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 12	100.00 1	99.85 24

Gipuma		99.03 65	99.16 50	98.64 187	99.94 2	98.51 104	99.32 23	99.75 36	99.58 29	98.60 219	99.62 37	98.22 82	99.51 344	97.70 151	99.73 147	97.89 374
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 25	99.31 34	99.53 37	99.91 3	98.98 69	99.63 7	99.58 61	99.44 41	99.78 29	99.76 12	96.39 205	99.92 53	99.44 39	99.92 56	99.68 58

pmmvs6		99.67 3	99.70 3	99.60 14	99.90 4	99.27 26	99.53 8	99.76 33	99.64 19	99.84 21	99.83 4	99.50 8	99.87 110	99.36 41	99.92 56	99.64 68

PS-MVSNAJss		99.46 14	99.49 13	99.35 72	99.90 4	98.15 130	99.20 45	99.65 51	99.48 34	99.92 8	99.71 19	98.07 95	99.96 12	99.53 33	100.00 1	99.93 11

testf1		99.25 36	99.16 50	99.51 46	99.89 6	99.63 4	98.71 99	99.69 42	98.90 108	99.43 82	99.35 91	98.86 28	99.67 277	97.81 142	99.81 101	99.24 231

APD_test2		99.25 36	99.16 50	99.51 46	99.89 6	99.63 4	98.71 99	99.69 42	98.90 108	99.43 82	99.35 91	98.86 28	99.67 277	97.81 142	99.81 101	99.24 231

ANet_high		99.57 7	99.67 5	99.28 87	99.89 6	98.09 137	99.14 54	99.93 5	99.82 5	99.93 6	99.81 6	99.17 18	99.94 37	99.31 44	100.00 1	99.82 29

anonymousdsp		99.51 11	99.47 17	99.62 9	99.88 9	99.08 67	99.34 20	99.69 42	98.93 106	99.65 48	99.72 18	98.93 26	99.95 24	99.11 57	100.00 1	99.82 29

v7n		99.53 9	99.57 10	99.41 62	99.88 9	98.54 102	99.45 11	99.61 57	99.66 17	99.68 42	99.66 29	98.44 63	99.95 24	99.73 20	99.96 25	99.75 48

mvs_tets		99.63 5	99.67 5	99.49 51	99.88 9	98.61 94	99.34 20	99.71 38	99.27 60	99.90 12	99.74 15	99.68 4	99.97 5	99.55 32	99.99 5	99.88 19

test_fmvsmconf0.01_n		99.57 7	99.63 7	99.36 66	99.87 12	98.13 133	98.08 170	99.95 1	99.45 39	99.98 2	99.75 13	99.80 1	99.97 5	99.82 8	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 50	99.09 88	99.89 15	99.68 22	99.53 7	99.97 5	99.50 36	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 75	99.11 78	99.70 38	99.73 17	99.00 22	99.97 5	99.26 48	99.98 12	99.89 16

MIMVSNet1		99.38 24	99.32 32	99.55 27	99.86 14	99.19 41	99.41 14	99.59 59	99.59 27	99.71 36	99.57 46	97.12 165	99.90 68	99.21 53	99.87 78	99.54 115

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 31	99.63 21	99.78 29	99.67 27	99.48 9	99.81 189	99.30 45	99.97 20	99.77 39
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 61	99.90 3	99.86 19	99.78 10	99.58 6	99.95 24	99.00 66	99.95 32	99.78 37

SixPastTwentyTwo		98.75 102	98.62 112	99.16 107	99.83 18	97.96 157	99.28 37	98.20 328	99.37 48	99.70 38	99.65 33	92.65 308	99.93 44	99.04 63	99.84 87	99.60 81

Baseline_NR-MVSNet		98.98 71	98.86 81	99.36 66	99.82 19	98.55 99	97.47 255	99.57 68	99.37 48	99.21 126	99.61 40	96.76 189	99.83 165	98.06 126	99.83 94	99.71 51

pm-mvs1		99.44 15	99.48 15	99.33 80	99.80 20	98.63 91	99.29 33	99.63 53	99.30 57	99.65 48	99.60 42	99.16 20	99.82 175	99.07 60	99.83 94	99.56 104

TransMVSNet (Re)		99.44 15	99.47 17	99.36 66	99.80 20	98.58 97	99.27 39	99.57 68	99.39 46	99.75 33	99.62 37	99.17 18	99.83 165	99.06 61	99.62 195	99.66 62

K. test v3		98.00 199	97.66 223	99.03 132	99.79 22	97.56 189	99.19 49	92.47 408	99.62 24	99.52 65	99.66 29	89.61 334	99.96 12	99.25 50	99.81 101	99.56 104

test_fmvsmconf0.1_n		99.49 12	99.54 11	99.34 75	99.78 23	98.11 134	97.77 216	99.90 11	99.33 53	99.97 3	99.66 29	99.71 3	99.96 12	99.79 14	99.99 5	99.96 8

APD_test1		98.83 89	98.66 106	99.34 75	99.78 23	99.47 9	98.42 136	99.45 116	98.28 152	98.98 156	99.19 126	97.76 118	99.58 319	96.57 233	99.55 222	98.97 279

test_vis3_rt		99.14 50	99.17 48	99.07 122	99.78 23	98.38 111	98.92 79	99.94 2	97.80 189	99.91 11	99.67 27	97.15 164	98.91 402	99.76 17	99.56 218	99.92 12

EGC-MVSNET		85.24 387	80.54 390	99.34 75	99.77 26	99.20 38	99.08 58	99.29 187	12.08 425	20.84 426	99.42 79	97.55 136	99.85 130	97.08 186	99.72 155	98.96 281

Anonymous20240521		98.69 113	98.87 78	98.16 250	99.77 26	95.11 292	99.08 58	99.44 120	99.34 52	99.33 102	99.55 54	94.10 284	99.94 37	99.25 50	99.96 25	99.42 170

FC-MVSNet-test		99.27 33	99.25 43	99.34 75	99.77 26	98.37 113	99.30 32	99.57 68	99.61 26	99.40 90	99.50 64	97.12 165	99.85 130	99.02 65	99.94 40	99.80 33

test_vis1_n		98.31 171	98.50 128	97.73 282	99.76 29	94.17 317	98.68 102	99.91 9	96.31 294	99.79 28	99.57 46	92.85 304	99.42 363	99.79 14	99.84 87	99.60 81

test_fmvs3		99.12 56	99.41 21	98.25 242	99.76 29	95.07 293	99.05 64	99.94 2	97.78 191	99.82 23	99.84 3	98.56 54	99.71 257	99.96 1	99.96 25	99.97 4

XXY-MVS		99.14 50	99.15 55	99.10 116	99.76 29	97.74 178	98.85 87	99.62 54	98.48 137	99.37 95	99.49 69	98.75 36	99.86 118	98.20 116	99.80 112	99.71 51

TDRefinement		99.42 20	99.38 24	99.55 27	99.76 29	99.33 20	99.68 6	99.71 38	99.38 47	99.53 63	99.61 40	98.64 44	99.80 196	98.24 113	99.84 87	99.52 126

fmvsm_s_conf0.1_n_a		99.17 45	99.30 37	98.80 163	99.75 33	96.59 242	97.97 192	99.86 16	98.22 155	99.88 17	99.71 19	98.59 50	99.84 148	99.73 20	99.98 12	99.98 3

tt0805		98.69 113	98.62 112	98.90 153	99.75 33	99.30 21	99.15 53	96.97 363	98.86 111	98.87 184	97.62 339	98.63 46	98.96 399	99.41 40	98.29 351	98.45 342

test_vis1_n_1920		98.40 158	98.92 73	96.81 338	99.74 35	90.76 389	98.15 160	99.91 9	98.33 143	99.89 15	99.55 54	95.07 255	99.88 93	99.76 17	99.93 45	99.79 34

FOURS1					99.73 36	99.67 3	99.43 12	99.54 83	99.43 43	99.26 118

PEN-MVS		99.41 21	99.34 29	99.62 9	99.73 36	99.14 56	99.29 33	99.54 83	99.62 24	99.56 55	99.42 79	98.16 90	99.96 12	98.78 80	99.93 45	99.77 39

lessismore_v0				98.97 140	99.73 36	97.53 191		86.71 422		99.37 95	99.52 63	89.93 332	99.92 53	98.99 67	99.72 155	99.44 163

SteuartSystems-ACMMP		98.79 95	98.54 123	99.54 30	99.73 36	99.16 47	98.23 150	99.31 171	97.92 180	98.90 175	98.90 199	98.00 101	99.88 93	96.15 265	99.72 155	99.58 93
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 189	98.15 180	98.22 245	99.73 36	95.15 289	97.36 262	99.68 47	94.45 348	98.99 155	99.27 108	96.87 179	99.94 37	97.13 183	99.91 63	99.57 98

Vis-MVSNet		99.34 26	99.36 26	99.27 90	99.73 36	98.26 120	99.17 50	99.78 31	99.11 78	99.27 114	99.48 70	98.82 31	99.95 24	98.94 70	99.93 45	99.59 87
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
SSC-MVS		98.71 106	98.74 90	98.62 193	99.72 42	96.08 258	98.74 92	98.64 308	99.74 10	99.67 44	99.24 117	94.57 270	99.95 24	99.11 57	99.24 276	99.82 29

test_f		98.67 121	98.87 78	98.05 259	99.72 42	95.59 270	98.51 123	99.81 26	96.30 296	99.78 29	99.82 5	96.14 215	98.63 408	99.82 8	99.93 45	99.95 9

ACMH	96.65 7	99.25 36	99.24 44	99.26 92	99.72 42	98.38 111	99.07 61	99.55 79	98.30 147	99.65 48	99.45 76	99.22 15	99.76 232	98.44 104	99.77 128	99.64 68
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.1_n		99.16 48	99.33 30	98.64 187	99.71 45	96.10 253	97.87 204	99.85 18	98.56 133	99.90 12	99.68 22	98.69 41	99.85 130	99.72 22	99.98 12	99.97 4

PS-CasMVS		99.40 22	99.33 30	99.62 9	99.71 45	99.10 64	99.29 33	99.53 86	99.53 31	99.46 77	99.41 83	98.23 79	99.95 24	98.89 74	99.95 32	99.81 32

DTE-MVSNet		99.43 19	99.35 27	99.66 7	99.71 45	99.30 21	99.31 27	99.51 90	99.64 19	99.56 55	99.46 72	98.23 79	99.97 5	98.78 80	99.93 45	99.72 50

WR-MVS_H		99.33 27	99.22 45	99.65 8	99.71 45	99.24 29	99.32 23	99.55 79	99.46 38	99.50 71	99.34 95	97.30 154	99.93 44	98.90 72	99.93 45	99.77 39

HPM-MVS_fast		99.01 66	98.82 84	99.57 20	99.71 45	99.35 16	99.00 69	99.50 92	97.33 233	98.94 171	98.86 209	98.75 36	99.82 175	97.53 161	99.71 160	99.56 104

ACMH+	96.62 9	99.08 63	99.00 66	99.33 80	99.71 45	98.83 79	98.60 109	99.58 61	99.11 78	99.53 63	99.18 130	98.81 32	99.67 277	96.71 223	99.77 128	99.50 132

PMVS	91.26 20	97.86 212	97.94 202	97.65 286	99.71 45	97.94 159	98.52 118	98.68 304	98.99 99	97.52 309	99.35 91	97.41 149	98.18 413	91.59 378	99.67 181	96.82 402
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FIs		99.14 50	99.09 59	99.29 86	99.70 52	98.28 119	99.13 55	99.52 89	99.48 34	99.24 123	99.41 83	96.79 186	99.82 175	98.69 90	99.88 75	99.76 44

VPNet		98.87 84	98.83 83	99.01 135	99.70 52	97.62 187	98.43 134	99.35 153	99.47 37	99.28 112	99.05 160	96.72 192	99.82 175	98.09 123	99.36 256	99.59 87

fmvsm_s_conf0.1_n_2		99.20 43	99.38 24	98.65 185	99.69 54	96.08 258	97.49 252	99.90 11	99.53 31	99.88 17	99.64 34	98.51 57	99.90 68	99.83 7	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 168	98.68 103	97.27 315	99.69 54	92.29 364	98.03 178	99.85 18	97.62 200	99.96 4	99.62 37	93.98 285	99.74 244	99.52 35	99.86 82	99.79 34

