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_s_conf0.1_n_a		99.26 91	99.06 110	99.85 43	99.52 235	99.62 84	99.54 175	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

UA-Net		99.42 55	99.29 65	99.80 64	99.62 183	99.55 98	99.50 207	99.70 18	98.79 96	99.77 90	99.96 1	97.45 125	99.96 41	98.92 162	99.90 56	99.89 30

fmvsm_s_conf0.1_n		99.29 84	99.10 99	99.86 34	99.70 123	99.65 76	99.53 184	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

test_fmvs1_n		98.41 240	98.14 253	99.21 229	99.82 53	97.71 326	99.74 48	99.49 201	99.32 30	99.99 2	99.95 3	85.32 474	99.97 29	99.82 29	99.84 102	99.96 7

DeepC-MVS	98.35 2	99.30 82	99.19 87	99.64 102	99.82 53	99.23 150	99.62 110	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
fmvsm_s_conf0.1_n_2		99.37 68	99.22 82	99.81 60	99.77 79	99.75 52	99.46 246	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

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	93.20 348	99.98 20	99.55 50	99.91 45	99.99 1

test_vis1_n		97.92 303	97.44 345	99.34 200	99.53 229	98.08 301	99.74 48	99.49 201	99.15 38	100.00 1	99.94 6	79.51 500	99.98 20	99.88 26	99.76 142	99.97 4

OurMVSNet-221017-0		97.88 308	97.77 299	98.19 375	98.71 439	96.53 395	99.88 4	99.00 415	97.79 259	98.78 356	99.94 6	91.68 389	99.35 376	97.21 367	96.99 376	98.69 369

fmvsm_s_conf0.5_n_11		99.32 78	99.16 91	99.80 64	99.83 47	99.70 61	99.57 147	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_3		99.37 68	99.20 85	99.87 22	99.75 93	99.70 61	99.48 232	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_2		99.32 78	99.13 94	99.89 12	99.80 64	99.77 49	99.44 257	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_fmvsmconf0.01_n		99.22 99	99.03 118	99.79 68	98.42 465	99.48 113	99.55 170	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

test2506		96.81 399	96.65 395	97.29 442	99.74 101	92.21 490	99.60 118	85.06 548	99.13 41	99.77 90	99.93 10	87.82 453	99.85 192	99.38 80	99.38 185	99.80 88

test1111		98.04 283	98.11 257	97.83 413	99.74 101	93.82 473	99.58 139	95.40 524	99.12 46	99.65 146	99.93 10	90.73 411	99.84 202	99.43 71	99.38 185	99.82 72

ECVR-MVS		98.04 283	98.05 266	98.00 391	99.74 101	94.37 468	99.59 129	94.98 525	99.13 41	99.66 136	99.93 10	90.67 412	99.84 202	99.40 74	99.38 185	99.80 88

SixPastTwentyTwo		97.50 367	97.33 363	98.03 386	98.65 447	96.23 408	99.77 35	98.68 468	97.14 335	97.90 434	99.93 10	90.45 413	99.18 413	97.00 382	96.43 386	98.67 382

fmvsm_s_conf0.5_n_10		99.41 59	99.24 77	99.92 1	99.83 47	99.84 20	99.53 184	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	99.48 232	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

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

fmvsm_s_conf0.5_n_a		99.56 21	99.47 24	99.85 43	99.83 47	99.64 82	99.52 186	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

fmvsm_s_conf0.5_n		99.51 29	99.40 37	99.85 43	99.84 38	99.65 76	99.51 196	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	99.50 207	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

test_fmvsmconf_n		99.70 3	99.64 4	99.87 22	99.80 64	99.66 72	99.48 232	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

test_fmvsmvis_n_1920		99.65 8	99.61 8	99.77 74	99.38 289	99.37 125	99.58 139	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

E5new		99.14 125	99.02 129	99.50 153	99.69 129	98.91 210	99.60 118	99.53 125	98.13 191	99.72 108	99.91 26	96.26 198	99.84 202	99.30 98	99.10 234	99.76 107

E6new		99.15 117	99.03 118	99.50 153	99.66 151	98.90 215	99.60 118	99.53 125	98.13 191	99.72 108	99.91 26	96.31 192	99.84 202	99.30 98	99.10 234	99.76 107

E6		99.15 117	99.03 118	99.50 153	99.66 151	98.90 215	99.60 118	99.53 125	98.13 191	99.72 108	99.91 26	96.31 192	99.84 202	99.30 98	99.10 234	99.76 107

E5		99.14 125	99.02 129	99.50 153	99.69 129	98.91 210	99.60 118	99.53 125	98.13 191	99.72 108	99.91 26	96.26 198	99.84 202	99.30 98	99.10 234	99.76 107

test_fmvsm_n_1920		99.69 6	99.66 3	99.78 71	99.84 38	99.44 118	99.58 139	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

test_vis1_n_1920		98.63 228	98.40 236	99.31 208	99.86 25	97.94 314	99.67 77	99.62 52	99.43 19	99.99 2	99.91 26	87.29 455	100.00 1	99.92 24	99.92 38	99.98 2

mvsany_test1		99.50 31	99.46 28	99.62 109	99.61 194	99.09 169	98.94 432	99.48 213	99.10 48	99.96 27	99.91 26	98.85 43	99.96 41	99.72 32	99.58 171	99.82 72

test_fmvs1		98.88 186	98.79 189	99.16 234	99.69 129	97.61 330	99.55 170	99.49 201	99.32 30	99.98 13	99.91 26	91.41 398	99.96 41	99.82 29	99.92 38	99.90 27

SD-MVS		99.41 59	99.52 14	99.05 246	99.74 101	99.68 65	99.46 246	99.52 134	99.11 47	99.88 42	99.91 26	99.43 1	97.70 498	98.72 198	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
ACMH	97.28 8	98.10 270	97.99 272	98.44 350	99.41 277	96.96 369	99.60 118	99.56 90	98.09 206	98.15 422	99.91 26	90.87 410	99.70 301	98.88 166	97.45 357	98.67 382
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
E4		99.13 129	99.01 137	99.49 160	99.68 136	98.90 215	99.52 186	99.52 134	98.13 191	99.71 118	99.90 36	96.32 190	99.84 202	99.21 116	99.11 225	99.75 113

viewdifsd2359ckpt11		98.78 210	98.74 195	98.89 275	99.67 139	97.04 359	99.50 207	99.58 78	98.26 161	99.56 176	99.90 36	94.36 308	99.87 177	99.49 61	98.32 301	99.77 100

viewmsd2359difaftdt		98.78 210	98.74 195	98.90 271	99.67 139	97.04 359	99.50 207	99.58 78	98.26 161	99.56 176	99.90 36	94.36 308	99.87 177	99.49 61	98.32 301	99.77 100

fmvsm_s_conf0.5_n_8		99.54 24	99.42 32	99.89 12	99.83 47	99.74 55	99.51 196	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

reproduce_model		99.63 9	99.54 13	99.90 8	99.78 71	99.88 10	99.56 155	99.55 100	99.15 38	99.90 34	99.90 36	99.00 23	99.97 29	99.11 132	99.91 45	99.86 43

patch_mono-2		99.26 91	99.62 7	98.16 377	99.81 58	94.59 464	99.52 186	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

VDDNet		97.55 361	97.02 385	99.16 234	99.49 252	98.12 299	99.38 292	99.30 356	95.35 433	99.68 125	99.90 36	82.62 490	99.93 109	99.31 95	98.13 318	99.42 271

QAPM		98.67 223	98.30 243	99.80 64	99.20 340	99.67 69	99.77 35	99.72 14	94.74 449	98.73 360	99.90 36	95.78 229	99.98 20	96.96 386	99.88 73	99.76 107

3Dnovator	97.25 9	99.24 96	99.05 113	99.81 60	99.12 362	99.66 72	99.84 12	99.74 13	99.09 55	98.92 329	99.90 36	95.94 218	99.98 20	98.95 156	99.92 38	99.79 92

PRO-TEST		98.69 220	98.70 201	98.65 316	99.39 285	96.74 384	99.64 98	99.34 327	98.20 176	99.53 185	99.89 45	93.26 344	99.90 149	99.32 92	99.78 135	99.32 289

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	98.83 182	99.88 73	99.93 22

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

viewmacassd2359aftdt		99.08 154	98.94 158	99.50 153	99.66 151	98.96 193	99.51 196	99.54 109	98.27 158	99.42 210	99.89 45	95.88 223	99.80 246	99.20 117	99.11 225	99.76 107

fmvsm_l_conf0.5_n_9		99.58 16	99.47 24	99.92 1	99.85 31	99.82 29	99.47 242	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

LuminaMVS		99.23 97	99.10 99	99.61 110	99.35 296	99.31 137	99.46 246	99.13 395	98.61 114	99.86 52	99.89 45	96.41 188	99.91 136	99.67 37	99.51 176	99.63 196

fmvsm_l_conf0.5_n_3		99.61 10	99.51 18	99.92 1	99.84 38	99.82 29	99.54 175	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

reproduce-ours		99.61 10	99.52 14	99.90 8	99.76 83	99.88 10	99.52 186	99.54 109	99.13 41	99.89 39	99.89 45	98.96 26	99.96 41	99.04 142	99.90 56	99.85 47

our_new_method		99.61 10	99.52 14	99.90 8	99.76 83	99.88 10	99.52 186	99.54 109	99.13 41	99.89 39	99.89 45	98.96 26	99.96 41	99.04 142	99.90 56	99.85 47

Anonymous20240529		98.09 271	97.68 311	99.34 200	99.66 151	98.44 282	99.40 283	99.43 279	93.67 461	99.22 269	99.89 45	90.23 418	99.93 109	99.26 112	98.33 297	99.66 177

CHOSEN 1792x2688		99.19 101	99.10 99	99.45 175	99.89 8	98.52 272	99.39 287	99.94 1	98.73 103	99.11 292	99.89 45	95.50 240	99.94 91	99.50 57	99.97 9	99.89 30

RPSCF		98.22 256	98.62 217	96.99 449	99.82 53	91.58 492	99.72 54	99.44 268	96.61 381	99.66 136	99.89 45	95.92 219	99.82 233	97.46 347	99.10 234	99.57 222

3Dnovator+	97.12 13	99.18 104	98.97 148	99.82 57	99.17 354	99.68 65	99.81 20	99.51 162	99.20 34	98.72 361	99.89 45	95.68 234	99.97 29	98.86 174	99.86 87	99.81 79

COLMAP_ROB	97.56 6	98.86 192	98.75 193	99.17 233	99.88 13	98.53 268	99.34 313	99.59 73	97.55 290	98.70 368	99.89 45	95.83 224	99.90 149	98.10 276	99.90 56	99.08 314
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
dtuplus		99.03 166	98.92 161	99.36 196	99.60 201	98.62 259	99.35 307	99.51 162	97.99 233	99.38 224	99.88 59	96.04 209	99.79 253	99.37 81	99.17 207	99.68 163

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 59	95.78 229	99.78 261	99.41 72	99.16 208	99.71 150

casdiffseed414692147		98.97 179	98.78 190	99.53 135	99.66 151	99.16 158	99.61 116	99.52 134	98.01 231	99.21 272	99.88 59	94.82 273	99.70 301	99.29 104	99.04 246	99.74 118

E2		99.15 117	99.03 118	99.49 160	99.65 163	98.93 208	99.49 224	99.52 134	98.14 188	99.72 108	99.88 59	96.57 178	99.84 202	99.17 124	99.13 218	99.72 138

E3		99.15 117	99.03 118	99.49 160	99.62 183	98.91 210	99.49 224	99.52 134	98.13 191	99.72 108	99.88 59	96.61 173	99.84 202	99.17 124	99.13 218	99.72 138

AstraMVS		99.09 152	99.03 118	99.25 223	99.66 151	98.13 297	99.57 147	98.24 488	98.82 90	99.91 31	99.88 59	95.81 226	99.90 149	99.72 32	99.67 160	99.74 118

fmvsm_s_conf0.5_n_7		99.34 75	99.29 65	99.48 165	99.70 123	98.63 257	99.42 270	99.63 46	99.46 9	99.98 13	99.88 59	95.59 237	99.96 41	99.97 2	99.98 4	99.85 47

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 59	94.56 298	99.93 109	99.67 37	98.26 305	99.72 138

sd_testset		98.75 215	98.57 224	99.29 216	99.81 58	98.26 290	99.56 155	99.62 52	98.78 99	99.64 151	99.88 59	92.02 380	99.88 170	99.54 51	98.26 305	99.72 138

dcpmvs_2		99.23 97	99.58 9	98.16 377	99.83 47	94.68 460	99.76 38	99.52 134	99.07 58	99.98 13	99.88 59	98.56 81	99.93 109	99.67 37	99.98 4	99.87 41

RRT-MVS		98.91 184	98.75 193	99.39 194	99.46 262	98.61 262	99.76 38	99.50 187	98.06 215	99.81 72	99.88 59	93.91 330	99.94 91	99.11 132	99.27 196	99.61 201

test_djsdf		98.67 223	98.57 224	98.98 254	98.70 440	98.91 210	99.88 4	99.46 248	97.55 290	99.22 269	99.88 59	95.73 232	99.28 386	99.03 144	97.62 340	98.75 352

DP-MVS		99.16 112	98.95 156	99.78 71	99.77 79	99.53 103	99.41 275	99.50 187	97.03 350	99.04 309	99.88 59	97.39 126	99.92 124	98.66 207	99.90 56	99.87 41

TDRefinement		95.42 431	94.57 441	97.97 394	89.83 548	96.11 412	99.48 232	98.75 455	96.74 369	96.68 465	99.88 59	88.65 439	99.71 293	98.37 250	82.74 517	98.09 465

EPP-MVSNet		99.13 129	98.99 143	99.53 135	99.65 163	99.06 175	99.81 20	99.33 336	97.43 308	99.60 166	99.88 59	97.14 139	99.84 202	99.13 129	98.94 253	99.69 157

OpenMVS	96.50 16	98.47 234	98.12 256	99.52 142	99.04 385	99.53 103	99.82 16	99.72 14	94.56 452	98.08 424	99.88 59	94.73 286	99.98 20	97.47 346	99.76 142	99.06 320

onestephybrid01		99.17 109	99.06 110	99.49 160	99.60 201	98.98 185	99.38 292	99.50 187	98.52 123	99.81 72	99.87 75	96.27 195	99.81 238	99.47 66	99.10 234	99.67 170

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 75	95.96 214	99.85 192	99.40 74	99.16 208	99.72 138

viewcassd2359sk11		99.18 104	99.08 105	99.49 160	99.65 163	98.95 199	99.48 232	99.51 162	98.10 205	99.72 108	99.87 75	97.13 140	99.84 202	99.13 129	99.14 215	99.69 157

Elysia		98.88 186	98.65 209	99.58 118	99.58 207	99.34 129	99.65 90	99.52 134	98.26 161	99.83 66	99.87 75	93.37 341	99.90 149	97.81 305	99.91 45	99.49 249

StellarMVS		98.88 186	98.65 209	99.58 118	99.58 207	99.34 129	99.65 90	99.52 134	98.26 161	99.83 66	99.87 75	93.37 341	99.90 149	97.81 305	99.91 45	99.49 249

guyue		99.16 112	99.04 115	99.52 142	99.69 129	98.92 209	99.59 129	98.81 447	98.73 103	99.90 34	99.87 75	95.34 247	99.88 170	99.66 40	99.81 121	99.74 118

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 75	94.84 272	99.93 109	99.69 34	99.84 102	99.41 274

lessismore_v0				97.79 417	98.69 443	95.44 439		94.75 528		95.71 475	99.87 75	88.69 437	99.32 381	95.89 420	94.93 428	98.62 404

