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_conf0.5_n_9		99.58 16	99.47 24	99.92 1	99.85 31	99.82 29	99.47 241	99.63 46	99.45 13	99.98 13	99.89 45	97.02 149	99.99 4	99.98 1	99.96 17	99.95 11

fmvsm_s_conf0.5_n_10		99.41 59	99.24 77	99.92 1	99.83 47	99.84 20	99.53 183	99.56 90	99.45 13	99.99 2	99.92 18	94.92 267	99.99 4	99.97 2	99.97 9	99.95 11

fmvsm_s_conf0.5_n_9		99.41 59	99.28 68	99.81 60	99.84 38	99.52 107	99.48 231	99.62 52	99.46 9	99.99 2	99.92 18	95.24 254	99.96 41	99.97 2	99.97 9	99.96 7

fmvsm_s_conf0.5_n_7		99.34 75	99.29 65	99.48 165	99.70 123	98.63 257	99.42 269	99.63 46	99.46 9	99.98 13	99.88 58	95.59 237	99.96 41	99.97 2	99.98 4	99.85 47

fmvsm_s_conf0.5_n_5		99.37 68	99.21 83	99.86 34	99.80 64	99.68 65	99.42 269	99.61 61	99.37 26	99.97 25	99.86 85	94.96 262	99.99 4	99.97 2	99.93 32	99.92 25

fmvsm_l_conf0.5_n_3		99.61 10	99.51 18	99.92 1	99.84 38	99.82 29	99.54 174	99.66 32	99.46 9	99.98 13	99.89 45	97.27 134	99.99 4	99.97 2	99.95 22	99.95 11

fmvsm_s_conf0.1_n_2		99.37 68	99.22 82	99.81 60	99.77 79	99.75 52	99.46 245	99.60 68	99.47 6	99.98 13	99.94 6	94.98 261	99.95 76	99.97 2	99.79 133	99.73 128

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 43	99.86 25	99.61 87	99.56 154	99.63 46	99.48 3	99.98 13	99.83 116	98.75 61	99.99 4	99.97 2	99.96 17	99.94 17

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 43	99.84 38	99.63 83	99.56 154	99.63 46	99.47 6	99.98 13	99.82 127	98.75 61	99.99 4	99.97 2	99.97 9	99.94 17

MM		99.40 64	99.28 68	99.74 80	99.67 139	99.31 137	99.52 185	98.87 437	99.55 1	99.74 101	99.80 160	96.47 182	99.98 20	99.97 2	99.97 9	99.94 17

test_fmvsmvis_n_1920		99.65 8	99.61 8	99.77 74	99.38 288	99.37 125	99.58 138	99.62 52	99.41 23	99.87 48	99.92 18	98.81 49	100.00 1	99.97 2	99.93 32	99.94 17

test_fmvsm_n_1920		99.69 6	99.66 3	99.78 71	99.84 38	99.44 118	99.58 138	99.69 22	99.43 19	99.98 13	99.91 26	98.62 77	100.00 1	99.97 2	99.95 22	99.90 27

fmvsm_s_conf0.5_n_11		99.32 78	99.16 91	99.80 64	99.83 47	99.70 61	99.57 146	99.56 90	99.45 13	99.99 2	99.93 10	94.18 318	99.99 4	99.96 13	99.98 4	99.73 128

fmvsm_s_conf0.5_n_2		99.32 78	99.13 94	99.89 12	99.80 64	99.77 49	99.44 256	99.58 78	99.47 6	99.99 2	99.93 10	94.04 323	99.96 41	99.96 13	99.93 32	99.93 22

test_fmvsmconf_n		99.70 3	99.64 4	99.87 22	99.80 64	99.66 72	99.48 231	99.64 42	99.45 13	99.92 30	99.92 18	98.62 77	99.99 4	99.96 13	99.99 1	99.96 7

fmvsm_s_conf0.5_n_8		99.54 24	99.42 32	99.89 12	99.83 47	99.74 55	99.51 195	99.62 52	99.46 9	99.99 2	99.90 36	96.60 174	99.98 20	99.95 16	99.95 22	99.96 7

fmvsm_s_conf0.5_n_6		99.54 24	99.44 31	99.85 43	99.51 238	99.67 69	99.50 206	99.64 42	99.43 19	99.98 13	99.78 184	97.26 137	99.95 76	99.95 16	99.93 32	99.92 25

fmvsm_s_conf0.5_n_4		99.36 72	99.24 77	99.73 83	99.78 71	99.53 103	99.49 223	99.60 68	99.42 22	99.99 2	99.86 85	95.15 257	99.95 76	99.95 16	99.89 67	99.73 128

fmvsm_s_conf0.5_n		99.51 29	99.40 37	99.85 43	99.84 38	99.65 76	99.51 195	99.67 27	99.13 41	99.98 13	99.92 18	96.60 174	99.96 41	99.95 16	99.96 17	99.95 11

test_fmvsmconf0.1_n		99.55 23	99.45 30	99.86 34	99.44 269	99.65 76	99.50 206	99.61 61	99.45 13	99.87 48	99.92 18	97.31 131	99.97 29	99.95 16	99.99 1	99.97 4

fmvsm_s_conf0.5_n_3		99.37 68	99.20 85	99.87 22	99.75 93	99.70 61	99.48 231	99.66 32	99.45 13	99.99 2	99.93 10	94.64 295	99.97 29	99.94 21	99.97 9	99.95 11

fmvsm_s_conf0.5_n_a		99.56 21	99.47 24	99.85 43	99.83 47	99.64 82	99.52 185	99.65 39	99.10 48	99.98 13	99.92 18	97.35 130	99.96 41	99.94 21	99.92 38	99.95 11

test_fmvsmconf0.01_n		99.22 99	99.03 118	99.79 68	98.42 462	99.48 113	99.55 169	99.51 162	99.39 24	99.78 86	99.93 10	94.80 276	99.95 76	99.93 23	99.95 22	99.94 17

test_vis1_n_1920		98.63 227	98.40 235	99.31 208	99.86 25	97.94 314	99.67 77	99.62 52	99.43 19	99.99 2	99.91 26	87.29 453	100.00 1	99.92 24	99.92 38	99.98 2

fmvsm_s_conf0.1_n		99.29 84	99.10 99	99.86 34	99.70 123	99.65 76	99.53 183	99.62 52	98.74 102	99.99 2	99.95 3	94.53 303	99.94 91	99.89 25	99.96 17	99.97 4

fmvsm_s_conf0.1_n_a		99.26 91	99.06 110	99.85 43	99.52 235	99.62 84	99.54 174	99.62 52	98.69 108	99.99 2	99.96 1	94.47 305	99.94 91	99.88 26	99.92 38	99.98 2

test_vis1_n		97.92 302	97.44 343	99.34 200	99.53 229	98.08 301	99.74 48	99.49 201	99.15 38	100.00 1	99.94 6	79.51 497	99.98 20	99.88 26	99.76 141	99.97 4

MGCNet		99.15 117	98.96 152	99.73 83	98.92 400	99.37 125	99.37 295	96.92 507	99.51 2	99.66 136	99.78 184	96.69 169	99.97 29	99.84 28	99.97 9	99.84 54

mmtdpeth		96.95 392	96.71 391	97.67 422	99.33 301	94.90 450	99.89 2	99.28 361	98.15 183	99.72 108	98.57 457	86.56 461	99.90 149	99.82 29	89.02 493	98.20 455

test_fmvs1_n		98.41 239	98.14 252	99.21 229	99.82 53	97.71 326	99.74 48	99.49 201	99.32 30	99.99 2	99.95 3	85.32 472	99.97 29	99.82 29	99.84 102	99.96 7

test_fmvs1		98.88 186	98.79 189	99.16 234	99.69 129	97.61 330	99.55 169	99.49 201	99.32 30	99.98 13	99.91 26	91.41 397	99.96 41	99.82 29	99.92 38	99.90 27

AstraMVS		99.09 152	99.03 118	99.25 223	99.66 151	98.13 297	99.57 146	98.24 484	98.82 90	99.91 31	99.88 58	95.81 226	99.90 149	99.72 32	99.67 159	99.74 118

mvsany_test1		99.50 31	99.46 28	99.62 109	99.61 194	99.09 169	98.94 429	99.48 213	99.10 48	99.96 27	99.91 26	98.85 43	99.96 41	99.72 32	99.58 170	99.82 72

patch_mono-2		99.26 91	99.62 7	98.16 374	99.81 58	94.59 460	99.52 185	99.64 42	99.33 29	99.73 103	99.90 36	99.00 23	99.99 4	99.69 34	99.98 4	99.89 30

SPE-MVS-test		99.49 33	99.48 22	99.54 127	99.78 71	99.30 140	99.89 2	99.58 78	98.56 119	99.73 103	99.69 236	98.55 82	99.82 232	99.69 34	99.85 94	99.48 252

balanced_ft_v1		99.02 168	98.98 146	99.15 238	99.39 285	98.12 299	99.79 31	99.51 162	98.20 176	99.66 136	99.87 74	94.84 272	99.93 109	99.69 34	99.84 102	99.41 273

LuminaMVS		99.23 97	99.10 99	99.61 110	99.35 295	99.31 137	99.46 245	99.13 393	98.61 114	99.86 52	99.89 45	96.41 188	99.91 136	99.67 37	99.51 175	99.63 196

SDMVSNet		99.11 145	98.90 167	99.75 77	99.81 58	99.59 90	99.81 20	99.65 39	98.78 99	99.64 151	99.88 58	94.56 298	99.93 109	99.67 37	98.26 303	99.72 138

dcpmvs_2		99.23 97	99.58 9	98.16 374	99.83 47	94.68 456	99.76 38	99.52 134	99.07 58	99.98 13	99.88 58	98.56 81	99.93 109	99.67 37	99.98 4	99.87 41

guyue		99.16 112	99.04 115	99.52 142	99.69 129	98.92 209	99.59 128	98.81 445	98.73 103	99.90 34	99.87 74	95.34 247	99.88 169	99.66 40	99.81 121	99.74 118

MVSMamba_PlusPlus		99.46 42	99.41 36	99.64 102	99.68 136	99.50 110	99.75 43	99.50 187	98.27 158	99.87 48	99.92 18	98.09 109	99.94 91	99.65 41	99.95 22	99.47 258

CS-MVS		99.50 31	99.48 22	99.54 127	99.76 83	99.42 120	99.90 1	99.55 100	98.56 119	99.78 86	99.70 225	98.65 75	99.79 252	99.65 41	99.78 135	99.41 273

EC-MVSNet		99.44 50	99.39 39	99.58 118	99.56 217	99.49 111	99.88 4	99.58 78	98.38 141	99.73 103	99.69 236	98.20 104	99.70 299	99.64 43	99.82 118	99.54 229

BP-MVS1		99.12 139	98.94 158	99.65 96	99.51 238	99.30 140	99.67 77	98.92 424	98.48 128	99.84 56	99.69 236	94.96 262	99.92 124	99.62 44	99.79 133	99.71 150

CANet		99.25 95	99.14 93	99.59 114	99.41 277	99.16 158	99.35 306	99.57 85	98.82 90	99.51 189	99.61 279	96.46 183	99.95 76	99.59 45	99.98 4	99.65 184

EI-MVSNet-UG-set		99.58 16	99.57 10	99.64 102	99.78 71	99.14 164	99.60 117	99.45 259	99.01 64	99.90 34	99.83 116	98.98 25	99.93 109	99.59 45	99.95 22	99.86 43

BridgeMVS		99.46 42	99.39 39	99.67 91	99.55 221	99.58 95	99.74 48	99.51 162	98.42 136	99.87 48	99.84 107	98.05 112	99.91 136	99.58 47	99.94 30	99.52 235

DELS-MVS		99.48 37	99.42 32	99.65 96	99.72 112	99.40 123	99.05 401	99.66 32	99.14 40	99.57 174	99.80 160	98.46 89	99.94 91	99.57 48	99.84 102	99.60 204
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 16	99.56 12	99.64 102	99.78 71	99.15 163	99.61 115	99.45 259	99.01 64	99.89 39	99.82 127	99.01 19	99.92 124	99.56 49	99.95 22	99.85 47

test_cas_vis1_n_1920		99.16 112	99.01 137	99.61 110	99.81 58	98.86 229	99.65 90	99.64 42	99.39 24	99.97 25	99.94 6	93.20 347	99.98 20	99.55 50	99.91 45	99.99 1

sd_testset		98.75 215	98.57 223	99.29 216	99.81 58	98.26 290	99.56 154	99.62 52	98.78 99	99.64 151	99.88 58	92.02 379	99.88 169	99.54 51	98.26 303	99.72 138

casdiffmvs_mvg		99.15 117	99.02 129	99.55 126	99.66 151	99.09 169	99.64 98	99.56 90	98.26 161	99.45 198	99.87 74	96.03 211	99.81 237	99.54 51	99.15 213	99.73 128
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		95.81 418	95.65 417	96.32 460	99.67 139	91.35 489	99.49 223	96.74 511	98.25 166	95.24 473	98.10 478	74.96 499	99.90 149	99.53 53	98.85 264	97.70 486

HyFIR lowres test		99.11 145	98.92 161	99.65 96	99.90 4	99.37 125	99.02 409	99.91 3	97.67 276	99.59 170	99.75 202	95.90 221	99.73 281	99.53 53	99.02 248	99.86 43

VNet		99.11 145	98.90 167	99.73 83	99.52 235	99.56 96	99.41 274	99.39 294	99.01 64	99.74 101	99.78 184	95.56 238	99.92 124	99.52 55	98.18 311	99.72 138

baseline		99.15 117	99.02 129	99.53 135	99.66 151	99.14 164	99.72 54	99.48 213	98.35 146	99.42 209	99.84 107	96.07 207	99.79 252	99.51 56	99.14 214	99.67 170

xiu_mvs_v1_base_debu		99.29 84	99.27 72	99.34 200	99.63 173	98.97 189	99.12 384	99.51 162	98.86 85	99.84 56	99.47 335	98.18 105	99.99 4	99.50 57	99.31 192	99.08 311

xiu_mvs_v1_base		99.29 84	99.27 72	99.34 200	99.63 173	98.97 189	99.12 384	99.51 162	98.86 85	99.84 56	99.47 335	98.18 105	99.99 4	99.50 57	99.31 192	99.08 311

xiu_mvs_v1_base_debi		99.29 84	99.27 72	99.34 200	99.63 173	98.97 189	99.12 384	99.51 162	98.86 85	99.84 56	99.47 335	98.18 105	99.99 4	99.50 57	99.31 192	99.08 311

CHOSEN 1792x2688		99.19 101	99.10 99	99.45 175	99.89 8	98.52 272	99.39 286	99.94 1	98.73 103	99.11 291	99.89 45	95.50 240	99.94 91	99.50 57	99.97 9	99.89 30

viewdifsd2359ckpt11		98.78 210	98.74 195	98.89 275	99.67 139	97.04 359	99.50 206	99.58 78	98.26 161	99.56 176	99.90 36	94.36 308	99.87 176	99.49 61	98.32 299	99.77 100

viewmsd2359difaftdt		98.78 210	98.74 195	98.90 271	99.67 139	97.04 359	99.50 206	99.58 78	98.26 161	99.56 176	99.90 36	94.36 308	99.87 176	99.49 61	98.32 299	99.77 100

VDD-MVS		97.73 338	97.35 355	98.88 280	99.47 260	97.12 349	99.34 311	98.85 440	98.19 178	99.67 131	99.85 92	82.98 485	99.92 124	99.49 61	98.32 299	99.60 204

h-mvs33		97.70 344	97.28 368	98.97 256	99.70 123	97.27 341	99.36 301	99.45 259	98.94 79	99.66 136	99.64 264	94.93 265	99.99 4	99.48 64	84.36 503	99.65 184

hse-mvs2		97.50 365	97.14 376	98.59 319	99.49 252	97.05 356	99.28 333	99.22 379	98.94 79	99.66 136	99.42 346	94.93 265	99.65 316	99.48 64	83.80 507	99.08 311

onestephybrid01		99.17 109	99.06 110	99.49 160	99.60 201	98.98 185	99.38 291	99.50 187	98.52 123	99.81 72	99.87 74	96.27 195	99.81 237	99.47 66	99.10 233	99.67 170

PVSNet_Blended_VisFu		99.36 72	99.28 68	99.61 110	99.86 25	99.07 174	99.47 241	99.93 2	97.66 277	99.71 118	99.86 85	97.73 120	99.96 41	99.47 66	99.82 118	99.79 92

viewmamba		99.20 100	99.12 96	99.44 180	99.61 194	98.87 225	99.42 269	99.52 134	98.42 136	99.84 56	99.84 107	96.85 156	99.78 260	99.46 68	99.11 224	99.67 170

