High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

LCM-MVSNet		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 13	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 16	100.00 1	99.85 29

Gipuma		99.03 79	99.16 61	98.64 210	99.94 2	98.51 108	99.32 26	99.75 42	99.58 38	98.60 259	99.62 40	98.22 103	99.51 388	97.70 184	99.73 176	97.89 421
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 29	99.31 41	99.53 38	99.91 3	98.98 71	99.63 7	99.58 83	99.44 52	99.78 39	99.76 15	96.39 241	99.92 64	99.44 54	99.92 68	99.68 69

pmmvs6		99.67 3	99.70 3	99.60 15	99.90 4	99.27 27	99.53 9	99.76 39	99.64 27	99.84 30	99.83 4	99.50 9	99.87 133	99.36 57	99.92 68	99.64 82

PS-MVSNAJss		99.46 17	99.49 16	99.35 76	99.90 4	98.15 135	99.20 48	99.65 67	99.48 44	99.92 8	99.71 22	98.07 117	99.96 14	99.53 47	100.00 1	99.93 11

testf1		99.25 41	99.16 61	99.51 48	99.89 6	99.63 4	98.71 104	99.69 54	98.90 132	99.43 102	99.35 103	98.86 34	99.67 314	97.81 173	99.81 127	99.24 269

APD_test2		99.25 41	99.16 61	99.51 48	99.89 6	99.63 4	98.71 104	99.69 54	98.90 132	99.43 102	99.35 103	98.86 34	99.67 314	97.81 173	99.81 127	99.24 269

ANet_high		99.57 10	99.67 6	99.28 92	99.89 6	98.09 142	99.14 57	99.93 5	99.82 8	99.93 6	99.81 8	99.17 20	99.94 42	99.31 61	100.00 1	99.82 35

anonymousdsp		99.51 14	99.47 21	99.62 9	99.88 9	99.08 69	99.34 23	99.69 54	98.93 128	99.65 63	99.72 21	98.93 32	99.95 26	99.11 77	100.00 1	99.82 35

v7n		99.53 12	99.57 13	99.41 66	99.88 9	98.54 106	99.45 14	99.61 76	99.66 24	99.68 57	99.66 32	98.44 77	99.95 26	99.73 27	99.96 28	99.75 58

mvs_tets		99.63 6	99.67 6	99.49 54	99.88 9	98.61 98	99.34 23	99.71 47	99.27 73	99.90 14	99.74 18	99.68 4	99.97 7	99.55 42	99.99 5	99.88 20

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 70	99.87 12	98.13 138	98.08 182	99.95 1	99.45 50	99.98 2	99.75 16	99.80 1	99.97 7	99.82 12	99.99 5	99.99 2

jajsoiax		99.58 9	99.61 11	99.48 56	99.87 12	98.61 98	99.28 40	99.66 63	99.09 107	99.89 18	99.68 25	99.53 7	99.97 7	99.50 50	99.99 5	99.87 21

test_djsdf		99.52 13	99.51 15	99.53 38	99.86 14	98.74 88	99.39 20	99.56 97	99.11 97	99.70 51	99.73 20	99.00 27	99.97 7	99.26 65	99.98 12	99.89 16

MIMVSNet1		99.38 28	99.32 39	99.55 28	99.86 14	99.19 42	99.41 17	99.59 81	99.59 36	99.71 49	99.57 49	97.12 197	99.90 80	99.21 70	99.87 96	99.54 137

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 26	99.85 16	99.11 64	99.90 1	99.78 36	99.63 29	99.78 39	99.67 30	99.48 10	99.81 217	99.30 62	99.97 21	99.77 49
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 20	99.69 5	99.58 83	99.90 3	99.86 24	99.78 13	99.58 6	99.95 26	99.00 87	99.95 38	99.78 46

SixPastTwentyTwo		98.75 126	98.62 139	99.16 114	99.83 18	97.96 162	99.28 40	98.20 368	99.37 60	99.70 51	99.65 36	92.65 347	99.93 53	99.04 84	99.84 110	99.60 98

sc_t1		99.62 7	99.66 8	99.53 38	99.82 19	99.09 68	99.50 11	99.63 71	99.88 4	99.86 24	99.80 11	99.03 24	99.89 96	99.48 52	99.93 55	99.60 98

Baseline_NR-MVSNet		98.98 87	98.86 105	99.36 70	99.82 19	98.55 103	97.47 286	99.57 90	99.37 60	99.21 155	99.61 43	96.76 223	99.83 191	98.06 151	99.83 117	99.71 61

pm-mvs1		99.44 19	99.48 18	99.33 85	99.80 21	98.63 95	99.29 36	99.63 71	99.30 70	99.65 63	99.60 45	99.16 22	99.82 201	99.07 80	99.83 117	99.56 124

TransMVSNet (Re)		99.44 19	99.47 21	99.36 70	99.80 21	98.58 101	99.27 42	99.57 90	99.39 58	99.75 44	99.62 40	99.17 20	99.83 191	99.06 82	99.62 231	99.66 76

K. test v3		98.00 241	97.66 266	99.03 141	99.79 23	97.56 198	99.19 52	92.47 454	99.62 32	99.52 84	99.66 32	89.61 378	99.96 14	99.25 67	99.81 127	99.56 124

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 79	99.78 24	98.11 139	97.77 238	99.90 11	99.33 65	99.97 3	99.66 32	99.71 3	99.96 14	99.79 19	99.99 5	99.96 8

APD_test1		98.83 110	98.66 132	99.34 79	99.78 24	99.47 9	98.42 144	99.45 145	98.28 184	98.98 188	99.19 145	97.76 145	99.58 362	96.57 277	99.55 258	98.97 323

test_vis3_rt		99.14 61	99.17 59	99.07 131	99.78 24	98.38 115	98.92 82	99.94 2	97.80 226	99.91 12	99.67 30	97.15 196	98.91 447	99.76 23	99.56 254	99.92 12

EGC-MVSNET		85.24 434	80.54 437	99.34 79	99.77 27	99.20 39	99.08 61	99.29 225	12.08 472	20.84 473	99.42 88	97.55 164	99.85 155	97.08 228	99.72 184	98.96 325

Anonymous20240521		98.69 138	98.87 101	98.16 286	99.77 27	95.11 327	99.08 61	99.44 153	99.34 64	99.33 125	99.55 57	94.10 322	99.94 42	99.25 67	99.96 28	99.42 199

FC-MVSNet-test		99.27 38	99.25 52	99.34 79	99.77 27	98.37 117	99.30 35	99.57 90	99.61 34	99.40 111	99.50 67	97.12 197	99.85 155	99.02 86	99.94 49	99.80 41

test_vis1_n		98.31 205	98.50 159	97.73 320	99.76 30	94.17 355	98.68 107	99.91 9	96.31 338	99.79 38	99.57 49	92.85 343	99.42 408	99.79 19	99.84 110	99.60 98

test_fmvs3		99.12 68	99.41 26	98.25 274	99.76 30	95.07 328	99.05 67	99.94 2	97.78 229	99.82 33	99.84 3	98.56 68	99.71 290	99.96 1	99.96 28	99.97 4

XXY-MVS		99.14 61	99.15 66	99.10 124	99.76 30	97.74 187	98.85 92	99.62 73	98.48 167	99.37 116	99.49 73	98.75 46	99.86 142	98.20 141	99.80 138	99.71 61

TDRefinement		99.42 24	99.38 29	99.55 28	99.76 30	99.33 21	99.68 6	99.71 47	99.38 59	99.53 82	99.61 43	98.64 56	99.80 225	98.24 136	99.84 110	99.52 149

fmvsm_s_conf0.1_n_a		99.17 52	99.30 44	98.80 178	99.75 34	96.59 261	97.97 212	99.86 16	98.22 187	99.88 21	99.71 22	98.59 62	99.84 173	99.73 27	99.98 12	99.98 3

tt0805		98.69 138	98.62 139	98.90 166	99.75 34	99.30 22	99.15 56	96.97 405	98.86 137	98.87 221	97.62 383	98.63 58	98.96 444	99.41 56	98.29 396	98.45 387

test_vis1_n_1920		98.40 188	98.92 94	96.81 382	99.74 36	90.76 433	98.15 170	99.91 9	98.33 175	99.89 18	99.55 57	95.07 293	99.88 114	99.76 23	99.93 55	99.79 43

FOURS1					99.73 37	99.67 3	99.43 15	99.54 106	99.43 54	99.26 143

PEN-MVS		99.41 25	99.34 36	99.62 9	99.73 37	99.14 57	99.29 36	99.54 106	99.62 32	99.56 73	99.42 88	98.16 111	99.96 14	98.78 101	99.93 55	99.77 49

lessismore_v0				98.97 153	99.73 37	97.53 200		86.71 469		99.37 116	99.52 66	89.93 374	99.92 64	98.99 88	99.72 184	99.44 192

SteuartSystems-ACMMP		98.79 119	98.54 152	99.54 31	99.73 37	99.16 48	98.23 160	99.31 209	97.92 217	98.90 210	98.90 231	98.00 123	99.88 114	96.15 309	99.72 184	99.58 113
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 226	98.15 218	98.22 280	99.73 37	95.15 324	97.36 299	99.68 59	94.45 395	98.99 187	99.27 122	96.87 212	99.94 42	97.13 225	99.91 77	99.57 118

Vis-MVSNet		99.34 30	99.36 33	99.27 95	99.73 37	98.26 124	99.17 53	99.78 36	99.11 97	99.27 139	99.48 74	98.82 37	99.95 26	98.94 91	99.93 55	99.59 105
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
tt0320-xc		99.64 5	99.68 5	99.50 53	99.72 43	98.98 71	99.51 10	99.85 18	99.86 6	99.88 21	99.82 5	99.02 26	99.90 80	99.54 43	99.95 38	99.61 96

SSC-MVS		98.71 130	98.74 116	98.62 216	99.72 43	96.08 285	98.74 97	98.64 348	99.74 13	99.67 59	99.24 135	94.57 308	99.95 26	99.11 77	99.24 320	99.82 35

test_f		98.67 146	98.87 101	98.05 295	99.72 43	95.59 300	98.51 128	99.81 31	96.30 340	99.78 39	99.82 5	96.14 252	98.63 454	99.82 12	99.93 55	99.95 9

ACMH	96.65 7	99.25 41	99.24 53	99.26 97	99.72 43	98.38 115	99.07 64	99.55 101	98.30 179	99.65 63	99.45 83	99.22 17	99.76 261	98.44 127	99.77 155	99.64 82
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		99.61 8	99.65 9	99.48 56	99.71 47	98.94 78	99.54 8	99.83 25	99.87 5	99.89 18	99.82 5	98.75 46	99.90 80	99.54 43	99.95 38	99.59 105

fmvsm_s_conf0.1_n		99.16 56	99.33 37	98.64 210	99.71 47	96.10 280	97.87 224	99.85 18	98.56 163	99.90 14	99.68 25	98.69 52	99.85 155	99.72 29	99.98 12	99.97 4

PS-CasMVS		99.40 26	99.33 37	99.62 9	99.71 47	99.10 65	99.29 36	99.53 110	99.53 41	99.46 97	99.41 92	98.23 100	99.95 26	98.89 95	99.95 38	99.81 39

DTE-MVSNet		99.43 23	99.35 34	99.66 7	99.71 47	99.30 22	99.31 30	99.51 116	99.64 27	99.56 73	99.46 79	98.23 100	99.97 7	98.78 101	99.93 55	99.72 60

WR-MVS_H		99.33 31	99.22 54	99.65 8	99.71 47	99.24 30	99.32 26	99.55 101	99.46 49	99.50 90	99.34 107	97.30 186	99.93 53	98.90 93	99.93 55	99.77 49

HPM-MVS_fast		99.01 81	98.82 109	99.57 21	99.71 47	99.35 17	99.00 72	99.50 119	97.33 274	98.94 205	98.86 241	98.75 46	99.82 201	97.53 196	99.71 193	99.56 124

ACMH+	96.62 9	99.08 75	99.00 86	99.33 85	99.71 47	98.83 83	98.60 114	99.58 83	99.11 97	99.53 82	99.18 149	98.81 38	99.67 314	96.71 266	99.77 155	99.50 155

PMVS	91.26 20	97.86 255	97.94 242	97.65 327	99.71 47	97.94 164	98.52 123	98.68 344	98.99 120	97.52 352	99.35 103	97.41 179	98.18 460	91.59 423	99.67 214	96.82 449
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
KinetiMVS		99.03 79	99.02 82	99.03 141	99.70 55	97.48 203	98.43 141	99.29 225	99.70 16	99.60 70	99.07 178	96.13 253	99.94 42	99.42 55	99.87 96	99.68 69

FIs		99.14 61	99.09 74	99.29 91	99.70 55	98.28 123	99.13 58	99.52 115	99.48 44	99.24 149	99.41 92	96.79 220	99.82 201	98.69 111	99.88 92	99.76 54

VPNet		98.87 101	98.83 108	99.01 145	99.70 55	97.62 196	98.43 141	99.35 190	99.47 47	99.28 137	99.05 186	96.72 226	99.82 201	98.09 148	99.36 299	99.59 105

fmvsm_s_conf0.1_n_2		99.20 50	99.38 29	98.65 208	99.69 58	96.08 285	97.49 283	99.90 11	99.53 41	99.88 21	99.64 37	98.51 71	99.90 80	99.83 10	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 202	98.68 129	97.27 358	99.69 58	92.29 407	98.03 193	99.85 18	97.62 239	99.96 4	99.62 40	93.98 323	99.74 274	99.52 49	99.86 103	99.79 43

MP-MVS-pluss		98.57 162	98.23 206	99.60 15	99.69 58	99.35 17	97.16 320	99.38 176	94.87 385	98.97 192	98.99 208	98.01 122	99.88 114	97.29 212	99.70 200	99.58 113
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 46	99.32 39	98.96 154	99.68 61	97.35 211	98.84 94	99.48 128	99.69 18	99.63 66	99.68 25	99.03 24	99.96 14	97.97 161	99.92 68	99.57 118

sd_testset		99.28 37	99.31 41	99.19 108	99.68 61	98.06 151	99.41 17	99.30 217	99.69 18	99.63 66	99.68 25	99.25 16	99.96 14	97.25 215	99.92 68	99.57 118

test_fmvs1_n		98.09 232	98.28 197	97.52 344	99.68 61	93.47 386	98.63 110	99.93 5	95.41 373	99.68 57	99.64 37	91.88 357	99.48 395	99.82 12	99.87 96	99.62 88

