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 14	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 88	99.16 62	98.64 236	99.94 2	98.51 114	99.32 26	99.75 43	99.58 38	98.60 300	99.62 40	98.22 113	99.51 433	97.70 208	99.73 199	97.89 470
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
OurMVSNet-221017-0		99.37 28	99.31 41	99.53 38	99.91 3	98.98 72	99.63 7	99.58 103	99.44 52	99.78 39	99.76 15	96.39 265	99.92 65	99.44 54	99.92 71	99.68 73

pmmvs6		99.67 3	99.70 3	99.60 16	99.90 4	99.27 26	99.53 9	99.76 39	99.64 26	99.84 30	99.83 4	99.50 9	99.87 135	99.36 57	99.92 71	99.64 86

PS-MVSNAJss		99.46 17	99.49 16	99.35 80	99.90 4	98.15 149	99.20 49	99.65 77	99.48 44	99.92 8	99.71 22	98.07 128	99.96 13	99.53 48	100.00 1	99.93 11

testf1		99.25 40	99.16 62	99.51 49	99.89 6	99.63 3	98.71 106	99.69 57	98.90 136	99.43 108	99.35 112	98.86 35	99.67 347	97.81 191	99.81 140	99.24 302

APD_test2		99.25 40	99.16 62	99.51 49	99.89 6	99.63 3	98.71 106	99.69 57	98.90 136	99.43 108	99.35 112	98.86 35	99.67 347	97.81 191	99.81 140	99.24 302

ANet_high		99.57 10	99.67 6	99.28 96	99.89 6	98.09 158	99.14 58	99.93 6	99.82 8	99.93 6	99.81 8	99.17 20	99.94 41	99.31 61	100.00 1	99.82 36

anonymousdsp		99.51 14	99.47 21	99.62 9	99.88 9	99.08 69	99.34 23	99.69 57	98.93 132	99.65 63	99.72 21	98.93 33	99.95 25	99.11 77	100.00 1	99.82 36

v7n		99.53 12	99.57 13	99.41 69	99.88 9	98.54 112	99.45 14	99.61 92	99.66 23	99.68 57	99.66 32	98.44 84	99.95 25	99.73 28	99.96 28	99.75 62

mvs_tets		99.63 6	99.67 6	99.49 55	99.88 9	98.61 104	99.34 23	99.71 48	99.27 74	99.90 14	99.74 18	99.68 4	99.97 6	99.55 43	99.99 5	99.88 20

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 74	99.87 12	98.13 152	98.08 197	99.95 2	99.45 50	99.98 2	99.75 16	99.80 1	99.97 6	99.82 12	99.99 5	99.99 2

jajsoiax		99.58 9	99.61 11	99.48 57	99.87 12	98.61 104	99.28 40	99.66 71	99.09 110	99.89 18	99.68 25	99.53 7	99.97 6	99.50 50	99.99 5	99.87 22

test_djsdf		99.52 13	99.51 15	99.53 38	99.86 14	98.74 92	99.39 20	99.56 121	99.11 100	99.70 51	99.73 20	99.00 27	99.97 6	99.26 65	99.98 12	99.89 16

MIMVSNet1		99.38 27	99.32 39	99.55 28	99.86 14	99.19 41	99.41 17	99.59 100	99.59 36	99.71 49	99.57 49	97.12 214	99.90 81	99.21 70	99.87 100	99.54 143

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 28	99.78 39	99.67 30	99.48 10	99.81 227	99.30 62	99.97 21	99.77 53
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 19	99.69 5	99.58 103	99.90 3	99.86 24	99.78 13	99.58 6	99.95 25	99.00 87	99.95 39	99.78 50

SixPastTwentyTwo		98.75 138	98.62 154	99.16 118	99.83 18	97.96 181	99.28 40	98.20 426	99.37 60	99.70 51	99.65 36	92.65 400	99.93 53	99.04 84	99.84 114	99.60 102

sc_t1		99.62 7	99.66 8	99.53 38	99.82 19	99.09 68	99.50 11	99.63 82	99.88 4	99.86 24	99.80 11	99.03 24	99.89 97	99.48 52	99.93 57	99.60 102

Baseline_NR-MVSNet		98.98 98	98.86 115	99.36 74	99.82 19	98.55 109	97.47 308	99.57 111	99.37 60	99.21 174	99.61 43	96.76 242	99.83 198	98.06 164	99.83 126	99.71 65

pm-mvs1		99.44 19	99.48 18	99.33 89	99.80 21	98.63 101	99.29 36	99.63 82	99.30 71	99.65 63	99.60 45	99.16 22	99.82 210	99.07 80	99.83 126	99.56 130

TransMVSNet (Re)		99.44 19	99.47 21	99.36 74	99.80 21	98.58 107	99.27 42	99.57 111	99.39 58	99.75 44	99.62 40	99.17 20	99.83 198	99.06 82	99.62 267	99.66 80

K. test v3		98.00 268	97.66 298	99.03 148	99.79 23	97.56 228	99.19 53	92.47 531	99.62 32	99.52 87	99.66 32	89.61 441	99.96 13	99.25 67	99.81 140	99.56 130

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 83	99.78 24	98.11 154	97.77 255	99.90 12	99.33 66	99.97 3	99.66 32	99.71 3	99.96 13	99.79 19	99.99 5	99.96 8

APD_test1		98.83 122	98.66 146	99.34 83	99.78 24	99.47 8	98.42 151	99.45 179	98.28 200	98.98 214	99.19 160	97.76 158	99.58 404	96.57 323	99.55 298	98.97 364

test_vis3_rt		99.14 62	99.17 60	99.07 138	99.78 24	98.38 124	98.92 83	99.94 3	97.80 248	99.91 12	99.67 30	97.15 212	98.91 502	99.76 23	99.56 293	99.92 12

EGC-MVSNET		85.24 510	80.54 513	99.34 83	99.77 27	99.20 38	99.08 62	99.29 262	12.08 551	20.84 553	99.42 89	97.55 178	99.85 159	97.08 266	99.72 208	98.96 367

Anonymous20240521		98.69 151	98.87 111	98.16 318	99.77 27	95.11 389	99.08 62	99.44 187	99.34 65	99.33 138	99.55 56	94.10 367	99.94 41	99.25 67	99.96 28	99.42 219

FC-MVSNet-test		99.27 37	99.25 52	99.34 83	99.77 27	98.37 126	99.30 35	99.57 111	99.61 34	99.40 117	99.50 68	97.12 214	99.85 159	99.02 86	99.94 51	99.80 45

test_vis1_n		98.31 227	98.50 175	97.73 365	99.76 30	94.17 422	98.68 109	99.91 10	96.31 376	99.79 38	99.57 49	92.85 396	99.42 458	99.79 19	99.84 114	99.60 102

test_fmvs3		99.12 69	99.41 26	98.25 305	99.76 30	95.07 390	99.05 68	99.94 3	97.78 251	99.82 34	99.84 3	98.56 73	99.71 311	99.96 1	99.96 28	99.97 4

XXY-MVS		99.14 62	99.15 67	99.10 130	99.76 30	97.74 212	98.85 93	99.62 89	98.48 181	99.37 125	99.49 74	98.75 47	99.86 145	98.20 152	99.80 152	99.71 65

TDRefinement		99.42 23	99.38 28	99.55 28	99.76 30	99.33 20	99.68 6	99.71 48	99.38 59	99.53 83	99.61 43	98.64 61	99.80 236	98.24 147	99.84 114	99.52 161

dtuonlycased		97.70 303	98.19 236	96.24 456	99.75 34	89.51 518	94.69 484	99.64 79	98.23 202	99.46 101	98.57 341	98.25 107	99.85 159	95.65 383	99.44 336	99.36 252

fmvsm_s_conf0.1_n_a		99.17 52	99.30 44	98.80 197	99.75 34	96.59 308	97.97 228	99.86 17	98.22 204	99.88 21	99.71 22	98.59 67	99.84 180	99.73 28	99.98 12	99.98 3

tt0805		98.69 151	98.62 154	98.90 178	99.75 34	99.30 21	99.15 57	96.97 470	98.86 142	98.87 249	97.62 438	98.63 63	98.96 498	99.41 56	98.29 461	98.45 434

test_vis1_n_1920		98.40 207	98.92 102	96.81 435	99.74 37	90.76 507	98.15 185	99.91 10	98.33 191	99.89 18	99.55 56	95.07 328	99.88 115	99.76 23	99.93 57	99.79 47

usedtu_dtu_shiyan2		98.99 94	98.86 115	99.39 72	99.73 38	98.71 98	99.05 68	99.47 170	99.16 94	99.49 94	99.12 187	96.34 271	99.93 53	98.05 166	99.36 348	99.54 143

FOURS1					99.73 38	99.67 2	99.43 15	99.54 132	99.43 54	99.26 157

PEN-MVS		99.41 24	99.34 35	99.62 9	99.73 38	99.14 57	99.29 36	99.54 132	99.62 32	99.56 74	99.42 89	98.16 122	99.96 13	98.78 102	99.93 57	99.77 53

lessismore_v0				98.97 162	99.73 38	97.53 231		86.71 549		99.37 125	99.52 67	89.93 436	99.92 65	98.99 88	99.72 208	99.44 210

SteuartSystems-ACMMP		98.79 131	98.54 167	99.54 31	99.73 38	99.16 48	98.23 174	99.31 246	97.92 238	98.90 237	98.90 258	98.00 134	99.88 115	96.15 358	99.72 208	99.58 117
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		98.17 251	98.15 244	98.22 311	99.73 38	95.15 386	97.36 322	99.68 64	94.45 456	98.99 213	99.27 132	96.87 231	99.94 41	97.13 263	99.91 80	99.57 124

Vis-MVSNet		99.34 29	99.36 32	99.27 99	99.73 38	98.26 138	99.17 54	99.78 36	99.11 100	99.27 153	99.48 75	98.82 38	99.95 25	98.94 91	99.93 57	99.59 109
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 45	98.98 72	99.51 10	99.85 19	99.86 6	99.88 21	99.82 5	99.02 26	99.90 81	99.54 44	99.95 39	99.61 100

SSC-MVS		98.71 142	98.74 128	98.62 242	99.72 45	96.08 336	98.74 99	98.64 397	99.74 12	99.67 59	99.24 145	94.57 346	99.95 25	99.11 77	99.24 374	99.82 36

test_f		98.67 161	98.87 111	98.05 333	99.72 45	95.59 355	98.51 135	99.81 32	96.30 378	99.78 39	99.82 5	96.14 279	98.63 510	99.82 12	99.93 57	99.95 9

ACMH	96.65 7	99.25 40	99.24 53	99.26 101	99.72 45	98.38 124	99.07 65	99.55 126	98.30 195	99.65 63	99.45 84	99.22 17	99.76 273	98.44 131	99.77 172	99.64 86
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 49	98.94 79	99.54 8	99.83 26	99.87 5	99.89 18	99.82 5	98.75 47	99.90 81	99.54 44	99.95 39	99.59 109

fmvsm_s_conf0.1_n		99.16 56	99.33 37	98.64 236	99.71 49	96.10 331	97.87 241	99.85 19	98.56 177	99.90 14	99.68 25	98.69 57	99.85 159	99.72 30	99.98 12	99.97 4

PS-CasMVS		99.40 25	99.33 37	99.62 9	99.71 49	99.10 65	99.29 36	99.53 136	99.53 41	99.46 101	99.41 94	98.23 110	99.95 25	98.89 96	99.95 39	99.81 41

DTE-MVSNet		99.43 22	99.35 33	99.66 7	99.71 49	99.30 21	99.31 30	99.51 144	99.64 26	99.56 74	99.46 80	98.23 110	99.97 6	98.78 102	99.93 57	99.72 64

WR-MVS_H		99.33 30	99.22 54	99.65 8	99.71 49	99.24 29	99.32 26	99.55 126	99.46 49	99.50 93	99.34 116	97.30 201	99.93 53	98.90 94	99.93 57	99.77 53

HPM-MVS_fast		99.01 90	98.82 121	99.57 21	99.71 49	99.35 16	99.00 73	99.50 149	97.33 301	98.94 232	98.86 269	98.75 47	99.82 210	97.53 225	99.71 217	99.56 130

ACMH+	96.62 9	99.08 79	99.00 94	99.33 89	99.71 49	98.83 87	98.60 121	99.58 103	99.11 100	99.53 83	99.18 164	98.81 39	99.67 347	96.71 307	99.77 172	99.50 169

PMVS	91.26 20	97.86 286	97.94 269	97.65 374	99.71 49	97.94 184	98.52 130	98.68 392	98.99 124	97.52 404	99.35 112	97.41 194	98.18 517	91.59 494	99.67 246	96.82 507
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FE-MVSNET2		99.15 57	99.22 54	98.94 167	99.70 57	97.49 232	98.62 118	99.67 70	98.85 145	99.34 135	99.54 62	98.47 77	99.81 227	98.93 92	99.91 80	99.51 165

KinetiMVS		99.03 88	99.02 90	99.03 148	99.70 57	97.48 235	98.43 148	99.29 262	99.70 15	99.60 71	99.07 200	96.13 281	99.94 41	99.42 55	99.87 100	99.68 73

FIs		99.14 62	99.09 82	99.29 95	99.70 57	98.28 136	99.13 59	99.52 142	99.48 44	99.24 167	99.41 94	96.79 239	99.82 210	98.69 112	99.88 95	99.76 58

VPNet		98.87 112	98.83 120	99.01 153	99.70 57	97.62 225	98.43 148	99.35 227	99.47 47	99.28 151	99.05 208	96.72 246	99.82 210	98.09 161	99.36 348	99.59 109

fmvsm_s_conf0.1_n_2		99.20 50	99.38 28	98.65 234	99.69 61	96.08 336	97.49 303	99.90 12	99.53 41	99.88 21	99.64 37	98.51 76	99.90 81	99.83 10	99.98 12	99.97 4

test_cas_vis1_n_1920		98.33 222	98.68 141	97.27 407	99.69 61	92.29 478	98.03 208	99.85 19	97.62 263	99.96 4	99.62 40	93.98 368	99.74 292	99.52 49	99.86 107	99.79 47

MP-MVS-pluss		98.57 178	98.23 230	99.60 16	99.69 61	99.35 16	97.16 345	99.38 213	94.87 442	98.97 218	98.99 232	98.01 133	99.88 115	97.29 246	99.70 228	99.58 117
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SDMVSNet		99.23 45	99.32 39	98.96 164	99.68 64	97.35 245	98.84 95	99.48 159	99.69 17	99.63 66	99.68 25	99.03 24	99.96 13	97.97 177	99.92 71	99.57 124

sd_testset		99.28 36	99.31 41	99.19 112	99.68 64	98.06 168	99.41 17	99.30 254	99.69 17	99.63 66	99.68 25	99.25 16	99.96 13	97.25 249	99.92 71	99.57 124

test_fmvs1_n		98.09 259	98.28 219	97.52 392	99.68 64	93.47 456	98.63 116	99.93 6	95.41 427	99.68 57	99.64 37	91.88 415	99.48 442	99.82 12	99.87 100	99.62 92

CHOSEN 1792x2688		97.49 319	97.14 336	98.54 265	99.68 64	96.09 334	96.50 392	99.62 89	91.58 504	98.84 254	98.97 239	92.36 403	99.88 115	96.76 299	99.95 39	99.67 78

tfpnnormal		98.90 108	98.90 105	98.91 175	99.67 68	97.82 202	99.00 73	99.44 187	99.45 50	99.51 92	99.24 145	98.20 117	99.86 145	95.92 368	99.69 234	99.04 350

MTAPA		98.88 111	98.64 150	99.61 13	99.67 68	99.36 15	98.43 148	99.20 290	98.83 149	98.89 240	98.90 258	96.98 225	99.92 65	97.16 256	99.70 228	99.56 130

test_fmvsmvis_n_1920		99.26 39	99.49 16	98.54 265	99.66 70	96.97 285	98.00 216	99.85 19	99.24 77	99.92 8	99.50 68	99.39 12	99.95 25	99.89 3	99.98 12	98.71 409

mvs5depth		99.30 33	99.59 12	98.44 281	99.65 71	95.35 374	99.82 3	99.94 3	99.83 7	99.42 112	99.94 2	98.13 125	99.96 13	99.63 36	99.96 28	100.00 1

fmvsm_l_conf0.5_n_a		99.19 51	99.27 47	98.94 167	99.65 71	97.05 280	97.80 250	99.76 39	98.70 159	99.78 39	99.11 189	98.79 43	99.95 25	99.85 6	99.96 28	99.83 33

