High-res multi-view results

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

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

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

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

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

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

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

LCM-MVSNet		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 13	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 16	100.00 1	99.85 30

Gipuma		99.03 85	99.16 63	98.64 224	99.94 2	98.51 113	99.32 26	99.75 42	99.58 39	98.60 274	99.62 40	98.22 109	99.51 411	97.70 195	99.73 185	97.89 444
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 29	99.31 42	99.53 39	99.91 3	98.98 72	99.63 7	99.58 94	99.44 53	99.78 40	99.76 15	96.39 254	99.92 66	99.44 55	99.92 69	99.68 71

pmmvs6		99.67 3	99.70 3	99.60 16	99.90 4	99.27 28	99.53 9	99.76 39	99.64 27	99.84 30	99.83 4	99.50 9	99.87 135	99.36 58	99.92 69	99.64 84

PS-MVSNAJss		99.46 17	99.49 16	99.35 81	99.90 4	98.15 140	99.20 48	99.65 69	99.48 45	99.92 8	99.71 22	98.07 124	99.96 14	99.53 48	100.00 1	99.93 11

testf1		99.25 41	99.16 63	99.51 49	99.89 6	99.63 4	98.71 106	99.69 54	98.90 134	99.43 107	99.35 109	98.86 34	99.67 334	97.81 182	99.81 134	99.24 284

APD_test2		99.25 41	99.16 63	99.51 49	99.89 6	99.63 4	98.71 106	99.69 54	98.90 134	99.43 107	99.35 109	98.86 34	99.67 334	97.81 182	99.81 134	99.24 284

ANet_high		99.57 10	99.67 6	99.28 97	99.89 6	98.09 147	99.14 57	99.93 5	99.82 8	99.93 6	99.81 8	99.17 20	99.94 42	99.31 62	100.00 1	99.82 36

anonymousdsp		99.51 14	99.47 21	99.62 10	99.88 9	99.08 70	99.34 23	99.69 54	98.93 130	99.65 64	99.72 21	98.93 32	99.95 26	99.11 78	100.00 1	99.82 36

v7n		99.53 12	99.57 13	99.41 70	99.88 9	98.54 111	99.45 14	99.61 82	99.66 24	99.68 58	99.66 32	98.44 82	99.95 26	99.73 28	99.96 28	99.75 60

mvs_tets		99.63 6	99.67 6	99.49 55	99.88 9	98.61 103	99.34 23	99.71 47	99.27 74	99.90 14	99.74 18	99.68 4	99.97 7	99.55 43	99.99 5	99.88 20

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 75	99.87 12	98.13 143	98.08 193	99.95 1	99.45 51	99.98 2	99.75 16	99.80 1	99.97 7	99.82 12	99.99 5	99.99 2

jajsoiax		99.58 9	99.61 11	99.48 57	99.87 12	98.61 103	99.28 40	99.66 65	99.09 109	99.89 18	99.68 25	99.53 7	99.97 7	99.50 51	99.99 5	99.87 22

test_djsdf		99.52 13	99.51 15	99.53 39	99.86 14	98.74 92	99.39 20	99.56 110	99.11 99	99.70 52	99.73 20	99.00 27	99.97 7	99.26 66	99.98 12	99.89 16

MIMVSNet1		99.38 28	99.32 40	99.55 29	99.86 14	99.19 43	99.41 17	99.59 91	99.59 37	99.71 50	99.57 49	97.12 209	99.90 82	99.21 71	99.87 98	99.54 142

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 27	99.85 16	99.11 65	99.90 1	99.78 36	99.63 29	99.78 40	99.67 30	99.48 10	99.81 223	99.30 63	99.97 21	99.77 50
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 20	99.69 5	99.58 94	99.90 3	99.86 24	99.78 13	99.58 6	99.95 26	99.00 88	99.95 38	99.78 47

SixPastTwentyTwo		98.75 136	98.62 151	99.16 119	99.83 18	97.96 167	99.28 40	98.20 391	99.37 61	99.70 52	99.65 36	92.65 361	99.93 54	99.04 85	99.84 112	99.60 100

sc_t1		99.62 7	99.66 8	99.53 39	99.82 19	99.09 69	99.50 11	99.63 73	99.88 4	99.86 24	99.80 11	99.03 24	99.89 98	99.48 53	99.93 56	99.60 100

Baseline_NR-MVSNet		98.98 94	98.86 112	99.36 75	99.82 19	98.55 108	97.47 301	99.57 101	99.37 61	99.21 165	99.61 43	96.76 236	99.83 193	98.06 158	99.83 123	99.71 63

pm-mvs1		99.44 19	99.48 18	99.33 90	99.80 21	98.63 100	99.29 36	99.63 73	99.30 71	99.65 64	99.60 45	99.16 22	99.82 206	99.07 81	99.83 123	99.56 129

TransMVSNet (Re)		99.44 19	99.47 21	99.36 75	99.80 21	98.58 106	99.27 42	99.57 101	99.39 59	99.75 45	99.62 40	99.17 20	99.83 193	99.06 83	99.62 244	99.66 78

K. test v3		98.00 255	97.66 280	99.03 146	99.79 23	97.56 203	99.19 52	92.47 477	99.62 33	99.52 88	99.66 32	89.61 394	99.96 14	99.25 68	99.81 134	99.56 129

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 84	99.78 24	98.11 144	97.77 250	99.90 11	99.33 66	99.97 3	99.66 32	99.71 3	99.96 14	99.79 19	99.99 5	99.96 8

APD_test1		98.83 120	98.66 144	99.34 84	99.78 24	99.47 9	98.42 151	99.45 160	98.28 193	98.98 202	99.19 154	97.76 156	99.58 385	96.57 300	99.55 271	98.97 346

test_vis3_rt		99.14 63	99.17 61	99.07 136	99.78 24	98.38 120	98.92 83	99.94 2	97.80 239	99.91 12	99.67 30	97.15 208	98.91 470	99.76 23	99.56 267	99.92 12

EGC-MVSNET		85.24 456	80.54 459	99.34 84	99.77 27	99.20 40	99.08 61	99.29 240	12.08 495	20.84 496	99.42 90	97.55 175	99.85 157	97.08 246	99.72 193	98.96 348

Anonymous20240521		98.69 149	98.87 108	98.16 301	99.77 27	95.11 344	99.08 61	99.44 168	99.34 65	99.33 131	99.55 57	94.10 336	99.94 42	99.25 68	99.96 28	99.42 213

FC-MVSNet-test		99.27 38	99.25 53	99.34 84	99.77 27	98.37 122	99.30 35	99.57 101	99.61 35	99.40 116	99.50 69	97.12 209	99.85 157	99.02 87	99.94 50	99.80 42

test_vis1_n		98.31 219	98.50 171	97.73 341	99.76 30	94.17 376	98.68 109	99.91 9	96.31 356	99.79 39	99.57 49	92.85 357	99.42 431	99.79 19	99.84 112	99.60 100

test_fmvs3		99.12 70	99.41 26	98.25 289	99.76 30	95.07 345	99.05 67	99.94 2	97.78 242	99.82 34	99.84 3	98.56 72	99.71 305	99.96 1	99.96 28	99.97 4

XXY-MVS		99.14 63	99.15 68	99.10 129	99.76 30	97.74 192	98.85 93	99.62 79	98.48 176	99.37 121	99.49 75	98.75 46	99.86 144	98.20 148	99.80 145	99.71 63

TDRefinement		99.42 24	99.38 29	99.55 29	99.76 30	99.33 21	99.68 6	99.71 47	99.38 60	99.53 83	99.61 43	98.64 60	99.80 232	98.24 143	99.84 112	99.52 159

fmvsm_s_conf0.1_n_a		99.17 53	99.30 45	98.80 189	99.75 34	96.59 275	97.97 223	99.86 16	98.22 196	99.88 21	99.71 22	98.59 66	99.84 175	99.73 28	99.98 12	99.98 3

tt0805		98.69 149	98.62 151	98.90 172	99.75 34	99.30 23	99.15 56	96.97 428	98.86 140	98.87 235	97.62 400	98.63 62	98.96 467	99.41 57	98.29 413	98.45 410

test_vis1_n_1920		98.40 202	98.92 100	96.81 405	99.74 36	90.76 456	98.15 181	99.91 9	98.33 184	99.89 18	99.55 57	95.07 307	99.88 116	99.76 23	99.93 56	99.79 44

usedtu_dtu_shiyan2		98.99 90	98.86 112	99.39 73	99.73 37	98.71 98	99.05 67	99.47 151	99.16 93	99.49 95	99.12 176	96.34 259	99.93 54	98.05 160	99.36 315	99.54 142

FOURS1					99.73 37	99.67 3	99.43 15	99.54 119	99.43 55	99.26 149

PEN-MVS		99.41 25	99.34 36	99.62 10	99.73 37	99.14 58	99.29 36	99.54 119	99.62 33	99.56 74	99.42 90	98.16 118	99.96 14	98.78 103	99.93 56	99.77 50

lessismore_v0				98.97 158	99.73 37	97.53 205		86.71 492		99.37 121	99.52 68	89.93 390	99.92 66	98.99 89	99.72 193	99.44 204

SteuartSystems-ACMMP		98.79 129	98.54 164	99.54 32	99.73 37	99.16 49	98.23 171	99.31 224	97.92 230	98.90 224	98.90 242	98.00 130	99.88 116	96.15 332	99.72 193	99.58 115
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 240	98.15 232	98.22 295	99.73 37	95.15 341	97.36 315	99.68 60	94.45 418	98.99 201	99.27 129	96.87 225	99.94 42	97.13 243	99.91 78	99.57 123

Vis-MVSNet		99.34 30	99.36 33	99.27 100	99.73 37	98.26 129	99.17 53	99.78 36	99.11 99	99.27 145	99.48 76	98.82 37	99.95 26	98.94 92	99.93 56	99.59 107
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
tt0320-xc		99.64 5	99.68 5	99.50 54	99.72 44	98.98 72	99.51 10	99.85 18	99.86 6	99.88 21	99.82 5	99.02 26	99.90 82	99.54 44	99.95 38	99.61 98

SSC-MVS		98.71 140	98.74 124	98.62 230	99.72 44	96.08 300	98.74 99	98.64 366	99.74 13	99.67 60	99.24 142	94.57 322	99.95 26	99.11 78	99.24 337	99.82 36

test_f		98.67 158	98.87 108	98.05 312	99.72 44	95.59 315	98.51 135	99.81 31	96.30 358	99.78 40	99.82 5	96.14 266	98.63 477	99.82 12	99.93 56	99.95 9

ACMH	96.65 7	99.25 41	99.24 54	99.26 102	99.72 44	98.38 120	99.07 64	99.55 114	98.30 188	99.65 64	99.45 85	99.22 17	99.76 268	98.44 129	99.77 162	99.64 84
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		99.61 8	99.65 9	99.48 57	99.71 48	98.94 79	99.54 8	99.83 25	99.87 5	99.89 18	99.82 5	98.75 46	99.90 82	99.54 44	99.95 38	99.59 107

fmvsm_s_conf0.1_n		99.16 57	99.33 38	98.64 224	99.71 48	96.10 295	97.87 236	99.85 18	98.56 172	99.90 14	99.68 25	98.69 56	99.85 157	99.72 30	99.98 12	99.97 4

PS-CasMVS		99.40 26	99.33 38	99.62 10	99.71 48	99.10 66	99.29 36	99.53 123	99.53 42	99.46 102	99.41 94	98.23 106	99.95 26	98.89 97	99.95 38	99.81 40

DTE-MVSNet		99.43 23	99.35 34	99.66 7	99.71 48	99.30 23	99.31 30	99.51 129	99.64 27	99.56 74	99.46 81	98.23 106	99.97 7	98.78 103	99.93 56	99.72 62

WR-MVS_H		99.33 31	99.22 55	99.65 8	99.71 48	99.24 31	99.32 26	99.55 114	99.46 50	99.50 94	99.34 113	97.30 197	99.93 54	98.90 95	99.93 56	99.77 50

HPM-MVS_fast		99.01 87	98.82 117	99.57 22	99.71 48	99.35 17	99.00 73	99.50 132	97.33 288	98.94 219	98.86 252	98.75 46	99.82 206	97.53 211	99.71 202	99.56 129

ACMH+	96.62 9	99.08 77	99.00 92	99.33 90	99.71 48	98.83 87	98.60 121	99.58 94	99.11 99	99.53 83	99.18 158	98.81 38	99.67 334	96.71 284	99.77 162	99.50 167

PMVS	91.26 20	97.86 269	97.94 256	97.65 350	99.71 48	97.94 169	98.52 130	98.68 362	98.99 122	97.52 369	99.35 109	97.41 190	98.18 483	91.59 446	99.67 223	96.82 472
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FE-MVSNET2		99.15 58	99.22 55	98.94 162	99.70 56	97.49 206	98.62 118	99.67 64	98.85 143	99.34 128	99.54 63	98.47 76	99.81 223	98.93 93	99.91 78	99.51 163

KinetiMVS		99.03 85	99.02 88	99.03 146	99.70 56	97.48 209	98.43 148	99.29 240	99.70 16	99.60 71	99.07 188	96.13 267	99.94 42	99.42 56	99.87 98	99.68 71

FIs		99.14 63	99.09 80	99.29 96	99.70 56	98.28 128	99.13 58	99.52 128	99.48 45	99.24 159	99.41 94	96.79 233	99.82 206	98.69 113	99.88 94	99.76 56

VPNet		98.87 110	98.83 116	99.01 150	99.70 56	97.62 201	98.43 148	99.35 205	99.47 48	99.28 143	99.05 196	96.72 239	99.82 206	98.09 155	99.36 315	99.59 107

fmvsm_s_conf0.1_n_2		99.20 51	99.38 29	98.65 222	99.69 60	96.08 300	97.49 296	99.90 11	99.53 42	99.88 21	99.64 37	98.51 75	99.90 82	99.83 10	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 216	98.68 139	97.27 381	99.69 60	92.29 430	98.03 204	99.85 18	97.62 252	99.96 4	99.62 40	93.98 337	99.74 287	99.52 50	99.86 105	99.79 44

MP-MVS-pluss		98.57 175	98.23 220	99.60 16	99.69 60	99.35 17	97.16 337	99.38 191	94.87 408	98.97 206	98.99 218	98.01 129	99.88 116	97.29 230	99.70 209	99.58 115
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 46	99.32 40	98.96 159	99.68 63	97.35 217	98.84 95	99.48 142	99.69 18	99.63 67	99.68 25	99.03 24	99.96 14	97.97 170	99.92 69	99.57 123

sd_testset		99.28 37	99.31 42	99.19 113	99.68 63	98.06 156	99.41 17	99.30 232	99.69 18	99.63 67	99.68 25	99.25 16	99.96 14	97.25 233	99.92 69	99.57 123

test_fmvs1_n		98.09 246	98.28 211	97.52 367	99.68 63	93.47 409	98.63 116	99.93 5	95.41 396	99.68 58	99.64 37	91.88 373	99.48 418	99.82 12	99.87 98	99.62 90

