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.

fmvsm_l_mol_unc0.5_1		99.77 1	99.70 1	99.97 1	99.88 13	99.92 2	99.36 302	99.67 27	99.51 2	99.96 27	99.97 1	99.01 19	99.99 4	99.98 1	99.99 1	99.99 1

fmvsm_l_conf0.5_n_9		99.58 17	99.47 25	99.92 2	99.85 32	99.82 30	99.47 242	99.63 47	99.45 14	99.98 13	99.89 46	97.02 150	99.99 4	99.98 1	99.96 18	99.95 12

fmvsm_s_conf0.5_n_10		99.41 60	99.24 78	99.92 2	99.83 48	99.84 21	99.53 184	99.56 91	99.45 14	99.99 2	99.92 19	94.92 269	99.99 4	99.97 3	99.97 10	99.95 12

fmvsm_s_conf0.5_n_9		99.41 60	99.28 69	99.81 61	99.84 39	99.52 108	99.48 232	99.62 53	99.46 10	99.99 2	99.92 19	95.24 256	99.96 42	99.97 3	99.97 10	99.96 8

fmvsm_s_conf0.5_n_7		99.34 76	99.29 66	99.48 166	99.70 124	98.63 259	99.42 270	99.63 47	99.46 10	99.98 13	99.88 59	95.59 239	99.96 42	99.97 3	99.98 5	99.85 48

fmvsm_s_conf0.5_n_5		99.37 69	99.21 84	99.86 35	99.80 65	99.68 66	99.42 270	99.61 62	99.37 27	99.97 25	99.86 86	94.96 264	99.99 4	99.97 3	99.93 33	99.92 26

fmvsm_l_conf0.5_n_3		99.61 11	99.51 19	99.92 2	99.84 39	99.82 30	99.54 175	99.66 33	99.46 10	99.98 13	99.89 46	97.27 135	99.99 4	99.97 3	99.95 23	99.95 12

fmvsm_s_conf0.1_n_2		99.37 69	99.22 83	99.81 61	99.77 80	99.75 53	99.46 246	99.60 69	99.47 7	99.98 13	99.94 7	94.98 263	99.95 77	99.97 3	99.79 134	99.73 129

fmvsm_l_conf0.5_n_a		99.71 2	99.67 2	99.85 44	99.86 26	99.61 88	99.56 155	99.63 47	99.48 4	99.98 13	99.83 117	98.75 62	99.99 4	99.97 3	99.96 18	99.94 18

fmvsm_l_conf0.5_n		99.71 2	99.67 2	99.85 44	99.84 39	99.63 84	99.56 155	99.63 47	99.47 7	99.98 13	99.82 128	98.75 62	99.99 4	99.97 3	99.97 10	99.94 18

MM		99.40 65	99.28 69	99.74 81	99.67 140	99.31 138	99.52 186	98.87 440	99.55 1	99.74 102	99.80 161	96.47 184	99.98 21	99.97 3	99.97 10	99.94 18

test_fmvsmvis_n_1920		99.65 9	99.61 9	99.77 75	99.38 289	99.37 126	99.58 139	99.62 53	99.41 24	99.87 49	99.92 19	98.81 50	100.00 1	99.97 3	99.93 33	99.94 18

test_fmvsm_n_1920		99.69 7	99.66 4	99.78 72	99.84 39	99.44 119	99.58 139	99.69 22	99.43 20	99.98 13	99.91 27	98.62 78	100.00 1	99.97 3	99.95 23	99.90 28

fmvsm_s_conf0.5_n_11		99.32 79	99.16 92	99.80 65	99.83 48	99.70 62	99.57 147	99.56 91	99.45 14	99.99 2	99.93 11	94.18 320	99.99 4	99.96 14	99.98 5	99.73 129

fmvsm_s_conf0.5_n_2		99.32 79	99.13 95	99.89 13	99.80 65	99.77 50	99.44 257	99.58 79	99.47 7	99.99 2	99.93 11	94.04 325	99.96 42	99.96 14	99.93 33	99.93 23

test_fmvsmconf_n		99.70 4	99.64 5	99.87 23	99.80 65	99.66 73	99.48 232	99.64 43	99.45 14	99.92 31	99.92 19	98.62 78	99.99 4	99.96 14	99.99 1	99.96 8

fmvsm_s_conf0.5_n_8		99.54 25	99.42 33	99.89 13	99.83 48	99.74 56	99.51 196	99.62 53	99.46 10	99.99 2	99.90 37	96.60 176	99.98 21	99.95 17	99.95 23	99.96 8

fmvsm_s_conf0.5_n_6		99.54 25	99.44 32	99.85 44	99.51 239	99.67 70	99.50 207	99.64 43	99.43 20	99.98 13	99.78 185	97.26 138	99.95 77	99.95 17	99.93 33	99.92 26

fmvsm_s_conf0.5_n_4		99.36 73	99.24 78	99.73 84	99.78 72	99.53 104	99.49 224	99.60 69	99.42 23	99.99 2	99.86 86	95.15 259	99.95 77	99.95 17	99.89 68	99.73 129

fmvsm_s_conf0.5_n		99.51 30	99.40 38	99.85 44	99.84 39	99.65 77	99.51 196	99.67 27	99.13 42	99.98 13	99.92 19	96.60 176	99.96 42	99.95 17	99.96 18	99.95 12

test_fmvsmconf0.1_n		99.55 24	99.45 31	99.86 35	99.44 270	99.65 77	99.50 207	99.61 62	99.45 14	99.87 49	99.92 19	97.31 132	99.97 30	99.95 17	99.99 1	99.97 5

fmvsm_s_conf0.5_n_3		99.37 69	99.20 86	99.87 23	99.75 94	99.70 62	99.48 232	99.66 33	99.45 14	99.99 2	99.93 11	94.64 297	99.97 30	99.94 22	99.97 10	99.95 12

fmvsm_s_conf0.5_n_a		99.56 22	99.47 25	99.85 44	99.83 48	99.64 83	99.52 186	99.65 40	99.10 49	99.98 13	99.92 19	97.35 131	99.96 42	99.94 22	99.92 39	99.95 12

test_fmvsmconf0.01_n		99.22 100	99.03 120	99.79 69	98.42 466	99.48 114	99.55 170	99.51 163	99.39 25	99.78 87	99.93 11	94.80 278	99.95 77	99.93 24	99.95 23	99.94 18

test_vis1_n_1920		98.63 229	98.40 237	99.31 210	99.86 26	97.94 316	99.67 77	99.62 53	99.43 20	99.99 2	99.91 27	87.29 456	100.00 1	99.92 25	99.92 39	99.98 3

fmvsm_s_conf0.1_n		99.29 85	99.10 100	99.86 35	99.70 124	99.65 77	99.53 184	99.62 53	98.74 103	99.99 2	99.95 4	94.53 305	99.94 92	99.89 26	99.96 18	99.97 5

fmvsm_s_conf0.1_n_a		99.26 92	99.06 112	99.85 44	99.52 236	99.62 85	99.54 175	99.62 53	98.69 109	99.99 2	99.96 2	94.47 307	99.94 92	99.88 27	99.92 39	99.98 3

test_vis1_n		97.92 304	97.44 346	99.34 202	99.53 230	98.08 303	99.74 48	99.49 203	99.15 39	100.00 1	99.94 7	79.51 501	99.98 21	99.88 27	99.76 142	99.97 5

MGCNet		99.15 119	98.96 154	99.73 84	98.92 404	99.37 126	99.37 296	96.92 512	99.51 2	99.66 138	99.78 185	96.69 171	99.97 30	99.84 29	99.97 10	99.84 55

mmtdpeth		96.95 396	96.71 395	97.67 426	99.33 303	94.90 455	99.89 2	99.28 363	98.15 185	99.72 109	98.57 461	86.56 464	99.90 150	99.82 30	89.02 498	98.20 460

test_fmvs1_n		98.41 241	98.14 254	99.21 231	99.82 54	97.71 328	99.74 48	99.49 203	99.32 31	99.99 2	99.95 4	85.32 475	99.97 30	99.82 30	99.84 103	99.96 8

test_fmvs1		98.88 188	98.79 191	99.16 236	99.69 130	97.61 332	99.55 170	99.49 203	99.32 31	99.98 13	99.91 27	91.41 399	99.96 42	99.82 30	99.92 39	99.90 28

AstraMVS		99.09 154	99.03 120	99.25 225	99.66 152	98.13 299	99.57 147	98.24 489	98.82 91	99.91 32	99.88 59	95.81 228	99.90 150	99.72 33	99.67 160	99.74 119

mvsany_test1		99.50 32	99.46 29	99.62 110	99.61 195	99.09 171	98.94 433	99.48 215	99.10 49	99.96 27	99.91 27	98.85 44	99.96 42	99.72 33	99.58 171	99.82 73

patch_mono-2		99.26 92	99.62 8	98.16 378	99.81 59	94.59 465	99.52 186	99.64 43	99.33 30	99.73 104	99.90 37	99.00 24	99.99 4	99.69 35	99.98 5	99.89 31

SPE-MVS-test		99.49 34	99.48 23	99.54 128	99.78 72	99.30 141	99.89 2	99.58 79	98.56 121	99.73 104	99.69 237	98.55 83	99.82 233	99.69 35	99.85 95	99.48 253

balanced_ft_v1		99.02 170	98.98 148	99.15 240	99.39 286	98.12 301	99.79 31	99.51 163	98.20 178	99.66 138	99.87 75	94.84 274	99.93 110	99.69 35	99.84 103	99.41 276

LuminaMVS		99.23 98	99.10 100	99.61 111	99.35 297	99.31 138	99.46 246	99.13 396	98.61 115	99.86 53	99.89 46	96.41 190	99.91 137	99.67 38	99.51 177	99.63 197

SDMVSNet		99.11 147	98.90 169	99.75 78	99.81 59	99.59 91	99.81 20	99.65 40	98.78 100	99.64 153	99.88 59	94.56 300	99.93 110	99.67 38	98.26 306	99.72 139

dcpmvs_2		99.23 98	99.58 10	98.16 378	99.83 48	94.68 461	99.76 38	99.52 135	99.07 59	99.98 13	99.88 59	98.56 82	99.93 110	99.67 38	99.98 5	99.87 42

guyue		99.16 114	99.04 117	99.52 143	99.69 130	98.92 211	99.59 129	98.81 448	98.73 104	99.90 35	99.87 75	95.34 249	99.88 170	99.66 41	99.81 122	99.74 119

MVSMamba_PlusPlus		99.46 43	99.41 37	99.64 103	99.68 137	99.50 111	99.75 43	99.50 188	98.27 160	99.87 49	99.92 19	98.09 110	99.94 92	99.65 42	99.95 23	99.47 259

CS-MVS		99.50 32	99.48 23	99.54 128	99.76 84	99.42 121	99.90 1	99.55 101	98.56 121	99.78 87	99.70 226	98.65 76	99.79 253	99.65 42	99.78 136	99.41 276

EC-MVSNet		99.44 51	99.39 40	99.58 119	99.56 218	99.49 112	99.88 4	99.58 79	98.38 143	99.73 104	99.69 237	98.20 105	99.70 302	99.64 44	99.82 119	99.54 230

BP-MVS1		99.12 141	98.94 160	99.65 97	99.51 239	99.30 141	99.67 77	98.92 427	98.48 130	99.84 57	99.69 237	94.96 264	99.92 125	99.62 45	99.79 134	99.71 151

CANet		99.25 96	99.14 94	99.59 115	99.41 278	99.16 159	99.35 308	99.57 86	98.82 91	99.51 191	99.61 280	96.46 185	99.95 77	99.59 46	99.98 5	99.65 185

EI-MVSNet-UG-set		99.58 17	99.57 11	99.64 103	99.78 72	99.14 165	99.60 118	99.45 261	99.01 65	99.90 35	99.83 117	98.98 26	99.93 110	99.59 46	99.95 23	99.86 44

BridgeMVS		99.46 43	99.39 40	99.67 92	99.55 222	99.58 96	99.74 48	99.51 163	98.42 138	99.87 49	99.84 108	98.05 113	99.91 137	99.58 48	99.94 31	99.52 236

DELS-MVS		99.48 38	99.42 33	99.65 97	99.72 113	99.40 124	99.05 405	99.66 33	99.14 41	99.57 176	99.80 161	98.46 90	99.94 92	99.57 49	99.84 103	99.60 205
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
EI-MVSNet-Vis-set		99.58 17	99.56 13	99.64 103	99.78 72	99.15 164	99.61 116	99.45 261	99.01 65	99.89 40	99.82 128	99.01 19	99.92 125	99.56 50	99.95 23	99.85 48

test_cas_vis1_n_1920		99.16 114	99.01 139	99.61 111	99.81 59	98.86 231	99.65 90	99.64 43	99.39 25	99.97 25	99.94 7	93.20 349	99.98 21	99.55 51	99.91 46	99.99 1

sd_testset		98.75 217	98.57 225	99.29 218	99.81 59	98.26 292	99.56 155	99.62 53	98.78 100	99.64 153	99.88 59	92.02 381	99.88 170	99.54 52	98.26 306	99.72 139

casdiffmvs_mvg		99.15 119	99.02 131	99.55 127	99.66 152	99.09 171	99.64 98	99.56 91	98.26 163	99.45 200	99.87 75	96.03 213	99.81 238	99.54 52	99.15 215	99.73 129
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_vis1_rt		95.81 422	95.65 421	96.32 464	99.67 140	91.35 494	99.49 224	96.74 516	98.25 168	95.24 477	98.10 483	74.96 503	99.90 150	99.53 54	98.85 266	97.70 491

HyFIR lowres test		99.11 147	98.92 163	99.65 97	99.90 4	99.37 126	99.02 413	99.91 3	97.67 278	99.59 172	99.75 203	95.90 223	99.73 283	99.53 54	99.02 250	99.86 44

VNet		99.11 147	98.90 169	99.73 84	99.52 236	99.56 97	99.41 275	99.39 296	99.01 65	99.74 102	99.78 185	95.56 240	99.92 125	99.52 56	98.18 315	99.72 139

baseline		99.15 119	99.02 131	99.53 136	99.66 152	99.14 165	99.72 54	99.48 215	98.35 148	99.42 211	99.84 108	96.07 209	99.79 253	99.51 57	99.14 216	99.67 171

xiu_mvs_v1_base_debu		99.29 85	99.27 73	99.34 202	99.63 174	98.97 191	99.12 388	99.51 163	98.86 86	99.84 57	99.47 337	98.18 106	99.99 4	99.50 58	99.31 194	99.08 315

xiu_mvs_v1_base		99.29 85	99.27 73	99.34 202	99.63 174	98.97 191	99.12 388	99.51 163	98.86 86	99.84 57	99.47 337	98.18 106	99.99 4	99.50 58	99.31 194	99.08 315

xiu_mvs_v1_base_debi		99.29 85	99.27 73	99.34 202	99.63 174	98.97 191	99.12 388	99.51 163	98.86 86	99.84 57	99.47 337	98.18 106	99.99 4	99.50 58	99.31 194	99.08 315

CHOSEN 1792x2688		99.19 102	99.10 100	99.45 176	99.89 8	98.52 274	99.39 287	99.94 1	98.73 104	99.11 293	99.89 46	95.50 242	99.94 92	99.50 58	99.97 10	99.89 31

viewdifsd2359ckpt11		98.78 212	98.74 197	98.89 277	99.67 140	97.04 361	99.50 207	99.58 79	98.26 163	99.56 178	99.90 37	94.36 310	99.87 177	99.49 62	98.32 302	99.77 101

viewmsd2359difaftdt		98.78 212	98.74 197	98.90 273	99.67 140	97.04 361	99.50 207	99.58 79	98.26 163	99.56 178	99.90 37	94.36 310	99.87 177	99.49 62	98.32 302	99.77 101

VDD-MVS		97.73 341	97.35 358	98.88 282	99.47 261	97.12 351	99.34 314	98.85 443	98.19 180	99.67 133	99.85 93	82.98 489	99.92 125	99.49 62	98.32 302	99.60 205

h-mvs33		97.70 347	97.28 371	98.97 258	99.70 124	97.27 343	99.36 302	99.45 261	98.94 80	99.66 138	99.64 265	94.93 267	99.99 4	99.48 65	84.36 508	99.65 185

hse-mvs2		97.50 368	97.14 379	98.59 321	99.49 253	97.05 358	99.28 337	99.22 381	98.94 80	99.66 138	99.42 348	94.93 267	99.65 319	99.48 65	83.80 512	99.08 315

onestephybrid01		99.17 110	99.06 112	99.49 161	99.60 202	98.98 187	99.38 292	99.50 188	98.52 125	99.81 73	99.87 75	96.27 197	99.81 238	99.47 67	99.10 235	99.67 171

PVSNet_Blended_VisFu		99.36 73	99.28 69	99.61 111	99.86 26	99.07 176	99.47 242	99.93 2	97.66 279	99.71 119	99.86 86	97.73 121	99.96 42	99.47 67	99.82 119	99.79 93

viewmamba		99.20 101	99.12 97	99.44 182	99.61 195	98.87 227	99.42 270	99.52 135	98.42 138	99.84 57	99.84 108	96.85 157	99.78 261	99.46 69	99.11 226	99.67 171