WB-MVS		98.52 193	98.55 165	98.43 282	99.65 71	95.59 355	98.52 130	98.77 380	99.65 25	99.52 87	99.00 230	94.34 356	99.93 53	98.65 114	98.83 424	99.76 58

CP-MVSNet		99.21 47	99.09 82	99.56 26	99.65 71	98.96 78	99.13 59	99.34 233	99.42 55	99.33 138	99.26 138	97.01 223	99.94 41	98.74 107	99.93 57	99.79 47

HPM-MVS		98.79 131	98.53 169	99.59 20	99.65 71	99.29 23	99.16 55	99.43 193	96.74 354	98.61 297	98.38 367	98.62 64	99.87 135	96.47 335	99.67 246	99.59 109
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
RPSCF		98.62 170	98.36 204	99.42 67	99.65 71	99.42 10	98.55 126	99.57 111	97.72 256	98.90 237	99.26 138	96.12 283	99.52 427	95.72 379	99.71 217	99.32 273

NormalMVS		98.26 235	97.97 265	99.15 123	99.64 77	97.83 197	98.28 168	99.43 193	99.24 77	98.80 263	98.85 272	89.76 439	99.94 41	98.04 167	99.67 246	99.68 73

lecture		99.25 40	99.12 71	99.62 9	99.64 77	99.40 11	98.89 88	99.51 144	99.19 89	99.37 125	99.25 143	98.36 90	99.88 115	98.23 149	99.67 246	99.59 109

fmvsm_l_conf0.5_n		99.21 47	99.28 46	99.02 151	99.64 77	97.28 257	97.82 246	99.76 39	98.73 151	99.82 34	99.09 198	98.81 39	99.95 25	99.86 4	99.96 28	99.83 33

test_fmvsmconf_n		99.44 19	99.48 18	99.31 94	99.64 77	98.10 157	97.68 270	99.84 23	99.29 72	99.92 8	99.57 49	99.60 5	99.96 13	99.74 27	99.98 12	99.89 16

TSAR-MVS + MP.		98.63 167	98.49 180	99.06 144	99.64 77	97.90 190	98.51 135	98.94 344	96.96 334	99.24 167	98.89 264	97.83 151	99.81 227	96.88 289	99.49 323	99.48 188
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PM-MVS		98.82 125	98.72 132	99.12 126	99.64 77	98.54 112	97.98 224	99.68 64	97.62 263	99.34 135	99.18 164	97.54 180	99.77 267	97.79 193	99.74 195	99.04 350

Elysia		99.15 57	99.14 68	99.18 113	99.63 83	97.92 186	98.50 137	99.43 193	99.67 20	99.70 51	99.13 183	96.66 249	99.98 4	99.54 44	99.96 28	99.64 86

StellarMVS		99.15 57	99.14 68	99.18 113	99.63 83	97.92 186	98.50 137	99.43 193	99.67 20	99.70 51	99.13 183	96.66 249	99.98 4	99.54 44	99.96 28	99.64 86

KD-MVS_self_test		99.25 40	99.18 59	99.44 65	99.63 83	99.06 70	98.69 108	99.54 132	99.31 69	99.62 69	99.53 64	97.36 198	99.86 145	99.24 69	99.71 217	99.39 232

EU-MVSNet		97.66 307	98.50 175	95.13 497	99.63 83	85.84 533	98.35 162	98.21 425	98.23 202	99.54 79	99.46 80	95.02 329	99.68 342	98.24 147	99.87 100	99.87 22

HyFIR lowres test		97.19 349	96.60 380	98.96 164	99.62 87	97.28 257	95.17 468	99.50 149	94.21 462	99.01 208	98.32 377	86.61 462	99.99 2	97.10 265	99.84 114	99.60 102

E5new		99.05 83	99.11 74	98.85 182	99.60 88	97.30 251	98.42 151	99.63 82	98.73 151	99.26 157	99.39 101	98.71 51	99.70 320	98.43 133	99.84 114	99.54 143

E6new		99.05 83	99.11 74	98.85 182	99.60 88	97.30 251	98.42 151	99.63 82	98.73 151	99.26 157	99.39 101	98.71 51	99.70 320	98.43 133	99.84 114	99.54 143

E6		99.05 83	99.11 74	98.85 182	99.60 88	97.30 251	98.42 151	99.63 82	98.73 151	99.26 157	99.39 101	98.71 51	99.70 320	98.43 133	99.84 114	99.54 143

E5		99.05 83	99.11 74	98.85 182	99.60 88	97.30 251	98.42 151	99.63 82	98.73 151	99.26 157	99.39 101	98.71 51	99.70 320	98.43 133	99.84 114	99.54 143

fmvsm_l_conf0.5_n_9		99.32 32	99.43 24	98.98 160	99.59 92	97.18 271	97.44 312	99.83 26	99.56 39	99.91 12	99.34 116	99.36 13	99.93 53	99.83 10	99.98 12	99.85 30

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 83	99.59 92	98.21 146	97.82 246	99.84 23	99.41 57	99.92 8	99.41 94	99.51 8	99.95 25	99.84 9	99.97 21	99.87 22

aaatest				99.45 64	99.58 94	98.93 80	98.68 109	99.60 94	96.46 370	99.53 83	98.77 292		99.83 198	96.67 312	99.64 258	99.58 117

MED-MVS		99.01 90	98.84 119	99.52 44	99.58 94	98.93 80	98.68 109	99.60 94	98.85 145	99.53 83	99.16 171	97.87 149	99.83 198	96.67 312	99.62 267	99.81 41

TestfortrainingZip a		99.09 73	98.92 102	99.61 13	99.58 94	99.17 43	98.68 109	99.27 269	98.85 145	99.61 70	99.16 171	97.14 213	99.86 145	98.39 138	99.57 289	99.81 41

FE-MVSNET		98.59 175	98.50 175	98.87 179	99.58 94	97.30 251	98.08 197	99.74 44	96.94 336	98.97 218	99.10 192	96.94 227	99.74 292	97.33 242	99.86 107	99.55 137

mmtdpeth		99.30 33	99.42 25	98.92 173	99.58 94	96.89 293	99.48 13	99.92 8	99.92 2	98.26 342	99.80 11	98.33 96	99.91 74	99.56 41	99.95 39	99.97 4

ACMMP_NAP		98.75 138	98.48 181	99.57 21	99.58 94	99.29 23	97.82 246	99.25 277	96.94 336	98.78 265	99.12 187	98.02 132	99.84 180	97.13 263	99.67 246	99.59 109

nrg030		99.40 25	99.35 33	99.54 31	99.58 94	99.13 60	98.98 76	99.48 159	99.68 19	99.46 101	99.26 138	98.62 64	99.73 299	99.17 74	99.92 71	99.76 58

VDDNet		98.21 243	97.95 266	99.01 153	99.58 94	97.74 212	99.01 71	97.29 458	99.67 20	98.97 218	99.50 68	90.45 433	99.80 236	97.88 184	99.20 383	99.48 188

COLMAP_ROB	96.50 10	98.99 94	98.85 118	99.41 69	99.58 94	99.10 65	98.74 99	99.56 121	99.09 110	99.33 138	99.19 160	98.40 86	99.72 309	95.98 366	99.76 188	99.42 219
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 30	99.45 23	98.99 156	99.57 103	97.73 214	97.93 230	99.83 26	99.22 80	99.93 6	99.30 126	99.42 11	99.96 13	99.85 6	99.99 5	99.29 284

ZNCC-MVS		98.68 157	98.40 193	99.54 31	99.57 103	99.21 32	98.46 145	99.29 262	97.28 308	98.11 354	98.39 365	98.00 134	99.87 135	96.86 292	99.64 258	99.55 137

MSP-MVS		98.40 207	98.00 260	99.61 13	99.57 103	99.25 28	98.57 124	99.35 227	97.55 274	99.31 147	97.71 431	94.61 345	99.88 115	96.14 359	99.19 386	99.70 70
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		98.32 223	98.39 196	98.13 320	99.57 103	95.54 358	97.78 252	99.49 157	97.37 298	99.19 176	97.65 435	98.96 30	99.49 438	96.50 334	98.99 412	99.34 262

MP-MVS		98.46 199	98.09 249	99.54 31	99.57 103	99.22 31	98.50 137	99.19 294	97.61 266	97.58 398	98.66 322	97.40 195	99.88 115	94.72 410	99.60 276	99.54 143
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
LPG-MVS_test		98.71 142	98.46 185	99.47 61	99.57 103	98.97 74	98.23 174	99.48 159	96.60 361	99.10 189	99.06 201	98.71 51	99.83 198	95.58 388	99.78 164	99.62 92

LGP-MVS_train				99.47 61	99.57 103	98.97 74		99.48 159	96.60 361	99.10 189	99.06 201	98.71 51	99.83 198	95.58 388	99.78 164	99.62 92

IS-MVSNet		98.19 246	97.90 275	99.08 136	99.57 103	97.97 178	99.31 30	98.32 419	99.01 123	98.98 214	99.03 213	91.59 417	99.79 249	95.49 391	99.80 152	99.48 188

viewdifsd2359ckpt11		98.84 119	99.04 87	98.24 307	99.56 111	95.51 360	97.38 317	99.70 54	99.16 94	99.57 72	99.40 98	98.26 105	99.71 311	98.55 125	99.82 133	99.50 169

viewmsd2359difaftdt		98.84 119	99.04 87	98.24 307	99.56 111	95.51 360	97.38 317	99.70 54	99.16 94	99.57 72	99.40 98	98.26 105	99.71 311	98.55 125	99.82 133	99.50 169

dcpmvs_2		98.78 133	99.11 74	97.78 355	99.56 111	93.67 450	99.06 66	99.86 17	99.50 43	99.66 60	99.26 138	97.21 209	99.99 2	98.00 172	99.91 80	99.68 73

test_0402		98.76 137	98.71 135	98.93 170	99.56 111	98.14 151	98.45 147	99.34 233	99.28 73	98.95 224	98.91 255	98.34 95	99.79 249	95.63 384	99.91 80	98.86 385

EPP-MVSNet		98.30 228	98.04 256	99.07 138	99.56 111	97.83 197	99.29 36	98.07 433	99.03 121	98.59 302	99.13 183	92.16 408	99.90 81	96.87 290	99.68 240	99.49 177

ACMMP		98.75 138	98.50 175	99.52 44	99.56 111	99.16 48	98.87 89	99.37 217	97.16 324	98.82 259	99.01 226	97.71 161	99.87 135	96.29 350	99.69 234	99.54 143
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
casdiffseed414692147		99.09 73	99.12 71	99.01 153	99.55 117	97.91 188	98.30 166	99.68 64	99.04 119	99.19 176	99.37 105	98.98 28	99.61 388	98.13 156	99.83 126	99.50 169

fmvsm_s_conf0.5_n_a		99.10 72	99.20 58	98.78 204	99.55 117	96.59 308	97.79 251	99.82 31	98.21 206	99.81 36	99.53 64	98.46 82	99.84 180	99.70 33	99.97 21	99.90 15

fmvsm_s_conf0.5_n		99.09 73	99.26 50	98.61 246	99.55 117	96.09 334	97.74 263	99.81 32	98.55 178	99.85 27	99.55 56	98.60 66	99.84 180	99.69 35	99.98 12	99.89 16

FMVSNet1		99.17 52	99.17 60	99.17 115	99.55 117	98.24 140	99.20 49	99.44 187	99.21 82	99.43 108	99.55 56	97.82 154	99.86 145	98.42 137	99.89 94	99.41 222

Vis-MVSNet (Re-imp)		97.46 321	97.16 333	98.34 295	99.55 117	96.10 331	98.94 81	98.44 412	98.32 193	98.16 348	98.62 334	88.76 446	99.73 299	93.88 436	99.79 159	99.18 324

ACMM	96.08 12	98.91 106	98.73 130	99.48 57	99.55 117	99.14 57	98.07 201	99.37 217	97.62 263	99.04 203	98.96 243	98.84 37	99.79 249	97.43 236	99.65 256	99.49 177
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
hybridcas		99.08 79	99.13 70	98.92 173	99.54 123	97.61 226	98.22 178	99.66 71	99.27 74	99.40 117	99.24 145	98.47 77	99.70 320	98.59 118	99.80 152	99.46 200

test_fmvs2		98.70 147	98.97 98	97.89 346	99.54 123	94.05 427	98.55 126	99.92 8	96.78 352	99.72 47	99.78 13	96.60 254	99.67 347	99.91 2	99.90 88	99.94 10

mPP-MVS		98.64 165	98.34 208	99.54 31	99.54 123	99.17 43	98.63 116	99.24 283	97.47 283	98.09 356	98.68 316	97.62 170	99.89 97	96.22 353	99.62 267	99.57 124

XVG-ACMP-BASELINE		98.56 180	98.34 208	99.22 109	99.54 123	98.59 106	97.71 266	99.46 175	97.25 312	98.98 214	98.99 232	97.54 180	99.84 180	95.88 369	99.74 195	99.23 304

Casviewmamba		99.12 69	99.12 71	99.09 134	99.53 127	98.08 162	98.34 164	99.66 71	99.35 64	99.35 130	99.23 151	98.39 88	99.72 309	98.46 129	99.81 140	99.47 197

viewmacassd2359aftdt		98.86 116	98.87 111	98.83 190	99.53 127	97.32 250	97.70 268	99.64 79	98.22 204	99.25 165	99.27 132	98.40 86	99.61 388	97.98 176	99.87 100	99.55 137

region2R		98.69 151	98.40 193	99.54 31	99.53 127	99.17 43	98.52 130	99.31 246	97.46 288	98.44 324	98.51 349	97.83 151	99.88 115	96.46 336	99.58 285	99.58 117

PGM-MVS		98.66 162	98.37 202	99.55 28	99.53 127	99.18 42	98.23 174	99.49 157	97.01 333	98.69 280	98.88 266	98.00 134	99.89 97	95.87 372	99.59 280	99.58 117

E4		98.87 112	98.88 108	98.81 194	99.52 131	97.23 261	97.62 281	99.61 92	98.58 172	99.18 181	99.33 119	98.29 99	99.69 330	97.99 175	99.83 126	99.52 161

Patchmatch-RL test		97.26 341	97.02 343	97.99 339	99.52 131	95.53 359	96.13 421	99.71 48	97.47 283	99.27 153	99.16 171	84.30 488	99.62 380	97.89 181	99.77 172	98.81 394

ACMMPR		98.70 147	98.42 191	99.54 31	99.52 131	99.14 57	98.52 130	99.31 246	97.47 283	98.56 308	98.54 344	97.75 159	99.88 115	96.57 323	99.59 280	99.58 117

DKM-HiRes		98.14 254	97.80 282	99.16 118	99.51 134	98.40 121	96.70 374	99.63 82	97.55 274	97.45 412	98.74 299	93.27 382	99.54 420	97.78 194	99.55 298	99.53 157

fmvsm_s_conf0.5_n_9		99.17 52	99.38 28	98.53 267	99.51 134	95.82 349	97.62 281	99.78 36	99.72 14	99.90 14	99.48 75	98.66 59	99.89 97	99.85 6	99.93 57	99.89 16

AstraMVS		98.16 253	98.07 254	98.41 285	99.51 134	95.86 346	98.00 216	95.14 509	98.97 127	99.43 108	99.24 145	93.25 383	99.84 180	99.21 70	99.87 100	99.54 143

fmvsm_s_conf0.5_n_8		99.13 66	99.26 50	98.74 217	99.51 134	96.44 321	97.65 276	99.65 77	99.66 23	99.78 39	99.48 75	97.92 142	99.93 53	99.72 30	99.95 39	99.87 22

GST-MVS		98.61 171	98.30 216	99.52 44	99.51 134	99.20 38	98.26 172	99.25 277	97.44 291	98.67 284	98.39 365	97.68 162	99.85 159	96.00 364	99.51 311	99.52 161

Anonymous20231206		98.21 243	98.21 231	98.20 312	99.51 134	95.43 370	98.13 187	99.32 241	96.16 385	98.93 233	98.82 282	96.00 288	99.83 198	97.32 244	99.73 199	99.36 252

ACMP	95.32 15	98.41 204	98.09 249	99.36 74	99.51 134	98.79 90	97.68 270	99.38 213	95.76 408	98.81 261	98.82 282	98.36 90	99.82 210	94.75 407	99.77 172	99.48 188
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
RoMa-HiRes		98.68 157	98.52 170	99.16 118	99.50 141	98.35 130	98.01 214	99.71 48	96.94 336	99.35 130	98.66 322	96.38 267	99.63 375	98.39 138	99.71 217	99.48 188

LuminaMVS		98.39 214	98.20 232	98.98 160	99.50 141	97.49 232	97.78 252	97.69 442	98.75 150	99.49 94	99.25 143	92.30 406	99.94 41	99.14 75	99.88 95	99.50 169