CHOSEN 1792x2688		97.49 298	97.14 313	98.54 253	99.68 63	96.09 298	96.50 373	99.62 79	91.58 456	98.84 238	98.97 225	92.36 363	99.88 116	96.76 277	99.95 38	99.67 76

tfpnnormal		98.90 105	98.90 102	98.91 169	99.67 67	97.82 184	99.00 73	99.44 168	99.45 51	99.51 93	99.24 142	98.20 113	99.86 144	95.92 341	99.69 212	99.04 332

MTAPA		98.88 109	98.64 147	99.61 14	99.67 67	99.36 16	98.43 148	99.20 264	98.83 145	98.89 227	98.90 242	96.98 219	99.92 66	97.16 238	99.70 209	99.56 129

test_fmvsmvis_n_1920		99.26 40	99.49 16	98.54 253	99.66 69	96.97 254	98.00 211	99.85 18	99.24 76	99.92 8	99.50 69	99.39 12	99.95 26	99.89 3	99.98 12	98.71 387

mvs5depth		99.30 34	99.59 12	98.44 267	99.65 70	95.35 333	99.82 3	99.94 2	99.83 7	99.42 111	99.94 2	98.13 121	99.96 14	99.63 36	99.96 28	100.00 1

fmvsm_l_conf0.5_n_a		99.19 52	99.27 48	98.94 162	99.65 70	97.05 249	97.80 245	99.76 39	98.70 154	99.78 40	99.11 178	98.79 42	99.95 26	99.85 6	99.96 28	99.83 33

WB-MVS		98.52 189	98.55 162	98.43 268	99.65 70	95.59 315	98.52 130	98.77 351	99.65 26	99.52 88	99.00 216	94.34 328	99.93 54	98.65 115	98.83 385	99.76 56

CP-MVSNet		99.21 48	99.09 80	99.56 27	99.65 70	98.96 78	99.13 58	99.34 211	99.42 56	99.33 131	99.26 135	97.01 217	99.94 42	98.74 108	99.93 56	99.79 44

HPM-MVS		98.79 129	98.53 166	99.59 20	99.65 70	99.29 25	99.16 54	99.43 174	96.74 336	98.61 272	98.38 343	98.62 63	99.87 135	96.47 312	99.67 223	99.59 107
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 167	98.36 197	99.42 68	99.65 70	99.42 11	98.55 126	99.57 101	97.72 246	98.90 224	99.26 135	96.12 269	99.52 406	95.72 352	99.71 202	99.32 260

NormalMVS		98.26 226	97.97 253	99.15 122	99.64 76	97.83 179	98.28 165	99.43 174	99.24 76	98.80 246	98.85 255	89.76 392	99.94 42	98.04 161	99.67 223	99.68 71

lecture		99.25 41	99.12 71	99.62 10	99.64 76	99.40 12	98.89 88	99.51 129	99.19 88	99.37 121	99.25 140	98.36 87	99.88 116	98.23 145	99.67 223	99.59 107

fmvsm_l_conf0.5_n		99.21 48	99.28 47	99.02 149	99.64 76	97.28 228	97.82 241	99.76 39	98.73 147	99.82 34	99.09 186	98.81 38	99.95 26	99.86 4	99.96 28	99.83 33

test_fmvsmconf_n		99.44 19	99.48 18	99.31 95	99.64 76	98.10 146	97.68 264	99.84 22	99.29 72	99.92 8	99.57 49	99.60 5	99.96 14	99.74 27	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 164	98.49 176	99.06 142	99.64 76	97.90 173	98.51 135	98.94 316	96.96 319	99.24 159	98.89 248	97.83 148	99.81 223	96.88 267	99.49 293	99.48 185
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 123	98.72 128	99.12 125	99.64 76	98.54 111	97.98 219	99.68 60	97.62 252	99.34 128	99.18 158	97.54 177	99.77 262	97.79 184	99.74 182	99.04 332

Elysia		99.15 58	99.14 69	99.18 114	99.63 82	97.92 170	98.50 137	99.43 174	99.67 21	99.70 52	99.13 173	96.66 242	99.98 4	99.54 44	99.96 28	99.64 84

StellarMVS		99.15 58	99.14 69	99.18 114	99.63 82	97.92 170	98.50 137	99.43 174	99.67 21	99.70 52	99.13 173	96.66 242	99.98 4	99.54 44	99.96 28	99.64 84

KD-MVS_self_test		99.25 41	99.18 60	99.44 66	99.63 82	99.06 71	98.69 108	99.54 119	99.31 69	99.62 70	99.53 65	97.36 194	99.86 144	99.24 70	99.71 202	99.39 226

EU-MVSNet		97.66 286	98.50 171	95.13 447	99.63 82	85.84 478	98.35 161	98.21 390	98.23 195	99.54 79	99.46 81	95.02 308	99.68 330	98.24 143	99.87 98	99.87 22

HyFIR lowres test		97.19 326	96.60 350	98.96 159	99.62 86	97.28 228	95.17 441	99.50 132	94.21 423	99.01 196	98.32 351	86.61 414	99.99 2	97.10 245	99.84 112	99.60 100

E5new		99.05 80	99.11 72	98.85 176	99.60 87	97.30 222	98.42 151	99.63 73	98.73 147	99.26 149	99.39 100	98.71 50	99.70 312	98.43 131	99.84 112	99.54 142

E6new		99.05 80	99.11 72	98.85 176	99.60 87	97.30 222	98.42 151	99.63 73	98.73 147	99.26 149	99.39 100	98.71 50	99.70 312	98.43 131	99.84 112	99.54 142

E6		99.05 80	99.11 72	98.85 176	99.60 87	97.30 222	98.42 151	99.63 73	98.73 147	99.26 149	99.39 100	98.71 50	99.70 312	98.43 131	99.84 112	99.54 142

E5		99.05 80	99.11 72	98.85 176	99.60 87	97.30 222	98.42 151	99.63 73	98.73 147	99.26 149	99.39 100	98.71 50	99.70 312	98.43 131	99.84 112	99.54 142

fmvsm_l_conf0.5_n_9		99.32 33	99.43 24	98.98 156	99.59 91	97.18 240	97.44 305	99.83 25	99.56 40	99.91 12	99.34 113	99.36 13	99.93 54	99.83 10	99.98 12	99.85 30

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 84	99.59 91	98.21 137	97.82 241	99.84 22	99.41 58	99.92 8	99.41 94	99.51 8	99.95 26	99.84 9	99.97 21	99.87 22

MED-MVS test				99.45 64	99.58 93	98.93 80	98.68 109	99.60 84	96.46 349	99.53 83	98.77 275		99.83 193	96.67 289	99.64 234	99.58 115

MED-MVS		98.90 105	98.72 128	99.45 64	99.58 93	98.93 80	98.68 109	99.60 84	98.14 214	99.53 83	98.77 275	97.87 145	99.83 193	96.67 289	99.64 234	99.58 115

TestfortrainingZip a		98.95 98	98.72 128	99.64 9	99.58 93	99.32 22	98.68 109	99.60 84	96.46 349	99.53 83	98.77 275	97.87 145	99.83 193	98.39 136	99.64 234	99.77 50

FE-MVSNET		98.59 172	98.50 171	98.87 173	99.58 93	97.30 222	98.08 193	99.74 43	96.94 321	98.97 206	99.10 181	96.94 221	99.74 287	97.33 228	99.86 105	99.55 136

mmtdpeth		99.30 34	99.42 25	98.92 168	99.58 93	96.89 262	99.48 13	99.92 7	99.92 2	98.26 310	99.80 11	98.33 93	99.91 75	99.56 41	99.95 38	99.97 4

ACMMP_NAP		98.75 136	98.48 177	99.57 22	99.58 93	99.29 25	97.82 241	99.25 253	96.94 321	98.78 248	99.12 176	98.02 128	99.84 175	97.13 243	99.67 223	99.59 107

nrg030		99.40 26	99.35 34	99.54 32	99.58 93	99.13 61	98.98 76	99.48 142	99.68 20	99.46 102	99.26 135	98.62 63	99.73 294	99.17 75	99.92 69	99.76 56

VDDNet		98.21 233	97.95 254	99.01 150	99.58 93	97.74 192	99.01 71	97.29 419	99.67 21	98.97 206	99.50 69	90.45 387	99.80 232	97.88 177	99.20 345	99.48 185

COLMAP_ROB	96.50 10	98.99 90	98.85 115	99.41 70	99.58 93	99.10 66	98.74 99	99.56 110	99.09 109	99.33 131	99.19 154	98.40 84	99.72 304	95.98 339	99.76 177	99.42 213
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	98.99 152	99.57 102	97.73 194	97.93 225	99.83 25	99.22 79	99.93 6	99.30 123	99.42 11	99.96 14	99.85 6	99.99 5	99.29 270

ZNCC-MVS		98.68 155	98.40 189	99.54 32	99.57 102	99.21 34	98.46 145	99.29 240	97.28 294	98.11 322	98.39 341	98.00 130	99.87 135	96.86 270	99.64 234	99.55 136

MSP-MVS		98.40 202	98.00 248	99.61 14	99.57 102	99.25 30	98.57 124	99.35 205	97.55 263	99.31 139	97.71 393	94.61 321	99.88 116	96.14 333	99.19 348	99.70 68
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
testgi		98.32 217	98.39 192	98.13 302	99.57 102	95.54 318	97.78 247	99.49 140	97.37 285	99.19 167	97.65 397	98.96 29	99.49 415	96.50 311	98.99 373	99.34 251

MP-MVS		98.46 195	98.09 237	99.54 32	99.57 102	99.22 33	98.50 137	99.19 268	97.61 255	97.58 363	98.66 303	97.40 191	99.88 116	94.72 378	99.60 251	99.54 142
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 140	98.46 181	99.47 61	99.57 102	98.97 74	98.23 171	99.48 142	96.60 341	99.10 178	99.06 189	98.71 50	99.83 193	95.58 359	99.78 156	99.62 90

LGP-MVS_train				99.47 61	99.57 102	98.97 74		99.48 142	96.60 341	99.10 178	99.06 189	98.71 50	99.83 193	95.58 359	99.78 156	99.62 90

IS-MVSNet		98.19 236	97.90 262	99.08 134	99.57 102	97.97 164	99.31 30	98.32 386	99.01 121	98.98 202	99.03 200	91.59 375	99.79 245	95.49 361	99.80 145	99.48 185

viewdifsd2359ckpt11		98.84 117	99.04 85	98.24 291	99.56 110	95.51 320	97.38 310	99.70 52	99.16 93	99.57 72	99.40 97	98.26 102	99.71 305	98.55 124	99.82 128	99.50 167

viewmsd2359difaftdt		98.84 117	99.04 85	98.24 291	99.56 110	95.51 320	97.38 310	99.70 52	99.16 93	99.57 72	99.40 97	98.26 102	99.71 305	98.55 124	99.82 128	99.50 167

dcpmvs_2		98.78 131	99.11 72	97.78 331	99.56 110	93.67 404	99.06 65	99.86 16	99.50 44	99.66 61	99.26 135	97.21 205	99.99 2	98.00 166	99.91 78	99.68 71

test_0402		98.76 135	98.71 133	98.93 165	99.56 110	98.14 142	98.45 147	99.34 211	99.28 73	98.95 212	98.91 239	98.34 92	99.79 245	95.63 356	99.91 78	98.86 365

EPP-MVSNet		98.30 220	98.04 244	99.07 136	99.56 110	97.83 179	99.29 36	98.07 397	99.03 119	98.59 276	99.13 173	92.16 367	99.90 82	96.87 268	99.68 217	99.49 174

ACMMP		98.75 136	98.50 171	99.52 45	99.56 110	99.16 49	98.87 89	99.37 195	97.16 309	98.82 242	99.01 212	97.71 159	99.87 135	96.29 324	99.69 212	99.54 142
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
fmvsm_s_conf0.5_n_a		99.10 72	99.20 59	98.78 196	99.55 116	96.59 275	97.79 246	99.82 30	98.21 198	99.81 37	99.53 65	98.46 80	99.84 175	99.70 33	99.97 21	99.90 15

fmvsm_s_conf0.5_n		99.09 73	99.26 51	98.61 234	99.55 116	96.09 298	97.74 257	99.81 31	98.55 173	99.85 27	99.55 57	98.60 65	99.84 175	99.69 35	99.98 12	99.89 16

FMVSNet1		99.17 53	99.17 61	99.17 116	99.55 116	98.24 131	99.20 48	99.44 168	99.21 81	99.43 107	99.55 57	97.82 151	99.86 144	98.42 135	99.89 92	99.41 216

Vis-MVSNet (Re-imp)		97.46 300	97.16 310	98.34 280	99.55 116	96.10 295	98.94 81	98.44 380	98.32 186	98.16 316	98.62 312	88.76 399	99.73 294	93.88 404	99.79 151	99.18 306

ACMM	96.08 12	98.91 103	98.73 126	99.48 57	99.55 116	99.14 58	98.07 197	99.37 195	97.62 252	99.04 192	98.96 228	98.84 36	99.79 245	97.43 222	99.65 232	99.49 174
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs2		98.70 145	98.97 96	97.89 323	99.54 121	94.05 381	98.55 126	99.92 7	96.78 334	99.72 48	99.78 13	96.60 246	99.67 334	99.91 2	99.90 86	99.94 10

mPP-MVS		98.64 162	98.34 200	99.54 32	99.54 121	99.17 45	98.63 116	99.24 258	97.47 271	98.09 324	98.68 298	97.62 168	99.89 98	96.22 327	99.62 244	99.57 123

XVG-ACMP-BASELINE		98.56 176	98.34 200	99.22 110	99.54 121	98.59 105	97.71 260	99.46 156	97.25 297	98.98 202	98.99 218	97.54 177	99.84 175	95.88 342	99.74 182	99.23 286

viewmacassd2359aftdt		98.86 114	98.87 108	98.83 182	99.53 124	97.32 221	97.70 262	99.64 71	98.22 196	99.25 157	99.27 129	98.40 84	99.61 371	97.98 169	99.87 98	99.55 136

region2R		98.69 149	98.40 189	99.54 32	99.53 124	99.17 45	98.52 130	99.31 224	97.46 276	98.44 295	98.51 326	97.83 148	99.88 116	96.46 313	99.58 260	99.58 115

PGM-MVS		98.66 159	98.37 196	99.55 29	99.53 124	99.18 44	98.23 171	99.49 140	97.01 318	98.69 259	98.88 249	98.00 130	99.89 98	95.87 345	99.59 255	99.58 115

E4		98.87 110	98.88 105	98.81 186	99.52 127	97.23 231	97.62 275	99.61 82	98.58 167	99.18 171	99.33 116	98.29 96	99.69 320	97.99 168	99.83 123	99.52 159

Patchmatch-RL test		97.26 319	97.02 320	97.99 316	99.52 127	95.53 319	96.13 398	99.71 47	97.47 271	99.27 145	99.16 164	84.30 438	99.62 364	97.89 174	99.77 162	98.81 373