MP-MVS-pluss		98.57 135	98.23 170	99.60 14	99.69 54	99.35 16	97.16 280	99.38 140	94.87 338	98.97 160	98.99 178	98.01 100	99.88 93	97.29 171	99.70 167	99.58 93
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 40	99.32 32	98.96 141	99.68 57	97.35 200	98.84 89	99.48 101	99.69 13	99.63 51	99.68 22	99.03 21	99.96 12	97.97 133	99.92 56	99.57 98

sd_testset		99.28 32	99.31 34	99.19 103	99.68 57	98.06 146	99.41 14	99.30 179	99.69 13	99.63 51	99.68 22	99.25 14	99.96 12	97.25 174	99.92 56	99.57 98

test_fmvs1_n		98.09 193	98.28 162	97.52 301	99.68 57	93.47 343	98.63 105	99.93 5	95.41 327	99.68 42	99.64 34	91.88 317	99.48 351	99.82 8	99.87 78	99.62 72

CHOSEN 1792x2688		97.49 241	97.14 256	98.54 211	99.68 57	96.09 256	96.50 312	99.62 54	91.58 386	98.84 187	98.97 184	92.36 310	99.88 93	96.76 216	99.95 32	99.67 61

tfpnnormal		98.90 81	98.90 75	98.91 150	99.67 61	97.82 170	99.00 69	99.44 120	99.45 39	99.51 70	99.24 117	98.20 85	99.86 118	95.92 274	99.69 170	99.04 266

MTAPA		98.88 83	98.64 109	99.61 12	99.67 61	99.36 15	98.43 134	99.20 210	98.83 115	98.89 177	98.90 199	96.98 175	99.92 53	97.16 178	99.70 167	99.56 104

test_fmvsmvis_n_1920		99.26 35	99.49 13	98.54 211	99.66 63	96.97 222	98.00 184	99.85 18	99.24 62	99.92 8	99.50 64	99.39 11	99.95 24	99.89 3	99.98 12	98.71 319

mvs5depth		99.30 29	99.59 9	98.44 224	99.65 64	95.35 281	99.82 3	99.94 2	99.83 4	99.42 85	99.94 2	98.13 93	99.96 12	99.63 26	99.96 25	100.00 1

fmvsm_l_conf0.5_n_a		99.19 44	99.27 40	98.94 144	99.65 64	97.05 218	97.80 212	99.76 33	98.70 119	99.78 29	99.11 146	98.79 34	99.95 24	99.85 5	99.96 25	99.83 26

WB-MVS		98.52 147	98.55 121	98.43 225	99.65 64	95.59 270	98.52 118	98.77 294	99.65 18	99.52 65	99.00 177	94.34 276	99.93 44	98.65 92	98.83 323	99.76 44

CP-MVSNet		99.21 41	99.09 59	99.56 25	99.65 64	98.96 74	99.13 55	99.34 159	99.42 44	99.33 102	99.26 112	97.01 173	99.94 37	98.74 85	99.93 45	99.79 34

HPM-MVS		98.79 95	98.53 124	99.59 18	99.65 64	99.29 23	99.16 51	99.43 126	96.74 276	98.61 217	98.38 285	98.62 47	99.87 110	96.47 245	99.67 181	99.59 87
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 130	98.36 152	99.42 60	99.65 64	99.42 11	98.55 114	99.57 68	97.72 194	98.90 175	99.26 112	96.12 217	99.52 339	95.72 285	99.71 160	99.32 212

fmvsm_l_conf0.5_n		99.21 41	99.28 39	99.02 134	99.64 70	97.28 204	97.82 209	99.76 33	98.73 116	99.82 23	99.09 152	98.81 32	99.95 24	99.86 4	99.96 25	99.83 26

test_fmvsmconf_n		99.44 15	99.48 15	99.31 85	99.64 70	98.10 136	97.68 227	99.84 21	99.29 58	99.92 8	99.57 46	99.60 5	99.96 12	99.74 19	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 127	98.49 132	99.06 128	99.64 70	97.90 161	98.51 123	98.94 259	96.96 263	99.24 123	98.89 205	97.83 111	99.81 189	96.88 206	99.49 241	99.48 146
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 91	98.72 94	99.12 112	99.64 70	98.54 102	97.98 189	99.68 47	97.62 200	99.34 101	99.18 130	97.54 137	99.77 226	97.79 144	99.74 144	99.04 266

KD-MVS_self_test		99.25 36	99.18 47	99.44 59	99.63 74	99.06 68	98.69 101	99.54 83	99.31 55	99.62 54	99.53 60	97.36 152	99.86 118	99.24 52	99.71 160	99.39 183

EU-MVSNet		97.66 229	98.50 128	95.13 380	99.63 74	85.84 410	98.35 142	98.21 327	98.23 154	99.54 59	99.46 72	95.02 256	99.68 274	98.24 113	99.87 78	99.87 20

HyFIR lowres test		97.19 267	96.60 291	98.96 141	99.62 76	97.28 204	95.17 374	99.50 92	94.21 353	99.01 153	98.32 293	86.61 352	99.99 2	97.10 185	99.84 87	99.60 81

mmtdpeth		99.30 29	99.42 20	98.92 149	99.58 77	96.89 229	99.48 10	99.92 7	99.92 2	98.26 254	99.80 9	98.33 72	99.91 62	99.56 31	99.95 32	99.97 4

ACMMP_NAP		98.75 102	98.48 133	99.57 20	99.58 77	99.29 23	97.82 209	99.25 199	96.94 265	98.78 194	99.12 145	98.02 99	99.84 148	97.13 183	99.67 181	99.59 87

nrg030		99.40 22	99.35 27	99.54 30	99.58 77	99.13 59	98.98 72	99.48 101	99.68 15	99.46 77	99.26 112	98.62 47	99.73 249	99.17 56	99.92 56	99.76 44

VDDNet		98.21 184	97.95 200	99.01 135	99.58 77	97.74 178	99.01 67	97.29 354	99.67 16	98.97 160	99.50 64	90.45 329	99.80 196	97.88 139	99.20 284	99.48 146

COLMAP_ROB	96.50 10	98.99 68	98.85 82	99.41 62	99.58 77	99.10 64	98.74 92	99.56 75	99.09 88	99.33 102	99.19 126	98.40 65	99.72 256	95.98 272	99.76 140	99.42 170
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 27	99.45 19	98.99 137	99.57 82	97.73 180	97.93 193	99.83 23	99.22 63	99.93 6	99.30 103	99.42 10	99.96 12	99.85 5	99.99 5	99.29 221

ZNCC-MVS		98.68 118	98.40 145	99.54 30	99.57 82	99.21 32	98.46 131	99.29 187	97.28 239	98.11 266	98.39 283	98.00 101	99.87 110	96.86 209	99.64 189	99.55 111

MSP-MVS		98.40 158	98.00 195	99.61 12	99.57 82	99.25 28	98.57 112	99.35 153	97.55 210	99.31 110	97.71 332	94.61 269	99.88 93	96.14 266	99.19 287	99.70 56
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		98.32 169	98.39 148	98.13 251	99.57 82	95.54 273	97.78 214	99.49 99	97.37 230	99.19 128	97.65 336	98.96 24	99.49 348	96.50 244	98.99 312	99.34 205

MP-MVS		98.46 152	98.09 185	99.54 30	99.57 82	99.22 31	98.50 125	99.19 214	97.61 203	97.58 303	98.66 246	97.40 150	99.88 93	94.72 311	99.60 202	99.54 115
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 106	98.46 137	99.47 56	99.57 82	98.97 70	98.23 150	99.48 101	96.60 281	99.10 138	99.06 153	98.71 39	99.83 165	95.58 292	99.78 122	99.62 72

LGP-MVS_train				99.47 56	99.57 82	98.97 70		99.48 101	96.60 281	99.10 138	99.06 153	98.71 39	99.83 165	95.58 292	99.78 122	99.62 72

IS-MVSNet		98.19 186	97.90 206	99.08 120	99.57 82	97.97 154	99.31 27	98.32 323	99.01 98	98.98 156	99.03 164	91.59 319	99.79 209	95.49 294	99.80 112	99.48 146

dcpmvs_2		98.78 97	99.11 56	97.78 273	99.56 90	93.67 339	99.06 62	99.86 16	99.50 33	99.66 45	99.26 112	97.21 162	99.99 2	98.00 131	99.91 63	99.68 58

test_0402		98.76 101	98.71 97	98.93 146	99.56 90	98.14 132	98.45 133	99.34 159	99.28 59	98.95 164	98.91 196	98.34 71	99.79 209	95.63 289	99.91 63	98.86 298

EPP-MVSNet		98.30 172	98.04 191	99.07 122	99.56 90	97.83 167	99.29 33	98.07 334	99.03 96	98.59 221	99.13 144	92.16 313	99.90 68	96.87 207	99.68 175	99.49 136

ACMMP		98.75 102	98.50 128	99.52 42	99.56 90	99.16 47	98.87 84	99.37 144	97.16 254	98.82 191	99.01 174	97.71 121	99.87 110	96.29 257	99.69 170	99.54 115
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 58	99.20 46	98.78 169	99.55 94	96.59 242	97.79 213	99.82 25	98.21 156	99.81 26	99.53 60	98.46 61	99.84 148	99.70 23	99.97 20	99.90 15

fmvsm_s_conf0.5_n		99.09 59	99.26 42	98.61 196	99.55 94	96.09 256	97.74 221	99.81 26	98.55 134	99.85 20	99.55 54	98.60 49	99.84 148	99.69 25	99.98 12	99.89 16

FMVSNet1		99.17 45	99.17 48	99.17 104	99.55 94	98.24 122	99.20 45	99.44 120	99.21 65	99.43 82	99.55 54	97.82 114	99.86 118	98.42 106	99.89 73	99.41 173

Vis-MVSNet (Re-imp)		97.46 243	97.16 253	98.34 235	99.55 94	96.10 253	98.94 77	98.44 317	98.32 145	98.16 260	98.62 255	88.76 339	99.73 249	93.88 337	99.79 117	99.18 246

ACMM	96.08 12	98.91 79	98.73 92	99.48 53	99.55 94	99.14 56	98.07 172	99.37 144	97.62 200	99.04 149	98.96 187	98.84 30	99.79 209	97.43 165	99.65 187	99.49 136
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 110	98.97 70	97.89 266	99.54 99	94.05 320	98.55 114	99.92 7	96.78 274	99.72 34	99.78 10	96.60 197	99.67 277	99.91 2	99.90 69	99.94 10

mPP-MVS		98.64 125	98.34 155	99.54 30	99.54 99	99.17 43	98.63 105	99.24 204	97.47 217	98.09 268	98.68 241	97.62 130	99.89 80	96.22 260	99.62 195	99.57 98

XVG-ACMP-BASELINE		98.56 136	98.34 155	99.22 100	99.54 99	98.59 96	97.71 224	99.46 112	97.25 242	98.98 156	98.99 178	97.54 137	99.84 148	95.88 275	99.74 144	99.23 233

region2R		98.69 113	98.40 145	99.54 30	99.53 102	99.17 43	98.52 118	99.31 171	97.46 222	98.44 239	98.51 269	97.83 111	99.88 93	96.46 246	99.58 211	99.58 93

PGM-MVS		98.66 122	98.37 151	99.55 27	99.53 102	99.18 42	98.23 150	99.49 99	97.01 262	98.69 205	98.88 206	98.00 101	99.89 80	95.87 278	99.59 206	99.58 93

Patchmatch-RL test		97.26 260	97.02 261	97.99 263	99.52 104	95.53 274	96.13 335	99.71 38	97.47 217	99.27 114	99.16 136	84.30 373	99.62 302	97.89 136	99.77 128	98.81 305

ACMMPR		98.70 110	98.42 143	99.54 30	99.52 104	99.14 56	98.52 118	99.31 171	97.47 217	98.56 226	98.54 264	97.75 119	99.88 93	96.57 233	99.59 206	99.58 93

GST-MVS		98.61 131	98.30 160	99.52 42	99.51 106	99.20 38	98.26 148	99.25 199	97.44 225	98.67 208	98.39 283	97.68 122	99.85 130	96.00 270	99.51 233	99.52 126

Anonymous20231206		98.21 184	98.21 171	98.20 246	99.51 106	95.43 279	98.13 162	99.32 166	96.16 299	98.93 172	98.82 218	96.00 222	99.83 165	97.32 170	99.73 147	99.36 199

ACMP	95.32 15	98.41 156	98.09 185	99.36 66	99.51 106	98.79 82	97.68 227	99.38 140	95.76 314	98.81 193	98.82 218	98.36 67	99.82 175	94.75 308	99.77 128	99.48 146
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DVP-MVS		98.77 100	98.52 125	99.52 42	99.50 109	99.21 32	98.02 180	98.84 283	97.97 174	99.08 140	99.02 165	97.61 131	99.88 93	96.99 193	99.63 192	99.48 146
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	99.50 109	99.23 30	98.02 180	99.32 166					99.88 93	96.99 193	99.63 192	99.68 58

test0726					99.50 109	99.21 32	98.17 158	99.35 153	97.97 174	99.26 118	99.06 153	97.61 131

