99.20 45	99.44 125	98.59 131	98.95 169	99.55 54	94.14 286	99.86 123	97.77 152	99.69 176	99.41 179

FMVSNet2		98.49 155	98.40 151	98.75 178	98.90 255	97.14 219	98.61 108	99.13 237	98.59 131	99.19 133	99.28 109	94.14 286	99.82 181	97.97 139	99.80 118	99.29 227

OMC-MVS		97.88 215	97.49 240	99.04 132	98.89 260	98.63 91	96.94 295	99.25 205	95.02 342	98.53 237	98.51 275	97.27 163	99.47 361	93.50 355	99.51 239	99.01 276

MVSFormer		98.26 184	98.43 147	97.77 279	98.88 261	93.89 337	99.39 17	99.56 80	99.11 81	98.16 266	98.13 310	93.81 294	99.97 5	99.26 53	99.57 221	99.43 173

lupinMVS		97.06 281	96.86 277	97.65 292	98.88 261	93.89 337	95.48 374	97.97 342	93.53 373	98.16 266	97.58 346	93.81 294	99.91 64	96.77 221	99.57 221	99.17 256

dmvs_re		95.98 322	95.39 332	97.74 285	98.86 263	97.45 196	98.37 140	95.69 396	97.95 182	96.56 363	95.95 387	90.70 333	97.68 425	88.32 409	96.13 412	98.11 371

DELS-MVS		98.27 182	98.20 178	98.48 223	98.86 263	96.70 241	95.60 369	99.20 216	97.73 199	98.45 244	98.71 240	97.50 149	99.82 181	98.21 121	99.59 212	98.93 293
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		97.89 213	97.98 203	97.60 297	98.86 263	94.35 317	96.21 337	99.44 125	97.45 231	99.06 147	98.88 211	97.99 109	99.28 391	94.38 331	99.58 217	99.18 252

LCM-MVSNet-Re		98.64 130	98.48 139	99.11 115	98.85 266	98.51 104	98.49 126	99.83 24	98.37 146	99.69 45	99.46 73	98.21 89	99.92 55	94.13 337	99.30 273	98.91 297

pmmvs4		97.58 241	97.28 252	98.51 218	98.84 267	96.93 229	95.40 378	98.52 320	93.60 372	98.61 223	98.65 254	95.10 260	99.60 316	96.97 202	99.79 123	98.99 281

NP-MVS					98.84 267	97.39 200					96.84 369

sss		97.21 271	96.93 271	98.06 262	98.83 269	95.22 292	96.75 307	98.48 322	94.49 353	97.27 331	97.90 329	92.77 311	99.80 202	96.57 240	99.32 268	99.16 259

PVSNet	93.40 17	95.67 331	95.70 317	95.57 378	98.83 269	88.57 405	92.50 421	97.72 347	92.69 385	96.49 370	96.44 379	93.72 297	99.43 368	93.61 350	99.28 276	98.71 326

MVE	83.40 22	92.50 384	91.92 386	94.25 394	98.83 269	91.64 377	92.71 420	83.52 434	95.92 318	86.46 432	95.46 400	95.20 257	95.40 430	80.51 426	98.64 345	95.73 423
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 365	93.91 357	93.39 406	98.82 272	81.72 433	97.76 220	95.28 398	98.60 130	96.54 364	96.66 373	65.85 429	99.62 308	96.65 233	98.99 318	98.82 307

ambc				98.24 249	98.82 272	95.97 266	98.62 107	99.00 262		99.27 119	99.21 127	96.99 180	99.50 352	96.55 247	99.50 246	99.26 233

旧先验1					98.82 272	97.45 196		98.76 301			98.34 296	95.50 251			99.01 315	99.23 239

test_vis1_rt		97.75 228	97.72 224	97.83 274	98.81 275	96.35 252	97.30 273	99.69 46	94.61 351	97.87 289	98.05 319	96.26 218	98.32 419	98.74 91	98.18 362	98.82 307

WTY-MVS		96.67 299	96.27 309	97.87 272	98.81 275	94.61 311	96.77 305	97.92 344	94.94 345	97.12 334	97.74 337	91.11 329	99.82 181	93.89 343	98.15 366	99.18 252

3Dnovator+	97.89 3	98.69 118	98.51 132	99.24 98	98.81 275	98.40 109	99.02 66	99.19 220	98.99 102	98.07 275	99.28 109	97.11 173	99.84 154	96.84 216	99.32 268	99.47 159

QAPM		97.31 262	96.81 283	98.82 161	98.80 278	97.49 193	99.06 62	99.19 220	90.22 407	97.69 302	99.16 140	96.91 183	99.90 70	90.89 399	99.41 256	99.07 266

VNet		98.42 161	98.30 166	98.79 168	98.79 279	97.29 204	98.23 150	98.66 311	99.31 58	98.85 191	98.80 226	94.80 271	99.78 226	98.13 126	99.13 301	99.31 222

DPM-MVS		96.32 311	95.59 323	98.51 218	98.76 280	97.21 212	94.54 403	98.26 331	91.94 392	96.37 371	97.25 362	93.06 305	99.43 368	91.42 389	98.74 334	98.89 299

3Dnovator	98.27 2	98.81 98	98.73 98	99.05 130	98.76 280	97.81 174	99.25 40	99.30 185	98.57 135	98.55 234	99.33 99	97.95 111	99.90 70	97.16 184	99.67 187	99.44 169

PLC	94.65 16	96.51 304	95.73 316	98.85 158	98.75 282	97.91 161	96.42 325	99.06 246	90.94 404	95.59 384	97.38 358	94.41 279	99.59 320	90.93 397	98.04 375	99.05 268
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 293	96.75 286	97.08 329	98.74 283	93.33 350	96.71 309	98.26 331	96.72 285	98.44 245	97.37 359	95.20 257	99.47 361	91.89 379	97.43 389	98.44 352

hse-mvs2		97.46 249	97.07 264	98.64 191	98.73 284	97.33 202	97.45 261	97.64 353	99.11 81	98.58 229	97.98 323	88.65 349	99.79 215	98.11 127	97.39 391	98.81 312