DVP-MVS		98.77 136	98.52 170	99.52 44	99.50 141	99.21 32	98.02 211	98.84 369	97.97 232	99.08 191	99.02 214	97.61 172	99.88 115	96.99 274	99.63 263	99.48 188
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	99.50 141	99.23 30	98.02 211	99.32 241					99.88 115	96.99 274	99.63 263	99.68 73

test0726					99.50 141	99.21 32	98.17 183	99.35 227	97.97 232	99.26 157	99.06 201	97.61 172

AllTest		98.44 202	98.20 232	99.16 118	99.50 141	98.55 109	98.25 173	99.58 103	96.80 350	98.88 244	99.06 201	97.65 165	99.57 406	94.45 417	99.61 274	99.37 244

TestCases				99.16 118	99.50 141	98.55 109		99.58 103	96.80 350	98.88 244	99.06 201	97.65 165	99.57 406	94.45 417	99.61 274	99.37 244

XVG-OURS		98.53 189	98.34 208	99.11 128	99.50 141	98.82 89	95.97 431	99.50 149	97.30 306	99.05 201	98.98 237	99.35 14	99.32 473	95.72 379	99.68 240	99.18 324

EG-PatchMatch MVS		98.99 94	99.01 92	98.94 167	99.50 141	97.47 236	98.04 206	99.59 100	98.15 222	99.40 117	99.36 111	98.58 72	99.76 273	98.78 102	99.68 240	99.59 109

fmvsm_s_conf0.5_n_2		99.14 62	99.31 41	98.63 240	99.49 150	96.08 336	97.38 317	99.81 32	99.48 44	99.84 30	99.57 49	98.46 82	99.89 97	99.82 12	99.97 21	99.91 13

SED-MVS		98.91 106	98.72 132	99.49 55	99.49 150	99.17 43	98.10 194	99.31 246	98.03 228	99.66 60	99.02 214	98.36 90	99.88 115	96.91 282	99.62 267	99.41 222

IU-MVS					99.49 150	99.15 52		98.87 360	92.97 487	99.41 114				96.76 299	99.62 267	99.66 80

test_241102_ONE					99.49 150	99.17 43		99.31 246	97.98 231	99.66 60	98.90 258	98.36 90	99.48 442

UA-Net		99.47 16	99.40 27	99.70 2	99.49 150	99.29 23	99.80 4	99.72 46	99.82 8	99.04 203	99.81 8	98.05 131	99.96 13	98.85 98	99.99 5	99.86 28

HFP-MVS		98.71 142	98.44 188	99.51 49	99.49 150	99.16 48	98.52 130	99.31 246	97.47 283	98.58 304	98.50 353	97.97 138	99.85 159	96.57 323	99.59 280	99.53 157

VPA-MVSNet		99.30 33	99.30 44	99.28 96	99.49 150	98.36 129	99.00 73	99.45 179	99.63 28	99.52 87	99.44 85	98.25 107	99.88 115	99.09 79	99.84 114	99.62 92

XVG-OURS-SEG-HR		98.49 196	98.28 219	99.14 124	99.49 150	98.83 87	96.54 388	99.48 159	97.32 303	99.11 186	98.61 336	99.33 15	99.30 476	96.23 352	98.38 455	99.28 287

fmvsm_s_conf0.5_n_11		99.21 47	99.34 35	98.80 197	99.48 158	96.56 313	97.97 228	99.69 57	99.63 28	99.84 30	99.54 62	98.21 115	99.94 41	99.76 23	99.95 39	99.88 20

114514_t		96.50 387	95.77 407	98.69 227	99.48 158	97.43 242	97.84 245	99.55 126	81.42 543	96.51 469	98.58 340	95.53 311	99.67 347	93.41 453	99.58 285	98.98 360

IterMVS-LS		98.55 184	98.70 138	98.09 325	99.48 158	94.73 405	97.22 339	99.39 211	98.97 127	99.38 121	99.31 125	96.00 288	99.93 53	98.58 119	99.97 21	99.60 102
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	98.78 204	99.47 161	96.56 313	97.75 261	99.71 48	99.60 35	99.74 46	99.44 85	97.96 139	99.95 25	99.86 4	99.94 51	99.82 36

fmvsm_s_conf0.5_n_5		99.07 82	99.10 80	98.99 156	99.47 161	97.22 264	97.40 314	99.83 26	97.61 266	99.85 27	99.30 126	98.80 41	99.95 25	99.71 32	99.90 88	99.78 50

v8		99.01 90	99.16 62	98.57 253	99.47 161	96.31 326	98.90 84	99.47 170	99.03 121	99.52 87	99.57 49	96.93 228	99.81 227	99.60 37	99.98 12	99.60 102

SSC-MVS3.2		98.53 189	98.79 124	97.74 362	99.46 164	93.62 453	96.45 395	99.34 233	99.33 66	98.93 233	98.70 312	97.90 143	99.90 81	99.12 76	99.92 71	99.69 72

fmvsm_s_conf0.5_n_3		99.22 46	99.37 31	98.78 204	99.46 164	96.58 311	97.65 276	99.72 46	99.47 47	99.86 24	99.50 68	98.94 31	99.89 97	99.75 26	99.97 21	99.86 28

XVS		98.72 141	98.45 186	99.53 38	99.46 164	99.21 32	98.65 114	99.34 233	98.62 166	97.54 402	98.63 331	97.50 186	99.83 198	96.79 295	99.53 305	99.56 130

X-MVStestdata		94.32 459	92.59 481	99.53 38	99.46 164	99.21 32	98.65 114	99.34 233	98.62 166	97.54 402	45.85 549	97.50 186	99.83 198	96.79 295	99.53 305	99.56 130

test20.03		98.78 133	98.77 127	98.78 204	99.46 164	97.20 267	97.78 252	99.24 283	99.04 119	99.41 114	98.90 258	97.65 165	99.76 273	97.70 208	99.79 159	99.39 232

guyue		98.01 267	97.93 271	98.26 303	99.45 169	95.48 365	98.08 197	96.24 489	98.89 138	99.34 135	99.14 181	91.32 424	99.82 210	99.07 80	99.83 126	99.48 188

CSCG		98.68 157	98.50 175	99.20 110	99.45 169	98.63 101	98.56 125	99.57 111	97.87 242	98.85 251	98.04 406	97.66 164	99.84 180	96.72 305	99.81 140	99.13 339

GeoE		99.05 83	98.99 96	99.25 104	99.44 171	98.35 130	98.73 103	99.56 121	98.42 185	98.91 236	98.81 285	98.94 31	99.91 74	98.35 141	99.73 199	99.49 177

v148		98.45 201	98.60 159	98.00 337	99.44 171	94.98 392	97.44 312	99.06 322	98.30 195	99.32 144	98.97 239	96.65 251	99.62 380	98.37 140	99.85 109	99.39 232

v10		98.97 99	99.11 74	98.55 260	99.44 171	96.21 330	98.90 84	99.55 126	98.73 151	99.48 96	99.60 45	96.63 253	99.83 198	99.70 33	99.99 5	99.61 100

V42		98.78 133	98.78 126	98.76 211	99.44 171	97.04 281	98.27 171	99.19 294	97.87 242	99.25 165	99.16 171	96.84 232	99.78 261	99.21 70	99.84 114	99.46 200

MDA-MVSNet-bldmvs		97.94 275	97.91 274	98.06 331	99.44 171	94.96 393	96.63 382	99.15 310	98.35 188	98.83 256	99.11 189	94.31 358	99.85 159	96.60 320	98.72 433	99.37 244

viewdifsd2359ckpt07		98.71 142	98.86 115	98.26 303	99.43 176	95.65 354	97.20 340	99.66 71	99.20 84	99.29 149	99.01 226	98.29 99	99.73 299	97.92 180	99.75 192	99.39 232

casdiffmvs_mvg		99.12 69	99.16 62	98.99 156	99.43 176	97.73 214	98.00 216	99.62 89	99.22 80	99.55 77	99.22 153	98.93 33	99.75 285	98.66 113	99.81 140	99.50 169
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		98.90 108	99.01 92	98.57 253	99.42 178	96.59 308	98.13 187	99.66 71	99.09 110	99.30 148	99.02 214	98.79 43	99.89 97	97.87 186	99.80 152	99.23 304

test1111		96.49 388	96.82 359	95.52 488	99.42 178	87.08 530	99.22 46	87.14 548	99.11 100	99.46 101	99.58 47	88.69 447	99.86 145	98.80 100	99.95 39	99.62 92

v2v482		98.56 180	98.62 154	98.37 292	99.42 178	95.81 350	97.58 290	99.16 305	97.90 240	99.28 151	99.01 226	95.98 293	99.79 249	99.33 59	99.90 88	99.51 165

OPM-MVS		98.56 180	98.32 214	99.25 104	99.41 181	98.73 95	97.13 347	99.18 298	97.10 327	98.75 271	98.92 252	98.18 118	99.65 367	96.68 311	99.56 293	99.37 244
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS2		98.07 261	98.08 252	98.04 334	99.41 181	94.59 411	94.59 489	99.40 209	97.50 280	98.82 259	98.83 279	96.83 234	99.84 180	97.50 228	99.81 140	99.71 65

E2		98.70 147	98.68 141	98.73 219	99.40 183	97.10 278	97.48 304	99.57 111	98.09 225	99.00 209	99.20 157	97.90 143	99.67 347	97.73 205	99.77 172	99.43 214

E3		98.69 151	98.68 141	98.73 219	99.40 183	97.10 278	97.48 304	99.57 111	98.09 225	99.00 209	99.20 157	97.90 143	99.67 347	97.73 205	99.77 172	99.43 214

ELoFTR		97.81 296	97.74 287	98.04 334	99.39 185	95.79 351	97.28 333	99.58 103	94.13 465	99.38 121	99.37 105	93.31 381	99.60 392	97.23 250	99.96 28	98.74 407

test_one_0601					99.39 185	99.20 38		99.31 246	98.49 180	98.66 286	99.02 214	97.64 168

mvsany_test3		98.87 112	98.92 102	98.74 217	99.38 187	96.94 289	98.58 123	99.10 316	96.49 367	99.96 4	99.81 8	98.18 118	99.45 452	98.97 89	99.79 159	99.83 33

patch_mono-2		98.51 194	98.63 152	98.17 315	99.38 187	94.78 402	97.36 322	99.69 57	98.16 217	98.49 317	99.29 129	97.06 217	99.97 6	98.29 145	99.91 80	99.76 58

test2506		92.39 493	91.89 495	93.89 513	99.38 187	82.28 549	99.32 26	66.03 556	99.08 114	98.77 268	99.57 49	66.26 538	99.84 180	98.71 110	99.95 39	99.54 143

ECVR-MVS		96.42 394	96.61 378	95.85 477	99.38 187	88.18 525	99.22 46	86.00 550	99.08 114	99.36 128	99.57 49	88.47 452	99.82 210	98.52 127	99.95 39	99.54 143

casdiffmvs		98.95 102	99.00 94	98.81 194	99.38 187	97.33 247	97.82 246	99.57 111	99.17 93	99.35 130	99.17 169	98.35 94	99.69 330	98.46 129	99.73 199	99.41 222
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		98.96 101	99.02 90	98.76 211	99.38 187	97.26 259	98.49 140	99.50 149	98.86 142	99.19 176	99.06 201	98.23 110	99.69 330	98.71 110	99.76 188	99.33 268

TranMVSNet+NR-MVSNet		99.17 52	99.07 85	99.46 63	99.37 193	98.87 85	98.39 157	99.42 200	99.42 55	99.36 128	99.06 201	98.38 89	99.95 25	98.34 142	99.90 88	99.57 124

fmvsm_s_conf0.5_n_6		99.08 79	99.21 57	98.69 227	99.36 194	96.51 315	97.62 281	99.68 64	98.43 184	99.85 27	99.10 192	99.12 23	99.88 115	99.77 22	99.92 71	99.67 78

tttt0517		95.64 430	94.98 443	97.64 377	99.36 194	93.81 445	98.72 104	90.47 542	98.08 227	98.67 284	98.34 372	73.88 524	99.92 65	97.77 197	99.51 311	99.20 314

test_part2					99.36 194	99.10 65				99.05 201

v1144		98.60 173	98.66 146	98.41 285	99.36 194	95.90 343	97.58 290	99.34 233	97.51 279	99.27 153	99.15 177	96.34 271	99.80 236	99.47 53	99.93 57	99.51 165

CP-MVS		98.70 147	98.42 191	99.52 44	99.36 194	99.12 62	98.72 104	99.36 221	97.54 277	98.30 336	98.40 364	97.86 150	99.89 97	96.53 332	99.72 208	99.56 130

RoMa-SfM		98.46 199	98.27 222	99.02 151	99.35 199	98.32 133	97.56 292	99.70 54	95.88 399	99.38 121	98.65 325	96.41 263	99.46 449	97.78 194	99.71 217	99.28 287

DKM		98.18 248	97.95 266	98.85 182	99.35 199	98.31 134	96.68 376	99.69 57	96.90 342	98.61 297	98.77 292	94.41 351	98.93 500	97.32 244	99.84 114	99.32 273

diffmvs_AUTHOR		98.50 195	98.59 161	98.23 310	99.35 199	95.48 365	96.61 384	99.60 94	98.37 186	98.90 237	99.00 230	97.37 197	99.76 273	98.22 150	99.85 109	99.46 200

Test_1112_low_res		96.99 366	96.55 382	98.31 298	99.35 199	95.47 368	95.84 443	99.53 136	91.51 506	96.80 451	98.48 356	91.36 423	99.83 198	96.58 321	99.53 305	99.62 92

DeepC-MVS	97.60 4	98.97 99	98.93 101	99.10 130	99.35 199	97.98 177	98.01 214	99.46 175	97.56 272	99.54 79	99.50 68	98.97 29	99.84 180	98.06 164	99.92 71	99.49 177
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
1112_ss		97.29 340	96.86 355	98.58 250	99.34 204	96.32 325	96.75 370	99.58 103	93.14 483	96.89 445	97.48 448	92.11 411	99.86 145	96.91 282	99.54 301	99.57 124

test-260524					99.33 205	99.02 71		99.25 277		99.23 169		96.59 255	99.85 159	98.10 160	99.62 267

reproduce_model		99.15 57	98.97 98	99.67 4	99.33 205	99.44 9	98.15 185	99.47 170	99.12 99	99.52 87	99.32 124	98.31 97	99.90 81	97.78 194	99.73 199	99.66 80

DenseAffine		98.10 256	97.86 278	98.84 188	99.32 207	97.93 185	96.62 383	99.76 39	96.68 359	98.65 287	98.72 303	94.46 349	99.33 471	96.76 299	99.75 192	99.25 298

MVSMamba_PlusPlus		98.83 122	98.98 97	98.36 293	99.32 207	96.58 311	98.90 84	99.41 204	99.75 10	98.72 275	99.50 68	96.17 278	99.94 41	99.27 64	99.78 164	98.57 427

fmvsm_s_conf0.5_n_4		99.01 90	99.22 54	98.38 289	99.31 209	95.48 365	97.56 292	99.73 45	98.87 140	99.75 44	99.27 132	98.80 41	99.86 145	99.80 17	99.90 88	99.81 41

SF-MVS		98.53 189	98.27 222	99.32 91	99.31 209	98.75 91	98.19 179	99.41 204	96.77 353	98.83 256	98.90 258	97.80 155	99.82 210	95.68 382	99.52 308	99.38 241

CPTT-MVS		97.84 292	97.36 320	99.27 99	99.31 209	98.46 117	98.29 167	99.27 269	94.90 441	97.83 381	98.37 368	94.90 331	99.84 180	93.85 438	99.54 301	99.51 165

UnsupCasMVSNet_eth		97.89 280	97.60 304	98.75 213	99.31 209	97.17 273	97.62 281	99.35 227	98.72 157	98.76 270	98.68 316	92.57 401	99.74 292	97.76 201	95.60 530	99.34 262

fmvsm_s_conf0.5_n_7		98.83 122	99.04 87	98.20 312	99.30 213	94.83 400	97.23 335	99.36 221	98.64 161	99.84 30	99.43 88	98.10 127	99.91 74	99.56 41	99.96 28	99.87 22

pmmvs-eth3d		98.47 198	98.34 208	98.86 181	99.30 213	97.76 210	97.16 345	99.28 266	95.54 418	99.42 112	99.19 160	97.27 204	99.63 375	97.89 181	99.97 21	99.20 314

viewcassd2359sk11		98.55 184	98.51 172	98.67 230	99.29 215	96.99 284	97.39 315	99.54 132	97.73 254	98.81 261	99.08 199	97.55 178	99.66 360	97.52 227	99.67 246	99.36 252