CHOSEN 280x420		99.12 139	99.13 94	99.08 242	99.66 151	97.89 315	98.43 488	99.71 16	98.88 84	99.62 158	99.76 197	96.63 172	99.70 299	99.46 68	99.99 1	99.66 177

casdiffmvs		99.13 129	98.98 146	99.56 124	99.65 163	99.16 158	99.56 154	99.50 187	98.33 149	99.41 214	99.86 85	95.92 219	99.83 223	99.45 70	99.16 207	99.70 154
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		98.04 282	98.11 256	97.83 410	99.74 101	93.82 469	99.58 138	95.40 520	99.12 46	99.65 146	99.93 10	90.73 410	99.84 201	99.43 71	99.38 184	99.82 72

hybridcas		99.13 129	99.00 141	99.51 147	99.70 123	99.04 178	99.65 90	99.52 134	98.20 176	99.75 100	99.88 58	95.78 229	99.78 260	99.41 72	99.16 207	99.71 150

viewmambaseed2359dif		99.01 173	98.90 167	99.32 206	99.58 207	98.51 274	99.33 313	99.54 109	97.85 248	99.44 203	99.85 92	96.01 212	99.79 252	99.41 72	99.13 217	99.67 170

hybridnocas07		99.13 129	99.03 118	99.46 173	99.63 173	98.90 215	99.38 291	99.52 134	98.41 138	99.82 70	99.84 107	96.09 206	99.80 245	99.40 74	99.16 207	99.68 163

Casviewmamba		99.16 112	99.02 129	99.59 114	99.66 151	99.21 152	99.68 73	99.52 134	98.31 153	99.60 166	99.87 74	95.96 214	99.85 191	99.40 74	99.16 207	99.72 138

hybrid		99.11 145	99.01 137	99.41 187	99.64 168	98.76 245	99.35 306	99.52 134	98.31 153	99.80 78	99.84 107	96.16 202	99.79 252	99.40 74	99.06 242	99.68 163

diffmvs_AUTHOR		99.19 101	99.10 99	99.48 165	99.64 168	98.85 230	99.32 316	99.48 213	98.50 126	99.81 72	99.81 142	96.82 162	99.88 169	99.40 74	99.12 222	99.71 150

VortexMVS		98.67 222	98.66 206	98.68 313	99.62 183	97.96 309	99.59 128	99.41 284	98.13 190	99.31 242	99.70 225	95.48 242	99.27 386	99.40 74	97.32 363	98.79 339

ECVR-MVS		98.04 282	98.05 265	98.00 388	99.74 101	94.37 464	99.59 128	94.98 521	99.13 41	99.66 136	99.93 10	90.67 411	99.84 201	99.40 74	99.38 184	99.80 88

test2506		96.81 396	96.65 392	97.29 439	99.74 101	92.21 486	99.60 117	85.06 543	99.13 41	99.77 90	99.93 10	87.82 451	99.85 191	99.38 80	99.38 184	99.80 88

dtuplus		99.03 166	98.92 161	99.36 196	99.60 201	98.62 259	99.35 306	99.51 162	97.99 232	99.38 223	99.88 58	96.04 209	99.79 252	99.37 81	99.17 206	99.68 163

DeepC-MVS	98.35 2	99.30 82	99.19 87	99.64 102	99.82 53	99.23 150	99.62 109	99.55 100	98.94 79	99.63 154	99.95 3	95.82 225	99.94 91	99.37 81	99.97 9	99.73 128
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
reproduce_monomvs		97.89 306	97.87 286	97.96 393	99.51 238	95.45 434	99.60 117	99.25 373	99.17 36	98.85 344	99.49 324	89.29 429	99.64 320	99.35 83	96.31 387	98.78 341

alignmvs		98.81 205	98.56 225	99.58 118	99.43 270	99.42 120	99.51 195	98.96 419	98.61 114	99.35 235	98.92 440	94.78 278	99.77 265	99.35 83	98.11 316	99.54 229

PS-MVSNAJ		99.32 78	99.32 53	99.30 213	99.57 213	98.94 203	98.97 423	99.46 248	98.92 82	99.71 118	99.24 397	99.01 19	99.98 20	99.35 83	99.66 160	98.97 329

VPA-MVSNet		98.29 252	97.95 276	99.30 213	99.16 353	99.54 100	99.50 206	99.58 78	98.27 158	99.35 235	99.37 365	92.53 367	99.65 316	99.35 83	94.46 432	98.72 355

mvs_anonymous		99.03 166	98.99 143	99.16 234	99.38 288	98.52 272	99.51 195	99.38 303	97.79 258	99.38 223	99.81 142	97.30 132	99.45 346	99.35 83	98.99 250	99.51 244

test-260524					99.82 53	99.84 20		99.63 46		99.85 55		98.54 83	99.94 91	99.34 88	99.88 73

xiu_mvs_v2_base		99.26 91	99.25 76	99.29 216	99.53 229	98.91 210	99.02 409	99.45 259	98.80 95	99.71 118	99.26 395	98.94 33	99.98 20	99.34 88	99.23 201	98.98 327

nrg030		98.64 226	98.42 233	99.28 220	99.05 380	99.69 64	99.81 20	99.46 248	98.04 224	99.01 311	99.82 127	96.69 169	99.38 363	99.34 88	94.59 431	98.78 341

UGNet		98.87 189	98.69 201	99.40 189	99.22 334	98.72 249	99.44 256	99.68 24	99.24 33	99.18 282	99.42 346	92.74 357	99.96 41	99.34 88	99.94 30	99.53 234
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 3	99.63 5	99.92 1	99.88 13	99.90 2	99.69 63	99.79 11	99.48 3	99.93 29	99.89 45	98.78 53	99.93 109	99.32 92	99.88 73	99.93 22

testing3-2		97.84 316	97.70 308	98.24 369	99.53 229	95.37 438	99.55 169	98.67 468	98.46 130	99.27 256	99.34 375	86.58 460	99.83 223	99.32 92	98.63 276	99.52 235

mvs_tets		98.40 242	98.23 246	98.91 269	98.67 442	98.51 274	99.66 84	99.53 125	98.19 178	98.65 374	99.81 142	92.75 355	99.44 351	99.31 94	97.48 353	98.77 345

VDDNet		97.55 359	97.02 382	99.16 234	99.49 252	98.12 299	99.38 291	99.30 355	95.35 430	99.68 125	99.90 36	82.62 487	99.93 109	99.31 94	98.13 315	99.42 270

diffmvs		99.14 125	99.02 129	99.51 147	99.61 194	98.96 193	99.28 333	99.49 201	98.46 130	99.72 108	99.71 221	96.50 181	99.88 169	99.31 94	99.11 224	99.67 170
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		99.14 125	99.02 129	99.50 153	99.69 129	98.91 210	99.60 117	99.53 125	98.13 190	99.72 108	99.91 26	96.26 198	99.84 201	99.30 97	99.10 233	99.76 107

E6new		99.15 117	99.03 118	99.50 153	99.66 151	98.90 215	99.60 117	99.53 125	98.13 190	99.72 108	99.91 26	96.31 192	99.84 201	99.30 97	99.10 233	99.76 107

E6		99.15 117	99.03 118	99.50 153	99.66 151	98.90 215	99.60 117	99.53 125	98.13 190	99.72 108	99.91 26	96.31 192	99.84 201	99.30 97	99.10 233	99.76 107

E5		99.14 125	99.02 129	99.50 153	99.69 129	98.91 210	99.60 117	99.53 125	98.13 190	99.72 108	99.91 26	96.26 198	99.84 201	99.30 97	99.10 233	99.76 107

NormalMVS		99.27 88	99.19 87	99.52 142	99.89 8	98.83 235	99.65 90	99.52 134	99.10 48	99.84 56	99.76 197	95.80 227	99.99 4	99.30 97	99.84 102	99.74 118

SymmetryMVS		99.15 117	99.02 129	99.52 142	99.72 112	98.83 235	99.65 90	99.34 327	99.10 48	99.84 56	99.76 197	95.80 227	99.99 4	99.30 97	98.72 273	99.73 128

casdiffseed414692147		98.97 179	98.78 190	99.53 135	99.66 151	99.16 158	99.61 115	99.52 134	98.01 230	99.21 271	99.88 58	94.82 273	99.70 299	99.29 103	99.04 245	99.74 118

MGCFI-Net		99.01 173	98.85 181	99.50 153	99.42 272	99.26 146	99.82 16	99.48 213	98.60 116	99.28 250	98.81 446	97.04 148	99.76 269	99.29 103	97.87 326	99.47 258

lecture		99.60 14	99.50 19	99.89 12	99.89 8	99.90 2	99.75 43	99.59 73	99.06 61	99.88 42	99.85 92	98.41 94	99.96 41	99.28 105	99.84 102	99.83 64

LFMVS		97.90 305	97.35 355	99.54 127	99.52 235	99.01 182	99.39 286	98.24 484	97.10 339	99.65 146	99.79 177	84.79 475	99.91 136	99.28 105	98.38 292	99.69 157

MSLP-MVS++		99.46 42	99.47 24	99.44 180	99.60 201	99.16 158	99.41 274	99.71 16	98.98 72	99.45 198	99.78 184	99.19 10	99.54 337	99.28 105	99.84 102	99.63 196

viewdifsd2359ckpt07		99.11 145	99.00 141	99.43 184	99.63 173	98.73 247	99.45 249	99.54 109	98.33 149	99.62 158	99.81 142	96.17 201	99.87 176	99.27 108	99.14 214	99.69 157

sasdasda		99.02 168	98.86 178	99.51 147	99.42 272	99.32 133	99.80 25	99.48 213	98.63 111	99.31 242	98.81 446	97.09 144	99.75 272	99.27 108	97.90 322	99.47 258

canonicalmvs		99.02 168	98.86 178	99.51 147	99.42 272	99.32 133	99.80 25	99.48 213	98.63 111	99.31 242	98.81 446	97.09 144	99.75 272	99.27 108	97.90 322	99.47 258

Anonymous20240529		98.09 270	97.68 310	99.34 200	99.66 151	98.44 282	99.40 282	99.43 279	93.67 457	99.22 268	99.89 45	90.23 417	99.93 109	99.26 111	98.33 295	99.66 177

EPNet		98.86 192	98.71 199	99.30 213	97.20 492	98.18 293	99.62 109	98.91 429	99.28 32	98.63 377	99.81 142	95.96 214	99.99 4	99.24 112	99.72 149	99.73 128
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
jajsoiax		98.43 236	98.28 243	98.88 280	98.60 451	98.43 283	99.82 16	99.53 125	98.19 178	98.63 377	99.80 160	93.22 346	99.44 351	99.22 113	97.50 349	98.77 345

APDe-MVS		99.66 7	99.57 10	99.92 1	99.77 79	99.89 6	99.75 43	99.56 90	99.02 62	99.88 42	99.85 92	99.18 11	99.96 41	99.22 113	99.92 38	99.90 27
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
E4		99.13 129	99.01 137	99.49 160	99.68 136	98.90 215	99.52 185	99.52 134	98.13 190	99.71 118	99.90 36	96.32 190	99.84 201	99.21 115	99.11 224	99.75 113

viewmacassd2359aftdt		99.08 154	98.94 158	99.50 153	99.66 151	98.96 193	99.51 195	99.54 109	98.27 158	99.42 209	99.89 45	95.88 223	99.80 245	99.20 116	99.11 224	99.76 107

SSM_0407		99.13 129	99.03 118	99.43 184	99.62 183	98.88 221	99.51 195	99.50 187	98.14 187	99.37 226	99.85 92	96.85 156	99.83 223	99.19 117	99.25 198	99.60 204

SSM_0404		99.16 112	99.06 110	99.44 180	99.65 163	98.96 193	99.49 223	99.50 187	98.14 187	99.62 158	99.85 92	96.85 156	99.85 191	99.19 117	99.26 197	99.52 235

VPNet		97.84 316	97.44 343	99.01 250	99.21 335	98.94 203	99.48 231	99.57 85	98.38 141	99.28 250	99.73 214	88.89 432	99.39 361	99.19 117	93.27 455	98.71 357

mvsmamba		99.06 159	98.96 152	99.36 196	99.47 260	98.64 256	99.70 59	99.05 405	97.61 282	99.65 146	99.83 116	96.54 179	99.92 124	99.19 117	99.62 166	99.51 244

sss		99.17 109	99.05 113	99.53 135	99.62 183	98.97 189	99.36 301	99.62 52	97.83 252	99.67 131	99.65 258	97.37 129	99.95 76	99.19 117	99.19 205	99.68 163

Vis-MVSNet		99.12 139	98.97 148	99.56 124	99.78 71	99.10 168	99.68 73	99.66 32	98.49 127	99.86 52	99.87 74	94.77 281	99.84 201	99.19 117	99.41 183	99.74 118
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
E2		99.15 117	99.03 118	99.49 160	99.65 163	98.93 208	99.49 223	99.52 134	98.14 187	99.72 108	99.88 58	96.57 178	99.84 201	99.17 123	99.13 217	99.72 138

E3		99.15 117	99.03 118	99.49 160	99.62 183	98.91 210	99.49 223	99.52 134	98.13 190	99.72 108	99.88 58	96.61 173	99.84 201	99.17 123	99.13 217	99.72 138

ab-mvs		98.86 192	98.63 211	99.54 127	99.64 168	99.19 153	99.44 256	99.54 109	97.77 261	99.30 246	99.81 142	94.20 315	99.93 109	99.17 123	98.82 267	99.49 249

Anonymous202405211		98.30 251	97.98 272	99.26 222	99.57 213	98.16 294	99.41 274	98.55 474	96.03 422	99.19 278	99.74 208	91.87 382	99.92 124	99.16 126	98.29 302	99.70 154

viewmanbaseed2359cas		99.18 104	99.07 109	99.50 153	99.62 183	99.01 182	99.50 206	99.52 134	98.25 166	99.68 125	99.82 127	96.93 154	99.80 245	99.15 127	99.11 224	99.70 154

viewcassd2359sk11		99.18 104	99.08 105	99.49 160	99.65 163	98.95 199	99.48 231	99.51 162	98.10 204	99.72 108	99.87 74	97.13 140	99.84 201	99.13 128	99.14 214	99.69 157

PS-MVSNAJss		98.92 183	98.92 161	98.90 271	98.78 422	98.53 268	99.78 33	99.54 109	98.07 210	99.00 315	99.76 197	99.01 19	99.37 366	99.13 128	97.23 366	98.81 338

EPP-MVSNet		99.13 129	98.99 143	99.53 135	99.65 163	99.06 175	99.81 20	99.33 335	97.43 306	99.60 166	99.88 58	97.14 139	99.84 201	99.13 128	98.94 252	99.69 157

reproduce_model		99.63 9	99.54 13	99.90 8	99.78 71	99.88 10	99.56 154	99.55 100	99.15 38	99.90 34	99.90 36	99.00 23	99.97 29	99.11 131	99.91 45	99.86 43

Effi-MVS+		98.81 205	98.59 222	99.48 165	99.46 262	99.12 167	98.08 505	99.50 187	97.50 297	99.38 223	99.41 350	96.37 189	99.81 237	99.11 131	98.54 285	99.51 244

RRT-MVS		98.91 184	98.75 193	99.39 194	99.46 262	98.61 262	99.76 38	99.50 187	98.06 214	99.81 72	99.88 58	93.91 330	99.94 91	99.11 131	99.27 195	99.61 201

E3new		99.18 104	99.08 105	99.48 165	99.63 173	98.94 203	99.46 245	99.50 187	98.06 214	99.72 108	99.84 107	97.27 134	99.84 201	99.10 134	99.13 217	99.67 170

ETV-MVS		99.26 91	99.21 83	99.40 189	99.46 262	99.30 140	99.56 154	99.52 134	98.52 123	99.44 203	99.27 393	98.41 94	99.86 183	99.10 134	99.59 169	99.04 319

TSAR-MVS + GP.		99.36 72	99.36 45	99.36 196	99.67 139	98.61 262	99.07 394	99.33 335	99.00 67	99.82 70	99.81 142	99.06 17	99.84 201	99.09 136	99.42 182	99.65 184

FIs		98.78 210	98.63 211	99.23 228	99.18 343	99.54 100	99.83 15	99.59 73	98.28 156	98.79 352	99.81 142	96.75 167	99.37 366	99.08 137	96.38 384	98.78 341

FC-MVSNet-test		98.75 215	98.62 216	99.15 238	99.08 370	99.45 117	99.86 11	99.60 68	98.23 171	98.70 365	99.82 127	96.80 164	99.22 401	99.07 138	96.38 384	98.79 339