AllTest		98.44 154	98.20 172	99.16 107	99.50 109	98.55 99	98.25 149	99.58 61	96.80 272	98.88 180	99.06 153	97.65 125	99.57 321	94.45 318	99.61 200	99.37 192

TestCases				99.16 107	99.50 109	98.55 99		99.58 61	96.80 272	98.88 180	99.06 153	97.65 125	99.57 321	94.45 318	99.61 200	99.37 192

XVG-OURS		98.53 144	98.34 155	99.11 114	99.50 109	98.82 81	95.97 341	99.50 92	97.30 237	99.05 147	98.98 182	99.35 12	99.32 377	95.72 285	99.68 175	99.18 246

EG-PatchMatch MVS		98.99 68	99.01 65	98.94 144	99.50 109	97.47 193	98.04 177	99.59 59	98.15 167	99.40 90	99.36 90	98.58 53	99.76 232	98.78 80	99.68 175	99.59 87

fmvsm_s_conf0.5_n_2		99.14 50	99.31 34	98.63 191	99.49 116	96.08 258	97.38 259	99.81 26	99.48 34	99.84 21	99.57 46	98.46 61	99.89 80	99.82 8	99.97 20	99.91 13

SED-MVS		98.91 79	98.72 94	99.49 51	99.49 116	99.17 43	98.10 168	99.31 171	98.03 170	99.66 45	99.02 165	98.36 67	99.88 93	96.91 199	99.62 195	99.41 173

IU-MVS					99.49 116	99.15 51		98.87 274	92.97 371	99.41 87				96.76 216	99.62 195	99.66 62

test_241102_ONE					99.49 116	99.17 43		99.31 171	97.98 173	99.66 45	98.90 199	98.36 67	99.48 351

UA-Net		99.47 13	99.40 22	99.70 2	99.49 116	99.29 23	99.80 4	99.72 37	99.82 5	99.04 149	99.81 6	98.05 98	99.96 12	98.85 76	99.99 5	99.86 23

HFP-MVS		98.71 106	98.44 140	99.51 46	99.49 116	99.16 47	98.52 118	99.31 171	97.47 217	98.58 223	98.50 273	97.97 105	99.85 130	96.57 233	99.59 206	99.53 123

VPA-MVSNet		99.30 29	99.30 37	99.28 87	99.49 116	98.36 116	99.00 69	99.45 116	99.63 21	99.52 65	99.44 77	98.25 77	99.88 93	99.09 59	99.84 87	99.62 72

XVG-OURS-SEG-HR		98.49 149	98.28 162	99.14 110	99.49 116	98.83 79	96.54 309	99.48 101	97.32 235	99.11 135	98.61 257	99.33 13	99.30 380	96.23 259	98.38 347	99.28 223

114514_t		96.50 300	95.77 308	98.69 182	99.48 124	97.43 197	97.84 208	99.55 79	81.42 418	96.51 360	98.58 261	95.53 242	99.67 277	93.41 350	99.58 211	98.98 276

IterMVS-LS		98.55 140	98.70 100	98.09 252	99.48 124	94.73 301	97.22 275	99.39 138	98.97 102	99.38 93	99.31 102	96.00 222	99.93 44	98.58 95	99.97 20	99.60 81
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v8		99.01 66	99.16 50	98.57 203	99.47 126	96.31 250	98.90 80	99.47 109	99.03 96	99.52 65	99.57 46	96.93 176	99.81 189	99.60 27	99.98 12	99.60 81

XVS		98.72 105	98.45 138	99.53 37	99.46 127	99.21 32	98.65 103	99.34 159	98.62 124	97.54 307	98.63 253	97.50 143	99.83 165	96.79 212	99.53 228	99.56 104

X-MVStestdata		94.32 348	92.59 366	99.53 37	99.46 127	99.21 32	98.65 103	99.34 159	98.62 124	97.54 307	45.85 423	97.50 143	99.83 165	96.79 212	99.53 228	99.56 104

test20.03		98.78 97	98.77 89	98.78 169	99.46 127	97.20 211	97.78 214	99.24 204	99.04 95	99.41 87	98.90 199	97.65 125	99.76 232	97.70 151	99.79 117	99.39 183

CSCG		98.68 118	98.50 128	99.20 101	99.45 130	98.63 91	98.56 113	99.57 68	97.87 184	98.85 185	98.04 314	97.66 124	99.84 148	96.72 221	99.81 101	99.13 255

GeoE		99.05 64	98.99 68	99.25 95	99.44 131	98.35 117	98.73 96	99.56 75	98.42 139	98.91 174	98.81 220	98.94 25	99.91 62	98.35 108	99.73 147	99.49 136

v148		98.45 153	98.60 117	98.00 262	99.44 131	94.98 294	97.44 257	99.06 240	98.30 147	99.32 108	98.97 184	96.65 195	99.62 302	98.37 107	99.85 83	99.39 183

v10		98.97 72	99.11 56	98.55 208	99.44 131	96.21 252	98.90 80	99.55 79	98.73 116	99.48 72	99.60 42	96.63 196	99.83 165	99.70 23	99.99 5	99.61 80

V42		98.78 97	98.78 88	98.76 173	99.44 131	97.04 219	98.27 147	99.19 214	97.87 184	99.25 122	99.16 136	96.84 180	99.78 220	99.21 53	99.84 87	99.46 155

MDA-MVSNet-bldmvs		97.94 203	97.91 205	98.06 257	99.44 131	94.96 295	96.63 307	99.15 230	98.35 141	98.83 188	99.11 146	94.31 277	99.85 130	96.60 230	98.72 329	99.37 192

casdiffmvs_mvg		99.12 56	99.16 50	98.99 137	99.43 136	97.73 180	98.00 184	99.62 54	99.22 63	99.55 58	99.22 122	98.93 26	99.75 239	98.66 91	99.81 101	99.50 132
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		96.49 301	96.82 275	95.52 373	99.42 137	87.08 407	99.22 42	87.14 421	99.11 78	99.46 77	99.58 44	88.69 340	99.86 118	98.80 78	99.95 32	99.62 72

v2v482		98.56 136	98.62 112	98.37 232	99.42 137	95.81 267	97.58 242	99.16 225	97.90 182	99.28 112	99.01 174	95.98 227	99.79 209	99.33 43	99.90 69	99.51 129

OPM-MVS		98.56 136	98.32 159	99.25 95	99.41 139	98.73 87	97.13 282	99.18 218	97.10 257	98.75 200	98.92 195	98.18 86	99.65 293	96.68 225	99.56 218	99.37 192
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 195	98.08 188	98.04 260	99.41 139	94.59 307	94.59 392	99.40 136	97.50 214	98.82 191	98.83 215	96.83 182	99.84 148	97.50 163	99.81 101	99.71 51

test_one_0601					99.39 141	99.20 38		99.31 171	98.49 136	98.66 210	99.02 165	97.64 128

mvsany_test3		98.87 84	98.92 73	98.74 179	99.38 142	96.94 226	98.58 111	99.10 235	96.49 286	99.96 4	99.81 6	98.18 86	99.45 358	98.97 68	99.79 117	99.83 26

patch_mono-2		98.51 148	98.63 110	98.17 248	99.38 142	94.78 298	97.36 262	99.69 42	98.16 166	98.49 235	99.29 105	97.06 168	99.97 5	98.29 112	99.91 63	99.76 44

test2506		92.39 377	91.89 379	93.89 393	99.38 142	82.28 423	99.32 23	66.03 429	99.08 90	98.77 197	99.57 46	66.26 419	99.84 148	98.71 88	99.95 32	99.54 115

ECVR-MVS		96.42 303	96.61 289	95.85 365	99.38 142	88.18 403	99.22 42	86.00 423	99.08 90	99.36 97	99.57 46	88.47 345	99.82 175	98.52 101	99.95 32	99.54 115

casdiffmvs		98.95 75	99.00 66	98.81 161	99.38 142	97.33 201	97.82 209	99.57 68	99.17 74	99.35 99	99.17 134	98.35 70	99.69 265	98.46 103	99.73 147	99.41 173
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 74	99.02 64	98.76 173	99.38 142	97.26 206	98.49 126	99.50 92	98.86 111	99.19 128	99.06 153	98.23 79	99.69 265	98.71 88	99.76 140	99.33 210

TranMVSNet+NR-MVSNet		99.17 45	99.07 62	99.46 58	99.37 148	98.87 77	98.39 138	99.42 129	99.42 44	99.36 97	99.06 153	98.38 66	99.95 24	98.34 109	99.90 69	99.57 98

tttt0517		95.64 327	94.98 337	97.64 288	99.36 149	93.81 334	98.72 97	90.47 416	98.08 169	98.67 208	98.34 290	73.88 406	99.92 53	97.77 146	99.51 233	99.20 238

test_part2					99.36 149	99.10 64				99.05 147

v1144		98.60 132	98.66 106	98.41 227	99.36 149	95.90 263	97.58 242	99.34 159	97.51 213	99.27 114	99.15 140	96.34 210	99.80 196	99.47 38	99.93 45	99.51 129

CP-MVS		98.70 110	98.42 143	99.52 42	99.36 149	99.12 61	98.72 97	99.36 148	97.54 211	98.30 248	98.40 282	97.86 110	99.89 80	96.53 242	99.72 155	99.56 104

Test_1112_low_res		96.99 282	96.55 293	98.31 238	99.35 153	95.47 277	95.84 353	99.53 86	91.51 388	96.80 349	98.48 276	91.36 321	99.83 165	96.58 231	99.53 228	99.62 72

DeepC-MVS	97.60 4	98.97 72	98.93 72	99.10 116	99.35 153	97.98 153	98.01 183	99.46 112	97.56 208	99.54 59	99.50 64	98.97 23	99.84 148	98.06 126	99.92 56	99.49 136
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 259	96.86 271	98.58 200	99.34 155	96.32 249	96.75 301	99.58 61	93.14 369	96.89 344	97.48 346	92.11 314	99.86 118	96.91 199	99.54 224	99.57 98

reproduce_model		99.15 49	98.97 70	99.67 4	99.33 156	99.44 10	98.15 160	99.47 109	99.12 77	99.52 65	99.32 101	98.31 73	99.90 68	97.78 145	99.73 147	99.66 62

MVSMamba_PlusPlus		98.83 89	98.98 69	98.36 233	99.32 157	96.58 244	98.90 80	99.41 133	99.75 8	98.72 203	99.50 64	96.17 214	99.94 37	99.27 47	99.78 122	98.57 335

SF-MVS		98.53 144	98.27 165	99.32 82	99.31 158	98.75 83	98.19 154	99.41 133	96.77 275	98.83 188	98.90 199	97.80 116	99.82 175	95.68 288	99.52 231	99.38 190

CPTT-MVS		97.84 218	97.36 242	99.27 90	99.31 158	98.46 107	98.29 145	99.27 193	94.90 337	97.83 287	98.37 286	94.90 258	99.84 148	93.85 339	99.54 224	99.51 129

UnsupCasMVSNet_eth		97.89 207	97.60 228	98.75 175	99.31 158	97.17 214	97.62 236	99.35 153	98.72 118	98.76 199	98.68 241	92.57 309	99.74 244	97.76 150	95.60 407	99.34 205

pmmvs-eth3d		98.47 151	98.34 155	98.86 155	99.30 161	97.76 176	97.16 280	99.28 190	95.54 320	99.42 85	99.19 126	97.27 157	99.63 299	97.89 136	99.97 20	99.20 238

mamv4		99.44 15	99.39 23	99.58 19	99.30 161	99.74 2	99.04 65	99.81 26	99.77 7	99.82 23	99.57 46	97.82 114	99.98 4	99.53 33	99.89 73	99.01 270

Anonymous20231211		99.27 33	99.27 40	99.26 92	99.29 163	98.18 128	99.49 9	99.51 90	99.70 12	99.80 27	99.68 22	96.84 180	99.83 165	99.21 53	99.91 63	99.77 39

UnsupCasMVSNet_bld		97.30 257	96.92 267	98.45 222	99.28 164	96.78 236	96.20 330	99.27 193	95.42 324	98.28 252	98.30 294	93.16 295	99.71 257	94.99 302	97.37 383	98.87 297

EC-MVSNet		99.09 59	99.05 63	99.20 101	99.28 164	98.93 75	99.24 41	99.84 21	99.08 90	98.12 265	98.37 286	98.72 38	99.90 68	99.05 62	99.77 128	98.77 313

reproduce-ours		99.09 59	98.90 75	99.67 4	99.27 166	99.49 6	98.00 184	99.42 129	99.05 93	99.48 72	99.27 108	98.29 75	99.89 80	97.61 155	99.71 160	99.62 72

our_new_method		99.09 59	98.90 75	99.67 4	99.27 166	99.49 6	98.00 184	99.42 129	99.05 93	99.48 72	99.27 108	98.29 75	99.89 80	97.61 155	99.71 160	99.62 72

