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.

mvs5depth		99.30 33	99.59 12	98.44 273	99.65 70	95.35 362	99.82 3	99.94 3	99.83 7	99.42 111	99.94 2	98.13 123	99.96 13	99.63 36	99.96 28	100.00 1

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 74	99.87 12	98.13 149	98.08 195	99.95 2	99.45 50	99.98 2	99.75 16	99.80 1	99.97 6	99.82 12	99.99 5	99.99 2

fmvsm_s_conf0.1_n_a		99.17 52	99.30 44	98.80 193	99.75 34	96.59 299	97.97 225	99.86 17	98.22 200	99.88 21	99.71 22	98.59 67	99.84 176	99.73 28	99.98 12	99.98 3

fmvsm_s_conf0.1_n_2		99.20 50	99.38 28	98.65 226	99.69 60	96.08 326	97.49 300	99.90 12	99.53 41	99.88 21	99.64 37	98.51 76	99.90 81	99.83 10	99.98 12	99.97 4

mmtdpeth		99.30 33	99.42 25	98.92 170	99.58 93	96.89 284	99.48 13	99.92 8	99.92 2	98.26 328	99.80 11	98.33 95	99.91 74	99.56 41	99.95 39	99.97 4

fmvsm_s_conf0.1_n		99.16 56	99.33 37	98.64 228	99.71 48	96.10 321	97.87 238	99.85 19	98.56 175	99.90 14	99.68 25	98.69 57	99.85 158	99.72 30	99.98 12	99.97 4

test_fmvs3		99.12 69	99.41 26	98.25 295	99.76 30	95.07 377	99.05 68	99.94 3	97.78 245	99.82 34	99.84 3	98.56 73	99.71 306	99.96 1	99.96 28	99.97 4

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 83	99.78 24	98.11 151	97.77 252	99.90 12	99.33 65	99.97 3	99.66 32	99.71 3	99.96 13	99.79 19	99.99 5	99.96 8

test_f		98.67 159	98.87 110	98.05 321	99.72 44	95.59 344	98.51 135	99.81 32	96.30 366	99.78 39	99.82 5	96.14 271	98.63 493	99.82 12	99.93 57	99.95 9

test_fmvs2		98.70 146	98.97 97	97.89 334	99.54 122	94.05 413	98.55 126	99.92 8	96.78 342	99.72 47	99.78 13	96.60 248	99.67 336	99.91 2	99.90 88	99.94 10

PS-MVSNAJss		99.46 17	99.49 16	99.35 80	99.90 4	98.15 146	99.20 49	99.65 74	99.48 44	99.92 8	99.71 22	98.07 126	99.96 13	99.53 48	100.00 1	99.93 11

test_vis3_rt		99.14 62	99.17 60	99.07 135	99.78 24	98.38 122	98.92 83	99.94 3	97.80 242	99.91 12	99.67 30	97.15 208	98.91 485	99.76 23	99.56 283	99.92 12

fmvsm_s_conf0.5_n_2		99.14 62	99.31 41	98.63 232	99.49 146	96.08 326	97.38 314	99.81 32	99.48 44	99.84 30	99.57 49	98.46 82	99.89 97	99.82 12	99.97 21	99.91 13

MVStest1		95.86 406	95.60 399	96.63 428	95.87 519	91.70 469	97.93 227	98.94 328	98.03 223	99.56 74	99.66 32	71.83 509	98.26 498	99.35 58	99.24 358	99.91 13

fmvsm_s_conf0.5_n_a		99.10 71	99.20 58	98.78 200	99.55 116	96.59 299	97.79 248	99.82 31	98.21 202	99.81 36	99.53 64	98.46 82	99.84 176	99.70 33	99.97 21	99.90 15

fmvsm_s_conf0.5_n_9		99.17 52	99.38 28	98.53 259	99.51 132	95.82 338	97.62 278	99.78 36	99.72 14	99.90 14	99.48 75	98.66 59	99.89 97	99.85 6	99.93 57	99.89 16

fmvsm_s_conf0.5_n		99.09 72	99.26 50	98.61 238	99.55 116	96.09 324	97.74 260	99.81 32	98.55 176	99.85 27	99.55 56	98.60 66	99.84 176	99.69 35	99.98 12	99.89 16

test_fmvsmconf_n		99.44 19	99.48 18	99.31 94	99.64 76	98.10 154	97.68 267	99.84 23	99.29 71	99.92 8	99.57 49	99.60 5	99.96 13	99.74 27	99.98 12	99.89 16

test_djsdf		99.52 13	99.51 15	99.53 38	99.86 14	98.74 91	99.39 20	99.56 115	99.11 99	99.70 51	99.73 20	99.00 27	99.97 6	99.26 65	99.98 12	99.89 16

fmvsm_s_conf0.5_n_11		99.21 47	99.34 35	98.80 193	99.48 154	96.56 304	97.97 225	99.69 55	99.63 28	99.84 30	99.54 62	98.21 113	99.94 41	99.76 23	99.95 39	99.88 20

mvs_tets		99.63 6	99.67 6	99.49 55	99.88 9	98.61 103	99.34 23	99.71 47	99.27 73	99.90 14	99.74 18	99.68 4	99.97 6	99.55 43	99.99 5	99.88 20

fmvsm_s_conf0.5_n_8		99.13 66	99.26 50	98.74 213	99.51 132	96.44 312	97.65 273	99.65 74	99.66 23	99.78 39	99.48 75	97.92 140	99.93 53	99.72 30	99.95 39	99.87 22

fmvsm_s_conf0.5_n_7		98.83 121	99.04 86	98.20 302	99.30 207	94.83 386	97.23 332	99.36 207	98.64 159	99.84 30	99.43 88	98.10 125	99.91 74	99.56 41	99.96 28	99.87 22

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 83	99.59 91	98.21 143	97.82 243	99.84 23	99.41 57	99.92 8	99.41 94	99.51 8	99.95 25	99.84 9	99.97 21	99.87 22

ttmdpeth		97.91 267	98.02 250	97.58 371	98.69 359	94.10 412	98.13 185	98.90 338	97.95 229	97.32 404	99.58 47	95.95 287	98.75 490	96.41 326	99.22 362	99.87 22

jajsoiax		99.58 9	99.61 11	99.48 57	99.87 12	98.61 103	99.28 40	99.66 69	99.09 109	99.89 18	99.68 25	99.53 7	99.97 6	99.50 50	99.99 5	99.87 22

EU-MVSNet		97.66 293	98.50 172	95.13 482	99.63 82	85.84 516	98.35 161	98.21 408	98.23 199	99.54 79	99.46 80	95.02 318	99.68 332	98.24 144	99.87 100	99.87 22

fmvsm_s_conf0.5_n_3		99.22 46	99.37 31	98.78 200	99.46 160	96.58 302	97.65 273	99.72 45	99.47 47	99.86 24	99.50 68	98.94 31	99.89 97	99.75 26	99.97 21	99.86 28

UA-Net		99.47 16	99.40 27	99.70 2	99.49 146	99.29 23	99.80 4	99.72 45	99.82 8	99.04 198	99.81 8	98.05 129	99.96 13	98.85 98	99.99 5	99.86 28

fmvsm_l_conf0.5_n_9		99.32 32	99.43 24	98.98 157	99.59 91	97.18 262	97.44 309	99.83 26	99.56 39	99.91 12	99.34 115	99.36 13	99.93 53	99.83 10	99.98 12	99.85 30

MM		98.22 234	97.99 253	98.91 172	98.66 369	96.97 276	97.89 234	94.44 497	99.54 40	98.95 218	99.14 177	93.50 365	99.92 65	99.80 17	99.96 28	99.85 30

LCM-MVSNet		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 14	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 16	100.00 1	99.85 30

fmvsm_l_conf0.5_n_a		99.19 51	99.27 47	98.94 164	99.65 70	97.05 271	97.80 247	99.76 39	98.70 157	99.78 39	99.11 184	98.79 43	99.95 25	99.85 6	99.96 28	99.83 33

fmvsm_l_conf0.5_n		99.21 47	99.28 46	99.02 148	99.64 76	97.28 248	97.82 243	99.76 39	98.73 150	99.82 34	99.09 193	98.81 39	99.95 25	99.86 4	99.96 28	99.83 33

mvsany_test3		98.87 111	98.92 101	98.74 213	99.38 183	96.94 280	98.58 123	99.10 300	96.49 355	99.96 4	99.81 8	98.18 116	99.45 436	98.97 89	99.79 158	99.83 33

PDCNetPlus		95.22 429	94.73 436	96.70 427	97.85 447	91.14 485	93.94 495	99.97 1	93.06 470	98.95 218	98.89 256	74.32 506	99.14 473	95.63 368	99.93 57	99.82 36

fmvsm_s_conf0.5_n_10		99.15 57	99.27 47	98.78 200	99.47 157	96.56 304	97.75 258	99.71 47	99.60 35	99.74 46	99.44 85	97.96 137	99.95 25	99.86 4	99.94 51	99.82 36

SSC-MVS		98.71 141	98.74 127	98.62 234	99.72 44	96.08 326	98.74 99	98.64 381	99.74 12	99.67 59	99.24 144	94.57 334	99.95 25	99.11 77	99.24 358	99.82 36

anonymousdsp		99.51 14	99.47 21	99.62 9	99.88 9	99.08 69	99.34 23	99.69 55	98.93 131	99.65 63	99.72 21	98.93 33	99.95 25	99.11 77	100.00 1	99.82 36

ANet_high		99.57 10	99.67 6	99.28 96	99.89 6	98.09 155	99.14 58	99.93 6	99.82 8	99.93 6	99.81 8	99.17 20	99.94 41	99.31 61	100.00 1	99.82 36

MED-MVS		99.01 89	98.84 118	99.52 44	99.58 93	98.93 79	98.68 109	99.60 89	98.85 144	99.53 83	99.16 168	97.87 147	99.83 194	96.67 298	99.64 249	99.81 41

TestfortrainingZip a		99.09 72	98.92 101	99.61 13	99.58 93	99.17 43	98.68 109	99.27 255	98.85 144	99.61 70	99.16 168	97.14 209	99.86 144	98.39 137	99.57 279	99.81 41

fmvsm_s_conf0.5_n_4		99.01 89	99.22 54	98.38 280	99.31 203	95.48 353	97.56 289	99.73 44	98.87 139	99.75 44	99.27 131	98.80 41	99.86 144	99.80 17	99.90 88	99.81 41

PS-CasMVS		99.40 25	99.33 37	99.62 9	99.71 48	99.10 65	99.29 36	99.53 129	99.53 41	99.46 101	99.41 94	98.23 108	99.95 25	98.89 96	99.95 39	99.81 41

VortexMVS		97.98 264	98.31 209	97.02 408	98.88 319	91.45 474	98.03 206	99.47 158	98.65 158	99.55 77	99.47 78	91.49 404	99.81 223	99.32 60	99.91 80	99.80 45

FC-MVSNet-test		99.27 37	99.25 52	99.34 83	99.77 27	98.37 124	99.30 35	99.57 106	99.61 34	99.40 116	99.50 68	97.12 210	99.85 158	99.02 86	99.94 51	99.80 45

test_cas_vis1_n_1920		98.33 218	98.68 140	97.27 395	99.69 60	92.29 463	98.03 206	99.85 19	97.62 257	99.96 4	99.62 40	93.98 355	99.74 288	99.52 49	99.86 107	99.79 47

test_vis1_n_1920		98.40 204	98.92 101	96.81 422	99.74 36	90.76 492	98.15 183	99.91 10	98.33 188	99.89 18	99.55 56	95.07 317	99.88 115	99.76 23	99.93 57	99.79 47

CP-MVSNet		99.21 47	99.09 81	99.56 26	99.65 70	98.96 77	99.13 59	99.34 219	99.42 55	99.33 135	99.26 137	97.01 218	99.94 41	98.74 107	99.93 57	99.79 47

fmvsm_s_conf0.5_n_5		99.07 81	99.10 79	98.99 153	99.47 157	97.22 255	97.40 311	99.83 26	97.61 260	99.85 27	99.30 125	98.80 41	99.95 25	99.71 32	99.90 88	99.78 50

UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 19	99.69 5	99.58 98	99.90 3	99.86 24	99.78 13	99.58 6	99.95 25	99.00 87	99.95 39	99.78 50

CVMVSNet		96.25 389	97.21 316	93.38 505	99.10 265	80.56 535	97.20 337	98.19 411	96.94 328	99.00 203	99.02 208	89.50 426	99.80 232	96.36 330	99.59 270	99.78 50

reproduce_monomvs		95.00 435	95.25 419	94.22 492	97.51 475	83.34 527	97.86 239	98.44 395	98.51 177	99.29 146	99.30 125	67.68 517	99.56 395	98.89 96	99.81 140	99.77 53

Anonymous20231211		99.27 37	99.27 47	99.26 101	99.29 209	98.18 144	99.49 12	99.51 136	99.70 15	99.80 37	99.68 25	96.84 227	99.83 194	99.21 70	99.91 80	99.77 53

PEN-MVS		99.41 24	99.34 35	99.62 9	99.73 37	99.14 57	99.29 36	99.54 125	99.62 32	99.56 74	99.42 89	98.16 120	99.96 13	98.78 102	99.93 57	99.77 53

WR-MVS_H		99.33 30	99.22 54	99.65 8	99.71 48	99.24 29	99.32 26	99.55 119	99.46 49	99.50 93	99.34 115	97.30 197	99.93 53	98.90 94	99.93 57	99.77 53

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 26	99.85 16	99.11 64	99.90 1	99.78 36	99.63 28	99.78 39	99.67 30	99.48 10	99.81 223	99.30 62	99.97 21	99.77 53
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
WB-MVS		98.52 190	98.55 163	98.43 274	99.65 70	95.59 344	98.52 130	98.77 364	99.65 25	99.52 87	99.00 223	94.34 343	99.93 53	98.65 114	98.83 408	99.76 58

patch_mono-2		98.51 191	98.63 150	98.17 305	99.38 183	94.78 388	97.36 319	99.69 55	98.16 212	98.49 305	99.29 128	97.06 213	99.97 6	98.29 143	99.91 80	99.76 58

nrg030		99.40 25	99.35 33	99.54 31	99.58 93	99.13 60	98.98 76	99.48 149	99.68 19	99.46 101	99.26 137	98.62 64	99.73 295	99.17 74	99.92 71	99.76 58

FIs		99.14 62	99.09 81	99.29 95	99.70 56	98.28 133	99.13 59	99.52 135	99.48 44	99.24 164	99.41 94	96.79 234	99.82 206	98.69 112	99.88 95	99.76 58

v7n		99.53 12	99.57 13	99.41 69	99.88 9	98.54 111	99.45 14	99.61 87	99.66 23	99.68 57	99.66 32	98.44 84	99.95 25	99.73 28	99.96 28	99.75 62

APDe-MVS		98.99 93	98.79 123	99.60 16	99.21 234	99.15 52	98.87 89	99.48 149	97.57 264	99.35 129	99.24 144	97.83 149	99.89 97	97.88 179	99.70 221	99.75 62
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DTE-MVSNet		99.43 22	99.35 33	99.66 7	99.71 48	99.30 21	99.31 30	99.51 136	99.64 26	99.56 74	99.46 80	98.23 108	99.97 6	98.78 102	99.93 57	99.72 64