CDS-MVSNet		97.69 232	97.35 249	98.69 185	98.73 284	97.02 223	96.92 299	98.75 304	95.89 319	98.59 227	98.67 249	92.08 321	99.74 250	96.72 227	99.81 107	99.32 218
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EIA-MVS		98.00 205	97.74 221	98.80 165	98.72 286	98.09 138	98.05 175	99.60 63	97.39 235	96.63 360	95.55 395	97.68 128	99.80 202	96.73 226	99.27 277	98.52 344

LFMVS		97.20 272	96.72 287	98.64 191	98.72 286	96.95 227	98.93 78	94.14 410	99.74 10	98.78 200	99.01 179	84.45 376	99.73 255	97.44 170	99.27 277	99.25 234

new_pmnet		96.99 288	96.76 285	97.67 290	98.72 286	94.89 301	95.95 354	98.20 334	92.62 386	98.55 234	98.54 270	94.88 267	99.52 346	93.96 341	99.44 254	98.59 341

Fast-Effi-MVS+		97.67 234	97.38 246	98.57 207	98.71 289	97.43 198	97.23 278	99.45 121	94.82 348	96.13 375	96.51 375	98.52 61	99.91 64	96.19 269	98.83 330	98.37 361

TEST9					98.71 289	98.08 142	95.96 352	99.03 254	91.40 398	95.85 381	97.53 348	96.52 206	99.76 238

train_agg		97.10 278	96.45 303	99.07 123	98.71 289	98.08 142	95.96 352	99.03 254	91.64 393	95.85 381	97.53 348	96.47 208	99.76 238	93.67 349	99.16 296	99.36 205

TSAR-MVS + GP.		98.18 193	97.98 203	98.77 175	98.71 289	97.88 163	96.32 331	98.66 311	96.33 300	99.23 130	98.51 275	97.48 153	99.40 372	97.16 184	99.46 249	99.02 275

FA-MVS(test-final)		96.99 288	96.82 281	97.50 309	98.70 293	94.78 303	99.34 20	96.99 368	95.07 341	98.48 242	99.33 99	88.41 352	99.65 299	96.13 275	98.92 327	98.07 374

AUN-MVS		96.24 316	95.45 328	98.60 202	98.70 293	97.22 210	97.38 265	97.65 351	95.95 317	95.53 391	97.96 327	82.11 393	99.79 215	96.31 262	97.44 388	98.80 317

our_test_3		97.39 257	97.73 223	96.34 356	98.70 293	89.78 401	94.61 400	98.97 264	96.50 293	99.04 154	98.85 217	95.98 233	99.84 154	97.26 179	99.67 187	99.41 179

ppachtmachnet_test		97.50 244	97.74 221	96.78 346	98.70 293	91.23 388	94.55 402	99.05 249	96.36 299	99.21 131	98.79 228	96.39 211	99.78 226	96.74 224	99.82 103	99.34 211

PCF-MVS	92.86 18	94.36 353	93.00 371	98.42 230	98.70 293	97.56 190	93.16 419	99.11 240	79.59 428	97.55 312	97.43 355	92.19 318	99.73 255	79.85 427	99.45 251	97.97 380
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 210	98.02 199	97.58 299	98.69 298	94.10 324	98.13 162	98.90 274	97.95 182	97.32 330	99.58 44	95.95 236	98.75 414	96.41 256	99.22 286	99.87 20

ETV-MVS		98.03 202	97.86 215	98.56 211	98.69 298	98.07 144	97.51 255	99.50 97	98.10 174	97.50 317	95.51 396	98.41 69	99.88 97	96.27 265	99.24 282	97.71 395

test_prior				98.95 145	98.69 298	97.95 159		99.03 254					99.59 320			99.30 225

mvsmamba		97.57 242	97.26 253	98.51 218	98.69 298	96.73 240	98.74 92	97.25 361	97.03 269	97.88 288	99.23 125	90.95 330	99.87 115	96.61 236	99.00 316	98.91 297

agg_prior					98.68 302	97.99 151		99.01 260		95.59 384			99.77 232

test_8					98.67 303	98.01 150	95.91 358	99.02 257	91.64 393	95.79 383	97.50 351	96.47 208	99.76 238

HQP-NCC					98.67 303		96.29 333		96.05 310	95.55 387

ACMP_Plane					98.67 303		96.29 333		96.05 310	95.55 387

CNVR-MVS		98.17 195	97.87 214	99.07 123	98.67 303	98.24 122	97.01 291	98.93 268	97.25 249	97.62 305	98.34 296	97.27 163	99.57 328	96.42 255	99.33 267	99.39 189

HQP-MVS		97.00 287	96.49 302	98.55 212	98.67 303	96.79 235	96.29 333	99.04 252	96.05 310	95.55 387	96.84 369	93.84 292	99.54 340	92.82 367	99.26 280	99.32 218