DPE-MVS		98.59 134	98.26 166	99.57 20	99.27 166	99.15 51	97.01 285	99.39 138	97.67 196	99.44 81	98.99 178	97.53 139	99.89 80	95.40 296	99.68 175	99.66 62
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 217	98.18 175	96.87 334	99.27 166	91.16 383	95.53 362	99.25 199	99.10 85	99.41 87	99.35 91	93.10 297	99.96 12	98.65 92	99.94 40	99.49 136

v1192		98.60 132	98.66 106	98.41 227	99.27 166	95.88 264	97.52 248	99.36 148	97.41 226	99.33 102	99.20 125	96.37 208	99.82 175	99.57 29	99.92 56	99.55 111

N_pmnet		97.63 231	97.17 252	98.99 137	99.27 166	97.86 164	95.98 340	93.41 405	95.25 329	99.47 76	98.90 199	95.63 239	99.85 130	96.91 199	99.73 147	99.27 224

FPMVS		93.44 364	92.23 370	97.08 323	99.25 172	97.86 164	95.61 359	97.16 358	92.90 373	93.76 407	98.65 248	75.94 404	95.66 420	79.30 420	97.49 376	97.73 384

new-patchmatchnet		98.35 164	98.74 90	97.18 318	99.24 173	92.23 366	96.42 317	99.48 101	98.30 147	99.69 40	99.53 60	97.44 148	99.82 175	98.84 77	99.77 128	99.49 136

MCST-MVS		98.00 199	97.63 226	99.10 116	99.24 173	98.17 129	96.89 294	98.73 301	95.66 315	97.92 278	97.70 334	97.17 163	99.66 288	96.18 264	99.23 279	99.47 153

UniMVSNet (Re)		98.87 84	98.71 97	99.35 72	99.24 173	98.73 87	97.73 223	99.38 140	98.93 106	99.12 134	98.73 232	96.77 187	99.86 118	98.63 94	99.80 112	99.46 155

jason		97.45 245	97.35 243	97.76 277	99.24 173	93.93 328	95.86 350	98.42 319	94.24 352	98.50 234	98.13 304	94.82 262	99.91 62	97.22 175	99.73 147	99.43 167
jason: jason.
IterMVS		97.73 223	98.11 184	96.57 344	99.24 173	90.28 392	95.52 364	99.21 208	98.86 111	99.33 102	99.33 97	93.11 296	99.94 37	98.49 102	99.94 40	99.48 146
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 140	98.62 112	98.32 236	99.22 178	95.58 272	97.51 250	99.45 116	97.16 254	99.45 80	99.24 117	96.12 217	99.85 130	99.60 27	99.88 75	99.55 111

ITE_SJBPF				98.87 154	99.22 178	98.48 106		99.35 153	97.50 214	98.28 252	98.60 259	97.64 128	99.35 373	93.86 338	99.27 271	98.79 311

h-mvs33		97.77 221	97.33 245	99.10 116	99.21 180	97.84 166	98.35 142	98.57 311	99.11 78	98.58 223	99.02 165	88.65 343	99.96 12	98.11 121	96.34 399	99.49 136

v144192		98.54 142	98.57 120	98.45 222	99.21 180	95.98 261	97.63 235	99.36 148	97.15 256	99.32 108	99.18 130	95.84 234	99.84 148	99.50 36	99.91 63	99.54 115

APDe-MVS		98.99 68	98.79 87	99.60 14	99.21 180	99.15 51	98.87 84	99.48 101	97.57 206	99.35 99	99.24 117	97.83 111	99.89 80	97.88 139	99.70 167	99.75 48
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 77	98.81 86	99.28 87	99.21 180	98.45 108	98.46 131	99.33 164	99.63 21	99.48 72	99.15 140	97.23 160	99.75 239	97.17 177	99.66 186	99.63 71

SR-MVS-dyc-post		98.81 93	98.55 121	99.57 20	99.20 184	99.38 12	98.48 129	99.30 179	98.64 120	98.95 164	98.96 187	97.49 146	99.86 118	96.56 237	99.39 252	99.45 159

RE-MVS-def			98.58 119		99.20 184	99.38 12	98.48 129	99.30 179	98.64 120	98.95 164	98.96 187	97.75 119		96.56 237	99.39 252	99.45 159

v1921920		98.54 142	98.60 117	98.38 230	99.20 184	95.76 269	97.56 244	99.36 148	97.23 248	99.38 93	99.17 134	96.02 220	99.84 148	99.57 29	99.90 69	99.54 115

thisisatest0530		95.27 334	94.45 345	97.74 280	99.19 187	94.37 311	97.86 205	90.20 417	97.17 253	98.22 255	97.65 336	73.53 407	99.90 68	96.90 204	99.35 258	98.95 282

Anonymous20240529		98.93 77	98.87 78	99.12 112	99.19 187	98.22 127	99.01 67	98.99 257	99.25 61	99.54 59	99.37 86	97.04 169	99.80 196	97.89 136	99.52 231	99.35 203

APD-MVS_3200maxsize		98.84 88	98.61 116	99.53 37	99.19 187	99.27 26	98.49 126	99.33 164	98.64 120	99.03 152	98.98 182	97.89 108	99.85 130	96.54 241	99.42 249	99.46 155

HQP_MVS		97.99 202	97.67 220	98.93 146	99.19 187	97.65 184	97.77 216	99.27 193	98.20 160	97.79 290	97.98 317	94.90 258	99.70 261	94.42 320	99.51 233	99.45 159

plane_prior7					99.19 187	97.87 163

ab-mvs		98.41 156	98.36 152	98.59 199	99.19 187	97.23 207	99.32 23	98.81 288	97.66 197	98.62 215	99.40 85	96.82 183	99.80 196	95.88 275	99.51 233	98.75 316

F-COLMAP		97.30 257	96.68 284	99.14 110	99.19 187	98.39 110	97.27 271	99.30 179	92.93 372	96.62 355	98.00 315	95.73 237	99.68 274	92.62 366	98.46 346	99.35 203

SR-MVS		98.71 106	98.43 141	99.57 20	99.18 194	99.35 16	98.36 141	99.29 187	98.29 150	98.88 180	98.85 212	97.53 139	99.87 110	96.14 266	99.31 264	99.48 146

UniMVSNet_NR-MVSNet		98.86 87	98.68 103	99.40 64	99.17 195	98.74 84	97.68 227	99.40 136	99.14 76	99.06 142	98.59 260	96.71 193	99.93 44	98.57 97	99.77 128	99.53 123

LF4IMVS		97.90 205	97.69 219	98.52 213	99.17 195	97.66 183	97.19 279	99.47 109	96.31 294	97.85 286	98.20 301	96.71 193	99.52 339	94.62 312	99.72 155	98.38 352

SMA-MVS		98.40 158	98.03 192	99.51 46	99.16 197	99.21 32	98.05 175	99.22 207	94.16 354	98.98 156	99.10 149	97.52 141	99.79 209	96.45 247	99.64 189	99.53 123
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 91	98.63 110	99.39 65	99.16 197	98.74 84	97.54 246	99.25 199	98.84 114	99.06 142	98.76 229	96.76 189	99.93 44	98.57 97	99.77 128	99.50 132

NR-MVSNet		98.95 75	98.82 84	99.36 66	99.16 197	98.72 89	99.22 42	99.20 210	99.10 85	99.72 34	98.76 229	96.38 207	99.86 118	98.00 131	99.82 97	99.50 132

MVS_111021_LR		98.30 172	98.12 183	98.83 158	99.16 197	98.03 148	96.09 337	99.30 179	97.58 205	98.10 267	98.24 297	98.25 77	99.34 374	96.69 224	99.65 187	99.12 256

DSMNet-mixed		97.42 248	97.60 228	96.87 334	99.15 201	91.46 373	98.54 116	99.12 232	92.87 374	97.58 303	99.63 36	96.21 213	99.90 68	95.74 284	99.54 224	99.27 224

D2MVS		97.84 218	97.84 210	97.83 269	99.14 202	94.74 300	96.94 289	98.88 272	95.84 312	98.89 177	98.96 187	94.40 274	99.69 265	97.55 158	99.95 32	99.05 262

pmmvs5		97.64 230	97.49 234	98.08 255	99.14 202	95.12 291	96.70 304	99.05 243	93.77 361	98.62 215	98.83 215	93.23 293	99.75 239	98.33 111	99.76 140	99.36 199

SPE-MVS-test		99.13 54	99.09 59	99.26 92	99.13 204	98.97 70	99.31 27	99.88 14	99.44 41	98.16 260	98.51 269	98.64 44	99.93 44	98.91 71	99.85 83	98.88 296

VDD-MVS		98.56 136	98.39 148	99.07 122	99.13 204	98.07 143	98.59 110	97.01 361	99.59 27	99.11 135	99.27 108	94.82 262	99.79 209	98.34 109	99.63 192	99.34 205

save fliter					99.11 206	97.97 154	96.53 311	99.02 251	98.24 153

APD-MVS		98.10 191	97.67 220	99.42 60	99.11 206	98.93 75	97.76 219	99.28 190	94.97 335	98.72 203	98.77 227	97.04 169	99.85 130	93.79 340	99.54 224	99.49 136
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 113	98.71 97	98.62 193	99.10 208	96.37 247	97.23 272	98.87 274	99.20 67	99.19 128	98.99 178	97.30 154	99.85 130	98.77 83	99.79 117	99.65 67

EI-MVSNet		98.40 158	98.51 126	98.04 260	99.10 208	94.73 301	97.20 276	98.87 274	98.97 102	99.06 142	99.02 165	96.00 222	99.80 196	98.58 95	99.82 97	99.60 81

CVMVSNet		96.25 308	97.21 251	93.38 399	99.10 208	80.56 426	97.20 276	98.19 330	96.94 265	99.00 154	99.02 165	89.50 336	99.80 196	96.36 253	99.59 206	99.78 37

EI-MVSNet-Vis-set		98.68 118	98.70 100	98.63 191	99.09 211	96.40 246	97.23 272	98.86 279	99.20 67	99.18 132	98.97 184	97.29 156	99.85 130	98.72 87	99.78 122	99.64 68

HPM-MVS++		98.10 191	97.64 225	99.48 53	99.09 211	99.13 59	97.52 248	98.75 298	97.46 222	96.90 343	97.83 327	96.01 221	99.84 148	95.82 282	99.35 258	99.46 155

DP-MVS Recon		97.33 255	96.92 267	98.57 203	99.09 211	97.99 150	96.79 297	99.35 153	93.18 368	97.71 294	98.07 312	95.00 257	99.31 378	93.97 333	99.13 295	98.42 349

MVS_111021_HR		98.25 180	98.08 188	98.75 175	99.09 211	97.46 194	95.97 341	99.27 193	97.60 204	97.99 276	98.25 296	98.15 92	99.38 369	96.87 207	99.57 215	99.42 170

BP-MVS1		97.40 250	96.97 263	98.71 181	99.07 215	96.81 232	98.34 144	97.18 356	98.58 129	98.17 257	98.61 257	84.01 375	99.94 37	98.97 68	99.78 122	99.37 192

9.14			97.78 212		99.07 215		97.53 247	99.32 166	95.53 321	98.54 230	98.70 238	97.58 133	99.76 232	94.32 325	99.46 243

PAPM_NR		96.82 289	96.32 300	98.30 239	99.07 215	96.69 240	97.48 253	98.76 295	95.81 313	96.61 356	96.47 371	94.12 283	99.17 391	90.82 392	97.78 371	99.06 261

TAMVS		98.24 181	98.05 190	98.80 163	99.07 215	97.18 213	97.88 201	98.81 288	96.66 280	99.17 133	99.21 123	94.81 264	99.77 226	96.96 197	99.88 75	99.44 163

CLD-MVS		97.49 241	97.16 253	98.48 219	99.07 215	97.03 220	94.71 385	99.21 208	94.46 346	98.06 270	97.16 358	97.57 134	99.48 351	94.46 317	99.78 122	98.95 282
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 54	99.10 58	99.24 97	99.06 220	99.15 51	99.36 19	99.88 14	99.36 51	98.21 256	98.46 277	98.68 42	99.93 44	99.03 64	99.85 83	98.64 328

thres100view900		94.19 351	93.67 355	95.75 368	99.06 220	91.35 376	98.03 178	94.24 400	98.33 143	97.40 319	94.98 400	79.84 391	99.62 302	83.05 413	98.08 363	96.29 406

thres600view7		94.45 346	93.83 352	96.29 352	99.06 220	91.53 372	97.99 188	94.24 400	98.34 142	97.44 317	95.01 398	79.84 391	99.67 277	84.33 411	98.23 352	97.66 387

plane_prior1					99.05 223

YYNet1		97.60 232	97.67 220	97.39 311	99.04 224	93.04 350	95.27 371	98.38 322	97.25 242	98.92 173	98.95 191	95.48 246	99.73 249	96.99 193	98.74 327	99.41 173