CHOSEN 280x420		99.12 141	99.13 95	99.08 244	99.66 152	97.89 317	98.43 493	99.71 16	98.88 85	99.62 160	99.76 198	96.63 174	99.70 302	99.46 69	99.99 1	99.66 178

casdiffmvs		99.13 131	98.98 148	99.56 125	99.65 164	99.16 159	99.56 155	99.50 188	98.33 151	99.41 216	99.86 86	95.92 221	99.83 224	99.45 71	99.16 209	99.70 155
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test1111		98.04 284	98.11 258	97.83 414	99.74 102	93.82 474	99.58 139	95.40 525	99.12 47	99.65 148	99.93 11	90.73 412	99.84 202	99.43 72	99.38 186	99.82 73

hybridcas		99.13 131	99.00 143	99.51 148	99.70 124	99.04 180	99.65 90	99.52 135	98.20 178	99.75 101	99.88 59	95.78 231	99.78 261	99.41 73	99.16 209	99.71 151

viewmambaseed2359dif		99.01 175	98.90 169	99.32 208	99.58 208	98.51 276	99.33 316	99.54 110	97.85 250	99.44 205	99.85 93	96.01 214	99.79 253	99.41 73	99.13 219	99.67 171

hybridnocas07		99.13 131	99.03 120	99.46 174	99.63 174	98.90 217	99.38 292	99.52 135	98.41 140	99.82 71	99.84 108	96.09 208	99.80 246	99.40 75	99.16 209	99.68 164

Casviewmamba		99.16 114	99.02 131	99.59 115	99.66 152	99.21 153	99.68 73	99.52 135	98.31 155	99.60 168	99.87 75	95.96 216	99.85 192	99.40 75	99.16 209	99.72 139

hybrid		99.11 147	99.01 139	99.41 189	99.64 169	98.76 247	99.35 308	99.52 135	98.31 155	99.80 79	99.84 108	96.16 204	99.79 253	99.40 75	99.06 244	99.68 164

diffmvs_AUTHOR		99.19 102	99.10 100	99.48 166	99.64 169	98.85 232	99.32 319	99.48 215	98.50 128	99.81 73	99.81 143	96.82 163	99.88 170	99.40 75	99.12 224	99.71 151

VortexMVS		98.67 224	98.66 208	98.68 315	99.62 184	97.96 311	99.59 129	99.41 286	98.13 192	99.31 244	99.70 226	95.48 244	99.27 390	99.40 75	97.32 367	98.79 343

ECVR-MVS		98.04 284	98.05 267	98.00 392	99.74 102	94.37 469	99.59 129	94.98 526	99.13 42	99.66 138	99.93 11	90.67 413	99.84 202	99.40 75	99.38 186	99.80 89

test2506		96.81 400	96.65 396	97.29 443	99.74 102	92.21 491	99.60 118	85.06 549	99.13 42	99.77 91	99.93 11	87.82 454	99.85 192	99.38 81	99.38 186	99.80 89

dtuplus		99.03 168	98.92 163	99.36 198	99.60 202	98.62 261	99.35 308	99.51 163	97.99 234	99.38 225	99.88 59	96.04 211	99.79 253	99.37 82	99.17 208	99.68 164

DeepC-MVS	98.35 2	99.30 83	99.19 88	99.64 103	99.82 54	99.23 151	99.62 109	99.55 101	98.94 80	99.63 156	99.95 4	95.82 227	99.94 92	99.37 82	99.97 10	99.73 129
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
reproduce_monomvs		97.89 308	97.87 288	97.96 397	99.51 239	95.45 438	99.60 118	99.25 375	99.17 37	98.85 348	99.49 326	89.29 431	99.64 323	99.35 84	96.31 391	98.78 345

alignmvs		98.81 207	98.56 227	99.58 119	99.43 271	99.42 121	99.51 196	98.96 422	98.61 115	99.35 237	98.92 442	94.78 280	99.77 266	99.35 84	98.11 320	99.54 230

PS-MVSNAJ		99.32 79	99.32 54	99.30 215	99.57 214	98.94 205	98.97 427	99.46 250	98.92 83	99.71 119	99.24 399	99.01 19	99.98 21	99.35 84	99.66 161	98.97 333

VPA-MVSNet		98.29 254	97.95 278	99.30 215	99.16 357	99.54 101	99.50 207	99.58 79	98.27 160	99.35 237	99.37 367	92.53 369	99.65 319	99.35 84	94.46 437	98.72 359

mvs_anonymous		99.03 168	98.99 145	99.16 236	99.38 289	98.52 274	99.51 196	99.38 305	97.79 260	99.38 225	99.81 143	97.30 133	99.45 350	99.35 84	98.99 252	99.51 245

test-260524					99.82 54	99.84 21		99.63 47		99.85 56		98.54 84	99.94 92	99.34 89	99.88 74

xiu_mvs_v2_base		99.26 92	99.25 77	99.29 218	99.53 230	98.91 212	99.02 413	99.45 261	98.80 96	99.71 119	99.26 397	98.94 34	99.98 21	99.34 89	99.23 203	98.98 331

nrg030		98.64 228	98.42 235	99.28 222	99.05 384	99.69 65	99.81 20	99.46 250	98.04 226	99.01 313	99.82 128	96.69 171	99.38 367	99.34 89	94.59 436	98.78 345

UGNet		98.87 191	98.69 203	99.40 191	99.22 338	98.72 251	99.44 257	99.68 24	99.24 34	99.18 284	99.42 348	92.74 359	99.96 42	99.34 89	99.94 31	99.53 235
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
TestfortrainingZip a		99.70 4	99.63 6	99.92 2	99.88 13	99.90 3	99.69 63	99.79 11	99.48 4	99.93 30	99.89 46	98.78 54	99.93 110	99.32 93	99.88 74	99.93 23

testing3-2		97.84 318	97.70 310	98.24 373	99.53 230	95.37 442	99.55 170	98.67 472	98.46 132	99.27 258	99.34 377	86.58 463	99.83 224	99.32 93	98.63 278	99.52 236

mvs_tets		98.40 244	98.23 248	98.91 271	98.67 446	98.51 276	99.66 84	99.53 126	98.19 180	98.65 378	99.81 143	92.75 357	99.44 355	99.31 95	97.48 357	98.77 349

VDDNet		97.55 362	97.02 386	99.16 236	99.49 253	98.12 301	99.38 292	99.30 357	95.35 434	99.68 127	99.90 37	82.62 491	99.93 110	99.31 95	98.13 319	99.42 273

diffmvs		99.14 127	99.02 131	99.51 148	99.61 195	98.96 195	99.28 337	99.49 203	98.46 132	99.72 109	99.71 222	96.50 183	99.88 170	99.31 95	99.11 226	99.67 171
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E5new		99.14 127	99.02 131	99.50 154	99.69 130	98.91 212	99.60 118	99.53 126	98.13 192	99.72 109	99.91 27	96.26 200	99.84 202	99.30 98	99.10 235	99.76 108

E6new		99.15 119	99.03 120	99.50 154	99.66 152	98.90 217	99.60 118	99.53 126	98.13 192	99.72 109	99.91 27	96.31 194	99.84 202	99.30 98	99.10 235	99.76 108

E6		99.15 119	99.03 120	99.50 154	99.66 152	98.90 217	99.60 118	99.53 126	98.13 192	99.72 109	99.91 27	96.31 194	99.84 202	99.30 98	99.10 235	99.76 108

E5		99.14 127	99.02 131	99.50 154	99.69 130	98.91 212	99.60 118	99.53 126	98.13 192	99.72 109	99.91 27	96.26 200	99.84 202	99.30 98	99.10 235	99.76 108

NormalMVS		99.27 89	99.19 88	99.52 143	99.89 8	98.83 237	99.65 90	99.52 135	99.10 49	99.84 57	99.76 198	95.80 229	99.99 4	99.30 98	99.84 103	99.74 119

SymmetryMVS		99.15 119	99.02 131	99.52 143	99.72 113	98.83 237	99.65 90	99.34 329	99.10 49	99.84 57	99.76 198	95.80 229	99.99 4	99.30 98	98.72 275	99.73 129

casdiffseed414692147		98.97 181	98.78 192	99.53 136	99.66 152	99.16 159	99.61 116	99.52 135	98.01 232	99.21 273	99.88 59	94.82 275	99.70 302	99.29 104	99.04 247	99.74 119

MGCFI-Net		99.01 175	98.85 183	99.50 154	99.42 273	99.26 147	99.82 16	99.48 215	98.60 117	99.28 252	98.81 449	97.04 149	99.76 270	99.29 104	97.87 330	99.47 259

lecture		99.60 15	99.50 20	99.89 13	99.89 8	99.90 3	99.75 43	99.59 74	99.06 62	99.88 43	99.85 93	98.41 95	99.96 42	99.28 106	99.84 103	99.83 65

LFMVS		97.90 307	97.35 358	99.54 128	99.52 236	99.01 184	99.39 287	98.24 489	97.10 343	99.65 148	99.79 178	84.79 479	99.91 137	99.28 106	98.38 295	99.69 158

MSLP-MVS++		99.46 43	99.47 25	99.44 182	99.60 202	99.16 159	99.41 275	99.71 16	98.98 73	99.45 200	99.78 185	99.19 10	99.54 341	99.28 106	99.84 103	99.63 197

viewdifsd2359ckpt07		99.11 147	99.00 143	99.43 186	99.63 174	98.73 249	99.45 250	99.54 110	98.33 151	99.62 160	99.81 143	96.17 203	99.87 177	99.27 109	99.14 216	99.69 158

sasdasda		99.02 170	98.86 180	99.51 148	99.42 273	99.32 134	99.80 25	99.48 215	98.63 112	99.31 244	98.81 449	97.09 145	99.75 274	99.27 109	97.90 326	99.47 259

canonicalmvs		99.02 170	98.86 180	99.51 148	99.42 273	99.32 134	99.80 25	99.48 215	98.63 112	99.31 244	98.81 449	97.09 145	99.75 274	99.27 109	97.90 326	99.47 259

Anonymous20240529		98.09 272	97.68 312	99.34 202	99.66 152	98.44 284	99.40 283	99.43 281	93.67 462	99.22 270	99.89 46	90.23 419	99.93 110	99.26 112	98.33 298	99.66 178

EPNet		98.86 194	98.71 201	99.30 215	97.20 496	98.18 295	99.62 109	98.91 432	99.28 33	98.63 381	99.81 143	95.96 216	99.99 4	99.24 113	99.72 150	99.73 129
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
jajsoiax		98.43 238	98.28 245	98.88 282	98.60 455	98.43 285	99.82 16	99.53 126	98.19 180	98.63 381	99.80 161	93.22 348	99.44 355	99.22 114	97.50 353	98.77 349

APDe-MVS		99.66 8	99.57 11	99.92 2	99.77 80	99.89 7	99.75 43	99.56 91	99.02 63	99.88 43	99.85 93	99.18 11	99.96 42	99.22 114	99.92 39	99.90 28
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
E4		99.13 131	99.01 139	99.49 161	99.68 137	98.90 217	99.52 186	99.52 135	98.13 192	99.71 119	99.90 37	96.32 192	99.84 202	99.21 116	99.11 226	99.75 114

viewmacassd2359aftdt		99.08 156	98.94 160	99.50 154	99.66 152	98.96 195	99.51 196	99.54 110	98.27 160	99.42 211	99.89 46	95.88 225	99.80 246	99.20 117	99.11 226	99.76 108

SSM_0407		99.13 131	99.03 120	99.43 186	99.62 184	98.88 223	99.51 196	99.50 188	98.14 189	99.37 228	99.85 93	96.85 157	99.83 224	99.19 118	99.25 200	99.60 205

SSM_0404		99.16 114	99.06 112	99.44 182	99.65 164	98.96 195	99.49 224	99.50 188	98.14 189	99.62 160	99.85 93	96.85 157	99.85 192	99.19 118	99.26 199	99.52 236

VPNet		97.84 318	97.44 346	99.01 252	99.21 339	98.94 205	99.48 232	99.57 86	98.38 143	99.28 252	99.73 215	88.89 434	99.39 365	99.19 118	93.27 460	98.71 361

mvsmamba		99.06 161	98.96 154	99.36 198	99.47 261	98.64 258	99.70 59	99.05 408	97.61 284	99.65 148	99.83 117	96.54 181	99.92 125	99.19 118	99.62 167	99.51 245

sss		99.17 110	99.05 115	99.53 136	99.62 184	98.97 191	99.36 302	99.62 53	97.83 254	99.67 133	99.65 259	97.37 130	99.95 77	99.19 118	99.19 207	99.68 164

Vis-MVSNet		99.12 141	98.97 150	99.56 125	99.78 72	99.10 170	99.68 73	99.66 33	98.49 129	99.86 53	99.87 75	94.77 283	99.84 202	99.19 118	99.41 185	99.74 119
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
E2		99.15 119	99.03 120	99.49 161	99.65 164	98.93 210	99.49 224	99.52 135	98.14 189	99.72 109	99.88 59	96.57 180	99.84 202	99.17 124	99.13 219	99.72 139

E3		99.15 119	99.03 120	99.49 161	99.62 184	98.91 212	99.49 224	99.52 135	98.13 192	99.72 109	99.88 59	96.61 175	99.84 202	99.17 124	99.13 219	99.72 139

ab-mvs		98.86 194	98.63 213	99.54 128	99.64 169	99.19 154	99.44 257	99.54 110	97.77 263	99.30 248	99.81 143	94.20 317	99.93 110	99.17 124	98.82 269	99.49 250

Anonymous202405211		98.30 253	97.98 274	99.26 224	99.57 214	98.16 296	99.41 275	98.55 479	96.03 426	99.19 280	99.74 209	91.87 384	99.92 125	99.16 127	98.29 305	99.70 155

viewmanbaseed2359cas		99.18 105	99.07 111	99.50 154	99.62 184	99.01 184	99.50 207	99.52 135	98.25 168	99.68 127	99.82 128	96.93 155	99.80 246	99.15 128	99.11 226	99.70 155

viewcassd2359sk11		99.18 105	99.08 106	99.49 161	99.65 164	98.95 201	99.48 232	99.51 163	98.10 206	99.72 109	99.87 75	97.13 141	99.84 202	99.13 129	99.14 216	99.69 158

PS-MVSNAJss		98.92 185	98.92 163	98.90 273	98.78 426	98.53 270	99.78 33	99.54 110	98.07 212	99.00 317	99.76 198	99.01 19	99.37 370	99.13 129	97.23 370	98.81 342

EPP-MVSNet		99.13 131	98.99 145	99.53 136	99.65 164	99.06 177	99.81 20	99.33 337	97.43 309	99.60 168	99.88 59	97.14 140	99.84 202	99.13 129	98.94 254	99.69 158

reproduce_model		99.63 10	99.54 14	99.90 9	99.78 72	99.88 11	99.56 155	99.55 101	99.15 39	99.90 35	99.90 37	99.00 24	99.97 30	99.11 132	99.91 46	99.86 44

Effi-MVS+		98.81 207	98.59 224	99.48 166	99.46 263	99.12 169	98.08 510	99.50 188	97.50 300	99.38 225	99.41 352	96.37 191	99.81 238	99.11 132	98.54 287	99.51 245

RRT-MVS		98.91 186	98.75 195	99.39 196	99.46 263	98.61 264	99.76 38	99.50 188	98.06 216	99.81 73	99.88 59	93.91 332	99.94 92	99.11 132	99.27 197	99.61 202

E3new		99.18 105	99.08 106	99.48 166	99.63 174	98.94 205	99.46 246	99.50 188	98.06 216	99.72 109	99.84 108	97.27 135	99.84 202	99.10 135	99.13 219	99.67 171

ETV-MVS		99.26 92	99.21 84	99.40 191	99.46 263	99.30 141	99.56 155	99.52 135	98.52 125	99.44 205	99.27 395	98.41 95	99.86 184	99.10 135	99.59 170	99.04 323

TSAR-MVS + GP.		99.36 73	99.36 46	99.36 198	99.67 140	98.61 264	99.07 398	99.33 337	99.00 68	99.82 71	99.81 143	99.06 17	99.84 202	99.09 137	99.42 184	99.65 185

FIs		98.78 212	98.63 213	99.23 230	99.18 347	99.54 101	99.83 15	99.59 74	98.28 158	98.79 356	99.81 143	96.75 168	99.37 370	99.08 138	96.38 388	98.78 345

FC-MVSNet-test		98.75 217	98.62 218	99.15 240	99.08 374	99.45 118	99.86 11	99.60 69	98.23 173	98.70 369	99.82 128	96.80 165	99.22 405	99.07 139	96.38 388	98.79 343

HPM-MVS_fast		99.51 30	99.40 38	99.85 44	99.91 1	99.79 43	99.76 38	99.56 91	97.72 270	99.76 97	99.75 203	99.13 13	99.92 125	99.07 139	99.92 39	99.85 48