CHOSEN 1792x2688		97.49 284	97.14 299	98.54 238	99.68 61	96.09 283	96.50 356	99.62 73	91.58 433	98.84 224	98.97 215	92.36 349	99.88 114	96.76 259	99.95 38	99.67 74

tfpnnormal		98.90 97	98.90 96	98.91 163	99.67 65	97.82 179	99.00 72	99.44 153	99.45 50	99.51 89	99.24 135	98.20 106	99.86 142	95.92 318	99.69 203	99.04 310

MTAPA		98.88 100	98.64 135	99.61 13	99.67 65	99.36 16	98.43 141	99.20 249	98.83 141	98.89 213	98.90 231	96.98 207	99.92 64	97.16 220	99.70 200	99.56 124

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 238	99.66 67	96.97 241	98.00 200	99.85 18	99.24 75	99.92 8	99.50 67	99.39 12	99.95 26	99.89 3	99.98 12	98.71 364

mvs5depth		99.30 34	99.59 12	98.44 252	99.65 68	95.35 316	99.82 3	99.94 2	99.83 7	99.42 106	99.94 2	98.13 114	99.96 14	99.63 35	99.96 28	100.00 1

fmvsm_l_conf0.5_n_a		99.19 51	99.27 47	98.94 157	99.65 68	97.05 236	97.80 233	99.76 39	98.70 146	99.78 39	99.11 168	98.79 42	99.95 26	99.85 6	99.96 28	99.83 32

WB-MVS		98.52 176	98.55 150	98.43 253	99.65 68	95.59 300	98.52 123	98.77 333	99.65 26	99.52 84	99.00 206	94.34 314	99.93 53	98.65 113	98.83 368	99.76 54

CP-MVSNet		99.21 48	99.09 74	99.56 26	99.65 68	98.96 77	99.13 58	99.34 196	99.42 55	99.33 125	99.26 128	97.01 205	99.94 42	98.74 106	99.93 55	99.79 43

HPM-MVS		98.79 119	98.53 154	99.59 19	99.65 68	99.29 24	99.16 54	99.43 159	96.74 320	98.61 257	98.38 328	98.62 59	99.87 133	96.47 289	99.67 214	99.59 105
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 155	98.36 185	99.42 64	99.65 68	99.42 11	98.55 119	99.57 90	97.72 233	98.90 210	99.26 128	96.12 255	99.52 383	95.72 329	99.71 193	99.32 246

NormalMVS		98.26 212	97.97 239	99.15 117	99.64 74	97.83 174	98.28 154	99.43 159	99.24 75	98.80 232	98.85 244	89.76 376	99.94 42	98.04 153	99.67 214	99.68 69

lecture		99.25 41	99.12 69	99.62 9	99.64 74	99.40 12	98.89 87	99.51 116	99.19 87	99.37 116	99.25 133	98.36 82	99.88 114	98.23 138	99.67 214	99.59 105

fmvsm_l_conf0.5_n		99.21 48	99.28 46	99.02 144	99.64 74	97.28 218	97.82 229	99.76 39	98.73 143	99.82 33	99.09 176	98.81 38	99.95 26	99.86 4	99.96 28	99.83 32

test_fmvsmconf_n		99.44 19	99.48 18	99.31 90	99.64 74	98.10 141	97.68 252	99.84 22	99.29 71	99.92 8	99.57 49	99.60 5	99.96 14	99.74 26	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 152	98.49 164	99.06 137	99.64 74	97.90 168	98.51 128	98.94 298	96.96 305	99.24 149	98.89 237	97.83 137	99.81 217	96.88 249	99.49 279	99.48 173
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 113	98.72 120	99.12 120	99.64 74	98.54 106	97.98 208	99.68 59	97.62 239	99.34 123	99.18 149	97.54 166	99.77 255	97.79 175	99.74 173	99.04 310

Elysia		99.15 57	99.14 67	99.18 109	99.63 80	97.92 165	98.50 130	99.43 159	99.67 21	99.70 51	99.13 164	96.66 229	99.98 4	99.54 43	99.96 28	99.64 82

StellarMVS		99.15 57	99.14 67	99.18 109	99.63 80	97.92 165	98.50 130	99.43 159	99.67 21	99.70 51	99.13 164	96.66 229	99.98 4	99.54 43	99.96 28	99.64 82

KD-MVS_self_test		99.25 41	99.18 58	99.44 63	99.63 80	99.06 70	98.69 106	99.54 106	99.31 68	99.62 69	99.53 63	97.36 183	99.86 142	99.24 69	99.71 193	99.39 212

EU-MVSNet		97.66 272	98.50 159	95.13 424	99.63 80	85.84 455	98.35 150	98.21 367	98.23 186	99.54 78	99.46 79	95.02 294	99.68 310	98.24 136	99.87 96	99.87 21

HyFIR lowres test		97.19 310	96.60 334	98.96 154	99.62 84	97.28 218	95.17 421	99.50 119	94.21 400	99.01 184	98.32 336	86.61 396	99.99 2	97.10 227	99.84 110	99.60 98

fmvsm_l_conf0.5_n_9		99.32 33	99.43 24	98.98 151	99.59 85	97.18 229	97.44 289	99.83 25	99.56 39	99.91 12	99.34 107	99.36 13	99.93 53	99.83 10	99.98 12	99.85 29

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 79	99.59 85	98.21 132	97.82 229	99.84 22	99.41 57	99.92 8	99.41 92	99.51 8	99.95 26	99.84 9	99.97 21	99.87 21

FE-MVSNET		98.59 159	98.50 159	98.87 167	99.58 87	97.30 216	98.08 182	99.74 43	96.94 307	98.97 192	99.10 171	96.94 208	99.74 274	97.33 210	99.86 103	99.55 131

mmtdpeth		99.30 34	99.42 25	98.92 162	99.58 87	96.89 248	99.48 13	99.92 7	99.92 2	98.26 295	99.80 11	98.33 88	99.91 73	99.56 40	99.95 38	99.97 4

ACMMP_NAP		98.75 126	98.48 165	99.57 21	99.58 87	99.29 24	97.82 229	99.25 238	96.94 307	98.78 234	99.12 167	98.02 121	99.84 173	97.13 225	99.67 214	99.59 105

nrg030		99.40 26	99.35 34	99.54 31	99.58 87	99.13 60	98.98 75	99.48 128	99.68 20	99.46 97	99.26 128	98.62 59	99.73 281	99.17 74	99.92 68	99.76 54

VDDNet		98.21 219	97.95 240	99.01 145	99.58 87	97.74 187	99.01 70	97.29 396	99.67 21	98.97 192	99.50 67	90.45 371	99.80 225	97.88 168	99.20 328	99.48 173

COLMAP_ROB	96.50 10	98.99 84	98.85 107	99.41 66	99.58 87	99.10 65	98.74 97	99.56 97	99.09 107	99.33 125	99.19 145	98.40 79	99.72 289	95.98 316	99.76 168	99.42 199
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvsm_n_1920		99.33 31	99.45 23	98.99 147	99.57 93	97.73 189	97.93 213	99.83 25	99.22 78	99.93 6	99.30 116	99.42 11	99.96 14	99.85 6	99.99 5	99.29 255

ZNCC-MVS		98.68 143	98.40 177	99.54 31	99.57 93	99.21 33	98.46 138	99.29 225	97.28 280	98.11 307	98.39 326	98.00 123	99.87 133	96.86 252	99.64 225	99.55 131

MSP-MVS		98.40 188	98.00 234	99.61 13	99.57 93	99.25 29	98.57 117	99.35 190	97.55 250	99.31 133	97.71 376	94.61 307	99.88 114	96.14 310	99.19 331	99.70 66
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		98.32 203	98.39 180	98.13 287	99.57 93	95.54 303	97.78 235	99.49 126	97.37 271	99.19 157	97.65 380	98.96 29	99.49 392	96.50 288	98.99 356	99.34 237

MP-MVS		98.46 182	98.09 223	99.54 31	99.57 93	99.22 32	98.50 130	99.19 253	97.61 242	97.58 346	98.66 288	97.40 180	99.88 114	94.72 355	99.60 238	99.54 137
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 130	98.46 169	99.47 60	99.57 93	98.97 73	98.23 160	99.48 128	96.60 325	99.10 167	99.06 179	98.71 50	99.83 191	95.58 336	99.78 149	99.62 88

LGP-MVS_train				99.47 60	99.57 93	98.97 73		99.48 128	96.60 325	99.10 167	99.06 179	98.71 50	99.83 191	95.58 336	99.78 149	99.62 88

IS-MVSNet		98.19 222	97.90 248	99.08 129	99.57 93	97.97 159	99.31 30	98.32 363	99.01 119	98.98 188	99.03 190	91.59 359	99.79 238	95.49 338	99.80 138	99.48 173

viewdifsd2359ckpt11		98.84 107	99.04 79	98.24 276	99.56 101	95.51 305	97.38 294	99.70 52	99.16 92	99.57 71	99.40 95	98.26 96	99.71 290	98.55 122	99.82 121	99.50 155

viewmsd2359difaftdt		98.84 107	99.04 79	98.24 276	99.56 101	95.51 305	97.38 294	99.70 52	99.16 92	99.57 71	99.40 95	98.26 96	99.71 290	98.55 122	99.82 121	99.50 155

dcpmvs_2		98.78 121	99.11 70	97.78 310	99.56 101	93.67 381	99.06 65	99.86 16	99.50 43	99.66 60	99.26 128	97.21 194	99.99 2	98.00 158	99.91 77	99.68 69

test_0402		98.76 125	98.71 123	98.93 159	99.56 101	98.14 137	98.45 140	99.34 196	99.28 72	98.95 198	98.91 228	98.34 87	99.79 238	95.63 333	99.91 77	98.86 342

EPP-MVSNet		98.30 206	98.04 230	99.07 131	99.56 101	97.83 174	99.29 36	98.07 374	99.03 117	98.59 261	99.13 164	92.16 353	99.90 80	96.87 250	99.68 208	99.49 162

ACMMP		98.75 126	98.50 159	99.52 44	99.56 101	99.16 48	98.87 88	99.37 180	97.16 295	98.82 228	99.01 202	97.71 148	99.87 133	96.29 301	99.69 203	99.54 137
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 70	99.20 57	98.78 184	99.55 107	96.59 261	97.79 234	99.82 30	98.21 189	99.81 36	99.53 63	98.46 75	99.84 173	99.70 32	99.97 21	99.90 15

fmvsm_s_conf0.5_n		99.09 71	99.26 50	98.61 219	99.55 107	96.09 283	97.74 245	99.81 31	98.55 164	99.85 27	99.55 57	98.60 61	99.84 173	99.69 34	99.98 12	99.89 16

FMVSNet1		99.17 52	99.17 59	99.17 111	99.55 107	98.24 126	99.20 48	99.44 153	99.21 80	99.43 102	99.55 57	97.82 140	99.86 142	98.42 129	99.89 90	99.41 202

Vis-MVSNet (Re-imp)		97.46 286	97.16 296	98.34 265	99.55 107	96.10 280	98.94 80	98.44 357	98.32 177	98.16 301	98.62 297	88.76 383	99.73 281	93.88 381	99.79 144	99.18 289

ACMM	96.08 12	98.91 95	98.73 118	99.48 56	99.55 107	99.14 57	98.07 186	99.37 180	97.62 239	99.04 180	98.96 218	98.84 36	99.79 238	97.43 205	99.65 223	99.49 162
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 135	98.97 90	97.89 303	99.54 112	94.05 358	98.55 119	99.92 7	96.78 318	99.72 47	99.78 13	96.60 233	99.67 314	99.91 2	99.90 84	99.94 10

mPP-MVS		98.64 150	98.34 188	99.54 31	99.54 112	99.17 44	98.63 110	99.24 243	97.47 258	98.09 309	98.68 283	97.62 157	99.89 96	96.22 304	99.62 231	99.57 118

XVG-ACMP-BASELINE		98.56 163	98.34 188	99.22 105	99.54 112	98.59 100	97.71 248	99.46 141	97.25 283	98.98 188	98.99 208	97.54 166	99.84 173	95.88 319	99.74 173	99.23 271

viewmacassd2359aftdt		98.86 104	98.87 101	98.83 172	99.53 115	97.32 215	97.70 250	99.64 69	98.22 187	99.25 147	99.27 122	98.40 79	99.61 348	97.98 160	99.87 96	99.55 131

region2R		98.69 138	98.40 177	99.54 31	99.53 115	99.17 44	98.52 123	99.31 209	97.46 263	98.44 280	98.51 311	97.83 137	99.88 114	96.46 290	99.58 247	99.58 113

PGM-MVS		98.66 147	98.37 184	99.55 28	99.53 115	99.18 43	98.23 160	99.49 126	97.01 304	98.69 245	98.88 238	98.00 123	99.89 96	95.87 322	99.59 242	99.58 113

Patchmatch-RL test		97.26 303	97.02 304	97.99 299	99.52 118	95.53 304	96.13 381	99.71 47	97.47 258	99.27 139	99.16 155	84.30 417	99.62 341	97.89 165	99.77 155	98.81 350

ACMMPR		98.70 135	98.42 175	99.54 31	99.52 118	99.14 57	98.52 123	99.31 209	97.47 258	98.56 267	98.54 306	97.75 146	99.88 114	96.57 277	99.59 242	99.58 113

fmvsm_s_conf0.5_n_9		99.17 52	99.38 29	98.53 240	99.51 120	95.82 295	97.62 263	99.78 36	99.72 15	99.90 14	99.48 74	98.66 54	99.89 96	99.85 6	99.93 55	99.89 16

AstraMVS		98.16 228	98.07 228	98.41 255	99.51 120	95.86 292	98.00 200	95.14 437	98.97 123	99.43 102	99.24 135	93.25 331	99.84 173	99.21 70	99.87 96	99.54 137

fmvsm_s_conf0.5_n_8		99.13 65	99.26 50	98.74 197	99.51 120	96.44 272	97.65 258	99.65 67	99.66 24	99.78 39	99.48 74	97.92 131	99.93 53	99.72 29	99.95 38	99.87 21