MM		98.22 188	97.99 202	98.91 152	98.66 308	96.97 224	97.89 200	94.44 404	99.54 30	98.95 169	99.14 147	93.50 298	99.92 55	99.80 14	99.96 27	99.85 26

test_fmvs1		97.72 230	97.94 208	97.07 331	98.66 308	92.39 367	97.68 229	99.81 28	95.20 340	99.54 64	99.44 78	91.56 326	99.41 371	99.78 18	99.77 134	99.40 188

balanced_conf03		98.63 132	98.72 100	98.38 234	98.66 308	96.68 243	98.90 80	99.42 134	98.99 102	98.97 165	99.19 130	95.81 241	99.85 136	98.77 89	99.77 134	98.60 338

thres200		93.72 367	93.14 369	95.46 382	98.66 308	91.29 384	96.61 314	94.63 403	97.39 235	96.83 353	93.71 418	79.88 396	99.56 331	82.40 424	98.13 367	95.54 424

wuyk23d		96.06 318	97.62 233	91.38 411	98.65 312	98.57 98	98.85 87	96.95 371	96.86 278	99.90 13	99.16 140	99.18 18	98.40 418	89.23 407	99.77 134	77.18 431

NCCC		97.86 218	97.47 243	99.05 130	98.61 313	98.07 144	96.98 293	98.90 274	97.63 205	97.04 339	97.93 328	95.99 232	99.66 294	95.31 304	98.82 332	99.43 173

DeepC-MVS_fast	96.85 6	98.30 178	98.15 186	98.75 178	98.61 313	97.23 208	97.76 220	99.09 243	97.31 243	98.75 206	98.66 252	97.56 141	99.64 302	96.10 276	99.55 228	99.39 189
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 369	92.09 380	97.75 283	98.60 315	94.40 315	97.32 271	95.26 399	97.56 215	96.79 356	95.50 397	53.57 437	99.77 232	95.26 305	98.97 322	99.08 264

thisisatest0515		94.12 360	93.16 368	96.97 335	98.60 315	92.90 357	93.77 415	90.61 423	94.10 365	96.91 346	95.87 390	74.99 411	99.80 202	94.52 322	99.12 304	98.20 367

GA-MVS		95.86 325	95.32 335	97.49 310	98.60 315	94.15 323	93.83 414	97.93 343	95.49 330	96.68 358	97.42 356	83.21 386	99.30 387	96.22 267	98.55 351	99.01 276

dmvs_testset		92.94 379	92.21 379	95.13 386	98.59 318	90.99 391	97.65 235	92.09 419	96.95 272	94.00 411	93.55 419	92.34 317	96.97 428	72.20 430	92.52 426	97.43 403

OPU-MVS				98.82 161	98.59 318	98.30 118	98.10 168				98.52 274	98.18 91	98.75 414	94.62 319	99.48 248	99.41 179

MSLP-MVS++		98.02 203	98.14 188	97.64 294	98.58 320	95.19 293	97.48 258	99.23 212	97.47 224	97.90 286	98.62 261	97.04 175	98.81 412	97.55 164	99.41 256	98.94 292

test12				98.93 148	98.58 320	97.83 168		98.66 311		96.53 365		95.51 250	99.69 271		99.13 301	99.27 230

CL-MVSNet_self_test		97.44 252	97.22 256	98.08 260	98.57 322	95.78 272	94.30 407	98.79 297	96.58 291	98.60 225	98.19 308	94.74 274	99.64 302	96.41 256	98.84 329	98.82 307

PS-MVSNAJ		97.08 280	97.39 245	96.16 367	98.56 323	92.46 365	95.24 382	98.85 288	97.25 249	97.49 318	95.99 386	98.07 100	99.90 70	96.37 258	98.67 344	96.12 420

CNLPA		97.17 275	96.71 288	98.55 212	98.56 323	98.05 148	96.33 330	98.93 268	96.91 275	97.06 338	97.39 357	94.38 281	99.45 365	91.66 383	99.18 295	98.14 370

xiu_mvs_v2_base		97.16 276	97.49 240	96.17 365	98.54 325	92.46 365	95.45 375	98.84 289	97.25 249	97.48 319	96.49 376	98.31 78	99.90 70	96.34 261	98.68 343	96.15 419

alignmvs		97.35 259	96.88 276	98.78 171	98.54 325	98.09 138	97.71 226	97.69 349	99.20 70	97.59 308	95.90 389	88.12 354	99.55 335	98.18 123	98.96 323	98.70 329

FE-MVS		95.66 332	94.95 345	97.77 279	98.53 327	95.28 289	99.40 16	96.09 387	93.11 379	97.96 283	99.26 116	79.10 403	99.77 232	92.40 376	98.71 338	98.27 365

Effi-MVS+		98.02 203	97.82 217	98.62 197	98.53 327	97.19 214	97.33 270	99.68 51	97.30 244	96.68 358	97.46 354	98.56 59	99.80 202	96.63 234	98.20 361	98.86 304

baseline1		95.96 323	95.44 329	97.52 307	98.51 329	93.99 331	98.39 138	96.09 387	98.21 162	98.40 252	97.76 336	86.88 356	99.63 305	95.42 302	89.27 429	98.95 288

MVS_Test		98.18 193	98.36 158	97.67 290	98.48 330	94.73 306	98.18 155	99.02 257	97.69 201	98.04 279	99.11 150	97.22 167	99.56 331	98.57 103	98.90 328	98.71 326

MGCFI-Net		98.34 171	98.28 168	98.51 218	98.47 331	97.59 189	98.96 74	99.48 106	99.18 76	97.40 325	95.50 397	98.66 48	99.50 352	98.18 123	98.71 338	98.44 352

BH-RMVSNet		96.83 293	96.58 298	97.58 299	98.47 331	94.05 325	96.67 311	97.36 356	96.70 287	97.87 289	97.98 323	95.14 259	99.44 367	90.47 402	98.58 350	99.25 234

sasdasda		98.34 171	98.26 172	98.58 204	98.46 333	97.82 171	98.96 74	99.46 117	99.19 74	97.46 320	95.46 400	98.59 55	99.46 363	98.08 130	98.71 338	98.46 346

canonicalmvs		98.34 171	98.26 172	98.58 204	98.46 333	97.82 171	98.96 74	99.46 117	99.19 74	97.46 320	95.46 400	98.59 55	99.46 363	98.08 130	98.71 338	98.46 346