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	99.45 199	99.87 75	96.03 211	99.81 238	99.54 51	99.15 214	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
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 75	94.77 281	99.84 202	99.19 118	99.41 184	99.74 118
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ACMH+	97.24 10	97.92 303	97.78 297	98.32 362	99.46 262	96.68 390	99.56 155	99.54 109	98.41 138	97.79 440	99.87 75	90.18 421	99.66 313	98.05 285	97.18 372	98.62 404

fmvsm_s_conf0.5_n_5		99.37 68	99.21 83	99.86 34	99.80 64	99.68 65	99.42 270	99.61 61	99.37 26	99.97 25	99.86 86	94.96 262	99.99 4	99.97 2	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	99.49 224	99.60 68	99.42 22	99.99 2	99.86 86	95.15 257	99.95 76	99.95 16	99.89 67	99.73 128

ACMMP_NAP		99.47 40	99.34 49	99.88 16	99.87 20	99.86 18	99.47 242	99.48 213	98.05 218	99.76 96	99.86 86	98.82 48	99.93 109	98.82 189	99.91 45	99.84 54

casdiffmvs		99.13 129	98.98 146	99.56 124	99.65 163	99.16 158	99.56 155	99.50 187	98.33 149	99.41 215	99.86 86	95.92 219	99.83 224	99.45 70	99.16 208	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
PVSNet_Blended_VisFu		99.36 72	99.28 68	99.61 110	99.86 25	99.07 174	99.47 242	99.93 2	97.66 278	99.71 118	99.86 86	97.73 120	99.96 41	99.47 66	99.82 118	99.79 92

IS-MVSNet		99.05 163	98.87 175	99.57 122	99.73 108	99.32 133	99.75 43	99.20 385	98.02 230	99.56 176	99.86 86	96.54 179	99.67 310	98.09 277	99.13 218	99.73 128

USDC		97.34 380	97.20 375	97.75 420	99.07 376	95.20 444	98.51 486	99.04 408	97.99 233	98.31 410	99.86 86	89.02 431	99.55 339	95.67 429	97.36 365	98.49 435

SSM_0407		99.13 129	99.03 118	99.43 184	99.62 183	98.88 221	99.51 196	99.50 187	98.14 188	99.37 227	99.85 93	96.85 156	99.83 224	99.19 118	99.25 199	99.60 204

viewmambaseed2359dif		99.01 173	98.90 167	99.32 206	99.58 207	98.51 274	99.33 315	99.54 109	97.85 249	99.44 204	99.85 93	96.01 212	99.79 253	99.41 72	99.13 218	99.67 170

SSM_0404		99.16 112	99.06 110	99.44 180	99.65 163	98.96 193	99.49 224	99.50 187	98.14 188	99.62 158	99.85 93	96.85 156	99.85 192	99.19 118	99.26 198	99.52 235

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 93	98.41 94	99.96 41	99.28 106	99.84 102	99.83 64

sc_t1		95.75 422	95.05 430	97.87 403	98.83 419	94.61 463	99.21 366	99.45 259	87.45 506	97.97 431	99.85 93	81.19 496	99.43 358	98.27 260	93.20 461	99.57 222

APD_test1		95.87 419	96.49 399	94.00 478	99.53 229	84.01 513	99.54 175	99.32 347	95.91 427	97.99 429	99.85 93	85.49 472	99.88 170	91.96 482	98.84 266	98.12 463

TSAR-MVS + MP.		99.58 16	99.50 19	99.81 60	99.91 1	99.66 72	99.63 105	99.39 294	98.91 83	99.78 86	99.85 93	99.36 2	99.94 91	98.84 179	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
tmp_tt		82.80 493	81.52 497	86.66 511	66.61 559	68.44 543	92.79 541	97.92 494	68.96 529	80.04 537	99.85 93	85.77 468	96.15 515	97.86 298	43.89 551	95.39 520

AllTest		98.87 189	98.72 197	99.31 208	99.86 25	98.48 279	99.56 155	99.61 61	97.85 249	99.36 233	99.85 93	95.95 216	99.85 192	96.66 402	99.83 114	99.59 215

TestCases				99.31 208	99.86 25	98.48 279		99.61 61	97.85 249	99.36 233	99.85 93	95.95 216	99.85 192	96.66 402	99.83 114	99.59 215

VDD-MVS		97.73 340	97.35 357	98.88 280	99.47 260	97.12 349	99.34 313	98.85 442	98.19 179	99.67 131	99.85 93	82.98 488	99.92 124	99.49 61	98.32 301	99.60 204

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 93	99.18 11	99.96 41	99.22 114	99.92 38	99.90 27
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DeepPCF-MVS	98.18 3	98.81 205	99.37 43	97.12 446	99.60 201	91.75 491	98.61 474	99.44 268	99.35 27	99.83 66	99.85 93	98.70 70	99.81 238	99.02 146	99.91 45	99.81 79

ACMM	97.58 5	98.37 246	98.34 239	98.48 339	99.41 277	97.10 350	99.56 155	99.45 259	98.53 122	99.04 309	99.85 93	93.00 350	99.71 293	98.74 195	97.45 357	98.64 395
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LS3D		99.27 88	99.12 96	99.74 80	99.18 346	99.75 52	99.56 155	99.57 85	98.45 132	99.49 194	99.85 93	97.77 119	99.94 91	98.33 255	99.84 102	99.52 235

viewmamba		99.20 100	99.12 96	99.44 180	99.61 194	98.87 225	99.42 270	99.52 134	98.42 136	99.84 56	99.84 108	96.85 156	99.78 261	99.46 68	99.11 225	99.67 170

hybridnocas07		99.13 129	99.03 118	99.46 173	99.63 173	98.90 215	99.38 292	99.52 134	98.41 138	99.82 70	99.84 108	96.09 206	99.80 246	99.40 74	99.16 208	99.68 163

hybrid		99.11 145	99.01 137	99.41 187	99.64 168	98.76 245	99.35 307	99.52 134	98.31 153	99.80 78	99.84 108	96.16 202	99.79 253	99.40 74	99.06 243	99.68 163

E3new		99.18 104	99.08 105	99.48 165	99.63 173	98.94 203	99.46 246	99.50 187	98.06 215	99.72 108	99.84 108	97.27 134	99.84 202	99.10 135	99.13 218	99.67 170

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	99.84 108	98.05 112	99.91 136	99.58 47	99.94 30	99.52 235

DPE-MVS		99.46 42	99.32 53	99.91 6	99.78 71	99.88 10	99.36 302	99.51 162	98.73 103	99.88 42	99.84 108	98.72 68	99.96 41	98.16 270	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
XVG-OURS		98.73 218	98.68 203	98.88 280	99.70 123	97.73 322	98.92 434	99.55 100	98.52 123	99.45 199	99.84 108	95.27 250	99.91 136	98.08 281	98.84 266	99.00 326

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	99.42 210	99.84 108	96.07 207	99.79 253	99.51 56	99.14 215	99.67 170

ACMMP		99.45 46	99.32 53	99.82 57	99.89 8	99.67 69	99.62 110	99.69 22	98.12 199	99.63 154	99.84 108	98.73 67	99.96 41	98.55 230	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
aaatest				99.87 22	99.88 13	99.81 34	99.69 63	99.87 6	99.34 28	99.90 34	99.83 117		99.95 76	98.83 182	99.89 67	99.83 64

aaEdge-Enhanced		99.56 21	99.46 28	99.86 34	99.80 64	99.81 34	99.37 296	99.70 18	99.18 35	99.83 66	99.83 117	98.74 66	99.93 109	98.83 182	99.89 67	99.83 64

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 43	99.86 25	99.61 87	99.56 155	99.63 46	99.48 3	99.98 13	99.83 117	98.75 61	99.99 4	99.97 2	99.96 17	99.94 17

EI-MVSNet-UG-set		99.58 16	99.57 10	99.64 102	99.78 71	99.14 164	99.60 118	99.45 259	99.01 64	99.90 34	99.83 117	98.98 25	99.93 109	99.59 45	99.95 22	99.86 43

EI-MVSNet		98.67 223	98.67 204	98.68 313	99.35 296	97.97 307	99.50 207	99.38 303	96.93 359	99.20 276	99.83 117	97.87 115	99.36 373	98.38 248	97.56 345	98.71 360

CVMVSNet		98.57 230	98.67 204	98.30 364	99.35 296	95.59 430	99.50 207	99.55 100	98.60 116	99.39 222	99.83 117	94.48 304	99.45 349	98.75 193	98.56 284	99.85 47

mvsmamba		99.06 159	98.96 152	99.36 196	99.47 260	98.64 256	99.70 59	99.05 407	97.61 283	99.65 146	99.83 117	96.54 179	99.92 124	99.19 118	99.62 167	99.51 244

LPG-MVS_test		98.22 256	98.13 255	98.49 337	99.33 302	97.05 356	99.58 139	99.55 100	97.46 301	99.24 264	99.83 117	92.58 366	99.72 286	98.09 277	97.51 350	98.68 374

LGP-MVS_train				98.49 337	99.33 302	97.05 356		99.55 100	97.46 301	99.24 264	99.83 117	92.58 366	99.72 286	98.09 277	97.51 350	98.68 374

SteuartSystems-ACMMP		99.54 24	99.42 32	99.87 22	99.82 53	99.81 34	99.59 129	99.51 162	98.62 113	99.79 81	99.83 117	99.28 5	99.97 29	98.48 234	99.90 56	99.84 54
Skip Steuart: Steuart Systems R&D Blog.
XXY-MVS		98.38 244	98.09 261	99.24 226	99.26 325	99.32 133	99.56 155	99.55 100	97.45 304	98.71 362	99.83 117	93.23 345	99.63 328	98.88 166	96.32 389	98.76 350

viewmanbaseed2359cas		99.18 104	99.07 109	99.50 153	99.62 183	99.01 182	99.50 207	99.52 134	98.25 166	99.68 125	99.82 128	96.93 154	99.80 246	99.15 128	99.11 225	99.70 154

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 43	99.84 38	99.63 83	99.56 155	99.63 46	99.47 6	99.98 13	99.82 128	98.75 61	99.99 4	99.97 2	99.97 9	99.94 17

SR-MVS-dyc-post		99.45 46	99.31 59	99.85 43	99.76 83	99.82 29	99.63 105	99.52 134	98.38 141	99.76 96	99.82 128	98.53 84	99.95 76	98.61 215	99.81 121	99.77 100

RE-MVS-def			99.34 49		99.76 83	99.82 29	99.63 105	99.52 134	98.38 141	99.76 96	99.82 128	98.75 61		98.61 215	99.81 121	99.77 100

test0726					99.85 31	99.89 6	99.62 110	99.50 187	99.10 48	99.86 52	99.82 128	98.94 33

SMA-MVS		99.44 50	99.30 61	99.85 43	99.73 108	99.83 23	99.56 155	99.47 235	97.45 304	99.78 86	99.82 128	99.18 11	99.91 136	98.79 190	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
nrg030		98.64 227	98.42 234	99.28 220	99.05 383	99.69 64	99.81 20	99.46 248	98.04 225	99.01 312	99.82 128	96.69 169	99.38 366	99.34 88	94.59 435	98.78 344

FC-MVSNet-test		98.75 215	98.62 217	99.15 238	99.08 373	99.45 117	99.86 11	99.60 68	98.23 171	98.70 368	99.82 128	96.80 164	99.22 404	99.07 139	96.38 387	98.79 342

EI-MVSNet-Vis-set		99.58 16	99.56 12	99.64 102	99.78 71	99.15 163	99.61 116	99.45 259	99.01 64	99.89 39	99.82 128	99.01 19	99.92 124	99.56 49	99.95 22	99.85 47

APD-MVS_3200maxsize		99.48 37	99.35 47	99.85 43	99.76 83	99.83 23	99.63 105	99.54 109	98.36 145	99.79 81	99.82 128	98.86 42	99.95 76	98.62 212	99.81 121	99.78 98

EU-MVSNet		97.98 294	98.03 268	97.81 416	98.72 436	96.65 391	99.66 84	99.66 32	98.09 206	98.35 407	99.82 128	95.25 253	98.01 490	97.41 353	95.30 419	98.78 344

APD-MVS		99.27 88	99.08 105	99.84 55	99.75 93	99.79 42	99.50 207	99.50 187	97.16 334	99.77 90	99.82 128	98.78 53	99.94 91	97.56 335	99.86 87	99.80 88
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TAMVS		99.12 139	99.08 105	99.24 226	99.46 262	98.55 266	99.51 196	99.46 248	98.09 206	99.45 199	99.82 128	98.34 98	99.51 342	98.70 200	98.93 254	99.67 170

DeepC-MVS_fast	98.69 1	99.49 33	99.39 39	99.77 74	99.63 173	99.59 90	99.36 302	99.46 248	99.07 58	99.79 81	99.82 128	98.85 43	99.92 124	98.68 205	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
MG-MVS		99.13 129	99.02 129	99.45 175	99.57 213	98.63 257	99.07 397	99.34 327	98.99 69	99.61 163	99.82 128	97.98 114	99.87 177	97.00 382	99.80 126	99.85 47

viewdifsd2359ckpt07		99.11 145	99.00 141	99.43 184	99.63 173	98.73 247	99.45 250	99.54 109	98.33 149	99.62 158	99.81 143	96.17 201	99.87 177	99.27 109	99.14 215	99.69 157

diffmvs_AUTHOR		99.19 101	99.10 99	99.48 165	99.64 168	98.85 230	99.32 318	99.48 213	98.50 126	99.81 72	99.81 143	96.82 162	99.88 170	99.40 74	99.12 223	99.71 150

mamba_0408		99.08 154	98.96 152	99.44 180	99.62 183	98.88 221	99.25 352	99.47 235	98.05 218	99.37 227	99.81 143	96.85 156	99.85 192	98.98 149	99.25 199	99.60 204

SSM_04072		99.06 159	98.96 152	99.35 199	99.62 183	98.88 221	99.25 352	99.47 235	98.05 218	99.37 227	99.81 143	96.85 156	99.58 334	98.98 149	99.25 199	99.60 204

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	99.81 143	94.54 301	99.96 41	98.40 246	99.93 32	99.74 118

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	99.81 143	99.27 6	99.96 41	98.85 176	99.80 126	99.81 79

test_one_0601					99.81 58	99.88 10		99.49 201	98.97 76	99.65 146	99.81 143	99.09 15

SED-MVS		99.61 10	99.52 14	99.88 16	99.84 38	99.90 2	99.60 118	99.48 213	99.08 56	99.91 31	99.81 143	99.20 8	99.96 41	98.91 163	99.85 94	99.79 92

test_241102_TWO								99.48 213	99.08 56	99.88 42	99.81 143	98.94 33	99.96 41	98.91 163	99.84 102	99.88 36

OPM-MVS		98.19 260	98.10 258	98.45 347	98.88 409	97.07 354	99.28 336	99.38 303	98.57 118	99.22 269	99.81 143	92.12 378	99.66 313	98.08 281	97.54 347	98.61 413
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
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	99.81 143	98.43 91	99.97 29	98.88 166	99.90 56	99.83 64

FIs		98.78 210	98.63 212	99.23 228	99.18 346	99.54 100	99.83 15	99.59 73	98.28 156	98.79 355	99.81 143	96.75 167	99.37 369	99.08 138	96.38 387	98.78 344

mvs_tets		98.40 243	98.23 247	98.91 269	98.67 445	98.51 274	99.66 84	99.53 125	98.19 179	98.65 377	99.81 143	92.75 356	99.44 354	99.31 95	97.48 356	98.77 348

mvs_anonymous		99.03 166	98.99 143	99.16 234	99.38 289	98.52 272	99.51 196	99.38 303	97.79 259	99.38 224	99.81 143	97.30 132	99.45 349	99.35 83	98.99 251	99.51 244

TSAR-MVS + GP.		99.36 72	99.36 45	99.36 196	99.67 139	98.61 262	99.07 397	99.33 336	99.00 67	99.82 70	99.81 143	99.06 17	99.84 202	99.09 137	99.42 183	99.65 184