MDA-MVSNet_test_wron		97.60 232	97.66 223	97.41 310	99.04 224	93.09 346	95.27 371	98.42 319	97.26 241	98.88 180	98.95 191	95.43 247	99.73 249	97.02 190	98.72 329	99.41 173

MIMVSNet		96.62 296	96.25 304	97.71 283	99.04 224	94.66 304	99.16 51	96.92 367	97.23 248	97.87 283	99.10 149	86.11 358	99.65 293	91.65 376	99.21 283	98.82 301

PatchMatch-RL		97.24 263	96.78 278	98.61 196	99.03 227	97.83 167	96.36 320	99.06 240	93.49 366	97.36 323	97.78 328	95.75 236	99.49 348	93.44 349	98.77 326	98.52 337

GDP-MVS		97.50 238	97.11 257	98.67 184	99.02 228	96.85 230	98.16 159	99.71 38	98.32 145	98.52 233	98.54 264	83.39 379	99.95 24	98.79 79	99.56 218	99.19 243

ZD-MVS					99.01 229	98.84 78		99.07 239	94.10 356	98.05 272	98.12 306	96.36 209	99.86 118	92.70 365	99.19 287

CDPH-MVS		97.26 260	96.66 287	99.07 122	99.00 230	98.15 130	96.03 339	99.01 254	91.21 392	97.79 290	97.85 326	96.89 178	99.69 265	92.75 363	99.38 255	99.39 183

diffmvs		98.22 182	98.24 169	98.17 248	99.00 230	95.44 278	96.38 319	99.58 61	97.79 190	98.53 231	98.50 273	96.76 189	99.74 244	97.95 135	99.64 189	99.34 205
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		98.40 158	98.19 174	99.03 132	99.00 230	97.65 184	96.85 295	98.94 259	98.57 130	98.89 177	98.50 273	95.60 240	99.85 130	97.54 160	99.85 83	99.59 87

plane_prior6					98.99 233	97.70 182						94.90 258

xiu_mvs_v1_base_debu		97.86 212	98.17 176	96.92 331	98.98 234	93.91 329	96.45 314	99.17 222	97.85 186	98.41 242	97.14 360	98.47 58	99.92 53	98.02 128	99.05 301	96.92 399

xiu_mvs_v1_base		97.86 212	98.17 176	96.92 331	98.98 234	93.91 329	96.45 314	99.17 222	97.85 186	98.41 242	97.14 360	98.47 58	99.92 53	98.02 128	99.05 301	96.92 399

xiu_mvs_v1_base_debi		97.86 212	98.17 176	96.92 331	98.98 234	93.91 329	96.45 314	99.17 222	97.85 186	98.41 242	97.14 360	98.47 58	99.92 53	98.02 128	99.05 301	96.92 399

MVP-Stereo		98.08 194	97.92 204	98.57 203	98.96 237	96.79 233	97.90 199	99.18 218	96.41 290	98.46 237	98.95 191	95.93 231	99.60 309	96.51 243	98.98 314	99.31 216
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 158	98.68 103	97.54 299	98.96 237	97.99 150	97.88 201	99.36 148	98.20 160	99.63 51	99.04 162	98.76 35	95.33 422	96.56 237	99.74 144	99.31 216
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				98.91 150	98.94 239	97.76 176		98.76 295	87.58 409	96.75 351	98.10 308	94.80 265	99.78 220	92.73 364	99.00 310	99.20 238

USDC		97.41 249	97.40 238	97.44 308	98.94 239	93.67 339	95.17 374	99.53 86	94.03 358	98.97 160	99.10 149	95.29 249	99.34 374	95.84 281	99.73 147	99.30 219

tfpn200view9		94.03 355	93.44 357	95.78 367	98.93 241	91.44 374	97.60 239	94.29 398	97.94 178	97.10 329	94.31 407	79.67 393	99.62 302	83.05 413	98.08 363	96.29 406

testdata				98.09 252	98.93 241	95.40 280		98.80 290	90.08 400	97.45 316	98.37 286	95.26 250	99.70 261	93.58 345	98.95 317	99.17 250

thres400		94.14 353	93.44 357	96.24 355	98.93 241	91.44 374	97.60 239	94.29 398	97.94 178	97.10 329	94.31 407	79.67 393	99.62 302	83.05 413	98.08 363	97.66 387

TAPA-MVS	96.21 11	96.63 295	95.95 306	98.65 185	98.93 241	98.09 137	96.93 291	99.28 190	83.58 415	98.13 264	97.78 328	96.13 216	99.40 365	93.52 346	99.29 269	98.45 342
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 245	96.93 227	95.54 361	98.78 293	85.72 412	96.86 346	98.11 307	94.43 272			99.10 300	99.23 233

PVSNet_BlendedMVS		97.55 237	97.53 231	97.60 291	98.92 245	93.77 336	96.64 306	99.43 126	94.49 344	97.62 299	99.18 130	96.82 183	99.67 277	94.73 309	99.93 45	99.36 199

PVSNet_Blended		96.88 285	96.68 284	97.47 306	98.92 245	93.77 336	94.71 385	99.43 126	90.98 394	97.62 299	97.36 354	96.82 183	99.67 277	94.73 309	99.56 218	98.98 276

MSDG		97.71 225	97.52 232	98.28 241	98.91 248	96.82 231	94.42 395	99.37 144	97.65 198	98.37 247	98.29 295	97.40 150	99.33 376	94.09 331	99.22 280	98.68 326

Anonymous202405211		97.90 205	97.50 233	99.08 120	98.90 249	98.25 121	98.53 117	96.16 378	98.87 110	99.11 135	98.86 209	90.40 330	99.78 220	97.36 168	99.31 264	99.19 243

原ACMM1				98.35 234	98.90 249	96.25 251		98.83 287	92.48 378	96.07 371	98.10 308	95.39 248	99.71 257	92.61 367	98.99 312	99.08 258

GBi-Net		98.65 123	98.47 135	99.17 104	98.90 249	98.24 122	99.20 45	99.44 120	98.59 126	98.95 164	99.55 54	94.14 280	99.86 118	97.77 146	99.69 170	99.41 173

test1		98.65 123	98.47 135	99.17 104	98.90 249	98.24 122	99.20 45	99.44 120	98.59 126	98.95 164	99.55 54	94.14 280	99.86 118	97.77 146	99.69 170	99.41 173

FMVSNet2		98.49 149	98.40 145	98.75 175	98.90 249	97.14 217	98.61 108	99.13 231	98.59 126	99.19 128	99.28 106	94.14 280	99.82 175	97.97 133	99.80 112	99.29 221

OMC-MVS		97.88 209	97.49 234	99.04 131	98.89 254	98.63 91	96.94 289	99.25 199	95.02 333	98.53 231	98.51 269	97.27 157	99.47 354	93.50 348	99.51 233	99.01 270

MVSFormer		98.26 178	98.43 141	97.77 274	98.88 255	93.89 332	99.39 17	99.56 75	99.11 78	98.16 260	98.13 304	93.81 288	99.97 5	99.26 48	99.57 215	99.43 167

lupinMVS		97.06 275	96.86 271	97.65 286	98.88 255	93.89 332	95.48 365	97.97 336	93.53 364	98.16 260	97.58 340	93.81 288	99.91 62	96.77 215	99.57 215	99.17 250

dmvs_re		95.98 316	95.39 326	97.74 280	98.86 257	97.45 195	98.37 140	95.69 389	97.95 176	96.56 357	95.95 379	90.70 327	97.68 416	88.32 401	96.13 403	98.11 364

DELS-MVS		98.27 176	98.20 172	98.48 219	98.86 257	96.70 239	95.60 360	99.20 210	97.73 193	98.45 238	98.71 235	97.50 143	99.82 175	98.21 115	99.59 206	98.93 287
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		97.89 207	97.98 197	97.60 291	98.86 257	94.35 312	96.21 329	99.44 120	97.45 224	99.06 142	98.88 206	97.99 104	99.28 384	94.38 324	99.58 211	99.18 246

LCM-MVSNet-Re		98.64 125	98.48 133	99.11 114	98.85 260	98.51 104	98.49 126	99.83 23	98.37 140	99.69 40	99.46 72	98.21 84	99.92 53	94.13 330	99.30 267	98.91 291

pmmvs4		97.58 235	97.28 246	98.51 214	98.84 261	96.93 227	95.40 369	98.52 314	93.60 363	98.61 217	98.65 248	95.10 254	99.60 309	96.97 196	99.79 117	98.99 275

NP-MVS					98.84 261	97.39 199					96.84 363

sss		97.21 265	96.93 265	98.06 257	98.83 263	95.22 287	96.75 301	98.48 316	94.49 344	97.27 325	97.90 323	92.77 305	99.80 196	96.57 233	99.32 262	99.16 253

PVSNet	93.40 17	95.67 325	95.70 311	95.57 372	98.83 263	88.57 399	92.50 412	97.72 341	92.69 376	96.49 363	96.44 372	93.72 291	99.43 361	93.61 343	99.28 270	98.71 319

MVE	83.40 22	92.50 376	91.92 378	94.25 387	98.83 263	91.64 371	92.71 411	83.52 425	95.92 310	86.46 423	95.46 392	95.20 251	95.40 421	80.51 418	98.64 338	95.73 414
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ambc				98.24 244	98.82 266	95.97 262	98.62 107	99.00 256		99.27 114	99.21 123	96.99 174	99.50 345	96.55 240	99.50 240	99.26 227

旧先验1					98.82 266	97.45 195		98.76 295			98.34 290	95.50 245			99.01 309	99.23 233

test_vis1_rt		97.75 222	97.72 218	97.83 269	98.81 268	96.35 248	97.30 267	99.69 42	94.61 342	97.87 283	98.05 313	96.26 212	98.32 411	98.74 85	98.18 355	98.82 301

WTY-MVS		96.67 293	96.27 303	97.87 267	98.81 268	94.61 306	96.77 299	97.92 338	94.94 336	97.12 328	97.74 331	91.11 323	99.82 175	93.89 336	98.15 359	99.18 246

3Dnovator+	97.89 3	98.69 113	98.51 126	99.24 97	98.81 268	98.40 109	99.02 66	99.19 214	98.99 99	98.07 269	99.28 106	97.11 167	99.84 148	96.84 210	99.32 262	99.47 153

QAPM		97.31 256	96.81 277	98.82 159	98.80 271	97.49 192	99.06 62	99.19 214	90.22 398	97.69 296	99.16 136	96.91 177	99.90 68	90.89 391	99.41 250	99.07 260

VNet		98.42 155	98.30 160	98.79 166	98.79 272	97.29 203	98.23 150	98.66 305	99.31 55	98.85 185	98.80 221	94.80 265	99.78 220	98.13 120	99.13 295	99.31 216

DPM-MVS		96.32 305	95.59 317	98.51 214	98.76 273	97.21 210	94.54 394	98.26 325	91.94 383	96.37 364	97.25 356	93.06 299	99.43 361	91.42 381	98.74 327	98.89 293

3Dnovator	98.27 2	98.81 93	98.73 92	99.05 129	98.76 273	97.81 173	99.25 40	99.30 179	98.57 130	98.55 228	99.33 97	97.95 106	99.90 68	97.16 178	99.67 181	99.44 163

PLC	94.65 16	96.51 298	95.73 310	98.85 156	98.75 275	97.91 160	96.42 317	99.06 240	90.94 395	95.59 377	97.38 352	94.41 273	99.59 313	90.93 389	98.04 368	99.05 262
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 287	96.75 280	97.08 323	98.74 276	93.33 344	96.71 303	98.26 325	96.72 277	98.44 239	97.37 353	95.20 251	99.47 354	91.89 372	97.43 380	98.44 345

hse-mvs2		97.46 243	97.07 258	98.64 187	98.73 277	97.33 201	97.45 256	97.64 347	99.11 78	98.58 223	97.98 317	88.65 343	99.79 209	98.11 121	97.39 382	98.81 305

CDS-MVSNet		97.69 226	97.35 243	98.69 182	98.73 277	97.02 221	96.92 293	98.75 298	95.89 311	98.59 221	98.67 243	92.08 315	99.74 244	96.72 221	99.81 101	99.32 212
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EIA-MVS		98.00 199	97.74 215	98.80 163	98.72 279	98.09 137	98.05 175	99.60 58	97.39 228	96.63 354	95.55 387	97.68 122	99.80 196	96.73 220	99.27 271	98.52 337