MVS-HIRNet		94.32 354	95.62 320	90.42 412	98.46 333	75.36 436	96.29 333	89.13 427	95.25 337	95.38 393	99.75 13	92.88 308	99.19 397	94.07 339	99.39 258	96.72 413

PHI-MVS		98.29 181	97.95 206	99.34 75	98.44 336	99.16 47	98.12 165	99.38 145	96.01 314	98.06 276	98.43 286	97.80 122	99.67 283	95.69 294	99.58 217	99.20 244

DVP-MVS++		98.90 86	98.70 106	99.51 46	98.43 337	99.15 51	99.43 12	99.32 172	98.17 169	99.26 123	99.02 170	98.18 91	99.88 97	97.07 193	99.45 251	99.49 142

MSC_two_6792asdad				99.32 83	98.43 337	98.37 113		98.86 285					99.89 83	97.14 187	99.60 208	99.71 55

No_MVS				99.32 83	98.43 337	98.37 113		98.86 285					99.89 83	97.14 187	99.60 208	99.71 55

Fast-Effi-MVS+-dtu		98.27 182	98.09 191	98.81 163	98.43 337	98.11 135	97.61 242	99.50 97	98.64 124	97.39 327	97.52 350	98.12 99	99.95 24	96.90 210	98.71 338	98.38 359

OpenMVS_ROB	95.38 14	95.84 327	95.18 340	97.81 276	98.41 341	97.15 218	97.37 267	98.62 315	83.86 423	98.65 217	98.37 292	94.29 284	99.68 280	88.41 408	98.62 348	96.60 414

DeepPCF-MVS	96.93 5	98.32 175	98.01 200	99.23 100	98.39 342	98.97 70	95.03 387	99.18 224	96.88 276	99.33 107	98.78 230	98.16 95	99.28 391	96.74 224	99.62 201	99.44 169

Patchmatch-test		96.55 303	96.34 305	97.17 326	98.35 343	93.06 353	98.40 137	97.79 345	97.33 240	98.41 248	98.67 249	83.68 384	99.69 271	95.16 307	99.31 270	98.77 320

AdaColmap		97.14 277	96.71 288	98.46 225	98.34 344	97.80 175	96.95 294	98.93 268	95.58 327	96.92 344	97.66 341	95.87 239	99.53 342	90.97 396	99.14 299	98.04 375

OpenMVS	96.65 7	97.09 279	96.68 290	98.32 241	98.32 345	97.16 217	98.86 86	99.37 149	89.48 411	96.29 373	99.15 144	96.56 204	99.90 70	92.90 364	99.20 290	97.89 383

MG-MVS		96.77 296	96.61 295	97.26 322	98.31 346	93.06 353	95.93 355	98.12 339	96.45 297	97.92 284	98.73 237	93.77 296	99.39 374	91.19 394	99.04 310	99.33 216

test_yl		96.69 297	96.29 307	97.90 269	98.28 347	95.24 290	97.29 274	97.36 356	98.21 162	98.17 263	97.86 330	86.27 360	99.55 335	94.87 313	98.32 355	98.89 299

DCV-MVSNet		96.69 297	96.29 307	97.90 269	98.28 347	95.24 290	97.29 274	97.36 356	98.21 162	98.17 263	97.86 330	86.27 360	99.55 335	94.87 313	98.32 355	98.89 299

CHOSEN 280x420		95.51 337	95.47 326	95.65 377	98.25 349	88.27 408	93.25 418	98.88 278	93.53 373	94.65 402	97.15 365	86.17 362	99.93 46	97.41 172	99.93 47	98.73 325

SCA		96.41 310	96.66 293	95.67 375	98.24 350	88.35 407	95.85 361	96.88 374	96.11 308	97.67 303	98.67 249	93.10 303	99.85 136	94.16 333	99.22 286	98.81 312

DeepMVS_CX				93.44 405	98.24 350	94.21 320		94.34 405	64.28 431	91.34 425	94.87 412	89.45 343	92.77 432	77.54 429	93.14 425	93.35 427

MS-PatchMatch		97.68 233	97.75 220	97.45 313	98.23 352	93.78 340	97.29 274	98.84 289	96.10 309	98.64 218	98.65 254	96.04 225	99.36 377	96.84 216	99.14 299	99.20 244

BH-w/o		95.13 343	94.89 347	95.86 370	98.20 353	91.31 383	95.65 367	97.37 355	93.64 371	96.52 366	95.70 393	93.04 306	99.02 403	88.10 410	95.82 415	97.24 406

mvs_anonymous		97.83 226	98.16 185	96.87 340	98.18 354	91.89 374	97.31 272	98.90 274	97.37 237	98.83 194	99.46 73	96.28 217	99.79 215	98.90 78	98.16 365	98.95 288

miper_lstm_enhance		97.18 274	97.16 259	97.25 323	98.16 355	92.85 358	95.15 385	99.31 177	97.25 249	98.74 208	98.78 230	90.07 337	99.78 226	97.19 182	99.80 118	99.11 263

RRT-MVS		97.88 215	97.98 203	97.61 296	98.15 356	93.77 341	98.97 73	99.64 57	99.16 78	98.69 211	99.42 80	91.60 324	99.89 83	97.63 160	98.52 352	99.16 259

ET-MVSNet_ETH3D		94.30 356	93.21 367	97.58 299	98.14 357	94.47 314	94.78 393	93.24 415	94.72 349	89.56 427	95.87 390	78.57 406	99.81 195	96.91 205	97.11 400	98.46 346

ADS-MVSNet2		95.43 338	94.98 343	96.76 347	98.14 357	91.74 375	97.92 196	97.76 346	90.23 405	96.51 367	98.91 201	85.61 367	99.85 136	92.88 365	96.90 401	98.69 330