HPM-MVS_fast		99.51 29	99.40 37	99.85 43	99.91 1	99.79 42	99.76 38	99.56 90	97.72 268	99.76 96	99.75 202	99.13 13	99.92 124	99.07 138	99.92 38	99.85 47

viewdifsd2359ckpt13		99.06 159	98.93 160	99.45 175	99.63 173	98.96 193	99.50 206	99.51 162	97.83 252	99.28 250	99.80 160	96.68 171	99.71 291	99.05 140	99.12 222	99.68 163

reproduce-ours		99.61 10	99.52 14	99.90 8	99.76 83	99.88 10	99.52 185	99.54 109	99.13 41	99.89 39	99.89 45	98.96 26	99.96 41	99.04 141	99.90 56	99.85 47

our_new_method		99.61 10	99.52 14	99.90 8	99.76 83	99.88 10	99.52 185	99.54 109	99.13 41	99.89 39	99.89 45	98.96 26	99.96 41	99.04 141	99.90 56	99.85 47

MVSFormer		99.17 109	99.12 96	99.29 216	99.51 238	98.94 203	99.88 4	99.46 248	97.55 289	99.80 78	99.65 258	97.39 126	99.28 383	99.03 143	99.85 94	99.65 184

test_djsdf		98.67 222	98.57 223	98.98 254	98.70 437	98.91 210	99.88 4	99.46 248	97.55 289	99.22 268	99.88 58	95.73 232	99.28 383	99.03 143	97.62 337	98.75 349

jason		99.13 129	99.03 118	99.45 175	99.46 262	98.87 225	99.12 384	99.26 370	98.03 226	99.79 81	99.65 258	97.02 149	99.85 191	99.02 145	99.90 56	99.65 184
jason: jason.
DeepPCF-MVS	98.18 3	98.81 205	99.37 43	97.12 443	99.60 201	91.75 487	98.61 470	99.44 268	99.35 27	99.83 66	99.85 92	98.70 70	99.81 237	99.02 145	99.91 45	99.81 79

CSCG		99.32 78	99.32 53	99.32 206	99.85 31	98.29 288	99.71 58	99.66 32	98.11 200	99.41 214	99.80 160	98.37 97	99.96 41	98.99 147	99.96 17	99.72 138

mamba_0408		99.08 154	98.96 152	99.44 180	99.62 183	98.88 221	99.25 349	99.47 235	98.05 217	99.37 226	99.81 142	96.85 156	99.85 191	98.98 148	99.25 198	99.60 204

SSM_04072		99.06 159	98.96 152	99.35 199	99.62 183	98.88 221	99.25 349	99.47 235	98.05 217	99.37 226	99.81 142	96.85 156	99.58 331	98.98 148	99.25 198	99.60 204

ET-MVSNet_ETH3D		96.49 403	95.64 418	99.05 246	99.53 229	98.82 238	98.84 444	97.51 501	97.63 279	84.77 518	99.21 402	92.09 378	98.91 462	98.98 148	92.21 471	99.41 273

PVSNet_BlendedMVS		98.86 192	98.80 186	99.03 248	99.76 83	98.79 241	99.28 333	99.91 3	97.42 308	99.67 131	99.37 365	97.53 123	99.88 169	98.98 148	97.29 364	98.42 440

PVSNet_Blended		99.08 154	98.97 148	99.42 186	99.76 83	98.79 241	98.78 452	99.91 3	96.74 366	99.67 131	99.49 324	97.53 123	99.88 169	98.98 148	99.85 94	99.60 204

viewdifsd2359ckpt09		99.01 173	98.87 175	99.40 189	99.62 183	98.79 241	99.44 256	99.51 162	97.76 263	99.35 235	99.69 236	96.42 187	99.75 272	98.97 153	99.11 224	99.66 177

GDP-MVS		99.08 154	98.89 171	99.64 102	99.53 229	99.34 129	99.64 98	99.48 213	98.32 151	99.77 90	99.66 256	95.14 258	99.93 109	98.97 153	99.50 177	99.64 191

3Dnovator	97.25 9	99.24 96	99.05 113	99.81 60	99.12 359	99.66 72	99.84 12	99.74 13	99.09 55	98.92 328	99.90 36	95.94 218	99.98 20	98.95 155	99.92 38	99.79 92

WBMVS		97.74 336	97.50 330	98.46 342	99.24 328	97.43 335	99.21 363	99.42 281	97.45 302	98.96 322	99.41 350	88.83 433	99.23 394	98.94 156	96.02 392	98.71 357

EIA-MVS		99.18 104	99.09 104	99.45 175	99.49 252	99.18 155	99.67 77	99.53 125	97.66 277	99.40 219	99.44 342	98.10 108	99.81 237	98.94 156	99.62 166	99.35 283

lupinMVS		99.13 129	99.01 137	99.46 173	99.51 238	98.94 203	99.05 401	99.16 389	97.86 245	99.80 78	99.56 296	97.39 126	99.86 183	98.94 156	99.85 94	99.58 219

DVP-MVS		99.57 20	99.47 24	99.88 16	99.85 31	99.89 6	99.57 146	99.37 313	99.10 48	99.81 72	99.80 160	98.94 33	99.96 41	98.93 159	99.86 87	99.81 79
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 6	99.84 38	99.89 6	99.57 146	99.51 162					99.96 41	98.93 159	99.86 87	99.88 36

UA-Net		99.42 55	99.29 65	99.80 64	99.62 183	99.55 98	99.50 206	99.70 18	98.79 96	99.77 90	99.96 1	97.45 125	99.96 41	98.92 161	99.90 56	99.89 30

SED-MVS		99.61 10	99.52 14	99.88 16	99.84 38	99.90 2	99.60 117	99.48 213	99.08 56	99.91 31	99.81 142	99.20 8	99.96 41	98.91 162	99.85 94	99.79 92

test_241102_TWO								99.48 213	99.08 56	99.88 42	99.81 142	98.94 33	99.96 41	98.91 162	99.84 102	99.88 36

MVS_111021_HR		99.41 59	99.32 53	99.66 92	99.72 112	99.47 115	98.95 427	99.85 8	98.82 90	99.54 183	99.73 214	98.51 86	99.74 275	98.91 162	99.88 73	99.77 100

MTAPA		99.52 28	99.39 39	99.89 12	99.90 4	99.86 18	99.66 84	99.47 235	98.79 96	99.68 125	99.81 142	98.43 91	99.97 29	98.88 165	99.90 56	99.83 64

XXY-MVS		98.38 243	98.09 260	99.24 226	99.26 322	99.32 133	99.56 154	99.55 100	97.45 302	98.71 359	99.83 116	93.23 344	99.63 326	98.88 165	96.32 386	98.76 347

ACMH	97.28 8	98.10 269	97.99 271	98.44 347	99.41 277	96.96 369	99.60 117	99.56 90	98.09 205	98.15 419	99.91 26	90.87 409	99.70 299	98.88 165	97.45 354	98.67 379
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MSC_two_6792asdad				99.87 22	99.51 238	99.76 50		99.33 335					99.96 41	98.87 168	99.84 102	99.89 30

No_MVS				99.87 22	99.51 238	99.76 50		99.33 335					99.96 41	98.87 168	99.84 102	99.89 30

MVS_Test		99.10 151	98.97 148	99.48 165	99.49 252	99.14 164	99.67 77	99.34 327	97.31 317	99.58 171	99.76 197	97.65 122	99.82 232	98.87 168	99.07 241	99.46 263

MVSTER		98.49 231	98.32 240	99.00 252	99.35 295	99.02 180	99.54 174	99.38 303	97.41 309	99.20 275	99.73 214	93.86 332	99.36 370	98.87 168	97.56 342	98.62 401

1112_ss		98.98 177	98.77 191	99.59 114	99.68 136	99.02 180	99.25 349	99.48 213	97.23 325	99.13 287	99.58 288	96.93 154	99.90 149	98.87 168	98.78 270	99.84 54

IU-MVS					99.84 38	99.88 10		99.32 346	98.30 155	99.84 56				98.86 173	99.85 94	99.89 30

3Dnovator+	97.12 13	99.18 104	98.97 148	99.82 57	99.17 351	99.68 65	99.81 20	99.51 162	99.20 34	98.72 358	99.89 45	95.68 234	99.97 29	98.86 173	99.86 87	99.81 79

DVP-MVS++		99.59 15	99.50 19	99.88 16	99.51 238	99.88 10	99.87 8	99.51 162	98.99 69	99.88 42	99.81 142	99.27 6	99.96 41	98.85 175	99.80 126	99.81 79

test_0728_THIRD									98.99 69	99.81 72	99.80 160	99.09 15	99.96 41	98.85 175	99.90 56	99.88 36

WTY-MVS		99.06 159	98.88 174	99.61 110	99.62 183	99.16 158	99.37 295	99.56 90	98.04 224	99.53 185	99.62 275	96.84 161	99.94 91	98.85 175	98.49 288	99.72 138

TSAR-MVS + MP.		99.58 16	99.50 19	99.81 60	99.91 1	99.66 72	99.63 104	99.39 294	98.91 83	99.78 86	99.85 92	99.36 2	99.94 91	98.84 178	99.88 73	99.82 72
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
Anonymous20231211		97.88 307	97.54 325	98.90 271	99.71 118	98.53 268	99.48 231	99.57 85	94.16 452	98.81 348	99.68 244	93.23 344	99.42 358	98.84 178	94.42 435	98.76 347

114514_t		98.93 182	98.67 203	99.72 86	99.85 31	99.53 103	99.62 109	99.59 73	92.65 474	99.71 118	99.78 184	98.06 111	99.90 149	98.84 178	99.91 45	99.74 118

MED-MVS test				99.87 22	99.88 13	99.81 34	99.69 63	99.87 6	99.34 28	99.90 34	99.83 116		99.95 76	98.83 181	99.89 67	99.83 64

MED-MVS		99.70 3	99.63 5	99.90 8	99.88 13	99.81 34	99.69 63	99.87 6	99.48 3	99.90 34	99.89 45	99.30 4	99.95 76	98.83 181	99.88 73	99.93 22

ME-MVS		99.56 21	99.46 28	99.86 34	99.80 64	99.81 34	99.37 295	99.70 18	99.18 35	99.83 66	99.83 116	98.74 66	99.93 109	98.83 181	99.89 67	99.83 64

tttt0517		98.42 237	98.14 252	99.28 220	99.66 151	98.38 286	99.74 48	96.85 508	97.68 274	99.79 81	99.74 208	91.39 398	99.89 164	98.83 181	99.56 171	99.57 222

MP-MVS-pluss		99.37 68	99.20 85	99.88 16	99.90 4	99.87 17	99.30 322	99.52 134	97.18 329	99.60 166	99.79 177	98.79 52	99.95 76	98.83 181	99.91 45	99.83 64
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
Test_1112_low_res		98.89 185	98.66 206	99.57 122	99.69 129	98.95 199	99.03 406	99.47 235	96.98 349	99.15 285	99.23 398	96.77 166	99.89 164	98.83 181	98.78 270	99.86 43

MVS_111021_LR		99.41 59	99.33 51	99.65 96	99.77 79	99.51 109	98.94 429	99.85 8	98.82 90	99.65 146	99.74 208	98.51 86	99.80 245	98.83 181	99.89 67	99.64 191

ACMMP_NAP		99.47 40	99.34 49	99.88 16	99.87 20	99.86 18	99.47 241	99.48 213	98.05 217	99.76 96	99.86 85	98.82 48	99.93 109	98.82 188	99.91 45	99.84 54

SMA-MVS		99.44 50	99.30 61	99.85 43	99.73 108	99.83 23	99.56 154	99.47 235	97.45 302	99.78 86	99.82 127	99.18 11	99.91 136	98.79 189	99.89 67	99.81 79
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 27	99.42 32	99.87 22	99.85 31	99.83 23	99.69 63	99.68 24	98.98 72	99.37 226	99.74 208	98.81 49	99.94 91	98.79 189	99.86 87	99.84 54

X-MVStestdata		96.55 401	95.45 421	99.87 22	99.85 31	99.83 23	99.69 63	99.68 24	98.98 72	99.37 226	64.01 550	98.81 49	99.94 91	98.79 189	99.86 87	99.84 54

CVMVSNet		98.57 229	98.67 203	98.30 361	99.35 295	95.59 427	99.50 206	99.55 100	98.60 116	99.39 221	99.83 116	94.48 304	99.45 346	98.75 192	98.56 283	99.85 47

CP-MVS		99.45 46	99.32 53	99.85 43	99.83 47	99.75 52	99.69 63	99.52 134	98.07 210	99.53 185	99.63 270	98.93 37	99.97 29	98.74 193	99.91 45	99.83 64

ACMM	97.58 5	98.37 245	98.34 238	98.48 336	99.41 277	97.10 350	99.56 154	99.45 259	98.53 122	99.04 308	99.85 92	93.00 349	99.71 291	98.74 193	97.45 354	98.64 392
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Effi-MVS+-dtu		98.78 210	98.89 171	98.47 341	99.33 301	96.91 375	99.57 146	99.30 355	98.47 129	99.41 214	98.99 430	96.78 165	99.74 275	98.73 195	99.38 184	98.74 353

ZNCC-MVS		99.47 40	99.33 51	99.87 22	99.87 20	99.81 34	99.64 98	99.67 27	98.08 209	99.55 182	99.64 264	98.91 38	99.96 41	98.72 196	99.90 56	99.82 72

SD-MVS		99.41 59	99.52 14	99.05 246	99.74 101	99.68 65	99.46 245	99.52 134	99.11 47	99.88 42	99.91 26	99.43 1	97.70 494	98.72 196	99.93 32	99.77 100
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		98.41 239	98.50 229	98.15 377	99.26 322	96.62 390	99.40 282	99.61 61	97.71 269	98.98 318	99.36 368	96.04 209	99.67 308	98.70 198	97.41 359	98.15 458

CDS-MVSNet		99.09 152	99.03 118	99.25 223	99.42 272	98.73 247	99.45 249	99.46 248	98.11 200	99.46 197	99.77 193	98.01 113	99.37 366	98.70 198	98.92 255	99.66 177
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		99.12 139	99.08 105	99.24 226	99.46 262	98.55 266	99.51 195	99.46 248	98.09 205	99.45 198	99.82 127	98.34 98	99.51 339	98.70 198	98.93 253	99.67 170

HFP-MVS		99.49 33	99.37 43	99.86 34	99.87 20	99.80 39	99.66 84	99.67 27	98.15 183	99.68 125	99.69 236	99.06 17	99.96 41	98.69 201	99.87 79	99.84 54

ACMMPR		99.49 33	99.36 45	99.86 34	99.87 20	99.79 42	99.66 84	99.67 27	98.15 183	99.67 131	99.69 236	98.95 31	99.96 41	98.69 201	99.87 79	99.84 54

UniMVSNet_ETH3D		97.32 379	96.81 388	98.87 284	99.40 282	97.46 334	99.51 195	99.53 125	95.86 425	98.54 387	99.77 193	82.44 488	99.66 311	98.68 203	97.52 346	99.50 248

DeepC-MVS_fast	98.69 1	99.49 33	99.39 39	99.77 74	99.63 173	99.59 90	99.36 301	99.46 248	99.07 58	99.79 81	99.82 127	98.85 43	99.92 124	98.68 203	99.87 79	99.82 72
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
anonymousdsp		98.44 235	98.28 243	98.94 261	98.50 458	98.96 193	99.77 35	99.50 187	97.07 341	98.87 337	99.77 193	94.76 282	99.28 383	98.66 205	97.60 338	98.57 422

DP-MVS		99.16 112	98.95 156	99.78 71	99.77 79	99.53 103	99.41 274	99.50 187	97.03 347	99.04 308	99.88 58	97.39 126	99.92 124	98.66 205	99.90 56	99.87 41

MonoMVSNet		98.38 243	98.47 231	98.12 379	98.59 453	96.19 407	99.72 54	98.79 449	97.89 242	99.44 203	99.52 314	96.13 203	98.90 464	98.64 207	97.54 344	99.28 291

MCST-MVS		99.43 53	99.30 61	99.82 57	99.79 69	99.74 55	99.29 327	99.40 291	98.79 96	99.52 187	99.62 275	98.91 38	99.90 149	98.64 207	99.75 143	99.82 72

CP-MVSNet		98.09 270	97.78 296	99.01 250	98.97 395	99.24 149	99.67 77	99.46 248	97.25 322	98.48 392	99.64 264	93.79 334	99.06 433	98.63 209	94.10 443	98.74 353

thisisatest0530		98.35 247	98.03 267	99.31 208	99.63 173	98.56 265	99.54 174	96.75 510	97.53 293	99.73 103	99.65 258	91.25 402	99.89 164	98.62 210	99.56 171	99.48 252

region2R		99.48 37	99.35 47	99.87 22	99.88 13	99.80 39	99.65 90	99.66 32	98.13 190	99.66 136	99.68 244	98.96 26	99.96 41	98.62 210	99.87 79	99.84 54