ACMMPR		98.70 145	98.42 187	99.54 32	99.52 127	99.14 58	98.52 130	99.31 224	97.47 271	98.56 282	98.54 321	97.75 157	99.88 116	96.57 300	99.59 255	99.58 115

fmvsm_s_conf0.5_n_9		99.17 53	99.38 29	98.53 255	99.51 130	95.82 310	97.62 275	99.78 36	99.72 15	99.90 14	99.48 76	98.66 58	99.89 98	99.85 6	99.93 56	99.89 16

AstraMVS		98.16 242	98.07 242	98.41 270	99.51 130	95.86 307	98.00 211	95.14 460	98.97 125	99.43 107	99.24 142	93.25 345	99.84 175	99.21 71	99.87 98	99.54 142

fmvsm_s_conf0.5_n_8		99.13 67	99.26 51	98.74 209	99.51 130	96.44 287	97.65 270	99.65 69	99.66 24	99.78 40	99.48 76	97.92 138	99.93 54	99.72 30	99.95 38	99.87 22

GST-MVS		98.61 168	98.30 208	99.52 45	99.51 130	99.20 40	98.26 169	99.25 253	97.44 279	98.67 262	98.39 341	97.68 160	99.85 157	96.00 337	99.51 283	99.52 159

Anonymous20231206		98.21 233	98.21 221	98.20 296	99.51 130	95.43 329	98.13 183	99.32 219	96.16 365	98.93 220	98.82 265	96.00 274	99.83 193	97.32 229	99.73 185	99.36 244

ACMP	95.32 15	98.41 199	98.09 237	99.36 75	99.51 130	98.79 90	97.68 264	99.38 191	95.76 383	98.81 244	98.82 265	98.36 87	99.82 206	94.75 375	99.77 162	99.48 185
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		98.39 208	98.20 222	98.98 156	99.50 136	97.49 206	97.78 247	97.69 406	98.75 146	99.49 95	99.25 140	92.30 365	99.94 42	99.14 76	99.88 94	99.50 167

DVP-MVS		98.77 134	98.52 167	99.52 45	99.50 136	99.21 34	98.02 207	98.84 340	97.97 224	99.08 180	99.02 201	97.61 170	99.88 116	96.99 254	99.63 241	99.48 185
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				99.60 16	99.50 136	99.23 32	98.02 207	99.32 219					99.88 116	96.99 254	99.63 241	99.68 71

test0726					99.50 136	99.21 34	98.17 179	99.35 205	97.97 224	99.26 149	99.06 189	97.61 170

AllTest		98.44 197	98.20 222	99.16 119	99.50 136	98.55 108	98.25 170	99.58 94	96.80 332	98.88 231	99.06 189	97.65 163	99.57 387	94.45 385	99.61 249	99.37 237

TestCases				99.16 119	99.50 136	98.55 108		99.58 94	96.80 332	98.88 231	99.06 189	97.65 163	99.57 387	94.45 385	99.61 249	99.37 237

XVG-OURS		98.53 185	98.34 200	99.11 127	99.50 136	98.82 89	95.97 404	99.50 132	97.30 292	99.05 190	98.98 223	99.35 14	99.32 445	95.72 352	99.68 217	99.18 306

EG-PatchMatch MVS		98.99 90	99.01 90	98.94 162	99.50 136	97.47 210	98.04 202	99.59 91	98.15 213	99.40 116	99.36 108	98.58 71	99.76 268	98.78 103	99.68 217	99.59 107

fmvsm_s_conf0.5_n_2		99.14 63	99.31 42	98.63 228	99.49 144	96.08 300	97.38 310	99.81 31	99.48 45	99.84 30	99.57 49	98.46 80	99.89 98	99.82 12	99.97 21	99.91 13

SED-MVS		98.91 103	98.72 128	99.49 55	99.49 144	99.17 45	98.10 190	99.31 224	98.03 220	99.66 61	99.02 201	98.36 87	99.88 116	96.91 260	99.62 244	99.41 216

IU-MVS					99.49 144	99.15 53		98.87 331	92.97 441	99.41 113				96.76 277	99.62 244	99.66 78

test_241102_ONE					99.49 144	99.17 45		99.31 224	97.98 223	99.66 61	98.90 242	98.36 87	99.48 418

UA-Net		99.47 16	99.40 27	99.70 2	99.49 144	99.29 25	99.80 4	99.72 45	99.82 8	99.04 192	99.81 8	98.05 127	99.96 14	98.85 99	99.99 5	99.86 28

HFP-MVS		98.71 140	98.44 184	99.51 49	99.49 144	99.16 49	98.52 130	99.31 224	97.47 271	98.58 278	98.50 330	97.97 134	99.85 157	96.57 300	99.59 255	99.53 156

VPA-MVSNet		99.30 34	99.30 45	99.28 97	99.49 144	98.36 125	99.00 73	99.45 160	99.63 29	99.52 88	99.44 86	98.25 104	99.88 116	99.09 80	99.84 112	99.62 90

XVG-OURS-SEG-HR		98.49 192	98.28 211	99.14 123	99.49 144	98.83 87	96.54 369	99.48 142	97.32 290	99.11 175	98.61 314	99.33 15	99.30 448	96.23 326	98.38 409	99.28 273

fmvsm_s_conf0.5_n_11		99.21 48	99.34 36	98.80 189	99.48 152	96.56 280	97.97 223	99.69 54	99.63 29	99.84 30	99.54 63	98.21 111	99.94 42	99.76 23	99.95 38	99.88 20

114514_t		96.50 359	95.77 368	98.69 217	99.48 152	97.43 214	97.84 240	99.55 114	81.42 488	96.51 427	98.58 318	95.53 294	99.67 334	93.41 417	99.58 260	98.98 342

IterMVS-LS		98.55 180	98.70 136	98.09 305	99.48 152	94.73 359	97.22 331	99.39 189	98.97 125	99.38 119	99.31 122	96.00 274	99.93 54	98.58 118	99.97 21	99.60 100
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.5_n_10		99.15 58	99.27 48	98.78 196	99.47 155	96.56 280	97.75 256	99.71 47	99.60 36	99.74 47	99.44 86	97.96 135	99.95 26	99.86 4	99.94 50	99.82 36

fmvsm_s_conf0.5_n_5		99.07 79	99.10 78	98.99 152	99.47 155	97.22 234	97.40 307	99.83 25	97.61 255	99.85 27	99.30 123	98.80 40	99.95 26	99.71 32	99.90 86	99.78 47

v8		99.01 87	99.16 63	98.57 241	99.47 155	96.31 292	98.90 84	99.47 151	99.03 119	99.52 88	99.57 49	96.93 222	99.81 223	99.60 37	99.98 12	99.60 100

SSC-MVS3.2		98.53 185	98.79 120	97.74 338	99.46 158	93.62 407	96.45 375	99.34 211	99.33 66	98.93 220	98.70 294	97.90 139	99.90 82	99.12 77	99.92 69	99.69 70

fmvsm_s_conf0.5_n_3		99.22 47	99.37 32	98.78 196	99.46 158	96.58 278	97.65 270	99.72 45	99.47 48	99.86 24	99.50 69	98.94 30	99.89 98	99.75 26	99.97 21	99.86 28

XVS		98.72 139	98.45 182	99.53 39	99.46 158	99.21 34	98.65 114	99.34 211	98.62 161	97.54 367	98.63 310	97.50 183	99.83 193	96.79 273	99.53 277	99.56 129

X-MVStestdata		94.32 413	92.59 432	99.53 39	99.46 158	99.21 34	98.65 114	99.34 211	98.62 161	97.54 367	45.85 493	97.50 183	99.83 193	96.79 273	99.53 277	99.56 129

test20.03		98.78 131	98.77 123	98.78 196	99.46 158	97.20 237	97.78 247	99.24 258	99.04 118	99.41 113	98.90 242	97.65 163	99.76 268	97.70 195	99.79 151	99.39 226

guyue		98.01 254	97.93 258	98.26 287	99.45 163	95.48 324	98.08 193	96.24 443	98.89 136	99.34 128	99.14 171	91.32 379	99.82 206	99.07 81	99.83 123	99.48 185

CSCG		98.68 155	98.50 171	99.20 111	99.45 163	98.63 100	98.56 125	99.57 101	97.87 234	98.85 236	98.04 372	97.66 162	99.84 175	96.72 282	99.81 134	99.13 321

GeoE		99.05 80	98.99 94	99.25 105	99.44 165	98.35 126	98.73 103	99.56 110	98.42 179	98.91 223	98.81 268	98.94 30	99.91 75	98.35 138	99.73 185	99.49 174

v148		98.45 196	98.60 156	98.00 315	99.44 165	94.98 347	97.44 305	99.06 294	98.30 188	99.32 137	98.97 225	96.65 244	99.62 364	98.37 137	99.85 107	99.39 226

v10		98.97 95	99.11 72	98.55 248	99.44 165	96.21 294	98.90 84	99.55 114	98.73 147	99.48 97	99.60 45	96.63 245	99.83 193	99.70 33	99.99 5	99.61 98

V42		98.78 131	98.78 122	98.76 203	99.44 165	97.04 250	98.27 168	99.19 268	97.87 234	99.25 157	99.16 164	96.84 226	99.78 256	99.21 71	99.84 112	99.46 195

MDA-MVSNet-bldmvs		97.94 260	97.91 261	98.06 310	99.44 165	94.96 348	96.63 365	99.15 284	98.35 182	98.83 239	99.11 178	94.31 329	99.85 157	96.60 297	98.72 391	99.37 237

viewdifsd2359ckpt07		98.71 140	98.86 112	98.26 287	99.43 170	95.65 314	97.20 332	99.66 65	99.20 83	99.29 141	99.01 212	98.29 96	99.73 294	97.92 173	99.75 181	99.39 226

casdiffmvs_mvg		99.12 70	99.16 63	98.99 152	99.43 170	97.73 194	98.00 211	99.62 79	99.22 79	99.55 77	99.22 148	98.93 32	99.75 280	98.66 114	99.81 134	99.50 167
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		98.90 105	99.01 90	98.57 241	99.42 172	96.59 275	98.13 183	99.66 65	99.09 109	99.30 140	99.02 201	98.79 42	99.89 98	97.87 179	99.80 145	99.23 286

test1111		96.49 360	96.82 334	95.52 440	99.42 172	87.08 475	99.22 45	87.14 491	99.11 99	99.46 102	99.58 47	88.69 400	99.86 144	98.80 101	99.95 38	99.62 90

v2v482		98.56 176	98.62 151	98.37 277	99.42 172	95.81 311	97.58 284	99.16 279	97.90 232	99.28 143	99.01 212	95.98 279	99.79 245	99.33 60	99.90 86	99.51 163

OPM-MVS		98.56 176	98.32 206	99.25 105	99.41 175	98.73 95	97.13 339	99.18 272	97.10 312	98.75 254	98.92 236	98.18 114	99.65 354	96.68 288	99.56 267	99.37 237
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 248	98.08 240	98.04 313	99.41 175	94.59 365	94.59 459	99.40 187	97.50 268	98.82 242	98.83 262	96.83 228	99.84 175	97.50 214	99.81 134	99.71 63

E2		98.70 145	98.68 139	98.73 211	99.40 177	97.10 247	97.48 297	99.57 101	98.09 217	99.00 197	99.20 151	97.90 139	99.67 334	97.73 193	99.77 162	99.43 208

E3		98.69 149	98.68 139	98.73 211	99.40 177	97.10 247	97.48 297	99.57 101	98.09 217	99.00 197	99.20 151	97.90 139	99.67 334	97.73 193	99.77 162	99.43 208

test_one_0601					99.39 179	99.20 40		99.31 224	98.49 175	98.66 264	99.02 201	97.64 166

mvsany_test3		98.87 110	98.92 100	98.74 209	99.38 180	96.94 258	98.58 123	99.10 289	96.49 346	99.96 4	99.81 8	98.18 114	99.45 426	98.97 90	99.79 151	99.83 33

patch_mono-2		98.51 190	98.63 149	98.17 299	99.38 180	94.78 356	97.36 315	99.69 54	98.16 208	98.49 291	99.29 126	97.06 212	99.97 7	98.29 142	99.91 78	99.76 56

test2506		92.39 444	91.89 446	93.89 461	99.38 180	82.28 492	99.32 26	66.03 499	99.08 113	98.77 251	99.57 49	66.26 485	99.84 175	98.71 111	99.95 38	99.54 142

ECVR-MVS		96.42 362	96.61 348	95.85 432	99.38 180	88.18 470	99.22 45	86.00 493	99.08 113	99.36 124	99.57 49	88.47 405	99.82 206	98.52 126	99.95 38	99.54 142

casdiffmvs		98.95 98	99.00 92	98.81 186	99.38 180	97.33 219	97.82 241	99.57 101	99.17 92	99.35 126	99.17 162	98.35 91	99.69 320	98.46 128	99.73 185	99.41 216
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 97	99.02 88	98.76 203	99.38 180	97.26 230	98.49 140	99.50 132	98.86 140	99.19 167	99.06 189	98.23 106	99.69 320	98.71 111	99.76 177	99.33 257

TranMVSNet+NR-MVSNet		99.17 53	99.07 83	99.46 63	99.37 186	98.87 85	98.39 157	99.42 180	99.42 56	99.36 124	99.06 189	98.38 86	99.95 26	98.34 139	99.90 86	99.57 123

fmvsm_s_conf0.5_n_6		99.08 77	99.21 58	98.69 217	99.36 187	96.51 282	97.62 275	99.68 60	98.43 178	99.85 27	99.10 181	99.12 23	99.88 116	99.77 22	99.92 69	99.67 76

tttt0517		95.64 390	94.98 400	97.64 353	99.36 187	93.81 399	98.72 104	90.47 485	98.08 219	98.67 262	98.34 348	73.88 471	99.92 66	97.77 186	99.51 283	99.20 296

test_part2					99.36 187	99.10 66				99.05 190

v1144		98.60 170	98.66 144	98.41 270	99.36 187	95.90 305	97.58 284	99.34 211	97.51 267	99.27 145	99.15 168	96.34 259	99.80 232	99.47 54	99.93 56	99.51 163

CP-MVS		98.70 145	98.42 187	99.52 45	99.36 187	99.12 63	98.72 104	99.36 199	97.54 265	98.30 304	98.40 340	97.86 147	99.89 98	96.53 309	99.72 193	99.56 129

diffmvs_AUTHOR		98.50 191	98.59 158	98.23 294	99.35 192	95.48 324	96.61 366	99.60 84	98.37 180	98.90 224	99.00 216	97.37 193	99.76 268	98.22 146	99.85 107	99.46 195

Test_1112_low_res		96.99 341	96.55 352	98.31 283	99.35 192	95.47 327	95.84 416	99.53 123	91.51 458	96.80 411	98.48 333	91.36 378	99.83 193	96.58 298	99.53 277	99.62 90