PRO-TEST		99.17 110	99.08 106	99.45 176	99.37 292	99.14 165	99.62 109	99.50 188	98.59 119	99.69 126	99.58 289	96.72 170	99.76 270	99.06 141	99.58 171	99.44 269

viewdifsd2359ckpt13		99.06 161	98.93 162	99.45 176	99.63 174	98.96 195	99.50 207	99.51 163	97.83 254	99.28 252	99.80 161	96.68 173	99.71 294	99.05 142	99.12 224	99.68 164

reproduce-ours		99.61 11	99.52 15	99.90 9	99.76 84	99.88 11	99.52 186	99.54 110	99.13 42	99.89 40	99.89 46	98.96 27	99.96 42	99.04 143	99.90 57	99.85 48

our_new_method		99.61 11	99.52 15	99.90 9	99.76 84	99.88 11	99.52 186	99.54 110	99.13 42	99.89 40	99.89 46	98.96 27	99.96 42	99.04 143	99.90 57	99.85 48

MVSFormer		99.17 110	99.12 97	99.29 218	99.51 239	98.94 205	99.88 4	99.46 250	97.55 291	99.80 79	99.65 259	97.39 127	99.28 387	99.03 145	99.85 95	99.65 185

test_djsdf		98.67 224	98.57 225	98.98 256	98.70 441	98.91 212	99.88 4	99.46 250	97.55 291	99.22 270	99.88 59	95.73 234	99.28 387	99.03 145	97.62 341	98.75 353

jason		99.13 131	99.03 120	99.45 176	99.46 263	98.87 227	99.12 388	99.26 372	98.03 228	99.79 82	99.65 259	97.02 150	99.85 192	99.02 147	99.90 57	99.65 185
jason: jason.
DeepPCF-MVS	98.18 3	98.81 207	99.37 44	97.12 447	99.60 202	91.75 492	98.61 475	99.44 270	99.35 28	99.83 67	99.85 93	98.70 71	99.81 238	99.02 147	99.91 46	99.81 80

CSCG		99.32 79	99.32 54	99.32 208	99.85 32	98.29 290	99.71 58	99.66 33	98.11 202	99.41 216	99.80 161	98.37 98	99.96 42	98.99 149	99.96 18	99.72 139

mamba_0408		99.08 156	98.96 154	99.44 182	99.62 184	98.88 223	99.25 353	99.47 237	98.05 219	99.37 228	99.81 143	96.85 157	99.85 192	98.98 150	99.25 200	99.60 205

SSM_04072		99.06 161	98.96 154	99.35 201	99.62 184	98.88 223	99.25 353	99.47 237	98.05 219	99.37 228	99.81 143	96.85 157	99.58 335	98.98 150	99.25 200	99.60 205

ET-MVSNet_ETH3D		96.49 407	95.64 422	99.05 248	99.53 230	98.82 240	98.84 448	97.51 506	97.63 281	84.77 523	99.21 404	92.09 380	98.91 467	98.98 150	92.21 476	99.41 276

PVSNet_BlendedMVS		98.86 194	98.80 188	99.03 250	99.76 84	98.79 243	99.28 337	99.91 3	97.42 312	99.67 133	99.37 367	97.53 124	99.88 170	98.98 150	97.29 368	98.42 445

PVSNet_Blended		99.08 156	98.97 150	99.42 188	99.76 84	98.79 243	98.78 456	99.91 3	96.74 370	99.67 133	99.49 326	97.53 124	99.88 170	98.98 150	99.85 95	99.60 205

viewdifsd2359ckpt09		99.01 175	98.87 177	99.40 191	99.62 184	98.79 243	99.44 257	99.51 163	97.76 265	99.35 237	99.69 237	96.42 189	99.75 274	98.97 155	99.11 226	99.66 178

GDP-MVS		99.08 156	98.89 173	99.64 103	99.53 230	99.34 130	99.64 98	99.48 215	98.32 153	99.77 91	99.66 257	95.14 260	99.93 110	98.97 155	99.50 179	99.64 192

3Dnovator	97.25 9	99.24 97	99.05 115	99.81 61	99.12 363	99.66 73	99.84 12	99.74 13	99.09 56	98.92 330	99.90 37	95.94 220	99.98 21	98.95 157	99.92 39	99.79 93

WBMVS		97.74 339	97.50 333	98.46 346	99.24 332	97.43 337	99.21 367	99.42 283	97.45 305	98.96 324	99.41 352	88.83 435	99.23 398	98.94 158	96.02 397	98.71 361

EIA-MVS		99.18 105	99.09 105	99.45 176	99.49 253	99.18 156	99.67 77	99.53 126	97.66 279	99.40 221	99.44 344	98.10 109	99.81 238	98.94 158	99.62 167	99.35 286

lupinMVS		99.13 131	99.01 139	99.46 174	99.51 239	98.94 205	99.05 405	99.16 392	97.86 247	99.80 79	99.56 298	97.39 127	99.86 184	98.94 158	99.85 95	99.58 220

DVP-MVS		99.57 21	99.47 25	99.88 17	99.85 32	99.89 7	99.57 147	99.37 315	99.10 49	99.81 73	99.80 161	98.94 34	99.96 42	98.93 161	99.86 88	99.81 80
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				99.91 7	99.84 39	99.89 7	99.57 147	99.51 163					99.96 42	98.93 161	99.86 88	99.88 37

UA-Net		99.42 56	99.29 66	99.80 65	99.62 184	99.55 99	99.50 207	99.70 18	98.79 97	99.77 91	99.96 2	97.45 126	99.96 42	98.92 163	99.90 57	99.89 31

SED-MVS		99.61 11	99.52 15	99.88 17	99.84 39	99.90 3	99.60 118	99.48 215	99.08 57	99.91 32	99.81 143	99.20 8	99.96 42	98.91 164	99.85 95	99.79 93

test_241102_TWO								99.48 215	99.08 57	99.88 43	99.81 143	98.94 34	99.96 42	98.91 164	99.84 103	99.88 37

MVS_111021_HR		99.41 60	99.32 54	99.66 93	99.72 113	99.47 116	98.95 431	99.85 8	98.82 91	99.54 185	99.73 215	98.51 87	99.74 277	98.91 164	99.88 74	99.77 101

MTAPA		99.52 29	99.39 40	99.89 13	99.90 4	99.86 19	99.66 84	99.47 237	98.79 97	99.68 127	99.81 143	98.43 92	99.97 30	98.88 167	99.90 57	99.83 65

XXY-MVS		98.38 245	98.09 262	99.24 228	99.26 326	99.32 134	99.56 155	99.55 101	97.45 305	98.71 363	99.83 117	93.23 346	99.63 329	98.88 167	96.32 390	98.76 351

ACMH	97.28 8	98.10 271	97.99 273	98.44 351	99.41 278	96.96 371	99.60 118	99.56 91	98.09 207	98.15 423	99.91 27	90.87 411	99.70 302	98.88 167	97.45 358	98.67 383
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MSC_two_6792asdad				99.87 23	99.51 239	99.76 51		99.33 337					99.96 42	98.87 170	99.84 103	99.89 31

No_MVS				99.87 23	99.51 239	99.76 51		99.33 337					99.96 42	98.87 170	99.84 103	99.89 31

MVS_Test		99.10 153	98.97 150	99.48 166	99.49 253	99.14 165	99.67 77	99.34 329	97.31 321	99.58 173	99.76 198	97.65 123	99.82 233	98.87 170	99.07 243	99.46 264

MVSTER		98.49 233	98.32 242	99.00 254	99.35 297	99.02 182	99.54 175	99.38 305	97.41 313	99.20 277	99.73 215	93.86 334	99.36 374	98.87 170	97.56 346	98.62 405

1112_ss		98.98 179	98.77 193	99.59 115	99.68 137	99.02 182	99.25 353	99.48 215	97.23 329	99.13 289	99.58 289	96.93 155	99.90 150	98.87 170	98.78 272	99.84 55

IU-MVS					99.84 39	99.88 11		99.32 348	98.30 157	99.84 57				98.86 175	99.85 95	99.89 31

3Dnovator+	97.12 13	99.18 105	98.97 150	99.82 58	99.17 355	99.68 66	99.81 20	99.51 163	99.20 35	98.72 362	99.89 46	95.68 236	99.97 30	98.86 175	99.86 88	99.81 80

DVP-MVS++		99.59 16	99.50 20	99.88 17	99.51 239	99.88 11	99.87 8	99.51 163	98.99 70	99.88 43	99.81 143	99.27 6	99.96 42	98.85 177	99.80 127	99.81 80

test_0728_THIRD									98.99 70	99.81 73	99.80 161	99.09 15	99.96 42	98.85 177	99.90 57	99.88 37

WTY-MVS		99.06 161	98.88 176	99.61 111	99.62 184	99.16 159	99.37 296	99.56 91	98.04 226	99.53 187	99.62 276	96.84 162	99.94 92	98.85 177	98.49 290	99.72 139

TSAR-MVS + MP.		99.58 17	99.50 20	99.81 61	99.91 1	99.66 73	99.63 104	99.39 296	98.91 84	99.78 87	99.85 93	99.36 2	99.94 92	98.84 180	99.88 74	99.82 73
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
Anonymous20231211		97.88 309	97.54 327	98.90 273	99.71 119	98.53 270	99.48 232	99.57 86	94.16 456	98.81 352	99.68 245	93.23 346	99.42 362	98.84 180	94.42 440	98.76 351

114514_t		98.93 184	98.67 205	99.72 87	99.85 32	99.53 104	99.62 109	99.59 74	92.65 479	99.71 119	99.78 185	98.06 112	99.90 150	98.84 180	99.91 46	99.74 119

aaatest				99.87 23	99.88 13	99.81 35	99.69 63	99.87 6	99.34 29	99.90 35	99.83 117		99.95 77	98.83 183	99.89 68	99.83 65

MED-MVS		99.70 4	99.63 6	99.90 9	99.88 13	99.81 35	99.69 63	99.87 6	99.48 4	99.90 35	99.89 46	99.30 4	99.95 77	98.83 183	99.88 74	99.93 23

aaEdge-Enhanced		99.56 22	99.46 29	99.86 35	99.80 65	99.81 35	99.37 296	99.70 18	99.18 36	99.83 67	99.83 117	98.74 67	99.93 110	98.83 183	99.89 68	99.83 65

tttt0517		98.42 239	98.14 254	99.28 222	99.66 152	98.38 288	99.74 48	96.85 513	97.68 276	99.79 82	99.74 209	91.39 400	99.89 165	98.83 183	99.56 173	99.57 223

MP-MVS-pluss		99.37 69	99.20 86	99.88 17	99.90 4	99.87 18	99.30 326	99.52 135	97.18 333	99.60 168	99.79 178	98.79 53	99.95 77	98.83 183	99.91 46	99.83 65
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
Test_1112_low_res		98.89 187	98.66 208	99.57 123	99.69 130	98.95 201	99.03 410	99.47 237	96.98 353	99.15 287	99.23 400	96.77 167	99.89 165	98.83 183	98.78 272	99.86 44

MVS_111021_LR		99.41 60	99.33 52	99.65 97	99.77 80	99.51 110	98.94 433	99.85 8	98.82 91	99.65 148	99.74 209	98.51 87	99.80 246	98.83 183	99.89 68	99.64 192

ACMMP_NAP		99.47 41	99.34 50	99.88 17	99.87 21	99.86 19	99.47 242	99.48 215	98.05 219	99.76 97	99.86 86	98.82 49	99.93 110	98.82 190	99.91 46	99.84 55

SMA-MVS		99.44 51	99.30 62	99.85 44	99.73 109	99.83 24	99.56 155	99.47 237	97.45 305	99.78 87	99.82 128	99.18 11	99.91 137	98.79 191	99.89 68	99.81 80
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
XVS		99.53 28	99.42 33	99.87 23	99.85 32	99.83 24	99.69 63	99.68 24	98.98 73	99.37 228	99.74 209	98.81 50	99.94 92	98.79 191	99.86 88	99.84 55

X-MVStestdata		96.55 405	95.45 425	99.87 23	99.85 32	99.83 24	99.69 63	99.68 24	98.98 73	99.37 228	64.01 558	98.81 50	99.94 92	98.79 191	99.86 88	99.84 55

nomal-1		97.78 331	97.52 329	98.54 336	99.27 321	96.47 399	99.32 319	98.56 476	97.43 309	98.92 330	98.91 443	88.14 449	99.72 287	98.75 194	98.39 293	99.44 269

CVMVSNet		98.57 231	98.67 205	98.30 365	99.35 297	95.59 431	99.50 207	99.55 101	98.60 117	99.39 223	99.83 117	94.48 306	99.45 350	98.75 194	98.56 285	99.85 48

CP-MVS		99.45 47	99.32 54	99.85 44	99.83 48	99.75 53	99.69 63	99.52 135	98.07 212	99.53 187	99.63 271	98.93 38	99.97 30	98.74 196	99.91 46	99.83 65

ACMM	97.58 5	98.37 247	98.34 240	98.48 340	99.41 278	97.10 352	99.56 155	99.45 261	98.53 124	99.04 310	99.85 93	93.00 351	99.71 294	98.74 196	97.45 358	98.64 396
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Effi-MVS+-dtu		98.78 212	98.89 173	98.47 345	99.33 303	96.91 377	99.57 147	99.30 357	98.47 131	99.41 216	98.99 432	96.78 166	99.74 277	98.73 198	99.38 186	98.74 357

ZNCC-MVS		99.47 41	99.33 52	99.87 23	99.87 21	99.81 35	99.64 98	99.67 27	98.08 211	99.55 184	99.64 265	98.91 39	99.96 42	98.72 199	99.90 57	99.82 73

SD-MVS		99.41 60	99.52 15	99.05 248	99.74 102	99.68 66	99.46 246	99.52 135	99.11 48	99.88 43	99.91 27	99.43 1	97.70 499	98.72 199	99.93 33	99.77 101
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
D2MVS		98.41 241	98.50 231	98.15 381	99.26 326	96.62 393	99.40 283	99.61 62	97.71 271	98.98 320	99.36 370	96.04 211	99.67 311	98.70 201	97.41 363	98.15 463

CDS-MVSNet		99.09 154	99.03 120	99.25 225	99.42 273	98.73 249	99.45 250	99.46 250	98.11 202	99.46 199	99.77 194	98.01 114	99.37 370	98.70 201	98.92 257	99.66 178
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		99.12 141	99.08 106	99.24 228	99.46 263	98.55 268	99.51 196	99.46 250	98.09 207	99.45 200	99.82 128	98.34 99	99.51 343	98.70 201	98.93 255	99.67 171

HFP-MVS		99.49 34	99.37 44	99.86 35	99.87 21	99.80 40	99.66 84	99.67 27	98.15 185	99.68 127	99.69 237	99.06 17	99.96 42	98.69 204	99.87 80	99.84 55

ACMMPR		99.49 34	99.36 46	99.86 35	99.87 21	99.79 43	99.66 84	99.67 27	98.15 185	99.67 133	99.69 237	98.95 32	99.96 42	98.69 204	99.87 80	99.84 55

UniMVSNet_ETH3D		97.32 383	96.81 392	98.87 286	99.40 283	97.46 336	99.51 196	99.53 126	95.86 429	98.54 391	99.77 194	82.44 492	99.66 314	98.68 206	97.52 350	99.50 249

DeepC-MVS_fast	98.69 1	99.49 34	99.39 40	99.77 75	99.63 174	99.59 91	99.36 302	99.46 250	99.07 59	99.79 82	99.82 128	98.85 44	99.92 125	98.68 206	99.87 80	99.82 73
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
anonymousdsp		98.44 237	98.28 245	98.94 263	98.50 462	98.96 195	99.77 35	99.50 188	97.07 345	98.87 341	99.77 194	94.76 284	99.28 387	98.66 208	97.60 342	98.57 427

DP-MVS		99.16 114	98.95 158	99.78 72	99.77 80	99.53 104	99.41 275	99.50 188	97.03 351	99.04 310	99.88 59	97.39 127	99.92 125	98.66 208	99.90 57	99.87 42

MonoMVSNet		98.38 245	98.47 233	98.12 383	98.59 457	96.19 411	99.72 54	98.79 453	97.89 244	99.44 205	99.52 316	96.13 205	98.90 469	98.64 210	97.54 348	99.28 295

MCST-MVS		99.43 54	99.30 62	99.82 58	99.79 70	99.74 56	99.29 331	99.40 293	98.79 97	99.52 189	99.62 276	98.91 39	99.90 150	98.64 210	99.75 144	99.82 73

CP-MVSNet		98.09 272	97.78 298	99.01 252	98.97 399	99.24 150	99.67 77	99.46 250	97.25 326	98.48 396	99.64 265	93.79 336	99.06 438	98.63 212	94.10 448	98.74 357

thisisatest0530		98.35 249	98.03 269	99.31 210	99.63 174	98.56 267	99.54 175	96.75 515	97.53 296	99.73 104	99.65 259	91.25 404	99.89 165	98.62 213	99.56 173	99.48 253

region2R		99.48 38	99.35 48	99.87 23	99.88 13	99.80 40	99.65 90	99.66 33	98.13 192	99.66 138	99.68 245	98.96 27	99.96 42	98.62 213	99.87 80	99.84 55