LFMVS		97.20 266	96.72 281	98.64 187	98.72 279	96.95 225	98.93 78	94.14 402	99.74 10	98.78 194	99.01 174	84.45 370	99.73 249	97.44 164	99.27 271	99.25 228

new_pmnet		96.99 282	96.76 279	97.67 284	98.72 279	94.89 296	95.95 345	98.20 328	92.62 377	98.55 228	98.54 264	94.88 261	99.52 339	93.96 334	99.44 248	98.59 334

Fast-Effi-MVS+		97.67 228	97.38 240	98.57 203	98.71 282	97.43 197	97.23 272	99.45 116	94.82 339	96.13 368	96.51 368	98.52 56	99.91 62	96.19 262	98.83 323	98.37 354

TEST9					98.71 282	98.08 141	95.96 343	99.03 248	91.40 389	95.85 374	97.53 342	96.52 200	99.76 232

train_agg		97.10 272	96.45 297	99.07 122	98.71 282	98.08 141	95.96 343	99.03 248	91.64 384	95.85 374	97.53 342	96.47 202	99.76 232	93.67 342	99.16 290	99.36 199

TSAR-MVS + GP.		98.18 187	97.98 197	98.77 172	98.71 282	97.88 162	96.32 323	98.66 305	96.33 292	99.23 125	98.51 269	97.48 147	99.40 365	97.16 178	99.46 243	99.02 269

FA-MVS(test-final)		96.99 282	96.82 275	97.50 303	98.70 286	94.78 298	99.34 20	96.99 362	95.07 332	98.48 236	99.33 97	88.41 346	99.65 293	96.13 268	98.92 320	98.07 367

AUN-MVS		96.24 310	95.45 322	98.60 198	98.70 286	97.22 209	97.38 259	97.65 345	95.95 309	95.53 384	97.96 321	82.11 387	99.79 209	96.31 255	97.44 379	98.80 310

our_test_3		97.39 251	97.73 217	96.34 350	98.70 286	89.78 395	94.61 391	98.97 258	96.50 285	99.04 149	98.85 212	95.98 227	99.84 148	97.26 173	99.67 181	99.41 173

ppachtmachnet_test		97.50 238	97.74 215	96.78 340	98.70 286	91.23 382	94.55 393	99.05 243	96.36 291	99.21 126	98.79 223	96.39 205	99.78 220	96.74 218	99.82 97	99.34 205

PCF-MVS	92.86 18	94.36 347	93.00 364	98.42 226	98.70 286	97.56 189	93.16 410	99.11 234	79.59 419	97.55 306	97.43 349	92.19 312	99.73 249	79.85 419	99.45 245	97.97 373
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 204	98.02 193	97.58 293	98.69 291	94.10 319	98.13 162	98.90 268	97.95 176	97.32 324	99.58 44	95.95 230	98.75 406	96.41 249	99.22 280	99.87 20

ETV-MVS		98.03 196	97.86 209	98.56 207	98.69 291	98.07 143	97.51 250	99.50 92	98.10 168	97.50 311	95.51 388	98.41 64	99.88 93	96.27 258	99.24 276	97.71 386

test_prior				98.95 143	98.69 291	97.95 158		99.03 248					99.59 313			99.30 219

mvsmamba		97.57 236	97.26 247	98.51 214	98.69 291	96.73 238	98.74 92	97.25 355	97.03 261	97.88 282	99.23 121	90.95 324	99.87 110	96.61 229	99.00 310	98.91 291

agg_prior					98.68 295	97.99 150		99.01 254		95.59 377			99.77 226

test_8					98.67 296	98.01 149	95.91 349	99.02 251	91.64 384	95.79 376	97.50 345	96.47 202	99.76 232

HQP-NCC					98.67 296		96.29 325		96.05 302	95.55 380

ACMP_Plane					98.67 296		96.29 325		96.05 302	95.55 380

CNVR-MVS		98.17 189	97.87 208	99.07 122	98.67 296	98.24 122	97.01 285	98.93 262	97.25 242	97.62 299	98.34 290	97.27 157	99.57 321	96.42 248	99.33 261	99.39 183

HQP-MVS		97.00 281	96.49 296	98.55 208	98.67 296	96.79 233	96.29 325	99.04 246	96.05 302	95.55 380	96.84 363	93.84 286	99.54 333	92.82 360	99.26 274	99.32 212

MM		98.22 182	97.99 196	98.91 150	98.66 301	96.97 222	97.89 200	94.44 396	99.54 30	98.95 164	99.14 143	93.50 292	99.92 53	99.80 13	99.96 25	99.85 24

test_fmvs1		97.72 224	97.94 202	97.07 325	98.66 301	92.39 361	97.68 227	99.81 26	95.20 331	99.54 59	99.44 77	91.56 320	99.41 364	99.78 16	99.77 128	99.40 182

balanced_conf03		98.63 127	98.72 94	98.38 230	98.66 301	96.68 241	98.90 80	99.42 129	98.99 99	98.97 160	99.19 126	95.81 235	99.85 130	98.77 83	99.77 128	98.60 331

thres200		93.72 360	93.14 362	95.46 376	98.66 301	91.29 378	96.61 308	94.63 395	97.39 228	96.83 347	93.71 410	79.88 390	99.56 324	82.40 416	98.13 360	95.54 415

wuyk23d		96.06 312	97.62 227	91.38 402	98.65 305	98.57 98	98.85 87	96.95 365	96.86 270	99.90 12	99.16 136	99.18 17	98.40 410	89.23 399	99.77 128	77.18 422

NCCC		97.86 212	97.47 237	99.05 129	98.61 306	98.07 143	96.98 287	98.90 268	97.63 199	97.04 333	97.93 322	95.99 226	99.66 288	95.31 297	98.82 325	99.43 167

DeepC-MVS_fast	96.85 6	98.30 172	98.15 180	98.75 175	98.61 306	97.23 207	97.76 219	99.09 237	97.31 236	98.75 200	98.66 246	97.56 135	99.64 296	96.10 269	99.55 222	99.39 183
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 362	92.09 372	97.75 278	98.60 308	94.40 310	97.32 265	95.26 391	97.56 208	96.79 350	95.50 389	53.57 428	99.77 226	95.26 298	98.97 315	99.08 258

thisisatest0515		94.12 354	93.16 361	96.97 329	98.60 308	92.90 351	93.77 406	90.61 415	94.10 356	96.91 340	95.87 382	74.99 405	99.80 196	94.52 315	99.12 298	98.20 360

GA-MVS		95.86 319	95.32 329	97.49 304	98.60 308	94.15 318	93.83 405	97.93 337	95.49 322	96.68 352	97.42 350	83.21 380	99.30 380	96.22 260	98.55 344	99.01 270

dmvs_testset		92.94 372	92.21 371	95.13 380	98.59 311	90.99 385	97.65 233	92.09 411	96.95 264	94.00 403	93.55 411	92.34 311	96.97 419	72.20 422	92.52 417	97.43 394

OPU-MVS				98.82 159	98.59 311	98.30 118	98.10 168				98.52 268	98.18 86	98.75 406	94.62 312	99.48 242	99.41 173

MSLP-MVS++		98.02 197	98.14 182	97.64 288	98.58 313	95.19 288	97.48 253	99.23 206	97.47 217	97.90 280	98.62 255	97.04 169	98.81 405	97.55 158	99.41 250	98.94 286

test12				98.93 146	98.58 313	97.83 167		98.66 305		96.53 358		95.51 244	99.69 265		99.13 295	99.27 224

CL-MVSNet_self_test		97.44 246	97.22 250	98.08 255	98.57 315	95.78 268	94.30 398	98.79 291	96.58 283	98.60 219	98.19 302	94.74 268	99.64 296	96.41 249	98.84 322	98.82 301

PS-MVSNAJ		97.08 274	97.39 239	96.16 361	98.56 316	92.46 359	95.24 373	98.85 282	97.25 242	97.49 312	95.99 378	98.07 95	99.90 68	96.37 251	98.67 337	96.12 411

CNLPA		97.17 269	96.71 282	98.55 208	98.56 316	98.05 147	96.33 322	98.93 262	96.91 267	97.06 332	97.39 351	94.38 275	99.45 358	91.66 375	99.18 289	98.14 363

xiu_mvs_v2_base		97.16 270	97.49 234	96.17 359	98.54 318	92.46 359	95.45 366	98.84 283	97.25 242	97.48 313	96.49 369	98.31 73	99.90 68	96.34 254	98.68 336	96.15 410

alignmvs		97.35 253	96.88 270	98.78 169	98.54 318	98.09 137	97.71 224	97.69 343	99.20 67	97.59 302	95.90 381	88.12 348	99.55 328	98.18 117	98.96 316	98.70 322

FE-MVS		95.66 326	94.95 339	97.77 274	98.53 320	95.28 284	99.40 16	96.09 380	93.11 370	97.96 277	99.26 112	79.10 397	99.77 226	92.40 369	98.71 331	98.27 358

Effi-MVS+		98.02 197	97.82 211	98.62 193	98.53 320	97.19 212	97.33 264	99.68 47	97.30 237	96.68 352	97.46 348	98.56 54	99.80 196	96.63 227	98.20 354	98.86 298

baseline1		95.96 317	95.44 323	97.52 301	98.51 322	93.99 326	98.39 138	96.09 380	98.21 156	98.40 246	97.76 330	86.88 350	99.63 299	95.42 295	89.27 420	98.95 282

MVS_Test		98.18 187	98.36 152	97.67 284	98.48 323	94.73 301	98.18 155	99.02 251	97.69 195	98.04 273	99.11 146	97.22 161	99.56 324	98.57 97	98.90 321	98.71 319

MGCFI-Net		98.34 165	98.28 162	98.51 214	98.47 324	97.59 188	98.96 74	99.48 101	99.18 73	97.40 319	95.50 389	98.66 43	99.50 345	98.18 117	98.71 331	98.44 345

BH-RMVSNet		96.83 287	96.58 292	97.58 293	98.47 324	94.05 320	96.67 305	97.36 350	96.70 279	97.87 283	97.98 317	95.14 253	99.44 360	90.47 394	98.58 343	99.25 228

sasdasda		98.34 165	98.26 166	98.58 200	98.46 326	97.82 170	98.96 74	99.46 112	99.19 71	97.46 314	95.46 392	98.59 50	99.46 356	98.08 124	98.71 331	98.46 339

canonicalmvs		98.34 165	98.26 166	98.58 200	98.46 326	97.82 170	98.96 74	99.46 112	99.19 71	97.46 314	95.46 392	98.59 50	99.46 356	98.08 124	98.71 331	98.46 339

MVS-HIRNet		94.32 348	95.62 314	90.42 403	98.46 326	75.36 427	96.29 325	89.13 419	95.25 329	95.38 386	99.75 13	92.88 302	99.19 390	94.07 332	99.39 252	96.72 404

PHI-MVS		98.29 175	97.95 200	99.34 75	98.44 329	99.16 47	98.12 165	99.38 140	96.01 306	98.06 270	98.43 280	97.80 116	99.67 277	95.69 287	99.58 211	99.20 238

DVP-MVS++		98.90 81	98.70 100	99.51 46	98.43 330	99.15 51	99.43 12	99.32 166	98.17 163	99.26 118	99.02 165	98.18 86	99.88 93	97.07 187	99.45 245	99.49 136

MSC_two_6792asdad				99.32 82	98.43 330	98.37 113		98.86 279					99.89 80	97.14 181	99.60 202	99.71 51

No_MVS				99.32 82	98.43 330	98.37 113		98.86 279					99.89 80	97.14 181	99.60 202	99.71 51

Fast-Effi-MVS+-dtu		98.27 176	98.09 185	98.81 161	98.43 330	98.11 134	97.61 238	99.50 92	98.64 120	97.39 321	97.52 344	98.12 94	99.95 24	96.90 204	98.71 331	98.38 352

OpenMVS_ROB	95.38 14	95.84 321	95.18 334	97.81 271	98.41 334	97.15 216	97.37 261	98.62 309	83.86 414	98.65 211	98.37 286	94.29 278	99.68 274	88.41 400	98.62 341	96.60 405

DeepPCF-MVS	96.93 5	98.32 169	98.01 194	99.23 99	98.39 335	98.97 70	95.03 378	99.18 218	96.88 268	99.33 102	98.78 225	98.16 90	99.28 384	96.74 218	99.62 195	99.44 163

Patchmatch-test		96.55 297	96.34 299	97.17 320	98.35 336	93.06 347	98.40 137	97.79 339	97.33 233	98.41 242	98.67 243	83.68 378	99.69 265	95.16 300	99.31 264	98.77 313

AdaColmap		97.14 271	96.71 282	98.46 221	98.34 337	97.80 174	96.95 288	98.93 262	95.58 319	96.92 338	97.66 335	95.87 233	99.53 335	90.97 388	99.14 293	98.04 368