DeepC-MVS	97.60 4	98.97 95	98.93 99	99.10 129	99.35 192	97.98 163	98.01 210	99.46 156	97.56 261	99.54 79	99.50 69	98.97 28	99.84 175	98.06 158	99.92 69	99.49 174
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 318	96.86 330	98.58 238	99.34 195	96.32 291	96.75 358	99.58 94	93.14 439	96.89 406	97.48 407	92.11 370	99.86 144	96.91 260	99.54 273	99.57 123

reproduce_model		99.15 58	98.97 96	99.67 4	99.33 196	99.44 10	98.15 181	99.47 151	99.12 98	99.52 88	99.32 121	98.31 94	99.90 82	97.78 185	99.73 185	99.66 78

MVSMamba_PlusPlus		98.83 120	98.98 95	98.36 278	99.32 197	96.58 278	98.90 84	99.41 184	99.75 11	98.72 257	99.50 69	96.17 265	99.94 42	99.27 65	99.78 156	98.57 403

fmvsm_s_conf0.5_n_4		99.01 87	99.22 55	98.38 274	99.31 198	95.48 324	97.56 286	99.73 44	98.87 138	99.75 45	99.27 129	98.80 40	99.86 144	99.80 17	99.90 86	99.81 40

SF-MVS		98.53 185	98.27 214	99.32 92	99.31 198	98.75 91	98.19 175	99.41 184	96.77 335	98.83 239	98.90 242	97.80 153	99.82 206	95.68 355	99.52 280	99.38 235

CPTT-MVS		97.84 275	97.36 299	99.27 100	99.31 198	98.46 116	98.29 164	99.27 247	94.90 407	97.83 347	98.37 344	94.90 310	99.84 175	93.85 406	99.54 273	99.51 163

UnsupCasMVSNet_eth		97.89 264	97.60 285	98.75 205	99.31 198	97.17 242	97.62 275	99.35 205	98.72 153	98.76 253	98.68 298	92.57 362	99.74 287	97.76 190	95.60 476	99.34 251

fmvsm_s_conf0.5_n_7		98.83 120	99.04 85	98.20 296	99.30 202	94.83 354	97.23 327	99.36 199	98.64 156	99.84 30	99.43 89	98.10 123	99.91 75	99.56 41	99.96 28	99.87 22

pmmvs-eth3d		98.47 194	98.34 200	98.86 175	99.30 202	97.76 190	97.16 337	99.28 244	95.54 389	99.42 111	99.19 154	97.27 200	99.63 361	97.89 174	99.97 21	99.20 296

mamv4		99.44 19	99.39 28	99.58 21	99.30 202	99.74 2	99.04 69	99.81 31	99.77 10	99.82 34	99.57 49	97.82 151	99.98 4	99.53 48	99.89 92	99.01 336

viewcassd2359sk11		98.55 180	98.51 168	98.67 220	99.29 205	96.99 253	97.39 308	99.54 119	97.73 244	98.81 244	99.08 187	97.55 175	99.66 347	97.52 213	99.67 223	99.36 244

SymmetryMVS		98.05 250	97.71 275	99.09 133	99.29 205	97.83 179	98.28 165	97.64 411	99.24 76	98.80 246	98.85 255	89.76 392	99.94 42	98.04 161	99.50 291	99.49 174

Anonymous20231211		99.27 38	99.27 48	99.26 102	99.29 205	98.18 138	99.49 12	99.51 129	99.70 16	99.80 38	99.68 25	96.84 226	99.83 193	99.21 71	99.91 78	99.77 50

viewmanbaseed2359cas		98.58 174	98.54 164	98.70 215	99.28 208	97.13 246	97.47 301	99.55 114	97.55 263	98.96 211	98.92 236	97.77 155	99.59 378	97.59 205	99.77 162	99.39 226

UnsupCasMVSNet_bld		97.30 316	96.92 326	98.45 265	99.28 208	96.78 269	96.20 392	99.27 247	95.42 393	98.28 308	98.30 352	93.16 348	99.71 305	94.99 369	97.37 447	98.87 364

EC-MVSNet		99.09 73	99.05 84	99.20 111	99.28 208	98.93 80	99.24 44	99.84 22	99.08 113	98.12 321	98.37 344	98.72 49	99.90 82	99.05 84	99.77 162	98.77 381

mamba_0408		98.80 127	98.88 105	98.55 248	99.27 211	96.50 283	98.00 211	99.60 84	98.93 130	99.22 162	98.84 260	98.59 66	99.89 98	97.74 191	99.72 193	99.27 274

SSM_04072		98.80 127	98.88 105	98.56 246	99.27 211	96.50 283	98.00 211	99.60 84	98.93 130	99.22 162	98.84 260	98.59 66	99.90 82	97.74 191	99.72 193	99.27 274

SSM_0407		98.86 114	98.96 98	98.55 248	99.27 211	96.50 283	98.04 202	99.66 65	99.09 109	99.22 162	99.02 201	98.79 42	99.87 135	97.87 179	99.72 193	99.27 274

reproduce-ours		99.09 73	98.90 102	99.67 4	99.27 211	99.49 6	98.00 211	99.42 180	99.05 116	99.48 97	99.27 129	98.29 96	99.89 98	97.61 202	99.71 202	99.62 90

our_new_method		99.09 73	98.90 102	99.67 4	99.27 211	99.49 6	98.00 211	99.42 180	99.05 116	99.48 97	99.27 129	98.29 96	99.89 98	97.61 202	99.71 202	99.62 90

DPE-MVS		98.59 172	98.26 215	99.57 22	99.27 211	99.15 53	97.01 342	99.39 189	97.67 248	99.44 106	98.99 218	97.53 179	99.89 98	95.40 363	99.68 217	99.66 78
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 274	98.18 227	96.87 401	99.27 211	91.16 450	95.53 426	99.25 253	99.10 106	99.41 113	99.35 109	93.10 350	99.96 14	98.65 115	99.94 50	99.49 174

v1192		98.60 170	98.66 144	98.41 270	99.27 211	95.88 306	97.52 291	99.36 199	97.41 280	99.33 131	99.20 151	96.37 257	99.82 206	99.57 39	99.92 69	99.55 136

N_pmnet		97.63 288	97.17 309	98.99 152	99.27 211	97.86 176	95.98 403	93.41 474	95.25 398	99.47 101	98.90 242	95.63 291	99.85 157	96.91 260	99.73 185	99.27 274

viewdifsd2359ckpt13		98.39 208	98.29 210	98.70 215	99.26 220	97.19 238	97.51 293	99.48 142	96.94 321	98.58 278	98.82 265	97.47 188	99.55 394	97.21 235	99.33 321	99.34 251

FPMVS		93.44 430	92.23 437	97.08 389	99.25 221	97.86 176	95.61 423	97.16 423	92.90 443	93.76 476	98.65 305	75.94 469	95.66 490	79.30 488	97.49 440	97.73 454

ME-MVS		98.61 168	98.33 205	99.44 66	99.24 222	98.93 80	97.45 303	99.06 294	98.14 214	99.06 182	98.77 275	96.97 220	99.82 206	96.67 289	99.64 234	99.58 115

new-patchmatchnet		98.35 211	98.74 124	97.18 384	99.24 222	92.23 432	96.42 379	99.48 142	98.30 188	99.69 56	99.53 65	97.44 189	99.82 206	98.84 100	99.77 162	99.49 174

MCST-MVS		98.00 255	97.63 283	99.10 129	99.24 222	98.17 139	96.89 351	98.73 359	95.66 384	97.92 338	97.70 395	97.17 207	99.66 347	96.18 331	99.23 340	99.47 193

UniMVSNet (Re)		98.87 110	98.71 133	99.35 81	99.24 222	98.73 95	97.73 259	99.38 191	98.93 130	99.12 174	98.73 284	96.77 234	99.86 144	98.63 117	99.80 145	99.46 195

jason		97.45 302	97.35 300	97.76 335	99.24 222	93.93 393	95.86 413	98.42 382	94.24 422	98.50 290	98.13 362	94.82 314	99.91 75	97.22 234	99.73 185	99.43 208
jason: jason.
IterMVS		97.73 280	98.11 236	96.57 411	99.24 222	90.28 459	95.52 428	99.21 262	98.86 140	99.33 131	99.33 116	93.11 349	99.94 42	98.49 127	99.94 50	99.48 185
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 180	98.62 151	98.32 281	99.22 228	95.58 317	97.51 293	99.45 160	97.16 309	99.45 105	99.24 142	96.12 269	99.85 157	99.60 37	99.88 94	99.55 136

ITE_SJBPF				98.87 173	99.22 228	98.48 115		99.35 205	97.50 268	98.28 308	98.60 316	97.64 166	99.35 441	93.86 405	99.27 332	98.79 379

h-mvs33		97.77 278	97.33 302	99.10 129	99.21 230	97.84 178	98.35 161	98.57 372	99.11 99	98.58 278	99.02 201	88.65 403	99.96 14	98.11 153	96.34 463	99.49 174

v144192		98.54 183	98.57 160	98.45 265	99.21 230	95.98 303	97.63 274	99.36 199	97.15 311	99.32 137	99.18 158	95.84 286	99.84 175	99.50 51	99.91 78	99.54 142

APDe-MVS		98.99 90	98.79 120	99.60 16	99.21 230	99.15 53	98.87 89	99.48 142	97.57 259	99.35 126	99.24 142	97.83 148	99.89 98	97.88 177	99.70 209	99.75 60
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 101	98.81 119	99.28 97	99.21 230	98.45 117	98.46 145	99.33 217	99.63 29	99.48 97	99.15 168	97.23 203	99.75 280	97.17 237	99.66 231	99.63 89

SR-MVS-dyc-post		98.81 125	98.55 162	99.57 22	99.20 234	99.38 13	98.48 143	99.30 232	98.64 156	98.95 212	98.96 228	97.49 186	99.86 144	96.56 304	99.39 311	99.45 200

RE-MVS-def			98.58 159		99.20 234	99.38 13	98.48 143	99.30 232	98.64 156	98.95 212	98.96 228	97.75 157		96.56 304	99.39 311	99.45 200

v1921920		98.54 183	98.60 156	98.38 274	99.20 234	95.76 313	97.56 286	99.36 199	97.23 303	99.38 119	99.17 162	96.02 272	99.84 175	99.57 39	99.90 86	99.54 142

E3new		98.41 199	98.34 200	98.62 230	99.19 237	96.90 261	97.32 318	99.50 132	97.40 282	98.63 267	98.92 236	97.21 205	99.65 354	97.34 226	99.52 280	99.31 264

thisisatest0530		95.27 399	94.45 410	97.74 338	99.19 237	94.37 369	97.86 237	90.20 486	97.17 308	98.22 311	97.65 397	73.53 472	99.90 82	96.90 265	99.35 318	98.95 349

Anonymous20240529		98.93 101	98.87 108	99.12 125	99.19 237	98.22 136	99.01 71	98.99 312	99.25 75	99.54 79	99.37 104	97.04 213	99.80 232	97.89 174	99.52 280	99.35 249

APD-MVS_3200maxsize		98.84 117	98.61 155	99.53 39	99.19 237	99.27 28	98.49 140	99.33 217	98.64 156	99.03 195	98.98 223	97.89 143	99.85 157	96.54 308	99.42 308	99.46 195

HQP_MVS		97.99 258	97.67 277	98.93 165	99.19 237	97.65 198	97.77 250	99.27 247	98.20 202	97.79 350	97.98 376	94.90 310	99.70 312	94.42 387	99.51 283	99.45 200

plane_prior7					99.19 237	97.87 175

ab-mvs		98.41 199	98.36 197	98.59 237	99.19 237	97.23 231	99.32 26	98.81 345	97.66 249	98.62 270	99.40 97	96.82 229	99.80 232	95.88 342	99.51 283	98.75 384

F-COLMAP		97.30 316	96.68 343	99.14 123	99.19 237	98.39 119	97.27 326	99.30 232	92.93 442	96.62 420	98.00 374	95.73 289	99.68 330	92.62 433	98.46 408	99.35 249

viewdifsd2359ckpt09		98.13 243	97.92 259	98.77 201	99.18 245	97.35 217	97.29 322	99.53 123	95.81 381	98.09 324	98.47 334	96.34 259	99.66 347	97.02 250	99.51 283	99.29 270

SR-MVS		98.71 140	98.43 185	99.57 22	99.18 245	99.35 17	98.36 160	99.29 240	98.29 191	98.88 231	98.85 255	97.53 179	99.87 135	96.14 333	99.31 325	99.48 185

UniMVSNet_NR-MVSNet		98.86 114	98.68 139	99.40 72	99.17 247	98.74 92	97.68 264	99.40 187	99.14 97	99.06 182	98.59 317	96.71 240	99.93 54	98.57 120	99.77 162	99.53 156

LF4IMVS		97.90 262	97.69 276	98.52 256	99.17 247	97.66 197	97.19 336	99.47 151	96.31 356	97.85 346	98.20 359	96.71 240	99.52 406	94.62 379	99.72 193	98.38 420

SMA-MVS		98.40 202	98.03 245	99.51 49	99.16 249	99.21 34	98.05 200	99.22 261	94.16 424	98.98 202	99.10 181	97.52 181	99.79 245	96.45 314	99.64 234	99.53 156
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		98.82 123	98.63 149	99.39 73	99.16 249	98.74 92	97.54 289	99.25 253	98.84 144	99.06 182	98.76 281	96.76 236	99.93 54	98.57 120	99.77 162	99.50 167

NR-MVSNet		98.95 98	98.82 117	99.36 75	99.16 249	98.72 97	99.22 45	99.20 264	99.10 106	99.72 48	98.76 281	96.38 256	99.86 144	98.00 166	99.82 128	99.50 167

MVS_111021_LR		98.30 220	98.12 235	98.83 182	99.16 249	98.03 158	96.09 400	99.30 232	97.58 258	98.10 323	98.24 355	98.25 104	99.34 442	96.69 287	99.65 232	99.12 322

DSMNet-mixed		97.42 305	97.60 285	96.87 401	99.15 253	91.46 439	98.54 128	99.12 286	92.87 444	97.58 363	99.63 39	96.21 264	99.90 82	95.74 351	99.54 273	99.27 274

D2MVS		97.84 275	97.84 266	97.83 327	99.14 254	94.74 358	96.94 346	98.88 329	95.84 378	98.89 227	98.96 228	94.40 326	99.69 320	97.55 208	99.95 38	99.05 328

pmmvs5		97.64 287	97.49 291	98.08 308	99.14 254	95.12 343	96.70 361	99.05 298	93.77 431	98.62 270	98.83 262	93.23 346	99.75 280	98.33 141	99.76 177	99.36 244

SPE-MVS-test		99.13 67	99.09 80	99.26 102	99.13 256	98.97 74	99.31 30	99.88 14	99.44 53	98.16 316	98.51 326	98.64 60	99.93 54	98.91 94	99.85 107	98.88 363