APD-MVS_3200maxsize		99.48 38	99.35 48	99.85 44	99.76 84	99.83 24	99.63 104	99.54 110	98.36 147	99.79 82	99.82 128	98.86 43	99.95 77	98.62 213	99.81 122	99.78 99

SR-MVS-dyc-post		99.45 47	99.31 60	99.85 44	99.76 84	99.82 30	99.63 104	99.52 135	98.38 143	99.76 97	99.82 128	98.53 85	99.95 77	98.61 216	99.81 122	99.77 101

RE-MVS-def			99.34 50		99.76 84	99.82 30	99.63 104	99.52 135	98.38 143	99.76 97	99.82 128	98.75 62		98.61 216	99.81 122	99.77 101

PHI-MVS		99.30 83	99.17 91	99.70 88	99.56 218	99.52 108	99.58 139	99.80 10	97.12 339	99.62 160	99.73 215	98.58 80	99.90 150	98.61 216	99.91 46	99.68 164

test_yl		98.86 194	98.63 213	99.54 128	99.49 253	99.18 156	99.50 207	99.07 405	98.22 174	99.61 165	99.51 320	95.37 247	99.84 202	98.60 219	98.33 298	99.59 216

DCV-MVSNet		98.86 194	98.63 213	99.54 128	99.49 253	99.18 156	99.50 207	99.07 405	98.22 174	99.61 165	99.51 320	95.37 247	99.84 202	98.60 219	98.33 298	99.59 216

CNVR-MVS		99.42 56	99.30 62	99.78 72	99.62 184	99.71 60	99.26 351	99.52 135	98.82 91	99.39 223	99.71 222	98.96 27	99.85 192	98.59 221	99.80 127	99.77 101

tt0805		97.97 298	97.77 300	98.57 326	99.59 206	96.61 394	99.45 250	99.08 402	98.21 176	98.88 338	99.80 161	88.66 439	99.70 302	98.58 222	97.72 336	99.39 280

WR-MVS		98.06 278	97.73 307	99.06 246	98.86 416	99.25 149	99.19 373	99.35 324	97.30 322	98.66 372	99.43 346	93.94 329	99.21 410	98.58 222	94.28 443	98.71 361

HPM-MVS		99.42 56	99.28 69	99.83 57	99.90 4	99.72 58	99.81 20	99.54 110	97.59 285	99.68 127	99.63 271	98.91 39	99.94 92	98.58 222	99.91 46	99.84 55
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
UniMVSNet_NR-MVSNet		98.22 257	97.97 275	98.96 259	98.92 404	98.98 187	99.48 232	99.53 126	97.76 265	98.71 363	99.46 341	96.43 188	99.22 405	98.57 225	92.87 470	98.69 370

DU-MVS		98.08 276	97.79 295	98.96 259	98.87 413	98.98 187	99.41 275	99.45 261	97.87 246	98.71 363	99.50 323	94.82 275	99.22 405	98.57 225	92.87 470	98.68 375

mPP-MVS		99.44 51	99.30 62	99.86 35	99.88 13	99.79 43	99.69 63	99.48 215	98.12 200	99.50 192	99.75 203	98.78 54	99.97 30	98.57 225	99.89 68	99.83 65

CANet_DTU		98.97 181	98.87 177	99.25 225	99.33 303	98.42 287	99.08 397	99.30 357	99.16 38	99.43 208	99.75 203	95.27 252	99.97 30	98.56 228	99.95 23	99.36 285

PMMVS		98.80 210	98.62 218	99.34 202	99.27 321	98.70 252	98.76 460	99.31 352	97.34 318	99.21 273	99.07 417	97.20 139	99.82 233	98.56 228	98.87 264	99.52 236

PVSNet	96.02 17	98.85 203	98.84 185	98.89 277	99.73 109	97.28 342	98.32 499	99.60 69	97.86 247	99.50 192	99.57 295	96.75 168	99.86 184	98.56 228	99.70 154	99.54 230

ACMMP		99.45 47	99.32 54	99.82 58	99.89 8	99.67 70	99.62 109	99.69 22	98.12 200	99.63 156	99.84 108	98.73 68	99.96 42	98.55 231	99.83 115	99.81 80
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
XVG-OURS-SEG-HR		98.69 222	98.62 218	98.89 277	99.71 119	97.74 323	99.12 388	99.54 110	98.44 137	99.42 211	99.71 222	94.20 317	99.92 125	98.54 232	98.90 263	99.00 327

PS-CasMVS		97.93 301	97.59 323	98.95 261	98.99 394	99.06 177	99.68 73	99.52 135	97.13 337	98.31 411	99.68 245	92.44 375	99.05 439	98.51 233	94.08 449	98.75 353

CostFormer		97.72 343	97.73 307	97.71 424	99.15 361	94.02 473	99.54 175	99.02 413	94.67 451	99.04 310	99.35 373	92.35 377	99.77 266	98.50 234	97.94 325	99.34 289

baseline1		98.31 251	97.95 278	99.38 197	99.50 251	98.74 248	99.59 129	98.93 424	98.41 140	99.14 288	99.60 283	94.59 298	99.79 253	98.48 235	93.29 459	99.61 202

SteuartSystems-ACMMP		99.54 25	99.42 33	99.87 23	99.82 54	99.81 35	99.59 129	99.51 163	98.62 114	99.79 82	99.83 117	99.28 5	99.97 30	98.48 235	99.90 57	99.84 55
Skip Steuart: Steuart Systems R&D Blog.
tpmrst		98.33 250	98.48 232	97.90 402	99.16 357	94.78 457	99.31 324	99.11 398	97.27 324	99.45 200	99.59 285	95.33 250	99.84 202	98.48 235	98.61 279	99.09 314

0.4-1-1-0.1		95.23 438	94.22 447	98.26 372	97.39 490	95.86 423	97.59 520	97.62 501	93.85 459	94.97 484	97.03 509	87.20 457	99.87 177	98.47 238	83.84 510	99.05 322

IB-MVS	95.67 18	96.22 411	95.44 426	98.57 326	99.21 339	96.70 387	98.65 472	97.74 500	96.71 372	97.27 452	98.54 463	86.03 468	99.92 125	98.47 238	86.30 505	99.10 310
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
MSP-MVS		99.42 56	99.27 73	99.88 17	99.89 8	99.80 40	99.67 77	99.50 188	98.70 108	99.77 91	99.49 326	98.21 104	99.95 77	98.46 240	99.77 139	99.88 37
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
testing11		97.50 368	97.10 382	98.71 311	99.20 341	96.91 377	99.29 331	98.82 446	97.89 244	98.21 419	98.40 468	85.63 471	99.83 224	98.45 241	98.04 322	99.37 284

myMVS_eth3d28		97.69 348	97.34 361	98.73 306	99.27 321	97.52 334	99.33 316	98.78 454	98.03 228	98.82 351	98.49 464	86.64 462	99.46 348	98.44 242	98.24 308	99.23 302

SR-MVS		99.43 54	99.29 66	99.86 35	99.75 94	99.83 24	99.59 129	99.62 53	98.21 176	99.73 104	99.79 178	98.68 72	99.96 42	98.44 242	99.77 139	99.79 93

HPM-MVS++		99.39 67	99.23 82	99.87 23	99.75 94	99.84 21	99.43 263	99.51 163	98.68 111	99.27 258	99.53 311	98.64 77	99.96 42	98.44 242	99.80 127	99.79 93

0.3-1-1-0.015		94.79 446	93.69 459	98.10 384	96.99 502	95.46 437	97.02 525	97.61 503	93.53 464	94.03 492	96.54 514	85.60 472	99.86 184	98.43 245	83.45 515	98.99 330

0.4-1-1-0.2		94.94 445	93.92 453	97.99 393	96.84 503	95.13 450	96.64 527	97.62 501	93.45 468	94.92 485	96.56 513	87.14 459	99.86 184	98.43 245	83.69 514	98.98 331

KinetiMVS		99.12 141	98.92 163	99.70 88	99.67 140	99.40 124	99.67 77	99.63 47	98.73 104	99.94 29	99.81 143	94.54 303	99.96 42	98.40 247	99.93 33	99.74 119

LTVRE_ROB	97.16 12	98.02 288	97.90 283	98.40 356	99.23 334	96.80 385	99.70 59	99.60 69	97.12 339	98.18 421	99.70 226	91.73 389	99.72 287	98.39 248	97.45 358	98.68 375
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
GST-MVS		99.40 65	99.24 78	99.85 44	99.86 26	99.79 43	99.60 118	99.67 27	97.97 237	99.63 156	99.68 245	98.52 86	99.95 77	98.38 249	99.86 88	99.81 80

EI-MVSNet		98.67 224	98.67 205	98.68 315	99.35 297	97.97 309	99.50 207	99.38 305	96.93 360	99.20 277	99.83 117	97.87 116	99.36 374	98.38 249	97.56 346	98.71 361

HY-MVS	97.30 7	98.85 203	98.64 212	99.47 172	99.42 273	99.08 174	99.62 109	99.36 317	97.39 315	99.28 252	99.68 245	96.44 187	99.92 125	98.37 251	98.22 309	99.40 279

TDRefinement		95.42 432	94.57 442	97.97 395	89.83 549	96.11 413	99.48 232	98.75 456	96.74 370	96.68 466	99.88 59	88.65 440	99.71 294	98.37 251	82.74 518	98.09 466

ttmdpeth		97.80 328	97.63 319	98.29 366	98.77 431	97.38 339	99.64 98	99.36 317	98.78 100	96.30 470	99.58 289	92.34 378	99.39 365	98.36 253	95.58 413	98.10 465

UniMVSNet (Re)		98.29 254	98.00 272	99.13 242	99.00 391	99.36 129	99.49 224	99.51 163	97.95 238	98.97 322	99.13 411	96.30 196	99.38 367	98.36 253	93.34 458	98.66 392

WR-MVS_H		98.13 268	97.87 288	98.90 273	99.02 388	98.84 234	99.70 59	99.59 74	97.27 324	98.40 402	99.19 405	95.53 241	99.23 398	98.34 255	93.78 454	98.61 414

PGM-MVS		99.45 47	99.31 60	99.86 35	99.87 21	99.78 49	99.58 139	99.65 40	97.84 253	99.71 119	99.80 161	99.12 14	99.97 30	98.33 256	99.87 80	99.83 65

LS3D		99.27 89	99.12 97	99.74 81	99.18 347	99.75 53	99.56 155	99.57 86	98.45 134	99.49 195	99.85 93	97.77 120	99.94 92	98.33 256	99.84 103	99.52 236

IterMVS-LS		98.46 236	98.42 235	98.58 325	99.59 206	98.00 307	99.37 296	99.43 281	96.94 359	99.07 302	99.59 285	97.87 116	99.03 442	98.32 258	95.62 412	98.71 361
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CLD-MVS		98.16 265	98.10 259	98.33 361	99.29 316	96.82 383	98.75 461	99.44 270	97.83 254	99.13 289	99.55 301	92.92 353	99.67 311	98.32 258	97.69 337	98.48 437
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PC_three_1452									98.18 183	99.84 57	99.70 226	99.31 3	98.52 481	98.30 260	99.80 127	99.81 80

sc_t1		95.75 423	95.05 431	97.87 404	98.83 420	94.61 464	99.21 367	99.45 261	87.45 507	97.97 432	99.85 93	81.19 497	99.43 359	98.27 261	93.20 462	99.57 223

UBG		97.85 314	97.48 335	98.95 261	99.25 330	97.64 330	99.24 358	98.74 460	97.90 243	98.64 379	98.20 477	88.65 440	99.81 238	98.27 261	98.40 292	99.42 273

NCCC		99.34 76	99.19 88	99.79 69	99.61 195	99.65 77	99.30 326	99.48 215	98.86 86	99.21 273	99.63 271	98.72 69	99.90 150	98.25 263	99.63 166	99.80 89

OPU-MVS				99.64 103	99.56 218	99.72 58	99.60 118				99.70 226	99.27 6	99.42 362	98.24 264	99.80 127	99.79 93

GeoE		98.85 203	98.62 218	99.53 136	99.61 195	99.08 174	99.80 25	99.51 163	97.10 343	99.31 244	99.78 185	95.23 257	99.77 266	98.21 265	99.03 248	99.75 114

cl22		97.85 314	97.64 318	98.48 340	99.09 371	97.87 318	98.60 478	99.33 337	97.11 342	98.87 341	99.22 401	92.38 376	99.17 416	98.21 265	95.99 400	98.42 445

SF-MVS		99.38 68	99.24 78	99.79 69	99.79 70	99.68 66	99.57 147	99.54 110	97.82 259	99.71 119	99.80 161	98.95 32	99.93 110	98.19 267	99.84 103	99.74 119

旧先验2							98.96 428		96.70 373	99.47 197			99.94 92	98.19 267

F-COLMAP		99.19 102	99.04 117	99.64 103	99.78 72	99.27 146	99.42 270	99.54 110	97.29 323	99.41 216	99.59 285	98.42 94	99.93 110	98.19 267	99.69 155	99.73 129

LCM-MVSNet-Re		97.83 321	98.15 253	96.87 456	99.30 312	92.25 490	99.59 129	98.26 487	97.43 309	96.20 471	99.13 411	96.27 197	98.73 477	98.17 270	98.99 252	99.64 192

DPE-MVS		99.46 43	99.32 54	99.91 7	99.78 72	99.88 11	99.36 302	99.51 163	98.73 104	99.88 43	99.84 108	98.72 69	99.96 42	98.16 271	99.87 80	99.88 37
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
cascas		97.69 348	97.43 350	98.48 340	98.60 455	97.30 341	98.18 505	99.39 296	92.96 475	98.41 401	98.78 453	93.77 337	99.27 390	98.16 271	98.61 279	98.86 339

icg_test_0407_2		98.79 211	98.86 180	98.57 326	99.55 222	96.93 372	99.07 398	99.44 270	98.05 219	99.66 138	99.80 161	97.13 141	99.18 414	98.15 273	98.92 257	99.60 205

IMVS_0407		98.86 194	98.91 167	98.72 308	99.55 222	96.93 372	99.50 207	99.44 270	98.05 219	99.66 138	99.80 161	97.13 141	99.65 319	98.15 273	98.92 257	99.60 205

IMVS_0404		98.53 232	98.52 230	98.55 332	99.55 222	96.93 372	99.20 370	99.44 270	98.05 219	98.96 324	99.80 161	94.66 295	99.13 422	98.15 273	98.92 257	99.60 205

IMVS_0403		98.86 194	98.89 173	98.78 303	99.55 222	96.93 372	99.58 139	99.44 270	98.05 219	99.68 127	99.80 161	96.81 164	99.80 246	98.15 273	98.92 257	99.60 205

COLMAP_ROB	97.56 6	98.86 194	98.75 195	99.17 235	99.88 13	98.53 270	99.34 314	99.59 74	97.55 291	98.70 369	99.89 46	95.83 226	99.90 150	98.10 277	99.90 57	99.08 315
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PEN-MVS		97.76 333	97.44 346	98.72 308	98.77 431	98.54 269	99.78 33	99.51 163	97.06 347	98.29 414	99.64 265	92.63 366	98.89 470	98.09 278	93.16 463	98.72 359

LPG-MVS_test		98.22 257	98.13 256	98.49 338	99.33 303	97.05 358	99.58 139	99.55 101	97.46 302	99.24 265	99.83 117	92.58 367	99.72 287	98.09 278	97.51 351	98.68 375

LGP-MVS_train				98.49 338	99.33 303	97.05 358		99.55 101	97.46 302	99.24 265	99.83 117	92.58 367	99.72 287	98.09 278	97.51 351	98.68 375

IS-MVSNet		99.05 165	98.87 177	99.57 123	99.73 109	99.32 134	99.75 43	99.20 386	98.02 231	99.56 178	99.86 86	96.54 181	99.67 311	98.09 278	99.13 219	99.73 129

thisisatest0515		98.14 267	97.79 295	99.19 233	99.50 251	98.50 278	98.61 475	96.82 514	96.95 357	99.54 185	99.43 346	91.66 393	99.86 184	98.08 282	99.51 177	99.22 303

OPM-MVS		98.19 261	98.10 259	98.45 348	98.88 410	97.07 356	99.28 337	99.38 305	98.57 120	99.22 270	99.81 143	92.12 379	99.66 314	98.08 282	97.54 348	98.61 414
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
XVG-OURS		98.73 220	98.68 204	98.88 282	99.70 124	97.73 324	98.92 435	99.55 101	98.52 125	99.45 200	99.84 108	95.27 252	99.91 137	98.08 282	98.84 267	99.00 327

Baseline_NR-MVSNet		97.76 333	97.45 341	98.68 315	99.09 371	98.29 290	99.41 275	98.85 443	95.65 431	98.63 381	99.67 252	94.82 275	99.10 432	98.07 285	92.89 469	98.64 396