SymmetryMVS		98.05 263	97.71 293	99.09 134	99.29 215	97.83 197	98.28 168	97.64 447	99.24 77	98.80 263	98.85 272	89.76 439	99.94 41	98.04 167	99.50 319	99.49 177

Anonymous20231211		99.27 37	99.27 47	99.26 101	99.29 215	98.18 147	99.49 12	99.51 144	99.70 15	99.80 37	99.68 25	96.84 232	99.83 198	99.21 70	99.91 80	99.77 53

viewmanbaseed2359cas		98.58 177	98.54 167	98.70 225	99.28 218	97.13 277	97.47 308	99.55 126	97.55 274	98.96 223	98.92 252	97.77 157	99.59 397	97.59 219	99.77 172	99.39 232

UnsupCasMVSNet_bld		97.30 338	96.92 350	98.45 279	99.28 218	96.78 302	96.20 415	99.27 269	95.42 424	98.28 340	98.30 379	93.16 386	99.71 311	94.99 401	97.37 498	98.87 384

EC-MVSNet		99.09 73	99.05 86	99.20 110	99.28 218	98.93 80	99.24 44	99.84 23	99.08 114	98.12 353	98.37 368	98.72 50	99.90 81	99.05 83	99.77 172	98.77 402

mamba_0408		98.80 129	98.88 108	98.55 260	99.27 221	96.50 316	98.00 216	99.60 94	98.93 132	99.22 171	98.84 277	98.59 67	99.89 97	97.74 203	99.72 208	99.27 291

SSM_04072		98.80 129	98.88 108	98.56 258	99.27 221	96.50 316	98.00 216	99.60 94	98.93 132	99.22 171	98.84 277	98.59 67	99.90 81	97.74 203	99.72 208	99.27 291

SSM_0407		98.86 116	98.96 100	98.55 260	99.27 221	96.50 316	98.04 206	99.66 71	99.09 110	99.22 171	99.02 214	98.79 43	99.87 135	97.87 186	99.72 208	99.27 291

reproduce-ours		99.09 73	98.90 105	99.67 4	99.27 221	99.49 5	98.00 216	99.42 200	99.05 117	99.48 96	99.27 132	98.29 99	99.89 97	97.61 216	99.71 217	99.62 92

our_new_method		99.09 73	98.90 105	99.67 4	99.27 221	99.49 5	98.00 216	99.42 200	99.05 117	99.48 96	99.27 132	98.29 99	99.89 97	97.61 216	99.71 217	99.62 92

DPE-MVS		98.59 175	98.26 225	99.57 21	99.27 221	99.15 52	97.01 350	99.39 211	97.67 259	99.44 107	98.99 232	97.53 182	99.89 97	95.40 393	99.68 240	99.66 80
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
IterMVS-SCA-FT		97.85 291	98.18 238	96.87 431	99.27 221	91.16 499	95.53 453	99.25 277	99.10 107	99.41 114	99.35 112	93.10 389	99.96 13	98.65 114	99.94 51	99.49 177

v1192		98.60 173	98.66 146	98.41 285	99.27 221	95.88 345	97.52 298	99.36 221	97.41 293	99.33 138	99.20 157	96.37 269	99.82 210	99.57 39	99.92 71	99.55 137

N_pmnet		97.63 309	97.17 332	98.99 156	99.27 221	97.86 194	95.98 430	93.41 528	95.25 431	99.47 100	98.90 258	95.63 307	99.85 159	96.91 282	99.73 199	99.27 291

PMatch-SfM		97.89 280	97.64 300	98.66 232	99.26 230	97.44 241	96.08 425	99.51 144	96.72 355	98.47 320	99.13 183	93.62 378	99.70 320	97.14 260	98.80 427	98.83 387

viewdifsd2359ckpt13		98.39 214	98.29 218	98.70 225	99.26 230	97.19 268	97.51 300	99.48 159	96.94 336	98.58 304	98.82 282	97.47 192	99.55 414	97.21 252	99.33 355	99.34 262

FPMVS		93.44 477	92.23 486	97.08 418	99.25 232	97.86 194	95.61 450	97.16 464	92.90 490	93.76 525	98.65 325	75.94 521	95.66 543	79.30 543	97.49 491	97.73 482

aaEdge-Enhanced		98.61 171	98.33 213	99.44 65	99.24 233	98.93 80	97.45 310	99.06 322	98.14 223	99.06 193	98.77 292	96.97 226	99.82 210	96.67 312	99.64 258	99.58 117

new-patchmatchnet		98.35 217	98.74 128	97.18 412	99.24 233	92.23 480	96.42 399	99.48 159	98.30 195	99.69 55	99.53 64	97.44 193	99.82 210	98.84 99	99.77 172	99.49 177

MCST-MVS		98.00 268	97.63 302	99.10 130	99.24 233	98.17 148	96.89 362	98.73 389	95.66 410	97.92 371	97.70 433	97.17 211	99.66 360	96.18 357	99.23 377	99.47 197

UniMVSNet (Re)		98.87 112	98.71 135	99.35 80	99.24 233	98.73 95	97.73 265	99.38 213	98.93 132	99.12 185	98.73 301	96.77 240	99.86 145	98.63 116	99.80 152	99.46 200

jason		97.45 323	97.35 321	97.76 359	99.24 233	93.93 439	95.86 440	98.42 415	94.24 461	98.50 316	98.13 396	94.82 335	99.91 74	97.22 251	99.73 199	99.43 214
jason: jason.
IterMVS		97.73 300	98.11 248	96.57 443	99.24 233	90.28 510	95.52 455	99.21 288	98.86 142	99.33 138	99.33 119	93.11 388	99.94 41	98.49 128	99.94 51	99.48 188
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		98.55 184	98.62 154	98.32 296	99.22 239	95.58 357	97.51 300	99.45 179	97.16 324	99.45 106	99.24 145	96.12 283	99.85 159	99.60 37	99.88 95	99.55 137

ITE_SJBPF				98.87 179	99.22 239	98.48 116		99.35 227	97.50 280	98.28 340	98.60 338	97.64 168	99.35 468	93.86 437	99.27 368	98.79 400

h-mvs33		97.77 298	97.33 323	99.10 130	99.21 241	97.84 196	98.35 162	98.57 403	99.11 100	98.58 304	99.02 214	88.65 450	99.96 13	98.11 158	96.34 516	99.49 177

v144192		98.54 187	98.57 163	98.45 279	99.21 241	95.98 339	97.63 280	99.36 221	97.15 326	99.32 144	99.18 164	95.84 300	99.84 180	99.50 50	99.91 80	99.54 143

APDe-MVS		98.99 94	98.79 124	99.60 16	99.21 241	99.15 52	98.87 89	99.48 159	97.57 270	99.35 130	99.24 145	97.83 151	99.89 97	97.88 184	99.70 228	99.75 62
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS		98.93 104	98.81 123	99.28 96	99.21 241	98.45 118	98.46 145	99.33 239	99.63 28	99.48 96	99.15 177	97.23 207	99.75 285	97.17 255	99.66 254	99.63 91

viewmamba		98.57 178	98.66 146	98.31 298	99.20 245	95.89 344	96.92 360	99.57 111	98.71 158	99.02 207	99.04 210	97.48 190	99.71 311	98.28 146	99.70 228	99.35 258

SR-MVS-dyc-post		98.81 127	98.55 165	99.57 21	99.20 245	99.38 12	98.48 143	99.30 254	98.64 161	98.95 224	98.96 243	97.49 189	99.86 145	96.56 327	99.39 344	99.45 206

RE-MVS-def			98.58 162		99.20 245	99.38 12	98.48 143	99.30 254	98.64 161	98.95 224	98.96 243	97.75 159		96.56 327	99.39 344	99.45 206

v1921920		98.54 187	98.60 159	98.38 289	99.20 245	95.76 353	97.56 292	99.36 221	97.23 318	99.38 121	99.17 169	96.02 286	99.84 180	99.57 39	99.90 88	99.54 143

E3new		98.41 204	98.34 208	98.62 242	99.19 249	96.90 292	97.32 325	99.50 149	97.40 295	98.63 291	98.92 252	97.21 209	99.65 367	97.34 240	99.52 308	99.31 278

thisisatest0530		95.27 443	94.45 455	97.74 362	99.19 249	94.37 415	97.86 242	90.20 543	97.17 323	98.22 343	97.65 435	73.53 525	99.90 81	96.90 287	99.35 351	98.95 368

Anonymous20240529		98.93 104	98.87 111	99.12 126	99.19 249	98.22 145	99.01 71	98.99 340	99.25 76	99.54 79	99.37 105	97.04 218	99.80 236	97.89 181	99.52 308	99.35 258

APD-MVS_3200maxsize		98.84 119	98.61 158	99.53 38	99.19 249	99.27 26	98.49 140	99.33 239	98.64 161	99.03 206	98.98 237	97.89 147	99.85 159	96.54 331	99.42 340	99.46 200

HQP_MVS		97.99 271	97.67 295	98.93 170	99.19 249	97.65 221	97.77 255	99.27 269	98.20 210	97.79 384	97.98 411	94.90 331	99.70 320	94.42 419	99.51 311	99.45 206

plane_prior7					99.19 249	97.87 193

ab-mvs		98.41 204	98.36 204	98.59 249	99.19 249	97.23 261	99.32 26	98.81 374	97.66 260	98.62 295	99.40 98	96.82 235	99.80 236	95.88 369	99.51 311	98.75 405

F-COLMAP		97.30 338	96.68 369	99.14 124	99.19 249	98.39 123	97.27 334	99.30 254	92.93 488	96.62 460	98.00 409	95.73 303	99.68 342	92.62 475	98.46 453	99.35 258

viewdifsd2359ckpt09		98.13 255	97.92 272	98.77 209	99.18 257	97.35 245	97.29 329	99.53 136	95.81 405	98.09 356	98.47 357	96.34 271	99.66 360	97.02 270	99.51 311	99.29 284

SR-MVS		98.71 142	98.43 189	99.57 21	99.18 257	99.35 16	98.36 160	99.29 262	98.29 198	98.88 244	98.85 272	97.53 182	99.87 135	96.14 359	99.31 360	99.48 188

UniMVSNet_NR-MVSNet		98.86 116	98.68 141	99.40 71	99.17 259	98.74 92	97.68 270	99.40 209	99.14 98	99.06 193	98.59 339	96.71 247	99.93 53	98.57 121	99.77 172	99.53 157

LF4IMVS		97.90 278	97.69 294	98.52 269	99.17 259	97.66 219	97.19 344	99.47 170	96.31 376	97.85 380	98.20 391	96.71 247	99.52 427	94.62 411	99.72 208	98.38 444

SMA-MVS		98.40 207	98.03 257	99.51 49	99.16 261	99.21 32	98.05 204	99.22 286	94.16 464	98.98 214	99.10 192	97.52 184	99.79 249	96.45 337	99.64 258	99.53 157
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		98.82 125	98.63 152	99.39 72	99.16 261	98.74 92	97.54 296	99.25 277	98.84 148	99.06 193	98.76 297	96.76 242	99.93 53	98.57 121	99.77 172	99.50 169

NR-MVSNet		98.95 102	98.82 121	99.36 74	99.16 261	98.72 97	99.22 46	99.20 290	99.10 107	99.72 47	98.76 297	96.38 267	99.86 145	98.00 172	99.82 133	99.50 169

MVS_111021_LR		98.30 228	98.12 247	98.83 190	99.16 261	98.03 170	96.09 424	99.30 254	97.58 269	98.10 355	98.24 387	98.25 107	99.34 469	96.69 310	99.65 256	99.12 340

dtuplus		98.32 223	98.39 196	98.10 323	99.15 265	95.29 378	96.68 376	99.51 144	97.32 303	99.18 181	99.15 177	97.61 172	99.62 380	97.19 253	99.74 195	99.38 241

DSMNet-mixed		97.42 326	97.60 304	96.87 431	99.15 265	91.46 488	98.54 128	99.12 313	92.87 491	97.58 398	99.63 39	96.21 277	99.90 81	95.74 378	99.54 301	99.27 291

hybridnocas07		98.32 223	98.37 202	98.17 315	99.14 267	95.51 360	96.67 378	99.56 121	97.85 244	98.75 271	98.95 247	96.65 251	99.63 375	98.00 172	99.78 164	99.37 244

D2MVS		97.84 292	97.84 280	97.83 351	99.14 267	94.74 404	96.94 356	98.88 358	95.84 401	98.89 240	98.96 243	94.40 353	99.69 330	97.55 222	99.95 39	99.05 346

pmmvs5		97.64 308	97.49 311	98.08 328	99.14 267	95.12 388	96.70 374	99.05 326	93.77 474	98.62 295	98.83 279	93.23 384	99.75 285	98.33 144	99.76 188	99.36 252

hybrid		98.22 240	98.27 222	98.08 328	99.13 270	95.24 380	96.61 384	99.53 136	97.43 292	98.46 321	98.97 239	96.75 245	99.65 367	97.84 189	99.69 234	99.35 258

SPE-MVS-test		99.13 66	99.09 82	99.26 101	99.13 270	98.97 74	99.31 30	99.88 15	99.44 52	98.16 348	98.51 349	98.64 61	99.93 53	98.91 93	99.85 109	98.88 383

VDD-MVS		98.56 180	98.39 196	99.07 138	99.13 270	98.07 165	98.59 122	97.01 467	99.59 36	99.11 186	99.27 132	94.82 335	99.79 249	98.34 142	99.63 263	99.34 262

save fliter					99.11 273	97.97 178	96.53 390	99.02 334	98.24 201

APD-MVS		98.10 256	97.67 295	99.42 67	99.11 273	98.93 80	97.76 258	99.28 266	94.97 439	98.72 275	98.77 292	97.04 218	99.85 159	93.79 439	99.54 301	99.49 177
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EI-MVSNet-UG-set		98.69 151	98.71 135	98.62 242	99.10 275	96.37 323	97.23 335	98.87 360	99.20 84	99.19 176	98.99 232	97.30 201	99.85 159	98.77 105	99.79 159	99.65 85

EI-MVSNet		98.40 207	98.51 172	98.04 334	99.10 275	94.73 405	97.20 340	98.87 360	98.97 127	99.06 193	99.02 214	96.00 288	99.80 236	98.58 119	99.82 133	99.60 102

CVMVSNet		96.25 404	97.21 331	93.38 521	99.10 275	80.56 553	97.20 340	98.19 428	96.94 336	99.00 209	99.02 214	89.50 443	99.80 236	96.36 344	99.59 280	99.78 50

EI-MVSNet-Vis-set		98.68 157	98.70 138	98.63 240	99.09 278	96.40 322	97.23 335	98.86 365	99.20 84	99.18 181	98.97 239	97.29 203	99.85 159	98.72 109	99.78 164	99.64 86

HPM-MVS++		98.10 256	97.64 300	99.48 57	99.09 278	99.13 60	97.52 298	98.75 386	97.46 288	96.90 444	97.83 424	96.01 287	99.84 180	95.82 376	99.35 351	99.46 200

DP-MVS Recon		97.33 335	96.92 350	98.57 253	99.09 278	97.99 174	96.79 365	99.35 227	93.18 482	97.71 388	98.07 404	95.00 330	99.31 474	93.97 432	99.13 394	98.42 441

MVS_111021_HR		98.25 238	98.08 252	98.75 213	99.09 278	97.46 238	95.97 431	99.27 269	97.60 268	97.99 366	98.25 385	98.15 124	99.38 464	96.87 290	99.57 289	99.42 219

BP-MVS1		97.40 328	96.97 346	98.71 223	99.07 282	96.81 298	98.34 164	97.18 462	98.58 172	98.17 345	98.61 336	84.01 490	99.94 41	98.97 89	99.78 164	99.37 244

9.14			97.78 284		99.07 282		97.53 297	99.32 241	95.53 419	98.54 312	98.70 312	97.58 175	99.76 273	94.32 424	99.46 326

PAPM_NR		96.82 374	96.32 393	98.30 300	99.07 282	96.69 306	97.48 304	98.76 382	95.81 405	96.61 461	96.47 479	94.12 366	99.17 487	90.82 510	97.78 483	99.06 345

TAMVS		98.24 239	98.05 255	98.80 197	99.07 282	97.18 271	97.88 238	98.81 374	96.66 360	99.17 184	99.21 155	94.81 338	99.77 267	96.96 279	99.88 95	99.44 210