EPNet		98.86 192	98.71 199	99.30 213	97.20 495	98.18 293	99.62 110	98.91 431	99.28 32	98.63 380	99.81 143	95.96 214	99.99 4	99.24 113	99.72 150	99.73 128
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ab-mvs		98.86 192	98.63 212	99.54 127	99.64 168	99.19 153	99.44 257	99.54 109	97.77 262	99.30 247	99.81 143	94.20 315	99.93 109	99.17 124	98.82 268	99.49 249

OMC-MVS		99.08 154	99.04 115	99.20 230	99.67 139	98.22 292	99.28 336	99.52 134	98.07 211	99.66 136	99.81 143	97.79 118	99.78 261	97.79 307	99.81 121	99.60 204

viewdifsd2359ckpt13		99.06 159	98.93 160	99.45 175	99.63 173	98.96 193	99.50 207	99.51 162	97.83 253	99.28 251	99.80 161	96.68 171	99.71 293	99.05 141	99.12 223	99.68 163

icg_test_0407_2		98.79 209	98.86 178	98.57 325	99.55 221	96.93 370	99.07 397	99.44 268	98.05 218	99.66 136	99.80 161	97.13 140	99.18 413	98.15 272	98.92 256	99.60 204

IMVS_0407		98.86 192	98.91 165	98.72 306	99.55 221	96.93 370	99.50 207	99.44 268	98.05 218	99.66 136	99.80 161	97.13 140	99.65 318	98.15 272	98.92 256	99.60 204

IMVS_0404		98.53 231	98.52 229	98.55 331	99.55 221	96.93 370	99.20 369	99.44 268	98.05 218	98.96 323	99.80 161	94.66 293	99.13 421	98.15 272	98.92 256	99.60 204

IMVS_0403		98.86 192	98.89 171	98.78 301	99.55 221	96.93 370	99.58 139	99.44 268	98.05 218	99.68 125	99.80 161	96.81 163	99.80 246	98.15 272	98.92 256	99.60 204

MM		99.40 64	99.28 68	99.74 80	99.67 139	99.31 137	99.52 186	98.87 439	99.55 1	99.74 101	99.80 161	96.47 182	99.98 20	99.97 2	99.97 9	99.94 17

test_fmvs2		97.25 385	97.30 367	97.09 447	99.43 270	93.31 482	99.73 52	98.87 439	98.83 89	99.28 251	99.80 161	84.45 480	99.66 313	97.88 295	97.45 357	98.30 452

tt0805		97.97 297	97.77 299	98.57 325	99.59 205	96.61 393	99.45 250	99.08 401	98.21 174	98.88 337	99.80 161	88.66 438	99.70 301	98.58 221	97.72 335	99.39 278

SF-MVS		99.38 67	99.24 77	99.79 68	99.79 69	99.68 65	99.57 147	99.54 109	97.82 258	99.71 118	99.80 161	98.95 31	99.93 109	98.19 266	99.84 102	99.74 118

DVP-MVS		99.57 20	99.47 24	99.88 16	99.85 31	99.89 6	99.57 147	99.37 313	99.10 48	99.81 72	99.80 161	98.94 33	99.96 41	98.93 160	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_THIRD									98.99 69	99.81 72	99.80 161	99.09 15	99.96 41	98.85 176	99.90 56	99.88 36

jajsoiax		98.43 237	98.28 244	98.88 280	98.60 454	98.43 283	99.82 16	99.53 125	98.19 179	98.63 380	99.80 161	93.22 347	99.44 354	99.22 114	97.50 352	98.77 348

PGM-MVS		99.45 46	99.31 59	99.86 34	99.87 20	99.78 48	99.58 139	99.65 39	97.84 252	99.71 118	99.80 161	99.12 14	99.97 29	98.33 255	99.87 79	99.83 64

TransMVSNet (Re)		97.15 389	96.58 396	98.86 287	99.12 362	98.85 230	99.49 224	98.91 431	95.48 432	97.16 456	99.80 161	93.38 340	99.11 428	94.16 455	91.73 477	98.62 404

K. test v3		97.10 391	96.79 392	98.01 389	98.72 436	96.33 403	99.87 8	97.05 509	97.59 284	96.16 471	99.80 161	88.71 436	99.04 439	96.69 400	96.55 384	98.65 393

DELS-MVS		99.48 37	99.42 32	99.65 96	99.72 112	99.40 123	99.05 404	99.66 32	99.14 40	99.57 174	99.80 161	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
CSCG		99.32 78	99.32 53	99.32 206	99.85 31	98.29 288	99.71 58	99.66 32	98.11 201	99.41 215	99.80 161	98.37 97	99.96 41	98.99 148	99.96 17	99.72 138

mvs5depth		96.66 401	96.22 406	97.97 394	97.00 500	96.28 405	98.66 470	99.03 411	96.61 381	96.93 462	99.79 178	87.20 456	99.47 345	96.65 404	94.13 445	98.16 461

SR-MVS		99.43 53	99.29 65	99.86 34	99.75 93	99.83 23	99.59 129	99.62 52	98.21 174	99.73 103	99.79 178	98.68 71	99.96 41	98.44 241	99.77 139	99.79 92

MP-MVS-pluss		99.37 68	99.20 85	99.88 16	99.90 4	99.87 17	99.30 325	99.52 134	97.18 332	99.60 166	99.79 178	98.79 52	99.95 76	98.83 182	99.91 45	99.83 64
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
pm-mvs1		97.68 350	97.28 370	98.88 280	99.06 379	98.62 259	99.50 207	99.45 259	96.32 402	97.87 436	99.79 178	92.47 370	99.35 376	97.54 337	93.54 455	98.67 382

LFMVS		97.90 306	97.35 357	99.54 127	99.52 235	99.01 182	99.39 287	98.24 488	97.10 342	99.65 146	99.79 178	84.79 478	99.91 136	99.28 106	98.38 294	99.69 157

TinyColmap		97.12 390	96.89 390	97.83 413	99.07 376	95.52 434	98.57 478	98.74 459	97.58 286	97.81 439	99.79 178	88.16 446	99.56 337	95.10 440	97.21 370	98.39 448

ACMP	97.20 11	98.06 277	97.94 279	98.45 347	99.37 292	97.01 363	99.44 257	99.49 201	97.54 294	98.45 398	99.79 178	91.95 382	99.72 286	97.91 293	97.49 355	98.62 404
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
fmvsm_s_conf0.5_n_6		99.54 24	99.44 31	99.85 43	99.51 238	99.67 69	99.50 207	99.64 42	99.43 19	99.98 13	99.78 185	97.26 137	99.95 76	99.95 16	99.93 32	99.92 25

GeoE		98.85 201	98.62 217	99.53 135	99.61 194	99.08 172	99.80 25	99.51 162	97.10 342	99.31 243	99.78 185	95.23 255	99.77 266	98.21 264	99.03 247	99.75 113

9.14			99.10 99		99.72 112		99.40 283	99.51 162	97.53 295	99.64 151	99.78 185	98.84 45	99.91 136	97.63 326	99.82 118

MGCNet		99.15 117	98.96 152	99.73 83	98.92 403	99.37 125	99.37 296	96.92 511	99.51 2	99.66 136	99.78 185	96.69 169	99.97 29	99.84 28	99.97 9	99.84 54

pmmvs6		96.53 405	96.09 410	97.82 415	98.69 443	95.47 435	99.37 296	99.47 235	93.46 466	97.41 446	99.78 185	87.06 460	99.33 379	96.92 391	92.70 471	98.65 393

MSLP-MVS++		99.46 42	99.47 24	99.44 180	99.60 201	99.16 158	99.41 275	99.71 16	98.98 72	99.45 199	99.78 185	99.19 10	99.54 340	99.28 106	99.84 102	99.63 196

VNet		99.11 145	98.90 167	99.73 83	99.52 235	99.56 96	99.41 275	99.39 294	99.01 64	99.74 101	99.78 185	95.56 238	99.92 124	99.52 55	98.18 314	99.72 138

114514_t		98.93 182	98.67 204	99.72 86	99.85 31	99.53 103	99.62 110	99.59 73	92.65 478	99.71 118	99.78 185	98.06 111	99.90 149	98.84 179	99.91 45	99.74 118

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	97.91 241	99.36 233	99.78 185	95.49 241	99.43 358	97.91 293	99.11 225	99.62 199

UniMVSNet_ETH3D		97.32 382	96.81 391	98.87 284	99.40 282	97.46 334	99.51 196	99.53 125	95.86 428	98.54 390	99.77 194	82.44 491	99.66 313	98.68 205	97.52 349	99.50 248

anonymousdsp		98.44 236	98.28 244	98.94 261	98.50 461	98.96 193	99.77 35	99.50 187	97.07 344	98.87 340	99.77 194	94.76 282	99.28 386	98.66 207	97.60 341	98.57 426

CDS-MVSNet		99.09 152	99.03 118	99.25 223	99.42 272	98.73 247	99.45 250	99.46 248	98.11 201	99.46 198	99.77 194	98.01 113	99.37 369	98.70 200	98.92 256	99.66 177
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MSDG		98.98 177	98.80 186	99.53 135	99.76 83	99.19 153	98.75 460	99.55 100	97.25 325	99.47 196	99.77 194	97.82 117	99.87 177	96.93 389	99.90 56	99.54 229

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	99.76 198	95.80 227	99.99 4	99.30 98	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	99.76 198	95.80 227	99.99 4	99.30 98	98.72 274	99.73 128

CHOSEN 280x420		99.12 139	99.13 94	99.08 242	99.66 151	97.89 315	98.43 492	99.71 16	98.88 84	99.62 158	99.76 198	96.63 172	99.70 301	99.46 68	99.99 1	99.66 177

PS-MVSNAJss		98.92 183	98.92 161	98.90 271	98.78 425	98.53 268	99.78 33	99.54 109	98.07 211	99.00 316	99.76 198	99.01 19	99.37 369	99.13 129	97.23 369	98.81 341

MVS_Test		99.10 151	98.97 148	99.48 165	99.49 252	99.14 164	99.67 77	99.34 327	97.31 320	99.58 171	99.76 198	97.65 122	99.82 233	98.87 169	99.07 242	99.46 263

TestfortrainingZip				99.69 89	99.58 207	99.62 84	99.69 63	99.38 303	98.98 72	99.84 56	99.75 203	98.84 45	99.78 261		99.21 203	99.66 177

CANet_DTU		98.97 179	98.87 175	99.25 223	99.33 302	98.42 285	99.08 396	99.30 356	99.16 37	99.43 207	99.75 203	95.27 250	99.97 29	98.56 227	99.95 22	99.36 283

mPP-MVS		99.44 50	99.30 61	99.86 34	99.88 13	99.79 42	99.69 63	99.48 213	98.12 199	99.50 191	99.75 203	98.78 53	99.97 29	98.57 224	99.89 67	99.83 64

HPM-MVS_fast		99.51 29	99.40 37	99.85 43	99.91 1	99.79 42	99.76 38	99.56 90	97.72 269	99.76 96	99.75 203	99.13 13	99.92 124	99.07 139	99.92 38	99.85 47

HyFIR lowres test		99.11 145	98.92 161	99.65 96	99.90 4	99.37 125	99.02 412	99.91 3	97.67 277	99.59 170	99.75 203	95.90 221	99.73 282	99.53 53	99.02 249	99.86 43

ITE_SJBPF				98.08 384	99.29 315	96.37 401		98.92 426	98.34 147	98.83 348	99.75 203	91.09 407	99.62 329	95.82 421	97.40 363	98.25 456

test_241102_ONE					99.84 38	99.90 2		99.48 213	99.07 58	99.91 31	99.74 209	99.20 8	99.76 270

Anonymous202405211		98.30 252	97.98 273	99.26 222	99.57 213	98.16 294	99.41 275	98.55 478	96.03 425	99.19 279	99.74 209	91.87 383	99.92 124	99.16 127	98.29 304	99.70 154

tttt0517		98.42 238	98.14 253	99.28 220	99.66 151	98.38 286	99.74 48	96.85 512	97.68 275	99.79 81	99.74 209	91.39 399	99.89 165	98.83 182	99.56 172	99.57 222

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	99.37 227	99.74 209	98.81 49	99.94 91	98.79 190	99.86 87	99.84 54

MP-MVS		99.33 77	99.15 92	99.87 22	99.88 13	99.82 29	99.66 84	99.46 248	98.09 206	99.48 195	99.74 209	98.29 100	99.96 41	97.93 292	99.87 79	99.82 72
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVS_111021_LR		99.41 59	99.33 51	99.65 96	99.77 79	99.51 109	98.94 432	99.85 8	98.82 90	99.65 146	99.74 209	98.51 86	99.80 246	98.83 182	99.89 67	99.64 191

VPNet		97.84 317	97.44 345	99.01 250	99.21 338	98.94 203	99.48 232	99.57 85	98.38 141	99.28 251	99.73 215	88.89 433	99.39 364	99.19 118	93.27 459	98.71 360

MVSTER		98.49 232	98.32 241	99.00 252	99.35 296	99.02 180	99.54 175	99.38 303	97.41 312	99.20 276	99.73 215	93.86 332	99.36 373	98.87 169	97.56 345	98.62 404

MVS_111021_HR		99.41 59	99.32 53	99.66 92	99.72 112	99.47 115	98.95 430	99.85 8	98.82 90	99.54 183	99.73 215	98.51 86	99.74 276	98.91 163	99.88 73	99.77 100

PHI-MVS		99.30 82	99.17 90	99.70 87	99.56 217	99.52 107	99.58 139	99.80 10	97.12 338	99.62 158	99.73 215	98.58 79	99.90 149	98.61 215	99.91 45	99.68 163

tt0320-xc		95.31 435	94.59 439	97.45 435	98.92 403	94.73 457	99.20 369	99.31 351	86.74 508	97.23 452	99.72 219	81.14 497	98.95 463	97.08 378	91.98 476	98.67 382

tt0320		95.71 424	95.07 429	97.62 427	99.05 383	95.02 450	99.25 352	99.52 134	86.81 507	97.97 431	99.72 219	83.58 485	99.15 416	96.38 412	93.35 456	98.68 374

IterMVS-SCA-FT		97.82 323	97.75 304	98.06 385	99.57 213	96.36 402	99.02 412	99.49 201	97.18 332	98.71 362	99.72 219	92.72 359	99.14 418	97.44 351	95.86 404	98.67 382

diffmvs		99.14 125	99.02 129	99.51 147	99.61 194	98.96 193	99.28 336	99.49 201	98.46 130	99.72 108	99.71 222	96.50 181	99.88 170	99.31 95	99.11 225	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
XVG-OURS-SEG-HR		98.69 220	98.62 217	98.89 275	99.71 118	97.74 321	99.12 387	99.54 109	98.44 135	99.42 210	99.71 222	94.20 315	99.92 124	98.54 231	98.90 262	99.00 326

EPNet_dtu		98.03 285	97.96 275	98.23 373	98.27 468	95.54 433	99.23 360	98.75 455	99.02 62	97.82 438	99.71 222	96.11 205	99.48 343	93.04 472	99.65 163	99.69 157
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNVR-MVS		99.42 55	99.30 61	99.78 71	99.62 183	99.71 59	99.26 350	99.52 134	98.82 90	99.39 222	99.71 222	98.96 26	99.85 192	98.59 220	99.80 126	99.77 100

VortexMVS		98.67 223	98.66 207	98.68 313	99.62 183	97.96 309	99.59 129	99.41 284	98.13 191	99.31 243	99.70 226	95.48 242	99.27 389	99.40 74	97.32 366	98.79 342

FE-MVS		98.48 233	98.17 249	99.40 189	99.54 228	98.96 193	99.68 73	98.81 447	95.54 431	99.62 158	99.70 226	93.82 333	99.93 109	97.35 357	99.46 180	99.32 289

PC_three_1452									98.18 182	99.84 56	99.70 226	99.31 3	98.52 480	98.30 259	99.80 126	99.81 79