VDD-MVS		98.56 176	98.39 192	99.07 136	99.13 256	98.07 153	98.59 122	97.01 426	99.59 37	99.11 175	99.27 129	94.82 314	99.79 245	98.34 139	99.63 241	99.34 251

save fliter					99.11 258	97.97 164	96.53 371	99.02 306	98.24 194

APD-MVS		98.10 244	97.67 277	99.42 68	99.11 258	98.93 80	97.76 253	99.28 244	94.97 405	98.72 257	98.77 275	97.04 213	99.85 157	93.79 407	99.54 273	99.49 174
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 149	98.71 133	98.62 230	99.10 260	96.37 289	97.23 327	98.87 331	99.20 83	99.19 167	98.99 218	97.30 197	99.85 157	98.77 106	99.79 151	99.65 83

EI-MVSNet		98.40 202	98.51 168	98.04 313	99.10 260	94.73 359	97.20 332	98.87 331	98.97 125	99.06 182	99.02 201	96.00 274	99.80 232	98.58 118	99.82 128	99.60 100

CVMVSNet		96.25 368	97.21 308	93.38 468	99.10 260	80.56 496	97.20 332	98.19 393	96.94 321	99.00 197	99.02 201	89.50 396	99.80 232	96.36 320	99.59 255	99.78 47

EI-MVSNet-Vis-set		98.68 155	98.70 136	98.63 228	99.09 263	96.40 288	97.23 327	98.86 336	99.20 83	99.18 171	98.97 225	97.29 199	99.85 157	98.72 110	99.78 156	99.64 84

HPM-MVS++		98.10 244	97.64 282	99.48 57	99.09 263	99.13 61	97.52 291	98.75 356	97.46 276	96.90 405	97.83 386	96.01 273	99.84 175	95.82 349	99.35 318	99.46 195

DP-MVS Recon		97.33 314	96.92 326	98.57 241	99.09 263	97.99 160	96.79 354	99.35 205	93.18 438	97.71 354	98.07 370	95.00 309	99.31 446	93.97 400	99.13 356	98.42 417

MVS_111021_HR		98.25 229	98.08 240	98.75 205	99.09 263	97.46 211	95.97 404	99.27 247	97.60 257	97.99 334	98.25 354	98.15 120	99.38 437	96.87 268	99.57 264	99.42 213

BP-MVS1		97.40 307	96.97 322	98.71 214	99.07 267	96.81 265	98.34 163	97.18 421	98.58 167	98.17 313	98.61 314	84.01 440	99.94 42	98.97 90	99.78 156	99.37 237

9.14			97.78 268		99.07 267		97.53 290	99.32 219	95.53 390	98.54 286	98.70 294	97.58 172	99.76 268	94.32 392	99.46 296

PAPM_NR		96.82 348	96.32 359	98.30 284	99.07 267	96.69 273	97.48 297	98.76 353	95.81 381	96.61 421	96.47 433	94.12 335	99.17 459	90.82 460	97.78 434	99.06 327

TAMVS		98.24 230	98.05 243	98.80 189	99.07 267	97.18 240	97.88 233	98.81 345	96.66 340	99.17 173	99.21 149	94.81 316	99.77 262	96.96 258	99.88 94	99.44 204

CLD-MVS		97.49 298	97.16 310	98.48 262	99.07 267	97.03 251	94.71 452	99.21 262	94.46 416	98.06 327	97.16 419	97.57 173	99.48 418	94.46 384	99.78 156	98.95 349
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CS-MVS		99.13 67	99.10 78	99.24 107	99.06 272	99.15 53	99.36 22	99.88 14	99.36 64	98.21 312	98.46 335	98.68 57	99.93 54	99.03 86	99.85 107	98.64 396

thres100view900		94.19 416	93.67 421	95.75 435	99.06 272	91.35 443	98.03 204	94.24 469	98.33 184	97.40 379	94.98 463	79.84 456	99.62 364	83.05 481	98.08 425	96.29 476

thres600view7		94.45 411	93.83 418	96.29 419	99.06 272	91.53 438	97.99 218	94.24 469	98.34 183	97.44 377	95.01 461	79.84 456	99.67 334	84.33 479	98.23 414	97.66 457

plane_prior1					99.05 275

YYNet1		97.60 289	97.67 277	97.39 377	99.04 276	93.04 416	95.27 437	98.38 385	97.25 297	98.92 222	98.95 232	95.48 298	99.73 294	96.99 254	98.74 389	99.41 216

MDA-MVSNet_test_wron		97.60 289	97.66 280	97.41 376	99.04 276	93.09 412	95.27 437	98.42 382	97.26 296	98.88 231	98.95 232	95.43 299	99.73 294	97.02 250	98.72 391	99.41 216

MIMVSNet		96.62 355	96.25 363	97.71 342	99.04 276	94.66 362	99.16 54	96.92 432	97.23 303	97.87 343	99.10 181	86.11 420	99.65 354	91.65 444	99.21 344	98.82 368

usedtu_dtu_shiyan1		97.37 309	97.13 314	98.11 303	99.03 279	95.40 330	94.47 462	98.99 312	96.87 327	97.97 335	97.81 387	92.12 368	99.75 280	97.49 219	99.43 306	99.16 316

FE-MVSNET3		97.37 309	97.13 314	98.11 303	99.03 279	95.40 330	94.47 462	98.99 312	96.87 327	97.97 335	97.81 387	92.12 368	99.75 280	97.49 219	99.43 306	99.16 316

icg_test_0407_2		98.20 235	98.38 194	97.65 350	99.03 279	94.03 384	95.78 418	99.45 160	98.16 208	99.06 182	98.71 287	98.27 100	99.68 330	97.50 214	99.45 298	99.22 291

IMVS_0407		98.39 208	98.64 147	97.66 348	99.03 279	94.03 384	98.10 190	99.45 160	98.16 208	99.06 182	98.71 287	98.27 100	99.71 305	97.50 214	99.45 298	99.22 291

IMVS_0404		98.07 248	98.20 222	97.69 343	99.03 279	94.03 384	96.67 362	99.45 160	98.16 208	98.03 331	98.71 287	96.80 232	99.82 206	97.50 214	99.45 298	99.22 291

IMVS_0403		98.34 212	98.56 161	97.66 348	99.03 279	94.03 384	97.98 219	99.45 160	98.16 208	98.89 227	98.71 287	97.90 139	99.74 287	97.50 214	99.45 298	99.22 291

PatchMatch-RL		97.24 322	96.78 337	98.61 234	99.03 279	97.83 179	96.36 382	99.06 294	93.49 436	97.36 383	97.78 389	95.75 288	99.49 415	93.44 416	98.77 388	98.52 405

viewmambaseed2359dif		98.19 236	98.26 215	97.99 316	99.02 286	95.03 346	96.59 368	99.53 123	96.21 360	99.00 197	98.99 218	97.62 168	99.61 371	97.62 201	99.72 193	99.33 257

GDP-MVS		97.50 295	97.11 316	98.67 220	99.02 286	96.85 263	98.16 180	99.71 47	98.32 186	98.52 289	98.54 321	83.39 444	99.95 26	98.79 102	99.56 267	99.19 302

ZD-MVS					99.01 288	98.84 86		99.07 293	94.10 426	98.05 329	98.12 364	96.36 258	99.86 144	92.70 432	99.19 348

CDPH-MVS		97.26 319	96.66 346	99.07 136	99.00 289	98.15 140	96.03 402	99.01 309	91.21 462	97.79 350	97.85 385	96.89 224	99.69 320	92.75 430	99.38 314	99.39 226

diffmvs		98.22 231	98.24 219	98.17 299	99.00 289	95.44 328	96.38 381	99.58 94	97.79 241	98.53 287	98.50 330	96.76 236	99.74 287	97.95 172	99.64 234	99.34 251
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		98.40 202	98.19 226	99.03 146	99.00 289	97.65 198	96.85 352	98.94 316	98.57 169	98.89 227	98.50 330	95.60 292	99.85 157	97.54 210	99.85 107	99.59 107

plane_prior6					98.99 292	97.70 196						94.90 310

xiu_mvs_v1_base_debu		97.86 269	98.17 228	96.92 398	98.98 293	93.91 394	96.45 375	99.17 276	97.85 236	98.41 298	97.14 421	98.47 76	99.92 66	98.02 163	99.05 362	96.92 469

xiu_mvs_v1_base		97.86 269	98.17 228	96.92 398	98.98 293	93.91 394	96.45 375	99.17 276	97.85 236	98.41 298	97.14 421	98.47 76	99.92 66	98.02 163	99.05 362	96.92 469

xiu_mvs_v1_base_debi		97.86 269	98.17 228	96.92 398	98.98 293	93.91 394	96.45 375	99.17 276	97.85 236	98.41 298	97.14 421	98.47 76	99.92 66	98.02 163	99.05 362	96.92 469

MVP-Stereo		98.08 247	97.92 259	98.57 241	98.96 296	96.79 266	97.90 231	99.18 272	96.41 352	98.46 293	98.95 232	95.93 283	99.60 374	96.51 310	98.98 376	99.31 264
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 202	98.68 139	97.54 365	98.96 296	97.99 160	97.88 233	99.36 199	98.20 202	99.63 67	99.04 198	98.76 45	95.33 492	96.56 304	99.74 182	99.31 264
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
新几何1				98.91 169	98.94 298	97.76 190		98.76 353	87.58 479	96.75 413	98.10 366	94.80 317	99.78 256	92.73 431	99.00 371	99.20 296

USDC		97.41 306	97.40 295	97.44 374	98.94 298	93.67 404	95.17 441	99.53 123	94.03 428	98.97 206	99.10 181	95.29 301	99.34 442	95.84 348	99.73 185	99.30 268

tfpn200view9		94.03 420	93.44 423	95.78 434	98.93 300	91.44 441	97.60 281	94.29 467	97.94 228	97.10 389	94.31 470	79.67 458	99.62 364	83.05 481	98.08 425	96.29 476

testdata				98.09 305	98.93 300	95.40 330		98.80 347	90.08 470	97.45 376	98.37 344	95.26 302	99.70 312	93.58 412	98.95 379	99.17 310

thres400		94.14 418	93.44 423	96.24 422	98.93 300	91.44 441	97.60 281	94.29 467	97.94 228	97.10 389	94.31 470	79.67 458	99.62 364	83.05 481	98.08 425	97.66 457

TAPA-MVS	96.21 11	96.63 354	95.95 365	98.65 222	98.93 300	98.09 147	96.93 348	99.28 244	83.58 485	98.13 320	97.78 389	96.13 267	99.40 433	93.52 413	99.29 330	98.45 410
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 304	96.93 259	95.54 425	98.78 350	85.72 482	96.86 408	98.11 365	94.43 324			99.10 361	99.23 286

PVSNet_BlendedMVS		97.55 294	97.53 288	97.60 357	98.92 304	93.77 401	96.64 364	99.43 174	94.49 414	97.62 359	99.18 158	96.82 229	99.67 334	94.73 376	99.93 56	99.36 244

PVSNet_Blended		96.88 344	96.68 343	97.47 372	98.92 304	93.77 401	94.71 452	99.43 174	90.98 464	97.62 359	97.36 415	96.82 229	99.67 334	94.73 376	99.56 267	98.98 342

MSDG		97.71 282	97.52 289	98.28 286	98.91 307	96.82 264	94.42 464	99.37 195	97.65 250	98.37 303	98.29 353	97.40 191	99.33 444	94.09 398	99.22 341	98.68 394

Anonymous202405211		97.90 262	97.50 290	99.08 134	98.90 308	98.25 130	98.53 129	96.16 444	98.87 138	99.11 175	98.86 252	90.40 388	99.78 256	97.36 225	99.31 325	99.19 302

原ACMM1				98.35 279	98.90 308	96.25 293		98.83 344	92.48 448	96.07 438	98.10 366	95.39 300	99.71 305	92.61 434	98.99 373	99.08 324

GBi-Net		98.65 160	98.47 179	99.17 116	98.90 308	98.24 131	99.20 48	99.44 168	98.59 164	98.95 212	99.55 57	94.14 332	99.86 144	97.77 186	99.69 212	99.41 216

test1		98.65 160	98.47 179	99.17 116	98.90 308	98.24 131	99.20 48	99.44 168	98.59 164	98.95 212	99.55 57	94.14 332	99.86 144	97.77 186	99.69 212	99.41 216

FMVSNet2		98.49 192	98.40 189	98.75 205	98.90 308	97.14 245	98.61 120	99.13 285	98.59 164	99.19 167	99.28 127	94.14 332	99.82 206	97.97 170	99.80 145	99.29 270

OMC-MVS		97.88 266	97.49 291	99.04 145	98.89 313	98.63 100	96.94 346	99.25 253	95.02 403	98.53 287	98.51 326	97.27 200	99.47 421	93.50 415	99.51 283	99.01 336

VortexMVS		97.98 259	98.31 207	97.02 392	98.88 314	91.45 440	98.03 204	99.47 151	98.65 155	99.55 77	99.47 79	91.49 377	99.81 223	99.32 61	99.91 78	99.80 42

MVSFormer		98.26 226	98.43 185	97.77 332	98.88 314	93.89 397	99.39 20	99.56 110	99.11 99	98.16 316	98.13 362	93.81 340	99.97 7	99.26 66	99.57 264	99.43 208

lupinMVS		97.06 334	96.86 330	97.65 350	98.88 314	93.89 397	95.48 429	97.97 399	93.53 434	98.16 316	97.58 401	93.81 340	99.91 75	96.77 276	99.57 264	99.17 310

dmvs_re		95.98 378	95.39 387	97.74 338	98.86 317	97.45 212	98.37 159	95.69 456	97.95 226	96.56 422	95.95 442	90.70 385	97.68 486	88.32 469	96.13 467	98.11 432

DELS-MVS		98.27 224	98.20 222	98.48 262	98.86 317	96.70 272	95.60 424	99.20 264	97.73 244	98.45 294	98.71 287	97.50 183	99.82 206	98.21 147	99.59 255	98.93 354
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		97.89 264	97.98 250	97.60 357	98.86 317	94.35 370	96.21 391	99.44 168	97.45 278	99.06 182	98.88 249	97.99 133	99.28 452	94.38 391	99.58 260	99.18 306

LCM-MVSNet-Re		98.64 162	98.48 177	99.11 127	98.85 320	98.51 113	98.49 140	99.83 25	98.37 180	99.69 56	99.46 81	98.21 111	99.92 66	94.13 397	99.30 328	98.91 358

pmmvs4		97.58 292	97.28 303	98.51 257	98.84 321	96.93 259	95.40 433	98.52 377	93.60 433	98.61 272	98.65 305	95.10 306	99.60 374	96.97 257	99.79 151	98.99 341

NP-MVS					98.84 321	97.39 216					96.84 424

sss		97.21 324	96.93 324	98.06 310	98.83 323	95.22 339	96.75 358	98.48 379	94.49 414	97.27 385	97.90 382	92.77 358	99.80 232	96.57 300	99.32 323	99.16 316