CLD-MVS		97.49 319	97.16 333	98.48 276	99.07 282	97.03 282	94.71 480	99.21 288	94.46 453	98.06 359	97.16 463	97.57 176	99.48 442	94.46 416	99.78 164	98.95 368
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 66	99.10 80	99.24 106	99.06 287	99.15 52	99.36 22	99.88 15	99.36 63	98.21 344	98.46 358	98.68 58	99.93 53	99.03 85	99.85 109	98.64 420

thres100view900		94.19 463	93.67 467	95.75 480	99.06 287	91.35 492	98.03 208	94.24 521	98.33 191	97.40 416	94.98 512	79.84 506	99.62 380	83.05 536	98.08 473	96.29 515

thres600view7		94.45 457	93.83 464	96.29 453	99.06 287	91.53 487	97.99 223	94.24 521	98.34 189	97.44 414	95.01 510	79.84 506	99.67 347	84.33 533	98.23 462	97.66 485

onestephybrid01		98.40 207	98.39 196	98.42 283	99.05 290	96.23 328	96.73 372	99.41 204	98.18 213	98.65 287	99.02 214	97.02 221	99.69 330	97.73 205	99.70 228	99.33 268

plane_prior1					99.05 290

YYNet1		97.60 310	97.67 295	97.39 403	99.04 292	93.04 463	95.27 464	98.38 418	97.25 312	98.92 235	98.95 247	95.48 315	99.73 299	96.99 274	98.74 431	99.41 222

MDA-MVSNet_test_wron		97.60 310	97.66 298	97.41 402	99.04 292	93.09 459	95.27 464	98.42 415	97.26 311	98.88 244	98.95 247	95.43 317	99.73 299	97.02 270	98.72 433	99.41 222

MIMVSNet		96.62 381	96.25 398	97.71 366	99.04 292	94.66 408	99.16 55	96.92 475	97.23 318	97.87 376	99.10 192	86.11 468	99.65 367	91.65 492	99.21 381	98.82 389

PMatch-Up-SfM		97.79 297	97.48 314	98.72 221	99.03 295	97.78 207	96.05 427	99.48 159	96.90 342	98.72 275	99.18 164	92.00 413	99.71 311	97.15 259	98.77 428	98.69 413

usedtu_dtu_shiyan1		97.37 330	97.13 337	98.11 321	99.03 295	95.40 371	94.47 492	98.99 340	96.87 345	97.97 367	97.81 425	92.12 409	99.75 285	97.49 233	99.43 338	99.16 334

FE-MVSNET3		97.37 330	97.13 337	98.11 321	99.03 295	95.40 371	94.47 492	98.99 340	96.87 345	97.97 367	97.81 425	92.12 409	99.75 285	97.49 233	99.43 338	99.16 334

icg_test_0407_2		98.20 245	98.38 200	97.65 374	99.03 295	94.03 430	95.78 445	99.45 179	98.16 217	99.06 193	98.71 305	98.27 103	99.68 342	97.50 228	99.45 328	99.22 309

IMVS_0407		98.39 214	98.64 150	97.66 372	99.03 295	94.03 430	98.10 194	99.45 179	98.16 217	99.06 193	98.71 305	98.27 103	99.71 311	97.50 228	99.45 328	99.22 309

IMVS_0404		98.07 261	98.20 232	97.69 367	99.03 295	94.03 430	96.67 378	99.45 179	98.16 217	98.03 363	98.71 305	96.80 238	99.82 210	97.50 228	99.45 328	99.22 309

IMVS_0403		98.34 218	98.56 164	97.66 372	99.03 295	94.03 430	97.98 224	99.45 179	98.16 217	98.89 240	98.71 305	97.90 143	99.74 292	97.50 228	99.45 328	99.22 309

PatchMatch-RL		97.24 344	96.78 362	98.61 246	99.03 295	97.83 197	96.36 403	99.06 322	93.49 479	97.36 420	97.78 427	95.75 302	99.49 438	93.44 452	98.77 428	98.52 429

ArgMatch-SfM		97.96 274	97.72 291	98.66 232	99.02 303	97.33 247	96.49 393	99.52 142	95.46 422	98.71 279	98.29 382	96.14 279	99.69 330	96.30 348	99.56 293	98.97 364

viewmambaseed2359dif		98.19 246	98.26 225	97.99 339	99.02 303	95.03 391	96.59 387	99.53 136	96.21 380	99.00 209	98.99 232	97.62 170	99.61 388	97.62 215	99.72 208	99.33 268

GDP-MVS		97.50 316	97.11 339	98.67 230	99.02 303	96.85 296	98.16 184	99.71 48	98.32 193	98.52 315	98.54 344	83.39 494	99.95 25	98.79 101	99.56 293	99.19 320

ZD-MVS					99.01 306	98.84 86		99.07 321	94.10 467	98.05 361	98.12 398	96.36 270	99.86 145	92.70 474	99.19 386

CDPH-MVS		97.26 341	96.66 373	99.07 138	99.00 307	98.15 149	96.03 428	99.01 337	91.21 510	97.79 384	97.85 422	96.89 230	99.69 330	92.75 472	99.38 347	99.39 232

diffmvs		98.22 240	98.24 229	98.17 315	99.00 307	95.44 369	96.38 401	99.58 103	97.79 250	98.53 313	98.50 353	96.76 242	99.74 292	97.95 179	99.64 258	99.34 262
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		98.40 207	98.19 236	99.03 148	99.00 307	97.65 221	96.85 363	98.94 344	98.57 174	98.89 240	98.50 353	95.60 309	99.85 159	97.54 224	99.85 109	99.59 109

plane_prior6					98.99 310	97.70 217						94.90 331

ArgMatch-Sym		97.83 294	97.54 306	98.71 223	98.98 311	97.65 221	96.25 413	99.43 193	95.60 413	98.85 251	97.98 411	95.72 304	99.56 409	95.54 390	99.50 319	98.92 374

xiu_mvs_v1_base_debu		97.86 286	98.17 239	96.92 428	98.98 311	93.91 440	96.45 395	99.17 302	97.85 244	98.41 327	97.14 465	98.47 77	99.92 65	98.02 169	99.05 400	96.92 503

xiu_mvs_v1_base		97.86 286	98.17 239	96.92 428	98.98 311	93.91 440	96.45 395	99.17 302	97.85 244	98.41 327	97.14 465	98.47 77	99.92 65	98.02 169	99.05 400	96.92 503

xiu_mvs_v1_base_debi		97.86 286	98.17 239	96.92 428	98.98 311	93.91 440	96.45 395	99.17 302	97.85 244	98.41 327	97.14 465	98.47 77	99.92 65	98.02 169	99.05 400	96.92 503

MVP-Stereo		98.08 260	97.92 272	98.57 253	98.96 315	96.79 299	97.90 236	99.18 298	96.41 372	98.46 321	98.95 247	95.93 297	99.60 392	96.51 333	98.98 415	99.31 278
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 207	98.68 141	97.54 390	98.96 315	97.99 174	97.88 238	99.36 221	98.20 210	99.63 66	99.04 210	98.76 46	95.33 545	96.56 327	99.74 195	99.31 278
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				98.91 175	98.94 317	97.76 210		98.76 382	87.58 534	96.75 453	98.10 400	94.80 339	99.78 261	92.73 473	99.00 410	99.20 314

USDC		97.41 327	97.40 316	97.44 400	98.94 317	93.67 450	95.17 468	99.53 136	94.03 470	98.97 218	99.10 192	95.29 320	99.34 469	95.84 375	99.73 199	99.30 282

tfpn200view9		94.03 467	93.44 469	95.78 479	98.93 319	91.44 490	97.60 287	94.29 518	97.94 236	97.10 428	94.31 520	79.67 508	99.62 380	83.05 536	98.08 473	96.29 515

testdata				98.09 325	98.93 319	95.40 371		98.80 376	90.08 519	97.45 412	98.37 368	95.26 321	99.70 320	93.58 446	98.95 418	99.17 328

thres400		94.14 465	93.44 469	96.24 456	98.93 319	91.44 490	97.60 287	94.29 518	97.94 236	97.10 428	94.31 520	79.67 508	99.62 380	83.05 536	98.08 473	97.66 485

TAPA-MVS	96.21 11	96.63 380	95.95 403	98.65 234	98.93 319	98.09 158	96.93 358	99.28 266	83.58 540	98.13 352	97.78 427	96.13 281	99.40 460	93.52 448	99.29 366	98.45 434
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.92 323	96.93 290	95.54 452	98.78 379	85.72 537	96.86 448	98.11 399	94.43 350			99.10 399	99.23 304

PVSNet_BlendedMVS		97.55 315	97.53 308	97.60 381	98.92 323	93.77 447	96.64 381	99.43 193	94.49 451	97.62 394	99.18 164	96.82 235	99.67 347	94.73 408	99.93 57	99.36 252

PVSNet_Blended		96.88 369	96.68 369	97.47 398	98.92 323	93.77 447	94.71 480	99.43 193	90.98 513	97.62 394	97.36 457	96.82 235	99.67 347	94.73 408	99.56 293	98.98 360

MSDG		97.71 302	97.52 309	98.28 302	98.91 326	96.82 297	94.42 494	99.37 217	97.65 261	98.37 333	98.29 382	97.40 195	99.33 471	94.09 430	99.22 378	98.68 417

Anonymous202405211		97.90 278	97.50 310	99.08 136	98.90 327	98.25 139	98.53 129	96.16 490	98.87 140	99.11 186	98.86 269	90.40 434	99.78 261	97.36 239	99.31 360	99.19 320

原ACMM1				98.35 294	98.90 327	96.25 327		98.83 373	92.48 495	96.07 480	98.10 400	95.39 318	99.71 311	92.61 476	98.99 412	99.08 342

GBi-Net		98.65 163	98.47 183	99.17 115	98.90 327	98.24 140	99.20 49	99.44 187	98.59 169	98.95 224	99.55 56	94.14 363	99.86 145	97.77 197	99.69 234	99.41 222

test1		98.65 163	98.47 183	99.17 115	98.90 327	98.24 140	99.20 49	99.44 187	98.59 169	98.95 224	99.55 56	94.14 363	99.86 145	97.77 197	99.69 234	99.41 222

FMVSNet2		98.49 196	98.40 193	98.75 213	98.90 327	97.14 276	98.61 120	99.13 312	98.59 169	99.19 176	99.28 130	94.14 363	99.82 210	97.97 177	99.80 152	99.29 284

OMC-MVS		97.88 283	97.49 311	99.04 147	98.89 332	98.63 101	96.94 356	99.25 277	95.02 437	98.53 313	98.51 349	97.27 204	99.47 445	93.50 450	99.51 311	99.01 355

VortexMVS		97.98 272	98.31 215	97.02 421	98.88 333	91.45 489	98.03 208	99.47 170	98.65 160	99.55 77	99.47 78	91.49 421	99.81 227	99.32 60	99.91 80	99.80 45

MVSFormer		98.26 235	98.43 189	97.77 356	98.88 333	93.89 443	99.39 20	99.56 121	99.11 100	98.16 348	98.13 396	93.81 372	99.97 6	99.26 65	99.57 289	99.43 214

lupinMVS		97.06 359	96.86 355	97.65 374	98.88 333	93.89 443	95.48 456	97.97 435	93.53 477	98.16 348	97.58 439	93.81 372	99.91 74	96.77 298	99.57 289	99.17 328

dmvs_re		95.98 416	95.39 427	97.74 362	98.86 336	97.45 239	98.37 159	95.69 504	97.95 234	96.56 463	95.95 489	90.70 431	97.68 525	88.32 521	96.13 520	98.11 458

DELS-MVS		98.27 233	98.20 232	98.48 276	98.86 336	96.70 305	95.60 451	99.20 290	97.73 254	98.45 323	98.71 305	97.50 186	99.82 210	98.21 151	99.59 280	98.93 373
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		97.89 280	97.98 262	97.60 381	98.86 336	94.35 416	96.21 414	99.44 187	97.45 290	99.06 193	98.88 266	97.99 137	99.28 480	94.38 423	99.58 285	99.18 324

LCM-MVSNet-Re		98.64 165	98.48 181	99.11 128	98.85 339	98.51 114	98.49 140	99.83 26	98.37 186	99.69 55	99.46 80	98.21 115	99.92 65	94.13 429	99.30 364	98.91 378

pmmvs4		97.58 313	97.28 324	98.51 270	98.84 340	96.93 290	95.40 460	98.52 409	93.60 476	98.61 297	98.65 325	95.10 327	99.60 392	96.97 278	99.79 159	98.99 359

NP-MVS					98.84 340	97.39 244					96.84 469

sss		97.21 347	96.93 348	98.06 331	98.83 342	95.22 384	96.75 370	98.48 411	94.49 451	97.27 422	97.90 418	92.77 397	99.80 236	96.57 323	99.32 358	99.16 334

PVSNet	93.40 17	95.67 428	95.70 410	95.57 486	98.83 342	88.57 521	92.50 530	97.72 440	92.69 493	96.49 472	96.44 480	93.72 375	99.43 456	93.61 443	99.28 367	98.71 409

MVE	83.40 22	92.50 492	91.92 494	94.25 506	98.83 342	91.64 485	92.71 528	83.52 552	95.92 397	86.46 546	95.46 503	95.20 322	95.40 544	80.51 541	98.64 442	95.73 523
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testing3-2		93.78 471	93.91 462	93.39 520	98.82 345	81.72 551	97.76 258	95.28 507	98.60 168	96.54 464	96.66 474	65.85 541	99.62 380	96.65 316	98.99 412	98.82 389

ambc				98.24 307	98.82 345	95.97 341	98.62 118	99.00 339		99.27 153	99.21 155	96.99 224	99.50 434	96.55 330	99.50 319	99.26 297

旧先验1					98.82 345	97.45 239		98.76 382			98.34 372	95.50 314			99.01 409	99.23 304

test_vis1_rt		97.75 299	97.72 291	97.83 351	98.81 348	96.35 324	97.30 328	99.69 57	94.61 449	97.87 376	98.05 405	96.26 275	98.32 514	98.74 107	98.18 465	98.82 389

WTY-MVS		96.67 378	96.27 397	97.87 349	98.81 348	94.61 410	96.77 368	97.92 437	94.94 440	97.12 427	97.74 430	91.11 426	99.82 210	93.89 435	98.15 469	99.18 324

3Dnovator+	97.89 3	98.69 151	98.51 172	99.24 106	98.81 348	98.40 121	99.02 70	99.19 294	98.99 124	98.07 358	99.28 130	97.11 216	99.84 180	96.84 293	99.32 358	99.47 197

dtuonly		96.49 388	97.28 324	94.10 509	98.80 351	83.27 545	93.66 517	99.48 159	95.10 435	97.87 376	98.30 379	95.61 308	99.68 342	96.98 277	99.75 192	99.33 268

LoFTR		97.97 273	97.79 283	98.53 267	98.80 351	97.47 236	97.01 350	99.55 126	95.55 416	99.46 101	99.22 153	94.22 361	99.44 454	96.45 337	99.82 133	98.68 417

QAPM		97.31 336	96.81 361	98.82 192	98.80 351	97.49 232	99.06 66	99.19 294	90.22 517	97.69 390	99.16 171	96.91 229	99.90 81	90.89 508	99.41 341	99.07 344

VNet		98.42 203	98.30 216	98.79 201	98.79 354	97.29 256	98.23 174	98.66 394	99.31 69	98.85 251	98.80 286	94.80 339	99.78 261	98.13 156	99.13 394	99.31 278

DPM-MVS		96.32 398	95.59 417	98.51 270	98.76 355	97.21 266	94.54 491	98.26 422	91.94 501	96.37 473	97.25 461	93.06 391	99.43 456	91.42 497	98.74 431	98.89 380

3Dnovator	98.27 2	98.81 127	98.73 130	99.05 145	98.76 355	97.81 205	99.25 43	99.30 254	98.57 174	98.55 310	99.33 119	97.95 140	99.90 81	97.16 256	99.67 246	99.44 210

PLC	94.65 16	96.51 385	95.73 409	98.85 182	98.75 357	97.91 188	96.42 399	99.06 322	90.94 514	95.59 489	97.38 455	94.41 351	99.59 397	90.93 506	98.04 478	99.05 346
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
BH-untuned		96.83 372	96.75 365	97.08 418	98.74 358	93.33 457	96.71 373	98.26 422	96.72 355	98.44 324	97.37 456	95.20 322	99.47 445	91.89 487	97.43 495	98.44 437

hse-mvs2		97.46 321	97.07 340	98.64 236	98.73 359	97.33 247	97.45 310	97.64 447	99.11 100	98.58 304	97.98 411	88.65 450	99.79 249	98.11 158	97.39 497	98.81 394