OpenMVS	96.65 7	97.09 273	96.68 284	98.32 236	98.32 338	97.16 215	98.86 86	99.37 144	89.48 402	96.29 366	99.15 140	96.56 198	99.90 68	92.90 357	99.20 284	97.89 374

MG-MVS		96.77 290	96.61 289	97.26 316	98.31 339	93.06 347	95.93 346	98.12 333	96.45 289	97.92 278	98.73 232	93.77 290	99.39 367	91.19 386	99.04 304	99.33 210

test_yl		96.69 291	96.29 301	97.90 264	98.28 340	95.24 285	97.29 268	97.36 350	98.21 156	98.17 257	97.86 324	86.27 354	99.55 328	94.87 306	98.32 348	98.89 293

DCV-MVSNet		96.69 291	96.29 301	97.90 264	98.28 340	95.24 285	97.29 268	97.36 350	98.21 156	98.17 257	97.86 324	86.27 354	99.55 328	94.87 306	98.32 348	98.89 293

CHOSEN 280x420		95.51 331	95.47 320	95.65 371	98.25 342	88.27 402	93.25 409	98.88 272	93.53 364	94.65 395	97.15 359	86.17 356	99.93 44	97.41 166	99.93 45	98.73 318

SCA		96.41 304	96.66 287	95.67 369	98.24 343	88.35 401	95.85 352	96.88 368	96.11 300	97.67 297	98.67 243	93.10 297	99.85 130	94.16 326	99.22 280	98.81 305

DeepMVS_CX				93.44 398	98.24 343	94.21 315		94.34 397	64.28 422	91.34 416	94.87 404	89.45 337	92.77 423	77.54 421	93.14 416	93.35 418

MS-PatchMatch		97.68 227	97.75 214	97.45 307	98.23 345	93.78 335	97.29 268	98.84 283	96.10 301	98.64 212	98.65 248	96.04 219	99.36 370	96.84 210	99.14 293	99.20 238

BH-w/o		95.13 337	94.89 341	95.86 364	98.20 346	91.31 377	95.65 358	97.37 349	93.64 362	96.52 359	95.70 385	93.04 300	99.02 396	88.10 402	95.82 406	97.24 397

mvs_anonymous		97.83 220	98.16 179	96.87 334	98.18 347	91.89 368	97.31 266	98.90 268	97.37 230	98.83 188	99.46 72	96.28 211	99.79 209	98.90 72	98.16 358	98.95 282

miper_lstm_enhance		97.18 268	97.16 253	97.25 317	98.16 348	92.85 352	95.15 376	99.31 171	97.25 242	98.74 202	98.78 225	90.07 331	99.78 220	97.19 176	99.80 112	99.11 257

RRT-MVS		97.88 209	97.98 197	97.61 290	98.15 349	93.77 336	98.97 73	99.64 52	99.16 75	98.69 205	99.42 79	91.60 318	99.89 80	97.63 154	98.52 345	99.16 253

ET-MVSNet_ETH3D		94.30 350	93.21 360	97.58 293	98.14 350	94.47 309	94.78 384	93.24 407	94.72 340	89.56 418	95.87 382	78.57 400	99.81 189	96.91 199	97.11 391	98.46 339

ADS-MVSNet2		95.43 332	94.98 337	96.76 341	98.14 350	91.74 369	97.92 196	97.76 340	90.23 396	96.51 360	98.91 196	85.61 361	99.85 130	92.88 358	96.90 392	98.69 323

ADS-MVSNet		95.24 335	94.93 340	96.18 358	98.14 350	90.10 394	97.92 196	97.32 353	90.23 396	96.51 360	98.91 196	85.61 361	99.74 244	92.88 358	96.90 392	98.69 323

c3_l		97.36 252	97.37 241	97.31 312	98.09 353	93.25 345	95.01 379	99.16 225	97.05 258	98.77 197	98.72 234	92.88 302	99.64 296	96.93 198	99.76 140	99.05 262

FMVSNet3		97.50 238	97.24 249	98.29 240	98.08 354	95.83 266	97.86 205	98.91 267	97.89 183	98.95 164	98.95 191	87.06 349	99.81 189	97.77 146	99.69 170	99.23 233

PAPM		91.88 385	90.34 388	96.51 345	98.06 355	92.56 357	92.44 413	97.17 357	86.35 410	90.38 417	96.01 377	86.61 352	99.21 389	70.65 423	95.43 408	97.75 383

Effi-MVS+-dtu		98.26 178	97.90 206	99.35 72	98.02 356	99.49 6	98.02 180	99.16 225	98.29 150	97.64 298	97.99 316	96.44 204	99.95 24	96.66 226	98.93 319	98.60 331

eth_miper_zixun_eth		97.23 264	97.25 248	97.17 320	98.00 357	92.77 354	94.71 385	99.18 218	97.27 240	98.56 226	98.74 231	91.89 316	99.69 265	97.06 189	99.81 101	99.05 262

HY-MVS	95.94 13	95.90 318	95.35 328	97.55 298	97.95 358	94.79 297	98.81 91	96.94 366	92.28 381	95.17 388	98.57 262	89.90 333	99.75 239	91.20 385	97.33 387	98.10 365

UGNet		98.53 144	98.45 138	98.79 166	97.94 359	96.96 224	99.08 58	98.54 312	99.10 85	96.82 348	99.47 71	96.55 199	99.84 148	98.56 100	99.94 40	99.55 111
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		96.47 302	95.70 311	98.79 166	97.92 360	99.12 61	98.28 146	98.60 310	92.16 382	95.54 383	96.17 376	94.77 267	99.52 339	89.62 397	98.23 352	97.72 385
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		96.86 286	96.55 293	97.79 272	97.91 361	94.21 315	97.56 244	98.87 274	97.49 216	99.06 142	99.05 160	80.72 388	99.80 196	98.44 104	99.82 97	99.37 192

API-MVS		97.04 277	96.91 269	97.42 309	97.88 362	98.23 126	98.18 155	98.50 315	97.57 206	97.39 321	96.75 365	96.77 187	99.15 393	90.16 395	99.02 308	94.88 416

miper_ehance_all_eth		97.06 275	97.03 260	97.16 322	97.83 363	93.06 347	94.66 388	99.09 237	95.99 307	98.69 205	98.45 278	92.73 307	99.61 308	96.79 212	99.03 305	98.82 301

cl____		97.02 278	96.83 274	97.58 293	97.82 364	94.04 322	94.66 388	99.16 225	97.04 259	98.63 213	98.71 235	88.68 342	99.69 265	97.00 191	99.81 101	99.00 274

DIV-MVS_self_test		97.02 278	96.84 273	97.58 293	97.82 364	94.03 323	94.66 388	99.16 225	97.04 259	98.63 213	98.71 235	88.69 340	99.69 265	97.00 191	99.81 101	99.01 270

CANet		97.87 211	97.76 213	98.19 247	97.75 366	95.51 275	96.76 300	99.05 243	97.74 192	96.93 337	98.21 300	95.59 241	99.89 80	97.86 141	99.93 45	99.19 243

UBG		93.25 367	92.32 368	96.04 363	97.72 367	90.16 393	95.92 348	95.91 384	96.03 305	93.95 405	93.04 415	69.60 411	99.52 339	90.72 393	97.98 369	98.45 342

mvsany_test1		97.60 232	97.54 230	97.77 274	97.72 367	95.35 281	95.36 370	97.13 359	94.13 355	99.71 36	99.33 97	97.93 107	99.30 380	97.60 157	98.94 318	98.67 327

PVSNet_0	89.98 21	91.15 386	90.30 389	93.70 395	97.72 367	84.34 419	90.24 416	97.42 348	90.20 399	93.79 406	93.09 414	90.90 326	98.89 404	86.57 408	72.76 423	97.87 376

CR-MVSNet		96.28 307	95.95 306	97.28 314	97.71 370	94.22 313	98.11 166	98.92 265	92.31 380	96.91 340	99.37 86	85.44 364	99.81 189	97.39 167	97.36 385	97.81 379

RPMNet		97.02 278	96.93 265	97.30 313	97.71 370	94.22 313	98.11 166	99.30 179	99.37 48	96.91 340	99.34 95	86.72 351	99.87 110	97.53 161	97.36 385	97.81 379

ETVMVS		92.60 375	91.08 384	97.18 318	97.70 372	93.65 341	96.54 309	95.70 387	96.51 284	94.68 394	92.39 418	61.80 425	99.50 345	86.97 405	97.41 381	98.40 350

pmmvs3		95.03 339	94.40 346	96.93 330	97.70 372	92.53 358	95.08 377	97.71 342	88.57 406	97.71 294	98.08 311	79.39 395	99.82 175	96.19 262	99.11 299	98.43 347

baseline2		93.73 359	92.83 365	96.42 348	97.70 372	91.28 379	96.84 296	89.77 418	93.96 360	92.44 413	95.93 380	79.14 396	99.77 226	92.94 356	96.76 396	98.21 359

WBMVS		95.18 336	94.78 342	96.37 349	97.68 375	89.74 396	95.80 354	98.73 301	97.54 211	98.30 248	98.44 279	70.06 409	99.82 175	96.62 228	99.87 78	99.54 115

tpm		94.67 344	94.34 348	95.66 370	97.68 375	88.42 400	97.88 201	94.90 392	94.46 346	96.03 373	98.56 263	78.66 398	99.79 209	95.88 275	95.01 410	98.78 312

CANet_DTU		97.26 260	97.06 259	97.84 268	97.57 377	94.65 305	96.19 331	98.79 291	97.23 248	95.14 389	98.24 297	93.22 294	99.84 148	97.34 169	99.84 87	99.04 266

testing11		93.08 370	92.02 374	96.26 354	97.56 378	90.83 388	96.32 323	95.70 387	96.47 288	92.66 412	93.73 409	64.36 423	99.59 313	93.77 341	97.57 374	98.37 354

tpm2		93.09 369	92.58 367	94.62 384	97.56 378	86.53 408	97.66 231	95.79 386	86.15 411	94.07 402	98.23 299	75.95 403	99.53 335	90.91 390	96.86 395	97.81 379

testing91		93.32 365	92.27 369	96.47 347	97.54 380	91.25 380	96.17 334	96.76 370	97.18 252	93.65 408	93.50 412	65.11 422	99.63 299	93.04 355	97.45 378	98.53 336

TR-MVS		95.55 329	95.12 335	96.86 337	97.54 380	93.94 327	96.49 313	96.53 375	94.36 351	97.03 335	96.61 367	94.26 279	99.16 392	86.91 407	96.31 400	97.47 393

testing99		93.04 371	91.98 377	96.23 356	97.53 382	90.70 390	96.35 321	95.94 383	96.87 269	93.41 409	93.43 413	63.84 424	99.59 313	93.24 353	97.19 388	98.40 350

1314		95.74 323	95.60 315	96.17 359	97.53 382	92.75 355	98.07 172	98.31 324	91.22 391	94.25 398	96.68 366	95.53 242	99.03 395	91.64 377	97.18 389	96.74 403

CostFormer		93.97 356	93.78 353	94.51 385	97.53 382	85.83 411	97.98 189	95.96 382	89.29 404	94.99 391	98.63 253	78.63 399	99.62 302	94.54 314	96.50 397	98.09 366

FMVSNet5		96.01 314	95.20 333	98.41 227	97.53 382	96.10 253	98.74 92	99.50 92	97.22 251	98.03 274	99.04 162	69.80 410	99.88 93	97.27 172	99.71 160	99.25 228

PMMVS		96.51 298	95.98 305	98.09 252	97.53 382	95.84 265	94.92 381	98.84 283	91.58 386	96.05 372	95.58 386	95.68 238	99.66 288	95.59 291	98.09 362	98.76 315

reproduce_monomvs		95.00 341	95.25 330	94.22 388	97.51 387	83.34 420	97.86 205	98.44 317	98.51 135	99.29 111	99.30 103	67.68 415	99.56 324	98.89 74	99.81 101	99.77 39

PAPR		95.29 333	94.47 344	97.75 278	97.50 388	95.14 290	94.89 382	98.71 303	91.39 390	95.35 387	95.48 391	94.57 270	99.14 394	84.95 410	97.37 383	98.97 279

testing222		91.96 383	90.37 387	96.72 342	97.47 389	92.59 356	96.11 336	94.76 393	96.83 271	92.90 411	92.87 416	57.92 426	99.55 328	86.93 406	97.52 375	98.00 372

PatchT		96.65 294	96.35 298	97.54 299	97.40 390	95.32 283	97.98 189	96.64 372	99.33 53	96.89 344	99.42 79	84.32 372	99.81 189	97.69 153	97.49 376	97.48 392

tpm cat1		93.29 366	93.13 363	93.75 394	97.39 391	84.74 414	97.39 258	97.65 345	83.39 416	94.16 399	98.41 281	82.86 383	99.39 367	91.56 379	95.35 409	97.14 398