APD-MVS_3200maxsize		99.48 37	99.35 47	99.85 43	99.76 83	99.83 23	99.63 104	99.54 109	98.36 145	99.79 81	99.82 127	98.86 42	99.95 76	98.62 210	99.81 121	99.78 98

SR-MVS-dyc-post		99.45 46	99.31 59	99.85 43	99.76 83	99.82 29	99.63 104	99.52 134	98.38 141	99.76 96	99.82 127	98.53 84	99.95 76	98.61 213	99.81 121	99.77 100

RE-MVS-def			99.34 49		99.76 83	99.82 29	99.63 104	99.52 134	98.38 141	99.76 96	99.82 127	98.75 61		98.61 213	99.81 121	99.77 100

PHI-MVS		99.30 82	99.17 90	99.70 87	99.56 217	99.52 107	99.58 138	99.80 10	97.12 335	99.62 158	99.73 214	98.58 79	99.90 149	98.61 213	99.91 45	99.68 163

test_yl		98.86 192	98.63 211	99.54 127	99.49 252	99.18 155	99.50 206	99.07 402	98.22 172	99.61 163	99.51 318	95.37 245	99.84 201	98.60 216	98.33 295	99.59 215

DCV-MVSNet		98.86 192	98.63 211	99.54 127	99.49 252	99.18 155	99.50 206	99.07 402	98.22 172	99.61 163	99.51 318	95.37 245	99.84 201	98.60 216	98.33 295	99.59 215

CNVR-MVS		99.42 55	99.30 61	99.78 71	99.62 183	99.71 59	99.26 347	99.52 134	98.82 90	99.39 221	99.71 221	98.96 26	99.85 191	98.59 218	99.80 126	99.77 100

tt0805		97.97 296	97.77 298	98.57 323	99.59 205	96.61 391	99.45 249	99.08 399	98.21 174	98.88 334	99.80 160	88.66 437	99.70 299	98.58 219	97.72 332	99.39 277

WR-MVS		98.06 276	97.73 305	99.06 244	98.86 412	99.25 148	99.19 369	99.35 322	97.30 318	98.66 368	99.43 344	93.94 327	99.21 406	98.58 219	94.28 438	98.71 357

HPM-MVS		99.42 55	99.28 68	99.83 56	99.90 4	99.72 57	99.81 20	99.54 109	97.59 283	99.68 125	99.63 270	98.91 38	99.94 91	98.58 219	99.91 45	99.84 54
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
UniMVSNet_NR-MVSNet		98.22 255	97.97 273	98.96 257	98.92 400	98.98 185	99.48 231	99.53 125	97.76 263	98.71 359	99.46 339	96.43 186	99.22 401	98.57 222	92.87 465	98.69 366

DU-MVS		98.08 274	97.79 293	98.96 257	98.87 409	98.98 185	99.41 274	99.45 259	97.87 244	98.71 359	99.50 321	94.82 273	99.22 401	98.57 222	92.87 465	98.68 371

mPP-MVS		99.44 50	99.30 61	99.86 34	99.88 13	99.79 42	99.69 63	99.48 213	98.12 198	99.50 190	99.75 202	98.78 53	99.97 29	98.57 222	99.89 67	99.83 64

CANet_DTU		98.97 179	98.87 175	99.25 223	99.33 301	98.42 285	99.08 393	99.30 355	99.16 37	99.43 206	99.75 202	95.27 250	99.97 29	98.56 225	99.95 22	99.36 282

PMMVS		98.80 208	98.62 216	99.34 200	99.27 319	98.70 250	98.76 455	99.31 350	97.34 314	99.21 271	99.07 415	97.20 138	99.82 232	98.56 225	98.87 262	99.52 235

PVSNet	96.02 17	98.85 201	98.84 183	98.89 275	99.73 108	97.28 340	98.32 494	99.60 68	97.86 245	99.50 190	99.57 293	96.75 167	99.86 183	98.56 225	99.70 153	99.54 229

ACMMP		99.45 46	99.32 53	99.82 57	99.89 8	99.67 69	99.62 109	99.69 22	98.12 198	99.63 154	99.84 107	98.73 67	99.96 41	98.55 228	99.83 114	99.81 79
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		98.69 220	98.62 216	98.89 275	99.71 118	97.74 321	99.12 384	99.54 109	98.44 135	99.42 209	99.71 221	94.20 315	99.92 124	98.54 229	98.90 261	99.00 323

PS-CasMVS		97.93 299	97.59 321	98.95 259	98.99 390	99.06 175	99.68 73	99.52 134	97.13 333	98.31 407	99.68 244	92.44 373	99.05 434	98.51 230	94.08 444	98.75 349

CostFormer		97.72 340	97.73 305	97.71 420	99.15 357	94.02 468	99.54 174	99.02 410	94.67 447	99.04 308	99.35 371	92.35 375	99.77 265	98.50 231	97.94 321	99.34 286

baseline1		98.31 249	97.95 276	99.38 195	99.50 250	98.74 246	99.59 128	98.93 421	98.41 138	99.14 286	99.60 282	94.59 296	99.79 252	98.48 232	93.29 454	99.61 201

SteuartSystems-ACMMP		99.54 24	99.42 32	99.87 22	99.82 53	99.81 34	99.59 128	99.51 162	98.62 113	99.79 81	99.83 116	99.28 5	99.97 29	98.48 232	99.90 56	99.84 54
Skip Steuart: Steuart Systems R&D Blog.
tpmrst		98.33 248	98.48 230	97.90 398	99.16 353	94.78 452	99.31 320	99.11 395	97.27 320	99.45 198	99.59 284	95.33 248	99.84 201	98.48 232	98.61 277	99.09 310

0.4-1-1-0.1		95.23 434	94.22 443	98.26 368	97.39 486	95.86 419	97.59 515	97.62 496	93.85 455	94.97 480	97.03 504	87.20 454	99.87 176	98.47 235	83.84 505	99.05 318

IB-MVS	95.67 18	96.22 407	95.44 422	98.57 323	99.21 335	96.70 384	98.65 467	97.74 495	96.71 368	97.27 448	98.54 458	86.03 465	99.92 124	98.47 235	86.30 500	99.10 306
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 55	99.27 72	99.88 16	99.89 8	99.80 39	99.67 77	99.50 187	98.70 107	99.77 90	99.49 324	98.21 103	99.95 76	98.46 237	99.77 138	99.88 36
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		97.50 365	97.10 379	98.71 309	99.20 337	96.91 375	99.29 327	98.82 443	97.89 242	98.21 415	98.40 463	85.63 468	99.83 223	98.45 238	98.04 318	99.37 281

myMVS_eth3d28		97.69 345	97.34 358	98.73 304	99.27 319	97.52 332	99.33 313	98.78 450	98.03 226	98.82 347	98.49 459	86.64 459	99.46 344	98.44 239	98.24 305	99.23 298

SR-MVS		99.43 53	99.29 65	99.86 34	99.75 93	99.83 23	99.59 128	99.62 52	98.21 174	99.73 103	99.79 177	98.68 71	99.96 41	98.44 239	99.77 138	99.79 92

HPM-MVS++		99.39 66	99.23 81	99.87 22	99.75 93	99.84 20	99.43 262	99.51 162	98.68 110	99.27 256	99.53 309	98.64 76	99.96 41	98.44 239	99.80 126	99.79 92

0.3-1-1-0.015		94.79 442	93.69 455	98.10 380	96.99 498	95.46 433	97.02 520	97.61 498	93.53 459	94.03 488	96.54 509	85.60 469	99.86 183	98.43 242	83.45 510	98.99 326

0.4-1-1-0.2		94.94 441	93.92 449	97.99 389	96.84 499	95.13 445	96.64 522	97.62 496	93.45 463	94.92 481	96.56 508	87.14 456	99.86 183	98.43 242	83.69 509	98.98 327

KinetiMVS		99.12 139	98.92 161	99.70 87	99.67 139	99.40 123	99.67 77	99.63 46	98.73 103	99.94 28	99.81 142	94.54 301	99.96 41	98.40 244	99.93 32	99.74 118

LTVRE_ROB	97.16 12	98.02 286	97.90 281	98.40 352	99.23 330	96.80 382	99.70 59	99.60 68	97.12 335	98.18 417	99.70 225	91.73 387	99.72 285	98.39 245	97.45 354	98.68 371
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 64	99.24 77	99.85 43	99.86 25	99.79 42	99.60 117	99.67 27	97.97 235	99.63 154	99.68 244	98.52 85	99.95 76	98.38 246	99.86 87	99.81 79

EI-MVSNet		98.67 222	98.67 203	98.68 313	99.35 295	97.97 307	99.50 206	99.38 303	96.93 356	99.20 275	99.83 116	97.87 115	99.36 370	98.38 246	97.56 342	98.71 357

HY-MVS	97.30 7	98.85 201	98.64 210	99.47 171	99.42 272	99.08 172	99.62 109	99.36 315	97.39 311	99.28 250	99.68 244	96.44 185	99.92 124	98.37 248	98.22 306	99.40 276

TDRefinement		95.42 428	94.57 438	97.97 391	89.83 545	96.11 409	99.48 231	98.75 452	96.74 366	96.68 462	99.88 58	88.65 438	99.71 291	98.37 248	82.74 513	98.09 461

ttmdpeth		97.80 326	97.63 317	98.29 362	98.77 427	97.38 337	99.64 98	99.36 315	98.78 99	96.30 466	99.58 288	92.34 376	99.39 361	98.36 250	95.58 408	98.10 460

UniMVSNet (Re)		98.29 252	98.00 270	99.13 240	99.00 387	99.36 128	99.49 223	99.51 162	97.95 236	98.97 320	99.13 409	96.30 194	99.38 363	98.36 250	93.34 453	98.66 388

WR-MVS_H		98.13 266	97.87 286	98.90 271	99.02 384	98.84 232	99.70 59	99.59 73	97.27 320	98.40 398	99.19 403	95.53 239	99.23 394	98.34 252	93.78 449	98.61 410

PGM-MVS		99.45 46	99.31 59	99.86 34	99.87 20	99.78 48	99.58 138	99.65 39	97.84 251	99.71 118	99.80 160	99.12 14	99.97 29	98.33 253	99.87 79	99.83 64

LS3D		99.27 88	99.12 96	99.74 80	99.18 343	99.75 52	99.56 154	99.57 85	98.45 132	99.49 193	99.85 92	97.77 119	99.94 91	98.33 253	99.84 102	99.52 235

IterMVS-LS		98.46 234	98.42 233	98.58 322	99.59 205	98.00 305	99.37 295	99.43 279	96.94 355	99.07 300	99.59 284	97.87 115	99.03 437	98.32 255	95.62 407	98.71 357
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CLD-MVS		98.16 263	98.10 257	98.33 357	99.29 314	96.82 380	98.75 456	99.44 268	97.83 252	99.13 287	99.55 299	92.92 351	99.67 308	98.32 255	97.69 333	98.48 432
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									98.18 181	99.84 56	99.70 225	99.31 3	98.52 476	98.30 257	99.80 126	99.81 79

sc_t1		95.75 419	95.05 427	97.87 400	98.83 416	94.61 459	99.21 363	99.45 259	87.45 502	97.97 428	99.85 92	81.19 493	99.43 355	98.27 258	93.20 457	99.57 222

UBG		97.85 312	97.48 332	98.95 259	99.25 326	97.64 328	99.24 354	98.74 456	97.90 241	98.64 375	98.20 472	88.65 438	99.81 237	98.27 258	98.40 290	99.42 270

NCCC		99.34 75	99.19 87	99.79 68	99.61 194	99.65 76	99.30 322	99.48 213	98.86 85	99.21 271	99.63 270	98.72 68	99.90 149	98.25 260	99.63 165	99.80 88

OPU-MVS				99.64 102	99.56 217	99.72 57	99.60 117				99.70 225	99.27 6	99.42 358	98.24 261	99.80 126	99.79 92

GeoE		98.85 201	98.62 216	99.53 135	99.61 194	99.08 172	99.80 25	99.51 162	97.10 339	99.31 242	99.78 184	95.23 255	99.77 265	98.21 262	99.03 246	99.75 113

cl22		97.85 312	97.64 316	98.48 336	99.09 367	97.87 316	98.60 473	99.33 335	97.11 338	98.87 337	99.22 399	92.38 374	99.17 412	98.21 262	95.99 395	98.42 440

SF-MVS		99.38 67	99.24 77	99.79 68	99.79 69	99.68 65	99.57 146	99.54 109	97.82 257	99.71 118	99.80 160	98.95 31	99.93 109	98.19 264	99.84 102	99.74 118

旧先验2							98.96 424		96.70 369	99.47 195			99.94 91	98.19 264

F-COLMAP		99.19 101	99.04 115	99.64 102	99.78 71	99.27 145	99.42 269	99.54 109	97.29 319	99.41 214	99.59 284	98.42 93	99.93 109	98.19 264	99.69 154	99.73 128

LCM-MVSNet-Re		97.83 319	98.15 251	96.87 452	99.30 310	92.25 485	99.59 128	98.26 482	97.43 306	96.20 467	99.13 409	96.27 195	98.73 472	98.17 267	98.99 250	99.64 191

DPE-MVS		99.46 42	99.32 53	99.91 6	99.78 71	99.88 10	99.36 301	99.51 162	98.73 103	99.88 42	99.84 107	98.72 68	99.96 41	98.16 268	99.87 79	99.88 36
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
cascas		97.69 345	97.43 347	98.48 336	98.60 451	97.30 339	98.18 500	99.39 294	92.96 470	98.41 397	98.78 450	93.77 335	99.27 386	98.16 268	98.61 277	98.86 335

icg_test_0407_2		98.79 209	98.86 178	98.57 323	99.55 221	96.93 370	99.07 394	99.44 268	98.05 217	99.66 136	99.80 160	97.13 140	99.18 410	98.15 270	98.92 255	99.60 204

IMVS_0407		98.86 192	98.91 165	98.72 306	99.55 221	96.93 370	99.50 206	99.44 268	98.05 217	99.66 136	99.80 160	97.13 140	99.65 316	98.15 270	98.92 255	99.60 204

IMVS_0404		98.53 230	98.52 228	98.55 329	99.55 221	96.93 370	99.20 366	99.44 268	98.05 217	98.96 322	99.80 160	94.66 293	99.13 418	98.15 270	98.92 255	99.60 204

IMVS_0403		98.86 192	98.89 171	98.78 301	99.55 221	96.93 370	99.58 138	99.44 268	98.05 217	99.68 125	99.80 160	96.81 163	99.80 245	98.15 270	98.92 255	99.60 204

COLMAP_ROB	97.56 6	98.86 192	98.75 193	99.17 233	99.88 13	98.53 268	99.34 311	99.59 73	97.55 289	98.70 365	99.89 45	95.83 224	99.90 149	98.10 274	99.90 56	99.08 311
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PEN-MVS		97.76 330	97.44 343	98.72 306	98.77 427	98.54 267	99.78 33	99.51 162	97.06 343	98.29 410	99.64 264	92.63 364	98.89 465	98.09 275	93.16 458	98.72 355

LPG-MVS_test		98.22 255	98.13 254	98.49 334	99.33 301	97.05 356	99.58 138	99.55 100	97.46 299	99.24 263	99.83 116	92.58 365	99.72 285	98.09 275	97.51 347	98.68 371

LGP-MVS_train				98.49 334	99.33 301	97.05 356		99.55 100	97.46 299	99.24 263	99.83 116	92.58 365	99.72 285	98.09 275	97.51 347	98.68 371

IS-MVSNet		99.05 163	98.87 175	99.57 122	99.73 108	99.32 133	99.75 43	99.20 384	98.02 229	99.56 176	99.86 85	96.54 179	99.67 308	98.09 275	99.13 217	99.73 128

thisisatest0515		98.14 265	97.79 293	99.19 231	99.50 250	98.50 276	98.61 470	96.82 509	96.95 353	99.54 183	99.43 344	91.66 391	99.86 183	98.08 279	99.51 175	99.22 299

OPM-MVS		98.19 259	98.10 257	98.45 344	98.88 406	97.07 354	99.28 333	99.38 303	98.57 118	99.22 268	99.81 142	92.12 377	99.66 311	98.08 279	97.54 344	98.61 410
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
XVG-OURS		98.73 218	98.68 202	98.88 280	99.70 123	97.73 322	98.92 431	99.55 100	98.52 123	99.45 198	99.84 107	95.27 250	99.91 136	98.08 279	98.84 265	99.00 323