CDS-MVSNet		97.69 304	97.35 321	98.69 227	98.73 359	97.02 283	96.92 360	98.75 386	95.89 398	98.59 302	98.67 318	92.08 412	99.74 292	96.72 305	99.81 140	99.32 273
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SD_0403		96.28 401	95.83 405	97.64 377	98.72 361	94.30 417	98.87 89	98.77 380	97.80 248	96.53 465	98.02 408	97.34 199	99.47 445	76.93 545	99.48 324	99.16 334

EIA-MVS		98.00 268	97.74 287	98.80 197	98.72 361	98.09 158	98.05 204	99.60 94	97.39 296	96.63 459	95.55 498	97.68 162	99.80 236	96.73 304	99.27 368	98.52 429

LFMVS		97.20 348	96.72 366	98.64 236	98.72 361	96.95 288	98.93 82	94.14 523	99.74 12	98.78 265	99.01 226	84.45 485	99.73 299	97.44 235	99.27 368	99.25 298

new_pmnet		96.99 366	96.76 363	97.67 370	98.72 361	94.89 397	95.95 435	98.20 426	92.62 494	98.55 310	98.54 344	94.88 334	99.52 427	93.96 433	99.44 336	98.59 426

Fast-Effi-MVS+		97.67 306	97.38 318	98.57 253	98.71 365	97.43 242	97.23 335	99.45 179	94.82 444	96.13 477	96.51 476	98.52 75	99.91 74	96.19 355	98.83 424	98.37 446

TEST9					98.71 365	98.08 162	95.96 433	99.03 331	91.40 507	95.85 485	97.53 442	96.52 258	99.76 273

train_agg		97.10 354	96.45 389	99.07 138	98.71 365	98.08 162	95.96 433	99.03 331	91.64 502	95.85 485	97.53 442	96.47 260	99.76 273	93.67 442	99.16 389	99.36 252

TSAR-MVS + GP.		98.18 248	97.98 262	98.77 209	98.71 365	97.88 192	96.32 406	98.66 394	96.33 374	99.23 169	98.51 349	97.48 190	99.40 460	97.16 256	99.46 326	99.02 353

FA-MVS(test-final)		96.99 366	96.82 359	97.50 394	98.70 369	94.78 402	99.34 23	96.99 468	95.07 436	98.48 319	99.33 119	88.41 453	99.65 367	96.13 361	98.92 421	98.07 461

AUN-MVS		96.24 406	95.45 423	98.60 248	98.70 369	97.22 264	97.38 317	97.65 445	95.95 396	95.53 496	97.96 416	82.11 502	99.79 249	96.31 346	97.44 494	98.80 399

our_test_3		97.39 329	97.73 290	96.34 451	98.70 369	89.78 516	94.61 488	98.97 343	96.50 366	99.04 203	98.85 272	95.98 293	99.84 180	97.26 248	99.67 246	99.41 222

ppachtmachnet_test		97.50 316	97.74 287	96.78 437	98.70 369	91.23 498	94.55 490	99.05 326	96.36 373	99.21 174	98.79 288	96.39 265	99.78 261	96.74 302	99.82 133	99.34 262

PCF-MVS	92.86 18	94.36 458	93.00 477	98.42 283	98.70 369	97.56 228	93.16 527	99.11 315	79.59 544	97.55 401	97.43 452	92.19 407	99.73 299	79.85 542	99.45 328	97.97 467
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ttmdpeth		97.91 277	98.02 258	97.58 383	98.69 374	94.10 426	98.13 187	98.90 354	97.95 234	97.32 421	99.58 47	95.95 296	98.75 507	96.41 340	99.22 378	99.87 22

ETV-MVS		98.03 264	97.86 278	98.56 258	98.69 374	98.07 165	97.51 300	99.50 149	98.10 224	97.50 406	95.51 499	98.41 85	99.88 115	96.27 351	99.24 374	97.71 484

test_prior				98.95 166	98.69 374	97.95 182		99.03 331					99.59 397			99.30 282

mvsmamba		97.57 314	97.26 326	98.51 270	98.69 374	96.73 304	98.74 99	97.25 459	97.03 332	97.88 375	99.23 151	90.95 427	99.87 135	96.61 319	99.00 410	98.91 378

agg_prior					98.68 378	97.99 174		99.01 337		95.59 489			99.77 267

test_8					98.67 379	98.01 171	95.91 439	99.02 334	91.64 502	95.79 488	97.50 446	96.47 260	99.76 273

HQP-NCC					98.67 379		96.29 408		96.05 388	95.55 492

ACMP_Plane					98.67 379		96.29 408		96.05 388	95.55 492

CNVR-MVS		98.17 251	97.87 277	99.07 138	98.67 379	98.24 140	97.01 350	98.93 347	97.25 312	97.62 394	98.34 372	97.27 204	99.57 406	96.42 339	99.33 355	99.39 232

HQP-MVS		97.00 365	96.49 385	98.55 260	98.67 379	96.79 299	96.29 408	99.04 329	96.05 388	95.55 492	96.84 469	93.84 370	99.54 420	92.82 468	99.26 372	99.32 273

MM		98.22 240	97.99 261	98.91 175	98.66 384	96.97 285	97.89 237	94.44 515	99.54 40	98.95 224	99.14 181	93.50 379	99.92 65	99.80 17	99.96 28	99.85 30

test_fmvs1		97.72 301	97.94 269	97.07 420	98.66 384	92.39 475	97.68 270	99.81 32	95.20 434	99.54 79	99.44 85	91.56 419	99.41 459	99.78 21	99.77 172	99.40 231

BridgeMVS		98.63 167	98.72 132	98.38 289	98.66 384	96.68 307	98.90 84	99.42 200	98.99 124	98.97 218	99.19 160	95.81 301	99.85 159	98.77 105	99.77 172	98.60 423

thres200		93.72 473	93.14 475	95.46 491	98.66 384	91.29 494	96.61 384	94.63 513	97.39 296	96.83 449	93.71 523	79.88 505	99.56 409	82.40 539	98.13 470	95.54 524

wuyk23d		96.06 409	97.62 303	91.38 525	98.65 388	98.57 108	98.85 93	96.95 472	96.86 348	99.90 14	99.16 171	99.18 19	98.40 513	89.23 519	99.77 172	77.18 548

NCCC		97.86 286	97.47 315	99.05 145	98.61 389	98.07 165	96.98 353	98.90 354	97.63 262	97.04 434	97.93 417	95.99 292	99.66 360	95.31 394	98.82 426	99.43 214

DeepC-MVS_fast	96.85 6	98.30 228	98.15 244	98.75 213	98.61 389	97.23 261	97.76 258	99.09 318	97.31 305	98.75 271	98.66 322	97.56 177	99.64 372	96.10 363	99.55 298	99.39 232
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing3		93.51 475	92.09 488	97.75 360	98.60 391	94.40 414	97.32 325	95.26 508	97.56 272	96.79 452	95.50 500	53.57 553	99.77 267	95.26 396	98.97 416	99.08 342

thisisatest0515		94.12 466	93.16 474	96.97 425	98.60 391	92.90 465	93.77 515	90.61 541	94.10 467	96.91 441	95.87 492	74.99 522	99.80 236	94.52 414	99.12 397	98.20 453

GA-MVS		95.86 422	95.32 432	97.49 395	98.60 391	94.15 423	93.83 514	97.93 436	95.49 420	96.68 457	97.42 453	83.21 495	99.30 476	96.22 353	98.55 450	99.01 355

dmvs_testset		92.94 487	92.21 487	95.13 497	98.59 394	90.99 502	97.65 276	92.09 534	96.95 335	94.00 521	93.55 524	92.34 405	96.97 535	72.20 546	92.52 540	97.43 494

OPU-MVS				98.82 192	98.59 394	98.30 135	98.10 194				98.52 348	98.18 118	98.75 507	94.62 411	99.48 324	99.41 222

MSLP-MVS++		98.02 265	98.14 246	97.64 377	98.58 396	95.19 385	97.48 304	99.23 285	97.47 283	97.90 373	98.62 334	97.04 218	98.81 505	97.55 222	99.41 341	98.94 372

test12				98.93 170	98.58 396	97.83 197		98.66 394		96.53 465		95.51 313	99.69 330		99.13 394	99.27 291

CL-MVSNet_self_test		97.44 324	97.22 330	98.08 328	98.57 398	95.78 352	94.30 498	98.79 377	96.58 363	98.60 300	98.19 392	94.74 342	99.64 372	96.41 340	98.84 423	98.82 389

PS-MVSNAJ		97.08 357	97.39 317	96.16 464	98.56 399	92.46 473	95.24 466	98.85 368	97.25 312	97.49 407	95.99 488	98.07 128	99.90 81	96.37 342	98.67 441	96.12 520

CNLPA		97.17 351	96.71 367	98.55 260	98.56 399	98.05 169	96.33 405	98.93 347	96.91 341	97.06 432	97.39 454	94.38 354	99.45 452	91.66 491	99.18 388	98.14 457

xiu_mvs_v2_base		97.16 352	97.49 311	96.17 462	98.54 401	92.46 473	95.45 457	98.84 369	97.25 312	97.48 408	96.49 477	98.31 97	99.90 81	96.34 345	98.68 440	96.15 519

alignmvs		97.35 333	96.88 354	98.78 204	98.54 401	98.09 158	97.71 266	97.69 442	99.20 84	97.59 397	95.90 491	88.12 456	99.55 414	98.18 153	98.96 417	98.70 412

FE-MVS		95.66 429	94.95 445	97.77 356	98.53 403	95.28 379	99.40 19	96.09 494	93.11 484	97.96 369	99.26 138	79.10 512	99.77 267	92.40 481	98.71 435	98.27 451

Effi-MVS+		98.02 265	97.82 281	98.62 242	98.53 403	97.19 268	97.33 324	99.68 64	97.30 306	96.68 457	97.46 451	98.56 73	99.80 236	96.63 317	98.20 464	98.86 385

baseline1		95.96 419	95.44 424	97.52 392	98.51 405	93.99 437	98.39 157	96.09 494	98.21 206	98.40 332	97.76 429	86.88 460	99.63 375	95.42 392	89.27 543	98.95 368

MVS_Test		98.18 248	98.36 204	97.67 370	98.48 406	94.73 405	98.18 180	99.02 334	97.69 257	98.04 362	99.11 189	97.22 208	99.56 409	98.57 121	98.90 422	98.71 409

MGCFI-Net		98.34 218	98.28 219	98.51 270	98.47 407	97.59 227	98.96 78	99.48 159	99.18 92	97.40 416	95.50 500	98.66 59	99.50 434	98.18 153	98.71 435	98.44 437

BH-RMVSNet		96.83 372	96.58 381	97.58 383	98.47 407	94.05 427	96.67 378	97.36 452	96.70 358	97.87 376	97.98 411	95.14 326	99.44 454	90.47 512	98.58 448	99.25 298

sasdasda		98.34 218	98.26 225	98.58 250	98.46 409	97.82 202	98.96 78	99.46 175	99.19 89	97.46 409	95.46 503	98.59 67	99.46 449	98.08 162	98.71 435	98.46 431

canonicalmvs		98.34 218	98.26 225	98.58 250	98.46 409	97.82 202	98.96 78	99.46 175	99.19 89	97.46 409	95.46 503	98.59 67	99.46 449	98.08 162	98.71 435	98.46 431

MVS-HIRNet		94.32 459	95.62 413	90.42 528	98.46 409	75.36 554	96.29 408	89.13 545	95.25 431	95.38 498	99.75 16	92.88 394	99.19 486	94.07 431	99.39 344	96.72 510

MatchFormer		97.07 358	96.92 350	97.49 395	98.44 412	95.92 342	96.79 365	99.14 311	93.08 485	99.32 144	99.10 192	93.89 369	99.03 493	92.78 471	99.78 164	97.52 490

PHI-MVS		98.29 231	97.95 266	99.34 83	98.44 412	99.16 48	98.12 191	99.38 213	96.01 392	98.06 359	98.43 361	97.80 155	99.67 347	95.69 381	99.58 285	99.20 314

DVP-MVS++		98.90 108	98.70 138	99.51 49	98.43 414	99.15 52	99.43 15	99.32 241	98.17 214	99.26 157	99.02 214	98.18 118	99.88 115	97.07 267	99.45 328	99.49 177

MSC_two_6792asdad				99.32 91	98.43 414	98.37 126		98.86 365					99.89 97	97.14 260	99.60 276	99.71 65

No_MVS				99.32 91	98.43 414	98.37 126		98.86 365					99.89 97	97.14 260	99.60 276	99.71 65

Fast-Effi-MVS+-dtu		98.27 233	98.09 249	98.81 194	98.43 414	98.11 154	97.61 286	99.50 149	98.64 161	97.39 418	97.52 445	98.12 126	99.95 25	96.90 287	98.71 435	98.38 444

OpenMVS_ROB	95.38 14	95.84 424	95.18 440	97.81 353	98.41 418	97.15 275	97.37 321	98.62 398	83.86 539	98.65 287	98.37 368	94.29 359	99.68 342	88.41 520	98.62 446	96.60 511

SIFT-CM-Cal		96.28 401	96.31 394	96.16 464	98.39 419	98.11 154	93.46 522	96.47 486	94.81 445	98.49 317	98.43 361	94.48 348	97.34 531	92.60 477	99.70 228	93.02 538

DeepPCF-MVS	96.93 5	98.32 223	98.01 259	99.23 108	98.39 419	98.97 74	95.03 472	99.18 298	96.88 344	99.33 138	98.78 290	98.16 122	99.28 480	96.74 302	99.62 267	99.44 210

Patchmatch-test		96.55 384	96.34 392	97.17 414	98.35 421	93.06 460	98.40 156	97.79 438	97.33 301	98.41 327	98.67 318	83.68 493	99.69 330	95.16 399	99.31 360	98.77 402

AdaColmap		97.14 353	96.71 367	98.46 278	98.34 422	97.80 206	96.95 355	98.93 347	95.58 415	96.92 439	97.66 434	95.87 299	99.53 423	90.97 505	99.14 392	98.04 462

OpenMVS	96.65 7	97.09 356	96.68 369	98.32 296	98.32 423	97.16 274	98.86 92	99.37 217	89.48 522	96.29 475	99.15 177	96.56 256	99.90 81	92.90 465	99.20 383	97.89 470

MG-MVS		96.77 375	96.61 378	97.26 408	98.31 424	93.06 460	95.93 436	98.12 431	96.45 371	97.92 371	98.73 301	93.77 374	99.39 462	91.19 502	99.04 403	99.33 268

TestfortrainingZip				98.97 162	98.30 425	98.43 120	98.68 109	98.26 422	97.76 252	98.86 250	98.16 395	95.15 325	99.47 445		97.55 488	99.02 353

SIFT-NN-NCMNet		95.39 440	95.22 437	95.92 473	98.29 426	98.34 132	93.58 519	94.60 514	94.07 469	94.84 507	97.53 442	94.37 355	96.62 538	91.01 504	98.64 442	92.80 541

SIFT-UMatch		96.33 397	96.47 386	95.89 475	98.29 426	97.95 182	93.84 513	97.24 460	95.78 407	98.72 275	98.04 406	93.45 380	96.81 536	93.14 460	99.73 199	92.91 540

test_yl		96.69 376	96.29 395	97.90 344	98.28 428	95.24 380	97.29 329	97.36 452	98.21 206	98.17 345	97.86 420	86.27 464	99.55 414	94.87 405	98.32 457	98.89 380

DCV-MVSNet		96.69 376	96.29 395	97.90 344	98.28 428	95.24 380	97.29 329	97.36 452	98.21 206	98.17 345	97.86 420	86.27 464	99.55 414	94.87 405	98.32 457	98.89 380

SIFT-NCM-Cal		96.56 383	96.68 369	96.20 460	98.27 430	98.44 119	94.40 495	96.67 480	95.29 429	97.63 393	98.17 393	96.40 264	96.59 540	93.61 443	99.66 254	93.57 531

SIFT-NN-UMatch		95.38 441	95.26 434	95.75 480	98.25 431	97.78 207	93.24 526	95.66 506	94.01 471	95.10 503	97.47 450	93.12 387	96.78 537	92.42 480	98.04 478	92.69 543

CHOSEN 280x420		95.51 435	95.47 421	95.65 485	98.25 431	88.27 524	93.25 525	98.88 358	93.53 477	94.65 511	97.15 464	86.17 466	99.93 53	97.41 237	99.93 57	98.73 408

SIFT-NN-CMatch		95.63 431	95.48 420	96.08 468	98.24 433	98.00 172	92.71 528	94.29 518	94.20 463	95.85 485	97.26 460	95.72 304	97.01 533	91.99 485	99.02 407	93.23 535