GST-MVS		98.61 156	98.30 194	99.52 44	99.51 120	99.20 39	98.26 158	99.25 238	97.44 266	98.67 248	98.39 326	97.68 149	99.85 155	96.00 314	99.51 269	99.52 149

Anonymous20231206		98.21 219	98.21 207	98.20 281	99.51 120	95.43 314	98.13 172	99.32 204	96.16 344	98.93 206	98.82 254	96.00 260	99.83 191	97.32 211	99.73 176	99.36 230

ACMP	95.32 15	98.41 186	98.09 223	99.36 70	99.51 120	98.79 86	97.68 252	99.38 176	95.76 360	98.81 230	98.82 254	98.36 82	99.82 201	94.75 352	99.77 155	99.48 173
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 194	98.20 208	98.98 151	99.50 126	97.49 201	97.78 235	97.69 383	98.75 142	99.49 91	99.25 133	92.30 351	99.94 42	99.14 75	99.88 92	99.50 155

DVP-MVS		98.77 124	98.52 155	99.52 44	99.50 126	99.21 33	98.02 196	98.84 322	97.97 211	99.08 169	99.02 191	97.61 159	99.88 114	96.99 236	99.63 228	99.48 173
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 15	99.50 126	99.23 31	98.02 196	99.32 204					99.88 114	96.99 236	99.63 228	99.68 69

test0726					99.50 126	99.21 33	98.17 168	99.35 190	97.97 211	99.26 143	99.06 179	97.61 159

AllTest		98.44 184	98.20 208	99.16 114	99.50 126	98.55 103	98.25 159	99.58 83	96.80 316	98.88 217	99.06 179	97.65 152	99.57 364	94.45 362	99.61 236	99.37 223

TestCases				99.16 114	99.50 126	98.55 103		99.58 83	96.80 316	98.88 217	99.06 179	97.65 152	99.57 364	94.45 362	99.61 236	99.37 223

XVG-OURS		98.53 172	98.34 188	99.11 122	99.50 126	98.82 85	95.97 387	99.50 119	97.30 278	99.05 178	98.98 213	99.35 14	99.32 422	95.72 329	99.68 208	99.18 289

EG-PatchMatch MVS		98.99 84	99.01 84	98.94 157	99.50 126	97.47 204	98.04 191	99.59 81	98.15 204	99.40 111	99.36 102	98.58 67	99.76 261	98.78 101	99.68 208	99.59 105

fmvsm_s_conf0.5_n_2		99.14 61	99.31 41	98.63 214	99.49 134	96.08 285	97.38 294	99.81 31	99.48 44	99.84 30	99.57 49	98.46 75	99.89 96	99.82 12	99.97 21	99.91 13

SED-MVS		98.91 95	98.72 120	99.49 54	99.49 134	99.17 44	98.10 179	99.31 209	98.03 207	99.66 60	99.02 191	98.36 82	99.88 114	96.91 242	99.62 231	99.41 202

IU-MVS					99.49 134	99.15 52		98.87 313	92.97 418	99.41 108				96.76 259	99.62 231	99.66 76

test_241102_ONE					99.49 134	99.17 44		99.31 209	97.98 210	99.66 60	98.90 231	98.36 82	99.48 395

UA-Net		99.47 16	99.40 27	99.70 2	99.49 134	99.29 24	99.80 4	99.72 45	99.82 8	99.04 180	99.81 8	98.05 120	99.96 14	98.85 97	99.99 5	99.86 27

HFP-MVS		98.71 130	98.44 172	99.51 48	99.49 134	99.16 48	98.52 123	99.31 209	97.47 258	98.58 263	98.50 315	97.97 127	99.85 155	96.57 277	99.59 242	99.53 146

VPA-MVSNet		99.30 34	99.30 44	99.28 92	99.49 134	98.36 120	99.00 72	99.45 145	99.63 29	99.52 84	99.44 84	98.25 98	99.88 114	99.09 79	99.84 110	99.62 88

XVG-OURS-SEG-HR		98.49 179	98.28 197	99.14 118	99.49 134	98.83 83	96.54 352	99.48 128	97.32 276	99.11 164	98.61 299	99.33 15	99.30 425	96.23 303	98.38 392	99.28 258

114514_t		96.50 343	95.77 352	98.69 203	99.48 142	97.43 208	97.84 228	99.55 101	81.42 465	96.51 405	98.58 303	95.53 280	99.67 314	93.41 394	99.58 247	98.98 320

IterMVS-LS		98.55 167	98.70 126	98.09 288	99.48 142	94.73 338	97.22 314	99.39 174	98.97 123	99.38 114	99.31 115	96.00 260	99.93 53	98.58 116	99.97 21	99.60 98
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_10		99.15 57	99.27 47	98.78 184	99.47 144	96.56 266	97.75 244	99.71 47	99.60 35	99.74 46	99.44 84	97.96 128	99.95 26	99.86 4	99.94 49	99.82 35

fmvsm_s_conf0.5_n_5		99.07 77	99.10 72	98.99 147	99.47 144	97.22 223	97.40 291	99.83 25	97.61 242	99.85 27	99.30 116	98.80 40	99.95 26	99.71 31	99.90 84	99.78 46

v8		99.01 81	99.16 61	98.57 226	99.47 144	96.31 277	98.90 83	99.47 137	99.03 117	99.52 84	99.57 49	96.93 209	99.81 217	99.60 36	99.98 12	99.60 98

SSC-MVS3.2		98.53 172	98.79 112	97.74 317	99.46 147	93.62 384	96.45 358	99.34 196	99.33 65	98.93 206	98.70 279	97.90 132	99.90 80	99.12 76	99.92 68	99.69 68

fmvsm_s_conf0.5_n_3		99.22 47	99.37 32	98.78 184	99.46 147	96.58 264	97.65 258	99.72 45	99.47 47	99.86 24	99.50 67	98.94 30	99.89 96	99.75 25	99.97 21	99.86 27

XVS		98.72 129	98.45 170	99.53 38	99.46 147	99.21 33	98.65 108	99.34 196	98.62 153	97.54 350	98.63 295	97.50 172	99.83 191	96.79 255	99.53 264	99.56 124

X-MVStestdata		94.32 392	92.59 411	99.53 38	99.46 147	99.21 33	98.65 108	99.34 196	98.62 153	97.54 350	45.85 470	97.50 172	99.83 191	96.79 255	99.53 264	99.56 124

test20.03		98.78 121	98.77 115	98.78 184	99.46 147	97.20 226	97.78 235	99.24 243	99.04 116	99.41 108	98.90 231	97.65 152	99.76 261	97.70 184	99.79 144	99.39 212

guyue		98.01 240	97.93 244	98.26 272	99.45 152	95.48 309	98.08 182	96.24 420	98.89 134	99.34 123	99.14 162	91.32 363	99.82 201	99.07 80	99.83 117	99.48 173

CSCG		98.68 143	98.50 159	99.20 106	99.45 152	98.63 95	98.56 118	99.57 90	97.87 221	98.85 222	98.04 357	97.66 151	99.84 173	96.72 264	99.81 127	99.13 299

GeoE		99.05 78	98.99 88	99.25 100	99.44 154	98.35 121	98.73 101	99.56 97	98.42 170	98.91 209	98.81 257	98.94 30	99.91 73	98.35 131	99.73 176	99.49 162

v148		98.45 183	98.60 144	98.00 298	99.44 154	94.98 330	97.44 289	99.06 279	98.30 179	99.32 131	98.97 215	96.65 231	99.62 341	98.37 130	99.85 105	99.39 212

v10		98.97 88	99.11 70	98.55 233	99.44 154	96.21 279	98.90 83	99.55 101	98.73 143	99.48 92	99.60 45	96.63 232	99.83 191	99.70 32	99.99 5	99.61 96

V42		98.78 121	98.78 114	98.76 191	99.44 154	97.04 237	98.27 157	99.19 253	97.87 221	99.25 147	99.16 155	96.84 213	99.78 249	99.21 70	99.84 110	99.46 183

MDA-MVSNet-bldmvs		97.94 246	97.91 247	98.06 293	99.44 154	94.96 331	96.63 348	99.15 269	98.35 173	98.83 225	99.11 168	94.31 315	99.85 155	96.60 274	98.72 374	99.37 223

viewdifsd2359ckpt07		98.71 130	98.86 105	98.26 272	99.43 159	95.65 299	97.20 315	99.66 63	99.20 82	99.29 135	99.01 202	98.29 91	99.73 281	97.92 164	99.75 172	99.39 212

casdiffmvs_mvg		99.12 68	99.16 61	98.99 147	99.43 159	97.73 189	98.00 200	99.62 73	99.22 78	99.55 76	99.22 141	98.93 32	99.75 269	98.66 112	99.81 127	99.50 155
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SSM_0404		98.90 97	99.01 84	98.57 226	99.42 161	96.59 261	98.13 172	99.66 63	99.09 107	99.30 134	99.02 191	98.79 42	99.89 96	97.87 170	99.80 138	99.23 271

test1111		96.49 344	96.82 318	95.52 417	99.42 161	87.08 452	99.22 45	87.14 468	99.11 97	99.46 97	99.58 47	88.69 384	99.86 142	98.80 99	99.95 38	99.62 88

v2v482		98.56 163	98.62 139	98.37 262	99.42 161	95.81 296	97.58 271	99.16 264	97.90 219	99.28 137	99.01 202	95.98 265	99.79 238	99.33 59	99.90 84	99.51 152

OPM-MVS		98.56 163	98.32 192	99.25 100	99.41 164	98.73 91	97.13 322	99.18 257	97.10 298	98.75 240	98.92 226	98.18 107	99.65 332	96.68 268	99.56 254	99.37 223
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 234	98.08 226	98.04 296	99.41 164	94.59 344	94.59 439	99.40 172	97.50 255	98.82 228	98.83 251	96.83 215	99.84 173	97.50 199	99.81 127	99.71 61

test_one_0601					99.39 166	99.20 39		99.31 209	98.49 166	98.66 250	99.02 191	97.64 155

mvsany_test3		98.87 101	98.92 94	98.74 197	99.38 167	96.94 245	98.58 116	99.10 274	96.49 330	99.96 4	99.81 8	98.18 107	99.45 403	98.97 89	99.79 144	99.83 32

patch_mono-2		98.51 177	98.63 137	98.17 284	99.38 167	94.78 335	97.36 299	99.69 54	98.16 199	98.49 276	99.29 119	97.06 200	99.97 7	98.29 135	99.91 77	99.76 54

test2506		92.39 423	91.89 425	93.89 438	99.38 167	82.28 469	99.32 26	66.03 476	99.08 111	98.77 237	99.57 49	66.26 464	99.84 173	98.71 109	99.95 38	99.54 137

ECVR-MVS		96.42 346	96.61 332	95.85 409	99.38 167	88.18 447	99.22 45	86.00 470	99.08 111	99.36 119	99.57 49	88.47 389	99.82 201	98.52 124	99.95 38	99.54 137

casdiffmvs		98.95 91	99.00 86	98.81 176	99.38 167	97.33 213	97.82 229	99.57 90	99.17 91	99.35 121	99.17 153	98.35 86	99.69 301	98.46 126	99.73 176	99.41 202
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 90	99.02 82	98.76 191	99.38 167	97.26 220	98.49 133	99.50 119	98.86 137	99.19 157	99.06 179	98.23 100	99.69 301	98.71 109	99.76 168	99.33 243

TranMVSNet+NR-MVSNet		99.17 52	99.07 77	99.46 62	99.37 173	98.87 81	98.39 146	99.42 165	99.42 55	99.36 119	99.06 179	98.38 81	99.95 26	98.34 132	99.90 84	99.57 118

fmvsm_s_conf0.5_n_6		99.08 75	99.21 56	98.69 203	99.36 174	96.51 267	97.62 263	99.68 59	98.43 169	99.85 27	99.10 171	99.12 23	99.88 114	99.77 22	99.92 68	99.67 74

tttt0517		95.64 371	94.98 381	97.64 330	99.36 174	93.81 376	98.72 102	90.47 462	98.08 206	98.67 248	98.34 333	73.88 450	99.92 64	97.77 177	99.51 269	99.20 281

test_part2					99.36 174	99.10 65				99.05 178

v1144		98.60 157	98.66 132	98.41 255	99.36 174	95.90 290	97.58 271	99.34 196	97.51 254	99.27 139	99.15 159	96.34 246	99.80 225	99.47 53	99.93 55	99.51 152

CP-MVS		98.70 135	98.42 175	99.52 44	99.36 174	99.12 62	98.72 102	99.36 184	97.54 252	98.30 289	98.40 325	97.86 136	99.89 96	96.53 286	99.72 184	99.56 124

diffmvs_AUTHOR		98.50 178	98.59 146	98.23 279	99.35 179	95.48 309	96.61 349	99.60 77	98.37 171	98.90 210	99.00 206	97.37 182	99.76 261	98.22 139	99.85 105	99.46 183

Test_1112_low_res		96.99 325	96.55 336	98.31 268	99.35 179	95.47 312	95.84 399	99.53 110	91.51 435	96.80 392	98.48 318	91.36 362	99.83 191	96.58 275	99.53 264	99.62 88

DeepC-MVS	97.60 4	98.97 88	98.93 93	99.10 124	99.35 179	97.98 158	98.01 199	99.46 141	97.56 248	99.54 78	99.50 67	98.97 28	99.84 173	98.06 151	99.92 68	99.49 162
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 302	96.86 314	98.58 223	99.34 182	96.32 276	96.75 341	99.58 83	93.14 416	96.89 387	97.48 390	92.11 354	99.86 142	96.91 242	99.54 260	99.57 118

reproduce_model		99.15 57	98.97 90	99.67 4	99.33 183	99.44 10	98.15 170	99.47 137	99.12 96	99.52 84	99.32 114	98.31 89	99.90 80	97.78 176	99.73 176	99.66 76