PVSNet	93.40 17	95.67 388	95.70 371	95.57 439	98.83 323	88.57 466	92.50 483	97.72 404	92.69 446	96.49 430	96.44 434	93.72 343	99.43 429	93.61 410	99.28 331	98.71 387

MVE	83.40 22	92.50 443	91.92 445	94.25 455	98.83 323	91.64 437	92.71 482	83.52 495	95.92 376	86.46 493	95.46 455	95.20 303	95.40 491	80.51 486	98.64 400	95.73 484
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 424	93.91 416	93.39 467	98.82 326	81.72 494	97.76 253	95.28 458	98.60 163	96.54 423	96.66 428	65.85 488	99.62 364	96.65 293	98.99 373	98.82 368

ambc				98.24 291	98.82 326	95.97 304	98.62 118	99.00 311		99.27 145	99.21 149	96.99 218	99.50 412	96.55 307	99.50 291	99.26 280

旧先验1					98.82 326	97.45 212		98.76 353			98.34 348	95.50 297			99.01 370	99.23 286

test_vis1_rt		97.75 279	97.72 274	97.83 327	98.81 329	96.35 290	97.30 321	99.69 54	94.61 412	97.87 343	98.05 371	96.26 263	98.32 480	98.74 108	98.18 417	98.82 368

WTY-MVS		96.67 352	96.27 362	97.87 325	98.81 329	94.61 364	96.77 356	97.92 401	94.94 406	97.12 388	97.74 392	91.11 381	99.82 206	93.89 403	98.15 421	99.18 306

3Dnovator+	97.89 3	98.69 149	98.51 168	99.24 107	98.81 329	98.40 118	99.02 70	99.19 268	98.99 122	98.07 326	99.28 127	97.11 211	99.84 175	96.84 271	99.32 323	99.47 193

QAPM		97.31 315	96.81 336	98.82 184	98.80 332	97.49 206	99.06 65	99.19 268	90.22 468	97.69 356	99.16 164	96.91 223	99.90 82	90.89 459	99.41 309	99.07 326

VNet		98.42 198	98.30 208	98.79 193	98.79 333	97.29 227	98.23 171	98.66 363	99.31 69	98.85 236	98.80 269	94.80 317	99.78 256	98.13 152	99.13 356	99.31 264

DPM-MVS		96.32 364	95.59 378	98.51 257	98.76 334	97.21 236	94.54 461	98.26 388	91.94 453	96.37 431	97.25 417	93.06 352	99.43 429	91.42 449	98.74 389	98.89 360

3Dnovator	98.27 2	98.81 125	98.73 126	99.05 143	98.76 334	97.81 187	99.25 43	99.30 232	98.57 169	98.55 284	99.33 116	97.95 136	99.90 82	97.16 238	99.67 223	99.44 204

PLC	94.65 16	96.51 357	95.73 370	98.85 176	98.75 336	97.91 172	96.42 379	99.06 294	90.94 465	95.59 445	97.38 413	94.41 325	99.59 378	90.93 457	98.04 430	99.05 328
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 346	96.75 339	97.08 389	98.74 337	93.33 410	96.71 360	98.26 388	96.72 337	98.44 295	97.37 414	95.20 303	99.47 421	91.89 439	97.43 444	98.44 413

hse-mvs2		97.46 300	97.07 317	98.64 224	98.73 338	97.33 219	97.45 303	97.64 411	99.11 99	98.58 278	97.98 376	88.65 403	99.79 245	98.11 153	97.39 446	98.81 373

CDS-MVSNet		97.69 283	97.35 300	98.69 217	98.73 338	97.02 252	96.92 350	98.75 356	95.89 377	98.59 276	98.67 300	92.08 371	99.74 287	96.72 282	99.81 134	99.32 260
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 366	95.83 367	97.64 353	98.72 340	94.30 371	98.87 89	98.77 351	97.80 239	96.53 424	98.02 373	97.34 195	99.47 421	76.93 490	99.48 294	99.16 316

EIA-MVS		98.00 255	97.74 271	98.80 189	98.72 340	98.09 147	98.05 200	99.60 84	97.39 283	96.63 419	95.55 450	97.68 160	99.80 232	96.73 281	99.27 332	98.52 405

LFMVS		97.20 325	96.72 340	98.64 224	98.72 340	96.95 257	98.93 82	94.14 471	99.74 13	98.78 248	99.01 212	84.45 435	99.73 294	97.44 221	99.27 332	99.25 281

new_pmnet		96.99 341	96.76 338	97.67 346	98.72 340	94.89 351	95.95 408	98.20 391	92.62 447	98.55 284	98.54 321	94.88 313	99.52 406	93.96 401	99.44 305	98.59 402

Fast-Effi-MVS+		97.67 285	97.38 297	98.57 241	98.71 344	97.43 214	97.23 327	99.45 160	94.82 409	96.13 435	96.51 430	98.52 74	99.91 75	96.19 329	98.83 385	98.37 422

TEST9					98.71 344	98.08 151	95.96 406	99.03 303	91.40 459	95.85 442	97.53 403	96.52 249	99.76 268

train_agg		97.10 331	96.45 356	99.07 136	98.71 344	98.08 151	95.96 406	99.03 303	91.64 454	95.85 442	97.53 403	96.47 251	99.76 268	93.67 409	99.16 351	99.36 244

TSAR-MVS + GP.		98.18 238	97.98 250	98.77 201	98.71 344	97.88 174	96.32 385	98.66 363	96.33 354	99.23 161	98.51 326	97.48 187	99.40 433	97.16 238	99.46 296	99.02 335

FA-MVS(test-final)		96.99 341	96.82 334	97.50 369	98.70 348	94.78 356	99.34 23	96.99 427	95.07 402	98.48 292	99.33 116	88.41 406	99.65 354	96.13 335	98.92 382	98.07 435

AUN-MVS		96.24 370	95.45 383	98.60 236	98.70 348	97.22 234	97.38 310	97.65 409	95.95 375	95.53 452	97.96 380	82.11 452	99.79 245	96.31 322	97.44 443	98.80 378

our_test_3		97.39 308	97.73 273	96.34 417	98.70 348	89.78 462	94.61 458	98.97 315	96.50 345	99.04 192	98.85 255	95.98 279	99.84 175	97.26 232	99.67 223	99.41 216

ppachtmachnet_test		97.50 295	97.74 271	96.78 407	98.70 348	91.23 449	94.55 460	99.05 298	96.36 353	99.21 165	98.79 271	96.39 254	99.78 256	96.74 279	99.82 128	99.34 251

PCF-MVS	92.86 18	94.36 412	93.00 430	98.42 269	98.70 348	97.56 203	93.16 481	99.11 288	79.59 489	97.55 366	97.43 410	92.19 366	99.73 294	79.85 487	99.45 298	97.97 441
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 261	98.02 246	97.58 359	98.69 353	94.10 380	98.13 183	98.90 325	97.95 226	97.32 384	99.58 47	95.95 282	98.75 475	96.41 316	99.22 341	99.87 22

ETV-MVS		98.03 251	97.86 265	98.56 246	98.69 353	98.07 153	97.51 293	99.50 132	98.10 216	97.50 371	95.51 451	98.41 83	99.88 116	96.27 325	99.24 337	97.71 456

test_prior				98.95 161	98.69 353	97.95 168		99.03 303					99.59 378			99.30 268

mvsmamba		97.57 293	97.26 304	98.51 257	98.69 353	96.73 271	98.74 99	97.25 420	97.03 317	97.88 342	99.23 147	90.95 382	99.87 135	96.61 296	99.00 371	98.91 358

agg_prior					98.68 357	97.99 160		99.01 309		95.59 445			99.77 262

test_8					98.67 358	98.01 159	95.91 412	99.02 306	91.64 454	95.79 444	97.50 406	96.47 251	99.76 268

HQP-NCC					98.67 358		96.29 387		96.05 368	95.55 448

ACMP_Plane					98.67 358		96.29 387		96.05 368	95.55 448

CNVR-MVS		98.17 240	97.87 264	99.07 136	98.67 358	98.24 131	97.01 342	98.93 319	97.25 297	97.62 359	98.34 348	97.27 200	99.57 387	96.42 315	99.33 321	99.39 226

HQP-MVS		97.00 340	96.49 355	98.55 248	98.67 358	96.79 266	96.29 387	99.04 301	96.05 368	95.55 448	96.84 424	93.84 338	99.54 400	92.82 427	99.26 335	99.32 260

MM		98.22 231	97.99 249	98.91 169	98.66 363	96.97 254	97.89 232	94.44 465	99.54 41	98.95 212	99.14 171	93.50 344	99.92 66	99.80 17	99.96 28	99.85 30

test_fmvs1		97.72 281	97.94 256	97.07 391	98.66 363	92.39 427	97.68 264	99.81 31	95.20 401	99.54 79	99.44 86	91.56 376	99.41 432	99.78 21	99.77 162	99.40 225

balanced_conf03		98.63 164	98.72 128	98.38 274	98.66 363	96.68 274	98.90 84	99.42 180	98.99 122	98.97 206	99.19 154	95.81 287	99.85 157	98.77 106	99.77 162	98.60 399

thres200		93.72 426	93.14 428	95.46 443	98.66 363	91.29 445	96.61 366	94.63 464	97.39 283	96.83 409	93.71 473	79.88 455	99.56 390	82.40 484	98.13 422	95.54 485

wuyk23d		96.06 373	97.62 284	91.38 472	98.65 367	98.57 107	98.85 93	96.95 430	96.86 330	99.90 14	99.16 164	99.18 19	98.40 479	89.23 467	99.77 162	77.18 492

NCCC		97.86 269	97.47 294	99.05 143	98.61 368	98.07 153	96.98 344	98.90 325	97.63 251	97.04 395	97.93 381	95.99 278	99.66 347	95.31 364	98.82 387	99.43 208

DeepC-MVS_fast	96.85 6	98.30 220	98.15 232	98.75 205	98.61 368	97.23 231	97.76 253	99.09 291	97.31 291	98.75 254	98.66 303	97.56 174	99.64 358	96.10 336	99.55 271	99.39 226
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 428	92.09 439	97.75 336	98.60 370	94.40 368	97.32 318	95.26 459	97.56 261	96.79 412	95.50 452	53.57 497	99.77 262	95.26 365	98.97 377	99.08 324

thisisatest0515		94.12 419	93.16 427	96.97 396	98.60 370	92.90 417	93.77 477	90.61 484	94.10 426	96.91 402	95.87 445	74.99 470	99.80 232	94.52 382	99.12 359	98.20 428

GA-MVS		95.86 382	95.32 392	97.49 370	98.60 370	94.15 377	93.83 476	97.93 400	95.49 391	96.68 417	97.42 411	83.21 445	99.30 448	96.22 327	98.55 406	99.01 336

dmvs_testset		92.94 438	92.21 438	95.13 447	98.59 373	90.99 452	97.65 270	92.09 480	96.95 320	94.00 472	93.55 474	92.34 364	96.97 489	72.20 491	92.52 486	97.43 464

OPU-MVS				98.82 184	98.59 373	98.30 127	98.10 190				98.52 325	98.18 114	98.75 475	94.62 379	99.48 294	99.41 216

MSLP-MVS++		98.02 252	98.14 234	97.64 353	98.58 375	95.19 340	97.48 297	99.23 260	97.47 271	97.90 340	98.62 312	97.04 213	98.81 473	97.55 208	99.41 309	98.94 353

test12				98.93 165	98.58 375	97.83 179		98.66 363		96.53 424		95.51 296	99.69 320		99.13 356	99.27 274

CL-MVSNet_self_test		97.44 303	97.22 307	98.08 308	98.57 377	95.78 312	94.30 467	98.79 348	96.58 343	98.60 274	98.19 360	94.74 320	99.64 358	96.41 316	98.84 384	98.82 368

PS-MVSNAJ		97.08 333	97.39 296	96.16 428	98.56 378	92.46 425	95.24 439	98.85 339	97.25 297	97.49 372	95.99 441	98.07 124	99.90 82	96.37 318	98.67 399	96.12 481

CNLPA		97.17 328	96.71 341	98.55 248	98.56 378	98.05 157	96.33 384	98.93 319	96.91 325	97.06 393	97.39 412	94.38 327	99.45 426	91.66 443	99.18 350	98.14 431

xiu_mvs_v2_base		97.16 329	97.49 291	96.17 426	98.54 380	92.46 425	95.45 430	98.84 340	97.25 297	97.48 373	96.49 431	98.31 94	99.90 82	96.34 321	98.68 398	96.15 480

alignmvs		97.35 312	96.88 329	98.78 196	98.54 380	98.09 147	97.71 260	97.69 406	99.20 83	97.59 362	95.90 444	88.12 408	99.55 394	98.18 149	98.96 378	98.70 390

FE-MVS		95.66 389	94.95 402	97.77 332	98.53 382	95.28 336	99.40 19	96.09 447	93.11 440	97.96 337	99.26 135	79.10 462	99.77 262	92.40 436	98.71 393	98.27 426

Effi-MVS+		98.02 252	97.82 267	98.62 230	98.53 382	97.19 238	97.33 317	99.68 60	97.30 292	96.68 417	97.46 409	98.56 72	99.80 232	96.63 294	98.20 416	98.86 365

baseline1		95.96 380	95.44 384	97.52 367	98.51 384	93.99 391	98.39 157	96.09 447	98.21 198	98.40 302	97.76 391	86.88 412	99.63 361	95.42 362	89.27 489	98.95 349

MVS_Test		98.18 238	98.36 197	97.67 346	98.48 385	94.73 359	98.18 176	99.02 306	97.69 247	98.04 330	99.11 178	97.22 204	99.56 390	98.57 120	98.90 383	98.71 387

MGCFI-Net		98.34 212	98.28 211	98.51 257	98.47 386	97.59 202	98.96 78	99.48 142	99.18 91	97.40 379	95.50 452	98.66 58	99.50 412	98.18 149	98.71 393	98.44 413

BH-RMVSNet		96.83 346	96.58 351	97.58 359	98.47 386	94.05 381	96.67 362	97.36 415	96.70 339	97.87 343	97.98 376	95.14 305	99.44 428	90.47 462	98.58 405	99.25 281

sasdasda		98.34 212	98.26 215	98.58 238	98.46 388	97.82 184	98.96 78	99.46 156	99.19 88	97.46 374	95.46 455	98.59 66	99.46 424	98.08 156	98.71 393	98.46 407

canonicalmvs		98.34 212	98.26 215	98.58 238	98.46 388	97.82 184	98.96 78	99.46 156	99.19 88	97.46 374	95.46 455	98.59 66	99.46 424	98.08 156	98.71 393	98.46 407

MVS-HIRNet		94.32 413	95.62 374	90.42 473	98.46 388	75.36 497	96.29 387	89.13 488	95.25 398	95.38 454	99.75 16	92.88 355	99.19 458	94.07 399	99.39 311	96.72 474