ACMH+	97.24 10	97.92 304	97.78 298	98.32 363	99.46 263	96.68 391	99.56 155	99.54 110	98.41 140	97.79 441	99.87 75	90.18 422	99.66 314	98.05 286	97.18 373	98.62 405

testing99		97.36 379	96.94 389	98.63 318	99.18 347	96.70 387	99.30 326	98.93 424	97.71 271	98.23 416	98.26 475	84.92 478	99.84 202	98.04 287	97.85 332	99.35 286

testing91		97.44 376	97.02 386	98.71 311	99.18 347	96.89 379	99.19 373	99.04 409	97.78 262	98.31 411	98.29 473	85.41 474	99.85 192	98.01 288	97.95 324	99.39 280

TranMVSNet+NR-MVSNet		97.93 301	97.66 314	98.76 305	98.78 426	98.62 261	99.65 90	99.49 203	97.76 265	98.49 395	99.60 283	94.23 316	98.97 461	98.00 289	92.90 468	98.70 366

DP-MVS Recon		99.12 141	98.95 158	99.65 97	99.74 102	99.70 62	99.27 342	99.57 86	96.40 401	99.42 211	99.68 245	98.75 62	99.80 246	97.98 290	99.72 150	99.44 269

test_prior2							98.96 428		98.34 149	99.01 313	99.52 316	98.68 72		97.96 291	99.74 147

Fast-Effi-MVS+-dtu		98.77 216	98.83 187	98.60 320	99.41 278	96.99 367	99.52 186	99.49 203	98.11 202	99.24 265	99.34 377	96.96 154	99.79 253	97.95 292	99.45 182	99.02 326

MP-MVS		99.33 78	99.15 93	99.87 23	99.88 13	99.82 30	99.66 84	99.46 250	98.09 207	99.48 196	99.74 209	98.29 101	99.96 42	97.93 293	99.87 80	99.82 73
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
Vis-MVSNet (Re-imp)		98.87 191	98.72 199	99.31 210	99.71 119	98.88 223	99.80 25	99.44 270	97.91 242	99.36 234	99.78 185	95.49 243	99.43 359	97.91 294	99.11 226	99.62 200

ACMP	97.20 11	98.06 278	97.94 280	98.45 348	99.37 292	97.01 365	99.44 257	99.49 203	97.54 295	98.45 399	99.79 178	91.95 383	99.72 287	97.91 294	97.49 356	98.62 405
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_fmvs2		97.25 386	97.30 368	97.09 448	99.43 271	93.31 483	99.73 52	98.87 440	98.83 90	99.28 252	99.80 161	84.45 481	99.66 314	97.88 296	97.45 358	98.30 453

Fast-Effi-MVS+		98.70 221	98.43 234	99.51 148	99.51 239	99.28 144	99.52 186	99.47 237	96.11 421	99.01 313	99.34 377	96.20 202	99.84 202	97.88 296	98.82 269	99.39 280

EPMVS		97.82 324	97.65 315	98.35 360	98.88 410	95.98 414	99.49 224	94.71 531	97.57 288	99.26 263	99.48 334	92.46 374	99.71 294	97.87 298	99.08 242	99.35 286

ETVMVS		97.50 368	96.90 390	99.29 218	99.23 334	98.78 246	99.32 319	98.90 434	97.52 298	98.56 389	98.09 484	84.72 480	99.69 308	97.86 299	97.88 329	99.39 280

miper_enhance_ethall		98.16 265	98.08 263	98.41 354	98.96 400	97.72 325	98.45 492	99.32 348	96.95 357	98.97 322	99.17 406	97.06 148	99.22 405	97.86 299	95.99 400	98.29 454

tmp_tt		82.80 494	81.52 498	86.66 512	66.61 560	68.44 544	92.79 542	97.92 495	68.96 530	80.04 538	99.85 93	85.77 469	96.15 516	97.86 299	43.89 552	95.39 521

NR-MVSNet		97.97 298	97.61 321	99.02 251	98.87 413	99.26 147	99.47 242	99.42 283	97.63 281	97.08 459	99.50 323	95.07 262	99.13 422	97.86 299	93.59 455	98.68 375

v148		97.79 330	97.55 324	98.50 337	98.74 434	97.72 325	99.54 175	99.33 337	96.26 408	98.90 334	99.51 320	94.68 292	99.14 419	97.83 303	93.15 464	98.63 403

CPTT-MVS		99.11 147	98.90 169	99.74 81	99.80 65	99.46 117	99.59 129	99.49 203	97.03 351	99.63 156	99.69 237	97.27 135	99.96 42	97.82 304	99.84 103	99.81 80

MDTV_nov1_ep13_2view						95.18 447	99.35 308		96.84 364	99.58 173		95.19 258		97.82 304		99.46 264

Elysia		98.88 188	98.65 210	99.58 119	99.58 208	99.34 130	99.65 90	99.52 135	98.26 163	99.83 67	99.87 75	93.37 343	99.90 150	97.81 306	99.91 46	99.49 250

StellarMVS		98.88 188	98.65 210	99.58 119	99.58 208	99.34 130	99.65 90	99.52 135	98.26 163	99.83 67	99.87 75	93.37 343	99.90 150	97.81 306	99.91 46	99.49 250

OMC-MVS		99.08 156	99.04 117	99.20 232	99.67 140	98.22 294	99.28 337	99.52 135	98.07 212	99.66 138	99.81 143	97.79 119	99.78 261	97.79 308	99.81 122	99.60 205

FA-MVS(test-final)		98.75 217	98.53 229	99.41 189	99.55 222	99.05 179	99.80 25	99.01 415	96.59 387	99.58 173	99.59 285	95.39 246	99.90 150	97.78 309	99.49 180	99.28 295

HQP_MVS		98.27 256	98.22 249	98.44 351	99.29 316	96.97 369	99.39 287	99.47 237	98.97 77	99.11 293	99.61 280	92.71 362	99.69 308	97.78 309	97.63 339	98.67 383

plane_prior5								99.47 237					99.69 308	97.78 309	97.63 339	98.67 383

dmvs_re		98.08 276	98.16 251	97.85 408	99.55 222	94.67 462	99.70 59	98.92 427	98.15 185	99.06 307	99.35 373	93.67 340	99.25 395	97.77 312	97.25 369	99.64 192

testdata				99.54 128	99.75 94	98.95 201		99.51 163	97.07 345	99.43 208	99.70 226	98.87 42	99.94 92	97.76 313	99.64 164	99.72 139

PLC	97.94 4	99.02 170	98.85 183	99.53 136	99.66 152	99.01 184	99.24 358	99.52 135	96.85 363	99.27 258	99.48 334	98.25 103	99.91 137	97.76 313	99.62 167	99.65 185
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		97.67 354	97.55 324	98.03 387	99.02 388	95.01 452	99.43 263	98.54 480	96.44 397	99.12 291	99.34 377	91.83 386	99.60 333	97.75 315	96.46 386	99.48 253

1314		98.68 223	98.54 228	99.11 243	98.89 408	98.65 256	99.27 342	99.49 203	96.89 361	97.99 430	99.56 298	97.72 122	99.83 224	97.74 316	99.27 197	98.84 341

XVG-ACMP-BASELINE		97.83 321	97.71 309	98.20 375	99.11 365	96.33 404	99.41 275	99.52 135	98.06 216	99.05 309	99.50 323	89.64 428	99.73 283	97.73 317	97.38 365	98.53 431

CNLPA		99.14 127	98.99 145	99.59 115	99.58 208	99.41 123	99.16 377	99.44 270	98.45 134	99.19 280	99.49 326	98.08 111	99.89 165	97.73 317	99.75 144	99.48 253

v2v482		98.06 278	97.77 300	98.92 267	98.90 407	98.82 240	99.57 147	99.36 317	96.65 377	99.19 280	99.35 373	94.20 317	99.25 395	97.72 319	94.97 427	98.69 370

gbinet_0.2-2-1-0.02		95.40 433	94.58 441	97.85 408	96.11 512	95.97 415	98.56 483	99.26 372	92.12 487	98.47 397	97.49 501	90.23 419	99.00 451	97.71 320	81.25 522	98.58 425

AUN-MVS		96.88 398	96.31 404	98.59 321	99.48 260	97.04 361	99.27 342	99.22 381	97.44 308	98.51 393	99.41 352	91.97 382	99.66 314	97.71 320	83.83 511	99.07 320

baseline2		97.87 311	97.55 324	98.82 295	99.18 347	98.02 306	99.41 275	96.58 519	96.97 354	96.51 467	99.17 406	93.43 341	99.57 336	97.71 320	99.03 248	98.86 339

原ACMM1				99.65 97	99.73 109	99.33 133		99.47 237	97.46 302	99.12 291	99.66 257	98.67 74	99.91 137	97.70 323	99.69 155	99.71 151

PVSNet_0	94.43 19	96.09 417	95.47 424	97.94 398	99.31 311	94.34 471	97.81 516	99.70 18	97.12 339	97.46 446	98.75 454	89.71 426	99.79 253	97.69 324	81.69 521	99.68 164

MAR-MVS		98.86 194	98.63 213	99.54 128	99.37 292	99.66 73	99.45 250	99.54 110	96.61 382	99.01 313	99.40 357	97.09 145	99.86 184	97.68 325	99.53 176	99.10 310
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
FBQ-MVS		97.45 375	97.07 384	98.59 321	99.27 321	96.84 380	99.35 308	98.81 448	97.55 291	98.89 337	98.61 459	85.29 476	99.62 330	97.67 326	98.21 313	99.32 291

9.14			99.10 100		99.72 113		99.40 283	99.51 163	97.53 296	99.64 153	99.78 185	98.84 46	99.91 137	97.63 327	99.82 119

train_agg		99.02 170	98.77 193	99.77 75	99.67 140	99.65 77	99.05 405	99.41 286	96.28 405	98.95 326	99.49 326	98.76 59	99.91 137	97.63 327	99.72 150	99.75 114

miper_ehance_all_eth		98.18 263	98.10 259	98.41 354	99.23 334	97.72 325	98.72 465	99.31 352	96.60 385	98.88 338	99.29 390	97.29 134	99.13 422	97.60 329	95.99 400	98.38 450

MDTV_nov1_ep13			98.32 242		99.11 365	94.44 467	99.27 342	98.74 460	97.51 299	99.40 221	99.62 276	94.78 280	99.76 270	97.59 330	98.81 271

c3_l		98.12 270	98.04 268	98.38 358	99.30 312	97.69 329	98.81 452	99.33 337	96.67 375	98.83 349	99.34 377	97.11 144	98.99 453	97.58 331	95.34 419	98.48 437

test_post1							99.23 361				65.14 557	94.18 320	99.71 294	97.58 331

SCA		98.19 261	98.16 251	98.27 371	99.30 312	95.55 432	99.07 398	98.97 420	97.57 288	99.43 208	99.57 295	92.72 360	99.74 277	97.58 331	99.20 206	99.52 236

JIA-IIPM		97.50 368	97.02 386	98.93 265	98.73 435	97.80 322	99.30 326	98.97 420	91.73 489	98.91 332	94.86 522	95.10 261	99.71 294	97.58 331	97.98 323	99.28 295

V42		98.06 278	97.79 295	98.86 289	98.98 397	98.84 234	99.69 63	99.34 329	96.53 389	99.30 248	99.37 367	94.67 293	99.32 382	97.57 335	94.66 434	98.42 445

gm-plane-assit					98.54 460	92.96 485			94.65 452		99.15 409		99.64 323	97.56 336

APD-MVS		99.27 89	99.08 106	99.84 56	99.75 94	99.79 43	99.50 207	99.50 188	97.16 335	99.77 91	99.82 128	98.78 54	99.94 92	97.56 336	99.86 88	99.80 89
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
pm-mvs1		97.68 351	97.28 371	98.88 282	99.06 380	98.62 261	99.50 207	99.45 261	96.32 403	97.87 437	99.79 178	92.47 371	99.35 377	97.54 338	93.54 456	98.67 383

usedtu_blend_shiyan5		95.04 440	94.10 448	97.86 407	96.45 507	95.92 418	99.29 331	99.22 381	86.17 513	98.36 405	97.68 495	91.20 405	99.07 435	97.53 339	80.97 525	98.60 417

blend_shiyan4		95.25 437	94.39 445	97.84 411	96.70 504	95.92 418	98.84 448	99.28 363	92.21 480	98.16 422	97.84 492	87.10 460	99.07 435	97.53 339	81.87 520	98.54 429

无先验							98.99 421	99.51 163	96.89 361				99.93 110	97.53 339		99.72 139

pmmvs5		97.52 365	97.30 368	98.16 378	98.57 458	96.73 386	99.27 342	98.90 434	96.14 419	98.37 404	99.53 311	91.54 396	99.14 419	97.51 342	95.87 404	98.63 403

mvsany_test3		93.77 458	93.45 461	94.74 476	95.78 516	88.01 505	99.64 98	98.25 488	98.28 158	94.31 488	97.97 486	68.89 520	98.51 482	97.50 343	90.37 488	97.71 488

test9_res														97.49 344	99.72 150	99.75 114

CDPH-MVS		99.13 131	98.91 167	99.80 65	99.75 94	99.71 60	99.15 381	99.41 286	96.60 385	99.60 168	99.55 301	98.83 48	99.90 150	97.48 345	99.83 115	99.78 99

AdaColmap		99.01 175	98.80 188	99.66 93	99.56 218	99.54 101	99.18 375	99.70 18	98.18 183	99.35 237	99.63 271	96.32 192	99.90 150	97.48 345	99.77 139	99.55 228

OpenMVS	96.50 16	98.47 235	98.12 257	99.52 143	99.04 386	99.53 104	99.82 16	99.72 14	94.56 453	98.08 425	99.88 59	94.73 288	99.98 21	97.47 347	99.76 142	99.06 321

IterMVS		97.83 321	97.77 300	98.02 389	99.58 208	96.27 407	99.02 413	99.48 215	97.22 330	98.71 363	99.70 226	92.75 357	99.13 422	97.46 348	96.00 399	98.67 383
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
RPSCF		98.22 257	98.62 218	96.99 450	99.82 54	91.58 493	99.72 54	99.44 270	96.61 382	99.66 138	99.89 46	95.92 221	99.82 233	97.46 348	99.10 235	99.57 223

usedtu_dtu_shiyan1		98.09 272	97.82 292	98.89 277	98.70 441	98.90 217	98.57 479	99.47 237	96.78 367	98.87 341	99.05 421	94.75 285	99.23 398	97.45 350	96.74 378	98.53 431

FE-MVSNET3		98.09 272	97.82 292	98.89 277	98.70 441	98.90 217	98.57 479	99.47 237	96.78 367	98.87 341	99.05 421	94.75 285	99.23 398	97.45 350	96.74 378	98.53 431

IterMVS-SCA-FT		97.82 324	97.75 305	98.06 386	99.57 214	96.36 403	99.02 413	99.49 203	97.18 333	98.71 363	99.72 219	92.72 360	99.14 419	97.44 352	95.86 405	98.67 383

PatchmatchNet		98.31 251	98.36 238	98.19 376	99.16 357	95.32 443	99.27 342	98.92 427	97.37 316	99.37 228	99.58 289	94.90 271	99.70 302	97.43 353	99.21 204	99.54 230
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EU-MVSNet		97.98 295	98.03 269	97.81 417	98.72 437	96.65 392	99.66 84	99.66 33	98.09 207	98.35 408	99.82 128	95.25 255	98.01 491	97.41 354	95.30 420	98.78 345

eth_miper_zixun_eth		98.05 283	97.96 276	98.33 361	99.26 326	97.38 339	98.56 483	99.31 352	96.65 377	98.88 338	99.52 316	96.58 178	99.12 428	97.39 355	95.53 416	98.47 439

UWE-MVS		97.58 361	97.29 370	98.48 340	99.09 371	96.25 408	99.01 418	96.61 518	97.86 247	99.19 280	99.01 428	88.72 436	99.90 150	97.38 356	98.69 276	99.28 295

testing222		97.16 389	96.50 399	99.16 236	99.16 357	98.47 283	99.27 342	98.66 473	97.71 271	98.23 416	98.15 479	82.28 494	99.84 202	97.36 357	97.66 338	99.18 305

FE-MVS		98.48 234	98.17 250	99.40 191	99.54 229	98.96 195	99.68 73	98.81 448	95.54 432	99.62 160	99.70 226	93.82 335	99.93 110	97.35 358	99.46 181	99.32 291

wanda-best-256-512		95.43 430	94.66 437	97.77 419	96.45 507	95.68 427	98.48 489	99.28 363	92.18 483	98.36 405	97.68 495	91.20 405	99.03 442	97.31 359	80.97 525	98.60 417

FE-blended-shiyan7		95.43 430	94.66 437	97.77 419	96.45 507	95.68 427	98.48 489	99.28 363	92.18 483	98.36 405	97.68 495	91.20 405	99.03 442	97.31 359	80.97 525	98.60 417

tpm2		97.44 376	97.34 361	97.74 423	99.15 361	94.36 470	99.45 250	98.94 423	93.45 468	98.90 334	99.44 344	91.35 401	99.59 334	97.31 359	98.07 321	99.29 294

blended_shiyan6		95.54 427	94.78 435	97.84 411	96.60 505	95.89 421	98.85 444	99.28 363	92.17 485	98.43 400	97.95 487	91.44 397	99.02 446	97.30 362	80.97 525	98.60 417