MVSMamba_PlusPlus		98.83 110	98.98 89	98.36 263	99.32 184	96.58 264	98.90 83	99.41 169	99.75 11	98.72 243	99.50 67	96.17 251	99.94 42	99.27 64	99.78 149	98.57 380

fmvsm_s_conf0.5_n_4		99.01 81	99.22 54	98.38 259	99.31 185	95.48 309	97.56 273	99.73 44	98.87 135	99.75 44	99.27 122	98.80 40	99.86 142	99.80 17	99.90 84	99.81 39

SF-MVS		98.53 172	98.27 200	99.32 87	99.31 185	98.75 87	98.19 164	99.41 169	96.77 319	98.83 225	98.90 231	97.80 142	99.82 201	95.68 332	99.52 267	99.38 221

CPTT-MVS		97.84 261	97.36 285	99.27 95	99.31 185	98.46 111	98.29 153	99.27 232	94.90 384	97.83 330	98.37 329	94.90 296	99.84 173	93.85 383	99.54 260	99.51 152

UnsupCasMVSNet_eth		97.89 250	97.60 271	98.75 193	99.31 185	97.17 231	97.62 263	99.35 190	98.72 145	98.76 239	98.68 283	92.57 348	99.74 274	97.76 181	95.60 454	99.34 237

fmvsm_s_conf0.5_n_7		98.83 110	99.04 79	98.20 281	99.30 189	94.83 333	97.23 310	99.36 184	98.64 148	99.84 30	99.43 87	98.10 116	99.91 73	99.56 40	99.96 28	99.87 21

pmmvs-eth3d		98.47 181	98.34 188	98.86 169	99.30 189	97.76 185	97.16 320	99.28 229	95.54 366	99.42 106	99.19 145	97.27 189	99.63 338	97.89 165	99.97 21	99.20 281

mamv4		99.44 19	99.39 28	99.58 20	99.30 189	99.74 2	99.04 68	99.81 31	99.77 10	99.82 33	99.57 49	97.82 140	99.98 4	99.53 47	99.89 90	99.01 314

viewcassd2359sk11		98.55 167	98.51 156	98.67 206	99.29 192	96.99 240	97.39 292	99.54 106	97.73 231	98.81 230	99.08 177	97.55 164	99.66 325	97.52 198	99.67 214	99.36 230

SymmetryMVS		98.05 236	97.71 261	99.09 128	99.29 192	97.83 174	98.28 154	97.64 388	99.24 75	98.80 232	98.85 244	89.76 376	99.94 42	98.04 153	99.50 277	99.49 162

Anonymous20231211		99.27 38	99.27 47	99.26 97	99.29 192	98.18 133	99.49 12	99.51 116	99.70 16	99.80 37	99.68 25	96.84 213	99.83 191	99.21 70	99.91 77	99.77 49

viewmanbaseed2359cas		98.58 161	98.54 152	98.70 201	99.28 195	97.13 235	97.47 286	99.55 101	97.55 250	98.96 197	98.92 226	97.77 144	99.59 355	97.59 192	99.77 155	99.39 212

UnsupCasMVSNet_bld		97.30 300	96.92 310	98.45 250	99.28 195	96.78 255	96.20 375	99.27 232	95.42 370	98.28 293	98.30 337	93.16 334	99.71 290	94.99 346	97.37 430	98.87 341

EC-MVSNet		99.09 71	99.05 78	99.20 106	99.28 195	98.93 79	99.24 44	99.84 22	99.08 111	98.12 306	98.37 329	98.72 49	99.90 80	99.05 83	99.77 155	98.77 358

mamba_0408		98.80 117	98.88 99	98.55 233	99.27 198	96.50 268	98.00 200	99.60 77	98.93 128	99.22 152	98.84 249	98.59 62	99.89 96	97.74 182	99.72 184	99.27 259

SSM_04072		98.80 117	98.88 99	98.56 231	99.27 198	96.50 268	98.00 200	99.60 77	98.93 128	99.22 152	98.84 249	98.59 62	99.90 80	97.74 182	99.72 184	99.27 259

SSM_0407		98.86 104	98.96 92	98.55 233	99.27 198	96.50 268	98.04 191	99.66 63	99.09 107	99.22 152	99.02 191	98.79 42	99.87 133	97.87 170	99.72 184	99.27 259

reproduce-ours		99.09 71	98.90 96	99.67 4	99.27 198	99.49 6	98.00 200	99.42 165	99.05 114	99.48 92	99.27 122	98.29 91	99.89 96	97.61 189	99.71 193	99.62 88

our_new_method		99.09 71	98.90 96	99.67 4	99.27 198	99.49 6	98.00 200	99.42 165	99.05 114	99.48 92	99.27 122	98.29 91	99.89 96	97.61 189	99.71 193	99.62 88

DPE-MVS		98.59 159	98.26 201	99.57 21	99.27 198	99.15 52	97.01 325	99.39 174	97.67 235	99.44 101	98.99 208	97.53 168	99.89 96	95.40 340	99.68 208	99.66 76
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 260	98.18 213	96.87 378	99.27 198	91.16 427	95.53 409	99.25 238	99.10 104	99.41 108	99.35 103	93.10 336	99.96 14	98.65 113	99.94 49	99.49 162

v1192		98.60 157	98.66 132	98.41 255	99.27 198	95.88 291	97.52 278	99.36 184	97.41 267	99.33 125	99.20 144	96.37 244	99.82 201	99.57 38	99.92 68	99.55 131

N_pmnet		97.63 274	97.17 295	98.99 147	99.27 198	97.86 171	95.98 386	93.41 451	95.25 375	99.47 96	98.90 231	95.63 277	99.85 155	96.91 242	99.73 176	99.27 259

viewdifsd2359ckpt13		98.39 194	98.29 196	98.70 201	99.26 207	97.19 227	97.51 280	99.48 128	96.94 307	98.58 263	98.82 254	97.47 177	99.55 371	97.21 217	99.33 304	99.34 237

FPMVS		93.44 409	92.23 416	97.08 366	99.25 208	97.86 171	95.61 406	97.16 400	92.90 420	93.76 453	98.65 290	75.94 448	95.66 467	79.30 465	97.49 423	97.73 431

new-patchmatchnet		98.35 197	98.74 116	97.18 361	99.24 209	92.23 409	96.42 362	99.48 128	98.30 179	99.69 55	99.53 63	97.44 178	99.82 201	98.84 98	99.77 155	99.49 162

MCST-MVS		98.00 241	97.63 269	99.10 124	99.24 209	98.17 134	96.89 334	98.73 341	95.66 361	97.92 321	97.70 378	97.17 195	99.66 325	96.18 308	99.23 323	99.47 181

UniMVSNet (Re)		98.87 101	98.71 123	99.35 76	99.24 209	98.73 91	97.73 247	99.38 176	98.93 128	99.12 163	98.73 269	96.77 221	99.86 142	98.63 115	99.80 138	99.46 183

jason		97.45 288	97.35 286	97.76 314	99.24 209	93.93 370	95.86 396	98.42 359	94.24 399	98.50 275	98.13 347	94.82 300	99.91 73	97.22 216	99.73 176	99.43 196
jason: jason.
IterMVS		97.73 266	98.11 222	96.57 388	99.24 209	90.28 436	95.52 411	99.21 247	98.86 137	99.33 125	99.33 110	93.11 335	99.94 42	98.49 125	99.94 49	99.48 173
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 167	98.62 139	98.32 266	99.22 214	95.58 302	97.51 280	99.45 145	97.16 295	99.45 100	99.24 135	96.12 255	99.85 155	99.60 36	99.88 92	99.55 131

ITE_SJBPF				98.87 167	99.22 214	98.48 110		99.35 190	97.50 255	98.28 293	98.60 301	97.64 155	99.35 418	93.86 382	99.27 315	98.79 356

h-mvs33		97.77 264	97.33 288	99.10 124	99.21 216	97.84 173	98.35 150	98.57 351	99.11 97	98.58 263	99.02 191	88.65 387	99.96 14	98.11 146	96.34 446	99.49 162

v144192		98.54 170	98.57 148	98.45 250	99.21 216	95.98 288	97.63 262	99.36 184	97.15 297	99.32 131	99.18 149	95.84 272	99.84 173	99.50 50	99.91 77	99.54 137

APDe-MVS		98.99 84	98.79 112	99.60 15	99.21 216	99.15 52	98.87 88	99.48 128	97.57 246	99.35 121	99.24 135	97.83 137	99.89 96	97.88 168	99.70 200	99.75 58
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 93	98.81 111	99.28 92	99.21 216	98.45 112	98.46 138	99.33 202	99.63 29	99.48 92	99.15 159	97.23 192	99.75 269	97.17 219	99.66 222	99.63 87

SR-MVS-dyc-post		98.81 115	98.55 150	99.57 21	99.20 220	99.38 13	98.48 136	99.30 217	98.64 148	98.95 198	98.96 218	97.49 175	99.86 142	96.56 281	99.39 295	99.45 188

RE-MVS-def			98.58 147		99.20 220	99.38 13	98.48 136	99.30 217	98.64 148	98.95 198	98.96 218	97.75 146		96.56 281	99.39 295	99.45 188

v1921920		98.54 170	98.60 144	98.38 259	99.20 220	95.76 298	97.56 273	99.36 184	97.23 289	99.38 114	99.17 153	96.02 258	99.84 173	99.57 38	99.90 84	99.54 137

thisisatest0530		95.27 378	94.45 389	97.74 317	99.19 223	94.37 348	97.86 225	90.20 463	97.17 294	98.22 296	97.65 380	73.53 451	99.90 80	96.90 247	99.35 301	98.95 326

Anonymous20240529		98.93 93	98.87 101	99.12 120	99.19 223	98.22 131	99.01 70	98.99 296	99.25 74	99.54 78	99.37 98	97.04 201	99.80 225	97.89 165	99.52 267	99.35 235

APD-MVS_3200maxsize		98.84 107	98.61 143	99.53 38	99.19 223	99.27 27	98.49 133	99.33 202	98.64 148	99.03 183	98.98 213	97.89 134	99.85 155	96.54 285	99.42 292	99.46 183

HQP_MVS		97.99 244	97.67 263	98.93 159	99.19 223	97.65 193	97.77 238	99.27 232	98.20 193	97.79 333	97.98 361	94.90 296	99.70 297	94.42 364	99.51 269	99.45 188

plane_prior7					99.19 223	97.87 170

ab-mvs		98.41 186	98.36 185	98.59 222	99.19 223	97.23 221	99.32 26	98.81 327	97.66 236	98.62 255	99.40 95	96.82 216	99.80 225	95.88 319	99.51 269	98.75 361

F-COLMAP		97.30 300	96.68 327	99.14 118	99.19 223	98.39 114	97.27 309	99.30 217	92.93 419	96.62 398	98.00 359	95.73 275	99.68 310	92.62 410	98.46 391	99.35 235

viewdifsd2359ckpt09		98.13 229	97.92 245	98.77 189	99.18 230	97.35 211	97.29 305	99.53 110	95.81 358	98.09 309	98.47 319	96.34 246	99.66 325	97.02 232	99.51 269	99.29 255

SR-MVS		98.71 130	98.43 173	99.57 21	99.18 230	99.35 17	98.36 149	99.29 225	98.29 182	98.88 217	98.85 244	97.53 168	99.87 133	96.14 310	99.31 308	99.48 173

UniMVSNet_NR-MVSNet		98.86 104	98.68 129	99.40 68	99.17 232	98.74 88	97.68 252	99.40 172	99.14 95	99.06 171	98.59 302	96.71 227	99.93 53	98.57 118	99.77 155	99.53 146

LF4IMVS		97.90 248	97.69 262	98.52 241	99.17 232	97.66 192	97.19 319	99.47 137	96.31 338	97.85 329	98.20 344	96.71 227	99.52 383	94.62 356	99.72 184	98.38 397

SMA-MVS		98.40 188	98.03 231	99.51 48	99.16 234	99.21 33	98.05 189	99.22 246	94.16 401	98.98 188	99.10 171	97.52 170	99.79 238	96.45 291	99.64 225	99.53 146
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		98.82 113	98.63 137	99.39 69	99.16 234	98.74 88	97.54 276	99.25 238	98.84 140	99.06 171	98.76 266	96.76 223	99.93 53	98.57 118	99.77 155	99.50 155

NR-MVSNet		98.95 91	98.82 109	99.36 70	99.16 234	98.72 93	99.22 45	99.20 249	99.10 104	99.72 47	98.76 266	96.38 243	99.86 142	98.00 158	99.82 121	99.50 155

MVS_111021_LR		98.30 206	98.12 221	98.83 172	99.16 234	98.03 153	96.09 383	99.30 217	97.58 245	98.10 308	98.24 340	98.25 98	99.34 419	96.69 267	99.65 223	99.12 300

DSMNet-mixed		97.42 291	97.60 271	96.87 378	99.15 238	91.46 416	98.54 121	99.12 271	92.87 421	97.58 346	99.63 39	96.21 250	99.90 80	95.74 328	99.54 260	99.27 259

D2MVS		97.84 261	97.84 252	97.83 306	99.14 239	94.74 337	96.94 329	98.88 311	95.84 357	98.89 213	98.96 218	94.40 312	99.69 301	97.55 193	99.95 38	99.05 306

pmmvs5		97.64 273	97.49 277	98.08 291	99.14 239	95.12 326	96.70 344	99.05 282	93.77 408	98.62 255	98.83 251	93.23 332	99.75 269	98.33 134	99.76 168	99.36 230

SPE-MVS-test		99.13 65	99.09 74	99.26 97	99.13 241	98.97 73	99.31 30	99.88 14	99.44 52	98.16 301	98.51 311	98.64 56	99.93 53	98.91 92	99.85 105	98.88 340

VDD-MVS		98.56 163	98.39 180	99.07 131	99.13 241	98.07 148	98.59 115	97.01 403	99.59 36	99.11 164	99.27 122	94.82 300	99.79 238	98.34 132	99.63 228	99.34 237

save fliter					99.11 243	97.97 159	96.53 354	99.02 290	98.24 185

APD-MVS		98.10 230	97.67 263	99.42 64	99.11 243	98.93 79	97.76 241	99.28 229	94.97 382	98.72 243	98.77 264	97.04 201	99.85 155	93.79 384	99.54 260	99.49 162
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 138	98.71 123	98.62 216	99.10 245	96.37 274	97.23 310	98.87 313	99.20 82	99.19 157	98.99 208	97.30 186	99.85 155	98.77 104	99.79 144	99.65 81