MSC_two_6792asdad				99.32 91	98.43 399	98.37 124		98.86 349					99.89 97	97.14 250	99.60 266	99.71 65

No_MVS				99.32 91	98.43 399	98.37 124		98.86 349					99.89 97	97.14 250	99.60 266	99.71 65

PMMVS2		98.07 253	98.08 244	98.04 322	99.41 177	94.59 397	94.59 475	99.40 195	97.50 273	98.82 252	98.83 271	96.83 229	99.84 176	97.50 220	99.81 140	99.71 65

Baseline_NR-MVSNet		98.98 97	98.86 114	99.36 74	99.82 19	98.55 108	97.47 305	99.57 106	99.37 60	99.21 170	99.61 43	96.76 237	99.83 194	98.06 160	99.83 126	99.71 65

XXY-MVS		99.14 62	99.15 67	99.10 128	99.76 30	97.74 206	98.85 93	99.62 84	98.48 179	99.37 124	99.49 74	98.75 47	99.86 144	98.20 149	99.80 151	99.71 65

test_0728_THIRD									98.17 209	99.08 186	99.02 208	97.89 145	99.88 115	97.07 256	99.71 212	99.70 70

MSP-MVS		98.40 204	98.00 252	99.61 13	99.57 102	99.25 28	98.57 124	99.35 213	97.55 268	99.31 144	97.71 415	94.61 333	99.88 115	96.14 344	99.19 370	99.70 70
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
SSC-MVS3.2		98.53 186	98.79 123	97.74 350	99.46 160	93.62 439	96.45 385	99.34 219	99.33 65	98.93 227	98.70 302	97.90 141	99.90 81	99.12 76	99.92 71	99.69 72

NormalMVS		98.26 229	97.97 257	99.15 121	99.64 76	97.83 192	98.28 166	99.43 181	99.24 76	98.80 256	98.85 264	89.76 422	99.94 41	98.04 163	99.67 237	99.68 73

KinetiMVS		99.03 87	99.02 89	99.03 145	99.70 56	97.48 228	98.43 148	99.29 248	99.70 15	99.60 71	99.07 195	96.13 272	99.94 41	99.42 55	99.87 100	99.68 73

dcpmvs_2		98.78 132	99.11 73	97.78 343	99.56 110	93.67 436	99.06 66	99.86 17	99.50 43	99.66 60	99.26 137	97.21 205	99.99 2	98.00 168	99.91 80	99.68 73

test_0728_SECOND				99.60 16	99.50 138	99.23 30	98.02 209	99.32 227					99.88 115	96.99 263	99.63 255	99.68 73

OurMVSNet-221017-0		99.37 28	99.31 41	99.53 38	99.91 3	98.98 71	99.63 7	99.58 98	99.44 52	99.78 39	99.76 15	96.39 258	99.92 65	99.44 54	99.92 71	99.68 73

fmvsm_s_conf0.5_n_6		99.08 78	99.21 57	98.69 221	99.36 190	96.51 306	97.62 278	99.68 62	98.43 181	99.85 27	99.10 187	99.12 23	99.88 115	99.77 22	99.92 71	99.67 78

CHOSEN 1792x2688		97.49 305	97.14 321	98.54 257	99.68 63	96.09 324	96.50 383	99.62 84	91.58 488	98.84 247	98.97 232	92.36 387	99.88 115	96.76 286	99.95 39	99.67 78

reproduce_model		99.15 57	98.97 97	99.67 4	99.33 201	99.44 9	98.15 183	99.47 158	99.12 98	99.52 87	99.32 123	98.31 96	99.90 81	97.78 189	99.73 194	99.66 80

IU-MVS					99.49 146	99.15 52		98.87 344	92.97 471	99.41 113				96.76 286	99.62 259	99.66 80

test_241102_TWO								99.30 240	98.03 223	99.26 154	99.02 208	97.51 182	99.88 115	96.91 269	99.60 266	99.66 80

DPE-MVS		98.59 173	98.26 219	99.57 21	99.27 215	99.15 52	97.01 347	99.39 197	97.67 253	99.44 106	98.99 225	97.53 179	99.89 97	95.40 376	99.68 231	99.66 80
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TransMVSNet (Re)		99.44 19	99.47 21	99.36 74	99.80 21	98.58 106	99.27 42	99.57 106	99.39 58	99.75 44	99.62 40	99.17 20	99.83 194	99.06 82	99.62 259	99.66 80

EI-MVSNet-UG-set		98.69 150	98.71 134	98.62 234	99.10 265	96.37 314	97.23 332	98.87 344	99.20 83	99.19 172	98.99 225	97.30 197	99.85 158	98.77 105	99.79 158	99.65 85

Elysia		99.15 57	99.14 68	99.18 113	99.63 82	97.92 181	98.50 137	99.43 181	99.67 20	99.70 51	99.13 179	96.66 244	99.98 4	99.54 44	99.96 28	99.64 86

StellarMVS		99.15 57	99.14 68	99.18 113	99.63 82	97.92 181	98.50 137	99.43 181	99.67 20	99.70 51	99.13 179	96.66 244	99.98 4	99.54 44	99.96 28	99.64 86

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

EI-MVSNet-Vis-set		98.68 156	98.70 137	98.63 232	99.09 268	96.40 313	97.23 332	98.86 349	99.20 83	99.18 177	98.97 232	97.29 199	99.85 158	98.72 109	99.78 163	99.64 86

ACMH	96.65 7	99.25 40	99.24 53	99.26 101	99.72 44	98.38 122	99.07 65	99.55 119	98.30 192	99.65 63	99.45 84	99.22 17	99.76 269	98.44 130	99.77 170	99.64 86
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DP-MVS		98.93 103	98.81 122	99.28 96	99.21 234	98.45 117	98.46 145	99.33 225	99.63 28	99.48 96	99.15 174	97.23 203	99.75 281	97.17 246	99.66 245	99.63 91

reproduce-ours		99.09 72	98.90 104	99.67 4	99.27 215	99.49 5	98.00 213	99.42 187	99.05 116	99.48 96	99.27 131	98.29 98	99.89 97	97.61 208	99.71 212	99.62 92

our_new_method		99.09 72	98.90 104	99.67 4	99.27 215	99.49 5	98.00 213	99.42 187	99.05 116	99.48 96	99.27 131	98.29 98	99.89 97	97.61 208	99.71 212	99.62 92

test_fmvs1_n		98.09 251	98.28 213	97.52 380	99.68 63	93.47 441	98.63 116	99.93 6	95.41 413	99.68 57	99.64 37	91.88 398	99.48 426	99.82 12	99.87 100	99.62 92

test1111		96.49 374	96.82 344	95.52 473	99.42 174	87.08 513	99.22 46	87.14 530	99.11 99	99.46 101	99.58 47	88.69 430	99.86 144	98.80 100	99.95 39	99.62 92

VPA-MVSNet		99.30 33	99.30 44	99.28 96	99.49 146	98.36 127	99.00 73	99.45 167	99.63 28	99.52 87	99.44 85	98.25 106	99.88 115	99.09 79	99.84 114	99.62 92

LPG-MVS_test		98.71 141	98.46 182	99.47 61	99.57 102	98.97 73	98.23 172	99.48 149	96.60 349	99.10 184	99.06 196	98.71 51	99.83 194	95.58 372	99.78 163	99.62 92

LGP-MVS_train				99.47 61	99.57 102	98.97 73		99.48 149	96.60 349	99.10 184	99.06 196	98.71 51	99.83 194	95.58 372	99.78 163	99.62 92

Test_1112_low_res		96.99 352	96.55 367	98.31 289	99.35 195	95.47 356	95.84 430	99.53 129	91.51 490	96.80 434	98.48 343	91.36 406	99.83 194	96.58 307	99.53 293	99.62 92

tt0320-xc		99.64 5	99.68 5	99.50 54	99.72 44	98.98 71	99.51 10	99.85 19	99.86 6	99.88 21	99.82 5	99.02 26	99.90 81	99.54 44	99.95 39	99.61 100

v10		98.97 98	99.11 73	98.55 252	99.44 167	96.21 320	98.90 84	99.55 119	98.73 150	99.48 96	99.60 45	96.63 247	99.83 194	99.70 33	99.99 5	99.61 100

sc_t1		99.62 7	99.66 8	99.53 38	99.82 19	99.09 68	99.50 11	99.63 78	99.88 4	99.86 24	99.80 11	99.03 24	99.89 97	99.48 52	99.93 57	99.60 102

test_vis1_n		98.31 221	98.50 172	97.73 353	99.76 30	94.17 408	98.68 109	99.91 10	96.31 364	99.79 38	99.57 49	92.85 381	99.42 442	99.79 19	99.84 114	99.60 102

v8		99.01 89	99.16 62	98.57 245	99.47 157	96.31 317	98.90 84	99.47 158	99.03 120	99.52 87	99.57 49	96.93 223	99.81 223	99.60 37	99.98 12	99.60 102

EI-MVSNet		98.40 204	98.51 169	98.04 322	99.10 265	94.73 391	97.20 337	98.87 344	98.97 126	99.06 188	99.02 208	96.00 279	99.80 232	98.58 119	99.82 133	99.60 102

SixPastTwentyTwo		98.75 137	98.62 152	99.16 118	99.83 18	97.96 177	99.28 40	98.20 409	99.37 60	99.70 51	99.65 36	92.65 385	99.93 53	99.04 84	99.84 114	99.60 102

IterMVS-LS		98.55 181	98.70 137	98.09 313	99.48 154	94.73 391	97.22 336	99.39 197	98.97 126	99.38 120	99.31 124	96.00 279	99.93 53	98.58 119	99.97 21	99.60 102
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		97.19 335	96.60 365	98.96 161	99.62 86	97.28 248	95.17 455	99.50 139	94.21 446	99.01 202	98.32 364	86.61 445	99.99 2	97.10 254	99.84 114	99.60 102

lecture		99.25 40	99.12 71	99.62 9	99.64 76	99.40 11	98.89 88	99.51 136	99.19 88	99.37 124	99.25 142	98.36 89	99.88 115	98.23 146	99.67 237	99.59 109

tt0320		99.61 8	99.65 9	99.48 57	99.71 48	98.94 78	99.54 8	99.83 26	99.87 5	99.89 18	99.82 5	98.75 47	99.90 81	99.54 44	99.95 39	99.59 109

ACMMP_NAP		98.75 137	98.48 178	99.57 21	99.58 93	99.29 23	97.82 243	99.25 263	96.94 328	98.78 258	99.12 182	98.02 130	99.84 176	97.13 252	99.67 237	99.59 109

VPNet		98.87 111	98.83 119	99.01 150	99.70 56	97.62 218	98.43 148	99.35 213	99.47 47	99.28 148	99.05 203	96.72 241	99.82 206	98.09 157	99.36 332	99.59 109

WR-MVS		98.40 204	98.19 230	99.03 145	99.00 294	97.65 215	96.85 359	98.94 328	98.57 172	98.89 234	98.50 340	95.60 298	99.85 158	97.54 216	99.85 109	99.59 109

HPM-MVS		98.79 130	98.53 167	99.59 20	99.65 70	99.29 23	99.16 55	99.43 181	96.74 344	98.61 285	98.38 354	98.62 64	99.87 135	96.47 321	99.67 237	99.59 109
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EG-PatchMatch MVS		98.99 93	99.01 91	98.94 164	99.50 138	97.47 229	98.04 204	99.59 95	98.15 217	99.40 116	99.36 110	98.58 72	99.76 269	98.78 102	99.68 231	99.59 109

Vis-MVSNet		99.34 29	99.36 32	99.27 99	99.73 37	98.26 135	99.17 54	99.78 36	99.11 99	99.27 150	99.48 75	98.82 38	99.95 25	98.94 91	99.93 57	99.59 109
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MED-MVS test				99.45 64	99.58 93	98.93 79	98.68 109	99.60 89	96.46 358	99.53 83	98.77 284		99.83 194	96.67 298	99.64 249	99.58 117

ME-MVS		98.61 169	98.33 207	99.44 65	99.24 226	98.93 79	97.45 307	99.06 306	98.14 218	99.06 188	98.77 284	96.97 221	99.82 206	96.67 298	99.64 249	99.58 117

MP-MVS-pluss		98.57 176	98.23 224	99.60 16	99.69 60	99.35 16	97.16 342	99.38 199	94.87 427	98.97 212	98.99 225	98.01 131	99.88 115	97.29 238	99.70 221	99.58 117
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
region2R		98.69 150	98.40 190	99.54 31	99.53 126	99.17 43	98.52 130	99.31 232	97.46 281	98.44 311	98.51 336	97.83 149	99.88 115	96.46 322	99.58 275	99.58 117

ACMMPR		98.70 146	98.42 188	99.54 31	99.52 129	99.14 57	98.52 130	99.31 232	97.47 276	98.56 296	98.54 331	97.75 157	99.88 115	96.57 309	99.59 270	99.58 117

PGM-MVS		98.66 160	98.37 197	99.55 28	99.53 126	99.18 42	98.23 172	99.49 147	97.01 325	98.69 270	98.88 258	98.00 132	99.89 97	95.87 357	99.59 270	99.58 117

SteuartSystems-ACMMP		98.79 130	98.54 165	99.54 31	99.73 37	99.16 48	98.23 172	99.31 232	97.92 233	98.90 231	98.90 250	98.00 132	99.88 115	96.15 343	99.72 203	99.58 117
Skip Steuart: Steuart Systems R&D Blog.
SDMVSNet		99.23 45	99.32 39	98.96 161	99.68 63	97.35 237	98.84 95	99.48 149	99.69 17	99.63 66	99.68 25	99.03 24	99.96 13	97.97 172	99.92 71	99.57 124

sd_testset		99.28 36	99.31 41	99.19 112	99.68 63	98.06 164	99.41 17	99.30 240	99.69 17	99.63 66	99.68 25	99.25 16	99.96 13	97.25 241	99.92 71	99.57 124

TranMVSNet+NR-MVSNet		99.17 52	99.07 84	99.46 63	99.37 189	98.87 84	98.39 157	99.42 187	99.42 55	99.36 127	99.06 196	98.38 88	99.95 25	98.34 140	99.90 88	99.57 124

mPP-MVS		98.64 163	98.34 202	99.54 31	99.54 122	99.17 43	98.63 116	99.24 268	97.47 276	98.09 342	98.68 306	97.62 168	99.89 97	96.22 338	99.62 259	99.57 124

PVSNet_Blended_VisFu		98.17 245	98.15 236	98.22 301	99.73 37	95.15 373	97.36 319	99.68 62	94.45 441	98.99 207	99.27 131	96.87 226	99.94 41	97.13 252	99.91 80	99.57 124

1112_ss		97.29 326	96.86 340	98.58 242	99.34 200	96.32 316	96.75 366	99.58 98	93.14 467	96.89 428	97.48 432	92.11 395	99.86 144	96.91 269	99.54 289	99.57 124

MTAPA		98.88 110	98.64 148	99.61 13	99.67 67	99.36 15	98.43 148	99.20 274	98.83 148	98.89 234	98.90 250	96.98 220	99.92 65	97.16 247	99.70 221	99.56 130