ADS-MVSNet		95.24 341	94.93 346	96.18 364	98.14 357	90.10 400	97.92 196	97.32 359	90.23 405	96.51 367	98.91 201	85.61 367	99.74 250	92.88 365	96.90 401	98.69 330

c3_l		97.36 258	97.37 247	97.31 318	98.09 360	93.25 351	95.01 388	99.16 231	97.05 266	98.77 203	98.72 239	92.88 308	99.64 302	96.93 204	99.76 146	99.05 268

FMVSNet3		97.50 244	97.24 255	98.29 245	98.08 361	95.83 270	97.86 205	98.91 273	97.89 189	98.95 169	98.95 196	87.06 355	99.81 195	97.77 152	99.69 176	99.23 239

PAPM		91.88 393	90.34 396	96.51 351	98.06 362	92.56 363	92.44 422	97.17 363	86.35 419	90.38 426	96.01 385	86.61 358	99.21 396	70.65 432	95.43 417	97.75 392

Effi-MVS+-dtu		98.26 184	97.90 212	99.35 72	98.02 363	99.49 6	98.02 180	99.16 231	98.29 156	97.64 304	97.99 322	96.44 210	99.95 24	96.66 232	98.93 326	98.60 338

eth_miper_zixun_eth		97.23 270	97.25 254	97.17 326	98.00 364	92.77 360	94.71 394	99.18 224	97.27 247	98.56 232	98.74 236	91.89 322	99.69 271	97.06 195	99.81 107	99.05 268

HY-MVS	95.94 13	95.90 324	95.35 334	97.55 304	97.95 365	94.79 302	98.81 91	96.94 372	92.28 390	95.17 395	98.57 268	89.90 339	99.75 245	91.20 393	97.33 396	98.10 372

UGNet		98.53 149	98.45 144	98.79 168	97.94 366	96.96 226	99.08 58	98.54 318	99.10 88	96.82 354	99.47 72	96.55 205	99.84 154	98.56 106	99.94 42	99.55 117
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		96.47 308	95.70 317	98.79 168	97.92 367	99.12 61	98.28 146	98.60 316	92.16 391	95.54 390	96.17 383	94.77 273	99.52 346	89.62 405	98.23 359	97.72 394
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		96.86 292	96.55 299	97.79 277	97.91 368	94.21 320	97.56 248	98.87 280	97.49 223	99.06 147	99.05 165	80.72 394	99.80 202	98.44 110	99.82 103	99.37 198

API-MVS		97.04 283	96.91 275	97.42 315	97.88 369	98.23 126	98.18 155	98.50 321	97.57 213	97.39 327	96.75 371	96.77 193	99.15 400	90.16 403	99.02 314	94.88 425

myMVS_eth3d28		92.92 380	92.31 376	94.77 389	97.84 370	87.59 412	96.19 339	96.11 386	97.08 265	94.27 405	93.49 421	66.07 428	98.78 413	91.78 381	97.93 378	97.92 382

miper_ehance_all_eth		97.06 281	97.03 266	97.16 328	97.83 371	93.06 353	94.66 397	99.09 243	95.99 315	98.69 211	98.45 284	92.73 313	99.61 315	96.79 218	99.03 311	98.82 307

cl____		97.02 284	96.83 280	97.58 299	97.82 372	94.04 327	94.66 397	99.16 231	97.04 267	98.63 219	98.71 240	88.68 348	99.69 271	97.00 197	99.81 107	99.00 280

DIV-MVS_self_test		97.02 284	96.84 279	97.58 299	97.82 372	94.03 328	94.66 397	99.16 231	97.04 267	98.63 219	98.71 240	88.69 346	99.69 271	97.00 197	99.81 107	99.01 276

CANet		97.87 217	97.76 219	98.19 252	97.75 374	95.51 279	96.76 306	99.05 249	97.74 198	96.93 343	98.21 306	95.59 247	99.89 83	97.86 147	99.93 47	99.19 249

UBG		93.25 374	92.32 375	96.04 369	97.72 375	90.16 399	95.92 357	95.91 391	96.03 313	93.95 413	93.04 424	69.60 418	99.52 346	90.72 401	97.98 376	98.45 349

mvsany_test1		97.60 238	97.54 236	97.77 279	97.72 375	95.35 286	95.36 379	97.13 365	94.13 364	99.71 41	99.33 99	97.93 112	99.30 387	97.60 163	98.94 325	98.67 334

PVSNet_0	89.98 21	91.15 394	90.30 397	93.70 402	97.72 375	84.34 426	90.24 425	97.42 354	90.20 408	93.79 414	93.09 423	90.90 332	98.89 411	86.57 416	72.76 432	97.87 385

CR-MVSNet		96.28 313	95.95 312	97.28 320	97.71 378	94.22 318	98.11 166	98.92 271	92.31 389	96.91 346	99.37 88	85.44 370	99.81 195	97.39 173	97.36 394	97.81 388

RPMNet		97.02 284	96.93 271	97.30 319	97.71 378	94.22 318	98.11 166	99.30 185	99.37 50	96.91 346	99.34 97	86.72 357	99.87 115	97.53 167	97.36 394	97.81 388

ETVMVS		92.60 383	91.08 392	97.18 324	97.70 380	93.65 346	96.54 315	95.70 394	96.51 292	94.68 401	92.39 427	61.80 434	99.50 352	86.97 413	97.41 390	98.40 357

pmmvs3		95.03 345	94.40 352	96.93 336	97.70 380	92.53 364	95.08 386	97.71 348	88.57 415	97.71 300	98.08 317	79.39 401	99.82 181	96.19 269	99.11 305	98.43 354

baseline2		93.73 366	92.83 372	96.42 354	97.70 380	91.28 385	96.84 302	89.77 426	93.96 369	92.44 421	95.93 388	79.14 402	99.77 232	92.94 363	96.76 405	98.21 366