EI-MVSNet		98.40 188	98.51 156	98.04 296	99.10 245	94.73 338	97.20 315	98.87 313	98.97 123	99.06 171	99.02 191	96.00 260	99.80 225	98.58 116	99.82 121	99.60 98

CVMVSNet		96.25 352	97.21 294	93.38 445	99.10 245	80.56 473	97.20 315	98.19 370	96.94 307	99.00 185	99.02 191	89.50 380	99.80 225	96.36 297	99.59 242	99.78 46

EI-MVSNet-Vis-set		98.68 143	98.70 126	98.63 214	99.09 248	96.40 273	97.23 310	98.86 318	99.20 82	99.18 161	98.97 215	97.29 188	99.85 155	98.72 108	99.78 149	99.64 82

HPM-MVS++		98.10 230	97.64 268	99.48 56	99.09 248	99.13 60	97.52 278	98.75 338	97.46 263	96.90 386	97.83 371	96.01 259	99.84 173	95.82 326	99.35 301	99.46 183

DP-MVS Recon		97.33 298	96.92 310	98.57 226	99.09 248	97.99 155	96.79 337	99.35 190	93.18 415	97.71 337	98.07 355	95.00 295	99.31 423	93.97 377	99.13 339	98.42 394

MVS_111021_HR		98.25 215	98.08 226	98.75 193	99.09 248	97.46 205	95.97 387	99.27 232	97.60 244	97.99 319	98.25 339	98.15 113	99.38 414	96.87 250	99.57 251	99.42 199

BP-MVS1		97.40 293	96.97 306	98.71 200	99.07 252	96.81 251	98.34 152	97.18 398	98.58 159	98.17 298	98.61 299	84.01 419	99.94 42	98.97 89	99.78 149	99.37 223

9.14			97.78 254		99.07 252		97.53 277	99.32 204	95.53 367	98.54 271	98.70 279	97.58 161	99.76 261	94.32 369	99.46 282

PAPM_NR		96.82 332	96.32 343	98.30 269	99.07 252	96.69 259	97.48 284	98.76 335	95.81 358	96.61 399	96.47 416	94.12 321	99.17 436	90.82 437	97.78 417	99.06 305

TAMVS		98.24 216	98.05 229	98.80 178	99.07 252	97.18 229	97.88 221	98.81 327	96.66 324	99.17 162	99.21 142	94.81 302	99.77 255	96.96 240	99.88 92	99.44 192

CLD-MVS		97.49 284	97.16 296	98.48 247	99.07 252	97.03 238	94.71 432	99.21 247	94.46 393	98.06 312	97.16 402	97.57 162	99.48 395	94.46 361	99.78 149	98.95 326
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 65	99.10 72	99.24 102	99.06 257	99.15 52	99.36 22	99.88 14	99.36 63	98.21 297	98.46 320	98.68 53	99.93 53	99.03 85	99.85 105	98.64 373

thres100view900		94.19 395	93.67 400	95.75 412	99.06 257	91.35 420	98.03 193	94.24 446	98.33 175	97.40 362	94.98 446	79.84 435	99.62 341	83.05 458	98.08 408	96.29 453

thres600view7		94.45 390	93.83 397	96.29 396	99.06 257	91.53 415	97.99 207	94.24 446	98.34 174	97.44 360	95.01 444	79.84 435	99.67 314	84.33 456	98.23 397	97.66 434

plane_prior1					99.05 260

YYNet1		97.60 275	97.67 263	97.39 354	99.04 261	93.04 393	95.27 418	98.38 362	97.25 283	98.92 208	98.95 222	95.48 284	99.73 281	96.99 236	98.74 372	99.41 202

MDA-MVSNet_test_wron		97.60 275	97.66 266	97.41 353	99.04 261	93.09 389	95.27 418	98.42 359	97.26 282	98.88 217	98.95 222	95.43 285	99.73 281	97.02 232	98.72 374	99.41 202

MIMVSNet		96.62 339	96.25 347	97.71 321	99.04 261	94.66 341	99.16 54	96.92 409	97.23 289	97.87 326	99.10 171	86.11 402	99.65 332	91.65 421	99.21 327	98.82 345

icg_test_0407_2		98.20 221	98.38 182	97.65 327	99.03 264	94.03 361	95.78 401	99.45 145	98.16 199	99.06 171	98.71 272	98.27 94	99.68 310	97.50 199	99.45 284	99.22 276

IMVS_0407		98.39 194	98.64 135	97.66 325	99.03 264	94.03 361	98.10 179	99.45 145	98.16 199	99.06 171	98.71 272	98.27 94	99.71 290	97.50 199	99.45 284	99.22 276

IMVS_0404		98.07 234	98.20 208	97.69 322	99.03 264	94.03 361	96.67 345	99.45 145	98.16 199	98.03 316	98.71 272	96.80 219	99.82 201	97.50 199	99.45 284	99.22 276

IMVS_0403		98.34 198	98.56 149	97.66 325	99.03 264	94.03 361	97.98 208	99.45 145	98.16 199	98.89 213	98.71 272	97.90 132	99.74 274	97.50 199	99.45 284	99.22 276

PatchMatch-RL		97.24 306	96.78 321	98.61 219	99.03 264	97.83 174	96.36 365	99.06 279	93.49 413	97.36 366	97.78 372	95.75 274	99.49 392	93.44 393	98.77 371	98.52 382

viewmambaseed2359dif		98.19 222	98.26 201	97.99 299	99.02 269	95.03 329	96.59 351	99.53 110	96.21 341	99.00 185	98.99 208	97.62 157	99.61 348	97.62 188	99.72 184	99.33 243

GDP-MVS		97.50 281	97.11 300	98.67 206	99.02 269	96.85 249	98.16 169	99.71 47	98.32 177	98.52 274	98.54 306	83.39 423	99.95 26	98.79 100	99.56 254	99.19 286

ZD-MVS					99.01 271	98.84 82		99.07 278	94.10 403	98.05 314	98.12 349	96.36 245	99.86 142	92.70 409	99.19 331

CDPH-MVS		97.26 303	96.66 330	99.07 131	99.00 272	98.15 135	96.03 385	99.01 293	91.21 439	97.79 333	97.85 370	96.89 211	99.69 301	92.75 407	99.38 298	99.39 212

diffmvs		98.22 217	98.24 205	98.17 284	99.00 272	95.44 313	96.38 364	99.58 83	97.79 228	98.53 272	98.50 315	96.76 223	99.74 274	97.95 163	99.64 225	99.34 237
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		98.40 188	98.19 212	99.03 141	99.00 272	97.65 193	96.85 335	98.94 298	98.57 160	98.89 213	98.50 315	95.60 278	99.85 155	97.54 195	99.85 105	99.59 105

plane_prior6					98.99 275	97.70 191						94.90 296

xiu_mvs_v1_base_debu		97.86 255	98.17 214	96.92 375	98.98 276	93.91 371	96.45 358	99.17 261	97.85 223	98.41 283	97.14 404	98.47 72	99.92 64	98.02 155	99.05 345	96.92 446

xiu_mvs_v1_base		97.86 255	98.17 214	96.92 375	98.98 276	93.91 371	96.45 358	99.17 261	97.85 223	98.41 283	97.14 404	98.47 72	99.92 64	98.02 155	99.05 345	96.92 446

xiu_mvs_v1_base_debi		97.86 255	98.17 214	96.92 375	98.98 276	93.91 371	96.45 358	99.17 261	97.85 223	98.41 283	97.14 404	98.47 72	99.92 64	98.02 155	99.05 345	96.92 446

MVP-Stereo		98.08 233	97.92 245	98.57 226	98.96 279	96.79 252	97.90 219	99.18 257	96.41 334	98.46 278	98.95 222	95.93 269	99.60 351	96.51 287	98.98 359	99.31 250
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 188	98.68 129	97.54 342	98.96 279	97.99 155	97.88 221	99.36 184	98.20 193	99.63 66	99.04 188	98.76 45	95.33 469	96.56 281	99.74 173	99.31 250
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				98.91 163	98.94 281	97.76 185		98.76 335	87.58 456	96.75 394	98.10 351	94.80 303	99.78 249	92.73 408	99.00 354	99.20 281

USDC		97.41 292	97.40 281	97.44 351	98.94 281	93.67 381	95.17 421	99.53 110	94.03 405	98.97 192	99.10 171	95.29 287	99.34 419	95.84 325	99.73 176	99.30 253

tfpn200view9		94.03 399	93.44 402	95.78 411	98.93 283	91.44 418	97.60 268	94.29 444	97.94 215	97.10 372	94.31 453	79.67 437	99.62 341	83.05 458	98.08 408	96.29 453

testdata				98.09 288	98.93 283	95.40 315		98.80 329	90.08 447	97.45 359	98.37 329	95.26 288	99.70 297	93.58 389	98.95 362	99.17 293

thres400		94.14 397	93.44 402	96.24 399	98.93 283	91.44 418	97.60 268	94.29 444	97.94 215	97.10 372	94.31 453	79.67 437	99.62 341	83.05 458	98.08 408	97.66 434

TAPA-MVS	96.21 11	96.63 338	95.95 349	98.65 208	98.93 283	98.09 142	96.93 331	99.28 229	83.58 462	98.13 305	97.78 372	96.13 253	99.40 410	93.52 390	99.29 313	98.45 387
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 287	96.93 246	95.54 408	98.78 332	85.72 459	96.86 389	98.11 350	94.43 310			99.10 344	99.23 271

PVSNet_BlendedMVS		97.55 280	97.53 274	97.60 334	98.92 287	93.77 378	96.64 347	99.43 159	94.49 391	97.62 342	99.18 149	96.82 216	99.67 314	94.73 353	99.93 55	99.36 230

PVSNet_Blended		96.88 328	96.68 327	97.47 349	98.92 287	93.77 378	94.71 432	99.43 159	90.98 441	97.62 342	97.36 398	96.82 216	99.67 314	94.73 353	99.56 254	98.98 320

MSDG		97.71 268	97.52 275	98.28 271	98.91 290	96.82 250	94.42 442	99.37 180	97.65 237	98.37 288	98.29 338	97.40 180	99.33 421	94.09 375	99.22 324	98.68 371

Anonymous202405211		97.90 248	97.50 276	99.08 129	98.90 291	98.25 125	98.53 122	96.16 421	98.87 135	99.11 164	98.86 241	90.40 372	99.78 249	97.36 208	99.31 308	99.19 286

原ACMM1				98.35 264	98.90 291	96.25 278		98.83 326	92.48 425	96.07 416	98.10 351	95.39 286	99.71 290	92.61 411	98.99 356	99.08 302

GBi-Net		98.65 148	98.47 167	99.17 111	98.90 291	98.24 126	99.20 48	99.44 153	98.59 156	98.95 198	99.55 57	94.14 318	99.86 142	97.77 177	99.69 203	99.41 202

test1		98.65 148	98.47 167	99.17 111	98.90 291	98.24 126	99.20 48	99.44 153	98.59 156	98.95 198	99.55 57	94.14 318	99.86 142	97.77 177	99.69 203	99.41 202

FMVSNet2		98.49 179	98.40 177	98.75 193	98.90 291	97.14 234	98.61 113	99.13 270	98.59 156	99.19 157	99.28 120	94.14 318	99.82 201	97.97 161	99.80 138	99.29 255

OMC-MVS		97.88 252	97.49 277	99.04 140	98.89 296	98.63 95	96.94 329	99.25 238	95.02 380	98.53 272	98.51 311	97.27 189	99.47 398	93.50 392	99.51 269	99.01 314

VortexMVS		97.98 245	98.31 193	97.02 369	98.88 297	91.45 417	98.03 193	99.47 137	98.65 147	99.55 76	99.47 77	91.49 361	99.81 217	99.32 60	99.91 77	99.80 41

MVSFormer		98.26 212	98.43 173	97.77 311	98.88 297	93.89 374	99.39 20	99.56 97	99.11 97	98.16 301	98.13 347	93.81 326	99.97 7	99.26 65	99.57 251	99.43 196

lupinMVS		97.06 318	96.86 314	97.65 327	98.88 297	93.89 374	95.48 412	97.97 376	93.53 411	98.16 301	97.58 384	93.81 326	99.91 73	96.77 258	99.57 251	99.17 293

dmvs_re		95.98 360	95.39 370	97.74 317	98.86 300	97.45 206	98.37 148	95.69 433	97.95 213	96.56 400	95.95 425	90.70 369	97.68 463	88.32 446	96.13 450	98.11 409

DELS-MVS		98.27 210	98.20 208	98.48 247	98.86 300	96.70 258	95.60 407	99.20 249	97.73 231	98.45 279	98.71 272	97.50 172	99.82 201	98.21 140	99.59 242	98.93 331
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		97.89 250	97.98 236	97.60 334	98.86 300	94.35 349	96.21 374	99.44 153	97.45 265	99.06 171	98.88 238	97.99 126	99.28 429	94.38 368	99.58 247	99.18 289

LCM-MVSNet-Re		98.64 150	98.48 165	99.11 122	98.85 303	98.51 108	98.49 133	99.83 25	98.37 171	99.69 55	99.46 79	98.21 105	99.92 64	94.13 374	99.30 311	98.91 335

pmmvs4		97.58 278	97.28 289	98.51 242	98.84 304	96.93 246	95.40 416	98.52 354	93.60 410	98.61 257	98.65 290	95.10 292	99.60 351	96.97 239	99.79 144	98.99 319

NP-MVS					98.84 304	97.39 210					96.84 407

sss		97.21 308	96.93 308	98.06 293	98.83 306	95.22 322	96.75 341	98.48 356	94.49 391	97.27 368	97.90 367	92.77 344	99.80 225	96.57 277	99.32 306	99.16 296

PVSNet	93.40 17	95.67 369	95.70 355	95.57 416	98.83 306	88.57 443	92.50 459	97.72 381	92.69 423	96.49 408	96.44 417	93.72 329	99.43 406	93.61 387	99.28 314	98.71 364