Baseline_NR-MVSNet		97.76 330	97.45 338	98.68 313	99.09 367	98.29 288	99.41 274	98.85 440	95.65 427	98.63 377	99.67 251	94.82 273	99.10 427	98.07 282	92.89 464	98.64 392

ACMH+	97.24 10	97.92 302	97.78 296	98.32 359	99.46 262	96.68 388	99.56 154	99.54 109	98.41 138	97.79 437	99.87 74	90.18 420	99.66 311	98.05 283	97.18 369	98.62 401

testing99		97.36 375	96.94 385	98.63 316	99.18 343	96.70 384	99.30 322	98.93 421	97.71 269	98.23 412	98.26 470	84.92 474	99.84 201	98.04 284	97.85 328	99.35 283

testing91		97.44 372	97.02 382	98.71 309	99.18 343	96.89 377	99.19 369	99.04 406	97.78 260	98.31 407	98.29 468	85.41 471	99.85 191	98.01 285	97.95 320	99.39 277

TranMVSNet+NR-MVSNet		97.93 299	97.66 312	98.76 303	98.78 422	98.62 259	99.65 90	99.49 201	97.76 263	98.49 391	99.60 282	94.23 314	98.97 456	98.00 286	92.90 463	98.70 362

DP-MVS Recon		99.12 139	98.95 156	99.65 96	99.74 101	99.70 61	99.27 338	99.57 85	96.40 397	99.42 209	99.68 244	98.75 61	99.80 245	97.98 287	99.72 149	99.44 268

test_prior2							98.96 424		98.34 147	99.01 311	99.52 314	98.68 71		97.96 288	99.74 146

Fast-Effi-MVS+-dtu		98.77 214	98.83 185	98.60 318	99.41 277	96.99 365	99.52 185	99.49 201	98.11 200	99.24 263	99.34 375	96.96 153	99.79 252	97.95 289	99.45 180	99.02 322

MP-MVS		99.33 77	99.15 92	99.87 22	99.88 13	99.82 29	99.66 84	99.46 248	98.09 205	99.48 194	99.74 208	98.29 100	99.96 41	97.93 290	99.87 79	99.82 72
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
Vis-MVSNet (Re-imp)		98.87 189	98.72 197	99.31 208	99.71 118	98.88 221	99.80 25	99.44 268	97.91 240	99.36 232	99.78 184	95.49 241	99.43 355	97.91 291	99.11 224	99.62 199

ACMP	97.20 11	98.06 276	97.94 278	98.45 344	99.37 291	97.01 363	99.44 256	99.49 201	97.54 292	98.45 395	99.79 177	91.95 381	99.72 285	97.91 291	97.49 352	98.62 401
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_fmvs2		97.25 382	97.30 365	97.09 444	99.43 270	93.31 478	99.73 52	98.87 437	98.83 89	99.28 250	99.80 160	84.45 477	99.66 311	97.88 293	97.45 354	98.30 448

Fast-Effi-MVS+		98.70 219	98.43 232	99.51 147	99.51 238	99.28 143	99.52 185	99.47 235	96.11 417	99.01 311	99.34 375	96.20 200	99.84 201	97.88 293	98.82 267	99.39 277

EPMVS		97.82 322	97.65 313	98.35 356	98.88 406	95.98 410	99.49 223	94.71 526	97.57 286	99.26 261	99.48 332	92.46 372	99.71 291	97.87 295	99.08 240	99.35 283

ETVMVS		97.50 365	96.90 386	99.29 216	99.23 330	98.78 244	99.32 316	98.90 431	97.52 295	98.56 385	98.09 479	84.72 476	99.69 305	97.86 296	97.88 325	99.39 277

miper_enhance_ethall		98.16 263	98.08 261	98.41 350	98.96 396	97.72 323	98.45 487	99.32 346	96.95 353	98.97 320	99.17 404	97.06 147	99.22 401	97.86 296	95.99 395	98.29 449

tmp_tt		82.80 490	81.52 494	86.66 508	66.61 555	68.44 539	92.79 537	97.92 490	68.96 525	80.04 531	99.85 92	85.77 466	96.15 511	97.86 296	43.89 543	95.39 516

NR-MVSNet		97.97 296	97.61 319	99.02 249	98.87 409	99.26 146	99.47 241	99.42 281	97.63 279	97.08 455	99.50 321	95.07 260	99.13 418	97.86 296	93.59 450	98.68 371

v148		97.79 328	97.55 322	98.50 333	98.74 430	97.72 323	99.54 174	99.33 335	96.26 404	98.90 331	99.51 318	94.68 290	99.14 415	97.83 300	93.15 459	98.63 399

CPTT-MVS		99.11 145	98.90 167	99.74 80	99.80 64	99.46 116	99.59 128	99.49 201	97.03 347	99.63 154	99.69 236	97.27 134	99.96 41	97.82 301	99.84 102	99.81 79

MDTV_nov1_ep13_2view						95.18 443	99.35 306		96.84 360	99.58 171		95.19 256		97.82 301		99.46 263

Elysia		98.88 186	98.65 208	99.58 118	99.58 207	99.34 129	99.65 90	99.52 134	98.26 161	99.83 66	99.87 74	93.37 341	99.90 149	97.81 303	99.91 45	99.49 249

StellarMVS		98.88 186	98.65 208	99.58 118	99.58 207	99.34 129	99.65 90	99.52 134	98.26 161	99.83 66	99.87 74	93.37 341	99.90 149	97.81 303	99.91 45	99.49 249

OMC-MVS		99.08 154	99.04 115	99.20 230	99.67 139	98.22 292	99.28 333	99.52 134	98.07 210	99.66 136	99.81 142	97.79 118	99.78 260	97.79 305	99.81 121	99.60 204

FA-MVS(test-final)		98.75 215	98.53 227	99.41 187	99.55 221	99.05 177	99.80 25	99.01 412	96.59 383	99.58 171	99.59 284	95.39 244	99.90 149	97.78 306	99.49 178	99.28 291

HQP_MVS		98.27 254	98.22 247	98.44 347	99.29 314	96.97 367	99.39 286	99.47 235	98.97 76	99.11 291	99.61 279	92.71 360	99.69 305	97.78 306	97.63 335	98.67 379

plane_prior5								99.47 235					99.69 305	97.78 306	97.63 335	98.67 379

dmvs_re		98.08 274	98.16 249	97.85 404	99.55 221	94.67 457	99.70 59	98.92 424	98.15 183	99.06 305	99.35 371	93.67 338	99.25 391	97.77 309	97.25 365	99.64 191

testdata				99.54 127	99.75 93	98.95 199		99.51 162	97.07 341	99.43 206	99.70 225	98.87 41	99.94 91	97.76 310	99.64 163	99.72 138

PLC	97.94 4	99.02 168	98.85 181	99.53 135	99.66 151	99.01 182	99.24 354	99.52 134	96.85 359	99.27 256	99.48 332	98.25 102	99.91 136	97.76 310	99.62 166	99.65 184
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		97.67 351	97.55 322	98.03 383	99.02 384	95.01 447	99.43 262	98.54 475	96.44 393	99.12 289	99.34 375	91.83 384	99.60 329	97.75 312	96.46 382	99.48 252

1314		98.68 221	98.54 226	99.11 241	98.89 404	98.65 254	99.27 338	99.49 201	96.89 357	97.99 426	99.56 296	97.72 121	99.83 223	97.74 313	99.27 195	98.84 337

XVG-ACMP-BASELINE		97.83 319	97.71 307	98.20 371	99.11 361	96.33 400	99.41 274	99.52 134	98.06 214	99.05 307	99.50 321	89.64 426	99.73 281	97.73 314	97.38 361	98.53 426

CNLPA		99.14 125	98.99 143	99.59 114	99.58 207	99.41 122	99.16 373	99.44 268	98.45 132	99.19 278	99.49 324	98.08 110	99.89 164	97.73 314	99.75 143	99.48 252

v2v482		98.06 276	97.77 298	98.92 265	98.90 403	98.82 238	99.57 146	99.36 315	96.65 373	99.19 278	99.35 371	94.20 315	99.25 391	97.72 316	94.97 422	98.69 366

gbinet_0.2-2-1-0.02		95.40 429	94.58 437	97.85 404	96.11 508	95.97 411	98.56 478	99.26 370	92.12 482	98.47 393	97.49 496	90.23 417	99.00 446	97.71 317	81.25 517	98.58 420

AUN-MVS		96.88 394	96.31 400	98.59 319	99.48 259	97.04 359	99.27 338	99.22 379	97.44 305	98.51 389	99.41 350	91.97 380	99.66 311	97.71 317	83.83 506	99.07 316

baseline2		97.87 309	97.55 322	98.82 293	99.18 343	98.02 304	99.41 274	96.58 514	96.97 350	96.51 463	99.17 404	93.43 339	99.57 332	97.71 317	99.03 246	98.86 335

原ACMM1				99.65 96	99.73 108	99.33 132		99.47 235	97.46 299	99.12 289	99.66 256	98.67 73	99.91 136	97.70 320	99.69 154	99.71 150

PVSNet_0	94.43 19	96.09 413	95.47 420	97.94 394	99.31 309	94.34 466	97.81 511	99.70 18	97.12 335	97.46 442	98.75 451	89.71 424	99.79 252	97.69 321	81.69 516	99.68 163

MAR-MVS		98.86 192	98.63 211	99.54 127	99.37 291	99.66 72	99.45 249	99.54 109	96.61 378	99.01 311	99.40 355	97.09 144	99.86 183	97.68 322	99.53 174	99.10 306
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
9.14			99.10 99		99.72 112		99.40 282	99.51 162	97.53 293	99.64 151	99.78 184	98.84 45	99.91 136	97.63 323	99.82 118

train_agg		99.02 168	98.77 191	99.77 74	99.67 139	99.65 76	99.05 401	99.41 284	96.28 401	98.95 324	99.49 324	98.76 58	99.91 136	97.63 323	99.72 149	99.75 113

miper_ehance_all_eth		98.18 261	98.10 257	98.41 350	99.23 330	97.72 323	98.72 460	99.31 350	96.60 381	98.88 334	99.29 388	97.29 133	99.13 418	97.60 325	95.99 395	98.38 445

MDTV_nov1_ep13			98.32 240		99.11 361	94.44 462	99.27 338	98.74 456	97.51 296	99.40 219	99.62 275	94.78 278	99.76 269	97.59 326	98.81 269

c3_l		98.12 268	98.04 266	98.38 354	99.30 310	97.69 327	98.81 448	99.33 335	96.67 371	98.83 345	99.34 375	97.11 143	98.99 448	97.58 327	95.34 414	98.48 432

test_post1							99.23 357				65.14 549	94.18 318	99.71 291	97.58 327

SCA		98.19 259	98.16 249	98.27 367	99.30 310	95.55 428	99.07 394	98.97 417	97.57 286	99.43 206	99.57 293	92.72 358	99.74 275	97.58 327	99.20 204	99.52 235

JIA-IIPM		97.50 365	97.02 382	98.93 263	98.73 431	97.80 320	99.30 322	98.97 417	91.73 484	98.91 329	94.86 516	95.10 259	99.71 291	97.58 327	97.98 319	99.28 291

V42		98.06 276	97.79 293	98.86 287	98.98 393	98.84 232	99.69 63	99.34 327	96.53 385	99.30 246	99.37 365	94.67 291	99.32 378	97.57 331	94.66 429	98.42 440

gm-plane-assit					98.54 456	92.96 480			94.65 448		99.15 407		99.64 320	97.56 332

APD-MVS		99.27 88	99.08 105	99.84 55	99.75 93	99.79 42	99.50 206	99.50 187	97.16 331	99.77 90	99.82 127	98.78 53	99.94 91	97.56 332	99.86 87	99.80 88
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
pm-mvs1		97.68 348	97.28 368	98.88 280	99.06 376	98.62 259	99.50 206	99.45 259	96.32 399	97.87 433	99.79 177	92.47 369	99.35 373	97.54 334	93.54 451	98.67 379

usedtu_blend_shiyan5		95.04 436	94.10 444	97.86 403	96.45 503	95.92 414	99.29 327	99.22 379	86.17 508	98.36 401	97.68 490	91.20 403	99.07 430	97.53 335	80.97 520	98.60 413

blend_shiyan4		95.25 433	94.39 441	97.84 407	96.70 500	95.92 414	98.84 444	99.28 361	92.21 475	98.16 418	97.84 487	87.10 457	99.07 430	97.53 335	81.87 515	98.54 424

无先验							98.99 417	99.51 162	96.89 357				99.93 109	97.53 335		99.72 138

pmmvs5		97.52 362	97.30 365	98.16 374	98.57 454	96.73 383	99.27 338	98.90 431	96.14 415	98.37 400	99.53 309	91.54 394	99.14 415	97.51 338	95.87 399	98.63 399

mvsany_test3		93.77 454	93.45 457	94.74 472	95.78 512	88.01 500	99.64 98	98.25 483	98.28 156	94.31 484	97.97 481	68.89 516	98.51 477	97.50 339	90.37 483	97.71 483

test9_res														97.49 340	99.72 149	99.75 113

CDPH-MVS		99.13 129	98.91 165	99.80 64	99.75 93	99.71 59	99.15 377	99.41 284	96.60 381	99.60 166	99.55 299	98.83 47	99.90 149	97.48 341	99.83 114	99.78 98

AdaColmap		99.01 173	98.80 186	99.66 92	99.56 217	99.54 100	99.18 371	99.70 18	98.18 181	99.35 235	99.63 270	96.32 190	99.90 149	97.48 341	99.77 138	99.55 227

OpenMVS	96.50 16	98.47 233	98.12 255	99.52 142	99.04 382	99.53 103	99.82 16	99.72 14	94.56 449	98.08 421	99.88 58	94.73 286	99.98 20	97.47 343	99.76 141	99.06 317

IterMVS		97.83 319	97.77 298	98.02 385	99.58 207	96.27 403	99.02 409	99.48 213	97.22 326	98.71 359	99.70 225	92.75 355	99.13 418	97.46 344	96.00 394	98.67 379
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
RPSCF		98.22 255	98.62 216	96.99 446	99.82 53	91.58 488	99.72 54	99.44 268	96.61 378	99.66 136	99.89 45	95.92 219	99.82 232	97.46 344	99.10 233	99.57 222

usedtu_dtu_shiyan1		98.09 270	97.82 290	98.89 275	98.70 437	98.90 215	98.57 474	99.47 235	96.78 363	98.87 337	99.05 419	94.75 283	99.23 394	97.45 346	96.74 374	98.53 426

FE-MVSNET3		98.09 270	97.82 290	98.89 275	98.70 437	98.90 215	98.57 474	99.47 235	96.78 363	98.87 337	99.05 419	94.75 283	99.23 394	97.45 346	96.74 374	98.53 426

IterMVS-SCA-FT		97.82 322	97.75 303	98.06 382	99.57 213	96.36 399	99.02 409	99.49 201	97.18 329	98.71 359	99.72 218	92.72 358	99.14 415	97.44 348	95.86 400	98.67 379

PatchmatchNet		98.31 249	98.36 236	98.19 372	99.16 353	95.32 439	99.27 338	98.92 424	97.37 312	99.37 226	99.58 288	94.90 269	99.70 299	97.43 349	99.21 202	99.54 229
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EU-MVSNet		97.98 293	98.03 267	97.81 413	98.72 433	96.65 389	99.66 84	99.66 32	98.09 205	98.35 404	99.82 127	95.25 253	98.01 486	97.41 350	95.30 415	98.78 341

eth_miper_zixun_eth		98.05 281	97.96 274	98.33 357	99.26 322	97.38 337	98.56 478	99.31 350	96.65 373	98.88 334	99.52 314	96.58 176	99.12 423	97.39 351	95.53 411	98.47 434

UWE-MVS		97.58 358	97.29 367	98.48 336	99.09 367	96.25 404	99.01 414	96.61 513	97.86 245	99.19 278	99.01 426	88.72 434	99.90 149	97.38 352	98.69 274	99.28 291

testing222		97.16 385	96.50 395	99.16 234	99.16 353	98.47 281	99.27 338	98.66 469	97.71 269	98.23 412	98.15 474	82.28 490	99.84 201	97.36 353	97.66 334	99.18 301

FE-MVS		98.48 232	98.17 248	99.40 189	99.54 228	98.96 193	99.68 73	98.81 445	95.54 428	99.62 158	99.70 225	93.82 333	99.93 109	97.35 354	99.46 179	99.32 288

wanda-best-256-512		95.43 426	94.66 433	97.77 415	96.45 503	95.68 423	98.48 484	99.28 361	92.18 478	98.36 401	97.68 490	91.20 403	99.03 437	97.31 355	80.97 520	98.60 413