OPU-MVS				99.64 102	99.56 217	99.72 57	99.60 118				99.70 226	99.27 6	99.42 361	98.24 263	99.80 126	99.79 92

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	99.70 226	98.65 75	99.79 253	99.65 41	99.78 135	99.41 274

tfpnnormal		97.84 317	97.47 337	98.98 254	99.20 340	99.22 151	99.64 98	99.61 61	96.32 402	98.27 414	99.70 226	93.35 343	99.44 354	95.69 427	95.40 417	98.27 454

v7n		97.87 310	97.52 328	98.92 265	98.76 432	98.58 264	99.84 12	99.46 248	96.20 411	98.91 331	99.70 226	94.89 270	99.44 354	96.03 417	93.89 451	98.75 352

testdata				99.54 127	99.75 93	98.95 199		99.51 162	97.07 344	99.43 207	99.70 226	98.87 41	99.94 91	97.76 312	99.64 164	99.72 138

IterMVS		97.83 320	97.77 299	98.02 388	99.58 207	96.27 406	99.02 412	99.48 213	97.22 329	98.71 362	99.70 226	92.75 356	99.13 421	97.46 347	96.00 398	98.67 382
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PCF-MVS	97.08 14	97.66 354	97.06 384	99.47 171	99.61 194	99.09 169	98.04 510	99.25 374	91.24 492	98.51 392	99.70 226	94.55 300	99.91 136	92.76 477	99.85 94	99.42 271
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
LTVRE_ROB	97.16 12	98.02 287	97.90 282	98.40 355	99.23 333	96.80 383	99.70 59	99.60 68	97.12 338	98.18 420	99.70 226	91.73 388	99.72 286	98.39 247	97.45 357	98.68 374
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
viewdifsd2359ckpt09		99.01 173	98.87 175	99.40 189	99.62 183	98.79 241	99.44 257	99.51 162	97.76 264	99.35 236	99.69 237	96.42 187	99.75 273	98.97 154	99.11 225	99.66 177

BP-MVS1		99.12 139	98.94 158	99.65 96	99.51 238	99.30 140	99.67 77	98.92 426	98.48 128	99.84 56	99.69 237	94.96 262	99.92 124	99.62 44	99.79 133	99.71 150

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	99.69 237	98.55 82	99.82 233	99.69 34	99.85 94	99.48 252

HFP-MVS		99.49 33	99.37 43	99.86 34	99.87 20	99.80 39	99.66 84	99.67 27	98.15 184	99.68 125	99.69 237	99.06 17	99.96 41	98.69 203	99.87 79	99.84 54

旧先验1					99.74 101	99.59 90		99.54 109			99.69 237	98.47 88			99.68 158	99.73 128

ACMMPR		99.49 33	99.36 45	99.86 34	99.87 20	99.79 42	99.66 84	99.67 27	98.15 184	99.67 131	99.69 237	98.95 31	99.96 41	98.69 203	99.87 79	99.84 54

CPTT-MVS		99.11 145	98.90 167	99.74 80	99.80 64	99.46 116	99.59 129	99.49 201	97.03 350	99.63 154	99.69 237	97.27 134	99.96 41	97.82 303	99.84 102	99.81 79

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	99.69 237	98.20 104	99.70 301	99.64 43	99.82 118	99.54 229

dtuonly		98.37 246	98.26 246	98.69 311	99.07 376	96.81 382	98.51 486	98.75 455	97.77 262	99.57 174	99.68 245	96.12 204	99.71 293	95.76 424	99.11 225	99.57 222

GST-MVS		99.40 64	99.24 77	99.85 43	99.86 25	99.79 42	99.60 118	99.67 27	97.97 236	99.63 154	99.68 245	98.52 85	99.95 76	98.38 248	99.86 87	99.81 79

Anonymous20231211		97.88 308	97.54 326	98.90 271	99.71 118	98.53 268	99.48 232	99.57 85	94.16 455	98.81 351	99.68 245	93.23 345	99.42 361	98.84 179	94.42 439	98.76 350

region2R		99.48 37	99.35 47	99.87 22	99.88 13	99.80 39	99.65 90	99.66 32	98.13 191	99.66 136	99.68 245	98.96 26	99.96 41	98.62 212	99.87 79	99.84 54

PS-CasMVS		97.93 300	97.59 322	98.95 259	98.99 393	99.06 175	99.68 73	99.52 134	97.13 336	98.31 410	99.68 245	92.44 374	99.05 438	98.51 232	94.08 448	98.75 352

HY-MVS	97.30 7	98.85 201	98.64 211	99.47 171	99.42 272	99.08 172	99.62 110	99.36 315	97.39 314	99.28 251	99.68 245	96.44 185	99.92 124	98.37 250	98.22 308	99.40 277

DP-MVS Recon		99.12 139	98.95 156	99.65 96	99.74 101	99.70 61	99.27 341	99.57 85	96.40 400	99.42 210	99.68 245	98.75 61	99.80 246	97.98 289	99.72 150	99.44 268

ADS-MVSNet2		98.02 287	98.07 265	97.87 403	99.33 302	95.19 445	99.23 360	99.08 401	96.24 408	99.10 295	99.67 252	94.11 320	98.93 465	96.81 394	99.05 244	99.48 252

ADS-MVSNet		98.20 259	98.08 262	98.56 329	99.33 302	96.48 397	99.23 360	99.15 392	96.24 408	99.10 295	99.67 252	94.11 320	99.71 293	96.81 394	99.05 244	99.48 252

DTE-MVSNet		97.51 366	97.19 376	98.46 345	98.63 449	98.13 297	99.84 12	99.48 213	96.68 373	97.97 431	99.67 252	92.92 352	98.56 479	96.88 393	92.60 473	98.70 365

Baseline_NR-MVSNet		97.76 332	97.45 340	98.68 313	99.09 370	98.29 288	99.41 275	98.85 442	95.65 430	98.63 380	99.67 252	94.82 273	99.10 431	98.07 284	92.89 468	98.64 395

CMPMVS	69.68 23	94.13 454	94.90 432	91.84 490	97.24 494	80.01 528	98.52 484	99.48 213	89.01 501	91.99 504	99.67 252	85.67 469	99.13 421	95.44 433	97.03 375	96.39 515
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
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	99.66 257	95.14 258	99.93 109	98.97 154	99.50 178	99.64 191

原ACMM1				99.65 96	99.73 108	99.33 132		99.47 235	97.46 301	99.12 290	99.66 257	98.67 73	99.91 136	97.70 322	99.69 155	99.71 150

thisisatest0530		98.35 248	98.03 268	99.31 208	99.63 173	98.56 265	99.54 175	96.75 514	97.53 295	99.73 103	99.65 259	91.25 403	99.89 165	98.62 212	99.56 172	99.48 252

test222					99.75 93	99.49 111	98.91 437	99.49 201	96.42 398	99.34 240	99.65 259	98.28 101			99.69 155	99.72 138

MVSFormer		99.17 109	99.12 96	99.29 216	99.51 238	98.94 203	99.88 4	99.46 248	97.55 290	99.80 78	99.65 259	97.39 126	99.28 386	99.03 144	99.85 94	99.65 184

jason		99.13 129	99.03 118	99.45 175	99.46 262	98.87 225	99.12 387	99.26 371	98.03 227	99.79 81	99.65 259	97.02 149	99.85 192	99.02 146	99.90 56	99.65 184
jason: jason.
BH-RMVSNet		98.41 240	98.08 262	99.40 189	99.41 277	98.83 235	99.30 325	98.77 454	97.70 273	98.94 327	99.65 259	92.91 354	99.74 276	96.52 406	99.55 174	99.64 191

sss		99.17 109	99.05 113	99.53 135	99.62 183	98.97 189	99.36 302	99.62 52	97.83 253	99.67 131	99.65 259	97.37 129	99.95 76	99.19 118	99.19 206	99.68 163

h-mvs33		97.70 346	97.28 370	98.97 256	99.70 123	97.27 341	99.36 302	99.45 259	98.94 79	99.66 136	99.64 265	94.93 265	99.99 4	99.48 64	84.36 507	99.65 184

ZNCC-MVS		99.47 40	99.33 51	99.87 22	99.87 20	99.81 34	99.64 98	99.67 27	98.08 210	99.55 182	99.64 265	98.91 38	99.96 41	98.72 198	99.90 56	99.82 72

新几何1				99.75 77	99.75 93	99.59 90		99.54 109	96.76 368	99.29 250	99.64 265	98.43 91	99.94 91	96.92 391	99.66 161	99.72 138

PEN-MVS		97.76 332	97.44 345	98.72 306	98.77 430	98.54 267	99.78 33	99.51 162	97.06 346	98.29 413	99.64 265	92.63 365	98.89 469	98.09 277	93.16 462	98.72 358

CP-MVSNet		98.09 271	97.78 297	99.01 250	98.97 398	99.24 149	99.67 77	99.46 248	97.25 325	98.48 395	99.64 265	93.79 334	99.06 437	98.63 211	94.10 447	98.74 356

LF4IMVS		97.52 364	97.46 339	97.70 424	98.98 396	95.55 431	99.29 330	98.82 445	98.07 211	98.66 371	99.64 265	89.97 422	99.61 331	97.01 381	96.68 379	97.94 480

HPM-MVS		99.42 55	99.28 68	99.83 56	99.90 4	99.72 57	99.81 20	99.54 109	97.59 284	99.68 125	99.63 271	98.91 38	99.94 91	98.58 221	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
NCCC		99.34 75	99.19 87	99.79 68	99.61 194	99.65 76	99.30 325	99.48 213	98.86 85	99.21 272	99.63 271	98.72 68	99.90 149	98.25 262	99.63 166	99.80 88

CP-MVS		99.45 46	99.32 53	99.85 43	99.83 47	99.75 52	99.69 63	99.52 134	98.07 211	99.53 185	99.63 271	98.93 37	99.97 29	98.74 195	99.91 45	99.83 64

AdaColmap		99.01 173	98.80 186	99.66 92	99.56 217	99.54 100	99.18 374	99.70 18	98.18 182	99.35 236	99.63 271	96.32 190	99.90 149	97.48 344	99.77 139	99.55 227

TAPA-MVS	97.07 15	97.74 338	97.34 360	98.94 261	99.70 123	97.53 331	99.25 352	99.51 162	91.90 487	99.30 247	99.63 271	98.78 53	99.64 322	88.09 503	99.87 79	99.65 184
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ppachtmachnet_test		97.49 372	97.45 340	97.61 430	98.62 450	95.24 443	98.80 452	99.46 248	96.11 420	98.22 417	99.62 276	96.45 184	98.97 460	93.77 459	95.97 402	98.61 413

MCST-MVS		99.43 53	99.30 61	99.82 57	99.79 69	99.74 55	99.29 330	99.40 291	98.79 96	99.52 188	99.62 276	98.91 38	99.90 149	98.64 209	99.75 144	99.82 72

WTY-MVS		99.06 159	98.88 174	99.61 110	99.62 183	99.16 158	99.37 296	99.56 90	98.04 225	99.53 185	99.62 276	96.84 161	99.94 91	98.85 176	98.49 289	99.72 138

MDTV_nov1_ep13			98.32 241		99.11 364	94.44 466	99.27 341	98.74 459	97.51 298	99.40 220	99.62 276	94.78 278	99.76 270	97.59 329	98.81 270

CANet		99.25 95	99.14 93	99.59 114	99.41 277	99.16 158	99.35 307	99.57 85	98.82 90	99.51 190	99.61 280	96.46 183	99.95 76	99.59 45	99.98 4	99.65 184

HQP_MVS		98.27 255	98.22 248	98.44 350	99.29 315	96.97 367	99.39 287	99.47 235	98.97 76	99.11 292	99.61 280	92.71 361	99.69 307	97.78 308	97.63 338	98.67 382

plane_prior4											99.61 280

baseline1		98.31 250	97.95 277	99.38 195	99.50 250	98.74 246	99.59 129	98.93 423	98.41 138	99.14 287	99.60 283	94.59 296	99.79 253	98.48 234	93.29 458	99.61 201

TranMVSNet+NR-MVSNet		97.93 300	97.66 313	98.76 303	98.78 425	98.62 259	99.65 90	99.49 201	97.76 264	98.49 394	99.60 283	94.23 314	98.97 460	98.00 288	92.90 467	98.70 365

FA-MVS(test-final)		98.75 215	98.53 228	99.41 187	99.55 221	99.05 177	99.80 25	99.01 414	96.59 386	99.58 171	99.59 285	95.39 244	99.90 149	97.78 308	99.49 179	99.28 294

tpmrst		98.33 249	98.48 231	97.90 401	99.16 356	94.78 456	99.31 323	99.11 397	97.27 323	99.45 199	99.59 285	95.33 248	99.84 202	98.48 234	98.61 278	99.09 313

IterMVS-LS		98.46 235	98.42 234	98.58 324	99.59 205	98.00 305	99.37 296	99.43 279	96.94 358	99.07 301	99.59 285	97.87 115	99.03 441	98.32 257	95.62 411	98.71 360
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
F-COLMAP		99.19 101	99.04 115	99.64 102	99.78 71	99.27 145	99.42 270	99.54 109	97.29 322	99.41 215	99.59 285	98.42 93	99.93 109	98.19 266	99.69 155	99.73 128

ttmdpeth		97.80 327	97.63 318	98.29 365	98.77 430	97.38 337	99.64 98	99.36 315	98.78 99	96.30 469	99.58 289	92.34 377	99.39 364	98.36 252	95.58 412	98.10 464

pmmvs4		98.13 267	97.90 282	98.81 296	98.61 452	98.87 225	98.99 420	99.21 384	96.44 396	99.06 306	99.58 289	95.90 221	99.11 428	97.18 373	96.11 395	98.46 441

1112_ss		98.98 177	98.77 191	99.59 114	99.68 136	99.02 180	99.25 352	99.48 213	97.23 328	99.13 288	99.58 289	96.93 154	99.90 149	98.87 169	98.78 271	99.84 54

ab-mvs-re		8.30 524	11.06 527	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	99.58 289	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

PatchmatchNet		98.31 250	98.36 237	98.19 375	99.16 356	95.32 442	99.27 341	98.92 426	97.37 315	99.37 227	99.58 289	94.90 269	99.70 301	97.43 352	99.21 203	99.54 229
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SCA		98.19 260	98.16 250	98.27 370	99.30 311	95.55 431	99.07 397	98.97 419	97.57 287	99.43 207	99.57 294	92.72 359	99.74 276	97.58 330	99.20 205	99.52 235

Patchmatch-test		97.93 300	97.65 314	98.77 302	99.18 346	97.07 354	99.03 409	99.14 394	96.16 415	98.74 359	99.57 294	94.56 298	99.72 286	93.36 467	99.11 225	99.52 235

PVSNet	96.02 17	98.85 201	98.84 183	98.89 275	99.73 108	97.28 340	98.32 498	99.60 68	97.86 246	99.50 191	99.57 294	96.75 167	99.86 184	98.56 227	99.70 154	99.54 229

cdsmvs_eth3d_5k		24.64 523	32.85 526	0.00 541	0.00 565	0.00 568	0.00 553	99.51 162	0.00 560	0.00 561	99.56 297	96.58 176	0.00 562	0.00 560	0.00 560	0.00 557

1314		98.68 222	98.54 227	99.11 241	98.89 407	98.65 254	99.27 341	99.49 201	96.89 360	97.99 429	99.56 297	97.72 121	99.83 224	97.74 315	99.27 196	98.84 340

lupinMVS		99.13 129	99.01 137	99.46 173	99.51 238	98.94 203	99.05 404	99.16 391	97.86 246	99.80 78	99.56 297	97.39 126	99.86 184	98.94 157	99.85 94	99.58 219

miper_lstm_enhance		98.00 292	97.91 281	98.28 369	99.34 301	97.43 335	98.88 439	99.36 315	96.48 393	98.80 353	99.55 300	95.98 213	98.91 466	97.27 363	95.50 416	98.51 434

DPM-MVS		98.95 181	98.71 199	99.66 92	99.63 173	99.55 98	98.64 472	99.10 398	97.93 239	99.42 210	99.55 300	98.67 73	99.80 246	95.80 423	99.68 158	99.61 201