WBMVS		95.18 342	94.78 348	96.37 355	97.68 383	89.74 402	95.80 363	98.73 307	97.54 218	98.30 254	98.44 285	70.06 416	99.82 181	96.62 235	99.87 84	99.54 121

tpm		94.67 350	94.34 354	95.66 376	97.68 383	88.42 406	97.88 201	94.90 400	94.46 355	96.03 380	98.56 269	78.66 404	99.79 215	95.88 282	95.01 419	98.78 319

CANet_DTU		97.26 266	97.06 265	97.84 273	97.57 385	94.65 310	96.19 339	98.79 297	97.23 255	95.14 396	98.24 303	93.22 300	99.84 154	97.34 175	99.84 93	99.04 272

testing11		93.08 377	92.02 382	96.26 360	97.56 386	90.83 394	96.32 331	95.70 394	96.47 296	92.66 420	93.73 417	64.36 432	99.59 320	93.77 348	97.57 383	98.37 361

tpm2		93.09 376	92.58 374	94.62 391	97.56 386	86.53 415	97.66 233	95.79 393	86.15 420	94.07 410	98.23 305	75.95 409	99.53 342	90.91 398	96.86 404	97.81 388

testing91		93.32 372	92.27 377	96.47 353	97.54 388	91.25 386	96.17 343	96.76 376	97.18 259	93.65 416	93.50 420	65.11 431	99.63 305	93.04 362	97.45 387	98.53 343

TR-MVS		95.55 335	95.12 341	96.86 343	97.54 388	93.94 332	96.49 320	96.53 381	94.36 360	97.03 341	96.61 374	94.26 285	99.16 399	86.91 415	96.31 409	97.47 402

testing99		93.04 378	91.98 385	96.23 362	97.53 390	90.70 396	96.35 329	95.94 390	96.87 277	93.41 417	93.43 422	63.84 433	99.59 320	93.24 360	97.19 397	98.40 357

1314		95.74 329	95.60 321	96.17 365	97.53 390	92.75 361	98.07 172	98.31 330	91.22 400	94.25 406	96.68 372	95.53 248	99.03 402	91.64 385	97.18 398	96.74 412

CostFormer		93.97 362	93.78 360	94.51 392	97.53 390	85.83 418	97.98 189	95.96 389	89.29 413	94.99 398	98.63 259	78.63 405	99.62 308	94.54 321	96.50 406	98.09 373

FMVSNet5		96.01 320	95.20 339	98.41 231	97.53 390	96.10 257	98.74 92	99.50 97	97.22 258	98.03 280	99.04 167	69.80 417	99.88 97	97.27 178	99.71 166	99.25 234

PMMVS		96.51 304	95.98 311	98.09 257	97.53 390	95.84 269	94.92 390	98.84 289	91.58 395	96.05 379	95.58 394	95.68 244	99.66 294	95.59 298	98.09 369	98.76 322

reproduce_monomvs		95.00 347	95.25 336	94.22 395	97.51 395	83.34 427	97.86 205	98.44 323	98.51 140	99.29 116	99.30 105	67.68 422	99.56 331	98.89 80	99.81 107	99.77 43

PAPR		95.29 339	94.47 350	97.75 283	97.50 396	95.14 295	94.89 391	98.71 309	91.39 399	95.35 394	95.48 399	94.57 276	99.14 401	84.95 418	97.37 392	98.97 285

testing222		91.96 391	90.37 395	96.72 348	97.47 397	92.59 362	96.11 345	94.76 401	96.83 279	92.90 419	92.87 425	57.92 435	99.55 335	86.93 414	97.52 384	98.00 379

PatchT		96.65 300	96.35 304	97.54 305	97.40 398	95.32 288	97.98 189	96.64 378	99.33 55	96.89 350	99.42 80	84.32 378	99.81 195	97.69 159	97.49 385	97.48 401

tpm cat1		93.29 373	93.13 370	93.75 401	97.39 399	84.74 421	97.39 264	97.65 351	83.39 425	94.16 407	98.41 287	82.86 389	99.39 374	91.56 387	95.35 418	97.14 407

PatchmatchNet		95.58 334	95.67 319	95.30 385	97.34 400	87.32 413	97.65 235	96.65 377	95.30 336	97.07 337	98.69 245	84.77 373	99.75 245	94.97 311	98.64 345	98.83 306
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 259	96.97 269	98.50 222	97.31 401	96.47 249	98.18 155	98.92 271	98.95 108	98.78 200	99.37 88	85.44 370	99.85 136	95.96 280	99.83 100	99.17 256

LS3D		98.63 132	98.38 156	99.36 66	97.25 402	99.38 12	99.12 57	99.32 172	99.21 68	98.44 245	98.88 211	97.31 159	99.80 202	96.58 238	99.34 266	98.92 294

IB-MVS	91.63 19	92.24 389	90.90 393	96.27 359	97.22 403	91.24 387	94.36 406	93.33 414	92.37 388	92.24 423	94.58 414	66.20 427	99.89 83	93.16 361	94.63 421	97.66 396
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		92.38 386	91.76 389	94.21 396	97.16 404	84.65 422	95.42 377	88.45 428	95.96 316	96.17 374	95.84 392	66.36 425	99.71 263	91.87 380	98.64 345	98.28 364

tpmrst		95.07 344	95.46 327	93.91 399	97.11 405	84.36 425	97.62 239	96.96 370	94.98 343	96.35 372	98.80 226	85.46 369	99.59 320	95.60 297	96.23 410	97.79 391