PHI-MVS		98.29 223	97.95 254	99.34 84	98.44 391	99.16 49	98.12 187	99.38 191	96.01 372	98.06 327	98.43 338	97.80 153	99.67 334	95.69 354	99.58 260	99.20 296

DVP-MVS++		98.90 105	98.70 136	99.51 49	98.43 392	99.15 53	99.43 15	99.32 219	98.17 205	99.26 149	99.02 201	98.18 114	99.88 116	97.07 247	99.45 298	99.49 174

MSC_two_6792asdad				99.32 92	98.43 392	98.37 122		98.86 336					99.89 98	97.14 241	99.60 251	99.71 63

No_MVS				99.32 92	98.43 392	98.37 122		98.86 336					99.89 98	97.14 241	99.60 251	99.71 63

Fast-Effi-MVS+-dtu		98.27 224	98.09 237	98.81 186	98.43 392	98.11 144	97.61 280	99.50 132	98.64 156	97.39 381	97.52 405	98.12 122	99.95 26	96.90 265	98.71 393	98.38 420

OpenMVS_ROB	95.38 14	95.84 384	95.18 397	97.81 329	98.41 396	97.15 244	97.37 314	98.62 367	83.86 484	98.65 265	98.37 344	94.29 330	99.68 330	88.41 468	98.62 403	96.60 475

DeepPCF-MVS	96.93 5	98.32 217	98.01 247	99.23 109	98.39 397	98.97 74	95.03 445	99.18 272	96.88 326	99.33 131	98.78 273	98.16 118	99.28 452	96.74 279	99.62 244	99.44 204

Patchmatch-test		96.55 356	96.34 358	97.17 386	98.35 398	93.06 413	98.40 156	97.79 402	97.33 288	98.41 298	98.67 300	83.68 443	99.69 320	95.16 367	99.31 325	98.77 381

AdaColmap		97.14 330	96.71 341	98.46 264	98.34 399	97.80 188	96.95 345	98.93 319	95.58 388	96.92 400	97.66 396	95.87 285	99.53 402	90.97 456	99.14 354	98.04 436

OpenMVS	96.65 7	97.09 332	96.68 343	98.32 281	98.32 400	97.16 243	98.86 92	99.37 195	89.48 472	96.29 433	99.15 168	96.56 247	99.90 82	92.90 424	99.20 345	97.89 444

MG-MVS		96.77 349	96.61 348	97.26 382	98.31 401	93.06 413	95.93 409	98.12 396	96.45 351	97.92 338	98.73 284	93.77 342	99.39 435	91.19 454	99.04 365	99.33 257

test_yl		96.69 350	96.29 360	97.90 321	98.28 402	95.24 337	97.29 322	97.36 415	98.21 198	98.17 313	97.86 383	86.27 416	99.55 394	94.87 373	98.32 410	98.89 360

DCV-MVSNet		96.69 350	96.29 360	97.90 321	98.28 402	95.24 337	97.29 322	97.36 415	98.21 198	98.17 313	97.86 383	86.27 416	99.55 394	94.87 373	98.32 410	98.89 360

CHOSEN 280x420		95.51 394	95.47 381	95.65 438	98.25 404	88.27 469	93.25 480	98.88 329	93.53 434	94.65 463	97.15 420	86.17 418	99.93 54	97.41 223	99.93 56	98.73 386

SCA		96.41 363	96.66 346	95.67 436	98.24 405	88.35 468	95.85 415	96.88 433	96.11 366	97.67 357	98.67 300	93.10 350	99.85 157	94.16 393	99.22 341	98.81 373

DeepMVS_CX				93.44 466	98.24 405	94.21 374		94.34 466	64.28 492	91.34 486	94.87 467	89.45 397	92.77 493	77.54 489	93.14 485	93.35 488

MS-PatchMatch		97.68 284	97.75 270	97.45 373	98.23 407	93.78 400	97.29 322	98.84 340	96.10 367	98.64 266	98.65 305	96.04 271	99.36 438	96.84 271	99.14 354	99.20 296

BH-w/o		95.13 402	94.89 404	95.86 431	98.20 408	91.31 444	95.65 422	97.37 414	93.64 432	96.52 426	95.70 448	93.04 353	99.02 464	88.10 470	95.82 475	97.24 467

mvs_anonymous		97.83 277	98.16 231	96.87 401	98.18 409	91.89 434	97.31 320	98.90 325	97.37 285	98.83 239	99.46 81	96.28 262	99.79 245	98.90 95	98.16 420	98.95 349

miper_lstm_enhance		97.18 327	97.16 310	97.25 383	98.16 410	92.85 418	95.15 443	99.31 224	97.25 297	98.74 256	98.78 273	90.07 389	99.78 256	97.19 236	99.80 145	99.11 323

RRT-MVS		97.88 266	97.98 250	97.61 356	98.15 411	93.77 401	98.97 77	99.64 71	99.16 93	98.69 259	99.42 90	91.60 374	99.89 98	97.63 200	98.52 407	99.16 316

ET-MVSNet_ETH3D		94.30 415	93.21 426	97.58 359	98.14 412	94.47 367	94.78 451	93.24 476	94.72 410	89.56 488	95.87 445	78.57 465	99.81 223	96.91 260	97.11 455	98.46 407

ADS-MVSNet2		95.43 397	94.98 400	96.76 408	98.14 412	91.74 435	97.92 228	97.76 403	90.23 466	96.51 427	98.91 239	85.61 426	99.85 157	92.88 425	96.90 456	98.69 391

ADS-MVSNet		95.24 400	94.93 403	96.18 425	98.14 412	90.10 461	97.92 228	97.32 418	90.23 466	96.51 427	98.91 239	85.61 426	99.74 287	92.88 425	96.90 456	98.69 391

c3_l		97.36 311	97.37 298	97.31 378	98.09 415	93.25 411	95.01 446	99.16 279	97.05 314	98.77 251	98.72 286	92.88 355	99.64 358	96.93 259	99.76 177	99.05 328

FMVSNet3		97.50 295	97.24 306	98.29 285	98.08 416	95.83 309	97.86 237	98.91 324	97.89 233	98.95 212	98.95 232	87.06 411	99.81 223	97.77 186	99.69 212	99.23 286

PAPM		91.88 453	90.34 455	96.51 412	98.06 417	92.56 423	92.44 484	97.17 422	86.35 480	90.38 487	96.01 440	86.61 414	99.21 457	70.65 493	95.43 477	97.75 453

Effi-MVS+-dtu		98.26 226	97.90 262	99.35 81	98.02 418	99.49 6	98.02 207	99.16 279	98.29 191	97.64 358	97.99 375	96.44 253	99.95 26	96.66 292	98.93 381	98.60 399

eth_miper_zixun_eth		97.23 323	97.25 305	97.17 386	98.00 419	92.77 420	94.71 452	99.18 272	97.27 295	98.56 282	98.74 283	91.89 372	99.69 320	97.06 249	99.81 134	99.05 328

HY-MVS	95.94 13	95.90 381	95.35 389	97.55 364	97.95 420	94.79 355	98.81 98	96.94 431	92.28 451	95.17 456	98.57 319	89.90 391	99.75 280	91.20 453	97.33 451	98.10 433

UGNet		98.53 185	98.45 182	98.79 193	97.94 421	96.96 256	99.08 61	98.54 375	99.10 106	96.82 410	99.47 79	96.55 248	99.84 175	98.56 123	99.94 50	99.55 136
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
MAR-MVS		96.47 361	95.70 371	98.79 193	97.92 422	99.12 63	98.28 165	98.60 368	92.16 452	95.54 451	96.17 438	94.77 319	99.52 406	89.62 465	98.23 414	97.72 455
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		96.86 345	96.55 352	97.79 330	97.91 423	94.21 374	97.56 286	98.87 331	97.49 270	99.06 182	99.05 196	80.72 453	99.80 232	98.44 129	99.82 128	99.37 237

API-MVS		97.04 336	96.91 328	97.42 375	97.88 424	98.23 135	98.18 176	98.50 378	97.57 259	97.39 381	96.75 426	96.77 234	99.15 461	90.16 463	99.02 369	94.88 486

myMVS_eth3d28		92.92 439	92.31 435	94.77 450	97.84 425	87.59 473	96.19 393	96.11 446	97.08 313	94.27 466	93.49 476	66.07 487	98.78 474	91.78 441	97.93 433	97.92 443

miper_ehance_all_eth		97.06 334	97.03 319	97.16 388	97.83 426	93.06 413	94.66 455	99.09 291	95.99 373	98.69 259	98.45 336	92.73 360	99.61 371	96.79 273	99.03 366	98.82 368

cl____		97.02 337	96.83 333	97.58 359	97.82 427	94.04 383	94.66 455	99.16 279	97.04 315	98.63 267	98.71 287	88.68 402	99.69 320	97.00 252	99.81 134	99.00 340

DIV-MVS_self_test		97.02 337	96.84 332	97.58 359	97.82 427	94.03 384	94.66 455	99.16 279	97.04 315	98.63 267	98.71 287	88.69 400	99.69 320	97.00 252	99.81 134	99.01 336

CANet		97.87 268	97.76 269	98.19 298	97.75 429	95.51 320	96.76 357	99.05 298	97.74 243	96.93 399	98.21 358	95.59 293	99.89 98	97.86 181	99.93 56	99.19 302

UBG		93.25 433	92.32 434	96.04 430	97.72 430	90.16 460	95.92 411	95.91 451	96.03 371	93.95 474	93.04 479	69.60 477	99.52 406	90.72 461	97.98 431	98.45 410

mvsany_test1		97.60 289	97.54 287	97.77 332	97.72 430	95.35 333	95.36 434	97.13 424	94.13 425	99.71 50	99.33 116	97.93 137	99.30 448	97.60 204	98.94 380	98.67 395

PVSNet_0	89.98 21	91.15 454	90.30 456	93.70 463	97.72 430	84.34 487	90.24 487	97.42 413	90.20 469	93.79 475	93.09 478	90.90 384	98.89 472	86.57 476	72.76 493	97.87 446

CR-MVSNet		96.28 366	95.95 365	97.28 380	97.71 433	94.22 372	98.11 188	98.92 322	92.31 450	96.91 402	99.37 104	85.44 429	99.81 223	97.39 224	97.36 449	97.81 449

RPMNet		97.02 337	96.93 324	97.30 379	97.71 433	94.22 372	98.11 188	99.30 232	99.37 61	96.91 402	99.34 113	86.72 413	99.87 135	97.53 211	97.36 449	97.81 449

ETVMVS		92.60 442	91.08 451	97.18 384	97.70 435	93.65 406	96.54 369	95.70 454	96.51 344	94.68 462	92.39 483	61.80 494	99.50 412	86.97 473	97.41 445	98.40 418

pmmvs3		95.03 404	94.40 411	96.93 397	97.70 435	92.53 424	95.08 444	97.71 405	88.57 476	97.71 354	98.08 369	79.39 460	99.82 206	96.19 329	99.11 360	98.43 415

baseline2		93.73 425	92.83 431	96.42 415	97.70 435	91.28 446	96.84 353	89.77 487	93.96 430	92.44 482	95.93 443	79.14 461	99.77 262	92.94 423	96.76 460	98.21 427

WBMVS		95.18 401	94.78 405	96.37 416	97.68 438	89.74 463	95.80 417	98.73 359	97.54 265	98.30 304	98.44 337	70.06 475	99.82 206	96.62 295	99.87 98	99.54 142

tpm		94.67 409	94.34 413	95.66 437	97.68 438	88.42 467	97.88 233	94.90 461	94.46 416	96.03 441	98.56 320	78.66 463	99.79 245	95.88 342	95.01 479	98.78 380

CANet_DTU		97.26 319	97.06 318	97.84 326	97.57 440	94.65 363	96.19 393	98.79 348	97.23 303	95.14 457	98.24 355	93.22 347	99.84 175	97.34 226	99.84 112	99.04 332

testing11		93.08 436	92.02 441	96.26 421	97.56 441	90.83 455	96.32 385	95.70 454	96.47 348	92.66 481	93.73 472	64.36 491	99.59 378	93.77 408	97.57 438	98.37 422

tpm2		93.09 435	92.58 433	94.62 452	97.56 441	86.53 476	97.66 268	95.79 453	86.15 481	94.07 471	98.23 357	75.95 468	99.53 402	90.91 458	96.86 459	97.81 449

testing91		93.32 431	92.27 436	96.47 414	97.54 443	91.25 447	96.17 397	96.76 435	97.18 307	93.65 477	93.50 475	65.11 490	99.63 361	93.04 422	97.45 442	98.53 404

TR-MVS		95.55 392	95.12 398	96.86 404	97.54 443	93.94 392	96.49 374	96.53 440	94.36 421	97.03 397	96.61 429	94.26 331	99.16 460	86.91 475	96.31 464	97.47 463

testing99		93.04 437	91.98 444	96.23 423	97.53 445	90.70 457	96.35 383	95.94 450	96.87 327	93.41 478	93.43 477	63.84 492	99.59 378	93.24 420	97.19 452	98.40 418

1314		95.74 386	95.60 376	96.17 426	97.53 445	92.75 421	98.07 197	98.31 387	91.22 461	94.25 467	96.68 427	95.53 294	99.03 463	91.64 445	97.18 453	96.74 473

CostFormer		93.97 421	93.78 419	94.51 453	97.53 445	85.83 479	97.98 219	95.96 449	89.29 474	94.99 459	98.63 310	78.63 464	99.62 364	94.54 381	96.50 461	98.09 434

FMVSNet5		96.01 375	95.20 396	98.41 270	97.53 445	96.10 295	98.74 99	99.50 132	97.22 306	98.03 331	99.04 198	69.80 476	99.88 116	97.27 231	99.71 202	99.25 281

PMMVS		96.51 357	95.98 364	98.09 305	97.53 445	95.84 308	94.92 448	98.84 340	91.58 456	96.05 440	95.58 449	95.68 290	99.66 347	95.59 358	98.09 424	98.76 383

reproduce_monomvs		95.00 406	95.25 393	94.22 456	97.51 450	83.34 488	97.86 237	98.44 380	98.51 174	99.29 141	99.30 123	67.68 481	99.56 390	98.89 97	99.81 134	99.77 50

PAPR		95.29 398	94.47 409	97.75 336	97.50 451	95.14 342	94.89 449	98.71 361	91.39 460	95.35 455	95.48 454	94.57 322	99.14 462	84.95 478	97.37 447	98.97 346

testing222		91.96 451	90.37 454	96.72 409	97.47 452	92.59 422	96.11 399	94.76 462	96.83 331	92.90 480	92.87 480	57.92 495	99.55 394	86.93 474	97.52 439	98.00 440

PatchT		96.65 353	96.35 357	97.54 365	97.40 453	95.32 335	97.98 219	96.64 437	99.33 66	96.89 406	99.42 90	84.32 437	99.81 223	97.69 197	97.49 440	97.48 462

tpm cat1		93.29 432	93.13 429	93.75 462	97.39 454	84.74 482	97.39 308	97.65 409	83.39 486	94.16 468	98.41 339	82.86 448	99.39 435	91.56 447	95.35 478	97.14 468