SCA		96.41 395	96.66 373	95.67 483	98.24 433	88.35 523	95.85 442	96.88 476	96.11 386	97.67 391	98.67 318	93.10 389	99.85 159	94.16 425	99.22 378	98.81 394

DeepMVS_CX				93.44 519	98.24 433	94.21 420		94.34 517	64.28 548	91.34 537	94.87 516	89.45 444	92.77 548	77.54 544	93.14 539	93.35 534

MS-PatchMatch		97.68 305	97.75 286	97.45 399	98.23 436	93.78 446	97.29 329	98.84 369	96.10 387	98.64 290	98.65 325	96.04 285	99.36 465	96.84 293	99.14 392	99.20 314

SIFT-ConvMatch		96.57 382	96.62 376	96.43 447	98.20 437	98.27 137	93.88 512	96.88 476	95.29 429	98.88 244	98.25 385	95.18 324	97.43 529	93.22 458	99.83 126	93.59 530

BH-w/o		95.13 447	94.89 447	95.86 476	98.20 437	91.31 493	95.65 449	97.37 451	93.64 475	96.52 468	95.70 496	93.04 392	99.02 495	88.10 522	95.82 528	97.24 500

SIFT-MNN		95.92 420	95.97 402	95.74 482	98.18 439	98.00 172	94.17 503	96.99 468	95.74 409	97.16 426	97.90 418	90.71 430	95.79 542	93.71 441	99.21 381	93.44 532

mvs_anonymous		97.83 294	98.16 242	96.87 431	98.18 439	91.89 482	97.31 327	98.90 354	97.37 298	98.83 256	99.46 80	96.28 274	99.79 249	98.90 94	98.16 468	98.95 368

PRO-TEST		97.94 275	98.16 242	97.26 408	98.17 441	93.56 455	98.36 160	99.22 286	98.46 182	97.93 370	99.41 94	94.82 335	99.87 135	97.64 212	99.45 328	98.35 449

SIFT-PCN-Cal		96.34 396	96.46 388	96.01 471	98.17 441	96.89 293	93.48 521	97.35 455	94.84 443	99.35 130	98.30 379	94.70 343	97.92 521	92.03 484	99.88 95	93.21 537

miper_lstm_enhance		97.18 350	97.16 333	97.25 410	98.16 443	92.85 466	95.15 470	99.31 246	97.25 312	98.74 274	98.78 290	90.07 435	99.78 261	97.19 253	99.80 152	99.11 341

RRT-MVS		97.88 283	97.98 262	97.61 380	98.15 444	93.77 447	98.97 77	99.64 79	99.16 94	98.69 280	99.42 89	91.60 416	99.89 97	97.63 214	98.52 452	99.16 334

ET-MVSNet_ETH3D		94.30 461	93.21 473	97.58 383	98.14 445	94.47 413	94.78 479	93.24 530	94.72 446	89.56 541	95.87 492	78.57 516	99.81 227	96.91 282	97.11 506	98.46 431

ADS-MVSNet2		95.43 439	94.98 443	96.76 438	98.14 445	91.74 483	97.92 233	97.76 439	90.23 515	96.51 469	98.91 255	85.61 474	99.85 159	92.88 466	96.90 508	98.69 413

ADS-MVSNet		95.24 444	94.93 446	96.18 461	98.14 445	90.10 513	97.92 233	97.32 457	90.23 515	96.51 469	98.91 255	85.61 474	99.74 292	92.88 466	96.90 508	98.69 413

SIFT-UM-Cal		96.49 388	96.62 376	96.12 467	98.13 448	97.89 191	93.35 523	98.44 412	95.48 421	98.63 291	98.34 372	95.45 316	97.45 528	92.22 483	99.50 319	93.02 538

SIFT-PointCN		96.45 393	96.47 386	96.39 449	98.13 448	97.54 230	93.31 524	97.23 461	94.67 448	98.68 283	98.32 377	94.64 344	97.81 523	93.50 450	99.77 172	93.83 528

c3_l		97.36 332	97.37 319	97.31 404	98.09 450	93.25 458	95.01 473	99.16 305	97.05 329	98.77 268	98.72 303	92.88 394	99.64 372	96.93 281	99.76 188	99.05 346

balanced_ft_v1		98.28 232	98.35 207	98.10 323	98.08 451	96.23 328	99.23 45	99.26 275	98.34 189	97.46 409	99.42 89	95.38 319	99.88 115	98.60 117	99.34 353	98.17 455

FMVSNet3		97.50 316	97.24 328	98.29 301	98.08 451	95.83 348	97.86 242	98.91 353	97.89 241	98.95 224	98.95 247	87.06 459	99.81 227	97.77 197	99.69 234	99.23 304

PAPM		91.88 502	90.34 504	96.51 444	98.06 453	92.56 471	92.44 531	97.17 463	86.35 535	90.38 540	96.01 487	86.61 462	99.21 485	70.65 548	95.43 531	97.75 480

Effi-MVS+-dtu		98.26 235	97.90 275	99.35 80	98.02 454	99.49 5	98.02 211	99.16 305	98.29 198	97.64 392	97.99 410	96.44 262	99.95 25	96.66 315	98.93 420	98.60 423

eth_miper_zixun_eth		97.23 345	97.25 327	97.17 414	98.00 455	92.77 468	94.71 480	99.18 298	97.27 310	98.56 308	98.74 299	91.89 414	99.69 330	97.06 269	99.81 140	99.05 346

ALIKED-LG		97.10 354	96.63 375	98.50 274	97.96 456	98.68 100	97.75 261	99.68 64	95.86 400	98.36 335	98.33 376	91.58 418	99.04 492	90.87 509	99.31 360	97.77 479

HY-MVS	95.94 13	95.90 421	95.35 429	97.55 389	97.95 457	94.79 401	98.81 98	96.94 473	92.28 498	95.17 501	98.57 341	89.90 437	99.75 285	91.20 501	97.33 502	98.10 459

UGNet		98.53 189	98.45 186	98.79 201	97.94 458	96.96 287	99.08 62	98.54 406	99.10 107	96.82 450	99.47 78	96.55 257	99.84 180	98.56 124	99.94 51	99.55 137
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
MAR-MVS		96.47 391	95.70 410	98.79 201	97.92 459	99.12 62	98.28 168	98.60 399	92.16 499	95.54 495	96.17 485	94.77 341	99.52 427	89.62 516	98.23 462	97.72 483
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		96.86 371	96.55 382	97.79 354	97.91 460	94.21 420	97.56 292	98.87 360	97.49 282	99.06 193	99.05 208	80.72 503	99.80 236	98.44 131	99.82 133	99.37 244

SIFT-NN-PointCN		96.06 409	96.11 400	95.91 474	97.88 461	97.73 214	93.49 520	97.51 449	93.22 481	96.57 462	98.26 384	96.23 276	96.60 539	92.54 478	99.27 368	93.40 533

API-MVS		97.04 361	96.91 353	97.42 401	97.88 461	98.23 144	98.18 180	98.50 410	97.57 270	97.39 418	96.75 472	96.77 240	99.15 489	90.16 513	99.02 407	94.88 526

PDCNetPlus		95.22 445	94.73 452	96.70 440	97.85 463	91.14 500	93.94 511	99.97 1	93.06 486	98.95 224	98.89 264	74.32 523	99.14 490	95.63 384	99.93 57	99.82 36

myMVS_eth3d28		92.92 488	92.31 484	94.77 500	97.84 464	87.59 528	96.19 416	96.11 492	97.08 328	94.27 514	93.49 526	66.07 540	98.78 506	91.78 489	97.93 482	97.92 469

miper_ehance_all_eth		97.06 359	97.03 342	97.16 416	97.83 465	93.06 460	94.66 485	99.09 318	95.99 394	98.69 280	98.45 359	92.73 399	99.61 388	96.79 295	99.03 404	98.82 389

cl____		97.02 362	96.83 358	97.58 383	97.82 466	94.04 429	94.66 485	99.16 305	97.04 330	98.63 291	98.71 305	88.68 449	99.69 330	97.00 272	99.81 140	99.00 358

DIV-MVS_self_test		97.02 362	96.84 357	97.58 383	97.82 466	94.03 430	94.66 485	99.16 305	97.04 330	98.63 291	98.71 305	88.69 447	99.69 330	97.00 272	99.81 140	99.01 355

SIFT-NCMNet		96.30 399	96.40 390	96.03 470	97.80 468	97.68 218	92.34 532	96.94 473	95.55 416	98.84 254	98.63 331	94.17 362	97.63 526	93.57 447	99.71 217	92.77 542

CANet		97.87 285	97.76 285	98.19 314	97.75 469	95.51 360	96.76 369	99.05 326	97.74 253	96.93 438	98.21 390	95.59 310	99.89 97	97.86 188	99.93 57	99.19 320

UBG		93.25 481	92.32 483	96.04 469	97.72 470	90.16 511	95.92 438	95.91 498	96.03 391	93.95 523	93.04 530	69.60 530	99.52 427	90.72 511	97.98 480	98.45 434

mvsany_test1		97.60 310	97.54 306	97.77 356	97.72 470	95.35 374	95.36 461	97.13 465	94.13 465	99.71 49	99.33 119	97.93 141	99.30 476	97.60 218	98.94 419	98.67 419

PVSNet_0	89.98 21	91.15 503	90.30 505	93.70 515	97.72 470	84.34 542	90.24 537	97.42 450	90.20 518	93.79 524	93.09 529	90.90 429	98.89 504	86.57 529	72.76 550	97.87 472

CR-MVSNet		96.28 401	95.95 403	97.28 406	97.71 473	94.22 418	98.11 192	98.92 351	92.31 497	96.91 441	99.37 105	85.44 477	99.81 227	97.39 238	97.36 500	97.81 475

RPMNet		97.02 362	96.93 348	97.30 405	97.71 473	94.22 418	98.11 192	99.30 254	99.37 60	96.91 441	99.34 116	86.72 461	99.87 135	97.53 225	97.36 500	97.81 475

ETVMVS		92.60 491	91.08 500	97.18 412	97.70 475	93.65 452	96.54 388	95.70 502	96.51 364	94.68 510	92.39 534	61.80 549	99.50 434	86.97 525	97.41 496	98.40 442

pmmvs3		95.03 449	94.40 457	96.93 427	97.70 475	92.53 472	95.08 471	97.71 441	88.57 529	97.71 388	98.08 403	79.39 510	99.82 210	96.19 355	99.11 398	98.43 439

baseline2		93.73 472	92.83 479	96.42 448	97.70 475	91.28 495	96.84 364	89.77 544	93.96 473	92.44 533	95.93 490	79.14 511	99.77 267	92.94 463	96.76 512	98.21 452

WBMVS		95.18 446	94.78 448	96.37 450	97.68 478	89.74 517	95.80 444	98.73 389	97.54 277	98.30 336	98.44 360	70.06 528	99.82 210	96.62 318	99.87 100	99.54 143

tpm		94.67 454	94.34 459	95.66 484	97.68 478	88.42 522	97.88 238	94.90 510	94.46 453	96.03 484	98.56 343	78.66 514	99.79 249	95.88 369	95.01 533	98.78 401

ALIKED-MNN		95.97 418	95.30 433	98.00 337	97.66 480	98.12 153	96.98 353	99.41 204	91.11 512	94.04 520	97.30 459	91.56 419	98.61 511	89.99 514	99.63 263	97.28 499

CANet_DTU		97.26 341	97.06 341	97.84 350	97.57 481	94.65 409	96.19 416	98.79 377	97.23 318	95.14 502	98.24 387	93.22 385	99.84 180	97.34 240	99.84 114	99.04 350

testing11		93.08 484	92.02 490	96.26 455	97.56 482	90.83 505	96.32 406	95.70 502	96.47 369	92.66 531	93.73 522	64.36 544	99.59 397	93.77 440	97.57 487	98.37 446

tpm2		93.09 483	92.58 482	94.62 503	97.56 482	86.53 531	97.66 274	95.79 501	86.15 536	94.07 519	98.23 389	75.95 520	99.53 423	90.91 507	96.86 511	97.81 475

testing91		93.32 479	92.27 485	96.47 446	97.54 484	91.25 496	96.17 420	96.76 479	97.18 322	93.65 526	93.50 525	65.11 543	99.63 375	93.04 461	97.45 493	98.53 428

TR-MVS		95.55 433	95.12 441	96.86 434	97.54 484	93.94 438	96.49 393	96.53 485	94.36 460	97.03 436	96.61 475	94.26 360	99.16 488	86.91 527	96.31 517	97.47 492

testing99		93.04 485	91.98 493	96.23 458	97.53 486	90.70 508	96.35 404	95.94 497	96.87 345	93.41 527	93.43 527	63.84 545	99.59 397	93.24 457	97.19 503	98.40 442

1314		95.74 426	95.60 415	96.17 462	97.53 486	92.75 469	98.07 201	98.31 420	91.22 509	94.25 515	96.68 473	95.53 311	99.03 493	91.64 493	97.18 504	96.74 509

CostFormer		93.97 468	93.78 465	94.51 504	97.53 486	85.83 534	97.98 224	95.96 496	89.29 524	94.99 505	98.63 331	78.63 515	99.62 380	94.54 413	96.50 514	98.09 460

FMVSNet5		96.01 413	95.20 439	98.41 285	97.53 486	96.10 331	98.74 99	99.50 149	97.22 321	98.03 363	99.04 210	69.80 529	99.88 115	97.27 247	99.71 217	99.25 298

PMMVS		96.51 385	95.98 401	98.09 325	97.53 486	95.84 347	94.92 475	98.84 369	91.58 504	96.05 482	95.58 497	95.68 306	99.66 360	95.59 387	98.09 472	98.76 404

reproduce_monomvs		95.00 451	95.25 435	94.22 507	97.51 491	83.34 544	97.86 242	98.44 412	98.51 179	99.29 149	99.30 126	67.68 534	99.56 409	98.89 96	99.81 140	99.77 53

PAPR		95.29 442	94.47 454	97.75 360	97.50 492	95.14 387	94.89 477	98.71 391	91.39 508	95.35 499	95.48 502	94.57 346	99.14 490	84.95 532	97.37 498	98.97 364

testing222		91.96 500	90.37 503	96.72 439	97.47 493	92.59 470	96.11 423	94.76 511	96.83 349	92.90 529	92.87 531	57.92 551	99.55 414	86.93 526	97.52 489	98.00 466

PatchT		96.65 379	96.35 391	97.54 390	97.40 494	95.32 377	97.98 224	96.64 482	99.33 66	96.89 445	99.42 89	84.32 487	99.81 227	97.69 210	97.49 491	97.48 491

tpm cat1		93.29 480	93.13 476	93.75 514	97.39 495	84.74 537	97.39 315	97.65 445	83.39 541	94.16 516	98.41 363	82.86 498	99.39 462	91.56 495	95.35 532	97.14 501

PatchmatchNet		95.58 432	95.67 412	95.30 496	97.34 496	87.32 529	97.65 276	96.65 481	95.30 428	97.07 431	98.69 314	84.77 482	99.75 285	94.97 403	98.64 442	98.83 387
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SP-LightGlue		97.22 346	97.01 344	97.88 347	97.33 497	97.19 268	96.38 401	99.08 320	97.28 308	96.53 465	97.50 446	92.36 403	98.70 509	97.84 189	98.76 430	97.74 481

Patchmtry		97.35 333	96.97 346	98.50 274	97.31 498	96.47 319	98.18 180	98.92 351	98.95 131	98.78 265	99.37 105	85.44 477	99.85 159	95.96 367	99.83 126	99.17 328

LS3D		98.63 167	98.38 200	99.36 74	97.25 499	99.38 12	99.12 61	99.32 241	99.21 82	98.44 324	98.88 266	97.31 200	99.80 236	96.58 321	99.34 353	98.92 374

IB-MVS	91.63 19	92.24 497	90.90 501	96.27 454	97.22 500	91.24 497	94.36 497	93.33 529	92.37 496	92.24 535	94.58 519	66.20 539	99.89 97	93.16 459	94.63 535	97.66 485
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		92.38 494	91.76 497	94.21 508	97.16 501	84.65 538	95.42 459	88.45 546	95.96 395	96.17 476	95.84 494	66.36 537	99.71 311	91.87 488	98.64 442	98.28 450

tpmrst		95.07 448	95.46 422	93.91 512	97.11 502	84.36 541	97.62 281	96.96 471	94.98 438	96.35 474	98.80 286	85.46 476	99.59 397	95.60 386	96.23 518	97.79 478