Syy-MVS		96.04 319	95.56 325	97.49 310	97.10 406	94.48 313	96.18 341	96.58 379	95.65 324	94.77 399	92.29 428	91.27 328	99.36 377	98.17 125	98.05 373	98.63 336

myMVS_eth3d		91.92 392	90.45 394	96.30 357	97.10 406	90.90 392	96.18 341	96.58 379	95.65 324	94.77 399	92.29 428	53.88 436	99.36 377	89.59 406	98.05 373	98.63 336

MDTV_nov1_ep13			95.22 338		97.06 408	83.20 428	97.74 223	96.16 384	94.37 359	96.99 342	98.83 220	83.95 382	99.53 342	93.90 342	97.95 377

MVS		93.19 375	92.09 380	96.50 352	96.91 409	94.03 328	98.07 172	98.06 341	68.01 430	94.56 404	96.48 377	95.96 235	99.30 387	83.84 420	96.89 403	96.17 417

E-PMN		94.17 358	94.37 353	93.58 403	96.86 410	85.71 419	90.11 427	97.07 366	98.17 169	97.82 295	97.19 363	84.62 375	98.94 407	89.77 404	97.68 382	96.09 421

JIA-IIPM		95.52 336	95.03 342	97.00 332	96.85 411	94.03 328	96.93 297	95.82 392	99.20 70	94.63 403	99.71 19	83.09 387	99.60 316	94.42 327	94.64 420	97.36 405

EMVS		93.83 364	94.02 356	93.23 408	96.83 412	84.96 420	89.77 428	96.32 383	97.92 186	97.43 324	96.36 382	86.17 362	98.93 408	87.68 411	97.73 381	95.81 422

cl22		95.79 328	95.39 332	96.98 334	96.77 413	92.79 359	94.40 405	98.53 319	94.59 352	97.89 287	98.17 309	82.82 390	99.24 393	96.37 258	99.03 311	98.92 294

WB-MVSnew		95.73 330	95.57 324	96.23 362	96.70 414	90.70 396	96.07 347	93.86 411	95.60 326	97.04 339	95.45 403	96.00 228	99.55 335	91.04 395	98.31 357	98.43 354

dp		93.47 370	93.59 363	93.13 409	96.64 415	81.62 434	97.66 233	96.42 382	92.80 384	96.11 376	98.64 257	78.55 407	99.59 320	93.31 358	92.18 428	98.16 369

MonoMVSNet		96.25 314	96.53 301	95.39 383	96.57 416	91.01 390	98.82 90	97.68 350	98.57 135	98.03 280	99.37 88	90.92 331	97.78 424	94.99 309	93.88 424	97.38 404

test-LLR		93.90 363	93.85 358	94.04 397	96.53 417	84.62 423	94.05 411	92.39 417	96.17 305	94.12 408	95.07 404	82.30 391	99.67 283	95.87 285	98.18 362	97.82 386

test-mter		92.33 388	91.76 389	94.04 397	96.53 417	84.62 423	94.05 411	92.39 417	94.00 368	94.12 408	95.07 404	65.63 430	99.67 283	95.87 285	98.18 362	97.82 386

TESTMET0.1,1		92.19 390	91.77 388	93.46 404	96.48 419	82.80 430	94.05 411	91.52 422	94.45 357	94.00 411	94.88 410	66.65 424	99.56 331	95.78 290	98.11 368	98.02 376

MVS_0304		97.44 252	97.01 268	98.72 183	96.42 420	96.74 239	97.20 282	91.97 420	98.46 143	98.30 254	98.79 228	92.74 312	99.91 64	99.30 50	99.94 42	99.52 132

miper_enhance_ethall		96.01 320	95.74 315	96.81 344	96.41 421	92.27 371	93.69 416	98.89 277	91.14 402	98.30 254	97.35 361	90.58 334	99.58 326	96.31 262	99.03 311	98.60 338

tpmvs		95.02 346	95.25 336	94.33 393	96.39 422	85.87 416	98.08 170	96.83 375	95.46 331	95.51 392	98.69 245	85.91 365	99.53 342	94.16 333	96.23 410	97.58 399

CMPMVS	75.91 23	96.29 312	95.44 329	98.84 159	96.25 423	98.69 90	97.02 290	99.12 238	88.90 414	97.83 293	98.86 214	89.51 341	98.90 410	91.92 378	99.51 239	98.92 294
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 351	93.69 361	96.99 333	96.05 424	93.61 348	94.97 389	93.49 412	96.17 305	97.57 311	94.88 410	82.30 391	99.01 405	93.60 351	94.17 423	98.37 361

EPMVS		93.72 367	93.27 366	95.09 388	96.04 425	87.76 410	98.13 162	85.01 433	94.69 350	96.92 344	98.64 257	78.47 408	99.31 385	95.04 308	96.46 407	98.20 367

cascas		94.79 349	94.33 355	96.15 368	96.02 426	92.36 369	92.34 423	99.26 204	85.34 422	95.08 397	94.96 409	92.96 307	98.53 417	94.41 330	98.59 349	97.56 400

MVStest1		95.86 325	95.60 321	96.63 349	95.87 427	91.70 376	97.93 193	98.94 265	98.03 176	99.56 60	99.66 29	71.83 414	98.26 420	99.35 47	99.24 282	99.91 13

gg-mvs-nofinetune		92.37 387	91.20 391	95.85 371	95.80 428	92.38 368	99.31 27	81.84 435	99.75 8	91.83 424	99.74 15	68.29 419	99.02 403	87.15 412	97.12 399	96.16 418

gm-plane-assit					94.83 429	81.97 432			88.07 417		94.99 407		99.60 316	91.76 382

GG-mvs-BLEND				94.76 390	94.54 430	92.13 373	99.31 27	80.47 436		88.73 430	91.01 430	67.59 423	98.16 423	82.30 425	94.53 422	93.98 426