CDPH-MVS		99.13 129	98.91 165	99.80 64	99.75 93	99.71 59	99.15 380	99.41 284	96.60 384	99.60 166	99.55 300	98.83 47	99.90 149	97.48 344	99.83 114	99.78 98

dp		97.75 336	97.80 293	97.59 431	99.10 367	93.71 476	99.32 318	98.88 437	96.48 393	99.08 300	99.55 300	92.67 364	99.82 233	96.52 406	98.58 281	99.24 300

CLD-MVS		98.16 264	98.10 258	98.33 360	99.29 315	96.82 381	98.75 460	99.44 268	97.83 253	99.13 288	99.55 300	92.92 352	99.67 310	98.32 257	97.69 336	98.48 436
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ArgMatch-SfM		96.18 413	95.78 418	97.38 439	99.08 373	94.64 462	99.20 369	99.33 336	98.01 231	98.54 390	99.54 305	83.13 487	99.43 358	93.86 458	91.29 479	98.08 466

ZD-MVS					99.71 118	99.79 42		99.61 61	96.84 363	99.56 176	99.54 305	98.58 79	99.96 41	96.93 389	99.75 144

cl____		98.01 290	97.84 290	98.55 331	99.25 329	97.97 307	98.71 465	99.34 327	96.47 395	98.59 387	99.54 305	95.65 235	99.21 409	97.21 367	95.77 405	98.46 441

DIV-MVS_self_test		98.01 290	97.85 289	98.48 339	99.24 331	97.95 312	98.71 465	99.35 322	96.50 389	98.60 386	99.54 305	95.72 233	99.03 441	97.21 367	95.77 405	98.46 441

MVS		97.28 383	96.55 397	99.48 165	98.78 425	98.95 199	99.27 341	99.39 294	83.53 515	98.08 424	99.54 305	96.97 152	99.87 177	94.23 453	99.16 208	99.63 196

ArgMatch-Sym		96.59 403	96.31 403	97.42 436	98.89 407	94.84 455	99.16 376	99.39 294	98.11 201	98.35 407	99.53 310	84.38 481	99.40 363	94.16 455	94.85 432	98.03 471

SSC-MVS3.2		97.34 380	97.15 377	97.93 398	99.02 387	95.76 425	99.48 232	99.58 78	97.62 282	99.09 298	99.53 310	87.95 449	99.27 389	96.42 409	95.66 410	98.75 352

pmmvs5		97.52 364	97.30 367	98.16 377	98.57 457	96.73 385	99.27 341	98.90 433	96.14 418	98.37 403	99.53 310	91.54 395	99.14 418	97.51 341	95.87 403	98.63 402

HPM-MVS++		99.39 66	99.23 81	99.87 22	99.75 93	99.84 20	99.43 263	99.51 162	98.68 110	99.27 257	99.53 310	98.64 76	99.96 41	98.44 241	99.80 126	99.79 92

PatchMatch-RL		98.84 204	98.62 217	99.52 142	99.71 118	99.28 143	99.06 401	99.77 12	97.74 268	99.50 191	99.53 310	95.41 243	99.84 202	97.17 374	99.64 164	99.44 268

MonoMVSNet		98.38 244	98.47 232	98.12 382	98.59 456	96.19 410	99.72 54	98.79 452	97.89 243	99.44 204	99.52 315	96.13 203	98.90 468	98.64 209	97.54 347	99.28 294

eth_miper_zixun_eth		98.05 282	97.96 275	98.33 360	99.26 325	97.38 337	98.56 482	99.31 351	96.65 376	98.88 337	99.52 315	96.58 176	99.12 427	97.39 354	95.53 415	98.47 438

test_prior2							98.96 427		98.34 147	99.01 312	99.52 315	98.68 71		97.96 290	99.74 147

test_0402		96.64 402	96.24 405	97.85 407	98.85 416	96.43 400	99.44 257	99.26 371	93.52 464	96.98 460	99.52 315	88.52 442	99.20 411	92.58 480	97.50 352	97.93 481

test_yl		98.86 192	98.63 212	99.54 127	99.49 252	99.18 155	99.50 207	99.07 404	98.22 172	99.61 163	99.51 319	95.37 245	99.84 202	98.60 218	98.33 297	99.59 215

DCV-MVSNet		98.86 192	98.63 212	99.54 127	99.49 252	99.18 155	99.50 207	99.07 404	98.22 172	99.61 163	99.51 319	95.37 245	99.84 202	98.60 218	98.33 297	99.59 215

v148		97.79 329	97.55 323	98.50 336	98.74 433	97.72 323	99.54 175	99.33 336	96.26 407	98.90 333	99.51 319	94.68 290	99.14 418	97.83 302	93.15 463	98.63 402

DU-MVS		98.08 275	97.79 294	98.96 257	98.87 412	98.98 185	99.41 275	99.45 259	97.87 245	98.71 362	99.50 322	94.82 273	99.22 404	98.57 224	92.87 469	98.68 374

NR-MVSNet		97.97 297	97.61 320	99.02 249	98.87 412	99.26 146	99.47 242	99.42 281	97.63 280	97.08 458	99.50 322	95.07 260	99.13 421	97.86 298	93.59 454	98.68 374

XVG-ACMP-BASELINE		97.83 320	97.71 308	98.20 374	99.11 364	96.33 403	99.41 275	99.52 134	98.06 215	99.05 308	99.50 322	89.64 427	99.73 282	97.73 316	97.38 364	98.53 430

dtuonlycased		97.04 393	97.33 363	96.16 465	99.08 373	90.59 497	98.79 454	99.38 303	97.19 331	96.91 463	99.49 325	90.22 420	98.75 474	97.04 380	97.89 327	99.14 305

RoMa-SfM		94.36 452	93.86 453	95.88 469	98.61 452	90.62 496	98.85 443	99.04 408	91.63 489	94.14 488	99.49 325	77.16 501	99.09 433	92.66 478	93.13 464	97.91 483

reproduce_monomvs		97.89 307	97.87 287	97.96 396	99.51 238	95.45 437	99.60 118	99.25 374	99.17 36	98.85 347	99.49 325	89.29 430	99.64 322	99.35 83	96.31 390	98.78 344

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	99.49 325	98.21 103	99.95 76	98.46 239	99.77 139	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
TEST9					99.67 139	99.65 76	99.05 404	99.41 284	96.22 410	98.95 325	99.49 325	98.77 57	99.91 136

train_agg		99.02 168	98.77 191	99.77 74	99.67 139	99.65 76	99.05 404	99.41 284	96.28 404	98.95 325	99.49 325	98.76 58	99.91 136	97.63 326	99.72 150	99.75 113

PVSNet_Blended		99.08 154	98.97 148	99.42 186	99.76 83	98.79 241	98.78 455	99.91 3	96.74 369	99.67 131	99.49 325	97.53 123	99.88 170	98.98 149	99.85 94	99.60 204

CNLPA		99.14 125	98.99 143	99.59 114	99.58 207	99.41 122	99.16 376	99.44 268	98.45 132	99.19 279	99.49 325	98.08 110	99.89 165	97.73 316	99.75 144	99.48 252

test_8					99.67 139	99.61 87	99.03 409	99.41 284	96.28 404	98.93 328	99.48 333	98.76 58	99.91 136

EPMVS		97.82 323	97.65 314	98.35 359	98.88 409	95.98 413	99.49 224	94.71 530	97.57 287	99.26 262	99.48 333	92.46 373	99.71 293	97.87 297	99.08 241	99.35 284

PLC	97.94 4	99.02 168	98.85 181	99.53 135	99.66 151	99.01 182	99.24 357	99.52 134	96.85 362	99.27 257	99.48 333	98.25 102	99.91 136	97.76 312	99.62 167	99.65 184
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
xiu_mvs_v1_base_debu		99.29 84	99.27 72	99.34 200	99.63 173	98.97 189	99.12 387	99.51 162	98.86 85	99.84 56	99.47 336	98.18 105	99.99 4	99.50 57	99.31 193	99.08 314

xiu_mvs_v1_base		99.29 84	99.27 72	99.34 200	99.63 173	98.97 189	99.12 387	99.51 162	98.86 85	99.84 56	99.47 336	98.18 105	99.99 4	99.50 57	99.31 193	99.08 314

xiu_mvs_v1_base_debi		99.29 84	99.27 72	99.34 200	99.63 173	98.97 189	99.12 387	99.51 162	98.86 85	99.84 56	99.47 336	98.18 105	99.99 4	99.50 57	99.31 193	99.08 314

v1921920		97.80 327	97.45 340	98.84 291	98.80 421	98.53 268	99.52 186	99.34 327	96.15 417	99.24 264	99.47 336	93.98 326	99.29 385	95.40 435	95.13 423	98.69 369

MVStest1		96.08 417	95.48 422	97.89 402	98.93 401	96.70 386	99.56 155	99.35 322	92.69 477	91.81 505	99.46 340	89.90 423	98.96 462	95.00 443	92.61 472	98.00 476

UniMVSNet_NR-MVSNet		98.22 256	97.97 274	98.96 257	98.92 403	98.98 185	99.48 232	99.53 125	97.76 264	98.71 362	99.46 340	96.43 186	99.22 404	98.57 224	92.87 469	98.69 369

testgi		97.65 355	97.50 332	98.13 381	99.36 295	96.45 399	99.42 270	99.48 213	97.76 264	97.87 436	99.45 342	91.09 407	98.81 471	94.53 448	98.52 287	99.13 308

EIA-MVS		99.18 104	99.09 104	99.45 175	99.49 252	99.18 155	99.67 77	99.53 125	97.66 278	99.40 220	99.44 343	98.10 108	99.81 238	98.94 157	99.62 167	99.35 284

tpm2		97.44 375	97.34 360	97.74 422	99.15 360	94.36 469	99.45 250	98.94 422	93.45 467	98.90 333	99.44 343	91.35 400	99.59 333	97.31 358	98.07 320	99.29 293

thisisatest0515		98.14 266	97.79 294	99.19 231	99.50 250	98.50 276	98.61 474	96.82 513	96.95 356	99.54 183	99.43 345	91.66 392	99.86 184	98.08 281	99.51 176	99.22 302

WR-MVS		98.06 277	97.73 306	99.06 244	98.86 415	99.25 148	99.19 372	99.35 322	97.30 321	98.66 371	99.43 345	93.94 327	99.21 409	98.58 221	94.28 442	98.71 360

hse-mvs2		97.50 367	97.14 378	98.59 320	99.49 252	97.05 356	99.28 336	99.22 380	98.94 79	99.66 136	99.42 347	94.93 265	99.65 318	99.48 64	83.80 511	99.08 314

v8		97.95 299	97.63 318	98.93 263	98.95 400	98.81 240	99.80 25	99.41 284	96.03 425	99.10 295	99.42 347	94.92 267	99.30 384	96.94 388	94.08 448	98.66 391

tpmvs		97.98 294	98.02 270	97.84 410	99.04 385	94.73 457	99.31 323	99.20 385	96.10 424	98.76 358	99.42 347	94.94 264	99.81 238	96.97 385	98.45 290	98.97 332

UGNet		98.87 189	98.69 202	99.40 189	99.22 337	98.72 249	99.44 257	99.68 24	99.24 33	99.18 283	99.42 347	92.74 358	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
RoMa-HiRes		92.56 465	92.07 468	94.02 477	97.77 485	87.59 505	98.87 441	98.46 481	89.82 496	92.47 500	99.41 351	71.58 512	97.29 503	90.47 491	89.79 494	97.17 502

WBMVS		97.74 338	97.50 332	98.46 345	99.24 331	97.43 335	99.21 366	99.42 281	97.45 304	98.96 323	99.41 351	88.83 434	99.23 397	98.94 157	96.02 396	98.71 360

AUN-MVS		96.88 397	96.31 403	98.59 320	99.48 259	97.04 359	99.27 341	99.22 380	97.44 307	98.51 392	99.41 351	91.97 381	99.66 313	97.71 319	83.83 510	99.07 319

Effi-MVS+		98.81 205	98.59 223	99.48 165	99.46 262	99.12 167	98.08 509	99.50 187	97.50 299	99.38 224	99.41 351	96.37 189	99.81 238	99.11 132	98.54 286	99.51 244

v10		97.85 313	97.52 328	98.86 287	98.99 393	98.67 252	99.75 43	99.41 284	95.70 429	98.98 319	99.41 351	94.75 283	99.23 397	96.01 419	94.63 434	98.67 382

v144192		97.92 303	97.60 321	98.87 284	98.83 419	98.65 254	99.55 170	99.34 327	96.20 411	99.32 242	99.40 356	94.36 308	99.26 392	96.37 413	95.03 425	98.70 365

NP-MVS					99.23 333	96.92 374					99.40 356

HQP-MVS		98.02 287	97.90 282	98.37 358	99.19 343	96.83 379	98.98 423	99.39 294	98.24 168	98.66 371	99.40 356	92.47 370	99.64 322	97.19 371	97.58 343	98.64 395

MAR-MVS		98.86 192	98.63 212	99.54 127	99.37 292	99.66 72	99.45 250	99.54 109	96.61 381	99.01 312	99.40 356	97.09 144	99.86 184	97.68 324	99.53 175	99.10 309
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
SD_0403		97.55 361	97.53 327	97.62 427	99.61 194	93.64 479	99.72 54	99.44 268	98.03 227	98.62 383	99.39 360	96.06 208	99.57 335	87.88 505	99.01 250	99.66 177

dongtai		93.26 459	92.93 463	94.25 476	99.39 285	85.68 509	97.68 517	93.27 534	92.87 475	96.85 464	99.39 360	82.33 492	97.48 501	76.78 528	97.80 332	99.58 219

API-MVS		99.04 164	99.03 118	99.06 244	99.40 282	99.31 137	99.55 170	99.56 90	98.54 121	99.33 241	99.39 360	98.76 58	99.78 261	96.98 384	99.78 135	98.07 467

CR-MVSNet		98.17 263	97.93 280	98.87 284	99.18 346	98.49 277	99.22 364	99.33 336	96.96 354	99.56 176	99.38 363	94.33 311	99.00 450	94.83 446	98.58 281	99.14 305

Patchmtry		97.75 336	97.40 352	98.81 296	99.10 367	98.87 225	99.11 393	99.33 336	94.83 447	98.81 351	99.38 363	94.33 311	99.02 445	96.10 415	95.57 413	98.53 430

BH-untuned		98.42 238	98.36 237	98.59 320	99.49 252	96.70 386	99.27 341	99.13 395	97.24 327	98.80 353	99.38 363	95.75 231	99.74 276	97.07 379	99.16 208	99.33 288

V42		98.06 277	97.79 294	98.86 287	98.98 396	98.84 232	99.69 63	99.34 327	96.53 388	99.30 247	99.37 366	94.67 291	99.32 381	97.57 334	94.66 433	98.42 444

VPA-MVSNet		98.29 253	97.95 277	99.30 213	99.16 356	99.54 100	99.50 207	99.58 78	98.27 158	99.35 236	99.37 366	92.53 368	99.65 318	99.35 83	94.46 436	98.72 358

PVSNet_BlendedMVS		98.86 192	98.80 186	99.03 248	99.76 83	98.79 241	99.28 336	99.91 3	97.42 311	99.67 131	99.37 366	97.53 123	99.88 170	98.98 149	97.29 367	98.42 444

D2MVS		98.41 240	98.50 230	98.15 380	99.26 325	96.62 392	99.40 283	99.61 61	97.71 270	98.98 319	99.36 369	96.04 209	99.67 310	98.70 200	97.41 362	98.15 462