Syy-MVS		96.04 411	95.56 419	97.49 395	97.10 503	94.48 412	96.18 418	96.58 483	95.65 411	94.77 508	92.29 536	91.27 425	99.36 465	98.17 155	98.05 476	98.63 421

myMVS_eth3d		91.92 501	90.45 502	96.30 452	97.10 503	90.90 503	96.18 418	96.58 483	95.65 411	94.77 508	92.29 536	53.88 552	99.36 465	89.59 518	98.05 476	98.63 421

blended_shiyan6		95.99 415	95.33 430	97.95 341	97.06 505	94.89 397	95.34 462	98.58 401	96.17 381	97.06 432	92.41 533	87.64 457	99.76 273	97.64 212	96.09 521	99.19 320

MDTV_nov1_ep13			95.22 437		97.06 505	83.20 546	97.74 263	96.16 490	94.37 459	96.99 437	98.83 279	83.95 491	99.53 423	93.90 434	97.95 481

blended_shiyan8		95.98 416	95.33 430	97.94 342	97.05 507	94.87 399	95.34 462	98.59 400	96.17 381	97.09 430	92.39 534	87.62 458	99.76 273	97.65 211	96.05 527	99.20 314

MASt3R-SfM		96.02 412	95.82 406	96.60 442	97.03 508	94.90 396	94.26 501	98.53 407	88.40 531	98.41 327	98.67 318	92.39 402	97.62 527	95.31 394	99.41 341	97.29 498

SP-SuperGlue		97.31 336	97.23 329	97.57 388	96.96 509	97.24 260	96.26 412	98.76 382	97.68 258	96.88 447	97.85 422	94.32 357	98.01 519	97.76 201	98.57 449	97.45 493

SIFT-NN		92.96 486	92.79 480	93.46 517	96.92 510	96.45 320	91.89 534	94.39 516	92.91 489	92.54 532	95.46 503	88.26 454	90.71 550	85.22 531	97.52 489	93.22 536

MVS		93.19 482	92.09 488	96.50 445	96.91 511	94.03 430	98.07 201	98.06 434	68.01 547	94.56 513	96.48 478	95.96 295	99.30 476	83.84 534	96.89 510	96.17 517

E-PMN		94.17 464	94.37 458	93.58 516	96.86 512	85.71 535	90.11 539	97.07 466	98.17 214	97.82 383	97.19 462	84.62 484	98.94 499	89.77 515	97.68 486	96.09 521

JIA-IIPM		95.52 434	95.03 442	97.00 422	96.85 513	94.03 430	96.93 358	95.82 499	99.20 84	94.63 512	99.71 22	83.09 496	99.60 392	94.42 419	94.64 534	97.36 496

EMVS		93.83 470	94.02 461	93.23 522	96.83 514	84.96 536	89.77 540	96.32 488	97.92 238	97.43 415	96.36 483	86.17 466	98.93 500	87.68 523	97.73 485	95.81 522

blend_shiyan4		92.09 499	90.16 506	97.88 347	96.78 515	94.93 394	95.24 466	98.58 401	96.22 379	96.07 480	91.42 538	63.46 548	99.73 299	96.70 308	76.98 549	98.98 360

cl22		95.79 425	95.39 427	96.98 424	96.77 516	92.79 467	94.40 495	98.53 407	94.59 450	97.89 374	98.17 393	82.82 499	99.24 482	96.37 342	99.03 404	98.92 374

SP-MNN		96.46 392	96.24 399	97.10 417	96.71 517	95.98 339	96.00 429	97.33 456	95.82 404	94.93 506	97.10 468	93.70 376	98.01 519	96.30 348	98.30 460	97.30 497

WB-MVSnew		95.73 427	95.57 418	96.23 458	96.70 518	90.70 508	96.07 426	93.86 525	95.60 413	97.04 434	95.45 507	96.00 288	99.55 414	91.04 503	98.31 459	98.43 439

dp		93.47 476	93.59 468	93.13 523	96.64 519	81.62 552	97.66 274	96.42 487	92.80 492	96.11 478	98.64 329	78.55 517	99.59 397	93.31 454	92.18 542	98.16 456

MonoMVSNet		96.25 404	96.53 384	95.39 492	96.57 520	91.01 501	98.82 97	97.68 444	98.57 174	98.03 363	99.37 105	90.92 428	97.78 524	94.99 401	93.88 538	97.38 495

wanda-best-256-512		95.48 436	94.74 450	97.68 368	96.53 521	94.12 424	94.17 503	98.57 403	95.84 401	96.71 454	91.16 539	86.05 469	99.76 273	97.57 220	96.09 521	99.17 328

FE-blended-shiyan7		95.48 436	94.74 450	97.68 368	96.53 521	94.12 424	94.17 503	98.57 403	95.84 401	96.71 454	91.16 539	86.05 469	99.76 273	97.57 220	96.09 521	99.17 328

usedtu_blend_shiyan5		96.20 407	95.62 413	97.94 342	96.53 521	94.93 394	98.83 96	99.59 100	98.89 138	96.71 454	91.16 539	86.05 469	99.73 299	96.70 308	96.09 521	99.17 328

test-LLR		93.90 469	93.85 463	94.04 510	96.53 521	84.62 539	94.05 508	92.39 532	96.17 381	94.12 517	95.07 508	82.30 500	99.67 347	95.87 372	98.18 465	97.82 473

test-mter		92.33 496	91.76 497	94.04 510	96.53 521	84.62 539	94.05 508	92.39 532	94.00 472	94.12 517	95.07 508	65.63 542	99.67 347	95.87 372	98.18 465	97.82 473

TESTMET0.1,1		92.19 498	91.77 496	93.46 517	96.48 526	82.80 548	94.05 508	91.52 540	94.45 456	94.00 521	94.88 514	66.65 536	99.56 409	95.78 377	98.11 471	98.02 463

MGCNet		97.44 324	97.01 344	98.72 221	96.42 527	96.74 303	97.20 340	91.97 538	98.46 182	98.30 336	98.79 288	92.74 398	99.91 74	99.30 62	99.94 51	99.52 161

miper_enhance_ethall		96.01 413	95.74 408	96.81 435	96.41 528	92.27 479	93.69 516	98.89 357	91.14 511	98.30 336	97.35 458	90.58 432	99.58 404	96.31 346	99.03 404	98.60 423

tpmvs		95.02 450	95.25 435	94.33 505	96.39 529	85.87 532	98.08 197	96.83 478	95.46 422	95.51 497	98.69 314	85.91 472	99.53 423	94.16 425	96.23 518	97.58 488

CMPMVS	75.91 23	96.29 400	95.44 424	98.84 188	96.25 530	98.69 99	97.02 349	99.12 313	88.90 526	97.83 381	98.86 269	89.51 442	98.90 503	91.92 486	99.51 311	98.92 374
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ALIKED-NN		94.29 462	93.41 471	96.94 426	96.18 531	97.66 219	94.90 476	98.68 392	88.85 527	90.43 539	96.81 471	89.82 438	96.59 540	86.67 528	98.33 456	96.58 512

test0.0.03 1		94.51 456	93.69 466	96.99 423	96.05 532	93.61 454	94.97 474	93.49 527	96.17 381	97.57 400	94.88 514	82.30 500	99.01 497	93.60 445	94.17 537	98.37 446

EPMVS		93.72 473	93.27 472	95.09 499	96.04 533	87.76 526	98.13 187	85.01 551	94.69 447	96.92 439	98.64 329	78.47 518	99.31 474	95.04 400	96.46 515	98.20 453

cascas		94.79 453	94.33 460	96.15 466	96.02 534	92.36 477	92.34 532	99.26 275	85.34 538	95.08 504	94.96 513	92.96 393	98.53 512	94.41 422	98.59 447	97.56 489

gbinet_0.2-2-1-0.02		95.44 438	94.55 453	98.14 319	95.99 535	95.34 376	94.71 480	98.29 421	96.00 393	96.05 482	90.50 543	84.99 479	99.79 249	97.33 242	97.07 507	99.28 287

MVStest1		95.86 422	95.60 415	96.63 441	95.87 536	91.70 484	97.93 230	98.94 344	98.03 228	99.56 74	99.66 32	71.83 526	98.26 515	99.35 58	99.24 374	99.91 13

gg-mvs-nofinetune		92.37 495	91.20 499	95.85 477	95.80 537	92.38 476	99.31 30	81.84 553	99.75 10	91.83 536	99.74 18	68.29 531	99.02 495	87.15 524	97.12 505	96.16 518

SP-DiffGlue		96.87 370	96.76 363	97.21 411	95.17 538	96.88 295	96.12 422	98.93 347	96.51 364	98.37 333	97.55 441	93.65 377	97.83 522	96.11 362	98.45 454	96.92 503

SP-NN		94.67 454	94.44 456	95.36 494	95.12 539	95.23 383	94.27 500	96.10 493	94.46 453	90.91 538	95.76 495	91.47 422	93.87 547	95.23 397	96.62 513	97.00 502

gm-plane-assit					94.83 540	81.97 550			88.07 533		94.99 511		99.60 392	91.76 490

GG-mvs-BLEND				94.76 501	94.54 541	92.13 481	99.31 30	80.47 554		88.73 544	91.01 542	67.59 535	98.16 518	82.30 540	94.53 536	93.98 527

UWE-MVS-28		90.22 504	89.28 507	93.02 524	94.50 542	82.87 547	96.52 391	87.51 547	95.21 433	92.36 534	96.04 486	71.57 527	98.25 516	72.04 547	97.77 484	97.94 468

EPNet_dtu		94.93 452	94.78 448	95.38 493	93.58 543	87.68 527	96.78 367	95.69 504	97.35 300	89.14 543	98.09 402	88.15 455	99.49 438	94.95 404	99.30 364	98.98 360
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
0.4-1-1-0.1		88.42 506	85.91 509	95.94 472	93.08 544	91.54 486	90.99 536	92.04 536	89.96 521	84.83 547	83.25 545	63.75 546	99.52 427	93.25 456	82.07 544	96.75 508

XFeat-MNN		93.41 478	92.98 478	94.68 502	92.63 545	92.92 464	89.72 541	95.81 500	92.10 500	97.23 425	96.29 484	84.95 480	97.31 532	89.60 517	98.54 451	93.81 529

dongtai		76.24 513	75.95 516	77.12 531	92.39 546	67.91 557	90.16 538	59.44 558	82.04 542	89.42 542	94.67 518	49.68 554	81.74 551	48.06 550	77.66 548	81.72 546

0.3-1-1-0.015		87.27 508	84.50 512	95.57 486	91.70 547	90.77 506	89.41 542	92.04 536	88.98 525	82.46 549	81.35 546	60.36 550	99.50 434	92.96 462	81.23 546	96.45 513

KD-MVS_2432*1600		92.87 489	91.99 491	95.51 489	91.37 548	89.27 519	94.07 506	98.14 429	95.42 424	97.25 423	96.44 480	67.86 532	99.24 482	91.28 499	96.08 525	98.02 463

miper_refine_blended		92.87 489	91.99 491	95.51 489	91.37 548	89.27 519	94.07 506	98.14 429	95.42 424	97.25 423	96.44 480	67.86 532	99.24 482	91.28 499	96.08 525	98.02 463

0.4-1-1-0.2		87.49 507	84.89 510	95.31 495	91.33 550	90.08 514	88.47 543	92.07 535	88.70 528	84.06 548	81.08 547	63.62 547	99.49 438	92.93 464	81.71 545	96.37 514

XFeat-NN		89.63 505	89.13 508	91.14 526	90.93 551	90.02 515	84.90 544	94.05 524	88.10 532	92.89 530	93.33 528	78.74 513	90.89 549	83.46 535	95.72 529	92.52 544

EPNet		96.14 408	95.44 424	98.25 305	90.76 552	95.50 364	97.92 233	94.65 512	98.97 127	92.98 528	98.85 272	89.12 445	99.87 135	95.99 365	99.68 240	99.39 232
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		69.30 514	68.95 517	70.34 532	87.68 553	65.00 558	91.11 535	59.90 557	69.02 546	74.46 551	88.89 544	48.58 555	68.03 553	28.61 551	72.33 551	77.99 547

GLUNet-SfM		86.26 509	84.68 511	91.01 527	80.58 554	83.56 543	78.04 545	93.59 526	76.70 545	95.29 500	94.72 517	77.51 519	94.26 546	66.39 549	99.33 355	95.20 525

test_method		79.78 511	79.50 514	80.62 529	80.21 555	45.76 559	70.82 546	98.41 417	31.08 550	80.89 550	97.71 431	84.85 481	97.37 530	91.51 496	80.03 547	98.75 405

tmp_tt		78.77 512	78.73 515	78.90 530	58.45 556	74.76 556	94.20 502	78.26 555	39.16 549	86.71 545	92.82 532	80.50 504	75.19 552	86.16 530	92.29 541	86.74 545

VLMVS		32.15 515	34.06 518	26.43 533	35.38 557	29.60 560	32.69 547	19.27 559	3.29 554	44.01 552	60.07 548	35.02 556	20.44 554	22.64 552	54.15 552	29.25 549

testmvs		17.12 517	20.53 520	6.87 535	12.05 558	4.20 562	93.62 518	6.73 560	4.62 553	10.41 554	24.33 550	8.28 558	3.56 556	9.69 554	15.07 553	12.86 551

test123		17.04 518	20.11 521	7.82 534	10.25 559	4.91 561	94.80 478	4.47 561	4.93 552	10.00 555	24.28 551	9.69 557	3.64 555	10.14 553	12.43 554	14.92 550

PatchmatchNet2					0.00 560	90.12 512	94.29 499	98.12 431	94.40 458
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
mmdepth		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

monomultidepth		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

test_blank		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

eth-test2					0.00 560

eth-test					0.00 560

uanet_test		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

DCPMVS		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

cdsmvs_eth3d_5k		24.66 516	32.88 519	0.00 536	0.00 560	0.00 563	0.00 548	99.10 316	0.00 555	0.00 556	97.58 439	99.21 18	0.00 557	0.00 555	0.00 555	0.00 552

pcd_1.5k_mvsjas		8.17 519	10.90 522	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	98.07 128	0.00 557	0.00 555	0.00 555	0.00 552

sosnet-low-res		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

sosnet		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

uncertanet		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

Regformer		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

ab-mvs-re		8.12 520	10.83 523	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	97.48 448	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

uanet		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

PatchmatchNet1														96.95 280	99.71 217	99.28 287
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													99.85 159
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						90.90 503								91.37 498

PC_three_1452									93.27 480	99.40 117	98.54 344	98.22 113	97.00 534	95.17 398	99.45 328	99.49 177

test_241102_TWO								99.30 254	98.03 228	99.26 157	99.02 214	97.51 185	99.88 115	96.91 282	99.60 276	99.66 80

test_0728_THIRD									98.17 214	99.08 191	99.02 214	97.89 147	99.88 115	97.07 267	99.71 217	99.70 70

GSMVS																98.81 394

sam_mvs1												84.74 483				98.81 394

sam_mvs												84.29 489

MTGPA								99.20 290

test_post1							97.59 289				20.48 553	83.07 497	99.66 360	94.16 425

test_post											21.25 552	83.86 492	99.70 320

patchmatchnet-post											98.77 292	84.37 486	99.85 159

MTMP							97.93 230	91.91 539

test9_res														93.28 455	99.15 391	99.38 241

agg_prior2														92.50 479	99.16 389	99.37 244

test_prior4						97.97 178	95.86 440

test_prior2							95.74 447		96.48 368	96.11 478	97.63 437	95.92 298		94.16 425	99.20 383

旧先验2							95.76 446		88.56 530	97.52 404			99.66 360	94.48 415

新几何2							95.93 436

无先验							95.74 447	98.74 388	89.38 523				99.73 299	92.38 482		99.22 309

原ACMM2							95.53 453

testdata2													99.79 249	92.80 470

segment_acmp												97.02 221

testdata1							95.44 458		96.32 375

plane_prior5								99.27 269					99.70 320	94.42 419	99.51 311	99.45 206

plane_prior4											97.98 411

plane_prior3						97.78 207			97.41 293	97.79 384

plane_prior2							97.77 255		98.20 210

plane_prior						97.65 221	97.07 348		96.72 355						99.36 348

n2								0.00 562

nn								0.00 562

door-mid								99.57 111

test11								98.87 360

door								99.41 204

HQP5-MVS						96.79 299

BP-MVS														92.82 468

HQP4-MVS										95.56 491			99.54 420			99.32 273

HQP3-MVS								99.04 329							99.26 372

HQP2-MVS												93.84 370

MDTV_nov1_ep13_2view						74.92 555	97.69 269		90.06 520	97.75 387		85.78 473		93.52 448		98.69 413

ACMMP++_ref															99.77 172

ACMMP++															99.68 240

Test By Simon												96.52 258

High-resolution multi-view benchmark