FE-blended-shiyan7		95.43 426	94.66 433	97.77 415	96.45 503	95.68 423	98.48 484	99.28 361	92.18 478	98.36 401	97.68 490	91.20 403	99.03 437	97.31 355	80.97 520	98.60 413

tpm2		97.44 372	97.34 358	97.74 419	99.15 357	94.36 465	99.45 249	98.94 420	93.45 463	98.90 331	99.44 342	91.35 399	99.59 330	97.31 355	98.07 317	99.29 290

blended_shiyan6		95.54 423	94.78 431	97.84 407	96.60 501	95.89 417	98.85 440	99.28 361	92.17 480	98.43 396	97.95 482	91.44 395	99.02 441	97.30 358	80.97 520	98.60 413

TESTMET0.1,1		97.55 359	97.27 371	98.40 352	98.93 398	96.53 393	98.67 463	97.61 498	96.96 351	98.64 375	99.28 390	88.63 440	99.45 346	97.30 358	99.38 184	99.21 300

miper_lstm_enhance		98.00 291	97.91 280	98.28 366	99.34 300	97.43 335	98.88 436	99.36 315	96.48 390	98.80 350	99.55 299	95.98 213	98.91 462	97.27 360	95.50 412	98.51 430

blended_shiyan8		95.56 422	94.79 430	97.87 400	96.60 501	95.90 416	98.85 440	99.27 368	92.19 476	98.47 393	97.94 485	91.43 396	99.11 424	97.26 361	81.09 519	98.60 413

test-LLR		98.06 276	97.90 281	98.55 329	98.79 419	97.10 350	98.67 463	97.75 493	97.34 314	98.61 381	98.85 443	94.45 306	99.45 346	97.25 362	99.38 184	99.10 306

test-mter		97.49 370	97.13 378	98.55 329	98.79 419	97.10 350	98.67 463	97.75 493	96.65 373	98.61 381	98.85 443	88.23 444	99.45 346	97.25 362	99.38 184	99.10 306

cl____		98.01 289	97.84 289	98.55 329	99.25 326	97.97 307	98.71 461	99.34 327	96.47 392	98.59 384	99.54 304	95.65 235	99.21 406	97.21 364	95.77 401	98.46 437

DIV-MVS_self_test		98.01 289	97.85 288	98.48 336	99.24 328	97.95 312	98.71 461	99.35 322	96.50 386	98.60 383	99.54 304	95.72 233	99.03 437	97.21 364	95.77 401	98.46 437

agg_prior2														97.21 364	99.73 148	99.75 113

OurMVSNet-221017-0		97.88 307	97.77 298	98.19 372	98.71 436	96.53 393	99.88 4	99.00 413	97.79 258	98.78 353	99.94 6	91.68 388	99.35 373	97.21 364	96.99 373	98.69 366

BP-MVS														97.19 368

HQP-MVS		98.02 286	97.90 281	98.37 355	99.19 340	96.83 378	98.98 420	99.39 294	98.24 168	98.66 368	99.40 355	92.47 369	99.64 320	97.19 368	97.58 340	98.64 392

pmmvs4		98.13 266	97.90 281	98.81 296	98.61 449	98.87 225	98.99 417	99.21 383	96.44 393	99.06 305	99.58 288	95.90 221	99.11 424	97.18 370	96.11 391	98.46 437

PatchMatch-RL		98.84 204	98.62 216	99.52 142	99.71 118	99.28 143	99.06 398	99.77 12	97.74 267	99.50 190	99.53 309	95.41 243	99.84 201	97.17 371	99.64 163	99.44 268

GBi-Net		97.68 348	97.48 332	98.29 362	99.51 238	97.26 343	99.43 262	99.48 213	96.49 387	99.07 300	99.32 383	90.26 414	98.98 449	97.10 372	96.65 377	98.62 401

test1		97.68 348	97.48 332	98.29 362	99.51 238	97.26 343	99.43 262	99.48 213	96.49 387	99.07 300	99.32 383	90.26 414	98.98 449	97.10 372	96.65 377	98.62 401

FMVSNet3		98.03 284	97.76 302	98.84 291	99.39 285	98.98 185	99.40 282	99.38 303	96.67 371	99.07 300	99.28 390	92.93 350	98.98 449	97.10 372	96.65 377	98.56 423

tt0320-xc		95.31 432	94.59 436	97.45 432	98.92 400	94.73 453	99.20 366	99.31 350	86.74 504	97.23 449	99.72 218	81.14 494	98.95 459	97.08 375	91.98 472	98.67 379

BH-untuned		98.42 237	98.36 236	98.59 319	99.49 252	96.70 384	99.27 338	99.13 393	97.24 324	98.80 350	99.38 362	95.75 231	99.74 275	97.07 376	99.16 207	99.33 287

dtuonlycased		97.04 390	97.33 361	96.16 462	99.08 370	90.59 493	98.79 451	99.38 303	97.19 328	96.91 460	99.49 324	90.22 419	98.75 470	97.04 377	97.89 324	99.14 302

LF4IMVS		97.52 362	97.46 337	97.70 421	98.98 393	95.55 428	99.29 327	98.82 443	98.07 210	98.66 368	99.64 264	89.97 421	99.61 328	97.01 378	96.68 376	97.94 476

SixPastTwentyTwo		97.50 365	97.33 361	98.03 383	98.65 444	96.23 405	99.77 35	98.68 465	97.14 332	97.90 431	99.93 10	90.45 412	99.18 410	97.00 379	96.43 383	98.67 379

MG-MVS		99.13 129	99.02 129	99.45 175	99.57 213	98.63 257	99.07 394	99.34 327	98.99 69	99.61 163	99.82 127	97.98 114	99.87 176	97.00 379	99.80 126	99.85 47

API-MVS		99.04 164	99.03 118	99.06 244	99.40 282	99.31 137	99.55 169	99.56 90	98.54 121	99.33 240	99.39 359	98.76 58	99.78 260	96.98 381	99.78 135	98.07 463

tpmvs		97.98 293	98.02 269	97.84 407	99.04 382	94.73 453	99.31 320	99.20 384	96.10 421	98.76 355	99.42 346	94.94 264	99.81 237	96.97 382	98.45 289	98.97 329

QAPM		98.67 222	98.30 242	99.80 64	99.20 337	99.67 69	99.77 35	99.72 14	94.74 446	98.73 357	99.90 36	95.78 229	99.98 20	96.96 383	99.88 73	99.76 107

PAPM_NR		99.04 164	98.84 183	99.66 92	99.74 101	99.44 118	99.39 286	99.38 303	97.70 272	99.28 250	99.28 390	98.34 98	99.85 191	96.96 383	99.45 180	99.69 157

v8		97.95 298	97.63 317	98.93 263	98.95 397	98.81 240	99.80 25	99.41 284	96.03 422	99.10 294	99.42 346	94.92 267	99.30 381	96.94 385	94.08 444	98.66 388

ZD-MVS					99.71 118	99.79 42		99.61 61	96.84 360	99.56 176	99.54 304	98.58 79	99.96 41	96.93 386	99.75 143

MSDG		98.98 177	98.80 186	99.53 135	99.76 83	99.19 153	98.75 456	99.55 100	97.25 322	99.47 195	99.77 193	97.82 117	99.87 176	96.93 386	99.90 56	99.54 229

pmmvs6		96.53 402	96.09 407	97.82 412	98.69 440	95.47 432	99.37 295	99.47 235	93.46 462	97.41 443	99.78 184	87.06 458	99.33 376	96.92 388	92.70 467	98.65 390

新几何1				99.75 77	99.75 93	99.59 90		99.54 109	96.76 365	99.29 249	99.64 264	98.43 91	99.94 91	96.92 388	99.66 160	99.72 138

DTE-MVSNet		97.51 364	97.19 374	98.46 342	98.63 446	98.13 297	99.84 12	99.48 213	96.68 370	97.97 428	99.67 251	92.92 351	98.56 475	96.88 390	92.60 469	98.70 362

ADS-MVSNet2		98.02 286	98.07 264	97.87 400	99.33 301	95.19 442	99.23 357	99.08 399	96.24 405	99.10 294	99.67 251	94.11 320	98.93 461	96.81 391	99.05 243	99.48 252

ADS-MVSNet		98.20 258	98.08 261	98.56 327	99.33 301	96.48 395	99.23 357	99.15 390	96.24 405	99.10 294	99.67 251	94.11 320	99.71 291	96.81 391	99.05 243	99.48 252

gg-mvs-nofinetune		96.17 411	95.32 423	98.73 304	98.79 419	98.14 296	99.38 291	94.09 528	91.07 490	98.07 424	91.04 529	89.62 427	99.35 373	96.75 393	99.09 239	98.68 371

v1144		97.98 293	97.69 309	98.85 290	98.87 409	98.66 253	99.54 174	99.35 322	96.27 403	99.23 267	99.35 371	94.67 291	99.23 394	96.73 394	95.16 418	98.68 371

UnsupCasMVSNet_eth		96.44 404	96.12 405	97.40 435	98.65 444	95.65 425	99.36 301	99.51 162	97.13 333	96.04 470	98.99 430	88.40 442	98.17 482	96.71 395	90.27 485	98.40 443

GA-MVS		97.85 312	97.47 335	99.00 252	99.38 288	97.99 306	98.57 474	99.15 390	97.04 346	98.90 331	99.30 386	89.83 423	99.38 363	96.70 396	98.33 295	99.62 199

K. test v3		97.10 388	96.79 389	98.01 386	98.72 433	96.33 400	99.87 8	97.05 505	97.59 283	96.16 468	99.80 160	88.71 435	99.04 435	96.69 397	96.55 381	98.65 390

testdata2													99.95 76	96.67 398

AllTest		98.87 189	98.72 197	99.31 208	99.86 25	98.48 279	99.56 154	99.61 61	97.85 248	99.36 232	99.85 92	95.95 216	99.85 191	96.66 399	99.83 114	99.59 215

TestCases				99.31 208	99.86 25	98.48 279		99.61 61	97.85 248	99.36 232	99.85 92	95.95 216	99.85 191	96.66 399	99.83 114	99.59 215

mvs5depth		96.66 398	96.22 403	97.97 391	97.00 497	96.28 402	98.66 466	99.03 409	96.61 378	96.93 459	99.79 177	87.20 454	99.47 342	96.65 401	94.13 441	98.16 457

test_fmvs3		92.10 464	91.77 466	93.08 483	96.19 506	86.25 502	99.82 16	98.62 471	96.65 373	95.19 476	96.90 505	55.05 529	95.93 513	96.63 402	90.92 482	97.06 501

dp		97.75 334	97.80 292	97.59 428	99.10 364	93.71 472	99.32 316	98.88 435	96.48 390	99.08 299	99.55 299	92.67 363	99.82 232	96.52 403	98.58 280	99.24 297

BH-RMVSNet		98.41 239	98.08 261	99.40 189	99.41 277	98.83 235	99.30 322	98.77 451	97.70 272	98.94 326	99.65 258	92.91 353	99.74 275	96.52 403	99.55 173	99.64 191

FMVSNet2		97.72 340	97.36 353	98.80 298	99.51 238	98.84 232	99.45 249	99.42 281	96.49 387	98.86 343	99.29 388	90.26 414	98.98 449	96.44 405	96.56 380	98.58 420

SSC-MVS3.2		97.34 377	97.15 375	97.93 395	99.02 384	95.76 422	99.48 231	99.58 78	97.62 281	99.09 297	99.53 309	87.95 447	99.27 386	96.42 406	95.66 406	98.75 349

ambc				93.06 484	92.68 536	82.36 512	98.47 486	98.73 462		95.09 478	97.41 497	55.55 527	99.10 427	96.42 406	91.32 474	97.71 483

tpm cat1		97.39 374	97.36 353	97.50 431	99.17 351	93.73 471	99.43 262	99.31 350	91.27 487	98.71 359	99.08 414	94.31 313	99.77 265	96.41 408	98.50 287	99.00 323

tt0320		95.71 421	95.07 426	97.62 424	99.05 380	95.02 446	99.25 349	99.52 134	86.81 503	97.97 428	99.72 218	83.58 482	99.15 413	96.38 409	93.35 452	98.68 371

v144192		97.92 302	97.60 320	98.87 284	98.83 416	98.65 254	99.55 169	99.34 327	96.20 408	99.32 241	99.40 355	94.36 308	99.26 389	96.37 410	95.03 421	98.70 362

Patchmatch-RL test		95.84 417	95.81 414	95.95 465	95.61 514	90.57 494	98.24 496	98.39 478	95.10 437	95.20 475	98.67 453	94.78 278	97.77 491	96.28 411	90.02 486	99.51 244

Patchmtry		97.75 334	97.40 350	98.81 296	99.10 364	98.87 225	99.11 390	99.33 335	94.83 444	98.81 348	99.38 362	94.33 311	99.02 441	96.10 412	95.57 409	98.53 426

BH-w/o		98.00 291	97.89 285	98.32 359	99.35 295	96.20 406	99.01 414	98.90 431	96.42 395	98.38 399	99.00 428	95.26 252	99.72 285	96.06 413	98.61 277	99.03 320

testing3		97.28 380	96.76 390	98.82 293	99.37 291	98.07 302	99.45 249	99.36 315	97.56 288	97.89 432	98.95 435	83.70 481	98.82 466	96.03 414	98.56 283	99.58 219

v7n		97.87 309	97.52 327	98.92 265	98.76 429	98.58 264	99.84 12	99.46 248	96.20 408	98.91 329	99.70 225	94.89 270	99.44 351	96.03 414	93.89 447	98.75 349

v10		97.85 312	97.52 327	98.86 287	98.99 390	98.67 252	99.75 43	99.41 284	95.70 426	98.98 318	99.41 350	94.75 283	99.23 394	96.01 416	94.63 430	98.67 379

lessismore_v0				97.79 414	98.69 440	95.44 436		94.75 524		95.71 472	99.87 74	88.69 436	99.32 378	95.89 417	94.93 424	98.62 401

ITE_SJBPF				98.08 381	99.29 314	96.37 398		98.92 424	98.34 147	98.83 345	99.75 202	91.09 406	99.62 327	95.82 418	97.40 360	98.25 452

FMVSNet1		96.84 395	96.36 399	98.29 362	99.32 308	97.26 343	99.43 262	99.48 213	95.11 435	98.55 386	99.32 383	83.95 480	98.98 449	95.81 419	96.26 388	98.62 401

DPM-MVS		98.95 181	98.71 199	99.66 92	99.63 173	99.55 98	98.64 468	99.10 396	97.93 238	99.42 209	99.55 299	98.67 73	99.80 245	95.80 420	99.68 157	99.61 201

dtuonly		98.37 245	98.26 245	98.69 311	99.07 373	96.81 381	98.51 482	98.75 452	97.77 261	99.57 174	99.68 244	96.12 204	99.71 291	95.76 421	99.11 224	99.57 222

MIMVSNet		97.73 338	97.45 338	98.57 323	99.45 268	97.50 333	99.02 409	98.98 416	96.11 417	99.41 214	99.14 408	90.28 413	98.74 471	95.74 422	98.93 253	99.47 258

test_f		91.90 466	91.26 469	93.84 477	95.52 517	85.92 503	99.69 63	98.53 476	95.31 432	93.87 489	96.37 511	55.33 528	98.27 480	95.70 423	90.98 481	97.32 495

tfpnnormal		97.84 316	97.47 335	98.98 254	99.20 337	99.22 151	99.64 98	99.61 61	96.32 399	98.27 411	99.70 225	93.35 343	99.44 351	95.69 424	95.40 413	98.27 450

MS-PatchMatch		97.24 384	97.32 363	96.99 446	98.45 461	93.51 477	98.82 447	99.32 346	97.41 309	98.13 420	99.30 386	88.99 431	99.56 334	95.68 425	99.80 126	97.90 480

EG-PatchMatch MVS		95.97 415	95.69 416	96.81 453	97.78 479	92.79 481	99.16 373	98.93 421	96.16 412	94.08 487	99.22 399	82.72 486	99.47 342	95.67 426	97.50 349	98.17 456

USDC		97.34 377	97.20 373	97.75 417	99.07 373	95.20 441	98.51 482	99.04 406	97.99 232	98.31 407	99.86 85	89.02 430	99.55 336	95.67 426	97.36 362	98.49 431

MVP-Stereo		97.81 324	97.75 303	97.99 389	97.53 484	96.60 392	98.96 424	98.85 440	97.22 326	97.23 449	99.36 368	95.28 249	99.46 344	95.51 428	99.78 135	97.92 478
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
WAC-MVS						97.16 347								95.47 429