XVS		98.72 140	98.45 183	99.53 38	99.46 160	99.21 32	98.65 114	99.34 219	98.62 164	97.54 386	98.63 319	97.50 183	99.83 194	96.79 282	99.53 293	99.56 130

pm-mvs1		99.44 19	99.48 18	99.33 89	99.80 21	98.63 100	99.29 36	99.63 78	99.30 70	99.65 63	99.60 45	99.16 22	99.82 206	99.07 80	99.83 126	99.56 130

X-MVStestdata		94.32 443	92.59 465	99.53 38	99.46 160	99.21 32	98.65 114	99.34 219	98.62 164	97.54 386	45.85 532	97.50 183	99.83 194	96.79 282	99.53 293	99.56 130

HPM-MVS_fast		99.01 89	98.82 120	99.57 21	99.71 48	99.35 16	99.00 73	99.50 139	97.33 294	98.94 226	98.86 261	98.75 47	99.82 206	97.53 217	99.71 212	99.56 130

K. test v3		98.00 260	97.66 287	99.03 145	99.79 23	97.56 221	99.19 53	92.47 513	99.62 32	99.52 87	99.66 32	89.61 424	99.96 13	99.25 67	99.81 140	99.56 130

CP-MVS		98.70 146	98.42 188	99.52 44	99.36 190	99.12 62	98.72 104	99.36 207	97.54 270	98.30 322	98.40 351	97.86 148	99.89 97	96.53 318	99.72 203	99.56 130

viewmacassd2359aftdt		98.86 115	98.87 110	98.83 186	99.53 126	97.32 241	97.70 265	99.64 76	98.22 200	99.25 162	99.27 131	98.40 86	99.61 374	97.98 171	99.87 100	99.55 137

FE-MVSNET		98.59 173	98.50 172	98.87 176	99.58 93	97.30 242	98.08 195	99.74 43	96.94 328	98.97 212	99.10 187	96.94 222	99.74 288	97.33 234	99.86 107	99.55 137

ZNCC-MVS		98.68 156	98.40 190	99.54 31	99.57 102	99.21 32	98.46 145	99.29 248	97.28 300	98.11 340	98.39 352	98.00 132	99.87 135	96.86 279	99.64 249	99.55 137

v1192		98.60 171	98.66 145	98.41 276	99.27 215	95.88 334	97.52 295	99.36 207	97.41 286	99.33 135	99.20 155	96.37 261	99.82 206	99.57 39	99.92 71	99.55 137

v1240		98.55 181	98.62 152	98.32 287	99.22 232	95.58 346	97.51 297	99.45 167	97.16 316	99.45 105	99.24 144	96.12 274	99.85 158	99.60 37	99.88 95	99.55 137

UGNet		98.53 186	98.45 183	98.79 197	97.94 442	96.96 278	99.08 62	98.54 390	99.10 106	96.82 433	99.47 78	96.55 250	99.84 176	98.56 124	99.94 51	99.55 137
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
usedtu_dtu_shiyan2		98.99 93	98.86 114	99.39 72	99.73 37	98.71 97	99.05 68	99.47 158	99.16 93	99.49 94	99.12 182	96.34 263	99.93 53	98.05 162	99.36 332	99.54 143

E5new		99.05 82	99.11 73	98.85 179	99.60 87	97.30 242	98.42 151	99.63 78	98.73 150	99.26 154	99.39 100	98.71 51	99.70 313	98.43 132	99.84 114	99.54 143

E6new		99.05 82	99.11 73	98.85 179	99.60 87	97.30 242	98.42 151	99.63 78	98.73 150	99.26 154	99.39 100	98.71 51	99.70 313	98.43 132	99.84 114	99.54 143

E6		99.05 82	99.11 73	98.85 179	99.60 87	97.30 242	98.42 151	99.63 78	98.73 150	99.26 154	99.39 100	98.71 51	99.70 313	98.43 132	99.84 114	99.54 143

E5		99.05 82	99.11 73	98.85 179	99.60 87	97.30 242	98.42 151	99.63 78	98.73 150	99.26 154	99.39 100	98.71 51	99.70 313	98.43 132	99.84 114	99.54 143

AstraMVS		98.16 247	98.07 246	98.41 276	99.51 132	95.86 335	98.00 213	95.14 491	98.97 126	99.43 107	99.24 144	93.25 368	99.84 176	99.21 70	99.87 100	99.54 143

WBMVS		95.18 430	94.78 432	96.37 436	97.68 462	89.74 501	95.80 431	98.73 373	97.54 270	98.30 322	98.44 347	70.06 511	99.82 206	96.62 304	99.87 100	99.54 143

test2506		92.39 477	91.89 479	93.89 497	99.38 183	82.28 531	99.32 26	66.03 538	99.08 113	98.77 261	99.57 49	66.26 521	99.84 176	98.71 110	99.95 39	99.54 143

ECVR-MVS		96.42 379	96.61 363	95.85 462	99.38 183	88.18 508	99.22 46	86.00 532	99.08 113	99.36 127	99.57 49	88.47 435	99.82 206	98.52 127	99.95 39	99.54 143

v144192		98.54 184	98.57 161	98.45 271	99.21 234	95.98 329	97.63 277	99.36 207	97.15 318	99.32 141	99.18 162	95.84 291	99.84 176	99.50 50	99.91 80	99.54 143

v1921920		98.54 184	98.60 157	98.38 280	99.20 238	95.76 342	97.56 289	99.36 207	97.23 310	99.38 120	99.17 166	96.02 277	99.84 176	99.57 39	99.90 88	99.54 143

MP-MVS		98.46 196	98.09 241	99.54 31	99.57 102	99.22 31	98.50 137	99.19 278	97.61 260	97.58 382	98.66 311	97.40 191	99.88 115	94.72 392	99.60 266	99.54 143
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MIMVSNet1		99.38 27	99.32 39	99.55 28	99.86 14	99.19 41	99.41 17	99.59 95	99.59 36	99.71 49	99.57 49	97.12 210	99.90 81	99.21 70	99.87 100	99.54 143

ACMMP		98.75 137	98.50 172	99.52 44	99.56 110	99.16 48	98.87 89	99.37 203	97.16 316	98.82 252	99.01 219	97.71 159	99.87 135	96.29 335	99.69 225	99.54 143
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
SMA-MVS		98.40 204	98.03 249	99.51 49	99.16 253	99.21 32	98.05 202	99.22 271	94.16 448	98.98 208	99.10 187	97.52 181	99.79 245	96.45 323	99.64 249	99.53 157
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
HFP-MVS		98.71 141	98.44 185	99.51 49	99.49 146	99.16 48	98.52 130	99.31 232	97.47 276	98.58 292	98.50 340	97.97 136	99.85 158	96.57 309	99.59 270	99.53 157

UniMVSNet_NR-MVSNet		98.86 115	98.68 140	99.40 71	99.17 251	98.74 91	97.68 267	99.40 195	99.14 97	99.06 188	98.59 327	96.71 242	99.93 53	98.57 121	99.77 170	99.53 157

E4		98.87 111	98.88 107	98.81 190	99.52 129	97.23 252	97.62 278	99.61 87	98.58 170	99.18 177	99.33 118	98.29 98	99.69 322	97.99 170	99.83 126	99.52 160

GST-MVS		98.61 169	98.30 210	99.52 44	99.51 132	99.20 38	98.26 170	99.25 263	97.44 284	98.67 274	98.39 352	97.68 160	99.85 158	96.00 349	99.51 299	99.52 160

MGCNet		97.44 310	97.01 329	98.72 217	96.42 510	96.74 294	97.20 337	91.97 520	98.46 180	98.30 322	98.79 280	92.74 383	99.91 74	99.30 62	99.94 51	99.52 160

TDRefinement		99.42 23	99.38 28	99.55 28	99.76 30	99.33 20	99.68 6	99.71 47	99.38 59	99.53 83	99.61 43	98.64 61	99.80 232	98.24 144	99.84 114	99.52 160

FE-MVSNET2		99.15 57	99.22 54	98.94 164	99.70 56	97.49 225	98.62 118	99.67 68	98.85 144	99.34 132	99.54 62	98.47 77	99.81 223	98.93 92	99.91 80	99.51 164

v1144		98.60 171	98.66 145	98.41 276	99.36 190	95.90 333	97.58 287	99.34 219	97.51 272	99.27 150	99.15 174	96.34 263	99.80 232	99.47 53	99.93 57	99.51 164

v2v482		98.56 177	98.62 152	98.37 283	99.42 174	95.81 339	97.58 287	99.16 289	97.90 235	99.28 148	99.01 219	95.98 284	99.79 245	99.33 59	99.90 88	99.51 164

CPTT-MVS		97.84 281	97.36 306	99.27 99	99.31 203	98.46 116	98.29 165	99.27 255	94.90 426	97.83 365	98.37 355	94.90 320	99.84 176	93.85 420	99.54 289	99.51 164

casdiffseed414692147		99.09 72	99.12 71	99.01 150	99.55 116	97.91 183	98.30 164	99.68 62	99.04 118	99.19 172	99.37 104	98.98 28	99.61 374	98.13 153	99.83 126	99.50 168

viewdifsd2359ckpt11		98.84 118	99.04 86	98.24 297	99.56 110	95.51 349	97.38 314	99.70 52	99.16 93	99.57 72	99.40 97	98.26 104	99.71 306	98.55 125	99.82 133	99.50 168

viewmsd2359difaftdt		98.84 118	99.04 86	98.24 297	99.56 110	95.51 349	97.38 314	99.70 52	99.16 93	99.57 72	99.40 97	98.26 104	99.71 306	98.55 125	99.82 133	99.50 168

LuminaMVS		98.39 210	98.20 226	98.98 157	99.50 138	97.49 225	97.78 249	97.69 424	98.75 149	99.49 94	99.25 142	92.30 390	99.94 41	99.14 75	99.88 95	99.50 168

DU-MVS		98.82 124	98.63 150	99.39 72	99.16 253	98.74 91	97.54 293	99.25 263	98.84 147	99.06 188	98.76 289	96.76 237	99.93 53	98.57 121	99.77 170	99.50 168

NR-MVSNet		98.95 101	98.82 120	99.36 74	99.16 253	98.72 96	99.22 46	99.20 274	99.10 106	99.72 47	98.76 289	96.38 260	99.86 144	98.00 168	99.82 133	99.50 168

casdiffmvs_mvg		99.12 69	99.16 62	98.99 153	99.43 172	97.73 208	98.00 213	99.62 84	99.22 79	99.55 77	99.22 151	98.93 33	99.75 281	98.66 113	99.81 140	99.50 168
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMH+	96.62 9	99.08 78	99.00 93	99.33 89	99.71 48	98.83 86	98.60 121	99.58 98	99.11 99	99.53 83	99.18 162	98.81 39	99.67 336	96.71 293	99.77 170	99.50 168

SymmetryMVS		98.05 255	97.71 282	99.09 132	99.29 209	97.83 192	98.28 166	97.64 429	99.24 76	98.80 256	98.85 264	89.76 422	99.94 41	98.04 163	99.50 307	99.49 176

DVP-MVS++		98.90 107	98.70 137	99.51 49	98.43 399	99.15 52	99.43 15	99.32 227	98.17 209	99.26 154	99.02 208	98.18 116	99.88 115	97.07 256	99.45 315	99.49 176

PC_three_1452									93.27 464	99.40 116	98.54 331	98.22 111	97.00 516	95.17 380	99.45 315	99.49 176

GeoE		99.05 82	98.99 95	99.25 104	99.44 167	98.35 128	98.73 103	99.56 115	98.42 182	98.91 230	98.81 277	98.94 31	99.91 74	98.35 139	99.73 194	99.49 176

h-mvs33		97.77 285	97.33 309	99.10 128	99.21 234	97.84 191	98.35 161	98.57 387	99.11 99	98.58 292	99.02 208	88.65 433	99.96 13	98.11 155	96.34 498	99.49 176

IterMVS-SCA-FT		97.85 280	98.18 231	96.87 418	99.27 215	91.16 484	95.53 440	99.25 263	99.10 106	99.41 113	99.35 111	93.10 374	99.96 13	98.65 114	99.94 51	99.49 176

new-patchmatchnet		98.35 213	98.74 127	97.18 399	99.24 226	92.23 465	96.42 389	99.48 149	98.30 192	99.69 55	99.53 64	97.44 189	99.82 206	98.84 99	99.77 170	99.49 176

APD-MVS		98.10 249	97.67 284	99.42 67	99.11 263	98.93 79	97.76 255	99.28 252	94.97 424	98.72 267	98.77 284	97.04 214	99.85 158	93.79 421	99.54 289	99.49 176
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EPP-MVSNet		98.30 222	98.04 248	99.07 135	99.56 110	97.83 192	99.29 36	98.07 415	99.03 120	98.59 290	99.13 179	92.16 392	99.90 81	96.87 277	99.68 231	99.49 176

DeepC-MVS	97.60 4	98.97 98	98.93 100	99.10 128	99.35 195	97.98 173	98.01 212	99.46 163	97.56 266	99.54 79	99.50 68	98.97 29	99.84 176	98.06 160	99.92 71	99.49 176
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMM	96.08 12	98.91 105	98.73 129	99.48 57	99.55 116	99.14 57	98.07 199	99.37 203	97.62 257	99.04 198	98.96 236	98.84 37	99.79 245	97.43 228	99.65 247	99.49 176
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
guyue		98.01 259	97.93 263	98.26 293	99.45 165	95.48 353	98.08 195	96.24 471	98.89 137	99.34 132	99.14 177	91.32 407	99.82 206	99.07 80	99.83 126	99.48 187

DVP-MVS		98.77 135	98.52 168	99.52 44	99.50 138	99.21 32	98.02 209	98.84 353	97.97 227	99.08 186	99.02 208	97.61 170	99.88 115	96.99 263	99.63 255	99.48 187
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
SR-MVS		98.71 141	98.43 186	99.57 21	99.18 249	99.35 16	98.36 160	99.29 248	98.29 195	98.88 238	98.85 264	97.53 179	99.87 135	96.14 344	99.31 344	99.48 187

TSAR-MVS + MP.		98.63 165	98.49 177	99.06 141	99.64 76	97.90 185	98.51 135	98.94 328	96.96 326	99.24 164	98.89 256	97.83 149	99.81 223	96.88 276	99.49 310	99.48 187
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
VDDNet		98.21 237	97.95 258	99.01 150	99.58 93	97.74 206	99.01 71	97.29 440	99.67 20	98.97 212	99.50 68	90.45 416	99.80 232	97.88 179	99.20 367	99.48 187

IterMVS		97.73 287	98.11 240	96.57 429	99.24 226	90.28 495	95.52 442	99.21 272	98.86 141	99.33 135	99.33 118	93.11 373	99.94 41	98.49 128	99.94 51	99.48 187
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IS-MVSNet		98.19 240	97.90 267	99.08 133	99.57 102	97.97 174	99.31 30	98.32 402	99.01 122	98.98 208	99.03 207	91.59 400	99.79 245	95.49 374	99.80 151	99.48 187

ACMP	95.32 15	98.41 201	98.09 241	99.36 74	99.51 132	98.79 89	97.68 267	99.38 199	95.76 396	98.81 254	98.82 274	98.36 89	99.82 206	94.75 389	99.77 170	99.48 187
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MCST-MVS		98.00 260	97.63 290	99.10 128	99.24 226	98.17 145	96.89 358	98.73 373	95.66 398	97.92 356	97.70 417	97.17 207	99.66 349	96.18 342	99.23 361	99.47 195