MVP-Stereo		97.81 325	97.75 304	97.99 392	97.53 487	96.60 394	98.96 427	98.85 442	97.22 329	97.23 452	99.36 369	95.28 249	99.46 347	95.51 431	99.78 135	97.92 482
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1240		97.69 347	97.32 365	98.79 299	98.85 416	98.43 283	99.48 232	99.36 315	96.11 420	99.27 257	99.36 369	93.76 336	99.24 396	94.46 449	95.23 420	98.70 365

dmvs_re		98.08 275	98.16 250	97.85 407	99.55 221	94.67 461	99.70 59	98.92 426	98.15 184	99.06 306	99.35 372	93.67 338	99.25 394	97.77 311	97.25 368	99.64 191

v1144		97.98 294	97.69 310	98.85 290	98.87 412	98.66 253	99.54 175	99.35 322	96.27 406	99.23 268	99.35 372	94.67 291	99.23 397	96.73 397	95.16 422	98.68 374

v2v482		98.06 277	97.77 299	98.92 265	98.90 406	98.82 238	99.57 147	99.36 315	96.65 376	99.19 279	99.35 372	94.20 315	99.25 394	97.72 318	94.97 426	98.69 369

CostFormer		97.72 342	97.73 306	97.71 423	99.15 360	94.02 472	99.54 175	99.02 412	94.67 450	99.04 309	99.35 372	92.35 376	99.77 266	98.50 233	97.94 324	99.34 287

testing3-2		97.84 317	97.70 309	98.24 372	99.53 229	95.37 441	99.55 170	98.67 471	98.46 130	99.27 257	99.34 376	86.58 462	99.83 224	99.32 92	98.63 277	99.52 235

our_test_3		97.65 355	97.68 311	97.55 432	98.62 450	94.97 452	98.84 447	99.30 356	96.83 365	98.19 419	99.34 376	97.01 151	99.02 445	95.00 443	96.01 397	98.64 395

c3_l		98.12 269	98.04 267	98.38 357	99.30 311	97.69 327	98.81 451	99.33 336	96.67 374	98.83 348	99.34 376	97.11 143	98.99 452	97.58 330	95.34 418	98.48 436

Fast-Effi-MVS+-dtu		98.77 214	98.83 185	98.60 319	99.41 277	96.99 365	99.52 186	99.49 201	98.11 201	99.24 264	99.34 376	96.96 153	99.79 253	97.95 291	99.45 181	99.02 325

Fast-Effi-MVS+		98.70 219	98.43 233	99.51 147	99.51 238	99.28 143	99.52 186	99.47 235	96.11 420	99.01 312	99.34 376	96.20 200	99.84 202	97.88 295	98.82 268	99.39 278

v1192		97.81 325	97.44 345	98.91 269	98.88 409	98.68 251	99.51 196	99.34 327	96.18 413	99.20 276	99.34 376	94.03 324	99.36 373	95.32 437	95.18 421	98.69 369

tpm		97.67 353	97.55 323	98.03 386	99.02 387	95.01 451	99.43 263	98.54 479	96.44 396	99.12 290	99.34 376	91.83 385	99.60 332	97.75 314	96.46 385	99.48 252

PAPM		97.59 359	97.09 382	99.07 243	99.06 379	98.26 290	98.30 499	99.10 398	94.88 445	98.08 424	99.34 376	96.27 195	99.64 322	89.87 494	98.92 256	99.31 292

GBi-Net		97.68 350	97.48 334	98.29 365	99.51 238	97.26 343	99.43 263	99.48 213	96.49 390	99.07 301	99.32 384	90.26 415	98.98 453	97.10 375	96.65 380	98.62 404

test1		97.68 350	97.48 334	98.29 365	99.51 238	97.26 343	99.43 263	99.48 213	96.49 390	99.07 301	99.32 384	90.26 415	98.98 453	97.10 375	96.65 380	98.62 404

FMVSNet1		96.84 398	96.36 402	98.29 365	99.32 309	97.26 343	99.43 263	99.48 213	95.11 438	98.55 389	99.32 384	83.95 483	98.98 453	95.81 422	96.26 391	98.62 404

MS-PatchMatch		97.24 387	97.32 365	96.99 449	98.45 464	93.51 481	98.82 450	99.32 347	97.41 312	98.13 423	99.30 387	88.99 432	99.56 337	95.68 428	99.80 126	97.90 484

GA-MVS		97.85 313	97.47 337	99.00 252	99.38 289	97.99 306	98.57 478	99.15 392	97.04 349	98.90 333	99.30 387	89.83 424	99.38 366	96.70 399	98.33 297	99.62 199

miper_ehance_all_eth		98.18 262	98.10 258	98.41 353	99.23 333	97.72 323	98.72 464	99.31 351	96.60 384	98.88 337	99.29 389	97.29 133	99.13 421	97.60 328	95.99 399	98.38 449

FMVSNet2		97.72 342	97.36 355	98.80 298	99.51 238	98.84 232	99.45 250	99.42 281	96.49 390	98.86 346	99.29 389	90.26 415	98.98 453	96.44 408	96.56 383	98.58 424

TESTMET0.1,1		97.55 361	97.27 373	98.40 355	98.93 401	96.53 395	98.67 467	97.61 502	96.96 354	98.64 378	99.28 391	88.63 441	99.45 349	97.30 361	99.38 185	99.21 303

FMVSNet3		98.03 285	97.76 303	98.84 291	99.39 285	98.98 185	99.40 283	99.38 303	96.67 374	99.07 301	99.28 391	92.93 351	98.98 453	97.10 375	96.65 380	98.56 427

PAPM_NR		99.04 164	98.84 183	99.66 92	99.74 101	99.44 118	99.39 287	99.38 303	97.70 273	99.28 251	99.28 391	98.34 98	99.85 192	96.96 386	99.45 181	99.69 157

EGC-MVSNET		82.80 493	77.86 500	97.62 427	97.91 476	96.12 411	99.33 315	99.28 362	8.40 558	25.05 560	99.27 394	84.11 482	99.33 379	89.20 497	98.22 308	97.42 498

ETV-MVS		99.26 91	99.21 83	99.40 189	99.46 262	99.30 140	99.56 155	99.52 134	98.52 123	99.44 204	99.27 394	98.41 94	99.86 184	99.10 135	99.59 170	99.04 322

xiu_mvs_v2_base		99.26 91	99.25 76	99.29 216	99.53 229	98.91 210	99.02 412	99.45 259	98.80 95	99.71 118	99.26 396	98.94 33	99.98 20	99.34 88	99.23 202	98.98 330

test20.03		96.12 415	95.96 413	96.63 458	97.44 488	95.45 437	99.51 196	99.38 303	96.55 387	96.16 471	99.25 397	93.76 336	96.17 514	87.35 509	94.22 443	98.27 454

PS-MVSNAJ		99.32 78	99.32 53	99.30 213	99.57 213	98.94 203	98.97 426	99.46 248	98.92 82	99.71 118	99.24 398	99.01 19	99.98 20	99.35 83	99.66 161	98.97 332

Test_1112_low_res		98.89 185	98.66 207	99.57 122	99.69 129	98.95 199	99.03 409	99.47 235	96.98 352	99.15 286	99.23 399	96.77 166	99.89 165	98.83 182	98.78 271	99.86 43

cl22		97.85 313	97.64 317	98.48 339	99.09 370	97.87 316	98.60 477	99.33 336	97.11 341	98.87 340	99.22 400	92.38 375	99.17 415	98.21 264	95.99 399	98.42 444

EG-PatchMatch MVS		95.97 418	95.69 419	96.81 456	97.78 482	92.79 485	99.16 376	98.93 423	96.16 415	94.08 490	99.22 400	82.72 489	99.47 345	95.67 429	97.50 352	98.17 460

TR-MVS		97.76 332	97.41 351	98.82 293	99.06 379	97.87 316	98.87 441	98.56 475	96.63 380	98.68 370	99.22 400	92.49 369	99.65 318	95.40 435	97.79 333	98.95 336

ET-MVSNet_ETH3D		96.49 406	95.64 421	99.05 246	99.53 229	98.82 238	98.84 447	97.51 505	97.63 280	84.77 522	99.21 403	92.09 379	98.91 466	98.98 149	92.21 475	99.41 274

WR-MVS_H		98.13 267	97.87 287	98.90 271	99.02 387	98.84 232	99.70 59	99.59 73	97.27 323	98.40 401	99.19 404	95.53 239	99.23 397	98.34 254	93.78 453	98.61 413

miper_enhance_ethall		98.16 264	98.08 262	98.41 353	98.96 399	97.72 323	98.45 491	99.32 347	96.95 356	98.97 321	99.17 405	97.06 147	99.22 404	97.86 298	95.99 399	98.29 453

baseline2		97.87 310	97.55 323	98.82 293	99.18 346	98.02 304	99.41 275	96.58 518	96.97 353	96.51 466	99.17 405	93.43 339	99.57 335	97.71 319	99.03 247	98.86 338

MIMVSNet1		95.51 427	95.04 431	96.92 454	97.38 490	95.60 429	99.52 186	99.50 187	93.65 462	96.97 461	99.17 405	85.28 476	96.56 511	88.36 502	95.55 414	98.60 416

gm-plane-assit					98.54 459	92.96 484			94.65 451		99.15 408		99.64 322	97.56 335

MIMVSNet		97.73 340	97.45 340	98.57 325	99.45 268	97.50 333	99.02 412	98.98 418	96.11 420	99.41 215	99.14 409	90.28 414	98.74 475	95.74 425	98.93 254	99.47 258

MASt3R-SfM		94.79 445	95.11 428	93.81 481	97.96 475	85.14 511	98.52 484	98.99 416	95.33 434	97.53 444	99.13 410	79.99 499	99.48 343	93.66 462	94.90 430	96.80 508

LCM-MVSNet-Re		97.83 320	98.15 252	96.87 455	99.30 311	92.25 489	99.59 129	98.26 486	97.43 308	96.20 470	99.13 410	96.27 195	98.73 476	98.17 269	98.99 251	99.64 191

UniMVSNet (Re)		98.29 253	98.00 271	99.13 240	99.00 390	99.36 128	99.49 224	99.51 162	97.95 237	98.97 321	99.13 410	96.30 194	99.38 366	98.36 252	93.34 457	98.66 391

N_pmnet		94.95 443	95.83 416	92.31 489	98.47 462	79.33 531	99.12 387	92.81 538	93.87 457	97.68 441	99.13 410	93.87 331	99.01 448	91.38 487	96.19 393	98.59 422

PAPR		98.63 228	98.34 239	99.51 147	99.40 282	99.03 179	98.80 452	99.36 315	96.33 401	99.00 316	99.12 414	98.46 89	99.84 202	95.23 439	99.37 192	99.66 177

tpm cat1		97.39 377	97.36 355	97.50 434	99.17 354	93.73 475	99.43 263	99.31 351	91.27 491	98.71 362	99.08 415	94.31 313	99.77 266	96.41 411	98.50 288	99.00 326

FMVSNet5		96.43 408	96.19 407	97.15 443	99.11 364	95.89 420	99.32 318	99.52 134	94.47 454	98.34 409	99.07 416	87.54 454	97.07 505	92.61 479	95.72 408	98.47 438

PMMVS		98.80 208	98.62 217	99.34 200	99.27 320	98.70 250	98.76 459	99.31 351	97.34 317	99.21 272	99.07 416	97.20 138	99.82 233	98.56 227	98.87 263	99.52 235

DKM		93.17 461	92.50 465	95.21 473	98.53 460	90.26 499	98.74 463	98.90 433	93.00 473	92.61 499	99.06 418	70.06 516	97.74 497	91.92 483	89.65 496	97.62 491

Anonymous20231206		96.22 410	96.03 411	96.79 457	97.31 493	94.14 471	99.63 105	99.08 401	96.17 414	97.04 459	99.06 418	93.94 327	97.76 496	86.96 512	95.06 424	98.47 438

usedtu_dtu_shiyan1		98.09 271	97.82 291	98.89 275	98.70 440	98.90 215	98.57 478	99.47 235	96.78 366	98.87 340	99.05 420	94.75 283	99.23 397	97.45 349	96.74 377	98.53 430

FE-MVSNET3		98.09 271	97.82 291	98.89 275	98.70 440	98.90 215	98.57 478	99.47 235	96.78 366	98.87 340	99.05 420	94.75 283	99.23 397	97.45 349	96.74 377	98.53 430

DeepMVS_CX				93.34 484	99.29 315	82.27 517		99.22 380	85.15 513	96.33 468	99.05 420	90.97 409	99.73 282	93.57 464	97.77 334	98.01 473

YYNet1		95.36 433	94.51 442	97.92 399	97.89 478	97.10 350	99.10 395	99.23 378	93.26 469	80.77 534	99.04 423	92.81 355	98.02 489	94.30 450	94.18 444	98.64 395

Anonymous20240521		96.20 412	95.89 415	97.13 445	97.72 486	94.96 453	99.79 31	99.29 360	93.01 472	97.20 455	99.03 424	89.69 426	98.36 483	91.16 488	96.13 394	98.07 467

MDA-MVSNet-bldmvs		94.96 442	93.98 450	97.92 399	98.24 469	97.27 341	99.15 380	99.33 336	93.80 460	80.09 536	99.03 424	88.31 444	97.86 494	93.49 465	94.36 440	98.62 404

test_method		91.10 471	91.36 471	90.31 500	95.85 514	73.72 540	94.89 528	99.25 374	68.39 530	95.82 474	99.02 426	80.50 498	98.95 463	93.64 463	94.89 431	98.25 456

DenseAffine		94.28 453	93.53 459	96.52 461	98.72 436	92.31 488	98.78 455	99.02 412	93.14 471	94.45 486	99.01 427	74.73 505	99.20 411	90.98 489	92.94 466	98.04 470

UWE-MVS		97.58 360	97.29 369	98.48 339	99.09 370	96.25 407	99.01 417	96.61 517	97.86 246	99.19 279	99.01 427	88.72 435	99.90 149	97.38 355	98.69 275	99.28 294

UWE-MVS-28		97.36 378	97.24 374	97.75 420	98.84 418	94.44 466	99.24 357	97.58 504	97.98 235	99.00 316	99.00 429	91.35 400	99.53 341	93.75 460	98.39 292	99.27 298

BH-w/o		98.00 292	97.89 286	98.32 362	99.35 296	96.20 409	99.01 417	98.90 433	96.42 398	98.38 402	99.00 429	95.26 252	99.72 286	96.06 416	98.61 278	99.03 323

Effi-MVS+-dtu		98.78 210	98.89 171	98.47 344	99.33 302	96.91 375	99.57 147	99.30 356	98.47 129	99.41 215	98.99 431	96.78 165	99.74 276	98.73 197	99.38 185	98.74 356

UnsupCasMVSNet_eth		96.44 407	96.12 408	97.40 438	98.65 447	95.65 428	99.36 302	99.51 162	97.13 336	96.04 473	98.99 431	88.40 443	98.17 486	96.71 398	90.27 489	98.40 447

test0.0.03 1		97.71 345	97.42 350	98.56 329	98.41 466	97.82 319	98.78 455	98.63 473	97.34 317	98.05 428	98.98 433	94.45 306	98.98 453	95.04 442	97.15 373	98.89 337

MDA-MVSNet_test_wron		95.45 428	94.60 438	98.01 389	98.16 473	97.21 346	99.11 393	99.24 377	93.49 465	80.73 535	98.98 433	93.02 349	98.18 485	94.22 454	94.45 438	98.64 395

FPMVS		84.93 490	85.65 490	82.75 516	86.77 552	63.39 545	98.35 494	98.92 426	74.11 522	83.39 527	98.98 433	50.85 536	92.40 532	84.54 519	94.97 426	92.46 525

testing3		97.28 383	96.76 393	98.82 293	99.37 292	98.07 302	99.45 250	99.36 315	97.56 289	97.89 435	98.95 436	83.70 484	98.82 470	96.03 417	98.56 284	99.58 219

WB-MVSnew		97.65 355	97.65 314	97.63 426	98.78 425	97.62 329	99.13 384	98.33 484	97.36 316	99.07 301	98.94 437	95.64 236	99.15 416	92.95 473	98.68 276	96.12 518