MVE	83.40 22	92.50 422	91.92 424	94.25 432	98.83 306	91.64 414	92.71 458	83.52 472	95.92 355	86.46 470	95.46 438	95.20 289	95.40 468	80.51 463	98.64 383	95.73 461
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 403	93.91 395	93.39 444	98.82 309	81.72 471	97.76 241	95.28 435	98.60 155	96.54 401	96.66 411	65.85 467	99.62 341	96.65 270	98.99 356	98.82 345

ambc				98.24 276	98.82 309	95.97 289	98.62 112	99.00 295		99.27 139	99.21 142	96.99 206	99.50 389	96.55 284	99.50 277	99.26 265

旧先验1					98.82 309	97.45 206		98.76 335			98.34 333	95.50 283			99.01 353	99.23 271

test_vis1_rt		97.75 265	97.72 260	97.83 306	98.81 312	96.35 275	97.30 304	99.69 54	94.61 389	97.87 326	98.05 356	96.26 249	98.32 457	98.74 106	98.18 400	98.82 345

WTY-MVS		96.67 336	96.27 346	97.87 304	98.81 312	94.61 343	96.77 339	97.92 378	94.94 383	97.12 371	97.74 375	91.11 365	99.82 201	93.89 380	98.15 404	99.18 289

3Dnovator+	97.89 3	98.69 138	98.51 156	99.24 102	98.81 312	98.40 113	99.02 69	99.19 253	98.99 120	98.07 311	99.28 120	97.11 199	99.84 173	96.84 253	99.32 306	99.47 181

QAPM		97.31 299	96.81 320	98.82 174	98.80 315	97.49 201	99.06 65	99.19 253	90.22 445	97.69 339	99.16 155	96.91 210	99.90 80	90.89 436	99.41 293	99.07 304

VNet		98.42 185	98.30 194	98.79 181	98.79 316	97.29 217	98.23 160	98.66 345	99.31 68	98.85 222	98.80 258	94.80 303	99.78 249	98.13 145	99.13 339	99.31 250

DPM-MVS		96.32 348	95.59 361	98.51 242	98.76 317	97.21 225	94.54 441	98.26 365	91.94 430	96.37 409	97.25 400	93.06 338	99.43 406	91.42 426	98.74 372	98.89 337

3Dnovator	98.27 2	98.81 115	98.73 118	99.05 138	98.76 317	97.81 182	99.25 43	99.30 217	98.57 160	98.55 269	99.33 110	97.95 129	99.90 80	97.16 220	99.67 214	99.44 192

PLC	94.65 16	96.51 341	95.73 354	98.85 170	98.75 319	97.91 167	96.42 362	99.06 279	90.94 442	95.59 422	97.38 396	94.41 311	99.59 355	90.93 434	98.04 413	99.05 306
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 330	96.75 323	97.08 366	98.74 320	93.33 387	96.71 343	98.26 365	96.72 321	98.44 280	97.37 397	95.20 289	99.47 398	91.89 416	97.43 427	98.44 390

hse-mvs2		97.46 286	97.07 301	98.64 210	98.73 321	97.33 213	97.45 288	97.64 388	99.11 97	98.58 263	97.98 361	88.65 387	99.79 238	98.11 146	97.39 429	98.81 350

CDS-MVSNet		97.69 269	97.35 286	98.69 203	98.73 321	97.02 239	96.92 333	98.75 338	95.89 356	98.59 261	98.67 285	92.08 355	99.74 274	96.72 264	99.81 127	99.32 246
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 350	95.83 351	97.64 330	98.72 323	94.30 350	98.87 88	98.77 333	97.80 226	96.53 402	98.02 358	97.34 184	99.47 398	76.93 467	99.48 280	99.16 296

EIA-MVS		98.00 241	97.74 257	98.80 178	98.72 323	98.09 142	98.05 189	99.60 77	97.39 269	96.63 397	95.55 433	97.68 149	99.80 225	96.73 263	99.27 315	98.52 382

LFMVS		97.20 309	96.72 324	98.64 210	98.72 323	96.95 244	98.93 81	94.14 448	99.74 13	98.78 234	99.01 202	84.45 414	99.73 281	97.44 204	99.27 315	99.25 266

new_pmnet		96.99 325	96.76 322	97.67 323	98.72 323	94.89 332	95.95 391	98.20 368	92.62 424	98.55 269	98.54 306	94.88 299	99.52 383	93.96 378	99.44 291	98.59 379

Fast-Effi-MVS+		97.67 271	97.38 283	98.57 226	98.71 327	97.43 208	97.23 310	99.45 145	94.82 386	96.13 413	96.51 413	98.52 70	99.91 73	96.19 306	98.83 368	98.37 399

TEST9					98.71 327	98.08 146	95.96 389	99.03 287	91.40 436	95.85 419	97.53 386	96.52 236	99.76 261

train_agg		97.10 315	96.45 340	99.07 131	98.71 327	98.08 146	95.96 389	99.03 287	91.64 431	95.85 419	97.53 386	96.47 238	99.76 261	93.67 386	99.16 334	99.36 230

TSAR-MVS + GP.		98.18 224	97.98 236	98.77 189	98.71 327	97.88 169	96.32 368	98.66 345	96.33 336	99.23 151	98.51 311	97.48 176	99.40 410	97.16 220	99.46 282	99.02 313

FA-MVS(test-final)		96.99 325	96.82 318	97.50 346	98.70 331	94.78 335	99.34 23	96.99 404	95.07 379	98.48 277	99.33 110	88.41 390	99.65 332	96.13 312	98.92 365	98.07 412

AUN-MVS		96.24 354	95.45 366	98.60 221	98.70 331	97.22 223	97.38 294	97.65 386	95.95 354	95.53 429	97.96 365	82.11 431	99.79 238	96.31 299	97.44 426	98.80 355

our_test_3		97.39 294	97.73 259	96.34 394	98.70 331	89.78 439	94.61 438	98.97 297	96.50 329	99.04 180	98.85 244	95.98 265	99.84 173	97.26 214	99.67 214	99.41 202

ppachtmachnet_test		97.50 281	97.74 257	96.78 384	98.70 331	91.23 426	94.55 440	99.05 282	96.36 335	99.21 155	98.79 260	96.39 241	99.78 249	96.74 261	99.82 121	99.34 237

PCF-MVS	92.86 18	94.36 391	93.00 409	98.42 254	98.70 331	97.56 198	93.16 457	99.11 273	79.59 466	97.55 349	97.43 393	92.19 352	99.73 281	79.85 464	99.45 284	97.97 418
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 247	98.02 232	97.58 336	98.69 336	94.10 357	98.13 172	98.90 307	97.95 213	97.32 367	99.58 47	95.95 268	98.75 452	96.41 293	99.22 324	99.87 21

ETV-MVS		98.03 237	97.86 251	98.56 231	98.69 336	98.07 148	97.51 280	99.50 119	98.10 205	97.50 354	95.51 434	98.41 78	99.88 114	96.27 302	99.24 320	97.71 433

test_prior				98.95 156	98.69 336	97.95 163		99.03 287					99.59 355			99.30 253

mvsmamba		97.57 279	97.26 290	98.51 242	98.69 336	96.73 257	98.74 97	97.25 397	97.03 303	97.88 325	99.23 140	90.95 366	99.87 133	96.61 273	99.00 354	98.91 335

agg_prior					98.68 340	97.99 155		99.01 293		95.59 422			99.77 255

test_8					98.67 341	98.01 154	95.91 395	99.02 290	91.64 431	95.79 421	97.50 389	96.47 238	99.76 261

HQP-NCC					98.67 341		96.29 370		96.05 347	95.55 425

ACMP_Plane					98.67 341		96.29 370		96.05 347	95.55 425

CNVR-MVS		98.17 226	97.87 250	99.07 131	98.67 341	98.24 126	97.01 325	98.93 301	97.25 283	97.62 342	98.34 333	97.27 189	99.57 364	96.42 292	99.33 304	99.39 212

HQP-MVS		97.00 324	96.49 339	98.55 233	98.67 341	96.79 252	96.29 370	99.04 285	96.05 347	95.55 425	96.84 407	93.84 324	99.54 377	92.82 404	99.26 318	99.32 246

MM		98.22 217	97.99 235	98.91 163	98.66 346	96.97 241	97.89 220	94.44 442	99.54 40	98.95 198	99.14 162	93.50 330	99.92 64	99.80 17	99.96 28	99.85 29

test_fmvs1		97.72 267	97.94 242	97.07 368	98.66 346	92.39 404	97.68 252	99.81 31	95.20 378	99.54 78	99.44 84	91.56 360	99.41 409	99.78 21	99.77 155	99.40 211

balanced_conf03		98.63 152	98.72 120	98.38 259	98.66 346	96.68 260	98.90 83	99.42 165	98.99 120	98.97 192	99.19 145	95.81 273	99.85 155	98.77 104	99.77 155	98.60 376

thres200		93.72 405	93.14 407	95.46 420	98.66 346	91.29 422	96.61 349	94.63 441	97.39 269	96.83 390	93.71 456	79.88 434	99.56 367	82.40 461	98.13 405	95.54 462

wuyk23d		96.06 356	97.62 270	91.38 449	98.65 350	98.57 102	98.85 92	96.95 407	96.86 314	99.90 14	99.16 155	99.18 19	98.40 456	89.23 444	99.77 155	77.18 469

NCCC		97.86 255	97.47 280	99.05 138	98.61 351	98.07 148	96.98 327	98.90 307	97.63 238	97.04 376	97.93 366	95.99 264	99.66 325	95.31 341	98.82 370	99.43 196

DeepC-MVS_fast	96.85 6	98.30 206	98.15 218	98.75 193	98.61 351	97.23 221	97.76 241	99.09 276	97.31 277	98.75 240	98.66 288	97.56 163	99.64 335	96.10 313	99.55 258	99.39 212
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 407	92.09 418	97.75 315	98.60 353	94.40 347	97.32 302	95.26 436	97.56 248	96.79 393	95.50 435	53.57 475	99.77 255	95.26 342	98.97 360	99.08 302

thisisatest0515		94.12 398	93.16 406	96.97 373	98.60 353	92.90 394	93.77 453	90.61 461	94.10 403	96.91 383	95.87 428	74.99 449	99.80 225	94.52 359	99.12 342	98.20 405

GA-MVS		95.86 363	95.32 373	97.49 347	98.60 353	94.15 356	93.83 452	97.93 377	95.49 368	96.68 395	97.42 394	83.21 424	99.30 425	96.22 304	98.55 389	99.01 314

dmvs_testset		92.94 417	92.21 417	95.13 424	98.59 356	90.99 429	97.65 258	92.09 457	96.95 306	94.00 449	93.55 457	92.34 350	96.97 466	72.20 468	92.52 464	97.43 441

OPU-MVS				98.82 174	98.59 356	98.30 122	98.10 179				98.52 310	98.18 107	98.75 452	94.62 356	99.48 280	99.41 202

MSLP-MVS++		98.02 238	98.14 220	97.64 330	98.58 358	95.19 323	97.48 284	99.23 245	97.47 258	97.90 323	98.62 297	97.04 201	98.81 450	97.55 193	99.41 293	98.94 330

test12				98.93 159	98.58 358	97.83 174		98.66 345		96.53 402		95.51 282	99.69 301		99.13 339	99.27 259

CL-MVSNet_self_test		97.44 289	97.22 293	98.08 291	98.57 360	95.78 297	94.30 445	98.79 330	96.58 327	98.60 259	98.19 345	94.74 306	99.64 335	96.41 293	98.84 367	98.82 345

PS-MVSNAJ		97.08 317	97.39 282	96.16 405	98.56 361	92.46 402	95.24 420	98.85 321	97.25 283	97.49 355	95.99 424	98.07 117	99.90 80	96.37 295	98.67 382	96.12 458

CNLPA		97.17 312	96.71 325	98.55 233	98.56 361	98.05 152	96.33 367	98.93 301	96.91 311	97.06 375	97.39 395	94.38 313	99.45 403	91.66 420	99.18 333	98.14 408

xiu_mvs_v2_base		97.16 313	97.49 277	96.17 403	98.54 363	92.46 402	95.45 413	98.84 322	97.25 283	97.48 356	96.49 414	98.31 89	99.90 80	96.34 298	98.68 381	96.15 457

alignmvs		97.35 296	96.88 313	98.78 184	98.54 363	98.09 142	97.71 248	97.69 383	99.20 82	97.59 345	95.90 427	88.12 392	99.55 371	98.18 142	98.96 361	98.70 367

FE-MVS		95.66 370	94.95 383	97.77 311	98.53 365	95.28 319	99.40 19	96.09 424	93.11 417	97.96 320	99.26 128	79.10 441	99.77 255	92.40 413	98.71 376	98.27 403

Effi-MVS+		98.02 238	97.82 253	98.62 216	98.53 365	97.19 227	97.33 301	99.68 59	97.30 278	96.68 395	97.46 392	98.56 68	99.80 225	96.63 271	98.20 399	98.86 342

baseline1		95.96 361	95.44 367	97.52 344	98.51 367	93.99 368	98.39 146	96.09 424	98.21 189	98.40 287	97.76 374	86.88 394	99.63 338	95.42 339	89.27 467	98.95 326

MVS_Test		98.18 224	98.36 185	97.67 323	98.48 368	94.73 338	98.18 165	99.02 290	97.69 234	98.04 315	99.11 168	97.22 193	99.56 367	98.57 118	98.90 366	98.71 364

MGCFI-Net		98.34 198	98.28 197	98.51 242	98.47 369	97.59 197	98.96 77	99.48 128	99.18 90	97.40 362	95.50 435	98.66 54	99.50 389	98.18 142	98.71 376	98.44 390

BH-RMVSNet		96.83 330	96.58 335	97.58 336	98.47 369	94.05 358	96.67 345	97.36 392	96.70 323	97.87 326	97.98 361	95.14 291	99.44 405	90.47 439	98.58 388	99.25 266

sasdasda		98.34 198	98.26 201	98.58 223	98.46 371	97.82 179	98.96 77	99.46 141	99.19 87	97.46 357	95.46 438	98.59 62	99.46 401	98.08 149	98.71 376	98.46 384

canonicalmvs		98.34 198	98.26 201	98.58 223	98.46 371	97.82 179	98.96 77	99.46 141	99.19 87	97.46 357	95.46 438	98.59 62	99.46 401	98.08 149	98.71 376	98.46 384