3Dnovator+	97.89 3	98.69 150	98.51 169	99.24 106	98.81 334	98.40 120	99.02 70	99.19 278	98.99 123	98.07 344	99.28 129	97.11 212	99.84 176	96.84 280	99.32 342	99.47 195

hybridcas		99.08 78	99.13 70	98.92 170	99.54 122	97.61 219	98.22 176	99.66 69	99.27 73	99.40 116	99.24 144	98.47 77	99.70 313	98.59 118	99.80 151	99.46 197

diffmvs_AUTHOR		98.50 192	98.59 159	98.23 300	99.35 195	95.48 353	96.61 375	99.60 89	98.37 183	98.90 231	99.00 223	97.37 193	99.76 269	98.22 147	99.85 109	99.46 197

HPM-MVS++		98.10 249	97.64 289	99.48 57	99.09 268	99.13 60	97.52 295	98.75 370	97.46 281	96.90 427	97.83 408	96.01 278	99.84 176	95.82 361	99.35 335	99.46 197

V42		98.78 132	98.78 125	98.76 207	99.44 167	97.04 272	98.27 169	99.19 278	97.87 237	99.25 162	99.16 168	96.84 227	99.78 257	99.21 70	99.84 114	99.46 197

APD-MVS_3200maxsize		98.84 118	98.61 156	99.53 38	99.19 241	99.27 26	98.49 140	99.33 225	98.64 159	99.03 201	98.98 230	97.89 145	99.85 158	96.54 317	99.42 325	99.46 197

UniMVSNet (Re)		98.87 111	98.71 134	99.35 80	99.24 226	98.73 94	97.73 262	99.38 199	98.93 131	99.12 180	98.73 292	96.77 235	99.86 144	98.63 116	99.80 151	99.46 197

SR-MVS-dyc-post		98.81 126	98.55 163	99.57 21	99.20 238	99.38 12	98.48 143	99.30 240	98.64 159	98.95 218	98.96 236	97.49 186	99.86 144	96.56 313	99.39 328	99.45 203

RE-MVS-def			98.58 160		99.20 238	99.38 12	98.48 143	99.30 240	98.64 159	98.95 218	98.96 236	97.75 157		96.56 313	99.39 328	99.45 203

HQP_MVS		97.99 263	97.67 284	98.93 167	99.19 241	97.65 215	97.77 252	99.27 255	98.20 206	97.79 368	97.98 396	94.90 320	99.70 313	94.42 401	99.51 299	99.45 203

plane_prior5								99.27 255					99.70 313	94.42 401	99.51 299	99.45 203

lessismore_v0				98.97 159	99.73 37	97.53 224		86.71 531		99.37 124	99.52 67	89.93 419	99.92 65	98.99 88	99.72 203	99.44 207

TAMVS		98.24 233	98.05 247	98.80 193	99.07 272	97.18 262	97.88 235	98.81 358	96.66 348	99.17 179	99.21 153	94.81 326	99.77 263	96.96 267	99.88 95	99.44 207

DeepPCF-MVS	96.93 5	98.32 219	98.01 251	99.23 108	98.39 404	98.97 73	95.03 459	99.18 282	96.88 334	99.33 135	98.78 282	98.16 120	99.28 463	96.74 288	99.62 259	99.44 207

3Dnovator	98.27 2	98.81 126	98.73 129	99.05 142	98.76 340	97.81 200	99.25 43	99.30 240	98.57 172	98.55 298	99.33 118	97.95 138	99.90 81	97.16 247	99.67 237	99.44 207

E2		98.70 146	98.68 140	98.73 215	99.40 179	97.10 269	97.48 301	99.57 106	98.09 220	99.00 203	99.20 155	97.90 141	99.67 336	97.73 199	99.77 170	99.43 211

E3		98.69 150	98.68 140	98.73 215	99.40 179	97.10 269	97.48 301	99.57 106	98.09 220	99.00 203	99.20 155	97.90 141	99.67 336	97.73 199	99.77 170	99.43 211

MVSFormer		98.26 229	98.43 186	97.77 344	98.88 319	93.89 429	99.39 20	99.56 115	99.11 99	98.16 334	98.13 381	93.81 359	99.97 6	99.26 65	99.57 279	99.43 211

jason		97.45 309	97.35 307	97.76 347	99.24 226	93.93 425	95.86 427	98.42 398	94.24 445	98.50 304	98.13 381	94.82 324	99.91 74	97.22 243	99.73 194	99.43 211
jason: jason.
NCCC		97.86 275	97.47 301	99.05 142	98.61 374	98.07 161	96.98 350	98.90 338	97.63 256	97.04 417	97.93 401	95.99 283	99.66 349	95.31 377	98.82 410	99.43 211

Anonymous20240521		98.69 150	98.87 110	98.16 307	99.77 27	95.11 376	99.08 62	99.44 175	99.34 64	99.33 135	99.55 56	94.10 354	99.94 41	99.25 67	99.96 28	99.42 216

MVS_111021_HR		98.25 232	98.08 244	98.75 209	99.09 268	97.46 231	95.97 418	99.27 255	97.60 262	97.99 352	98.25 370	98.15 122	99.38 448	96.87 277	99.57 279	99.42 216

COLMAP_ROB	96.50 10	98.99 93	98.85 117	99.41 69	99.58 93	99.10 65	98.74 99	99.56 115	99.09 109	99.33 135	99.19 158	98.40 86	99.72 305	95.98 351	99.76 186	99.42 216
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SED-MVS		98.91 105	98.72 131	99.49 55	99.49 146	99.17 43	98.10 192	99.31 232	98.03 223	99.66 60	99.02 208	98.36 89	99.88 115	96.91 269	99.62 259	99.41 219

OPU-MVS				98.82 188	98.59 379	98.30 132	98.10 192				98.52 335	98.18 116	98.75 490	94.62 393	99.48 311	99.41 219

our_test_3		97.39 315	97.73 280	96.34 437	98.70 354	89.78 500	94.61 474	98.97 327	96.50 354	99.04 198	98.85 264	95.98 284	99.84 176	97.26 240	99.67 237	99.41 219

casdiffmvs		98.95 101	99.00 93	98.81 190	99.38 183	97.33 239	97.82 243	99.57 106	99.17 92	99.35 129	99.17 166	98.35 93	99.69 322	98.46 129	99.73 194	99.41 219
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
YYNet1		97.60 296	97.67 284	97.39 391	99.04 281	93.04 448	95.27 451	98.38 401	97.25 304	98.92 229	98.95 240	95.48 304	99.73 295	96.99 263	98.74 413	99.41 219

MDA-MVSNet_test_wron		97.60 296	97.66 287	97.41 390	99.04 281	93.09 444	95.27 451	98.42 398	97.26 303	98.88 238	98.95 240	95.43 306	99.73 295	97.02 259	98.72 415	99.41 219

GBi-Net		98.65 161	98.47 180	99.17 115	98.90 313	98.24 137	99.20 49	99.44 175	98.59 167	98.95 218	99.55 56	94.14 350	99.86 144	97.77 191	99.69 225	99.41 219

test1		98.65 161	98.47 180	99.17 115	98.90 313	98.24 137	99.20 49	99.44 175	98.59 167	98.95 218	99.55 56	94.14 350	99.86 144	97.77 191	99.69 225	99.41 219

FMVSNet1		99.17 52	99.17 60	99.17 115	99.55 116	98.24 137	99.20 49	99.44 175	99.21 81	99.43 107	99.55 56	97.82 152	99.86 144	98.42 136	99.89 94	99.41 219

test_fmvs1		97.72 288	97.94 261	97.07 407	98.66 369	92.39 460	97.68 267	99.81 32	95.20 420	99.54 79	99.44 85	91.56 402	99.41 443	99.78 21	99.77 170	99.40 228

viewdifsd2359ckpt07		98.71 141	98.86 114	98.26 293	99.43 172	95.65 343	97.20 337	99.66 69	99.20 83	99.29 146	99.01 219	98.29 98	99.73 295	97.92 175	99.75 190	99.39 229

viewmanbaseed2359cas		98.58 175	98.54 165	98.70 219	99.28 212	97.13 268	97.47 305	99.55 119	97.55 268	98.96 217	98.92 244	97.77 155	99.59 383	97.59 211	99.77 170	99.39 229

KD-MVS_self_test		99.25 40	99.18 59	99.44 65	99.63 82	99.06 70	98.69 108	99.54 125	99.31 68	99.62 69	99.53 64	97.36 194	99.86 144	99.24 69	99.71 212	99.39 229

v148		98.45 198	98.60 157	98.00 325	99.44 167	94.98 379	97.44 309	99.06 306	98.30 192	99.32 141	98.97 232	96.65 246	99.62 367	98.37 138	99.85 109	99.39 229

test20.03		98.78 132	98.77 126	98.78 200	99.46 160	97.20 258	97.78 249	99.24 268	99.04 118	99.41 113	98.90 250	97.65 163	99.76 269	97.70 201	99.79 158	99.39 229

CDPH-MVS		97.26 327	96.66 358	99.07 135	99.00 294	98.15 146	96.03 415	99.01 321	91.21 494	97.79 368	97.85 406	96.89 225	99.69 322	92.75 454	99.38 331	99.39 229

EPNet		96.14 393	95.44 408	98.25 295	90.76 535	95.50 352	97.92 230	94.65 494	98.97 126	92.98 511	98.85 264	89.12 428	99.87 135	95.99 350	99.68 231	99.39 229
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNVR-MVS		98.17 245	97.87 269	99.07 135	98.67 364	98.24 137	97.01 347	98.93 331	97.25 304	97.62 378	98.34 359	97.27 200	99.57 392	96.42 325	99.33 339	99.39 229

DeepC-MVS_fast	96.85 6	98.30 222	98.15 236	98.75 209	98.61 374	97.23 252	97.76 255	99.09 302	97.31 297	98.75 264	98.66 311	97.56 174	99.64 361	96.10 348	99.55 287	99.39 229
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SF-MVS		98.53 186	98.27 216	99.32 91	99.31 203	98.75 90	98.19 177	99.41 191	96.77 343	98.83 249	98.90 250	97.80 153	99.82 206	95.68 367	99.52 296	99.38 238

test9_res														93.28 437	99.15 375	99.38 238

BP-MVS1		97.40 314	96.97 331	98.71 218	99.07 272	96.81 289	98.34 163	97.18 444	98.58 170	98.17 331	98.61 324	84.01 473	99.94 41	98.97 89	99.78 163	99.37 240

OPM-MVS		98.56 177	98.32 208	99.25 104	99.41 177	98.73 94	97.13 344	99.18 282	97.10 319	98.75 264	98.92 244	98.18 116	99.65 356	96.68 297	99.56 283	99.37 240
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
agg_prior2														92.50 461	99.16 373	99.37 240

AllTest		98.44 199	98.20 226	99.16 118	99.50 138	98.55 108	98.25 171	99.58 98	96.80 340	98.88 238	99.06 196	97.65 163	99.57 392	94.45 399	99.61 264	99.37 240

TestCases				99.16 118	99.50 138	98.55 108		99.58 98	96.80 340	98.88 238	99.06 196	97.65 163	99.57 392	94.45 399	99.61 264	99.37 240

MDA-MVSNet-bldmvs		97.94 266	97.91 266	98.06 319	99.44 167	94.96 380	96.63 374	99.15 294	98.35 185	98.83 249	99.11 184	94.31 345	99.85 158	96.60 306	98.72 415	99.37 240

MVSTER		96.86 357	96.55 367	97.79 342	97.91 444	94.21 406	97.56 289	98.87 344	97.49 275	99.06 188	99.05 203	80.72 486	99.80 232	98.44 130	99.82 133	99.37 240

viewcassd2359sk11		98.55 181	98.51 169	98.67 224	99.29 209	96.99 275	97.39 312	99.54 125	97.73 248	98.81 254	99.08 194	97.55 175	99.66 349	97.52 219	99.67 237	99.36 247

pmmvs5		97.64 294	97.49 298	98.08 316	99.14 258	95.12 375	96.70 369	99.05 310	93.77 458	98.62 283	98.83 271	93.23 369	99.75 281	98.33 142	99.76 186	99.36 247

Anonymous20231206		98.21 237	98.21 225	98.20 302	99.51 132	95.43 358	98.13 185	99.32 227	96.16 373	98.93 227	98.82 274	96.00 279	99.83 194	97.32 236	99.73 194	99.36 247

train_agg		97.10 340	96.45 374	99.07 135	98.71 350	98.08 159	95.96 420	99.03 315	91.64 486	95.85 468	97.53 426	96.47 253	99.76 269	93.67 424	99.16 373	99.36 247

PVSNet_BlendedMVS		97.55 301	97.53 295	97.60 369	98.92 309	93.77 433	96.64 373	99.43 181	94.49 436	97.62 378	99.18 162	96.82 230	99.67 336	94.73 390	99.93 57	99.36 247

hybrid		98.22 234	98.27 216	98.08 316	99.13 260	95.24 367	96.61 375	99.53 129	97.43 285	98.46 308	98.97 232	96.75 240	99.65 356	97.84 184	99.69 225	99.35 252

Anonymous20240529		98.93 103	98.87 110	99.12 124	99.19 241	98.22 142	99.01 71	98.99 324	99.25 75	99.54 79	99.37 104	97.04 214	99.80 232	97.89 176	99.52 296	99.35 252

F-COLMAP		97.30 324	96.68 354	99.14 122	99.19 241	98.39 121	97.27 331	99.30 240	92.93 472	96.62 443	98.00 394	95.73 294	99.68 332	92.62 457	98.46 435	99.35 252

viewdifsd2359ckpt13		98.39 210	98.29 212	98.70 219	99.26 224	97.19 259	97.51 297	99.48 149	96.94 328	98.58 292	98.82 274	97.47 188	99.55 399	97.21 244	99.33 339	99.34 255

ppachtmachnet_test		97.50 302	97.74 277	96.78 424	98.70 354	91.23 483	94.55 476	99.05 310	96.36 361	99.21 170	98.79 280	96.39 258	99.78 257	96.74 288	99.82 133	99.34 255

VDD-MVS		98.56 177	98.39 193	99.07 135	99.13 260	98.07 161	98.59 122	97.01 449	99.59 36	99.11 181	99.27 131	94.82 324	99.79 245	98.34 140	99.63 255	99.34 255

testgi		98.32 219	98.39 193	98.13 309	99.57 102	95.54 347	97.78 249	99.49 147	97.37 291	99.19 172	97.65 419	98.96 30	99.49 422	96.50 320	98.99 396	99.34 255

diffmvs		98.22 234	98.24 223	98.17 305	99.00 294	95.44 357	96.38 391	99.58 98	97.79 244	98.53 301	98.50 340	96.76 237	99.74 288	97.95 174	99.64 249	99.34 255
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UnsupCasMVSNet_eth		97.89 270	97.60 292	98.75 209	99.31 203	97.17 264	97.62 278	99.35 213	98.72 156	98.76 263	98.68 306	92.57 386	99.74 288	97.76 195	95.60 512	99.34 255

viewmambaseed2359dif		98.19 240	98.26 219	97.99 327	99.02 291	95.03 378	96.59 378	99.53 129	96.21 368	99.00 203	98.99 225	97.62 168	99.61 374	97.62 207	99.72 203	99.33 261

baseline		98.96 100	99.02 89	98.76 207	99.38 183	97.26 250	98.49 140	99.50 139	98.86 141	99.19 172	99.06 196	98.23 108	99.69 322	98.71 110	99.76 186	99.33 261