SSC-MVS		92.73 464	93.73 454	89.72 506	95.02 525	81.38 522	99.76 38	99.23 378	94.87 446	92.80 498	98.93 438	94.71 288	91.37 535	74.49 534	93.80 452	96.42 514

testf1		90.42 475	90.68 475	89.65 507	97.78 482	73.97 538	99.13 384	98.81 447	89.62 498	91.80 506	98.93 438	62.23 527	98.80 472	86.61 514	91.17 480	96.19 516

APD_test2		90.42 475	90.68 475	89.65 507	97.78 482	73.97 538	99.13 384	98.81 447	89.62 498	91.80 506	98.93 438	62.23 527	98.80 472	86.61 514	91.17 480	96.19 516

alignmvs		98.81 205	98.56 226	99.58 118	99.43 270	99.42 120	99.51 196	98.96 421	98.61 114	99.35 236	98.92 441	94.78 278	99.77 266	99.35 83	98.11 319	99.54 229

nomal-1		97.78 330	97.52 328	98.54 335	99.27 320	96.47 398	99.32 318	98.56 475	97.43 308	98.92 329	98.91 442	88.14 448	99.72 286	98.75 193	98.39 292	99.44 268

WB-MVS		93.10 462	94.10 447	90.12 503	95.51 521	81.88 519	99.73 52	99.27 369	95.05 441	93.09 497	98.91 442	94.70 289	91.89 533	76.62 529	94.02 450	96.58 513

DKM-HiRes		92.13 466	91.58 470	93.78 482	98.24 469	88.09 503	98.61 474	98.68 468	91.39 490	90.36 509	98.90 444	67.97 521	96.01 516	91.39 486	88.65 498	97.24 500

test-LLR		98.06 277	97.90 282	98.55 331	98.79 422	97.10 350	98.67 467	97.75 497	97.34 317	98.61 384	98.85 445	94.45 306	99.45 349	97.25 365	99.38 185	99.10 309

test-mter		97.49 372	97.13 380	98.55 331	98.79 422	97.10 350	98.67 467	97.75 497	96.65 376	98.61 384	98.85 445	88.23 445	99.45 349	97.25 365	99.38 185	99.10 309

dmvs_testset		95.02 440	96.12 408	91.72 491	99.10 367	80.43 527	99.58 139	97.87 496	97.47 300	95.22 477	98.82 447	93.99 325	95.18 521	88.09 503	94.91 429	99.56 226

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	99.28 251	98.81 448	97.04 148	99.76 270	99.29 104	97.87 329	99.47 258

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	99.31 243	98.81 448	97.09 144	99.75 273	99.27 109	97.90 325	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	99.31 243	98.81 448	97.09 144	99.75 273	99.27 109	97.90 325	99.47 258

new_pmnet		96.38 409	96.03 411	97.41 437	98.13 474	95.16 447	99.05 404	99.20 385	93.94 456	97.39 449	98.79 451	91.61 394	99.04 439	90.43 492	95.77 405	98.05 469

cascas		97.69 347	97.43 349	98.48 339	98.60 454	97.30 339	98.18 504	99.39 294	92.96 474	98.41 400	98.78 452	93.77 335	99.27 389	98.16 270	98.61 278	98.86 338

PVSNet_0	94.43 19	96.09 416	95.47 423	97.94 397	99.31 310	94.34 470	97.81 515	99.70 18	97.12 338	97.46 445	98.75 453	89.71 425	99.79 253	97.69 323	81.69 520	99.68 163

patchmatchnet-post											98.70 454	94.79 277	99.74 276

Patchmatch-RL test		95.84 420	95.81 417	95.95 468	95.61 517	90.57 498	98.24 500	98.39 482	95.10 440	95.20 478	98.67 455	94.78 278	97.77 495	96.28 414	90.02 490	99.51 244

thres100view900		97.76 332	97.45 340	98.69 311	99.72 112	97.86 318	99.59 129	98.74 459	97.93 239	99.26 262	98.62 456	91.75 386	99.83 224	93.22 469	98.18 314	98.37 450

thres600view7		97.86 312	97.51 331	98.92 265	99.72 112	97.95 312	99.59 129	98.74 459	97.94 238	99.27 257	98.62 456	91.75 386	99.86 184	93.73 461	98.19 313	98.96 334

FBQ-MVS		97.45 374	97.07 383	98.59 320	99.27 320	96.84 378	99.35 307	98.81 447	97.55 290	98.89 336	98.61 458	85.29 475	99.62 329	97.67 325	98.21 312	99.32 289

DSMNet-mixed		97.25 385	97.35 357	96.95 452	97.84 480	93.61 480	99.57 147	96.63 516	96.13 419	98.87 340	98.61 458	94.59 296	97.70 498	95.08 441	98.86 264	99.55 227

mmtdpeth		96.95 395	96.71 394	97.67 425	99.33 302	94.90 454	99.89 2	99.28 362	98.15 184	99.72 108	98.57 460	86.56 463	99.90 149	99.82 29	89.02 497	98.20 459

MVS_clip		71.06 509	74.26 508	61.45 534	84.42 556	45.51 562	79.78 549	56.58 561	40.80 553	90.25 510	98.55 461	61.46 529	49.70 557	80.63 525	75.89 537	89.13 535

IB-MVS	95.67 18	96.22 410	95.44 425	98.57 325	99.21 338	96.70 386	98.65 471	97.74 499	96.71 371	97.27 451	98.54 462	86.03 467	99.92 124	98.47 237	86.30 504	99.10 309
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
myMVS_eth3d28		97.69 347	97.34 360	98.73 304	99.27 320	97.52 332	99.33 315	98.78 453	98.03 227	98.82 350	98.49 463	86.64 461	99.46 347	98.44 241	98.24 307	99.23 301

GG-mvs-BLEND				98.45 347	98.55 458	98.16 294	99.43 263	93.68 533		97.23 452	98.46 464	89.30 429	99.22 404	95.43 434	98.22 308	97.98 478

tfpn200view9		97.72 342	97.38 353	98.72 306	99.69 129	97.96 309	99.50 207	98.73 465	97.83 253	99.17 284	98.45 465	91.67 390	99.83 224	93.22 469	98.18 314	98.37 450

thres400		97.77 331	97.38 353	98.92 265	99.69 129	97.96 309	99.50 207	98.73 465	97.83 253	99.17 284	98.45 465	91.67 390	99.83 224	93.22 469	98.18 314	98.96 334

testing11		97.50 367	97.10 381	98.71 309	99.20 340	96.91 375	99.29 330	98.82 445	97.89 243	98.21 418	98.40 467	85.63 470	99.83 224	98.45 240	98.04 321	99.37 282

kuosan		90.92 473	90.11 478	93.34 484	98.78 425	85.59 510	98.15 507	93.16 536	89.37 500	92.07 503	98.38 468	81.48 495	95.19 520	62.54 541	97.04 374	99.25 299

KD-MVS_2432*1600		94.62 447	93.72 455	97.31 440	97.19 496	95.82 423	98.34 495	99.20 385	95.00 443	97.57 442	98.35 469	87.95 449	98.10 487	92.87 475	77.00 535	98.01 473

miper_refine_blended		94.62 447	93.72 455	97.31 440	97.19 496	95.82 423	98.34 495	99.20 385	95.00 443	97.57 442	98.35 469	87.95 449	98.10 487	92.87 475	77.00 535	98.01 473

thres200		97.61 358	97.28 370	98.62 318	99.64 168	98.03 303	99.26 350	98.74 459	97.68 275	99.09 298	98.32 471	91.66 392	99.81 238	92.88 474	98.22 308	98.03 471

testing91		97.44 375	97.02 385	98.71 309	99.18 346	96.89 377	99.19 372	99.04 408	97.78 261	98.31 410	98.29 472	85.41 473	99.85 192	98.01 287	97.95 323	99.39 278

usedtu_dtu_shiyan2		91.34 470	89.96 479	95.47 472	93.61 535	90.81 495	99.15 380	98.68 468	86.37 510	95.19 479	98.27 473	72.64 508	97.05 506	85.40 517	80.32 530	98.54 428

testing99		97.36 378	96.94 388	98.63 317	99.18 346	96.70 386	99.30 325	98.93 423	97.71 270	98.23 415	98.26 474	84.92 477	99.84 202	98.04 286	97.85 331	99.35 284

OpenMVS_ROB	92.34 20	94.38 451	93.70 457	96.41 462	97.38 490	93.17 483	99.06 401	98.75 455	86.58 509	94.84 485	98.26 474	81.53 494	99.32 381	89.01 499	97.87 329	96.76 509

UBG		97.85 313	97.48 334	98.95 259	99.25 329	97.64 328	99.24 357	98.74 459	97.90 242	98.64 378	98.20 476	88.65 439	99.81 238	98.27 260	98.40 291	99.42 271

LoFTR		93.25 460	92.33 466	95.99 467	97.91 476	90.83 494	99.06 401	98.56 475	92.19 480	90.24 511	98.18 477	72.97 506	99.26 392	89.37 496	92.52 474	97.89 485

testing222		97.16 388	96.50 398	99.16 234	99.16 356	98.47 281	99.27 341	98.66 472	97.71 270	98.23 415	98.15 478	82.28 493	99.84 202	97.36 356	97.66 337	99.18 304

Syy-MVS		97.09 392	97.14 378	96.95 452	99.00 390	92.73 486	99.29 330	99.39 294	97.06 346	97.41 446	98.15 478	93.92 329	98.68 477	91.71 484	98.34 295	99.45 266

myMVS_eth3d		96.89 396	96.37 401	98.43 352	99.00 390	97.16 347	99.29 330	99.39 294	97.06 346	97.41 446	98.15 478	83.46 486	98.68 477	95.27 438	98.34 295	99.45 266

CL-MVSNet_self_test		94.49 449	93.97 451	96.08 466	96.16 510	93.67 478	98.33 497	99.38 303	95.13 436	97.33 450	98.15 478	92.69 363	96.57 510	88.67 500	79.87 532	97.99 477

test_vis1_rt		95.81 421	95.65 420	96.32 463	99.67 139	91.35 493	99.49 224	96.74 515	98.25 166	95.24 476	98.10 482	74.96 502	99.90 149	99.53 53	98.85 265	97.70 490

ETVMVS		97.50 367	96.90 389	99.29 216	99.23 333	98.78 244	99.32 318	98.90 433	97.52 297	98.56 388	98.09 483	84.72 479	99.69 307	97.86 298	97.88 328	99.39 278

pmmvs3		94.09 455	93.25 462	96.60 459	94.76 527	94.49 465	98.92 434	98.18 492	89.66 497	96.48 467	98.06 484	86.28 465	97.33 502	89.68 495	87.20 503	97.97 479

mvsany_test3		93.77 457	93.45 460	94.74 475	95.78 515	88.01 504	99.64 98	98.25 487	98.28 156	94.31 487	97.97 485	68.89 519	98.51 481	97.50 342	90.37 487	97.71 487

PMatch-Up-SfM		86.75 489	85.43 491	90.73 498	94.97 526	81.39 521	97.55 520	94.92 526	86.33 511	83.10 528	97.95 486	46.03 545	93.97 528	87.59 506	80.39 529	96.83 507

PMatch-SfM		88.28 482	86.92 487	92.38 488	95.93 512	84.56 512	97.84 514	96.01 520	88.80 503	84.11 524	97.95 486	49.73 539	95.66 519	89.15 498	82.72 518	96.91 506

blended_shiyan6		95.54 426	94.78 434	97.84 410	96.60 504	95.89 420	98.85 443	99.28 362	92.17 484	98.43 399	97.95 486	91.44 396	99.02 445	97.30 361	80.97 524	98.60 416

blended_shiyan8		95.56 425	94.79 433	97.87 403	96.60 504	95.90 419	98.85 443	99.27 369	92.19 480	98.47 396	97.94 489	91.43 397	99.11 428	97.26 364	81.09 523	98.60 416

MatchFormer		91.94 468	90.72 473	95.58 471	97.82 481	89.79 502	98.92 434	98.87 439	88.24 505	88.03 516	97.92 490	70.39 514	99.23 397	85.21 518	91.12 482	97.72 486

blend_shiyan4		95.25 436	94.39 444	97.84 410	96.70 503	95.92 417	98.84 447	99.28 362	92.21 479	98.16 421	97.84 491	87.10 459	99.07 434	97.53 338	81.87 519	98.54 428

ELoFTR		89.95 477	88.65 482	93.85 479	95.93 512	85.85 508	98.64 472	98.31 485	90.34 495	85.03 521	97.76 492	60.28 530	99.01 448	87.27 510	84.26 508	96.71 512

PM-MVS		92.96 463	92.23 467	95.14 474	95.61 517	89.98 501	99.37 296	98.21 490	94.80 448	95.04 482	97.69 493	65.06 523	97.90 493	94.30 450	89.98 491	97.54 496

wanda-best-256-512		95.43 429	94.66 436	97.77 418	96.45 506	95.68 426	98.48 488	99.28 362	92.18 482	98.36 404	97.68 494	91.20 404	99.03 441	97.31 358	80.97 524	98.60 416

FE-blended-shiyan7		95.43 429	94.66 436	97.77 418	96.45 506	95.68 426	98.48 488	99.28 362	92.18 482	98.36 404	97.68 494	91.20 404	99.03 441	97.31 358	80.97 524	98.60 416

usedtu_blend_shiyan5		95.04 439	94.10 447	97.86 406	96.45 506	95.92 417	99.29 330	99.22 380	86.17 512	98.36 404	97.68 494	91.20 404	99.07 434	97.53 338	80.97 524	98.60 416

FE-MVSNET2		95.10 438	94.44 443	97.08 448	95.08 523	95.97 414	99.51 196	99.37 313	95.02 442	94.10 489	97.57 497	86.18 466	97.66 500	93.28 468	89.86 492	97.61 492

FE-MVSNET		94.07 456	93.36 461	96.22 464	94.05 531	94.71 459	99.56 155	98.36 483	93.15 470	93.76 493	97.55 498	86.47 464	96.49 512	87.48 507	89.83 493	97.48 497

pmmvs-eth3d		95.34 434	94.73 435	97.15 443	95.53 519	95.94 416	99.35 307	99.10 398	95.13 436	93.55 494	97.54 499	88.15 447	97.91 492	94.58 447	89.69 495	97.61 492

gbinet_0.2-2-1-0.02		95.40 432	94.58 440	97.85 407	96.11 511	95.97 414	98.56 482	99.26 371	92.12 486	98.47 396	97.49 500	90.23 418	99.00 450	97.71 319	81.25 521	98.58 424

ambc				93.06 487	92.68 539	82.36 516	98.47 490	98.73 465		95.09 481	97.41 501	55.55 531	99.10 431	96.42 409	91.32 478	97.71 487

RPMNet		96.72 400	95.90 414	99.19 231	99.18 346	98.49 277	99.22 364	99.52 134	88.72 504	99.56 176	97.38 502	94.08 322	99.95 76	86.87 513	98.58 281	99.14 305

new-patchmatchnet		94.48 450	94.08 449	95.67 470	95.08 523	92.41 487	99.18 374	99.28 362	94.55 453	93.49 495	97.37 503	87.86 452	97.01 507	91.57 485	88.36 499	97.61 492

PDCNetPlus		84.77 491	83.24 494	89.36 509	94.33 530	83.93 514	98.13 508	76.80 553	83.26 516	86.31 518	97.33 504	62.90 525	92.65 530	87.20 511	62.90 541	91.50 528

KD-MVS_self_test		95.00 441	94.34 445	96.96 451	97.07 499	95.39 440	99.56 155	99.44 268	95.11 438	97.13 457	97.32 505	91.86 384	97.27 504	90.35 493	81.23 522	98.23 458

PatchT		97.03 394	96.44 400	98.79 299	98.99 393	98.34 287	99.16 376	99.07 404	92.13 485	99.52 188	97.31 506	94.54 301	98.98 453	88.54 501	98.73 273	99.03 323

ALIKED-LG		88.17 484	87.32 486	90.75 497	98.67 445	81.68 520	98.16 505	94.72 529	78.63 519	86.08 520	97.07 507	70.16 515	96.62 509	71.97 537	90.37 487	93.95 523