MVS-HIRNet		94.32 392	95.62 358	90.42 450	98.46 371	75.36 474	96.29 370	89.13 465	95.25 375	95.38 431	99.75 16	92.88 341	99.19 435	94.07 376	99.39 295	96.72 451

PHI-MVS		98.29 209	97.95 240	99.34 79	98.44 374	99.16 48	98.12 176	99.38 176	96.01 351	98.06 312	98.43 323	97.80 142	99.67 314	95.69 331	99.58 247	99.20 281

DVP-MVS++		98.90 97	98.70 126	99.51 48	98.43 375	99.15 52	99.43 15	99.32 204	98.17 196	99.26 143	99.02 191	98.18 107	99.88 114	97.07 229	99.45 284	99.49 162

MSC_two_6792asdad				99.32 87	98.43 375	98.37 117		98.86 318					99.89 96	97.14 223	99.60 238	99.71 61

No_MVS				99.32 87	98.43 375	98.37 117		98.86 318					99.89 96	97.14 223	99.60 238	99.71 61

Fast-Effi-MVS+-dtu		98.27 210	98.09 223	98.81 176	98.43 375	98.11 139	97.61 267	99.50 119	98.64 148	97.39 364	97.52 388	98.12 115	99.95 26	96.90 247	98.71 376	98.38 397

OpenMVS_ROB	95.38 14	95.84 365	95.18 378	97.81 308	98.41 379	97.15 233	97.37 298	98.62 349	83.86 461	98.65 251	98.37 329	94.29 316	99.68 310	88.41 445	98.62 386	96.60 452

DeepPCF-MVS	96.93 5	98.32 203	98.01 233	99.23 104	98.39 380	98.97 73	95.03 425	99.18 257	96.88 312	99.33 125	98.78 262	98.16 111	99.28 429	96.74 261	99.62 231	99.44 192

Patchmatch-test		96.55 340	96.34 342	97.17 363	98.35 381	93.06 390	98.40 145	97.79 379	97.33 274	98.41 283	98.67 285	83.68 422	99.69 301	95.16 344	99.31 308	98.77 358

AdaColmap		97.14 314	96.71 325	98.46 249	98.34 382	97.80 183	96.95 328	98.93 301	95.58 365	96.92 381	97.66 379	95.87 271	99.53 379	90.97 433	99.14 337	98.04 413

OpenMVS	96.65 7	97.09 316	96.68 327	98.32 266	98.32 383	97.16 232	98.86 91	99.37 180	89.48 449	96.29 411	99.15 159	96.56 234	99.90 80	92.90 401	99.20 328	97.89 421

MG-MVS		96.77 333	96.61 332	97.26 359	98.31 384	93.06 390	95.93 392	98.12 373	96.45 333	97.92 321	98.73 269	93.77 328	99.39 412	91.19 431	99.04 348	99.33 243

test_yl		96.69 334	96.29 344	97.90 301	98.28 385	95.24 320	97.29 305	97.36 392	98.21 189	98.17 298	97.86 368	86.27 398	99.55 371	94.87 350	98.32 393	98.89 337

DCV-MVSNet		96.69 334	96.29 344	97.90 301	98.28 385	95.24 320	97.29 305	97.36 392	98.21 189	98.17 298	97.86 368	86.27 398	99.55 371	94.87 350	98.32 393	98.89 337

CHOSEN 280x420		95.51 375	95.47 364	95.65 415	98.25 387	88.27 446	93.25 456	98.88 311	93.53 411	94.65 440	97.15 403	86.17 400	99.93 53	97.41 206	99.93 55	98.73 363

SCA		96.41 347	96.66 330	95.67 413	98.24 388	88.35 445	95.85 398	96.88 410	96.11 345	97.67 340	98.67 285	93.10 336	99.85 155	94.16 370	99.22 324	98.81 350

DeepMVS_CX				93.44 443	98.24 388	94.21 353		94.34 443	64.28 469	91.34 463	94.87 450	89.45 381	92.77 470	77.54 466	93.14 463	93.35 465

MS-PatchMatch		97.68 270	97.75 256	97.45 350	98.23 390	93.78 377	97.29 305	98.84 322	96.10 346	98.64 252	98.65 290	96.04 257	99.36 415	96.84 253	99.14 337	99.20 281

BH-w/o		95.13 381	94.89 385	95.86 408	98.20 391	91.31 421	95.65 405	97.37 391	93.64 409	96.52 404	95.70 431	93.04 339	99.02 441	88.10 447	95.82 453	97.24 444

mvs_anonymous		97.83 263	98.16 217	96.87 378	98.18 392	91.89 411	97.31 303	98.90 307	97.37 271	98.83 225	99.46 79	96.28 248	99.79 238	98.90 93	98.16 403	98.95 326

miper_lstm_enhance		97.18 311	97.16 296	97.25 360	98.16 393	92.85 395	95.15 423	99.31 209	97.25 283	98.74 242	98.78 262	90.07 373	99.78 249	97.19 218	99.80 138	99.11 301

RRT-MVS		97.88 252	97.98 236	97.61 333	98.15 394	93.77 378	98.97 76	99.64 69	99.16 92	98.69 245	99.42 88	91.60 358	99.89 96	97.63 187	98.52 390	99.16 296

ET-MVSNet_ETH3D		94.30 394	93.21 405	97.58 336	98.14 395	94.47 346	94.78 431	93.24 453	94.72 387	89.56 465	95.87 428	78.57 444	99.81 217	96.91 242	97.11 438	98.46 384

ADS-MVSNet2		95.43 376	94.98 381	96.76 385	98.14 395	91.74 412	97.92 216	97.76 380	90.23 443	96.51 405	98.91 228	85.61 405	99.85 155	92.88 402	96.90 439	98.69 368

ADS-MVSNet		95.24 379	94.93 384	96.18 402	98.14 395	90.10 438	97.92 216	97.32 395	90.23 443	96.51 405	98.91 228	85.61 405	99.74 274	92.88 402	96.90 439	98.69 368

c3_l		97.36 295	97.37 284	97.31 355	98.09 398	93.25 388	95.01 426	99.16 264	97.05 300	98.77 237	98.72 271	92.88 341	99.64 335	96.93 241	99.76 168	99.05 306

FMVSNet3		97.50 281	97.24 292	98.29 270	98.08 399	95.83 294	97.86 225	98.91 306	97.89 220	98.95 198	98.95 222	87.06 393	99.81 217	97.77 177	99.69 203	99.23 271

PAPM		91.88 431	90.34 434	96.51 389	98.06 400	92.56 400	92.44 460	97.17 399	86.35 457	90.38 464	96.01 423	86.61 396	99.21 434	70.65 470	95.43 455	97.75 430

Effi-MVS+-dtu		98.26 212	97.90 248	99.35 76	98.02 401	99.49 6	98.02 196	99.16 264	98.29 182	97.64 341	97.99 360	96.44 240	99.95 26	96.66 269	98.93 364	98.60 376

eth_miper_zixun_eth		97.23 307	97.25 291	97.17 363	98.00 402	92.77 397	94.71 432	99.18 257	97.27 281	98.56 267	98.74 268	91.89 356	99.69 301	97.06 231	99.81 127	99.05 306

HY-MVS	95.94 13	95.90 362	95.35 372	97.55 341	97.95 403	94.79 334	98.81 96	96.94 408	92.28 428	95.17 433	98.57 304	89.90 375	99.75 269	91.20 430	97.33 434	98.10 410

UGNet		98.53 172	98.45 170	98.79 181	97.94 404	96.96 243	99.08 61	98.54 352	99.10 104	96.82 391	99.47 77	96.55 235	99.84 173	98.56 121	99.94 49	99.55 131
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		96.47 345	95.70 355	98.79 181	97.92 405	99.12 62	98.28 154	98.60 350	92.16 429	95.54 428	96.17 421	94.77 305	99.52 383	89.62 442	98.23 397	97.72 432
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		96.86 329	96.55 336	97.79 309	97.91 406	94.21 353	97.56 273	98.87 313	97.49 257	99.06 171	99.05 186	80.72 432	99.80 225	98.44 127	99.82 121	99.37 223

API-MVS		97.04 320	96.91 312	97.42 352	97.88 407	98.23 130	98.18 165	98.50 355	97.57 246	97.39 364	96.75 409	96.77 221	99.15 438	90.16 440	99.02 352	94.88 463

myMVS_eth3d28		92.92 418	92.31 414	94.77 427	97.84 408	87.59 450	96.19 376	96.11 423	97.08 299	94.27 443	93.49 459	66.07 466	98.78 451	91.78 418	97.93 416	97.92 420

miper_ehance_all_eth		97.06 318	97.03 303	97.16 365	97.83 409	93.06 390	94.66 435	99.09 276	95.99 352	98.69 245	98.45 321	92.73 346	99.61 348	96.79 255	99.03 349	98.82 345

cl____		97.02 321	96.83 317	97.58 336	97.82 410	94.04 360	94.66 435	99.16 264	97.04 301	98.63 253	98.71 272	88.68 386	99.69 301	97.00 234	99.81 127	99.00 318

DIV-MVS_self_test		97.02 321	96.84 316	97.58 336	97.82 410	94.03 361	94.66 435	99.16 264	97.04 301	98.63 253	98.71 272	88.69 384	99.69 301	97.00 234	99.81 127	99.01 314

CANet		97.87 254	97.76 255	98.19 283	97.75 412	95.51 305	96.76 340	99.05 282	97.74 230	96.93 380	98.21 343	95.59 279	99.89 96	97.86 172	99.93 55	99.19 286

UBG		93.25 412	92.32 413	96.04 407	97.72 413	90.16 437	95.92 394	95.91 428	96.03 350	93.95 451	93.04 462	69.60 456	99.52 383	90.72 438	97.98 414	98.45 387

mvsany_test1		97.60 275	97.54 273	97.77 311	97.72 413	95.35 316	95.36 417	97.13 401	94.13 402	99.71 49	99.33 110	97.93 130	99.30 425	97.60 191	98.94 363	98.67 372

PVSNet_0	89.98 21	91.15 432	90.30 435	93.70 440	97.72 413	84.34 464	90.24 463	97.42 390	90.20 446	93.79 452	93.09 461	90.90 368	98.89 449	86.57 453	72.76 470	97.87 423

CR-MVSNet		96.28 350	95.95 349	97.28 357	97.71 416	94.22 351	98.11 177	98.92 304	92.31 427	96.91 383	99.37 98	85.44 408	99.81 217	97.39 207	97.36 432	97.81 426

RPMNet		97.02 321	96.93 308	97.30 356	97.71 416	94.22 351	98.11 177	99.30 217	99.37 60	96.91 383	99.34 107	86.72 395	99.87 133	97.53 196	97.36 432	97.81 426

ETVMVS		92.60 421	91.08 430	97.18 361	97.70 418	93.65 383	96.54 352	95.70 431	96.51 328	94.68 439	92.39 465	61.80 472	99.50 389	86.97 450	97.41 428	98.40 395

pmmvs3		95.03 383	94.40 390	96.93 374	97.70 418	92.53 401	95.08 424	97.71 382	88.57 453	97.71 337	98.08 354	79.39 439	99.82 201	96.19 306	99.11 343	98.43 392

baseline2		93.73 404	92.83 410	96.42 392	97.70 418	91.28 423	96.84 336	89.77 464	93.96 407	92.44 459	95.93 426	79.14 440	99.77 255	92.94 400	96.76 443	98.21 404

WBMVS		95.18 380	94.78 386	96.37 393	97.68 421	89.74 440	95.80 400	98.73 341	97.54 252	98.30 289	98.44 322	70.06 454	99.82 201	96.62 272	99.87 96	99.54 137

tpm		94.67 388	94.34 392	95.66 414	97.68 421	88.42 444	97.88 221	94.90 438	94.46 393	96.03 418	98.56 305	78.66 442	99.79 238	95.88 319	95.01 457	98.78 357

CANet_DTU		97.26 303	97.06 302	97.84 305	97.57 423	94.65 342	96.19 376	98.79 330	97.23 289	95.14 434	98.24 340	93.22 333	99.84 173	97.34 209	99.84 110	99.04 310

testing11		93.08 415	92.02 420	96.26 398	97.56 424	90.83 432	96.32 368	95.70 431	96.47 332	92.66 458	93.73 455	64.36 470	99.59 355	93.77 385	97.57 421	98.37 399

tpm2		93.09 414	92.58 412	94.62 429	97.56 424	86.53 453	97.66 256	95.79 430	86.15 458	94.07 448	98.23 342	75.95 447	99.53 379	90.91 435	96.86 442	97.81 426

testing91		93.32 410	92.27 415	96.47 391	97.54 426	91.25 424	96.17 380	96.76 412	97.18 293	93.65 454	93.50 458	65.11 469	99.63 338	93.04 399	97.45 425	98.53 381

TR-MVS		95.55 373	95.12 379	96.86 381	97.54 426	93.94 369	96.49 357	96.53 417	94.36 398	97.03 378	96.61 412	94.26 317	99.16 437	86.91 452	96.31 447	97.47 440

testing99		93.04 416	91.98 423	96.23 400	97.53 428	90.70 434	96.35 366	95.94 427	96.87 313	93.41 455	93.43 460	63.84 471	99.59 355	93.24 397	97.19 435	98.40 395

1314		95.74 367	95.60 359	96.17 403	97.53 428	92.75 398	98.07 186	98.31 364	91.22 438	94.25 444	96.68 410	95.53 280	99.03 440	91.64 422	97.18 436	96.74 450

CostFormer		93.97 400	93.78 398	94.51 430	97.53 428	85.83 456	97.98 208	95.96 426	89.29 451	94.99 436	98.63 295	78.63 443	99.62 341	94.54 358	96.50 444	98.09 411

FMVSNet5		96.01 358	95.20 377	98.41 255	97.53 428	96.10 280	98.74 97	99.50 119	97.22 292	98.03 316	99.04 188	69.80 455	99.88 114	97.27 213	99.71 193	99.25 266