MG-MVS		96.77 361	96.61 363	97.26 396	98.31 409	93.06 445	95.93 423	98.12 414	96.45 359	97.92 356	98.73 292	93.77 361	99.39 446	91.19 484	99.04 387	99.33 261

DKM		98.18 242	97.95 258	98.85 179	99.35 195	98.31 131	96.68 370	99.69 55	96.90 333	98.61 285	98.77 284	94.41 338	98.93 483	97.32 236	99.84 114	99.32 264

HQP4-MVS										95.56 474			99.54 405			99.32 264

CDS-MVSNet		97.69 290	97.35 307	98.69 221	98.73 344	97.02 274	96.92 357	98.75 370	95.89 386	98.59 290	98.67 308	92.08 396	99.74 288	96.72 291	99.81 140	99.32 264
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HQP-MVS		97.00 351	96.49 370	98.55 252	98.67 364	96.79 290	96.29 398	99.04 313	96.05 376	95.55 475	96.84 453	93.84 357	99.54 405	92.82 450	99.26 356	99.32 264

RPSCF		98.62 168	98.36 198	99.42 67	99.65 70	99.42 10	98.55 126	99.57 106	97.72 250	98.90 231	99.26 137	96.12 274	99.52 411	95.72 364	99.71 212	99.32 264

E3new		98.41 201	98.34 202	98.62 234	99.19 241	96.90 283	97.32 322	99.50 139	97.40 288	98.63 279	98.92 244	97.21 205	99.65 356	97.34 232	99.52 296	99.31 269

MVP-Stereo		98.08 252	97.92 264	98.57 245	98.96 301	96.79 290	97.90 233	99.18 282	96.41 360	98.46 308	98.95 240	95.93 288	99.60 378	96.51 319	98.98 399	99.31 269
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 204	98.68 140	97.54 378	98.96 301	97.99 170	97.88 235	99.36 207	98.20 206	99.63 66	99.04 205	98.76 46	95.33 527	96.56 313	99.74 191	99.31 269
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
VNet		98.42 200	98.30 210	98.79 197	98.79 339	97.29 247	98.23 172	98.66 378	99.31 68	98.85 245	98.80 278	94.80 327	99.78 257	98.13 153	99.13 378	99.31 269

test_prior				98.95 163	98.69 359	97.95 178		99.03 315					99.59 383			99.30 273

USDC		97.41 313	97.40 302	97.44 388	98.94 303	93.67 436	95.17 455	99.53 129	94.03 454	98.97 212	99.10 187	95.29 309	99.34 453	95.84 360	99.73 194	99.30 273

viewdifsd2359ckpt09		98.13 248	97.92 264	98.77 205	99.18 249	97.35 237	97.29 326	99.53 129	95.81 393	98.09 342	98.47 344	96.34 263	99.66 349	97.02 259	99.51 299	99.29 275

test_fmvsm_n_1920		99.33 30	99.45 23	98.99 153	99.57 102	97.73 208	97.93 227	99.83 26	99.22 79	99.93 6	99.30 125	99.42 11	99.96 13	99.85 6	99.99 5	99.29 275

FMVSNet2		98.49 193	98.40 190	98.75 209	98.90 313	97.14 267	98.61 120	99.13 296	98.59 167	99.19 172	99.28 129	94.14 350	99.82 206	97.97 172	99.80 151	99.29 275

RoMa-SfM		98.46 196	98.27 216	99.02 148	99.35 195	98.32 130	97.56 289	99.70 52	95.88 387	99.38 120	98.65 313	96.41 256	99.46 433	97.78 189	99.71 212	99.28 278

gbinet_0.2-2-1-0.02		95.44 422	94.55 437	98.14 308	95.99 518	95.34 364	94.71 467	98.29 404	96.00 381	96.05 465	90.50 527	84.99 462	99.79 245	97.33 234	97.07 489	99.28 278

XVG-OURS-SEG-HR		98.49 193	98.28 213	99.14 122	99.49 146	98.83 86	96.54 379	99.48 149	97.32 296	99.11 181	98.61 324	99.33 15	99.30 459	96.23 337	98.38 437	99.28 278

mamba_0408		98.80 128	98.88 107	98.55 252	99.27 215	96.50 307	98.00 213	99.60 89	98.93 131	99.22 167	98.84 269	98.59 67	99.89 97	97.74 197	99.72 203	99.27 281

SSM_04072		98.80 128	98.88 107	98.56 250	99.27 215	96.50 307	98.00 213	99.60 89	98.93 131	99.22 167	98.84 269	98.59 67	99.90 81	97.74 197	99.72 203	99.27 281

SSM_0407		98.86 115	98.96 99	98.55 252	99.27 215	96.50 307	98.04 204	99.66 69	99.09 109	99.22 167	99.02 208	98.79 43	99.87 135	97.87 181	99.72 203	99.27 281

test12				98.93 167	98.58 381	97.83 192		98.66 378		96.53 448		95.51 302	99.69 322		99.13 378	99.27 281

DSMNet-mixed		97.42 312	97.60 292	96.87 418	99.15 257	91.46 473	98.54 128	99.12 297	92.87 475	97.58 382	99.63 39	96.21 269	99.90 81	95.74 363	99.54 289	99.27 281

N_pmnet		97.63 295	97.17 317	98.99 153	99.27 215	97.86 189	95.98 417	93.41 510	95.25 417	99.47 100	98.90 250	95.63 297	99.85 158	96.91 269	99.73 194	99.27 281

ambc				98.24 297	98.82 331	95.97 331	98.62 118	99.00 323		99.27 150	99.21 153	96.99 219	99.50 418	96.55 316	99.50 307	99.26 287

LFMVS		97.20 334	96.72 351	98.64 228	98.72 346	96.95 279	98.93 82	94.14 505	99.74 12	98.78 258	99.01 219	84.45 468	99.73 295	97.44 227	99.27 352	99.25 288

FMVSNet5		96.01 397	95.20 423	98.41 276	97.53 470	96.10 321	98.74 99	99.50 139	97.22 313	98.03 349	99.04 205	69.80 512	99.88 115	97.27 239	99.71 212	99.25 288

BH-RMVSNet		96.83 358	96.58 366	97.58 371	98.47 392	94.05 413	96.67 371	97.36 434	96.70 347	97.87 361	97.98 396	95.14 315	99.44 438	90.47 494	98.58 430	99.25 288

testf1		99.25 40	99.16 62	99.51 49	99.89 6	99.63 3	98.71 106	99.69 55	98.90 135	99.43 107	99.35 111	98.86 35	99.67 336	97.81 186	99.81 140	99.24 291

APD_test2		99.25 40	99.16 62	99.51 49	99.89 6	99.63 3	98.71 106	99.69 55	98.90 135	99.43 107	99.35 111	98.86 35	99.67 336	97.81 186	99.81 140	99.24 291

SSM_0404		98.90 107	99.01 91	98.57 245	99.42 174	96.59 299	98.13 185	99.66 69	99.09 109	99.30 145	99.02 208	98.79 43	99.89 97	97.87 181	99.80 151	99.23 293

旧先验1					98.82 331	97.45 232		98.76 366			98.34 359	95.50 303			99.01 393	99.23 293

test222					98.92 309	96.93 281	95.54 439	98.78 363	85.72 520	96.86 431	98.11 384	94.43 337			99.10 383	99.23 293

XVG-ACMP-BASELINE		98.56 177	98.34 202	99.22 109	99.54 122	98.59 105	97.71 263	99.46 163	97.25 304	98.98 208	98.99 225	97.54 177	99.84 176	95.88 354	99.74 191	99.23 293

FMVSNet3		97.50 302	97.24 313	98.29 291	98.08 435	95.83 337	97.86 239	98.91 337	97.89 236	98.95 218	98.95 240	87.06 442	99.81 223	97.77 191	99.69 225	99.23 293

icg_test_0407_2		98.20 239	98.38 195	97.65 362	99.03 284	94.03 416	95.78 432	99.45 167	98.16 212	99.06 188	98.71 295	98.27 102	99.68 332	97.50 220	99.45 315	99.22 298

IMVS_0407		98.39 210	98.64 148	97.66 360	99.03 284	94.03 416	98.10 192	99.45 167	98.16 212	99.06 188	98.71 295	98.27 102	99.71 306	97.50 220	99.45 315	99.22 298

IMVS_0404		98.07 253	98.20 226	97.69 355	99.03 284	94.03 416	96.67 371	99.45 167	98.16 212	98.03 349	98.71 295	96.80 233	99.82 206	97.50 220	99.45 315	99.22 298

IMVS_0403		98.34 214	98.56 162	97.66 360	99.03 284	94.03 416	97.98 221	99.45 167	98.16 212	98.89 234	98.71 295	97.90 141	99.74 288	97.50 220	99.45 315	99.22 298

无先验							95.74 434	98.74 372	89.38 507				99.73 295	92.38 464		99.22 298

blended_shiyan8		95.98 400	95.33 414	97.94 330	97.05 491	94.87 385	95.34 449	98.59 384	96.17 369	97.09 413	92.39 518	87.62 441	99.76 269	97.65 204	96.05 509	99.20 303

tttt0517		95.64 414	94.98 427	97.64 365	99.36 190	93.81 431	98.72 104	90.47 524	98.08 222	98.67 274	98.34 359	73.88 507	99.92 65	97.77 191	99.51 299	99.20 303

pmmvs-eth3d		98.47 195	98.34 202	98.86 178	99.30 207	97.76 204	97.16 342	99.28 252	95.54 405	99.42 111	99.19 158	97.27 200	99.63 364	97.89 176	99.97 21	99.20 303

MS-PatchMatch		97.68 291	97.75 276	97.45 387	98.23 421	93.78 432	97.29 326	98.84 353	96.10 375	98.64 278	98.65 313	96.04 276	99.36 449	96.84 280	99.14 376	99.20 303

新几何1				98.91 172	98.94 303	97.76 204		98.76 366	87.58 517	96.75 436	98.10 385	94.80 327	99.78 257	92.73 455	99.00 394	99.20 303

PHI-MVS		98.29 225	97.95 258	99.34 83	98.44 397	99.16 48	98.12 189	99.38 199	96.01 380	98.06 345	98.43 348	97.80 153	99.67 336	95.69 366	99.58 275	99.20 303

blended_shiyan6		95.99 399	95.33 414	97.95 329	97.06 489	94.89 383	95.34 449	98.58 385	96.17 369	97.06 415	92.41 517	87.64 440	99.76 269	97.64 205	96.09 503	99.19 309

GDP-MVS		97.50 302	97.11 324	98.67 224	99.02 291	96.85 287	98.16 182	99.71 47	98.32 190	98.52 303	98.54 331	83.39 477	99.95 25	98.79 101	99.56 283	99.19 309

Anonymous202405211		97.90 268	97.50 297	99.08 133	98.90 313	98.25 136	98.53 129	96.16 472	98.87 139	99.11 181	98.86 261	90.40 417	99.78 257	97.36 231	99.31 344	99.19 309

CANet		97.87 274	97.76 275	98.19 304	97.75 453	95.51 349	96.76 365	99.05 310	97.74 247	96.93 421	98.21 375	95.59 299	99.89 97	97.86 183	99.93 57	99.19 309

XVG-OURS		98.53 186	98.34 202	99.11 126	99.50 138	98.82 88	95.97 418	99.50 139	97.30 298	99.05 196	98.98 230	99.35 14	99.32 456	95.72 364	99.68 231	99.18 313

WTY-MVS		96.67 364	96.27 382	97.87 337	98.81 334	94.61 396	96.77 364	97.92 419	94.94 425	97.12 410	97.74 414	91.11 409	99.82 206	93.89 417	98.15 451	99.18 313

Vis-MVSNet (Re-imp)		97.46 307	97.16 318	98.34 286	99.55 116	96.10 321	98.94 81	98.44 395	98.32 190	98.16 334	98.62 322	88.76 429	99.73 295	93.88 418	99.79 158	99.18 313

TinyColmap		97.89 270	97.98 254	97.60 369	98.86 322	94.35 402	96.21 403	99.44 175	97.45 283	99.06 188	98.88 258	97.99 135	99.28 463	94.38 405	99.58 275	99.18 313

wanda-best-256-512		95.48 420	94.74 434	97.68 356	96.53 504	94.12 410	94.17 487	98.57 387	95.84 389	96.71 437	91.16 523	86.05 452	99.76 269	97.57 212	96.09 503	99.17 317

FE-blended-shiyan7		95.48 420	94.74 434	97.68 356	96.53 504	94.12 410	94.17 487	98.57 387	95.84 389	96.71 437	91.16 523	86.05 452	99.76 269	97.57 212	96.09 503	99.17 317

usedtu_blend_shiyan5		96.20 392	95.62 397	97.94 330	96.53 504	94.93 381	98.83 96	99.59 95	98.89 137	96.71 437	91.16 523	86.05 452	99.73 295	96.70 294	96.09 503	99.17 317

testdata				98.09 313	98.93 305	95.40 359		98.80 360	90.08 503	97.45 396	98.37 355	95.26 310	99.70 313	93.58 428	98.95 402	99.17 317

lupinMVS		97.06 345	96.86 340	97.65 362	98.88 319	93.89 429	95.48 443	97.97 417	93.53 461	98.16 334	97.58 423	93.81 359	99.91 74	96.77 285	99.57 279	99.17 317

Patchmtry		97.35 319	96.97 331	98.50 266	97.31 482	96.47 310	98.18 178	98.92 335	98.95 130	98.78 258	99.37 104	85.44 460	99.85 158	95.96 352	99.83 126	99.17 317

usedtu_dtu_shiyan1		97.37 316	97.13 322	98.11 310	99.03 284	95.40 359	94.47 478	98.99 324	96.87 335	97.97 353	97.81 409	92.12 393	99.75 281	97.49 225	99.43 323	99.16 323

FE-MVSNET3		97.37 316	97.13 322	98.11 310	99.03 284	95.40 359	94.47 478	98.99 324	96.87 335	97.97 353	97.81 409	92.12 393	99.75 281	97.49 225	99.43 323	99.16 323

SD_0403		96.28 386	95.83 390	97.64 365	98.72 346	94.30 403	98.87 89	98.77 364	97.80 242	96.53 448	98.02 393	97.34 195	99.47 429	76.93 527	99.48 311	99.16 323

RRT-MVS		97.88 272	97.98 254	97.61 368	98.15 428	93.77 433	98.97 77	99.64 76	99.16 93	98.69 270	99.42 89	91.60 399	99.89 97	97.63 206	98.52 434	99.16 323

sss		97.21 333	96.93 333	98.06 319	98.83 328	95.22 371	96.75 366	98.48 394	94.49 436	97.27 405	97.90 402	92.77 382	99.80 232	96.57 309	99.32 342	99.16 323

CSCG		98.68 156	98.50 172	99.20 110	99.45 165	98.63 100	98.56 125	99.57 106	97.87 237	98.85 245	98.04 391	97.66 162	99.84 176	96.72 291	99.81 140	99.13 328