UWE-MVS-28		90.22 395	89.28 398	93.02 410	94.50 431	82.87 429	96.52 318	87.51 429	95.21 339	92.36 422	96.04 384	71.57 415	98.25 421	72.04 431	97.77 380	97.94 381

EPNet_dtu		94.93 348	94.78 348	95.38 384	93.58 432	87.68 411	96.78 304	95.69 396	97.35 239	89.14 429	98.09 316	88.15 353	99.49 355	94.95 312	99.30 273	98.98 282
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 399	75.95 402	77.12 415	92.39 433	67.91 439	90.16 426	59.44 440	82.04 426	89.42 428	94.67 413	49.68 438	81.74 433	48.06 433	77.66 431	81.72 429

KD-MVS_2432*1600		92.87 381	91.99 383	95.51 380	91.37 434	89.27 403	94.07 409	98.14 337	95.42 332	97.25 332	96.44 379	67.86 420	99.24 393	91.28 391	96.08 413	98.02 376

miper_refine_blended		92.87 381	91.99 383	95.51 380	91.37 434	89.27 403	94.07 409	98.14 337	95.42 332	97.25 332	96.44 379	67.86 420	99.24 393	91.28 391	96.08 413	98.02 376

EPNet		96.14 317	95.44 329	98.25 247	90.76 436	95.50 280	97.92 196	94.65 402	98.97 105	92.98 418	98.85 217	89.12 344	99.87 115	95.99 278	99.68 181	99.39 189
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 400	68.95 403	70.34 416	87.68 437	65.00 440	91.11 424	59.90 439	69.02 429	74.46 434	88.89 431	48.58 439	68.03 435	28.61 434	72.33 433	77.99 430

test_method		79.78 397	79.50 400	80.62 413	80.21 438	45.76 441	70.82 429	98.41 327	31.08 433	80.89 433	97.71 338	84.85 372	97.37 426	91.51 388	80.03 430	98.75 323

tmp_tt		78.77 398	78.73 401	78.90 414	58.45 439	74.76 438	94.20 408	78.26 437	39.16 432	86.71 431	92.82 426	80.50 395	75.19 434	86.16 417	92.29 427	86.74 428

testmvs		17.12 402	20.53 405	6.87 418	12.05 440	4.20 443	93.62 417	6.73 441	4.62 436	10.41 436	24.33 433	8.28 441	3.56 437	9.69 436	15.07 434	12.86 433

test123		17.04 403	20.11 406	7.82 417	10.25 441	4.91 442	94.80 392	4.47 442	4.93 435	10.00 437	24.28 434	9.69 440	3.64 436	10.14 435	12.43 435	14.92 432

mmdepth		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

monomultidepth		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

test_blank		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

eth-test2					0.00 442

eth-test					0.00 442

uanet_test		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

DCPMVS		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

cdsmvs_eth3d_5k		24.66 401	32.88 404	0.00 419	0.00 442	0.00 444	0.00 430	99.10 241	0.00 437	0.00 438	97.58 346	99.21 17	0.00 438	0.00 437	0.00 436	0.00 434

pcd_1.5k_mvsjas		8.17 404	10.90 407	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	98.07 100	0.00 438	0.00 437	0.00 436	0.00 434

sosnet-low-res		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

sosnet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uncertanet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

Regformer		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

ab-mvs-re		8.12 405	10.83 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	97.48 352	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uanet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

WAC-MVS						90.90 392								91.37 390

PC_three_1452									93.27 376	99.40 95	98.54 270	98.22 87	97.00 427	95.17 306	99.45 251	99.49 142

test_241102_TWO								99.30 185	98.03 176	99.26 123	99.02 170	97.51 148	99.88 97	96.91 205	99.60 208	99.66 68

test_0728_THIRD									98.17 169	99.08 145	99.02 170	97.89 114	99.88 97	97.07 193	99.71 166	99.70 60

GSMVS																98.81 312

sam_mvs1												84.74 374				98.81 312

sam_mvs												84.29 380

MTGPA								99.20 216

test_post1							97.59 245				20.48 436	83.07 388	99.66 294	94.16 333

test_post											21.25 435	83.86 383	99.70 267

patchmatchnet-post											98.77 232	84.37 377	99.85 136

MTMP							97.93 193	91.91 421

test9_res														93.28 359	99.15 298	99.38 196

agg_prior2														92.50 375	99.16 296	99.37 198

test_prior4						97.97 155	95.86 359

test_prior2							95.74 365		96.48 295	96.11 376	97.63 344	95.92 238		94.16 333	99.20 290

旧先验2							95.76 364		88.56 416	97.52 315			99.66 294	94.48 323

新几何2							95.93 355

无先验							95.74 365	98.74 306	89.38 412				99.73 255	92.38 377		99.22 243

原ACMM2							95.53 371

testdata2													99.79 215	92.80 369

segment_acmp												97.02 178

testdata1							95.44 376		96.32 301

plane_prior5								99.27 199					99.70 267	94.42 327	99.51 239	99.45 165

plane_prior4											97.98 323

plane_prior3						97.78 176			97.41 233	97.79 296

plane_prior2							97.77 217		98.20 166

plane_prior						97.65 185	97.07 289		96.72 285						99.36 262

n2								0.00 443

nn								0.00 443

door-mid								99.57 73

test11								98.87 280

door								99.41 138

HQP5-MVS						96.79 235

BP-MVS														92.82 367

HQP4-MVS										95.56 386			99.54 340			99.32 218

HQP3-MVS								99.04 252							99.26 280

HQP2-MVS												93.84 292

MDTV_nov1_ep13_2view						74.92 437	97.69 228		90.06 410	97.75 299		85.78 366		93.52 353		98.69 330

ACMMP++_ref															99.77 134

ACMMP++															99.68 181

Test By Simon												96.52 206

High-resolution multi-view benchmark