PMMVS		96.51 341	95.98 348	98.09 288	97.53 428	95.84 293	94.92 428	98.84 322	91.58 433	96.05 417	95.58 432	95.68 276	99.66 325	95.59 335	98.09 407	98.76 360

reproduce_monomvs		95.00 385	95.25 374	94.22 433	97.51 433	83.34 465	97.86 225	98.44 357	98.51 165	99.29 135	99.30 116	67.68 460	99.56 367	98.89 95	99.81 127	99.77 49

PAPR		95.29 377	94.47 388	97.75 315	97.50 434	95.14 325	94.89 429	98.71 343	91.39 437	95.35 432	95.48 437	94.57 308	99.14 439	84.95 455	97.37 430	98.97 323

testing222		91.96 429	90.37 433	96.72 386	97.47 435	92.59 399	96.11 382	94.76 439	96.83 315	92.90 457	92.87 463	57.92 473	99.55 371	86.93 451	97.52 422	98.00 417

PatchT		96.65 337	96.35 341	97.54 342	97.40 436	95.32 318	97.98 208	96.64 414	99.33 65	96.89 387	99.42 88	84.32 416	99.81 217	97.69 186	97.49 423	97.48 439

tpm cat1		93.29 411	93.13 408	93.75 439	97.39 437	84.74 459	97.39 292	97.65 386	83.39 463	94.16 445	98.41 324	82.86 427	99.39 412	91.56 424	95.35 456	97.14 445

PatchmatchNet		95.58 372	95.67 357	95.30 423	97.34 438	87.32 451	97.65 258	96.65 413	95.30 374	97.07 374	98.69 281	84.77 411	99.75 269	94.97 348	98.64 383	98.83 344
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 296	96.97 306	98.50 246	97.31 439	96.47 271	98.18 165	98.92 304	98.95 127	98.78 234	99.37 98	85.44 408	99.85 155	95.96 317	99.83 117	99.17 293

LS3D		98.63 152	98.38 182	99.36 70	97.25 440	99.38 13	99.12 60	99.32 204	99.21 80	98.44 280	98.88 238	97.31 185	99.80 225	96.58 275	99.34 303	98.92 332

IB-MVS	91.63 19	92.24 427	90.90 431	96.27 397	97.22 441	91.24 425	94.36 444	93.33 452	92.37 426	92.24 461	94.58 452	66.20 465	99.89 96	93.16 398	94.63 459	97.66 434
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		92.38 424	91.76 427	94.21 434	97.16 442	84.65 460	95.42 415	88.45 466	95.96 353	96.17 412	95.84 430	66.36 463	99.71 290	91.87 417	98.64 383	98.28 402

tpmrst		95.07 382	95.46 365	93.91 437	97.11 443	84.36 463	97.62 263	96.96 406	94.98 381	96.35 410	98.80 258	85.46 407	99.59 355	95.60 334	96.23 448	97.79 429

Syy-MVS		96.04 357	95.56 363	97.49 347	97.10 444	94.48 345	96.18 378	96.58 415	95.65 362	94.77 437	92.29 466	91.27 364	99.36 415	98.17 144	98.05 411	98.63 374

myMVS_eth3d		91.92 430	90.45 432	96.30 395	97.10 444	90.90 430	96.18 378	96.58 415	95.65 362	94.77 437	92.29 466	53.88 474	99.36 415	89.59 443	98.05 411	98.63 374

MDTV_nov1_ep13			95.22 376		97.06 446	83.20 466	97.74 245	96.16 421	94.37 397	96.99 379	98.83 251	83.95 420	99.53 379	93.90 379	97.95 415

MVS		93.19 413	92.09 418	96.50 390	96.91 447	94.03 361	98.07 186	98.06 375	68.01 468	94.56 442	96.48 415	95.96 267	99.30 425	83.84 457	96.89 441	96.17 455

E-PMN		94.17 396	94.37 391	93.58 441	96.86 448	85.71 457	90.11 465	97.07 402	98.17 196	97.82 332	97.19 401	84.62 413	98.94 445	89.77 441	97.68 420	96.09 459

JIA-IIPM		95.52 374	95.03 380	97.00 370	96.85 449	94.03 361	96.93 331	95.82 429	99.20 82	94.63 441	99.71 22	83.09 425	99.60 351	94.42 364	94.64 458	97.36 443

EMVS		93.83 402	94.02 394	93.23 446	96.83 450	84.96 458	89.77 466	96.32 419	97.92 217	97.43 361	96.36 420	86.17 400	98.93 446	87.68 448	97.73 419	95.81 460

cl22		95.79 366	95.39 370	96.98 372	96.77 451	92.79 396	94.40 443	98.53 353	94.59 390	97.89 324	98.17 346	82.82 428	99.24 431	96.37 295	99.03 349	98.92 332

WB-MVSnew		95.73 368	95.57 362	96.23 400	96.70 452	90.70 434	96.07 384	93.86 449	95.60 364	97.04 376	95.45 441	96.00 260	99.55 371	91.04 432	98.31 395	98.43 392

dp		93.47 408	93.59 401	93.13 447	96.64 453	81.62 472	97.66 256	96.42 418	92.80 422	96.11 414	98.64 293	78.55 445	99.59 355	93.31 395	92.18 466	98.16 407

MonoMVSNet		96.25 352	96.53 338	95.39 421	96.57 454	91.01 428	98.82 95	97.68 385	98.57 160	98.03 316	99.37 98	90.92 367	97.78 462	94.99 346	93.88 462	97.38 442

test-LLR		93.90 401	93.85 396	94.04 435	96.53 455	84.62 461	94.05 449	92.39 455	96.17 342	94.12 446	95.07 442	82.30 429	99.67 314	95.87 322	98.18 400	97.82 424

test-mter		92.33 426	91.76 427	94.04 435	96.53 455	84.62 461	94.05 449	92.39 455	94.00 406	94.12 446	95.07 442	65.63 468	99.67 314	95.87 322	98.18 400	97.82 424

TESTMET0.1,1		92.19 428	91.77 426	93.46 442	96.48 457	82.80 468	94.05 449	91.52 460	94.45 395	94.00 449	94.88 448	66.65 462	99.56 367	95.78 327	98.11 406	98.02 414

MGCNet		97.44 289	97.01 305	98.72 199	96.42 458	96.74 256	97.20 315	91.97 458	98.46 168	98.30 289	98.79 260	92.74 345	99.91 73	99.30 62	99.94 49	99.52 149

miper_enhance_ethall		96.01 358	95.74 353	96.81 382	96.41 459	92.27 408	93.69 454	98.89 310	91.14 440	98.30 289	97.35 399	90.58 370	99.58 362	96.31 299	99.03 349	98.60 376

tpmvs		95.02 384	95.25 374	94.33 431	96.39 460	85.87 454	98.08 182	96.83 411	95.46 369	95.51 430	98.69 281	85.91 403	99.53 379	94.16 370	96.23 448	97.58 437

CMPMVS	75.91 23	96.29 349	95.44 367	98.84 171	96.25 461	98.69 94	97.02 324	99.12 271	88.90 452	97.83 330	98.86 241	89.51 379	98.90 448	91.92 415	99.51 269	98.92 332
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 389	93.69 399	96.99 371	96.05 462	93.61 385	94.97 427	93.49 450	96.17 342	97.57 348	94.88 448	82.30 429	99.01 443	93.60 388	94.17 461	98.37 399

EPMVS		93.72 405	93.27 404	95.09 426	96.04 463	87.76 448	98.13 172	85.01 471	94.69 388	96.92 381	98.64 293	78.47 446	99.31 423	95.04 345	96.46 445	98.20 405

cascas		94.79 387	94.33 393	96.15 406	96.02 464	92.36 406	92.34 461	99.26 237	85.34 460	95.08 435	94.96 447	92.96 340	98.53 455	94.41 367	98.59 387	97.56 438

MVStest1		95.86 363	95.60 359	96.63 387	95.87 465	91.70 413	97.93 213	98.94 298	98.03 207	99.56 73	99.66 32	71.83 452	98.26 458	99.35 58	99.24 320	99.91 13

gg-mvs-nofinetune		92.37 425	91.20 429	95.85 409	95.80 466	92.38 405	99.31 30	81.84 473	99.75 11	91.83 462	99.74 18	68.29 457	99.02 441	87.15 449	97.12 437	96.16 456

gm-plane-assit					94.83 467	81.97 470			88.07 455		94.99 445		99.60 351	91.76 419

GG-mvs-BLEND				94.76 428	94.54 468	92.13 410	99.31 30	80.47 474		88.73 468	91.01 468	67.59 461	98.16 461	82.30 462	94.53 460	93.98 464

UWE-MVS-28		90.22 433	89.28 436	93.02 448	94.50 469	82.87 467	96.52 355	87.51 467	95.21 377	92.36 460	96.04 422	71.57 453	98.25 459	72.04 469	97.77 418	97.94 419

EPNet_dtu		94.93 386	94.78 386	95.38 422	93.58 470	87.68 449	96.78 338	95.69 433	97.35 273	89.14 467	98.09 353	88.15 391	99.49 392	94.95 349	99.30 311	98.98 320
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 437	75.95 440	77.12 453	92.39 471	67.91 477	90.16 464	59.44 478	82.04 464	89.42 466	94.67 451	49.68 476	81.74 471	48.06 471	77.66 469	81.72 467

KD-MVS_2432*1600		92.87 419	91.99 421	95.51 418	91.37 472	89.27 441	94.07 447	98.14 371	95.42 370	97.25 369	96.44 417	67.86 458	99.24 431	91.28 428	96.08 451	98.02 414

miper_refine_blended		92.87 419	91.99 421	95.51 418	91.37 472	89.27 441	94.07 447	98.14 371	95.42 370	97.25 369	96.44 417	67.86 458	99.24 431	91.28 428	96.08 451	98.02 414

EPNet		96.14 355	95.44 367	98.25 274	90.76 474	95.50 308	97.92 216	94.65 440	98.97 123	92.98 456	98.85 244	89.12 382	99.87 133	95.99 315	99.68 208	99.39 212
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 438	68.95 441	70.34 454	87.68 475	65.00 478	91.11 462	59.90 477	69.02 467	74.46 472	88.89 469	48.58 477	68.03 473	28.61 472	72.33 471	77.99 468

test_method		79.78 435	79.50 438	80.62 451	80.21 476	45.76 479	70.82 467	98.41 361	31.08 471	80.89 471	97.71 376	84.85 410	97.37 464	91.51 425	80.03 468	98.75 361

tmp_tt		78.77 436	78.73 439	78.90 452	58.45 477	74.76 476	94.20 446	78.26 475	39.16 470	86.71 469	92.82 464	80.50 433	75.19 472	86.16 454	92.29 465	86.74 466

testmvs		17.12 440	20.53 443	6.87 456	12.05 478	4.20 481	93.62 455	6.73 479	4.62 474	10.41 474	24.33 471	8.28 479	3.56 475	9.69 474	15.07 472	12.86 471

test123		17.04 441	20.11 444	7.82 455	10.25 479	4.91 480	94.80 430	4.47 480	4.93 473	10.00 475	24.28 472	9.69 478	3.64 474	10.14 473	12.43 473	14.92 470

mmdepth		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

monomultidepth		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

test_blank		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

eth-test2					0.00 480

eth-test					0.00 480

uanet_test		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

DCPMVS		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

cdsmvs_eth3d_5k		24.66 439	32.88 442	0.00 457	0.00 480	0.00 482	0.00 468	99.10 274	0.00 475	0.00 476	97.58 384	99.21 18	0.00 476	0.00 475	0.00 474	0.00 472

pcd_1.5k_mvsjas		8.17 442	10.90 445	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	98.07 117	0.00 476	0.00 475	0.00 474	0.00 472

sosnet-low-res		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

sosnet		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

uncertanet		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

Regformer		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

ab-mvs-re		8.12 443	10.83 446	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	97.48 390	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

uanet		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

WAC-MVS						90.90 430								91.37 427

PC_three_1452									93.27 414	99.40 111	98.54 306	98.22 103	97.00 465	95.17 343	99.45 284	99.49 162

test_241102_TWO								99.30 217	98.03 207	99.26 143	99.02 191	97.51 171	99.88 114	96.91 242	99.60 238	99.66 76

test_0728_THIRD									98.17 196	99.08 169	99.02 191	97.89 134	99.88 114	97.07 229	99.71 193	99.70 66

GSMVS																98.81 350

sam_mvs1												84.74 412				98.81 350

sam_mvs												84.29 418

MTGPA								99.20 249

test_post1							97.59 270				20.48 474	83.07 426	99.66 325	94.16 370

test_post											21.25 473	83.86 421	99.70 297

patchmatchnet-post											98.77 264	84.37 415	99.85 155

MTMP							97.93 213	91.91 459

test9_res														93.28 396	99.15 336	99.38 221

agg_prior2														92.50 412	99.16 334	99.37 223

test_prior4						97.97 159	95.86 396

test_prior2							95.74 403		96.48 331	96.11 414	97.63 382	95.92 270		94.16 370	99.20 328

旧先验2							95.76 402		88.56 454	97.52 352			99.66 325	94.48 360

新几何2							95.93 392

无先验							95.74 403	98.74 340	89.38 450				99.73 281	92.38 414		99.22 276

原ACMM2							95.53 409

testdata2													99.79 238	92.80 406

segment_acmp												97.02 204

testdata1							95.44 414		96.32 337

plane_prior5								99.27 232					99.70 297	94.42 364	99.51 269	99.45 188

plane_prior4											97.98 361

plane_prior3						97.78 184			97.41 267	97.79 333

plane_prior2							97.77 238		98.20 193

plane_prior						97.65 193	97.07 323		96.72 321						99.36 299

n2								0.00 481

nn								0.00 481

door-mid								99.57 90

test11								98.87 313

door								99.41 169

HQP5-MVS						96.79 252

BP-MVS														92.82 404

HQP4-MVS										95.56 424			99.54 377			99.32 246

HQP3-MVS								99.04 285							99.26 318

HQP2-MVS												93.84 324

MDTV_nov1_ep13_2view						74.92 475	97.69 251		90.06 448	97.75 336		85.78 404		93.52 390		98.69 368

ACMMP++_ref															99.77 155

ACMMP++															99.68 208

Test By Simon												96.52 236

High-resolution multi-view benchmark