PatchmatchNet		95.58 328	95.67 313	95.30 379	97.34 392	87.32 406	97.65 233	96.65 371	95.30 328	97.07 331	98.69 239	84.77 367	99.75 239	94.97 304	98.64 338	98.83 300
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 253	96.97 263	98.50 218	97.31 393	96.47 245	98.18 155	98.92 265	98.95 105	98.78 194	99.37 86	85.44 364	99.85 130	95.96 273	99.83 94	99.17 250

LS3D		98.63 127	98.38 150	99.36 66	97.25 394	99.38 12	99.12 57	99.32 166	99.21 65	98.44 239	98.88 206	97.31 153	99.80 196	96.58 231	99.34 260	98.92 288

IB-MVS	91.63 19	92.24 381	90.90 385	96.27 353	97.22 395	91.24 381	94.36 397	93.33 406	92.37 379	92.24 414	94.58 406	66.20 420	99.89 80	93.16 354	94.63 412	97.66 387
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		92.38 378	91.76 381	94.21 389	97.16 396	84.65 415	95.42 368	88.45 420	95.96 308	96.17 367	95.84 384	66.36 418	99.71 257	91.87 373	98.64 338	98.28 357

tpmrst		95.07 338	95.46 321	93.91 392	97.11 397	84.36 418	97.62 236	96.96 364	94.98 334	96.35 365	98.80 221	85.46 363	99.59 313	95.60 290	96.23 401	97.79 382

Syy-MVS		96.04 313	95.56 319	97.49 304	97.10 398	94.48 308	96.18 332	96.58 373	95.65 316	94.77 392	92.29 419	91.27 322	99.36 370	98.17 119	98.05 366	98.63 329

myMVS_eth3d		91.92 384	90.45 386	96.30 351	97.10 398	90.90 386	96.18 332	96.58 373	95.65 316	94.77 392	92.29 419	53.88 427	99.36 370	89.59 398	98.05 366	98.63 329

MDTV_nov1_ep13			95.22 332		97.06 400	83.20 421	97.74 221	96.16 378	94.37 350	96.99 336	98.83 215	83.95 376	99.53 335	93.90 335	97.95 370

MVS		93.19 368	92.09 372	96.50 346	96.91 401	94.03 323	98.07 172	98.06 335	68.01 421	94.56 397	96.48 370	95.96 229	99.30 380	83.84 412	96.89 394	96.17 408

E-PMN		94.17 352	94.37 347	93.58 396	96.86 402	85.71 412	90.11 418	97.07 360	98.17 163	97.82 289	97.19 357	84.62 369	98.94 400	89.77 396	97.68 373	96.09 412

JIA-IIPM		95.52 330	95.03 336	97.00 326	96.85 403	94.03 323	96.93 291	95.82 385	99.20 67	94.63 396	99.71 19	83.09 381	99.60 309	94.42 320	94.64 411	97.36 396

EMVS		93.83 358	94.02 350	93.23 400	96.83 404	84.96 413	89.77 419	96.32 377	97.92 180	97.43 318	96.36 375	86.17 356	98.93 401	87.68 403	97.73 372	95.81 413

cl22		95.79 322	95.39 326	96.98 328	96.77 405	92.79 353	94.40 396	98.53 313	94.59 343	97.89 281	98.17 303	82.82 384	99.24 386	96.37 251	99.03 305	98.92 288

WB-MVSnew		95.73 324	95.57 318	96.23 356	96.70 406	90.70 390	96.07 338	93.86 403	95.60 318	97.04 333	95.45 395	96.00 222	99.55 328	91.04 387	98.31 350	98.43 347

dp		93.47 363	93.59 356	93.13 401	96.64 407	81.62 425	97.66 231	96.42 376	92.80 375	96.11 369	98.64 251	78.55 401	99.59 313	93.31 351	92.18 419	98.16 362

MonoMVSNet		96.25 308	96.53 295	95.39 377	96.57 408	91.01 384	98.82 90	97.68 344	98.57 130	98.03 274	99.37 86	90.92 325	97.78 415	94.99 302	93.88 415	97.38 395

test-LLR		93.90 357	93.85 351	94.04 390	96.53 409	84.62 416	94.05 402	92.39 409	96.17 297	94.12 400	95.07 396	82.30 385	99.67 277	95.87 278	98.18 355	97.82 377

test-mter		92.33 380	91.76 381	94.04 390	96.53 409	84.62 416	94.05 402	92.39 409	94.00 359	94.12 400	95.07 396	65.63 421	99.67 277	95.87 278	98.18 355	97.82 377

TESTMET0.1,1		92.19 382	91.77 380	93.46 397	96.48 411	82.80 422	94.05 402	91.52 414	94.45 348	94.00 403	94.88 402	66.65 417	99.56 324	95.78 283	98.11 361	98.02 369

MVS_0304		97.44 246	97.01 262	98.72 180	96.42 412	96.74 237	97.20 276	91.97 412	98.46 138	98.30 248	98.79 223	92.74 306	99.91 62	99.30 45	99.94 40	99.52 126

miper_enhance_ethall		96.01 314	95.74 309	96.81 338	96.41 413	92.27 365	93.69 407	98.89 271	91.14 393	98.30 248	97.35 355	90.58 328	99.58 319	96.31 255	99.03 305	98.60 331

tpmvs		95.02 340	95.25 330	94.33 386	96.39 414	85.87 409	98.08 170	96.83 369	95.46 323	95.51 385	98.69 239	85.91 359	99.53 335	94.16 326	96.23 401	97.58 390

CMPMVS	75.91 23	96.29 306	95.44 323	98.84 157	96.25 415	98.69 90	97.02 284	99.12 232	88.90 405	97.83 287	98.86 209	89.51 335	98.90 403	91.92 371	99.51 233	98.92 288
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 345	93.69 354	96.99 327	96.05 416	93.61 342	94.97 380	93.49 404	96.17 297	97.57 305	94.88 402	82.30 385	99.01 398	93.60 344	94.17 414	98.37 354

EPMVS		93.72 360	93.27 359	95.09 382	96.04 417	87.76 404	98.13 162	85.01 424	94.69 341	96.92 338	98.64 251	78.47 402	99.31 378	95.04 301	96.46 398	98.20 360

cascas		94.79 343	94.33 349	96.15 362	96.02 418	92.36 363	92.34 414	99.26 198	85.34 413	95.08 390	94.96 401	92.96 301	98.53 409	94.41 323	98.59 342	97.56 391

MVStest1		95.86 319	95.60 315	96.63 343	95.87 419	91.70 370	97.93 193	98.94 259	98.03 170	99.56 55	99.66 29	71.83 408	98.26 412	99.35 42	99.24 276	99.91 13

gg-mvs-nofinetune		92.37 379	91.20 383	95.85 365	95.80 420	92.38 362	99.31 27	81.84 426	99.75 8	91.83 415	99.74 15	68.29 412	99.02 396	87.15 404	97.12 390	96.16 409

gm-plane-assit					94.83 421	81.97 424			88.07 408		94.99 399		99.60 309	91.76 374

GG-mvs-BLEND				94.76 383	94.54 422	92.13 367	99.31 27	80.47 427		88.73 421	91.01 421	67.59 416	98.16 414	82.30 417	94.53 413	93.98 417

EPNet_dtu		94.93 342	94.78 342	95.38 378	93.58 423	87.68 405	96.78 298	95.69 389	97.35 232	89.14 420	98.09 310	88.15 347	99.49 348	94.95 305	99.30 267	98.98 276
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 390	75.95 393	77.12 406	92.39 424	67.91 430	90.16 417	59.44 431	82.04 417	89.42 419	94.67 405	49.68 429	81.74 424	48.06 424	77.66 422	81.72 420

KD-MVS_2432*1600		92.87 373	91.99 375	95.51 374	91.37 425	89.27 397	94.07 400	98.14 331	95.42 324	97.25 326	96.44 372	67.86 413	99.24 386	91.28 383	96.08 404	98.02 369

miper_refine_blended		92.87 373	91.99 375	95.51 374	91.37 425	89.27 397	94.07 400	98.14 331	95.42 324	97.25 326	96.44 372	67.86 413	99.24 386	91.28 383	96.08 404	98.02 369

EPNet		96.14 311	95.44 323	98.25 242	90.76 427	95.50 276	97.92 196	94.65 394	98.97 102	92.98 410	98.85 212	89.12 338	99.87 110	95.99 271	99.68 175	99.39 183
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 391	68.95 394	70.34 407	87.68 428	65.00 431	91.11 415	59.90 430	69.02 420	74.46 425	88.89 422	48.58 430	68.03 426	28.61 425	72.33 424	77.99 421

test_method		79.78 388	79.50 391	80.62 404	80.21 429	45.76 432	70.82 420	98.41 321	31.08 424	80.89 424	97.71 332	84.85 366	97.37 417	91.51 380	80.03 421	98.75 316

tmp_tt		78.77 389	78.73 392	78.90 405	58.45 430	74.76 429	94.20 399	78.26 428	39.16 423	86.71 422	92.82 417	80.50 389	75.19 425	86.16 409	92.29 418	86.74 419

testmvs		17.12 393	20.53 396	6.87 409	12.05 431	4.20 434	93.62 408	6.73 432	4.62 427	10.41 427	24.33 424	8.28 432	3.56 428	9.69 427	15.07 425	12.86 424

test123		17.04 394	20.11 397	7.82 408	10.25 432	4.91 433	94.80 383	4.47 433	4.93 426	10.00 428	24.28 425	9.69 431	3.64 427	10.14 426	12.43 426	14.92 423

mmdepth		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

monomultidepth		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

test_blank		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

eth-test2					0.00 433

eth-test					0.00 433

uanet_test		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

DCPMVS		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

cdsmvs_eth3d_5k		24.66 392	32.88 395	0.00 410	0.00 433	0.00 435	0.00 421	99.10 235	0.00 428	0.00 429	97.58 340	99.21 16	0.00 429	0.00 428	0.00 427	0.00 425

pcd_1.5k_mvsjas		8.17 395	10.90 398	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	98.07 95	0.00 429	0.00 428	0.00 427	0.00 425

sosnet-low-res		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

sosnet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uncertanet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

Regformer		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

ab-mvs-re		8.12 396	10.83 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	97.48 346	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uanet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

WAC-MVS						90.90 386								91.37 382

PC_three_1452									93.27 367	99.40 90	98.54 264	98.22 82	97.00 418	95.17 299	99.45 245	99.49 136

test_241102_TWO								99.30 179	98.03 170	99.26 118	99.02 165	97.51 142	99.88 93	96.91 199	99.60 202	99.66 62

test_0728_THIRD									98.17 163	99.08 140	99.02 165	97.89 108	99.88 93	97.07 187	99.71 160	99.70 56

GSMVS																98.81 305

sam_mvs1												84.74 368				98.81 305

sam_mvs												84.29 374

MTGPA								99.20 210

test_post1							97.59 241				20.48 427	83.07 382	99.66 288	94.16 326

test_post											21.25 426	83.86 377	99.70 261

patchmatchnet-post											98.77 227	84.37 371	99.85 130

MTMP							97.93 193	91.91 413

test9_res														93.28 352	99.15 292	99.38 190

agg_prior2														92.50 368	99.16 290	99.37 192

test_prior4						97.97 154	95.86 350

test_prior2							95.74 356		96.48 287	96.11 369	97.63 338	95.92 232		94.16 326	99.20 284

旧先验2							95.76 355		88.56 407	97.52 309			99.66 288	94.48 316

新几何2							95.93 346

无先验							95.74 356	98.74 300	89.38 403				99.73 249	92.38 370		99.22 237

原ACMM2							95.53 362

testdata2													99.79 209	92.80 362

segment_acmp												97.02 172

testdata1							95.44 367		96.32 293

plane_prior5								99.27 193					99.70 261	94.42 320	99.51 233	99.45 159

plane_prior4											97.98 317

plane_prior3						97.78 175			97.41 226	97.79 290

plane_prior2							97.77 216		98.20 160

plane_prior						97.65 184	97.07 283		96.72 277						99.36 256

n2								0.00 434

nn								0.00 434

door-mid								99.57 68

test11								98.87 274

door								99.41 133

HQP5-MVS						96.79 233

BP-MVS														92.82 360

HQP4-MVS										95.56 379			99.54 333			99.32 212

HQP3-MVS								99.04 246							99.26 274

HQP2-MVS												93.84 286

MDTV_nov1_ep13_2view						74.92 428	97.69 226		90.06 401	97.75 293		85.78 360		93.52 346		98.69 323

ACMMP++_ref															99.77 128

ACMMP++															99.68 175

Test By Simon												96.52 200

High-resolution multi-view benchmark