TESTMET0.1,1		97.55 362	97.27 374	98.40 356	98.93 402	96.53 396	98.67 468	97.61 503	96.96 355	98.64 379	99.28 392	88.63 442	99.45 350	97.30 362	99.38 186	99.21 304

miper_lstm_enhance		98.00 293	97.91 282	98.28 370	99.34 302	97.43 337	98.88 440	99.36 317	96.48 394	98.80 354	99.55 301	95.98 215	98.91 467	97.27 364	95.50 417	98.51 435

blended_shiyan8		95.56 426	94.79 434	97.87 404	96.60 505	95.90 420	98.85 444	99.27 370	92.19 481	98.47 397	97.94 490	91.43 398	99.11 429	97.26 365	81.09 524	98.60 417

test-LLR		98.06 278	97.90 283	98.55 332	98.79 423	97.10 352	98.67 468	97.75 498	97.34 318	98.61 385	98.85 446	94.45 308	99.45 350	97.25 366	99.38 186	99.10 310

test-mter		97.49 373	97.13 381	98.55 332	98.79 423	97.10 352	98.67 468	97.75 498	96.65 377	98.61 385	98.85 446	88.23 446	99.45 350	97.25 366	99.38 186	99.10 310

cl____		98.01 291	97.84 291	98.55 332	99.25 330	97.97 309	98.71 466	99.34 329	96.47 396	98.59 388	99.54 306	95.65 237	99.21 410	97.21 368	95.77 406	98.46 442

DIV-MVS_self_test		98.01 291	97.85 290	98.48 340	99.24 332	97.95 314	98.71 466	99.35 324	96.50 390	98.60 387	99.54 306	95.72 235	99.03 442	97.21 368	95.77 406	98.46 442

agg_prior2														97.21 368	99.73 149	99.75 114

OurMVSNet-221017-0		97.88 309	97.77 300	98.19 376	98.71 440	96.53 396	99.88 4	99.00 416	97.79 260	98.78 357	99.94 7	91.68 390	99.35 377	97.21 368	96.99 377	98.69 370

BP-MVS														97.19 372

HQP-MVS		98.02 288	97.90 283	98.37 359	99.19 344	96.83 381	98.98 424	99.39 296	98.24 170	98.66 372	99.40 357	92.47 371	99.64 323	97.19 372	97.58 344	98.64 396

pmmvs4		98.13 268	97.90 283	98.81 298	98.61 453	98.87 227	98.99 421	99.21 385	96.44 397	99.06 307	99.58 289	95.90 223	99.11 429	97.18 374	96.11 396	98.46 442

PatchMatch-RL		98.84 206	98.62 218	99.52 143	99.71 119	99.28 144	99.06 402	99.77 12	97.74 269	99.50 192	99.53 311	95.41 245	99.84 202	97.17 375	99.64 164	99.44 269

GBi-Net		97.68 351	97.48 335	98.29 366	99.51 239	97.26 345	99.43 263	99.48 215	96.49 391	99.07 302	99.32 385	90.26 416	98.98 454	97.10 376	96.65 381	98.62 405

test1		97.68 351	97.48 335	98.29 366	99.51 239	97.26 345	99.43 263	99.48 215	96.49 391	99.07 302	99.32 385	90.26 416	98.98 454	97.10 376	96.65 381	98.62 405

FMVSNet3		98.03 286	97.76 304	98.84 293	99.39 286	98.98 187	99.40 283	99.38 305	96.67 375	99.07 302	99.28 392	92.93 352	98.98 454	97.10 376	96.65 381	98.56 428

tt0320-xc		95.31 436	94.59 440	97.45 436	98.92 404	94.73 458	99.20 370	99.31 352	86.74 509	97.23 453	99.72 219	81.14 498	98.95 464	97.08 379	91.98 477	98.67 383

BH-untuned		98.42 239	98.36 238	98.59 321	99.49 253	96.70 387	99.27 342	99.13 396	97.24 328	98.80 354	99.38 364	95.75 233	99.74 277	97.07 380	99.16 209	99.33 290

dtuonlycased		97.04 394	97.33 364	96.16 466	99.08 374	90.59 498	98.79 455	99.38 305	97.19 332	96.91 464	99.49 326	90.22 421	98.75 475	97.04 381	97.89 328	99.14 306

LF4IMVS		97.52 365	97.46 340	97.70 425	98.98 397	95.55 432	99.29 331	98.82 446	98.07 212	98.66 372	99.64 265	89.97 423	99.61 332	97.01 382	96.68 380	97.94 481

SixPastTwentyTwo		97.50 368	97.33 364	98.03 387	98.65 448	96.23 409	99.77 35	98.68 469	97.14 336	97.90 435	99.93 11	90.45 414	99.18 414	97.00 383	96.43 387	98.67 383

MG-MVS		99.13 131	99.02 131	99.45 176	99.57 214	98.63 259	99.07 398	99.34 329	98.99 70	99.61 165	99.82 128	97.98 115	99.87 177	97.00 383	99.80 127	99.85 48

API-MVS		99.04 166	99.03 120	99.06 246	99.40 283	99.31 138	99.55 170	99.56 91	98.54 123	99.33 242	99.39 361	98.76 59	99.78 261	96.98 385	99.78 136	98.07 468

tpmvs		97.98 295	98.02 271	97.84 411	99.04 386	94.73 458	99.31 324	99.20 386	96.10 425	98.76 359	99.42 348	94.94 266	99.81 238	96.97 386	98.45 291	98.97 333

QAPM		98.67 224	98.30 244	99.80 65	99.20 341	99.67 70	99.77 35	99.72 14	94.74 450	98.73 361	99.90 37	95.78 231	99.98 21	96.96 387	99.88 74	99.76 108

PAPM_NR		99.04 166	98.84 185	99.66 93	99.74 102	99.44 119	99.39 287	99.38 305	97.70 274	99.28 252	99.28 392	98.34 99	99.85 192	96.96 387	99.45 182	99.69 158

v8		97.95 300	97.63 319	98.93 265	98.95 401	98.81 242	99.80 25	99.41 286	96.03 426	99.10 296	99.42 348	94.92 269	99.30 385	96.94 389	94.08 449	98.66 392

ZD-MVS					99.71 119	99.79 43		99.61 62	96.84 364	99.56 178	99.54 306	98.58 80	99.96 42	96.93 390	99.75 144

MSDG		98.98 179	98.80 188	99.53 136	99.76 84	99.19 154	98.75 461	99.55 101	97.25 326	99.47 197	99.77 194	97.82 118	99.87 177	96.93 390	99.90 57	99.54 230

pmmvs6		96.53 406	96.09 411	97.82 416	98.69 444	95.47 436	99.37 296	99.47 237	93.46 467	97.41 447	99.78 185	87.06 461	99.33 380	96.92 392	92.70 472	98.65 394

新几何1				99.75 78	99.75 94	99.59 91		99.54 110	96.76 369	99.29 251	99.64 265	98.43 92	99.94 92	96.92 392	99.66 161	99.72 139

DTE-MVSNet		97.51 367	97.19 377	98.46 346	98.63 450	98.13 299	99.84 12	99.48 215	96.68 374	97.97 432	99.67 252	92.92 353	98.56 480	96.88 394	92.60 474	98.70 366

ADS-MVSNet2		98.02 288	98.07 266	97.87 404	99.33 303	95.19 446	99.23 361	99.08 402	96.24 409	99.10 296	99.67 252	94.11 322	98.93 466	96.81 395	99.05 245	99.48 253

ADS-MVSNet		98.20 260	98.08 263	98.56 330	99.33 303	96.48 398	99.23 361	99.15 393	96.24 409	99.10 296	99.67 252	94.11 322	99.71 294	96.81 395	99.05 245	99.48 253

gg-mvs-nofinetune		96.17 415	95.32 427	98.73 306	98.79 423	98.14 298	99.38 292	94.09 533	91.07 495	98.07 428	91.04 537	89.62 429	99.35 377	96.75 397	99.09 241	98.68 375

v1144		97.98 295	97.69 311	98.85 292	98.87 413	98.66 255	99.54 175	99.35 324	96.27 407	99.23 269	99.35 373	94.67 293	99.23 398	96.73 398	95.16 423	98.68 375

UnsupCasMVSNet_eth		96.44 408	96.12 409	97.40 439	98.65 448	95.65 429	99.36 302	99.51 163	97.13 337	96.04 474	98.99 432	88.40 444	98.17 487	96.71 399	90.27 490	98.40 448

GA-MVS		97.85 314	97.47 338	99.00 254	99.38 289	97.99 308	98.57 479	99.15 393	97.04 350	98.90 334	99.30 388	89.83 425	99.38 367	96.70 400	98.33 298	99.62 200

K. test v3		97.10 392	96.79 393	98.01 390	98.72 437	96.33 404	99.87 8	97.05 510	97.59 285	96.16 472	99.80 161	88.71 437	99.04 440	96.69 401	96.55 385	98.65 394

testdata2													99.95 77	96.67 402

AllTest		98.87 191	98.72 199	99.31 210	99.86 26	98.48 281	99.56 155	99.61 62	97.85 250	99.36 234	99.85 93	95.95 218	99.85 192	96.66 403	99.83 115	99.59 216

TestCases				99.31 210	99.86 26	98.48 281		99.61 62	97.85 250	99.36 234	99.85 93	95.95 218	99.85 192	96.66 403	99.83 115	99.59 216

mvs5depth		96.66 402	96.22 407	97.97 395	97.00 501	96.28 406	98.66 471	99.03 412	96.61 382	96.93 463	99.79 178	87.20 457	99.47 346	96.65 405	94.13 446	98.16 462

test_fmvs3		92.10 468	91.77 470	93.08 487	96.19 510	86.25 507	99.82 16	98.62 475	96.65 377	95.19 480	96.90 510	55.05 534	95.93 518	96.63 406	90.92 487	97.06 506

dp		97.75 337	97.80 294	97.59 432	99.10 368	93.71 477	99.32 319	98.88 438	96.48 394	99.08 301	99.55 301	92.67 365	99.82 233	96.52 407	98.58 282	99.24 301

BH-RMVSNet		98.41 241	98.08 263	99.40 191	99.41 278	98.83 237	99.30 326	98.77 455	97.70 274	98.94 328	99.65 259	92.91 355	99.74 277	96.52 407	99.55 175	99.64 192

FMVSNet2		97.72 343	97.36 356	98.80 300	99.51 239	98.84 234	99.45 250	99.42 283	96.49 391	98.86 347	99.29 390	90.26 416	98.98 454	96.44 409	96.56 384	98.58 425

SSC-MVS3.2		97.34 381	97.15 378	97.93 399	99.02 388	95.76 426	99.48 232	99.58 79	97.62 283	99.09 299	99.53 311	87.95 450	99.27 390	96.42 410	95.66 411	98.75 353

ambc				93.06 488	92.68 540	82.36 517	98.47 491	98.73 466		95.09 482	97.41 502	55.55 532	99.10 432	96.42 410	91.32 479	97.71 488

tpm cat1		97.39 378	97.36 356	97.50 435	99.17 355	93.73 476	99.43 263	99.31 352	91.27 492	98.71 363	99.08 416	94.31 315	99.77 266	96.41 412	98.50 289	99.00 327

tt0320		95.71 425	95.07 430	97.62 428	99.05 384	95.02 451	99.25 353	99.52 135	86.81 508	97.97 432	99.72 219	83.58 486	99.15 417	96.38 413	93.35 457	98.68 375

v144192		97.92 304	97.60 322	98.87 286	98.83 420	98.65 256	99.55 170	99.34 329	96.20 412	99.32 243	99.40 357	94.36 310	99.26 393	96.37 414	95.03 426	98.70 366

Patchmatch-RL test		95.84 421	95.81 418	95.95 469	95.61 518	90.57 499	98.24 501	98.39 483	95.10 441	95.20 479	98.67 456	94.78 280	97.77 496	96.28 415	90.02 491	99.51 245

Patchmtry		97.75 337	97.40 353	98.81 298	99.10 368	98.87 227	99.11 394	99.33 337	94.83 448	98.81 352	99.38 364	94.33 313	99.02 446	96.10 416	95.57 414	98.53 431

BH-w/o		98.00 293	97.89 287	98.32 363	99.35 297	96.20 410	99.01 418	98.90 434	96.42 399	98.38 403	99.00 430	95.26 254	99.72 287	96.06 417	98.61 279	99.03 324

testing3		97.28 384	96.76 394	98.82 295	99.37 292	98.07 304	99.45 250	99.36 317	97.56 290	97.89 436	98.95 437	83.70 485	98.82 471	96.03 418	98.56 285	99.58 220

v7n		97.87 311	97.52 329	98.92 267	98.76 433	98.58 266	99.84 12	99.46 250	96.20 412	98.91 332	99.70 226	94.89 272	99.44 355	96.03 418	93.89 452	98.75 353

v10		97.85 314	97.52 329	98.86 289	98.99 394	98.67 254	99.75 43	99.41 286	95.70 430	98.98 320	99.41 352	94.75 285	99.23 398	96.01 420	94.63 435	98.67 383

lessismore_v0				97.79 418	98.69 444	95.44 440		94.75 529		95.71 476	99.87 75	88.69 438	99.32 382	95.89 421	94.93 429	98.62 405

ITE_SJBPF				98.08 385	99.29 316	96.37 402		98.92 427	98.34 149	98.83 349	99.75 203	91.09 408	99.62 330	95.82 422	97.40 364	98.25 457

FMVSNet1		96.84 399	96.36 403	98.29 366	99.32 310	97.26 345	99.43 263	99.48 215	95.11 439	98.55 390	99.32 385	83.95 484	98.98 454	95.81 423	96.26 392	98.62 405

DPM-MVS		98.95 183	98.71 201	99.66 93	99.63 174	99.55 99	98.64 473	99.10 399	97.93 240	99.42 211	99.55 301	98.67 74	99.80 246	95.80 424	99.68 158	99.61 202

dtuonly		98.37 247	98.26 247	98.69 313	99.07 377	96.81 384	98.51 487	98.75 456	97.77 263	99.57 176	99.68 245	96.12 206	99.71 294	95.76 425	99.11 226	99.57 223

MIMVSNet		97.73 341	97.45 341	98.57 326	99.45 269	97.50 335	99.02 413	98.98 419	96.11 421	99.41 216	99.14 410	90.28 415	98.74 476	95.74 426	98.93 255	99.47 259

test_f		91.90 470	91.26 473	93.84 481	95.52 521	85.92 508	99.69 63	98.53 481	95.31 436	93.87 493	96.37 516	55.33 533	98.27 485	95.70 427	90.98 486	97.32 500

tfpnnormal		97.84 318	97.47 338	98.98 256	99.20 341	99.22 152	99.64 98	99.61 62	96.32 403	98.27 415	99.70 226	93.35 345	99.44 355	95.69 428	95.40 418	98.27 455

MS-PatchMatch		97.24 388	97.32 366	96.99 450	98.45 465	93.51 482	98.82 451	99.32 348	97.41 313	98.13 424	99.30 388	88.99 433	99.56 338	95.68 429	99.80 127	97.90 485

EG-PatchMatch MVS		95.97 419	95.69 420	96.81 457	97.78 483	92.79 486	99.16 377	98.93 424	96.16 416	94.08 491	99.22 401	82.72 490	99.47 346	95.67 430	97.50 353	98.17 461

USDC		97.34 381	97.20 376	97.75 421	99.07 377	95.20 445	98.51 487	99.04 409	97.99 234	98.31 411	99.86 86	89.02 432	99.55 340	95.67 430	97.36 366	98.49 436

MVP-Stereo		97.81 326	97.75 305	97.99 393	97.53 488	96.60 395	98.96 428	98.85 443	97.22 330	97.23 453	99.36 370	95.28 251	99.46 348	95.51 432	99.78 136	97.92 483
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
WAC-MVS						97.16 349								95.47 433

CMPMVS	69.68 23	94.13 455	94.90 433	91.84 491	97.24 495	80.01 529	98.52 485	99.48 215	89.01 502	91.99 505	99.67 252	85.67 470	99.13 422	95.44 434	97.03 376	96.39 516
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
GG-mvs-BLEND				98.45 348	98.55 459	98.16 296	99.43 263	93.68 534		97.23 453	98.46 465	89.30 430	99.22 405	95.43 435	98.22 309	97.98 479

v1921920		97.80 328	97.45 341	98.84 293	98.80 422	98.53 270	99.52 186	99.34 329	96.15 418	99.24 265	99.47 337	93.98 328	99.29 386	95.40 436	95.13 424	98.69 370