PatchmatchNet		95.58 391	95.67 373	95.30 446	97.34 455	87.32 474	97.65 270	96.65 436	95.30 397	97.07 392	98.69 296	84.77 432	99.75 280	94.97 371	98.64 400	98.83 367
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmtry		97.35 312	96.97 322	98.50 261	97.31 456	96.47 286	98.18 176	98.92 322	98.95 129	98.78 248	99.37 104	85.44 429	99.85 157	95.96 340	99.83 123	99.17 310

LS3D		98.63 164	98.38 194	99.36 75	97.25 457	99.38 13	99.12 60	99.32 219	99.21 81	98.44 295	98.88 249	97.31 196	99.80 232	96.58 298	99.34 320	98.92 355

IB-MVS	91.63 19	92.24 448	90.90 452	96.27 420	97.22 458	91.24 448	94.36 466	93.33 475	92.37 449	92.24 484	94.58 469	66.20 486	99.89 98	93.16 421	94.63 481	97.66 457
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		92.38 445	91.76 448	94.21 457	97.16 459	84.65 483	95.42 432	88.45 489	95.96 374	96.17 434	95.84 447	66.36 484	99.71 305	91.87 440	98.64 400	98.28 425

tpmrst		95.07 403	95.46 382	93.91 460	97.11 460	84.36 486	97.62 275	96.96 429	94.98 404	96.35 432	98.80 269	85.46 428	99.59 378	95.60 357	96.23 465	97.79 452

Syy-MVS		96.04 374	95.56 380	97.49 370	97.10 461	94.48 366	96.18 395	96.58 438	95.65 385	94.77 460	92.29 485	91.27 380	99.36 438	98.17 151	98.05 428	98.63 397

myMVS_eth3d		91.92 452	90.45 453	96.30 418	97.10 461	90.90 453	96.18 395	96.58 438	95.65 385	94.77 460	92.29 485	53.88 496	99.36 438	89.59 466	98.05 428	98.63 397

blended_shiyan6		95.99 377	95.33 390	97.95 318	97.06 463	94.89 351	95.34 435	98.58 370	96.17 361	97.06 393	92.41 482	87.64 409	99.76 268	97.64 199	96.09 468	99.19 302

MDTV_nov1_ep13			95.22 395		97.06 463	83.20 489	97.74 257	96.16 444	94.37 420	96.99 398	98.83 262	83.95 441	99.53 402	93.90 402	97.95 432

blended_shiyan8		95.98 378	95.33 390	97.94 319	97.05 465	94.87 353	95.34 435	98.59 369	96.17 361	97.09 391	92.39 483	87.62 410	99.76 268	97.65 198	96.05 474	99.20 296

MVS		93.19 434	92.09 439	96.50 413	96.91 466	94.03 384	98.07 197	98.06 398	68.01 491	94.56 465	96.48 432	95.96 281	99.30 448	83.84 480	96.89 458	96.17 478

E-PMN		94.17 417	94.37 412	93.58 464	96.86 467	85.71 480	90.11 489	97.07 425	98.17 205	97.82 349	97.19 418	84.62 434	98.94 468	89.77 464	97.68 437	96.09 482

JIA-IIPM		95.52 393	95.03 399	97.00 393	96.85 468	94.03 384	96.93 348	95.82 452	99.20 83	94.63 464	99.71 22	83.09 446	99.60 374	94.42 387	94.64 480	97.36 466

EMVS		93.83 423	94.02 415	93.23 469	96.83 469	84.96 481	89.77 490	96.32 442	97.92 230	97.43 378	96.36 437	86.17 418	98.93 469	87.68 471	97.73 436	95.81 483

blend_shiyan4		92.09 450	90.16 457	97.88 324	96.78 470	94.93 349	95.24 439	98.58 370	96.22 359	96.07 438	91.42 487	63.46 493	99.73 294	96.70 285	76.98 492	98.98 342

cl22		95.79 385	95.39 387	96.98 395	96.77 471	92.79 419	94.40 465	98.53 376	94.59 413	97.89 341	98.17 361	82.82 449	99.24 454	96.37 318	99.03 366	98.92 355

WB-MVSnew		95.73 387	95.57 379	96.23 423	96.70 472	90.70 457	96.07 401	93.86 472	95.60 387	97.04 395	95.45 458	96.00 274	99.55 394	91.04 455	98.31 412	98.43 415

dp		93.47 429	93.59 422	93.13 470	96.64 473	81.62 495	97.66 268	96.42 441	92.80 445	96.11 436	98.64 308	78.55 466	99.59 378	93.31 418	92.18 488	98.16 430

MonoMVSNet		96.25 368	96.53 354	95.39 444	96.57 474	91.01 451	98.82 97	97.68 408	98.57 169	98.03 331	99.37 104	90.92 383	97.78 485	94.99 369	93.88 484	97.38 465

wanda-best-256-512		95.48 395	94.74 407	97.68 344	96.53 475	94.12 378	94.17 469	98.57 372	95.84 378	96.71 414	91.16 488	86.05 421	99.76 268	97.57 206	96.09 468	99.17 310

FE-blended-shiyan7		95.48 395	94.74 407	97.68 344	96.53 475	94.12 378	94.17 469	98.57 372	95.84 378	96.71 414	91.16 488	86.05 421	99.76 268	97.57 206	96.09 468	99.17 310

usedtu_blend_shiyan5		96.20 371	95.62 374	97.94 319	96.53 475	94.93 349	98.83 96	99.59 91	98.89 136	96.71 414	91.16 488	86.05 421	99.73 294	96.70 285	96.09 468	99.17 310

test-LLR		93.90 422	93.85 417	94.04 458	96.53 475	84.62 484	94.05 473	92.39 478	96.17 361	94.12 469	95.07 459	82.30 450	99.67 334	95.87 345	98.18 417	97.82 447

test-mter		92.33 447	91.76 448	94.04 458	96.53 475	84.62 484	94.05 473	92.39 478	94.00 429	94.12 469	95.07 459	65.63 489	99.67 334	95.87 345	98.18 417	97.82 447

TESTMET0.1,1		92.19 449	91.77 447	93.46 465	96.48 480	82.80 491	94.05 473	91.52 483	94.45 418	94.00 472	94.88 465	66.65 483	99.56 390	95.78 350	98.11 423	98.02 437

MGCNet		97.44 303	97.01 321	98.72 213	96.42 481	96.74 270	97.20 332	91.97 481	98.46 177	98.30 304	98.79 271	92.74 359	99.91 75	99.30 63	99.94 50	99.52 159

miper_enhance_ethall		96.01 375	95.74 369	96.81 405	96.41 482	92.27 431	93.69 478	98.89 328	91.14 463	98.30 304	97.35 416	90.58 386	99.58 385	96.31 322	99.03 366	98.60 399

tpmvs		95.02 405	95.25 393	94.33 454	96.39 483	85.87 477	98.08 193	96.83 434	95.46 392	95.51 453	98.69 296	85.91 424	99.53 402	94.16 393	96.23 465	97.58 460

CMPMVS	75.91 23	96.29 365	95.44 384	98.84 181	96.25 484	98.69 99	97.02 341	99.12 286	88.90 475	97.83 347	98.86 252	89.51 395	98.90 471	91.92 438	99.51 283	98.92 355
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		94.51 410	93.69 420	96.99 394	96.05 485	93.61 408	94.97 447	93.49 473	96.17 361	97.57 365	94.88 465	82.30 450	99.01 466	93.60 411	94.17 483	98.37 422

EPMVS		93.72 426	93.27 425	95.09 449	96.04 486	87.76 471	98.13 183	85.01 494	94.69 411	96.92 400	98.64 308	78.47 467	99.31 446	95.04 368	96.46 462	98.20 428

cascas		94.79 408	94.33 414	96.15 429	96.02 487	92.36 429	92.34 485	99.26 252	85.34 483	95.08 458	94.96 464	92.96 354	98.53 478	94.41 390	98.59 404	97.56 461

MVStest1		95.86 382	95.60 376	96.63 410	95.87 488	91.70 436	97.93 225	98.94 316	98.03 220	99.56 74	99.66 32	71.83 473	98.26 481	99.35 59	99.24 337	99.91 13

gg-mvs-nofinetune		92.37 446	91.20 450	95.85 432	95.80 489	92.38 428	99.31 30	81.84 496	99.75 11	91.83 485	99.74 18	68.29 478	99.02 464	87.15 472	97.12 454	96.16 479

gm-plane-assit					94.83 490	81.97 493			88.07 478		94.99 462		99.60 374	91.76 442

GG-mvs-BLEND				94.76 451	94.54 491	92.13 433	99.31 30	80.47 497		88.73 491	91.01 491	67.59 482	98.16 484	82.30 485	94.53 482	93.98 487

UWE-MVS-28		90.22 455	89.28 458	93.02 471	94.50 492	82.87 490	96.52 372	87.51 490	95.21 400	92.36 483	96.04 439	71.57 474	98.25 482	72.04 492	97.77 435	97.94 442

EPNet_dtu		94.93 407	94.78 405	95.38 445	93.58 493	87.68 472	96.78 355	95.69 456	97.35 287	89.14 490	98.09 368	88.15 407	99.49 415	94.95 372	99.30 328	98.98 342
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		76.24 459	75.95 462	77.12 476	92.39 494	67.91 500	90.16 488	59.44 501	82.04 487	89.42 489	94.67 468	49.68 498	81.74 494	48.06 494	77.66 491	81.72 490

KD-MVS_2432*1600		92.87 440	91.99 442	95.51 441	91.37 495	89.27 464	94.07 471	98.14 394	95.42 393	97.25 386	96.44 434	67.86 479	99.24 454	91.28 451	96.08 472	98.02 437

miper_refine_blended		92.87 440	91.99 442	95.51 441	91.37 495	89.27 464	94.07 471	98.14 394	95.42 393	97.25 386	96.44 434	67.86 479	99.24 454	91.28 451	96.08 472	98.02 437

EPNet		96.14 372	95.44 384	98.25 289	90.76 497	95.50 323	97.92 228	94.65 463	98.97 125	92.98 479	98.85 255	89.12 398	99.87 135	95.99 338	99.68 217	99.39 226
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 460	68.95 463	70.34 477	87.68 498	65.00 501	91.11 486	59.90 500	69.02 490	74.46 495	88.89 492	48.58 499	68.03 496	28.61 495	72.33 494	77.99 491

test_method		79.78 457	79.50 460	80.62 474	80.21 499	45.76 502	70.82 491	98.41 384	31.08 494	80.89 494	97.71 393	84.85 431	97.37 487	91.51 448	80.03 490	98.75 384

tmp_tt		78.77 458	78.73 461	78.90 475	58.45 500	74.76 499	94.20 468	78.26 498	39.16 493	86.71 492	92.82 481	80.50 454	75.19 495	86.16 477	92.29 487	86.74 489

testmvs		17.12 462	20.53 465	6.87 479	12.05 501	4.20 504	93.62 479	6.73 502	4.62 497	10.41 497	24.33 494	8.28 501	3.56 498	9.69 497	15.07 495	12.86 494

test123		17.04 463	20.11 466	7.82 478	10.25 502	4.91 503	94.80 450	4.47 503	4.93 496	10.00 498	24.28 495	9.69 500	3.64 497	10.14 496	12.43 496	14.92 493

mmdepth		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 497	0.00 495

monomultidepth		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 497	0.00 495

test_blank		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 497	0.00 495

eth-test2					0.00 503

eth-test					0.00 503

uanet_test		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 497	0.00 495

DCPMVS		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 497	0.00 495

cdsmvs_eth3d_5k		24.66 461	32.88 464	0.00 480	0.00 503	0.00 505	0.00 492	99.10 289	0.00 498	0.00 499	97.58 401	99.21 18	0.00 499	0.00 498	0.00 497	0.00 495

pcd_1.5k_mvsjas		8.17 464	10.90 467	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	98.07 124	0.00 499	0.00 498	0.00 497	0.00 495

sosnet-low-res		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 497	0.00 495

sosnet		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 497	0.00 495

uncertanet		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 497	0.00 495

Regformer		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 497	0.00 495

ab-mvs-re		8.12 465	10.83 468	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	97.48 407	0.00 502	0.00 499	0.00 498	0.00 497	0.00 495

uanet		0.00 466	0.00 469	0.00 480	0.00 503	0.00 505	0.00 492	0.00 504	0.00 498	0.00 499	0.00 498	0.00 502	0.00 499	0.00 498	0.00 497	0.00 495

TestfortrainingZip							98.68 109

WAC-MVS						90.90 453								91.37 450

PC_three_1452									93.27 437	99.40 116	98.54 321	98.22 109	97.00 488	95.17 366	99.45 298	99.49 174

test_241102_TWO								99.30 232	98.03 220	99.26 149	99.02 201	97.51 182	99.88 116	96.91 260	99.60 251	99.66 78

test_0728_THIRD									98.17 205	99.08 180	99.02 201	97.89 143	99.88 116	97.07 247	99.71 202	99.70 68

GSMVS																98.81 373

sam_mvs1												84.74 433				98.81 373

sam_mvs												84.29 439

MTGPA								99.20 264

test_post1							97.59 283				20.48 497	83.07 447	99.66 347	94.16 393

test_post											21.25 496	83.86 442	99.70 312

patchmatchnet-post											98.77 275	84.37 436	99.85 157

MTMP							97.93 225	91.91 482

test9_res														93.28 419	99.15 353	99.38 235

agg_prior2														92.50 435	99.16 351	99.37 237

test_prior4						97.97 164	95.86 413

test_prior2							95.74 420		96.48 347	96.11 436	97.63 399	95.92 284		94.16 393	99.20 345

旧先验2							95.76 419		88.56 477	97.52 369			99.66 347	94.48 383

新几何2							95.93 409

无先验							95.74 420	98.74 358	89.38 473				99.73 294	92.38 437		99.22 291

原ACMM2							95.53 426

testdata2													99.79 245	92.80 429

segment_acmp												97.02 216

testdata1							95.44 431		96.32 355

plane_prior5								99.27 247					99.70 312	94.42 387	99.51 283	99.45 200

plane_prior4											97.98 376

plane_prior3						97.78 189			97.41 280	97.79 350

plane_prior2							97.77 250		98.20 202

plane_prior						97.65 198	97.07 340		96.72 337						99.36 315

n2								0.00 504

nn								0.00 504

door-mid								99.57 101

test11								98.87 331

door								99.41 184

HQP5-MVS						96.79 266

BP-MVS														92.82 427

HQP4-MVS										95.56 447			99.54 400			99.32 260

HQP3-MVS								99.04 301							99.26 335

HQP2-MVS												93.84 338

MDTV_nov1_ep13_2view						74.92 498	97.69 263		90.06 471	97.75 353		85.78 425		93.52 413		98.69 391

ACMMP++_ref															99.77 162

ACMMP++															99.68 217

Test By Simon												96.52 249

High-resolution multi-view benchmark