CMPMVS	69.68 23	94.13 451	94.90 429	91.84 487	97.24 491	80.01 524	98.52 480	99.48 213	89.01 497	91.99 501	99.67 251	85.67 467	99.13 418	95.44 430	97.03 372	96.39 511
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
GG-mvs-BLEND				98.45 344	98.55 455	98.16 294	99.43 262	93.68 529		97.23 449	98.46 460	89.30 428	99.22 401	95.43 431	98.22 306	97.98 474

v1921920		97.80 326	97.45 338	98.84 291	98.80 418	98.53 268	99.52 185	99.34 327	96.15 414	99.24 263	99.47 335	93.98 326	99.29 382	95.40 432	95.13 419	98.69 366

TR-MVS		97.76 330	97.41 349	98.82 293	99.06 376	97.87 316	98.87 438	98.56 472	96.63 377	98.68 367	99.22 399	92.49 368	99.65 316	95.40 432	97.79 330	98.95 333

v1192		97.81 324	97.44 343	98.91 269	98.88 406	98.68 251	99.51 195	99.34 327	96.18 410	99.20 275	99.34 375	94.03 324	99.36 370	95.32 434	95.18 417	98.69 366

myMVS_eth3d		96.89 393	96.37 398	98.43 349	99.00 387	97.16 347	99.29 327	99.39 294	97.06 343	97.41 443	98.15 474	83.46 483	98.68 473	95.27 435	98.34 293	99.45 266

PAPR		98.63 227	98.34 238	99.51 147	99.40 282	99.03 179	98.80 449	99.36 315	96.33 398	99.00 315	99.12 413	98.46 89	99.84 201	95.23 436	99.37 191	99.66 177

TinyColmap		97.12 387	96.89 387	97.83 410	99.07 373	95.52 431	98.57 474	98.74 456	97.58 285	97.81 436	99.79 177	88.16 445	99.56 334	95.10 437	97.21 367	98.39 444

DSMNet-mixed		97.25 382	97.35 355	96.95 449	97.84 477	93.61 476	99.57 146	96.63 512	96.13 416	98.87 337	98.61 456	94.59 296	97.70 494	95.08 438	98.86 263	99.55 227

test0.0.03 1		97.71 343	97.42 348	98.56 327	98.41 463	97.82 319	98.78 452	98.63 470	97.34 314	98.05 425	98.98 432	94.45 306	98.98 449	95.04 439	97.15 370	98.89 334

MVStest1		96.08 414	95.48 419	97.89 399	98.93 398	96.70 384	99.56 154	99.35 322	92.69 473	91.81 502	99.46 339	89.90 422	98.96 458	95.00 440	92.61 468	98.00 472

our_test_3		97.65 353	97.68 310	97.55 429	98.62 447	94.97 448	98.84 444	99.30 355	96.83 362	98.19 416	99.34 375	97.01 151	99.02 441	95.00 440	96.01 393	98.64 392

MVS-HIRNet		95.75 419	95.16 424	97.51 430	99.30 310	93.69 473	98.88 436	95.78 517	85.09 510	98.78 353	92.65 525	91.29 401	99.37 366	94.85 442	99.85 94	99.46 263

CR-MVSNet		98.17 262	97.93 279	98.87 284	99.18 343	98.49 277	99.22 361	99.33 335	96.96 351	99.56 176	99.38 362	94.33 311	99.00 446	94.83 443	98.58 280	99.14 302

pmmvs-eth3d		95.34 431	94.73 432	97.15 440	95.53 516	95.94 413	99.35 306	99.10 396	95.13 433	93.55 491	97.54 495	88.15 446	97.91 488	94.58 444	89.69 491	97.61 488

testgi		97.65 353	97.50 330	98.13 378	99.36 294	96.45 396	99.42 269	99.48 213	97.76 263	97.87 433	99.45 341	91.09 406	98.81 467	94.53 445	98.52 286	99.13 305

v1240		97.69 345	97.32 363	98.79 299	98.85 413	98.43 283	99.48 231	99.36 315	96.11 417	99.27 256	99.36 368	93.76 336	99.24 393	94.46 446	95.23 416	98.70 362

YYNet1		95.36 430	94.51 439	97.92 396	97.89 475	97.10 350	99.10 392	99.23 377	93.26 465	80.77 528	99.04 422	92.81 354	98.02 485	94.30 447	94.18 440	98.64 392

PM-MVS		92.96 460	92.23 464	95.14 471	95.61 514	89.98 497	99.37 295	98.21 486	94.80 445	95.04 479	97.69 489	65.06 520	97.90 489	94.30 447	89.98 487	97.54 492

test_vis3_rt		87.04 482	85.81 486	90.73 495	93.99 529	81.96 514	99.76 38	90.23 538	92.81 472	81.35 527	91.56 527	40.06 546	99.07 430	94.27 449	88.23 496	91.15 525

MVS		97.28 380	96.55 394	99.48 165	98.78 422	98.95 199	99.27 338	99.39 294	83.53 511	98.08 421	99.54 304	96.97 152	99.87 176	94.23 450	99.16 207	99.63 196

MDA-MVSNet_test_wron		95.45 425	94.60 435	98.01 386	98.16 470	97.21 346	99.11 390	99.24 376	93.49 461	80.73 529	98.98 432	93.02 348	98.18 481	94.22 451	94.45 434	98.64 392

ArgMatch-Sym		96.59 400	96.31 400	97.42 433	98.89 404	94.84 451	99.16 373	99.39 294	98.11 200	98.35 404	99.53 309	84.38 478	99.40 360	94.16 452	94.85 428	98.03 467

TransMVSNet (Re)		97.15 386	96.58 393	98.86 287	99.12 359	98.85 230	99.49 223	98.91 429	95.48 429	97.16 453	99.80 160	93.38 340	99.11 424	94.16 452	91.73 473	98.62 401

UnsupCasMVSNet_bld		93.53 455	92.51 461	96.58 457	97.38 487	93.82 469	98.24 496	99.48 213	91.10 489	93.10 493	96.66 507	74.89 501	98.37 478	94.03 454	87.71 498	97.56 491

ArgMatch-SfM		96.18 410	95.78 415	97.38 436	99.08 370	94.64 458	99.20 366	99.33 335	98.01 230	98.54 387	99.54 304	83.13 484	99.43 355	93.86 455	91.29 475	98.08 462

ppachtmachnet_test		97.49 370	97.45 338	97.61 427	98.62 447	95.24 440	98.80 449	99.46 248	96.11 417	98.22 414	99.62 275	96.45 184	98.97 456	93.77 456	95.97 398	98.61 410

UWE-MVS-28		97.36 375	97.24 372	97.75 417	98.84 415	94.44 462	99.24 354	97.58 500	97.98 234	99.00 315	99.00 428	91.35 399	99.53 338	93.75 457	98.39 291	99.27 295

thres600view7		97.86 311	97.51 329	98.92 265	99.72 112	97.95 312	99.59 128	98.74 456	97.94 237	99.27 256	98.62 454	91.75 385	99.86 183	93.73 458	98.19 310	98.96 331

MASt3R-SfM		94.79 442	95.11 425	93.81 478	97.96 472	85.14 507	98.52 480	98.99 414	95.33 431	97.53 441	99.13 409	79.99 496	99.48 340	93.66 459	94.90 426	96.80 504

test_method		91.10 468	91.36 468	90.31 497	95.85 511	73.72 536	94.89 524	99.25 373	68.39 526	95.82 471	99.02 425	80.50 495	98.95 459	93.64 460	94.89 427	98.25 452

DeepMVS_CX				93.34 481	99.29 314	82.27 513		99.22 379	85.15 509	96.33 465	99.05 419	90.97 408	99.73 281	93.57 461	97.77 331	98.01 469

MDA-MVSNet-bldmvs		94.96 439	93.98 447	97.92 396	98.24 466	97.27 341	99.15 377	99.33 335	93.80 456	80.09 530	99.03 423	88.31 443	97.86 490	93.49 462	94.36 436	98.62 401

SP-DiffGlue		90.78 471	90.71 471	90.98 492	95.45 519	81.30 519	97.92 509	97.30 503	75.18 517	92.09 499	95.93 512	74.93 500	94.89 520	93.46 463	94.12 442	96.74 507

Patchmatch-test		97.93 299	97.65 313	98.77 302	99.18 343	97.07 354	99.03 406	99.14 392	96.16 412	98.74 356	99.57 293	94.56 298	99.72 285	93.36 464	99.11 224	99.52 235

FE-MVSNET2		95.10 435	94.44 440	97.08 445	95.08 520	95.97 411	99.51 195	99.37 313	95.02 439	94.10 486	97.57 493	86.18 464	97.66 496	93.28 465	89.86 488	97.61 488

thres100view900		97.76 330	97.45 338	98.69 311	99.72 112	97.86 318	99.59 128	98.74 456	97.93 238	99.26 261	98.62 454	91.75 385	99.83 223	93.22 466	98.18 311	98.37 446

tfpn200view9		97.72 340	97.38 351	98.72 306	99.69 129	97.96 309	99.50 206	98.73 462	97.83 252	99.17 283	98.45 461	91.67 389	99.83 223	93.22 466	98.18 311	98.37 446

thres400		97.77 329	97.38 351	98.92 265	99.69 129	97.96 309	99.50 206	98.73 462	97.83 252	99.17 283	98.45 461	91.67 389	99.83 223	93.22 466	98.18 311	98.96 331

EPNet_dtu		98.03 284	97.96 274	98.23 370	98.27 465	95.54 430	99.23 357	98.75 452	99.02 62	97.82 435	99.71 221	96.11 205	99.48 340	93.04 469	99.65 162	99.69 157
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WB-MVSnew		97.65 353	97.65 313	97.63 423	98.78 422	97.62 329	99.13 381	98.33 480	97.36 313	99.07 300	98.94 436	95.64 236	99.15 413	92.95 470	98.68 275	96.12 514

thres200		97.61 356	97.28 368	98.62 317	99.64 168	98.03 303	99.26 347	98.74 456	97.68 274	99.09 297	98.32 467	91.66 391	99.81 237	92.88 471	98.22 306	98.03 467

KD-MVS_2432*1600		94.62 444	93.72 452	97.31 437	97.19 493	95.82 420	98.34 491	99.20 384	95.00 440	97.57 439	98.35 465	87.95 447	98.10 483	92.87 472	77.00 530	98.01 469

miper_refine_blended		94.62 444	93.72 452	97.31 437	97.19 493	95.82 420	98.34 491	99.20 384	95.00 440	97.57 439	98.35 465	87.95 447	98.10 483	92.87 472	77.00 530	98.01 469

PCF-MVS	97.08 14	97.66 352	97.06 381	99.47 171	99.61 194	99.09 169	98.04 506	99.25 373	91.24 488	98.51 389	99.70 225	94.55 300	99.91 136	92.76 474	99.85 94	99.42 270
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
RoMa-SfM		94.36 449	93.86 450	95.88 466	98.61 449	90.62 492	98.85 440	99.04 406	91.63 485	94.14 485	99.49 324	77.16 498	99.09 429	92.66 475	93.13 460	97.91 479

FMVSNet5		96.43 405	96.19 404	97.15 440	99.11 361	95.89 417	99.32 316	99.52 134	94.47 451	98.34 406	99.07 415	87.54 452	97.07 501	92.61 476	95.72 404	98.47 434

test_0402		96.64 399	96.24 402	97.85 404	98.85 413	96.43 397	99.44 256	99.26 370	93.52 460	96.98 457	99.52 314	88.52 441	99.20 408	92.58 477	97.50 349	97.93 477

APD_test1		95.87 416	96.49 396	94.00 475	99.53 229	84.01 509	99.54 174	99.32 346	95.91 424	97.99 426	99.85 92	85.49 470	99.88 169	91.96 478	98.84 265	98.12 459

DKM		93.17 458	92.50 462	95.21 470	98.53 457	90.26 495	98.74 459	98.90 431	93.00 469	92.61 496	99.06 417	70.06 513	97.74 493	91.92 479	89.65 492	97.62 487

Syy-MVS		97.09 389	97.14 376	96.95 449	99.00 387	92.73 482	99.29 327	99.39 294	97.06 343	97.41 443	98.15 474	93.92 329	98.68 473	91.71 480	98.34 293	99.45 266

new-patchmatchnet		94.48 447	94.08 446	95.67 467	95.08 520	92.41 483	99.18 371	99.28 361	94.55 450	93.49 492	97.37 499	87.86 450	97.01 503	91.57 481	88.36 495	97.61 488

DKM-HiRes		92.13 463	91.58 467	93.78 479	98.24 466	88.09 499	98.61 470	98.68 465	91.39 486	90.36 506	98.90 442	67.97 518	96.01 512	91.39 482	88.65 494	97.24 496

N_pmnet		94.95 440	95.83 413	92.31 486	98.47 459	79.33 527	99.12 384	92.81 534	93.87 454	97.68 438	99.13 409	93.87 331	99.01 444	91.38 483	96.19 389	98.59 419

Anonymous20240521		96.20 409	95.89 412	97.13 442	97.72 483	94.96 449	99.79 31	99.29 359	93.01 468	97.20 452	99.03 423	89.69 425	98.36 479	91.16 484	96.13 390	98.07 463

DenseAffine		94.28 450	93.53 456	96.52 458	98.72 433	92.31 484	98.78 452	99.02 410	93.14 467	94.45 483	99.01 426	74.73 502	99.20 408	90.98 485	92.94 462	98.04 466

LCM-MVSNet		86.80 485	85.22 490	91.53 489	87.81 548	80.96 520	98.23 498	98.99 414	71.05 523	90.13 508	96.51 510	48.45 540	96.88 504	90.51 486	85.30 502	96.76 505

RoMa-HiRes		92.56 462	92.07 465	94.02 474	97.77 482	87.59 501	98.87 438	98.46 477	89.82 492	92.47 497	99.41 350	71.58 509	97.29 499	90.47 487	89.79 490	97.17 498

new_pmnet		96.38 406	96.03 408	97.41 434	98.13 471	95.16 444	99.05 401	99.20 384	93.94 453	97.39 446	98.79 449	91.61 393	99.04 435	90.43 488	95.77 401	98.05 465

KD-MVS_self_test		95.00 438	94.34 442	96.96 448	97.07 496	95.39 437	99.56 154	99.44 268	95.11 435	97.13 454	97.32 501	91.86 383	97.27 500	90.35 489	81.23 518	98.23 454

PAPM		97.59 357	97.09 380	99.07 243	99.06 376	98.26 290	98.30 495	99.10 396	94.88 442	98.08 421	99.34 375	96.27 195	99.64 320	89.87 490	98.92 255	99.31 289

pmmvs3		94.09 452	93.25 459	96.60 456	94.76 524	94.49 461	98.92 431	98.18 488	89.66 493	96.48 464	98.06 480	86.28 463	97.33 498	89.68 491	87.20 499	97.97 475

LoFTR		93.25 457	92.33 463	95.99 464	97.91 473	90.83 490	99.06 398	98.56 472	92.19 476	90.24 507	98.18 473	72.97 503	99.26 389	89.37 492	92.52 470	97.89 481

EGC-MVSNET		82.80 490	77.86 497	97.62 424	97.91 473	96.12 408	99.33 313	99.28 361	8.40 551	25.05 553	99.27 393	84.11 479	99.33 376	89.20 493	98.22 306	97.42 494

PMatch-SfM		88.28 479	86.92 484	92.38 485	95.93 509	84.56 508	97.84 510	96.01 516	88.80 499	84.11 520	97.95 482	49.73 535	95.66 515	89.15 494	82.72 514	96.91 502

OpenMVS_ROB	92.34 20	94.38 448	93.70 454	96.41 459	97.38 487	93.17 479	99.06 398	98.75 452	86.58 505	94.84 482	98.26 470	81.53 491	99.32 378	89.01 495	97.87 326	96.76 505

CL-MVSNet_self_test		94.49 446	93.97 448	96.08 463	96.16 507	93.67 474	98.33 493	99.38 303	95.13 433	97.33 447	98.15 474	92.69 362	96.57 506	88.67 496	79.87 528	97.99 473

PatchT		97.03 391	96.44 397	98.79 299	98.99 390	98.34 287	99.16 373	99.07 402	92.13 481	99.52 187	97.31 502	94.54 301	98.98 449	88.54 497	98.73 272	99.03 320

MIMVSNet1		95.51 424	95.04 428	96.92 451	97.38 487	95.60 426	99.52 185	99.50 187	93.65 458	96.97 458	99.17 404	85.28 473	96.56 507	88.36 498	95.55 410	98.60 413

dmvs_testset		95.02 437	96.12 405	91.72 488	99.10 364	80.43 523	99.58 138	97.87 492	97.47 298	95.22 474	98.82 445	93.99 325	95.18 517	88.09 499	94.91 425	99.56 226