MVS_111021_LR		98.30 222	98.12 239	98.83 186	99.16 253	98.03 166	96.09 413	99.30 240	97.58 263	98.10 341	98.24 372	98.25 106	99.34 453	96.69 296	99.65 247	99.12 329

miper_lstm_enhance		97.18 336	97.16 318	97.25 397	98.16 427	92.85 451	95.15 457	99.31 232	97.25 304	98.74 266	98.78 282	90.07 418	99.78 257	97.19 245	99.80 151	99.11 330

testing3		93.51 459	92.09 472	97.75 348	98.60 376	94.40 400	97.32 322	95.26 490	97.56 266	96.79 435	95.50 484	53.57 536	99.77 263	95.26 378	98.97 400	99.08 331

原ACMM1				98.35 285	98.90 313	96.25 318		98.83 357	92.48 479	96.07 463	98.10 385	95.39 307	99.71 306	92.61 458	98.99 396	99.08 331

QAPM		97.31 322	96.81 346	98.82 188	98.80 337	97.49 225	99.06 66	99.19 278	90.22 501	97.69 374	99.16 168	96.91 224	99.90 81	90.89 490	99.41 326	99.07 333

PAPM_NR		96.82 360	96.32 378	98.30 290	99.07 272	96.69 297	97.48 301	98.76 366	95.81 393	96.61 444	96.47 463	94.12 353	99.17 470	90.82 492	97.78 465	99.06 334

eth_miper_zixun_eth		97.23 331	97.25 312	97.17 401	98.00 439	92.77 453	94.71 467	99.18 282	97.27 302	98.56 296	98.74 291	91.89 397	99.69 322	97.06 258	99.81 140	99.05 335

D2MVS		97.84 281	97.84 271	97.83 339	99.14 258	94.74 390	96.94 353	98.88 342	95.84 389	98.89 234	98.96 236	94.40 340	99.69 322	97.55 214	99.95 39	99.05 335

c3_l		97.36 318	97.37 305	97.31 392	98.09 434	93.25 443	95.01 460	99.16 289	97.05 321	98.77 261	98.72 294	92.88 379	99.64 361	96.93 268	99.76 186	99.05 335

PLC	94.65 16	96.51 371	95.73 393	98.85 179	98.75 342	97.91 183	96.42 389	99.06 306	90.94 498	95.59 472	97.38 439	94.41 338	99.59 383	90.93 488	98.04 460	99.05 335
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tfpnnormal		98.90 107	98.90 104	98.91 172	99.67 67	97.82 197	99.00 73	99.44 175	99.45 50	99.51 92	99.24 144	98.20 115	99.86 144	95.92 353	99.69 225	99.04 339

CANet_DTU		97.26 327	97.06 326	97.84 338	97.57 465	94.65 395	96.19 405	98.79 361	97.23 310	95.14 485	98.24 372	93.22 370	99.84 176	97.34 232	99.84 114	99.04 339

PM-MVS		98.82 124	98.72 131	99.12 124	99.64 76	98.54 111	97.98 221	99.68 62	97.62 257	99.34 132	99.18 162	97.54 177	99.77 263	97.79 188	99.74 191	99.04 339

TestfortrainingZip				98.97 159	98.30 410	98.43 119	98.68 109	98.26 405	97.76 246	98.86 244	98.16 380	95.15 314	99.47 429		97.55 470	99.02 342

TSAR-MVS + GP.		98.18 242	97.98 254	98.77 205	98.71 350	97.88 187	96.32 396	98.66 378	96.33 362	99.23 166	98.51 336	97.48 187	99.40 444	97.16 247	99.46 313	99.02 342

DIV-MVS_self_test		97.02 348	96.84 342	97.58 371	97.82 450	94.03 416	94.66 471	99.16 289	97.04 322	98.63 279	98.71 295	88.69 430	99.69 322	97.00 261	99.81 140	99.01 344

GA-MVS		95.86 406	95.32 416	97.49 383	98.60 376	94.15 409	93.83 498	97.93 418	95.49 407	96.68 440	97.42 437	83.21 478	99.30 459	96.22 338	98.55 432	99.01 344

OMC-MVS		97.88 272	97.49 298	99.04 144	98.89 318	98.63 100	96.94 353	99.25 263	95.02 422	98.53 301	98.51 336	97.27 200	99.47 429	93.50 432	99.51 299	99.01 344

cl____		97.02 348	96.83 343	97.58 371	97.82 450	94.04 415	94.66 471	99.16 289	97.04 322	98.63 279	98.71 295	88.68 432	99.69 322	97.00 261	99.81 140	99.00 347

pmmvs4		97.58 299	97.28 310	98.51 262	98.84 326	96.93 281	95.40 447	98.52 392	93.60 460	98.61 285	98.65 313	95.10 316	99.60 378	96.97 266	99.79 158	98.99 348

blend_shiyan4		92.09 483	90.16 490	97.88 335	96.78 498	94.93 381	95.24 453	98.58 385	96.22 367	96.07 463	91.42 522	63.46 531	99.73 295	96.70 294	76.98 531	98.98 349

EPNet_dtu		94.93 436	94.78 432	95.38 478	93.58 526	87.68 510	96.78 363	95.69 486	97.35 293	89.14 526	98.09 387	88.15 438	99.49 422	94.95 386	99.30 348	98.98 349
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t		96.50 373	95.77 391	98.69 221	99.48 154	97.43 234	97.84 242	99.55 119	81.42 526	96.51 452	98.58 328	95.53 300	99.67 336	93.41 435	99.58 275	98.98 349

PVSNet_Blended		96.88 355	96.68 354	97.47 386	98.92 309	93.77 433	94.71 467	99.43 181	90.98 497	97.62 378	97.36 441	96.82 230	99.67 336	94.73 390	99.56 283	98.98 349

APD_test1		98.83 121	98.66 145	99.34 83	99.78 24	99.47 8	98.42 151	99.45 167	98.28 197	98.98 208	99.19 158	97.76 156	99.58 390	96.57 309	99.55 287	98.97 353

PAPR		95.29 426	94.47 438	97.75 348	97.50 476	95.14 374	94.89 464	98.71 375	91.39 492	95.35 482	95.48 486	94.57 334	99.14 473	84.95 514	97.37 480	98.97 353

EGC-MVSNET		85.24 494	80.54 497	99.34 83	99.77 27	99.20 38	99.08 62	99.29 248	12.08 534	20.84 535	99.42 89	97.55 175	99.85 158	97.08 255	99.72 203	98.96 355

thisisatest0530		95.27 427	94.45 439	97.74 350	99.19 241	94.37 401	97.86 239	90.20 525	97.17 315	98.22 329	97.65 419	73.53 508	99.90 81	96.90 274	99.35 335	98.95 356

mvs_anonymous		97.83 283	98.16 235	96.87 418	98.18 424	91.89 467	97.31 324	98.90 338	97.37 291	98.83 249	99.46 80	96.28 266	99.79 245	98.90 94	98.16 450	98.95 356

baseline1		95.96 403	95.44 408	97.52 380	98.51 390	93.99 423	98.39 157	96.09 476	98.21 202	98.40 318	97.76 413	86.88 443	99.63 364	95.42 375	89.27 525	98.95 356

CLD-MVS		97.49 305	97.16 318	98.48 268	99.07 272	97.03 273	94.71 467	99.21 272	94.46 438	98.06 345	97.16 447	97.57 173	99.48 426	94.46 398	99.78 163	98.95 356
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MSLP-MVS++		98.02 257	98.14 238	97.64 365	98.58 381	95.19 372	97.48 301	99.23 270	97.47 276	97.90 358	98.62 322	97.04 214	98.81 488	97.55 214	99.41 326	98.94 360

DELS-MVS		98.27 227	98.20 226	98.48 268	98.86 322	96.70 296	95.60 438	99.20 274	97.73 248	98.45 310	98.71 295	97.50 183	99.82 206	98.21 148	99.59 270	98.93 361
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
cl22		95.79 409	95.39 411	96.98 411	96.77 499	92.79 452	94.40 481	98.53 391	94.59 435	97.89 359	98.17 378	82.82 482	99.24 465	96.37 328	99.03 388	98.92 362

LS3D		98.63 165	98.38 195	99.36 74	97.25 483	99.38 12	99.12 61	99.32 227	99.21 81	98.44 311	98.88 258	97.31 196	99.80 232	96.58 307	99.34 337	98.92 362

CMPMVS	75.91 23	96.29 385	95.44 408	98.84 185	96.25 513	98.69 98	97.02 346	99.12 297	88.90 510	97.83 365	98.86 261	89.51 425	98.90 486	91.92 468	99.51 299	98.92 362
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LCM-MVSNet-Re		98.64 163	98.48 178	99.11 126	98.85 325	98.51 113	98.49 140	99.83 26	98.37 183	99.69 55	99.46 80	98.21 113	99.92 65	94.13 411	99.30 348	98.91 365

mvsmamba		97.57 300	97.26 311	98.51 262	98.69 359	96.73 295	98.74 99	97.25 441	97.03 324	97.88 360	99.23 150	90.95 410	99.87 135	96.61 305	99.00 394	98.91 365

DPM-MVS		96.32 383	95.59 401	98.51 262	98.76 340	97.21 257	94.54 477	98.26 405	91.94 485	96.37 456	97.25 445	93.06 376	99.43 440	91.42 479	98.74 413	98.89 367

test_yl		96.69 362	96.29 380	97.90 332	98.28 413	95.24 367	97.29 326	97.36 434	98.21 202	98.17 331	97.86 404	86.27 447	99.55 399	94.87 387	98.32 439	98.89 367

DCV-MVSNet		96.69 362	96.29 380	97.90 332	98.28 413	95.24 367	97.29 326	97.36 434	98.21 202	98.17 331	97.86 404	86.27 447	99.55 399	94.87 387	98.32 439	98.89 367

SPE-MVS-test		99.13 66	99.09 81	99.26 101	99.13 260	98.97 73	99.31 30	99.88 15	99.44 52	98.16 334	98.51 336	98.64 61	99.93 53	98.91 93	99.85 109	98.88 370

UnsupCasMVSNet_bld		97.30 324	96.92 335	98.45 271	99.28 212	96.78 293	96.20 404	99.27 255	95.42 410	98.28 326	98.30 366	93.16 371	99.71 306	94.99 383	97.37 480	98.87 371

Effi-MVS+		98.02 257	97.82 272	98.62 234	98.53 388	97.19 259	97.33 321	99.68 62	97.30 298	96.68 440	97.46 435	98.56 73	99.80 232	96.63 303	98.20 446	98.86 372

test_0402		98.76 136	98.71 134	98.93 167	99.56 110	98.14 148	98.45 147	99.34 219	99.28 72	98.95 218	98.91 247	98.34 94	99.79 245	95.63 368	99.91 80	98.86 372

PatchmatchNet		95.58 416	95.67 396	95.30 481	97.34 480	87.32 512	97.65 273	96.65 463	95.30 414	97.07 414	98.69 304	84.77 465	99.75 281	94.97 385	98.64 424	98.83 374
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
testing3-2		93.78 455	93.91 446	93.39 504	98.82 331	81.72 533	97.76 255	95.28 489	98.60 166	96.54 447	96.66 458	65.85 524	99.62 367	96.65 302	98.99 396	98.82 375

test_vis1_rt		97.75 286	97.72 281	97.83 339	98.81 334	96.35 315	97.30 325	99.69 55	94.61 434	97.87 361	98.05 390	96.26 267	98.32 497	98.74 107	98.18 447	98.82 375

CL-MVSNet_self_test		97.44 310	97.22 315	98.08 316	98.57 383	95.78 341	94.30 484	98.79 361	96.58 351	98.60 288	98.19 377	94.74 330	99.64 361	96.41 326	98.84 407	98.82 375

miper_ehance_all_eth		97.06 345	97.03 327	97.16 403	97.83 449	93.06 445	94.66 471	99.09 302	95.99 382	98.69 270	98.45 346	92.73 384	99.61 374	96.79 282	99.03 388	98.82 375

MIMVSNet		96.62 367	96.25 383	97.71 354	99.04 281	94.66 394	99.16 55	96.92 457	97.23 310	97.87 361	99.10 187	86.11 451	99.65 356	91.65 474	99.21 365	98.82 375

hse-mvs2		97.46 307	97.07 325	98.64 228	98.73 344	97.33 239	97.45 307	97.64 429	99.11 99	98.58 292	97.98 396	88.65 433	99.79 245	98.11 155	97.39 479	98.81 380

GSMVS																98.81 380

sam_mvs1												84.74 466				98.81 380

SCA		96.41 380	96.66 358	95.67 468	98.24 418	88.35 506	95.85 429	96.88 458	96.11 374	97.67 375	98.67 308	93.10 374	99.85 158	94.16 407	99.22 362	98.81 380

Patchmatch-RL test		97.26 327	97.02 328	97.99 327	99.52 129	95.53 348	96.13 410	99.71 47	97.47 276	99.27 150	99.16 168	84.30 471	99.62 367	97.89 176	99.77 170	98.81 380

AUN-MVS		96.24 391	95.45 407	98.60 240	98.70 354	97.22 255	97.38 314	97.65 427	95.95 384	95.53 479	97.96 400	82.11 485	99.79 245	96.31 332	97.44 476	98.80 385

ITE_SJBPF				98.87 176	99.22 232	98.48 115		99.35 213	97.50 273	98.28 326	98.60 326	97.64 166	99.35 452	93.86 419	99.27 352	98.79 386

tpm		94.67 438	94.34 443	95.66 469	97.68 462	88.42 505	97.88 235	94.90 492	94.46 438	96.03 467	98.56 330	78.66 497	99.79 245	95.88 354	95.01 515	98.78 387

Patchmatch-test		96.55 370	96.34 377	97.17 401	98.35 406	93.06 445	98.40 156	97.79 420	97.33 294	98.41 314	98.67 308	83.68 476	99.69 322	95.16 381	99.31 344	98.77 388

EC-MVSNet		99.09 72	99.05 85	99.20 110	99.28 212	98.93 79	99.24 44	99.84 23	99.08 113	98.12 339	98.37 355	98.72 50	99.90 81	99.05 83	99.77 170	98.77 388

PMMVS		96.51 371	95.98 386	98.09 313	97.53 470	95.84 336	94.92 462	98.84 353	91.58 488	96.05 465	95.58 481	95.68 296	99.66 349	95.59 371	98.09 454	98.76 390

test_method		79.78 495	79.50 498	80.62 513	80.21 538	45.76 541	70.82 529	98.41 400	31.08 533	80.89 533	97.71 415	84.85 464	97.37 512	91.51 478	80.03 529	98.75 391

ab-mvs		98.41 201	98.36 198	98.59 241	99.19 241	97.23 252	99.32 26	98.81 358	97.66 254	98.62 283	99.40 97	96.82 230	99.80 232	95.88 354	99.51 299	98.75 391

ELoFTR		97.81 284	97.74 277	98.04 322	99.39 181	95.79 340	97.28 330	99.58 98	94.13 449	99.38 120	99.37 104	93.31 367	99.60 378	97.23 242	99.96 28	98.74 393