0.4-1-1-0.1		95.23 437	94.22 446	98.26 371	97.39 489	95.86 422	97.59 519	97.62 500	93.85 458	94.97 483	97.03 508	87.20 456	99.87 177	98.47 237	83.84 509	99.05 321

ALIKED-NN		88.27 483	87.61 485	90.24 501	98.46 463	79.97 529	97.04 523	94.61 531	75.25 520	86.99 517	96.90 509	72.78 507	95.78 518	75.45 532	91.01 484	94.97 521

test_fmvs3		92.10 467	91.77 469	93.08 486	96.19 509	86.25 506	99.82 16	98.62 474	96.65 376	95.19 479	96.90 509	55.05 533	95.93 517	96.63 405	90.92 486	97.06 505

UnsupCasMVSNet_bld		93.53 458	92.51 464	96.58 460	97.38 490	93.82 473	98.24 500	99.48 213	91.10 493	93.10 496	96.66 511	74.89 504	98.37 482	94.03 457	87.71 502	97.56 495

0.4-1-1-0.2		94.94 444	93.92 452	97.99 392	96.84 502	95.13 449	96.64 526	97.62 500	93.45 467	94.92 484	96.56 512	87.14 458	99.86 184	98.43 244	83.69 513	98.98 330

0.3-1-1-0.015		94.79 445	93.69 458	98.10 383	96.99 501	95.46 436	97.02 524	97.61 502	93.53 463	94.03 491	96.54 513	85.60 471	99.86 184	98.43 244	83.45 514	98.99 329

LCM-MVSNet		86.80 488	85.22 493	91.53 492	87.81 551	80.96 524	98.23 502	98.99 416	71.05 527	90.13 512	96.51 514	48.45 544	96.88 508	90.51 490	85.30 506	96.76 509

test_f		91.90 469	91.26 472	93.84 480	95.52 520	85.92 507	99.69 63	98.53 480	95.31 435	93.87 492	96.37 515	55.33 532	98.27 484	95.70 426	90.98 485	97.32 499

SP-DiffGlue		90.78 474	90.71 474	90.98 495	95.45 522	81.30 523	97.92 513	97.30 507	75.18 521	92.09 502	95.93 516	74.93 503	94.89 524	93.46 466	94.12 446	96.74 511

VLMVS_CLIP		71.76 506	73.17 509	67.54 531	63.66 561	40.57 564	82.57 548	89.67 543	44.24 552	82.97 530	95.88 517	37.85 553	71.58 554	83.87 520	77.80 533	90.48 530

ALIKED-MNN		86.97 486	85.90 488	90.16 502	99.06 379	79.59 530	97.93 512	94.82 527	72.37 525	84.41 523	95.46 518	68.55 520	96.43 513	72.40 535	88.11 501	94.47 522

PMMVS2		86.87 487	85.37 492	91.35 493	90.21 545	83.80 515	98.89 438	97.45 506	83.13 517	91.67 508	95.03 519	48.49 543	94.70 526	85.86 516	77.62 534	95.54 519

Gipuma		90.99 472	90.15 477	93.51 483	98.73 434	90.12 500	93.98 533	99.45 259	79.32 518	92.28 501	94.91 520	69.61 517	97.98 491	87.42 508	95.67 409	92.45 526
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
JIA-IIPM		97.50 367	97.02 385	98.93 263	98.73 434	97.80 320	99.30 325	98.97 419	91.73 488	98.91 331	94.86 521	95.10 259	99.71 293	97.58 330	97.98 322	99.28 294

SP-SuperGlue		89.23 479	88.68 480	90.88 496	98.23 471	80.60 526	98.16 505	97.30 507	73.08 523	89.64 513	94.62 522	71.80 511	94.91 523	82.11 523	93.22 460	97.14 504

SP-LightGlue		89.28 478	88.68 480	91.06 494	98.21 472	80.90 525	98.19 503	96.96 510	72.38 524	89.60 514	94.43 523	72.44 509	95.06 522	82.91 521	93.03 465	97.22 501

VLMVS		64.83 514	67.01 515	58.30 536	65.95 560	42.53 563	76.90 551	66.20 559	29.52 554	82.93 531	94.37 524	42.34 547	55.19 556	72.39 536	72.45 538	77.18 539

SP-MNN		88.33 481	87.78 484	89.95 505	98.28 467	77.92 533	98.01 511	95.69 523	70.61 528	86.18 519	94.36 525	71.09 513	94.76 525	81.51 524	94.32 441	97.17 502

XFeat-MNN		82.40 495	82.10 496	83.31 514	93.04 537	68.49 542	95.39 527	90.86 540	60.29 537	81.56 532	94.09 526	66.79 522	91.70 534	76.62 529	80.26 531	89.74 532

SP-NN		88.62 480	88.17 483	89.96 504	97.89 478	78.51 532	97.19 522	96.09 519	71.28 526	88.29 515	94.00 527	71.98 510	93.65 529	82.37 522	94.46 436	97.71 487

PMVS	70.75 22	75.98 502	74.97 505	79.01 519	70.98 558	55.18 557	93.37 536	98.21 490	65.08 535	61.78 548	93.83 528	21.74 561	92.53 531	78.59 527	91.12 482	89.34 534
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
XFeat-NN		82.84 492	83.12 495	82.00 518	94.35 529	67.14 544	93.32 538	89.27 544	62.21 536	84.06 525	93.50 529	69.15 518	89.40 536	78.92 526	83.33 515	89.46 533

GLUNet-SfM		78.99 498	76.32 502	86.99 510	89.16 550	73.30 541	93.36 537	90.45 541	66.38 533	74.95 542	93.30 530	52.29 535	94.61 527	75.35 533	51.65 548	93.07 524

MVS-HIRNet		95.75 422	95.16 427	97.51 433	99.30 311	93.69 477	98.88 439	95.78 521	85.09 514	98.78 356	92.65 531	91.29 402	99.37 369	94.85 445	99.85 94	99.46 263

E-PMN		80.61 496	79.88 498	82.81 515	90.75 543	76.38 536	97.69 516	95.76 522	66.44 532	83.52 526	92.25 532	62.54 526	87.16 544	68.53 539	61.40 542	84.89 537

test_vis3_rt		87.04 485	85.81 489	90.73 498	93.99 532	81.96 518	99.76 38	90.23 542	92.81 476	81.35 533	91.56 533	40.06 551	99.07 434	94.27 452	88.23 500	91.15 529

EMVS		80.02 497	79.22 499	82.43 517	91.19 542	76.40 535	97.55 520	92.49 539	66.36 534	83.01 529	91.27 534	64.63 524	85.79 547	65.82 540	60.65 543	85.08 536

MVS_baseline		35.35 522	39.65 525	22.45 540	47.29 562	11.23 567	38.03 552	9.90 566	5.09 559	58.24 551	91.18 535	16.48 563	0.13 561	42.28 553	48.39 549	55.99 553

gg-mvs-nofinetune		96.17 414	95.32 426	98.73 304	98.79 422	98.14 296	99.38 292	94.09 532	91.07 494	98.07 427	91.04 536	89.62 428	99.35 376	96.75 396	99.09 240	98.68 374

SIFT-MNN		75.73 503	75.71 503	75.77 521	95.65 516	60.92 548	94.36 530	87.62 545	58.67 539	75.90 540	90.94 537	49.64 541	89.04 538	44.85 548	83.80 511	77.35 538

SIFT-NN		76.99 500	77.37 501	75.84 520	97.10 498	62.39 546	94.15 532	87.21 546	59.41 538	79.90 538	90.73 538	54.60 534	88.56 539	47.22 543	86.03 505	76.57 540

SIFT-ConvMatch		69.43 511	68.09 514	73.45 526	93.86 534	60.02 552	92.57 542	77.69 552	57.58 543	62.69 546	90.53 539	42.14 548	86.65 546	43.98 549	51.72 547	73.67 545

SIFT-NN-NCMNet		75.53 504	75.57 504	75.42 522	93.93 533	61.35 547	94.41 529	86.44 547	58.51 540	76.23 539	90.44 540	50.56 537	89.34 537	46.60 544	83.04 516	75.58 542

SIFT-UMatch		68.14 512	66.40 516	73.38 527	92.20 541	59.42 553	92.84 540	76.01 555	56.87 545	58.37 550	90.35 541	41.97 549	87.16 544	42.64 550	46.35 550	73.55 547

SIFT-NN-CMatch		72.61 505	71.92 510	74.68 523	92.79 538	60.24 550	93.28 539	81.57 551	58.24 542	75.18 541	90.26 542	49.66 540	87.35 543	46.02 545	60.26 544	76.45 541

SIFT-CM-Cal		66.94 513	65.48 517	71.33 529	93.05 536	58.77 554	91.46 545	70.45 557	56.64 548	61.97 547	89.98 543	40.72 550	83.32 550	42.57 551	42.47 552	71.90 548

SIFT-UM-Cal		64.60 515	62.65 518	70.42 530	92.22 540	58.07 556	92.29 543	66.92 558	56.70 546	50.16 554	89.97 544	37.90 552	82.95 551	42.33 552	35.40 555	70.24 550

SIFT-NN-UMatch		71.65 507	70.86 511	74.00 525	90.69 544	60.53 549	93.59 534	81.89 549	58.42 541	60.99 549	89.71 545	50.18 538	87.89 541	45.77 546	66.55 540	73.57 546

SIFT-NCM-Cal		71.65 507	70.76 512	74.34 524	94.61 528	60.18 551	94.16 531	81.72 550	57.21 544	55.36 552	89.56 546	42.48 546	88.45 540	41.31 554	80.41 528	74.39 544

ANet_high		77.30 499	74.86 506	84.62 513	75.88 557	77.61 534	97.63 518	93.15 537	88.81 502	64.27 545	89.29 547	36.51 555	83.93 548	75.89 531	52.31 546	92.33 527

SIFT-NN-PointCN		70.32 510	69.71 513	72.13 528	90.01 546	58.29 555	93.45 535	76.20 554	56.66 547	70.25 544	89.20 548	48.94 542	83.41 549	45.45 547	57.26 545	74.70 543

MVE	76.82 21	76.91 501	74.31 507	84.70 512	85.38 555	76.05 537	96.88 525	93.17 535	67.39 531	71.28 543	89.01 549	21.66 562	87.69 542	71.74 538	72.29 539	90.35 531
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SIFT-PCN-Cal		61.29 517	60.21 520	64.54 533	89.88 547	50.56 559	91.21 546	65.73 560	53.15 550	48.59 555	87.20 550	36.60 554	76.52 552	37.37 557	32.17 556	66.54 551

SIFT-PointCN		62.71 516	61.56 519	66.18 532	89.53 549	50.88 558	91.81 544	72.35 556	53.65 549	50.49 553	86.32 551	33.30 556	76.23 553	35.91 558	40.66 553	71.43 549

SIFT-NCMNet		55.02 518	53.54 521	59.46 535	86.55 553	47.35 561	87.85 547	46.22 562	51.77 551	44.11 556	83.50 552	27.88 559	68.75 555	32.81 559	21.14 559	62.27 552

testmvs		39.17 520	43.78 522	25.37 539	36.04 564	16.84 566	98.36 493	26.56 563	20.06 556	38.51 558	67.32 553	29.64 558	15.30 560	37.59 555	39.90 554	43.98 555

test123		39.01 521	42.50 523	28.53 538	39.17 563	20.91 565	98.75 460	19.17 565	19.83 557	38.57 557	66.67 554	33.16 557	15.42 559	37.50 556	29.66 557	49.26 554

test_post											65.99 555	94.65 294	99.73 282

test_post1							99.23 360				65.14 556	94.18 318	99.71 293	97.58 330

X-MVStestdata		96.55 404	95.45 424	99.87 22	99.85 31	99.83 23	99.69 63	99.68 24	98.98 72	99.37 227	64.01 557	98.81 49	99.94 91	98.79 190	99.86 87	99.84 54

wuyk23d		40.18 519	41.29 524	36.84 537	86.18 554	49.12 560	79.73 550	22.81 564	27.64 555	25.46 559	28.45 558	21.98 560	48.89 558	55.80 542	23.56 558	12.51 556

test_blank		0.13 526	0.17 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	1.57 559	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

mmdepth		0.02 527	0.03 530	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.27 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

monomultidepth		0.02 527	0.03 530	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.27 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

uanet_test		0.02 527	0.03 530	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.27 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

DCPMVS		0.02 527	0.03 530	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.27 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

pcd_1.5k_mvsjas		8.27 525	11.03 528	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.27 560	99.01 19	0.00 562	0.00 560	0.00 560	0.00 557

sosnet-low-res		0.02 527	0.03 530	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.27 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

sosnet		0.02 527	0.03 530	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.27 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

uncertanet		0.02 527	0.03 530	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.27 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

Regformer		0.02 527	0.03 530	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.27 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

uanet		0.02 527	0.03 530	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.27 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

PatchmatchNet2					0.00 565	95.16 447	98.77 458	99.17 390	93.82 459
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														91.97 481	96.20 392	98.59 422
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													99.13 421
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
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

WAC-MVS						97.16 347								95.47 432

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

MSC_two_6792asdad				99.87 22	99.51 238	99.76 50		99.33 336					99.96 41	98.87 169	99.84 102	99.89 30

No_MVS				99.87 22	99.51 238	99.76 50		99.33 336					99.96 41	98.87 169	99.84 102	99.89 30

eth-test2					0.00 565

eth-test					0.00 565

IU-MVS					99.84 38	99.88 10		99.32 347	98.30 155	99.84 56				98.86 174	99.85 94	99.89 30

save fliter					99.76 83	99.59 90	99.14 383	99.40 291	99.00 67

test_0728_SECOND				99.91 6	99.84 38	99.89 6	99.57 147	99.51 162					99.96 41	98.93 160	99.86 87	99.88 36

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

MTMP							99.54 175	98.88 437

test9_res														97.49 343	99.72 150	99.75 113

agg_prior2														97.21 367	99.73 149	99.75 113

agg_prior					99.67 139	99.62 84		99.40 291		98.87 340			99.91 136

test_prior4						99.56 96	98.99 420

test_prior				99.68 90	99.67 139	99.48 113		99.56 90					99.83 224			99.74 118

旧先验2							98.96 427		96.70 372	99.47 196			99.94 91	98.19 266

新几何2							99.01 417

无先验							98.99 420	99.51 162	96.89 360				99.93 109	97.53 338		99.72 138

原ACMM2							98.95 430

testdata2													99.95 76	96.67 401

segment_acmp												98.96 26

testdata1							98.85 443		98.32 151

test12				99.75 77	99.64 168	99.61 87		99.29 360		99.21 272		98.38 96	99.89 165		99.74 147	99.74 118

plane_prior7					99.29 315	97.03 362

plane_prior6					99.27 320	96.98 366						92.71 361

plane_prior5								99.47 235					99.69 307	97.78 308	97.63 338	98.67 382

plane_prior3						97.00 364			98.69 108	99.11 292

plane_prior2							99.39 287		98.97 76

plane_prior1					99.26 325

plane_prior						96.97 367	99.21 366		98.45 132						97.60 341

n2								0.00 567

nn								0.00 567

door-mid								98.05 493

test11								99.35 322

door								97.92 494

HQP5-MVS						96.83 379

HQP-NCC					99.19 343		98.98 423		98.24 168	98.66 371

ACMP_Plane					99.19 343		98.98 423		98.24 168	98.66 371

BP-MVS														97.19 371

HQP4-MVS										98.66 371			99.64 322			98.64 395

HQP3-MVS								99.39 294							97.58 343

HQP2-MVS												92.47 370

MDTV_nov1_ep13_2view						95.18 446	99.35 307		96.84 363	99.58 171		95.19 256		97.82 303		99.46 263

ACMMP++_ref															97.19 371

ACMMP++															97.43 361

Test By Simon												98.75 61

High-resolution multi-view benchmark