TAPA-MVS	97.07 15	97.74 336	97.34 358	98.94 261	99.70 123	97.53 331	99.25 349	99.51 162	91.90 483	99.30 246	99.63 270	98.78 53	99.64 320	88.09 499	99.87 79	99.65 184
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SD_0403		97.55 359	97.53 326	97.62 424	99.61 194	93.64 475	99.72 54	99.44 268	98.03 226	98.62 380	99.39 359	96.06 208	99.57 332	87.88 501	99.01 249	99.66 177

PMatch-Up-SfM		86.75 486	85.43 488	90.73 495	94.97 523	81.39 517	97.55 516	94.92 522	86.33 507	83.10 524	97.95 482	46.03 541	93.97 524	87.59 502	80.39 525	96.83 503

FE-MVSNET		94.07 453	93.36 458	96.22 461	94.05 528	94.71 455	99.56 154	98.36 479	93.15 466	93.76 490	97.55 494	86.47 462	96.49 508	87.48 503	89.83 489	97.48 493

Gipuma		90.99 469	90.15 474	93.51 480	98.73 431	90.12 496	93.98 529	99.45 259	79.32 514	92.28 498	94.91 515	69.61 514	97.98 487	87.42 504	95.67 405	92.45 522
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test20.03		96.12 412	95.96 410	96.63 455	97.44 485	95.45 434	99.51 195	99.38 303	96.55 384	96.16 468	99.25 396	93.76 336	96.17 510	87.35 505	94.22 439	98.27 450

ELoFTR		89.95 474	88.65 479	93.85 476	95.93 509	85.85 504	98.64 468	98.31 481	90.34 491	85.03 517	97.76 488	60.28 526	99.01 444	87.27 506	84.26 504	96.71 508

PDCNetPlus		84.77 488	83.24 491	89.36 506	94.33 527	83.93 510	98.13 504	76.80 548	83.26 512	86.31 514	97.33 500	62.90 522	92.65 526	87.20 507	62.90 534	91.50 524

Anonymous20231206		96.22 407	96.03 408	96.79 454	97.31 490	94.14 467	99.63 104	99.08 399	96.17 411	97.04 456	99.06 417	93.94 327	97.76 492	86.96 508	95.06 420	98.47 434

RPMNet		96.72 397	95.90 411	99.19 231	99.18 343	98.49 277	99.22 361	99.52 134	88.72 500	99.56 176	97.38 498	94.08 322	99.95 76	86.87 509	98.58 280	99.14 302

testf1		90.42 472	90.68 472	89.65 504	97.78 479	73.97 534	99.13 381	98.81 445	89.62 494	91.80 503	98.93 437	62.23 524	98.80 468	86.61 510	91.17 476	96.19 512

APD_test2		90.42 472	90.68 472	89.65 504	97.78 479	73.97 534	99.13 381	98.81 445	89.62 494	91.80 503	98.93 437	62.23 524	98.80 468	86.61 510	91.17 476	96.19 512

PMMVS2		86.87 484	85.37 489	91.35 490	90.21 542	83.80 511	98.89 435	97.45 502	83.13 513	91.67 505	95.03 514	48.49 539	94.70 522	85.86 512	77.62 529	95.54 515

usedtu_dtu_shiyan2		91.34 467	89.96 476	95.47 469	93.61 532	90.81 491	99.15 377	98.68 465	86.37 506	95.19 476	98.27 469	72.64 505	97.05 502	85.40 513	80.32 526	98.54 424

MatchFormer		91.94 465	90.72 470	95.58 468	97.82 478	89.79 498	98.92 431	98.87 437	88.24 501	88.03 512	97.92 486	70.39 511	99.23 394	85.21 514	91.12 478	97.72 482

FPMVS		84.93 487	85.65 487	82.75 513	86.77 549	63.39 541	98.35 490	98.92 424	74.11 518	83.39 523	98.98 432	50.85 532	92.40 528	84.54 515	94.97 422	92.46 521

SP-LightGlue		89.28 475	88.68 477	91.06 491	98.21 469	80.90 521	98.19 499	96.96 506	72.38 520	89.60 510	94.43 518	72.44 506	95.06 518	82.91 516	93.03 461	97.22 497

SP-NN		88.62 477	88.17 480	89.96 501	97.89 475	78.51 528	97.19 518	96.09 515	71.28 522	88.29 511	94.00 521	71.98 507	93.65 525	82.37 517	94.46 432	97.71 483

SP-SuperGlue		89.23 476	88.68 477	90.88 493	98.23 468	80.60 522	98.16 501	97.30 503	73.08 519	89.64 509	94.62 517	71.80 508	94.91 519	82.11 518	93.22 456	97.14 500

SP-MNN		88.33 478	87.78 481	89.95 502	98.28 464	77.92 529	98.01 507	95.69 519	70.61 524	86.18 515	94.36 519	71.09 510	94.76 521	81.51 519	94.32 437	97.17 498

XFeat-NN		82.84 489	83.12 492	82.00 515	94.35 526	67.14 540	93.32 534	89.27 539	62.21 532	84.06 521	93.50 523	69.15 515	89.40 532	78.92 520	83.33 511	89.46 528

PMVS	70.75 22	75.98 499	74.97 502	79.01 516	70.98 554	55.18 553	93.37 532	98.21 486	65.08 531	61.78 542	93.83 522	21.74 555	92.53 527	78.59 521	91.12 478	89.34 529
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
dongtai		93.26 456	92.93 460	94.25 473	99.39 285	85.68 505	97.68 513	93.27 530	92.87 471	96.85 461	99.39 359	82.33 489	97.48 497	76.78 522	97.80 329	99.58 219

XFeat-MNN		82.40 492	82.10 493	83.31 511	93.04 534	68.49 538	95.39 523	90.86 536	60.29 533	81.56 526	94.09 520	66.79 519	91.70 530	76.62 523	80.26 527	89.74 527

WB-MVS		93.10 459	94.10 444	90.12 500	95.51 518	81.88 515	99.73 52	99.27 368	95.05 438	93.09 494	98.91 441	94.70 289	91.89 529	76.62 523	94.02 446	96.58 509

ANet_high		77.30 496	74.86 503	84.62 510	75.88 553	77.61 530	97.63 514	93.15 533	88.81 498	64.27 539	89.29 540	36.51 549	83.93 544	75.89 525	52.31 539	92.33 523

ALIKED-NN		88.27 480	87.61 482	90.24 498	98.46 460	79.97 525	97.04 519	94.61 527	75.25 516	86.99 513	96.90 505	72.78 504	95.78 514	75.45 526	91.01 480	94.97 517

GLUNet-SfM		78.99 495	76.32 499	86.99 507	89.16 547	73.30 537	93.36 533	90.45 537	66.38 529	74.95 536	93.30 524	52.29 531	94.61 523	75.35 527	51.65 541	93.07 520

SSC-MVS		92.73 461	93.73 451	89.72 503	95.02 522	81.38 518	99.76 38	99.23 377	94.87 443	92.80 495	98.93 437	94.71 288	91.37 531	74.49 528	93.80 448	96.42 510

ALIKED-MNN		86.97 483	85.90 485	90.16 499	99.06 376	79.59 526	97.93 508	94.82 523	72.37 521	84.41 519	95.46 513	68.55 517	96.43 509	72.40 529	88.11 497	94.47 518

ALIKED-LG		88.17 481	87.32 483	90.75 494	98.67 442	81.68 516	98.16 501	94.72 525	78.63 515	86.08 516	97.07 503	70.16 512	96.62 505	71.97 530	90.37 483	93.95 519

MVE	76.82 21	76.91 498	74.31 504	84.70 509	85.38 552	76.05 533	96.88 521	93.17 531	67.39 527	71.28 537	89.01 542	21.66 556	87.69 538	71.74 531	72.29 532	90.35 526
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 493	79.88 495	82.81 512	90.75 540	76.38 532	97.69 512	95.76 518	66.44 528	83.52 522	92.25 526	62.54 523	87.16 540	68.53 532	61.40 535	84.89 531

EMVS		80.02 494	79.22 496	82.43 514	91.19 539	76.40 531	97.55 516	92.49 535	66.36 530	83.01 525	91.27 528	64.63 521	85.79 543	65.82 533	60.65 536	85.08 530

kuosan		90.92 470	90.11 475	93.34 481	98.78 422	85.59 506	98.15 503	93.16 532	89.37 496	92.07 500	98.38 464	81.48 492	95.19 516	62.54 534	97.04 371	99.25 296

wuyk23d		40.18 513	41.29 518	36.84 531	86.18 551	49.12 556	79.73 544	22.81 557	27.64 548	25.46 552	28.45 551	21.98 554	48.89 551	55.80 535	23.56 550	12.51 548

SIFT-NN		76.99 497	77.37 498	75.84 517	97.10 495	62.39 542	94.15 528	87.21 541	59.41 534	79.90 532	90.73 531	54.60 530	88.56 535	47.22 536	86.03 501	76.57 533

SIFT-NN-NCMNet		75.53 501	75.57 501	75.42 519	93.93 530	61.35 543	94.41 525	86.44 542	58.51 536	76.23 533	90.44 533	50.56 533	89.34 533	46.60 537	83.04 512	75.58 535

SIFT-NN-CMatch		72.61 502	71.92 505	74.68 520	92.79 535	60.24 546	93.28 535	81.57 546	58.24 538	75.18 535	90.26 535	49.66 536	87.35 539	46.02 538	60.26 537	76.45 534

SIFT-NN-UMatch		71.65 503	70.86 506	74.00 522	90.69 541	60.53 545	93.59 530	81.89 544	58.42 537	60.99 543	89.71 538	50.18 534	87.89 537	45.77 539	66.55 533	73.57 539

SIFT-NN-PointCN		70.32 505	69.71 508	72.13 525	90.01 543	58.29 551	93.45 531	76.20 549	56.66 543	70.25 538	89.20 541	48.94 538	83.41 545	45.45 540	57.26 538	74.70 536

SIFT-MNN		75.73 500	75.71 500	75.77 518	95.65 513	60.92 544	94.36 526	87.62 540	58.67 535	75.90 534	90.94 530	49.64 537	89.04 534	44.85 541	83.80 507	77.35 532

SIFT-ConvMatch		69.43 506	68.09 509	73.45 523	93.86 531	60.02 548	92.57 538	77.69 547	57.58 539	62.69 540	90.53 532	42.14 543	86.65 542	43.98 542	51.72 540	73.67 538

SIFT-UMatch		68.14 507	66.40 510	73.38 524	92.20 538	59.42 549	92.84 536	76.01 550	56.87 541	58.37 544	90.35 534	41.97 544	87.16 540	42.64 543	46.35 542	73.55 540

SIFT-CM-Cal		66.94 508	65.48 511	71.33 526	93.05 533	58.77 550	91.46 541	70.45 552	56.64 544	61.97 541	89.98 536	40.72 545	83.32 546	42.57 544	42.47 544	71.90 541

SIFT-UM-Cal		64.60 509	62.65 512	70.42 527	92.22 537	58.07 552	92.29 539	66.92 553	56.70 542	50.16 547	89.97 537	37.90 547	82.95 547	42.33 545	35.40 547	70.24 543

SIFT-NCM-Cal		71.65 503	70.76 507	74.34 521	94.61 525	60.18 547	94.16 527	81.72 545	57.21 540	55.36 545	89.56 539	42.48 542	88.45 536	41.31 546	80.41 524	74.39 537

testmvs		39.17 514	43.78 516	25.37 533	36.04 557	16.84 559	98.36 489	26.56 556	20.06 549	38.51 551	67.32 546	29.64 552	15.30 553	37.59 547	39.90 546	43.98 547

test123		39.01 515	42.50 517	28.53 532	39.17 556	20.91 558	98.75 456	19.17 558	19.83 550	38.57 550	66.67 547	33.16 551	15.42 552	37.50 548	29.66 549	49.26 546

SIFT-PCN-Cal		61.29 511	60.21 514	64.54 529	89.88 544	50.56 555	91.21 542	65.73 554	53.15 546	48.59 548	87.20 543	36.60 548	76.52 548	37.37 549	32.17 548	66.54 544

SIFT-PointCN		62.71 510	61.56 513	66.18 528	89.53 546	50.88 554	91.81 540	72.35 551	53.65 545	50.49 546	86.32 544	33.30 550	76.23 549	35.91 550	40.66 545	71.43 542

SIFT-NCMNet		55.02 512	53.54 515	59.46 530	86.55 550	47.35 557	87.85 543	46.22 555	51.77 547	44.11 549	83.50 545	27.88 553	68.75 550	32.81 551	21.14 551	62.27 545

mmdepth		0.02 520	0.03 523	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.27 553	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

monomultidepth		0.02 520	0.03 523	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.27 553	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

test_blank		0.13 519	0.17 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	1.57 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uanet_test		0.02 520	0.03 523	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.27 553	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

DCPMVS		0.02 520	0.03 523	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.27 553	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

cdsmvs_eth3d_5k		24.64 516	32.85 519	0.00 534	0.00 558	0.00 560	0.00 545	99.51 162	0.00 552	0.00 554	99.56 296	96.58 176	0.00 554	0.00 552	0.00 552	0.00 549

pcd_1.5k_mvsjas		8.27 518	11.03 521	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.27 553	99.01 19	0.00 554	0.00 552	0.00 552	0.00 549

sosnet-low-res		0.02 520	0.03 523	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.27 553	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

sosnet		0.02 520	0.03 523	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.27 553	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uncertanet		0.02 520	0.03 523	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.27 553	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

Regformer		0.02 520	0.03 523	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.27 553	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

ab-mvs-re		8.30 517	11.06 520	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	99.58 288	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uanet		0.02 520	0.03 523	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.27 553	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

TestfortrainingZip				99.69 89	99.58 207	99.62 84	99.69 63	99.38 303	98.98 72	99.84 56	99.75 202	98.84 45	99.78 260		99.21 202	99.66 177

FOURS1					99.91 1	99.93 1	99.87 8	99.56 90	99.10 48	99.81 72

test_one_0601					99.81 58	99.88 10		99.49 201	98.97 76	99.65 146	99.81 142	99.09 15

eth-test2					0.00 558

eth-test					0.00 558

test_241102_ONE					99.84 38	99.90 2		99.48 213	99.07 58	99.91 31	99.74 208	99.20 8	99.76 269

save fliter					99.76 83	99.59 90	99.14 380	99.40 291	99.00 67

test0726					99.85 31	99.89 6	99.62 109	99.50 187	99.10 48	99.86 52	99.82 127	98.94 33

GSMVS																99.52 235

test_part2					99.81 58	99.83 23				99.77 90

sam_mvs1												94.86 271				99.52 235

sam_mvs												94.72 287

MTGPA								99.47 235

test_post											65.99 548	94.65 294	99.73 281

patchmatchnet-post											98.70 452	94.79 277	99.74 275

MTMP							99.54 174	98.88 435

TEST9					99.67 139	99.65 76	99.05 401	99.41 284	96.22 407	98.95 324	99.49 324	98.77 57	99.91 136

test_8					99.67 139	99.61 87	99.03 406	99.41 284	96.28 401	98.93 327	99.48 332	98.76 58	99.91 136

agg_prior					99.67 139	99.62 84		99.40 291		98.87 337			99.91 136

test_prior4						99.56 96	98.99 417

test_prior				99.68 90	99.67 139	99.48 113		99.56 90					99.83 223			99.74 118

新几何2							99.01 414

旧先验1					99.74 101	99.59 90		99.54 109			99.69 236	98.47 88			99.68 157	99.73 128

原ACMM2							98.95 427

test222					99.75 93	99.49 111	98.91 434	99.49 201	96.42 395	99.34 239	99.65 258	98.28 101			99.69 154	99.72 138

segment_acmp												98.96 26

testdata1							98.85 440		98.32 151

test12				99.75 77	99.64 168	99.61 87		99.29 359		99.21 271		98.38 96	99.89 164		99.74 146	99.74 118

plane_prior7					99.29 314	97.03 362

plane_prior6					99.27 319	96.98 366						92.71 360

plane_prior4											99.61 279

plane_prior3						97.00 364			98.69 108	99.11 291

plane_prior2							99.39 286		98.97 76

plane_prior1					99.26 322

plane_prior						96.97 367	99.21 363		98.45 132						97.60 338

n2								0.00 559

nn								0.00 559

door-mid								98.05 489

test11								99.35 322

door								97.92 490

HQP5-MVS						96.83 378

HQP-NCC					99.19 340		98.98 420		98.24 168	98.66 368

ACMP_Plane					99.19 340		98.98 420		98.24 168	98.66 368

HQP4-MVS										98.66 368			99.64 320			98.64 392

HQP3-MVS								99.39 294							97.58 340

HQP2-MVS												92.47 369

NP-MVS					99.23 330	96.92 374					99.40 355

ACMMP++_ref															97.19 368

ACMMP++															97.43 358

Test By Simon												98.75 61

High-resolution multi-view benchmark