CHOSEN 280x420		95.51 419	95.47 405	95.65 470	98.25 416	88.27 507	93.25 508	98.88 342	93.53 461	94.65 494	97.15 448	86.17 449	99.93 53	97.41 229	99.93 57	98.73 394

test_fmvsmvis_n_1920		99.26 39	99.49 16	98.54 257	99.66 69	96.97 276	98.00 213	99.85 19	99.24 76	99.92 8	99.50 68	99.39 12	99.95 25	99.89 3	99.98 12	98.71 395

MVS_Test		98.18 242	98.36 198	97.67 358	98.48 391	94.73 391	98.18 178	99.02 318	97.69 251	98.04 348	99.11 184	97.22 204	99.56 395	98.57 121	98.90 406	98.71 395

PVSNet	93.40 17	95.67 412	95.70 394	95.57 471	98.83 328	88.57 504	92.50 513	97.72 422	92.69 477	96.49 455	96.44 464	93.72 362	99.43 440	93.61 425	99.28 351	98.71 395

alignmvs		97.35 319	96.88 339	98.78 200	98.54 386	98.09 155	97.71 263	97.69 424	99.20 83	97.59 381	95.90 475	88.12 439	99.55 399	98.18 150	98.96 401	98.70 398

ADS-MVSNet2		95.43 423	94.98 427	96.76 425	98.14 429	91.74 468	97.92 230	97.76 421	90.23 499	96.51 452	98.91 247	85.61 457	99.85 158	92.88 448	96.90 490	98.69 399

ADS-MVSNet		95.24 428	94.93 430	96.18 446	98.14 429	90.10 497	97.92 230	97.32 439	90.23 499	96.51 452	98.91 247	85.61 457	99.74 288	92.88 448	96.90 490	98.69 399

MDTV_nov1_ep13_2view						74.92 537	97.69 266		90.06 504	97.75 371		85.78 456		93.52 430		98.69 399

LoFTR		97.97 265	97.79 273	98.53 259	98.80 337	97.47 229	97.01 347	99.55 119	95.55 403	99.46 101	99.22 151	94.22 348	99.44 438	96.45 323	99.82 133	98.68 402

MSDG		97.71 289	97.52 296	98.28 292	98.91 312	96.82 288	94.42 480	99.37 203	97.65 255	98.37 319	98.29 368	97.40 191	99.33 455	94.09 412	99.22 362	98.68 402

mvsany_test1		97.60 296	97.54 294	97.77 344	97.72 454	95.35 362	95.36 448	97.13 447	94.13 449	99.71 49	99.33 118	97.93 139	99.30 459	97.60 210	98.94 403	98.67 404

CS-MVS		99.13 66	99.10 79	99.24 106	99.06 277	99.15 52	99.36 22	99.88 15	99.36 63	98.21 330	98.46 345	98.68 58	99.93 53	99.03 85	99.85 109	98.64 405

Syy-MVS		96.04 396	95.56 403	97.49 383	97.10 487	94.48 398	96.18 407	96.58 465	95.65 399	94.77 491	92.29 520	91.27 408	99.36 449	98.17 152	98.05 458	98.63 406

myMVS_eth3d		91.92 485	90.45 486	96.30 438	97.10 487	90.90 488	96.18 407	96.58 465	95.65 399	94.77 491	92.29 520	53.88 535	99.36 449	89.59 500	98.05 458	98.63 406

BridgeMVS		98.63 165	98.72 131	98.38 280	98.66 369	96.68 298	98.90 84	99.42 187	98.99 123	98.97 212	99.19 158	95.81 292	99.85 158	98.77 105	99.77 170	98.60 408

miper_enhance_ethall		96.01 397	95.74 392	96.81 422	96.41 511	92.27 464	93.69 500	98.89 341	91.14 495	98.30 322	97.35 442	90.58 415	99.58 390	96.31 332	99.03 388	98.60 408

Effi-MVS+-dtu		98.26 229	97.90 267	99.35 80	98.02 438	99.49 5	98.02 209	99.16 289	98.29 195	97.64 376	97.99 395	96.44 255	99.95 25	96.66 301	98.93 404	98.60 408

new_pmnet		96.99 352	96.76 348	97.67 358	98.72 346	94.89 383	95.95 422	98.20 409	92.62 478	98.55 298	98.54 331	94.88 323	99.52 411	93.96 415	99.44 322	98.59 411

MVSMamba_PlusPlus		98.83 121	98.98 96	98.36 284	99.32 202	96.58 302	98.90 84	99.41 191	99.75 10	98.72 267	99.50 68	96.17 270	99.94 41	99.27 64	99.78 163	98.57 412

testing91		93.32 463	92.27 469	96.47 432	97.54 468	91.25 481	96.17 409	96.76 461	97.18 314	93.65 509	93.50 509	65.11 526	99.63 364	93.04 443	97.45 475	98.53 413

EIA-MVS		98.00 260	97.74 277	98.80 193	98.72 346	98.09 155	98.05 202	99.60 89	97.39 289	96.63 442	95.55 482	97.68 160	99.80 232	96.73 290	99.27 352	98.52 414

PatchMatch-RL		97.24 330	96.78 347	98.61 238	99.03 284	97.83 192	96.36 393	99.06 306	93.49 463	97.36 403	97.78 411	95.75 293	99.49 422	93.44 434	98.77 411	98.52 414

sasdasda		98.34 214	98.26 219	98.58 242	98.46 394	97.82 197	98.96 78	99.46 163	99.19 88	97.46 393	95.46 487	98.59 67	99.46 433	98.08 158	98.71 417	98.46 416

ET-MVSNet_ETH3D		94.30 445	93.21 457	97.58 371	98.14 429	94.47 399	94.78 466	93.24 512	94.72 431	89.56 524	95.87 476	78.57 499	99.81 223	96.91 269	97.11 488	98.46 416

canonicalmvs		98.34 214	98.26 219	98.58 242	98.46 394	97.82 197	98.96 78	99.46 163	99.19 88	97.46 393	95.46 487	98.59 67	99.46 433	98.08 158	98.71 417	98.46 416

UBG		93.25 465	92.32 467	96.04 454	97.72 454	90.16 496	95.92 425	95.91 480	96.03 379	93.95 506	93.04 514	69.60 513	99.52 411	90.72 493	97.98 462	98.45 419

tt0805		98.69 150	98.62 152	98.90 175	99.75 34	99.30 21	99.15 57	96.97 452	98.86 141	98.87 243	97.62 422	98.63 63	98.96 481	99.41 56	98.29 443	98.45 419

TAPA-MVS	96.21 11	96.63 366	95.95 388	98.65 226	98.93 305	98.09 155	96.93 355	99.28 252	83.58 523	98.13 338	97.78 411	96.13 272	99.40 444	93.52 430	99.29 350	98.45 419
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MGCFI-Net		98.34 214	98.28 213	98.51 262	98.47 392	97.59 220	98.96 78	99.48 149	99.18 91	97.40 399	95.50 484	98.66 59	99.50 418	98.18 150	98.71 417	98.44 422

BH-untuned		96.83 358	96.75 350	97.08 405	98.74 343	93.33 442	96.71 368	98.26 405	96.72 345	98.44 311	97.37 440	95.20 311	99.47 429	91.89 469	97.43 477	98.44 422

WB-MVSnew		95.73 411	95.57 402	96.23 443	96.70 501	90.70 493	96.07 414	93.86 507	95.60 401	97.04 417	95.45 491	96.00 279	99.55 399	91.04 485	98.31 441	98.43 424

pmmvs3		95.03 433	94.40 441	96.93 414	97.70 459	92.53 457	95.08 458	97.71 423	88.57 513	97.71 372	98.08 388	79.39 493	99.82 206	96.19 340	99.11 382	98.43 424

DP-MVS Recon		97.33 321	96.92 335	98.57 245	99.09 268	97.99 170	96.79 361	99.35 213	93.18 466	97.71 372	98.07 389	95.00 319	99.31 457	93.97 414	99.13 378	98.42 426

testing99		93.04 469	91.98 477	96.23 443	97.53 470	90.70 493	96.35 394	95.94 479	96.87 335	93.41 510	93.43 511	63.84 528	99.59 383	93.24 439	97.19 485	98.40 427

ETVMVS		92.60 475	91.08 484	97.18 399	97.70 459	93.65 438	96.54 379	95.70 484	96.51 352	94.68 493	92.39 518	61.80 532	99.50 418	86.97 507	97.41 478	98.40 427

Fast-Effi-MVS+-dtu		98.27 227	98.09 241	98.81 190	98.43 399	98.11 151	97.61 283	99.50 139	98.64 159	97.39 401	97.52 429	98.12 124	99.95 25	96.90 274	98.71 417	98.38 429

LF4IMVS		97.90 268	97.69 283	98.52 261	99.17 251	97.66 213	97.19 341	99.47 158	96.31 364	97.85 364	98.20 376	96.71 242	99.52 411	94.62 393	99.72 203	98.38 429

testing11		93.08 468	92.02 474	96.26 441	97.56 466	90.83 490	96.32 396	95.70 484	96.47 357	92.66 514	93.73 506	64.36 527	99.59 383	93.77 422	97.57 469	98.37 431

Fast-Effi-MVS+		97.67 292	97.38 304	98.57 245	98.71 350	97.43 234	97.23 332	99.45 167	94.82 429	96.13 460	96.51 460	98.52 75	99.91 74	96.19 340	98.83 408	98.37 431

test0.0.03 1		94.51 440	93.69 450	96.99 410	96.05 515	93.61 440	94.97 461	93.49 509	96.17 369	97.57 384	94.88 498	82.30 483	99.01 480	93.60 427	94.17 519	98.37 431

UWE-MVS		92.38 478	91.76 481	94.21 493	97.16 485	84.65 521	95.42 446	88.45 528	95.96 383	96.17 459	95.84 478	66.36 520	99.71 306	91.87 470	98.64 424	98.28 434

FE-MVS		95.66 413	94.95 429	97.77 344	98.53 388	95.28 366	99.40 19	96.09 476	93.11 468	97.96 355	99.26 137	79.10 495	99.77 263	92.40 463	98.71 417	98.27 435

baseline2		93.73 456	92.83 463	96.42 434	97.70 459	91.28 480	96.84 360	89.77 526	93.96 457	92.44 516	95.93 474	79.14 494	99.77 263	92.94 445	96.76 494	98.21 436

thisisatest0515		94.12 450	93.16 458	96.97 412	98.60 376	92.90 450	93.77 499	90.61 523	94.10 451	96.91 424	95.87 476	74.99 505	99.80 232	94.52 396	99.12 381	98.20 437

EPMVS		93.72 457	93.27 456	95.09 484	96.04 516	87.76 509	98.13 185	85.01 533	94.69 432	96.92 422	98.64 317	78.47 501	99.31 457	95.04 382	96.46 497	98.20 437

balanced_ft_v1		98.28 226	98.35 201	98.10 312	98.08 435	96.23 319	99.23 45	99.26 261	98.34 186	97.46 393	99.42 89	95.38 308	99.88 115	98.60 117	99.34 337	98.17 439

dp		93.47 460	93.59 452	93.13 507	96.64 502	81.62 534	97.66 271	96.42 469	92.80 476	96.11 461	98.64 317	78.55 500	99.59 383	93.31 436	92.18 524	98.16 440

CNLPA		97.17 337	96.71 352	98.55 252	98.56 384	98.05 165	96.33 395	98.93 331	96.91 332	97.06 415	97.39 438	94.38 341	99.45 436	91.66 473	99.18 372	98.14 441

dmvs_re		95.98 400	95.39 411	97.74 350	98.86 322	97.45 232	98.37 159	95.69 486	97.95 229	96.56 446	95.95 473	90.70 414	97.68 508	88.32 503	96.13 502	98.11 442

HY-MVS	95.94 13	95.90 405	95.35 413	97.55 377	97.95 441	94.79 387	98.81 98	96.94 455	92.28 482	95.17 484	98.57 329	89.90 420	99.75 281	91.20 483	97.33 484	98.10 443

CostFormer		93.97 452	93.78 449	94.51 489	97.53 470	85.83 517	97.98 221	95.96 478	89.29 508	94.99 488	98.63 319	78.63 498	99.62 367	94.54 395	96.50 496	98.09 444

FA-MVS(test-final)		96.99 352	96.82 344	97.50 382	98.70 354	94.78 388	99.34 23	96.99 450	95.07 421	98.48 307	99.33 118	88.41 436	99.65 356	96.13 346	98.92 405	98.07 445

AdaColmap		97.14 339	96.71 352	98.46 270	98.34 407	97.80 201	96.95 352	98.93 331	95.58 402	96.92 422	97.66 418	95.87 290	99.53 407	90.97 487	99.14 376	98.04 446

KD-MVS_2432*1600		92.87 473	91.99 475	95.51 474	91.37 531	89.27 502	94.07 490	98.14 412	95.42 410	97.25 406	96.44 464	67.86 515	99.24 465	91.28 481	96.08 507	98.02 447

miper_refine_blended		92.87 473	91.99 475	95.51 474	91.37 531	89.27 502	94.07 490	98.14 412	95.42 410	97.25 406	96.44 464	67.86 515	99.24 465	91.28 481	96.08 507	98.02 447

TESTMET0.1,1		92.19 482	91.77 480	93.46 501	96.48 509	82.80 530	94.05 492	91.52 522	94.45 441	94.00 504	94.88 498	66.65 519	99.56 395	95.78 362	98.11 453	98.02 447

testing222		91.96 484	90.37 487	96.72 426	97.47 477	92.59 455	96.11 412	94.76 493	96.83 339	92.90 512	92.87 515	57.92 534	99.55 399	86.93 508	97.52 471	98.00 450

PCF-MVS	92.86 18	94.36 442	93.00 461	98.42 275	98.70 354	97.56 221	93.16 510	99.11 299	79.59 527	97.55 385	97.43 436	92.19 391	99.73 295	79.85 524	99.45 315	97.97 451
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS-28		90.22 488	89.28 491	93.02 508	94.50 525	82.87 529	96.52 382	87.51 529	95.21 419	92.36 517	96.04 470	71.57 510	98.25 499	72.04 529	97.77 466	97.94 452

myMVS_eth3d28		92.92 472	92.31 468	94.77 485	97.84 448	87.59 511	96.19 405	96.11 474	97.08 320	94.27 497	93.49 510	66.07 523	98.78 489	91.78 471	97.93 464	97.92 453

OpenMVS	96.65 7	97.09 342	96.68 354	98.32 287	98.32 408	97.16 265	98.86 92	99.37 203	89.48 506	96.29 458	99.15 174	96.56 249	99.90 81	92.90 447	99.20 367	97.89 454

Gipuma		99.03 87	99.16 62	98.64 228	99.94 2	98.51 113	99.32 26	99.75 42	99.58 38	98.60 288	99.62 40	98.22 111	99.51 417	97.70 201	99.73 194	97.89 454
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PVSNet_0	89.98 21	91.15 487	90.30 489	93.70 499	97.72 454	84.34 525	90.24 520	97.42 432	90.20 502	93.79 507	93.09 513	90.90 412	98.89 487	86.57 511	72.76 532	97.87 456

test-LLR		93.90 453	93.85 447	94.04 494	96.53 504	84.62 522	94.05 492	92.39 514	96.17 369	94.12 500	95.07 492	82.30 483	99.67 336	95.87 357	98.18 447	97.82 457

test-mter		92.33 480	91.76 481	94.04 494	96.53 504	84.62 522	94.05 492	92.39 514	94.00 456	94.12 500	95.07 492	65.63 525	99.67 336	95.87 357	98.18 447	97.82 457

tpm2		93.09 467	92.58 466	94.62 488	97.56 466	86.53 514	97.66 271	95.79 483	86.15 519	94.07 502	98.23 374	75.95 503	99.53 407	90.91 489	96.86 493	97.81 459