TR-MVS		97.76 333	97.41 352	98.82 295	99.06 380	97.87 318	98.87 442	98.56 476	96.63 381	98.68 371	99.22 401	92.49 370	99.65 319	95.40 436	97.79 334	98.95 337

v1192		97.81 326	97.44 346	98.91 271	98.88 410	98.68 253	99.51 196	99.34 329	96.18 414	99.20 277	99.34 377	94.03 326	99.36 374	95.32 438	95.18 422	98.69 370

myMVS_eth3d		96.89 397	96.37 402	98.43 353	99.00 391	97.16 349	99.29 331	99.39 296	97.06 347	97.41 447	98.15 479	83.46 487	98.68 478	95.27 439	98.34 296	99.45 267

PAPR		98.63 229	98.34 240	99.51 148	99.40 283	99.03 181	98.80 453	99.36 317	96.33 402	99.00 317	99.12 415	98.46 90	99.84 202	95.23 440	99.37 193	99.66 178

TinyColmap		97.12 391	96.89 391	97.83 414	99.07 377	95.52 435	98.57 479	98.74 460	97.58 287	97.81 440	99.79 178	88.16 447	99.56 338	95.10 441	97.21 371	98.39 449

DSMNet-mixed		97.25 386	97.35 358	96.95 453	97.84 481	93.61 481	99.57 147	96.63 517	96.13 420	98.87 341	98.61 459	94.59 298	97.70 499	95.08 442	98.86 265	99.55 228

test0.0.03 1		97.71 346	97.42 351	98.56 330	98.41 467	97.82 321	98.78 456	98.63 474	97.34 318	98.05 429	98.98 434	94.45 308	98.98 454	95.04 443	97.15 374	98.89 338

MVStest1		96.08 418	95.48 423	97.89 403	98.93 402	96.70 387	99.56 155	99.35 324	92.69 478	91.81 506	99.46 341	89.90 424	98.96 463	95.00 444	92.61 473	98.00 477

our_test_3		97.65 356	97.68 312	97.55 433	98.62 451	94.97 453	98.84 448	99.30 357	96.83 366	98.19 420	99.34 377	97.01 152	99.02 446	95.00 444	96.01 398	98.64 396

MVS-HIRNet		95.75 423	95.16 428	97.51 434	99.30 312	93.69 478	98.88 440	95.78 522	85.09 515	98.78 357	92.65 532	91.29 403	99.37 370	94.85 446	99.85 95	99.46 264

CR-MVSNet		98.17 264	97.93 281	98.87 286	99.18 347	98.49 279	99.22 365	99.33 337	96.96 355	99.56 178	99.38 364	94.33 313	99.00 451	94.83 447	98.58 282	99.14 306

pmmvs-eth3d		95.34 435	94.73 436	97.15 444	95.53 520	95.94 417	99.35 308	99.10 399	95.13 437	93.55 495	97.54 500	88.15 448	97.91 493	94.58 448	89.69 496	97.61 493

testgi		97.65 356	97.50 333	98.13 382	99.36 296	96.45 400	99.42 270	99.48 215	97.76 265	97.87 437	99.45 343	91.09 408	98.81 472	94.53 449	98.52 288	99.13 309

v1240		97.69 348	97.32 366	98.79 301	98.85 417	98.43 285	99.48 232	99.36 317	96.11 421	99.27 258	99.36 370	93.76 338	99.24 397	94.46 450	95.23 421	98.70 366

YYNet1		95.36 434	94.51 443	97.92 400	97.89 479	97.10 352	99.10 396	99.23 379	93.26 470	80.77 535	99.04 424	92.81 356	98.02 490	94.30 451	94.18 445	98.64 396

PM-MVS		92.96 464	92.23 468	95.14 475	95.61 518	89.98 502	99.37 296	98.21 491	94.80 449	95.04 483	97.69 494	65.06 524	97.90 494	94.30 451	89.98 492	97.54 497

test_vis3_rt		87.04 486	85.81 490	90.73 499	93.99 533	81.96 519	99.76 38	90.23 543	92.81 477	81.35 534	91.56 534	40.06 552	99.07 435	94.27 453	88.23 501	91.15 530

MVS		97.28 384	96.55 398	99.48 166	98.78 426	98.95 201	99.27 342	99.39 296	83.53 516	98.08 425	99.54 306	96.97 153	99.87 177	94.23 454	99.16 209	99.63 197

MDA-MVSNet_test_wron		95.45 429	94.60 439	98.01 390	98.16 474	97.21 348	99.11 394	99.24 378	93.49 466	80.73 536	98.98 434	93.02 350	98.18 486	94.22 455	94.45 439	98.64 396

ArgMatch-Sym		96.59 404	96.31 404	97.42 437	98.89 408	94.84 456	99.16 377	99.39 296	98.11 202	98.35 408	99.53 311	84.38 482	99.40 364	94.16 456	94.85 433	98.03 472

TransMVSNet (Re)		97.15 390	96.58 397	98.86 289	99.12 363	98.85 232	99.49 224	98.91 432	95.48 433	97.16 457	99.80 161	93.38 342	99.11 429	94.16 456	91.73 478	98.62 405

UnsupCasMVSNet_bld		93.53 459	92.51 465	96.58 461	97.38 491	93.82 474	98.24 501	99.48 215	91.10 494	93.10 497	96.66 512	74.89 505	98.37 483	94.03 458	87.71 503	97.56 496

ArgMatch-SfM		96.18 414	95.78 419	97.38 440	99.08 374	94.64 463	99.20 370	99.33 337	98.01 232	98.54 391	99.54 306	83.13 488	99.43 359	93.86 459	91.29 480	98.08 467

ppachtmachnet_test		97.49 373	97.45 341	97.61 431	98.62 451	95.24 444	98.80 453	99.46 250	96.11 421	98.22 418	99.62 276	96.45 186	98.97 461	93.77 460	95.97 403	98.61 414

UWE-MVS-28		97.36 379	97.24 375	97.75 421	98.84 419	94.44 467	99.24 358	97.58 505	97.98 236	99.00 317	99.00 430	91.35 401	99.53 342	93.75 461	98.39 293	99.27 299

thres600view7		97.86 313	97.51 332	98.92 267	99.72 113	97.95 314	99.59 129	98.74 460	97.94 239	99.27 258	98.62 457	91.75 387	99.86 184	93.73 462	98.19 314	98.96 335

MASt3R-SfM		94.79 446	95.11 429	93.81 482	97.96 476	85.14 512	98.52 485	98.99 417	95.33 435	97.53 445	99.13 411	79.99 500	99.48 344	93.66 463	94.90 431	96.80 509

test_method		91.10 472	91.36 472	90.31 501	95.85 515	73.72 541	94.89 529	99.25 375	68.39 531	95.82 475	99.02 427	80.50 499	98.95 464	93.64 464	94.89 432	98.25 457

DeepMVS_CX				93.34 485	99.29 316	82.27 518		99.22 381	85.15 514	96.33 469	99.05 421	90.97 410	99.73 283	93.57 465	97.77 335	98.01 474

MDA-MVSNet-bldmvs		94.96 443	93.98 451	97.92 400	98.24 470	97.27 343	99.15 381	99.33 337	93.80 461	80.09 537	99.03 425	88.31 445	97.86 495	93.49 466	94.36 441	98.62 405

SP-DiffGlue		90.78 475	90.71 475	90.98 496	95.45 523	81.30 524	97.92 514	97.30 508	75.18 522	92.09 503	95.93 517	74.93 504	94.89 525	93.46 467	94.12 447	96.74 512

Patchmatch-test		97.93 301	97.65 315	98.77 304	99.18 347	97.07 356	99.03 410	99.14 395	96.16 416	98.74 360	99.57 295	94.56 300	99.72 287	93.36 468	99.11 226	99.52 236

FE-MVSNET2		95.10 439	94.44 444	97.08 449	95.08 524	95.97 415	99.51 196	99.37 315	95.02 443	94.10 490	97.57 498	86.18 467	97.66 501	93.28 469	89.86 493	97.61 493

thres100view900		97.76 333	97.45 341	98.69 313	99.72 113	97.86 320	99.59 129	98.74 460	97.93 240	99.26 263	98.62 457	91.75 387	99.83 224	93.22 470	98.18 315	98.37 451

tfpn200view9		97.72 343	97.38 354	98.72 308	99.69 130	97.96 311	99.50 207	98.73 466	97.83 254	99.17 285	98.45 466	91.67 391	99.83 224	93.22 470	98.18 315	98.37 451

thres400		97.77 332	97.38 354	98.92 267	99.69 130	97.96 311	99.50 207	98.73 466	97.83 254	99.17 285	98.45 466	91.67 391	99.83 224	93.22 470	98.18 315	98.96 335

EPNet_dtu		98.03 286	97.96 276	98.23 374	98.27 469	95.54 434	99.23 361	98.75 456	99.02 63	97.82 439	99.71 222	96.11 207	99.48 344	93.04 473	99.65 163	99.69 158
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WB-MVSnew		97.65 356	97.65 315	97.63 427	98.78 426	97.62 331	99.13 385	98.33 485	97.36 317	99.07 302	98.94 438	95.64 238	99.15 417	92.95 474	98.68 277	96.12 519

thres200		97.61 359	97.28 371	98.62 319	99.64 169	98.03 305	99.26 351	98.74 460	97.68 276	99.09 299	98.32 472	91.66 393	99.81 238	92.88 475	98.22 309	98.03 472

KD-MVS_2432*1600		94.62 448	93.72 456	97.31 441	97.19 497	95.82 424	98.34 496	99.20 386	95.00 444	97.57 443	98.35 470	87.95 450	98.10 488	92.87 476	77.00 536	98.01 474

miper_refine_blended		94.62 448	93.72 456	97.31 441	97.19 497	95.82 424	98.34 496	99.20 386	95.00 444	97.57 443	98.35 470	87.95 450	98.10 488	92.87 476	77.00 536	98.01 474

PCF-MVS	97.08 14	97.66 355	97.06 385	99.47 172	99.61 195	99.09 171	98.04 511	99.25 375	91.24 493	98.51 393	99.70 226	94.55 302	99.91 137	92.76 478	99.85 95	99.42 273
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
RoMa-SfM		94.36 453	93.86 454	95.88 470	98.61 453	90.62 497	98.85 444	99.04 409	91.63 490	94.14 489	99.49 326	77.16 502	99.09 434	92.66 479	93.13 465	97.91 484

FMVSNet5		96.43 409	96.19 408	97.15 444	99.11 365	95.89 421	99.32 319	99.52 135	94.47 455	98.34 410	99.07 417	87.54 455	97.07 506	92.61 480	95.72 409	98.47 439

test_0402		96.64 403	96.24 406	97.85 408	98.85 417	96.43 401	99.44 257	99.26 372	93.52 465	96.98 461	99.52 316	88.52 443	99.20 412	92.58 481	97.50 353	97.93 482

PatchmatchNet1														91.97 482	96.20 393	98.59 423
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
APD_test1		95.87 420	96.49 400	94.00 479	99.53 230	84.01 514	99.54 175	99.32 348	95.91 428	97.99 430	99.85 93	85.49 473	99.88 170	91.96 483	98.84 267	98.12 464

DKM		93.17 462	92.50 466	95.21 474	98.53 461	90.26 500	98.74 464	98.90 434	93.00 474	92.61 500	99.06 419	70.06 517	97.74 498	91.92 484	89.65 497	97.62 492

Syy-MVS		97.09 393	97.14 379	96.95 453	99.00 391	92.73 487	99.29 331	99.39 296	97.06 347	97.41 447	98.15 479	93.92 331	98.68 478	91.71 485	98.34 296	99.45 267

new-patchmatchnet		94.48 451	94.08 450	95.67 471	95.08 524	92.41 488	99.18 375	99.28 363	94.55 454	93.49 496	97.37 504	87.86 453	97.01 508	91.57 486	88.36 500	97.61 493

DKM-HiRes		92.13 467	91.58 471	93.78 483	98.24 470	88.09 504	98.61 475	98.68 469	91.39 491	90.36 510	98.90 445	67.97 522	96.01 517	91.39 487	88.65 499	97.24 501

N_pmnet		94.95 444	95.83 417	92.31 490	98.47 463	79.33 532	99.12 388	92.81 539	93.87 458	97.68 442	99.13 411	93.87 333	99.01 449	91.38 488	96.19 394	98.59 423

Anonymous20240521		96.20 413	95.89 416	97.13 446	97.72 487	94.96 454	99.79 31	99.29 361	93.01 473	97.20 456	99.03 425	89.69 427	98.36 484	91.16 489	96.13 395	98.07 468

DenseAffine		94.28 454	93.53 460	96.52 462	98.72 437	92.31 489	98.78 456	99.02 413	93.14 472	94.45 487	99.01 428	74.73 506	99.20 412	90.98 490	92.94 467	98.04 471

LCM-MVSNet		86.80 489	85.22 494	91.53 493	87.81 552	80.96 525	98.23 503	98.99 417	71.05 528	90.13 513	96.51 515	48.45 545	96.88 509	90.51 491	85.30 507	96.76 510

RoMa-HiRes		92.56 466	92.07 469	94.02 478	97.77 486	87.59 506	98.87 442	98.46 482	89.82 497	92.47 501	99.41 352	71.58 513	97.29 504	90.47 492	89.79 495	97.17 503

new_pmnet		96.38 410	96.03 412	97.41 438	98.13 475	95.16 448	99.05 405	99.20 386	93.94 457	97.39 450	98.79 452	91.61 395	99.04 440	90.43 493	95.77 406	98.05 470

KD-MVS_self_test		95.00 442	94.34 446	96.96 452	97.07 500	95.39 441	99.56 155	99.44 270	95.11 439	97.13 458	97.32 506	91.86 385	97.27 505	90.35 494	81.23 523	98.23 459

PAPM		97.59 360	97.09 383	99.07 245	99.06 380	98.26 292	98.30 500	99.10 399	94.88 446	98.08 425	99.34 377	96.27 197	99.64 323	89.87 495	98.92 257	99.31 293

pmmvs3		94.09 456	93.25 463	96.60 460	94.76 528	94.49 466	98.92 435	98.18 493	89.66 498	96.48 468	98.06 485	86.28 466	97.33 503	89.68 496	87.20 504	97.97 480

LoFTR		93.25 461	92.33 467	95.99 468	97.91 477	90.83 495	99.06 402	98.56 476	92.19 481	90.24 512	98.18 478	72.97 507	99.26 393	89.37 497	92.52 475	97.89 486

EGC-MVSNET		82.80 494	77.86 501	97.62 428	97.91 477	96.12 412	99.33 316	99.28 363	8.40 559	25.05 561	99.27 395	84.11 483	99.33 380	89.20 498	98.22 309	97.42 499

PMatch-SfM		88.28 483	86.92 488	92.38 489	95.93 513	84.56 513	97.84 515	96.01 521	88.80 504	84.11 525	97.95 487	49.73 540	95.66 520	89.15 499	82.72 519	96.91 507

OpenMVS_ROB	92.34 20	94.38 452	93.70 458	96.41 463	97.38 491	93.17 484	99.06 402	98.75 456	86.58 510	94.84 486	98.26 475	81.53 495	99.32 382	89.01 500	97.87 330	96.76 510

CL-MVSNet_self_test		94.49 450	93.97 452	96.08 467	96.16 511	93.67 479	98.33 498	99.38 305	95.13 437	97.33 451	98.15 479	92.69 364	96.57 511	88.67 501	79.87 533	97.99 478

PatchT		97.03 395	96.44 401	98.79 301	98.99 394	98.34 289	99.16 377	99.07 405	92.13 486	99.52 189	97.31 507	94.54 303	98.98 454	88.54 502	98.73 274	99.03 324

MIMVSNet1		95.51 428	95.04 432	96.92 455	97.38 491	95.60 430	99.52 186	99.50 188	93.65 463	96.97 462	99.17 406	85.28 477	96.56 512	88.36 503	95.55 415	98.60 417

dmvs_testset		95.02 441	96.12 409	91.72 492	99.10 368	80.43 528	99.58 139	97.87 497	97.47 301	95.22 478	98.82 448	93.99 327	95.18 522	88.09 504	94.91 430	99.56 227

TAPA-MVS	97.07 15	97.74 339	97.34 361	98.94 263	99.70 124	97.53 333	99.25 353	99.51 163	91.90 488	99.30 248	99.63 271	98.78 54	99.64 323	88.09 504	99.87 80	99.65 185
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SD_0403		97.55 362	97.53 328	97.62 428	99.61 195	93.64 480	99.72 54	99.44 270	98.03 228	98.62 384	99.39 361	96.06 210	99.57 336	87.88 506	99.01 251	99.66 178

PMatch-Up-SfM		86.75 490	85.43 492	90.73 499	94.97 527	81.39 522	97.55 521	94.92 527	86.33 512	83.10 529	97.95 487	46.03 546	93.97 529	87.59 507	80.39 530	96.83 508

FE-MVSNET		94.07 457	93.36 462	96.22 465	94.05 532	94.71 460	99.56 155	98.36 484	93.15 471	93.76 494	97.55 499	86.47 465	96.49 513	87.48 508	89.83 494	97.48 498

Gipuma		90.99 473	90.15 478	93.51 484	98.73 435	90.12 501	93.98 534	99.45 261	79.32 519	92.28 502	94.91 521	69.61 518	97.98 492	87.42 509	95.67 410	92.45 527
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test20.03		96.12 416	95.96 414	96.63 459	97.44 489	95.45 438	99.51 196	99.38 305	96.55 388	96.16 472	99.25 398	93.76 338	96.17 515	87.35 510	94.22 444	98.27 455

ELoFTR		89.95 478	88.65 483	93.85 480	95.93 513	85.85 509	98.64 473	98.31 486	90.34 496	85.03 522	97.76 493	60.28 531	99.01 449	87.27 511	84.26 509	96.71 513

PDCNetPlus		84.77 492	83.24 495	89.36 510	94.33 531	83.93 515	98.13 509	76.80 554	83.26 517	86.31 519	97.33 505	62.90 526	92.65 531	87.20 512	62.90 542	91.50 529

Anonymous20231206		96.22 411	96.03 412	96.79 458	97.31 494	94.14 472	99.63 104	99.08 402	96.17 415	97.04 460	99.06 419	93.94 329	97.76 497	86.96 513	95.06 425	98.47 439

RPMNet		96.72 401	95.90 415	99.19 233	99.18 347	98.49 279	99.22 365	99.52 135	88.72 505	99.56 178	97.38 503	94.08 324	99.95 77	86.87 514	98.58 282	99.14 306

testf1		90.42 476	90.68 476	89.65 508	97.78 483	73.97 539	99.13 385	98.81 448	89.62 499	91.80 507	98.93 439	62.23 528	98.80 473	86.61 515	91.17 481	96.19 517

APD_test2		90.42 476	90.68 476	89.65 508	97.78 483	73.97 539	99.13 385	98.81 448	89.62 499	91.80 507	98.93 439	62.23 528	98.80 473	86.61 515	91.17 481	96.19 517

PMMVS2		86.87 488	85.37 493	91.35 494	90.21 546	83.80 516	98.89 439	97.45 507	83.13 518	91.67 509	95.03 520	48.49 544	94.70 527	85.86 517	77.62 535	95.54 520

usedtu_dtu_shiyan2		91.34 471	89.96 480	95.47 473	93.61 536	90.81 496	99.15 381	98.68 469	86.37 511	95.19 480	98.27 474	72.64 509	97.05 507	85.40 518	80.32 531	98.54 429

MatchFormer		91.94 469	90.72 474	95.58 472	97.82 482	89.79 503	98.92 435	98.87 440	88.24 506	88.03 517	97.92 491	70.39 515	99.23 398	85.21 519	91.12 483	97.72 487

FPMVS		84.93 491	85.65 491	82.75 517	86.77 553	63.39 546	98.35 495	98.92 427	74.11 523	83.39 528	98.98 434	50.85 537	92.40 533	84.54 520	94.97 427	92.46 526

VLMVS_CLIP		71.76 507	73.17 510	67.54 532	63.66 562	40.57 565	82.57 549	89.67 544	44.24 553	82.97 531	95.88 518	37.85 554	71.58 555	83.87 521	77.80 534	90.48 531

SP-LightGlue		89.28 479	88.68 481	91.06 495	98.21 473	80.90 526	98.19 504	96.96 511	72.38 525	89.60 515	94.43 524	72.44 510	95.06 523	82.91 522	93.03 466	97.22 502

SP-NN		88.62 481	88.17 484	89.96 505	97.89 479	78.51 533	97.19 523	96.09 520	71.28 527	88.29 516	94.00 528	71.98 511	93.65 530	82.37 523	94.46 437	97.71 488

SP-SuperGlue		89.23 480	88.68 481	90.88 497	98.23 472	80.60 527	98.16 506	97.30 508	73.08 524	89.64 514	94.62 523	71.80 512	94.91 524	82.11 524	93.22 461	97.14 505

SP-MNN		88.33 482	87.78 485	89.95 506	98.28 468	77.92 534	98.01 512	95.69 524	70.61 529	86.18 520	94.36 526	71.09 514	94.76 526	81.51 525	94.32 442	97.17 503

MVS_clip		71.06 510	74.26 509	61.45 535	84.42 557	45.51 563	79.78 550	56.58 562	40.80 554	90.25 511	98.55 462	61.46 530	49.70 558	80.63 526	75.89 538	89.13 536

XFeat-NN		82.84 493	83.12 496	82.00 519	94.35 530	67.14 545	93.32 539	89.27 545	62.21 537	84.06 526	93.50 530	69.15 519	89.40 537	78.92 527	83.33 516	89.46 534

PMVS	70.75 22	75.98 503	74.97 506	79.01 520	70.98 559	55.18 558	93.37 537	98.21 491	65.08 536	61.78 549	93.83 529	21.74 562	92.53 532	78.59 528	91.12 483	89.34 535
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
dongtai		93.26 460	92.93 464	94.25 477	99.39 286	85.68 510	97.68 518	93.27 535	92.87 476	96.85 465	99.39 361	82.33 493	97.48 502	76.78 529	97.80 333	99.58 220

XFeat-MNN		82.40 496	82.10 497	83.31 515	93.04 538	68.49 543	95.39 528	90.86 541	60.29 538	81.56 533	94.09 527	66.79 523	91.70 535	76.62 530	80.26 532	89.74 533

WB-MVS		93.10 463	94.10 448	90.12 504	95.51 522	81.88 520	99.73 52	99.27 370	95.05 442	93.09 498	98.91 443	94.70 291	91.89 534	76.62 530	94.02 451	96.58 514

ANet_high		77.30 500	74.86 507	84.62 514	75.88 558	77.61 535	97.63 519	93.15 538	88.81 503	64.27 546	89.29 548	36.51 556	83.93 549	75.89 532	52.31 547	92.33 528

ALIKED-NN		88.27 484	87.61 486	90.24 502	98.46 464	79.97 530	97.04 524	94.61 532	75.25 521	86.99 518	96.90 510	72.78 508	95.78 519	75.45 533	91.01 485	94.97 522

GLUNet-SfM		78.99 499	76.32 503	86.99 511	89.16 551	73.30 542	93.36 538	90.45 542	66.38 534	74.95 543	93.30 531	52.29 536	94.61 528	75.35 534	51.65 549	93.07 525

SSC-MVS		92.73 465	93.73 455	89.72 507	95.02 526	81.38 523	99.76 38	99.23 379	94.87 447	92.80 499	98.93 439	94.71 290	91.37 536	74.49 535	93.80 453	96.42 515

ALIKED-MNN		86.97 487	85.90 489	90.16 503	99.06 380	79.59 531	97.93 513	94.82 528	72.37 526	84.41 524	95.46 519	68.55 521	96.43 514	72.40 536	88.11 502	94.47 523

VLMVS		64.83 515	67.01 516	58.30 537	65.95 561	42.53 564	76.90 552	66.20 560	29.52 555	82.93 532	94.37 525	42.34 548	55.19 557	72.39 537	72.45 539	77.18 540

ALIKED-LG		88.17 485	87.32 487	90.75 498	98.67 446	81.68 521	98.16 506	94.72 530	78.63 520	86.08 521	97.07 508	70.16 516	96.62 510	71.97 538	90.37 488	93.95 524

MVE	76.82 21	76.91 502	74.31 508	84.70 513	85.38 556	76.05 538	96.88 526	93.17 536	67.39 532	71.28 544	89.01 550	21.66 563	87.69 543	71.74 539	72.29 540	90.35 532
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 497	79.88 499	82.81 516	90.75 544	76.38 537	97.69 517	95.76 523	66.44 533	83.52 527	92.25 533	62.54 527	87.16 545	68.53 540	61.40 543	84.89 538

EMVS		80.02 498	79.22 500	82.43 518	91.19 543	76.40 536	97.55 521	92.49 540	66.36 535	83.01 530	91.27 535	64.63 525	85.79 548	65.82 541	60.65 544	85.08 537

kuosan		90.92 474	90.11 479	93.34 485	98.78 426	85.59 511	98.15 508	93.16 537	89.37 501	92.07 504	98.38 469	81.48 496	95.19 521	62.54 542	97.04 375	99.25 300

wuyk23d		40.18 520	41.29 525	36.84 538	86.18 555	49.12 561	79.73 551	22.81 565	27.64 556	25.46 560	28.45 559	21.98 561	48.89 559	55.80 543	23.56 559	12.51 557

SIFT-NN		76.99 501	77.37 502	75.84 521	97.10 499	62.39 547	94.15 533	87.21 547	59.41 539	79.90 539	90.73 539	54.60 535	88.56 540	47.22 544	86.03 506	76.57 541

SIFT-NN-NCMNet		75.53 505	75.57 505	75.42 523	93.93 534	61.35 548	94.41 530	86.44 548	58.51 541	76.23 540	90.44 541	50.56 538	89.34 538	46.60 545	83.04 517	75.58 543

SIFT-NN-CMatch		72.61 506	71.92 511	74.68 524	92.79 539	60.24 551	93.28 540	81.57 552	58.24 543	75.18 542	90.26 543	49.66 541	87.35 544	46.02 546	60.26 545	76.45 542

SIFT-NN-UMatch		71.65 508	70.86 512	74.00 526	90.69 545	60.53 550	93.59 535	81.89 550	58.42 542	60.99 550	89.71 546	50.18 539	87.89 542	45.77 547	66.55 541	73.57 547

SIFT-NN-PointCN		70.32 511	69.71 514	72.13 529	90.01 547	58.29 556	93.45 536	76.20 555	56.66 548	70.25 545	89.20 549	48.94 543	83.41 550	45.45 548	57.26 546	74.70 544

SIFT-MNN		75.73 504	75.71 504	75.77 522	95.65 517	60.92 549	94.36 531	87.62 546	58.67 540	75.90 541	90.94 538	49.64 542	89.04 539	44.85 549	83.80 512	77.35 539

SIFT-ConvMatch		69.43 512	68.09 515	73.45 527	93.86 535	60.02 553	92.57 543	77.69 553	57.58 544	62.69 547	90.53 540	42.14 549	86.65 547	43.98 550	51.72 548	73.67 546

SIFT-UMatch		68.14 513	66.40 517	73.38 528	92.20 542	59.42 554	92.84 541	76.01 556	56.87 546	58.37 551	90.35 542	41.97 550	87.16 545	42.64 551	46.35 551	73.55 548

SIFT-CM-Cal		66.94 514	65.48 518	71.33 530	93.05 537	58.77 555	91.46 546	70.45 558	56.64 549	61.97 548	89.98 544	40.72 551	83.32 551	42.57 552	42.47 553	71.90 549

SIFT-UM-Cal		64.60 516	62.65 519	70.42 531	92.22 541	58.07 557	92.29 544	66.92 559	56.70 547	50.16 555	89.97 545	37.90 553	82.95 552	42.33 553	35.40 556	70.24 551

MVS_baseline		35.35 523	39.65 526	22.45 541	47.29 563	11.23 568	38.03 553	9.90 567	5.09 560	58.24 552	91.18 536	16.48 564	0.13 562	42.28 554	48.39 550	55.99 554

SIFT-NCM-Cal		71.65 508	70.76 513	74.34 525	94.61 529	60.18 552	94.16 532	81.72 551	57.21 545	55.36 553	89.56 547	42.48 547	88.45 541	41.31 555	80.41 529	74.39 545

testmvs		39.17 521	43.78 523	25.37 540	36.04 565	16.84 567	98.36 494	26.56 564	20.06 557	38.51 559	67.32 554	29.64 559	15.30 561	37.59 556	39.90 555	43.98 556

test123		39.01 522	42.50 524	28.53 539	39.17 564	20.91 566	98.75 461	19.17 566	19.83 558	38.57 558	66.67 555	33.16 558	15.42 560	37.50 557	29.66 558	49.26 555

SIFT-PCN-Cal		61.29 518	60.21 521	64.54 534	89.88 548	50.56 560	91.21 547	65.73 561	53.15 551	48.59 556	87.20 551	36.60 555	76.52 553	37.37 558	32.17 557	66.54 552

SIFT-PointCN		62.71 517	61.56 520	66.18 533	89.53 550	50.88 559	91.81 545	72.35 557	53.65 550	50.49 554	86.32 552	33.30 557	76.23 554	35.91 559	40.66 554	71.43 550

SIFT-NCMNet		55.02 519	53.54 522	59.46 536	86.55 554	47.35 562	87.85 548	46.22 563	51.77 552	44.11 557	83.50 553	27.88 560	68.75 556	32.81 560	21.14 560	62.27 553

mmdepth		0.02 528	0.03 531	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.27 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

monomultidepth		0.02 528	0.03 531	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.27 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

test_blank		0.13 527	0.17 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	1.57 560	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

uanet_test		0.02 528	0.03 531	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.27 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

DCPMVS		0.02 528	0.03 531	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.27 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

cdsmvs_eth3d_5k		24.64 524	32.85 527	0.00 542	0.00 566	0.00 569	0.00 554	99.51 163	0.00 561	0.00 562	99.56 298	96.58 178	0.00 563	0.00 561	0.00 561	0.00 558

pcd_1.5k_mvsjas		8.27 526	11.03 529	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.27 561	99.01 19	0.00 563	0.00 561	0.00 561	0.00 558

sosnet-low-res		0.02 528	0.03 531	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.27 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

sosnet		0.02 528	0.03 531	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.27 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

uncertanet		0.02 528	0.03 531	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.27 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

Regformer		0.02 528	0.03 531	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.27 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

ab-mvs-re		8.30 525	11.06 528	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	99.58 289	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

uanet		0.02 528	0.03 531	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.27 561	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

Meshroom													0.00 563
: In preparation.
AliceVision / Meshro													0.00 563
: In preparation.
AliceVision_Meshroom													0.00 563
: In preparation.
PatchmatchNet2					0.00 566	95.16 448	98.77 459	99.17 391	93.82 460
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													99.13 422
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip				99.69 90	99.58 208	99.62 85	99.69 63	99.38 305	98.98 73	99.84 57	99.75 203	98.84 46	99.78 261		99.21 204	99.66 178

FOURS1					99.91 1	99.93 1	99.87 8	99.56 91	99.10 49	99.81 73

test_one_0601					99.81 59	99.88 11		99.49 203	98.97 77	99.65 148	99.81 143	99.09 15

eth-test2					0.00 566

eth-test					0.00 566

test_241102_ONE					99.84 39	99.90 3		99.48 215	99.07 59	99.91 32	99.74 209	99.20 8	99.76 270

save fliter					99.76 84	99.59 91	99.14 384	99.40 293	99.00 68

test0726					99.85 32	99.89 7	99.62 109	99.50 188	99.10 49	99.86 53	99.82 128	98.94 34

GSMVS																99.52 236

test_part2					99.81 59	99.83 24				99.77 91

sam_mvs1												94.86 273				99.52 236

sam_mvs												94.72 289

MTGPA								99.47 237

test_post											65.99 556	94.65 296	99.73 283

patchmatchnet-post											98.70 455	94.79 279	99.74 277

MTMP							99.54 175	98.88 438

TEST9					99.67 140	99.65 77	99.05 405	99.41 286	96.22 411	98.95 326	99.49 326	98.77 58	99.91 137

test_8					99.67 140	99.61 88	99.03 410	99.41 286	96.28 405	98.93 329	99.48 334	98.76 59	99.91 137

agg_prior					99.67 140	99.62 85		99.40 293		98.87 341			99.91 137

test_prior4						99.56 97	98.99 421

test_prior				99.68 91	99.67 140	99.48 114		99.56 91					99.83 224			99.74 119

新几何2							99.01 418

旧先验1					99.74 102	99.59 91		99.54 110			99.69 237	98.47 89			99.68 158	99.73 129

原ACMM2							98.95 431

test222					99.75 94	99.49 112	98.91 438	99.49 203	96.42 399	99.34 241	99.65 259	98.28 102			99.69 155	99.72 139

segment_acmp												98.96 27

testdata1							98.85 444		98.32 153

test12				99.75 78	99.64 169	99.61 88		99.29 361		99.21 273		98.38 97	99.89 165		99.74 147	99.74 119

plane_prior7					99.29 316	97.03 364

plane_prior6					99.27 321	96.98 368						92.71 362

plane_prior4											99.61 280

plane_prior3						97.00 366			98.69 109	99.11 293

plane_prior2							99.39 287		98.97 77

plane_prior1					99.26 326

plane_prior						96.97 369	99.21 367		98.45 134						97.60 342

n2								0.00 568

nn								0.00 568

door-mid								98.05 494

test11								99.35 324

door								97.92 495

HQP5-MVS						96.83 381

HQP-NCC					99.19 344		98.98 424		98.24 170	98.66 372

ACMP_Plane					99.19 344		98.98 424		98.24 170	98.66 372

HQP4-MVS										98.66 372			99.64 323			98.64 396

HQP3-MVS								99.39 296							97.58 344

HQP2-MVS												92.47 371

NP-MVS					99.23 334	96.92 376					99.40 357

ACMMP++_ref															97.19 372

ACMMP++															97.43 362

Test By Simon												98.75 62

High-resolution multi-view benchmark