CR-MVSNet		96.28 386	95.95 388	97.28 394	97.71 457	94.22 404	98.11 190	98.92 335	92.31 481	96.91 424	99.37 104	85.44 460	99.81 223	97.39 230	97.36 482	97.81 459

RPMNet		97.02 348	96.93 333	97.30 393	97.71 457	94.22 404	98.11 190	99.30 240	99.37 60	96.91 424	99.34 115	86.72 444	99.87 135	97.53 217	97.36 482	97.81 459

tpmrst		95.07 432	95.46 406	93.91 496	97.11 486	84.36 524	97.62 278	96.96 453	94.98 423	96.35 457	98.80 278	85.46 459	99.59 383	95.60 370	96.23 500	97.79 462

ALIKED-LG		97.10 340	96.63 360	98.50 266	97.96 440	98.68 99	97.75 258	99.68 62	95.86 388	98.36 321	98.33 363	91.58 401	99.04 475	90.87 491	99.31 344	97.77 463

PAPM		91.88 486	90.34 488	96.51 430	98.06 437	92.56 456	92.44 514	97.17 445	86.35 518	90.38 523	96.01 471	86.61 445	99.21 468	70.65 530	95.43 513	97.75 464

SP-LightGlue		97.22 332	97.01 329	97.88 335	97.33 481	97.19 259	96.38 391	99.08 304	97.28 300	96.53 448	97.50 430	92.36 387	98.70 492	97.84 184	98.76 412	97.74 465

FPMVS		93.44 461	92.23 470	97.08 405	99.25 225	97.86 189	95.61 437	97.16 446	92.90 474	93.76 508	98.65 313	75.94 504	95.66 525	79.30 525	97.49 473	97.73 466

MAR-MVS		96.47 376	95.70 394	98.79 197	97.92 443	99.12 62	98.28 166	98.60 383	92.16 483	95.54 478	96.17 469	94.77 329	99.52 411	89.62 498	98.23 444	97.72 467
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
ETV-MVS		98.03 256	97.86 270	98.56 250	98.69 359	98.07 161	97.51 297	99.50 139	98.10 219	97.50 390	95.51 483	98.41 85	99.88 115	96.27 336	99.24 358	97.71 468

thres600view7		94.45 441	93.83 448	96.29 439	99.06 277	91.53 472	97.99 220	94.24 503	98.34 186	97.44 397	95.01 494	79.84 489	99.67 336	84.33 515	98.23 444	97.66 469

thres400		94.14 449	93.44 453	96.24 442	98.93 305	91.44 475	97.60 284	94.29 500	97.94 231	97.10 411	94.31 504	79.67 491	99.62 367	83.05 518	98.08 455	97.66 469

IB-MVS	91.63 19	92.24 481	90.90 485	96.27 440	97.22 484	91.24 482	94.36 483	93.33 511	92.37 480	92.24 518	94.58 503	66.20 522	99.89 97	93.16 441	94.63 517	97.66 469
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
tpmvs		95.02 434	95.25 419	94.33 490	96.39 512	85.87 515	98.08 195	96.83 460	95.46 409	95.51 480	98.69 304	85.91 455	99.53 407	94.16 407	96.23 500	97.58 472

cascas		94.79 437	94.33 444	96.15 451	96.02 517	92.36 462	92.34 515	99.26 261	85.34 521	95.08 487	94.96 497	92.96 378	98.53 495	94.41 404	98.59 429	97.56 473

MatchFormer		97.07 344	96.92 335	97.49 383	98.44 397	95.92 332	96.79 361	99.14 295	93.08 469	99.32 141	99.10 187	93.89 356	99.03 476	92.78 453	99.78 163	97.52 474

PatchT		96.65 365	96.35 376	97.54 378	97.40 478	95.32 365	97.98 221	96.64 464	99.33 65	96.89 428	99.42 89	84.32 470	99.81 223	97.69 203	97.49 473	97.48 475

TR-MVS		95.55 417	95.12 425	96.86 421	97.54 468	93.94 424	96.49 384	96.53 467	94.36 444	97.03 419	96.61 459	94.26 347	99.16 471	86.91 509	96.31 499	97.47 476

SP-SuperGlue		97.31 322	97.23 314	97.57 376	96.96 492	97.24 251	96.26 402	98.76 366	97.68 252	96.88 430	97.85 406	94.32 344	98.01 502	97.76 195	98.57 431	97.45 477

dmvs_testset		92.94 471	92.21 471	95.13 482	98.59 379	90.99 487	97.65 273	92.09 516	96.95 327	94.00 504	93.55 508	92.34 389	96.97 517	72.20 528	92.52 522	97.43 478

MonoMVSNet		96.25 389	96.53 369	95.39 477	96.57 503	91.01 486	98.82 97	97.68 426	98.57 172	98.03 349	99.37 104	90.92 411	97.78 507	94.99 383	93.88 520	97.38 479

JIA-IIPM		95.52 418	95.03 426	97.00 409	96.85 496	94.03 416	96.93 355	95.82 481	99.20 83	94.63 495	99.71 22	83.09 479	99.60 378	94.42 401	94.64 516	97.36 480

SP-MNN		96.46 377	96.24 384	97.10 404	96.71 500	95.98 329	96.00 416	97.33 438	95.82 392	94.93 489	97.10 452	93.70 363	98.01 502	96.30 334	98.30 442	97.30 481

ALIKED-MNN		95.97 402	95.30 417	98.00 325	97.66 464	98.12 150	96.98 350	99.41 191	91.11 496	94.04 503	97.30 443	91.56 402	98.61 494	89.99 496	99.63 255	97.28 482

BH-w/o		95.13 431	94.89 431	95.86 461	98.20 422	91.31 478	95.65 436	97.37 433	93.64 459	96.52 451	95.70 480	93.04 377	99.02 478	88.10 504	95.82 510	97.24 483

tpm cat1		93.29 464	93.13 460	93.75 498	97.39 479	84.74 520	97.39 312	97.65 427	83.39 524	94.16 499	98.41 350	82.86 481	99.39 446	91.56 477	95.35 514	97.14 484

SP-NN		94.67 438	94.44 440	95.36 479	95.12 522	95.23 370	94.27 485	96.10 475	94.46 438	90.91 521	95.76 479	91.47 405	93.87 529	95.23 379	96.62 495	97.00 485

SP-DiffGlue		96.87 356	96.76 348	97.21 398	95.17 521	96.88 286	96.12 411	98.93 331	96.51 352	98.37 319	97.55 425	93.65 364	97.83 505	96.11 347	98.45 436	96.92 486

xiu_mvs_v1_base_debu		97.86 275	98.17 232	96.92 415	98.98 298	93.91 426	96.45 385	99.17 286	97.85 239	98.41 314	97.14 449	98.47 77	99.92 65	98.02 165	99.05 384	96.92 486

xiu_mvs_v1_base		97.86 275	98.17 232	96.92 415	98.98 298	93.91 426	96.45 385	99.17 286	97.85 239	98.41 314	97.14 449	98.47 77	99.92 65	98.02 165	99.05 384	96.92 486

xiu_mvs_v1_base_debi		97.86 275	98.17 232	96.92 415	98.98 298	93.91 426	96.45 385	99.17 286	97.85 239	98.41 314	97.14 449	98.47 77	99.92 65	98.02 165	99.05 384	96.92 486

PMVS	91.26 20	97.86 275	97.94 261	97.65 362	99.71 48	97.94 180	98.52 130	98.68 376	98.99 123	97.52 388	99.35 111	97.41 190	98.18 500	91.59 476	99.67 237	96.82 490
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
0.4-1-1-0.1		88.42 490	85.91 493	95.94 457	93.08 527	91.54 471	90.99 519	92.04 518	89.96 505	84.83 530	83.25 529	63.75 529	99.52 411	93.25 438	82.07 526	96.75 491

1314		95.74 410	95.60 399	96.17 447	97.53 470	92.75 454	98.07 199	98.31 403	91.22 493	94.25 498	96.68 457	95.53 300	99.03 476	91.64 475	97.18 486	96.74 492

MVS-HIRNet		94.32 443	95.62 397	90.42 512	98.46 394	75.36 536	96.29 398	89.13 527	95.25 417	95.38 481	99.75 16	92.88 379	99.19 469	94.07 413	99.39 328	96.72 493

OpenMVS_ROB	95.38 14	95.84 408	95.18 424	97.81 341	98.41 403	97.15 266	97.37 318	98.62 382	83.86 522	98.65 277	98.37 355	94.29 346	99.68 332	88.41 502	98.62 428	96.60 494

ALIKED-NN		94.29 446	93.41 455	96.94 413	96.18 514	97.66 213	94.90 463	98.68 376	88.85 511	90.43 522	96.81 455	89.82 421	96.59 522	86.67 510	98.33 438	96.58 495

0.3-1-1-0.015		87.27 492	84.50 496	95.57 471	91.70 530	90.77 491	89.41 525	92.04 518	88.98 509	82.46 532	81.35 530	60.36 533	99.50 418	92.96 444	81.23 528	96.45 496

0.4-1-1-0.2		87.49 491	84.89 494	95.31 480	91.33 533	90.08 498	88.47 526	92.07 517	88.70 512	84.06 531	81.08 531	63.62 530	99.49 422	92.93 446	81.71 527	96.37 497

thres100view900		94.19 447	93.67 451	95.75 465	99.06 277	91.35 477	98.03 206	94.24 503	98.33 188	97.40 399	94.98 496	79.84 489	99.62 367	83.05 518	98.08 455	96.29 498

tfpn200view9		94.03 451	93.44 453	95.78 464	98.93 305	91.44 475	97.60 284	94.29 500	97.94 231	97.10 411	94.31 504	79.67 491	99.62 367	83.05 518	98.08 455	96.29 498

MVS		93.19 466	92.09 472	96.50 431	96.91 494	94.03 416	98.07 199	98.06 416	68.01 530	94.56 496	96.48 462	95.96 286	99.30 459	83.84 516	96.89 492	96.17 500

gg-mvs-nofinetune		92.37 479	91.20 483	95.85 462	95.80 520	92.38 461	99.31 30	81.84 535	99.75 10	91.83 519	99.74 18	68.29 514	99.02 478	87.15 506	97.12 487	96.16 501

xiu_mvs_v2_base		97.16 338	97.49 298	96.17 447	98.54 386	92.46 458	95.45 444	98.84 353	97.25 304	97.48 392	96.49 461	98.31 96	99.90 81	96.34 331	98.68 422	96.15 502

PS-MVSNAJ		97.08 343	97.39 303	96.16 449	98.56 384	92.46 458	95.24 453	98.85 352	97.25 304	97.49 391	95.99 472	98.07 126	99.90 81	96.37 328	98.67 423	96.12 503

E-PMN		94.17 448	94.37 442	93.58 500	96.86 495	85.71 518	90.11 522	97.07 448	98.17 209	97.82 367	97.19 446	84.62 467	98.94 482	89.77 497	97.68 468	96.09 504

EMVS		93.83 454	94.02 445	93.23 506	96.83 497	84.96 519	89.77 523	96.32 470	97.92 233	97.43 398	96.36 467	86.17 449	98.93 483	87.68 505	97.73 467	95.81 505

MVE	83.40 22	92.50 476	91.92 478	94.25 491	98.83 328	91.64 470	92.71 511	83.52 534	95.92 385	86.46 529	95.46 487	95.20 311	95.40 526	80.51 523	98.64 424	95.73 506
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
thres200		93.72 457	93.14 459	95.46 476	98.66 369	91.29 479	96.61 375	94.63 495	97.39 289	96.83 432	93.71 507	79.88 488	99.56 395	82.40 521	98.13 452	95.54 507

GLUNet-SfM		86.26 493	84.68 495	91.01 511	80.58 537	83.56 526	78.04 528	93.59 508	76.70 528	95.29 483	94.72 501	77.51 502	94.26 528	66.39 531	99.33 339	95.20 508

API-MVS		97.04 347	96.91 338	97.42 389	97.88 445	98.23 141	98.18 178	98.50 393	97.57 264	97.39 401	96.75 456	96.77 235	99.15 472	90.16 495	99.02 391	94.88 509

GG-mvs-BLEND				94.76 486	94.54 524	92.13 466	99.31 30	80.47 536		88.73 527	91.01 526	67.59 518	98.16 501	82.30 522	94.53 518	93.98 510

SIFT-PointCN		96.45 378	96.47 371	96.39 435	98.13 432	97.54 223	93.31 507	97.23 443	94.67 433	98.68 273	98.32 364	94.64 332	97.81 506	93.50 432	99.77 170	93.83 511

XFeat-MNN		93.41 462	92.98 462	94.68 487	92.63 528	92.92 449	89.72 524	95.81 482	92.10 484	97.23 408	96.29 468	84.95 463	97.31 514	89.60 499	98.54 433	93.81 512

SIFT-ConvMatch		96.57 368	96.62 361	96.43 433	98.20 422	98.27 134	93.88 496	96.88 458	95.29 415	98.88 238	98.25 370	95.18 313	97.43 511	93.22 440	99.83 126	93.59 513

SIFT-NCM-Cal		96.56 369	96.68 354	96.20 445	98.27 415	98.44 118	94.40 481	96.67 462	95.29 415	97.63 377	98.17 378	96.40 257	96.59 522	93.61 425	99.66 245	93.57 514

SIFT-MNN		95.92 404	95.97 387	95.74 467	98.18 424	98.00 168	94.17 487	96.99 450	95.74 397	97.16 409	97.90 402	90.71 413	95.79 524	93.71 423	99.21 365	93.44 515

SIFT-NN-PointCN		96.06 394	96.11 385	95.91 459	97.88 445	97.73 208	93.49 503	97.51 431	93.22 465	96.57 445	98.26 369	96.23 268	96.60 521	92.54 460	99.27 352	93.40 516

DeepMVS_CX				93.44 503	98.24 418	94.21 406		94.34 499	64.28 531	91.34 520	94.87 500	89.45 427	92.77 530	77.54 526	93.14 521	93.35 517

SIFT-NN-CMatch		95.63 415	95.48 404	96.08 453	98.24 418	98.00 168	92.71 511	94.29 500	94.20 447	95.85 468	97.26 444	95.72 295	97.01 515	91.99 467	99.02 391	93.23 518

SIFT-NN		92.96 470	92.79 464	93.46 501	96.92 493	96.45 311	91.89 517	94.39 498	92.91 473	92.54 515	95.46 487	88.26 437	90.71 532	85.22 513	97.52 471	93.22 519

SIFT-PCN-Cal		96.34 381	96.46 373	96.01 456	98.17 426	96.89 284	93.48 504	97.35 437	94.84 428	99.35 129	98.30 366	94.70 331	97.92 504	92.03 466	99.88 95	93.21 520

SIFT-UM-Cal		96.49 374	96.62 361	96.12 452	98.13 432	97.89 186	93.35 506	98.44 395	95.48 408	98.63 279	98.34 359	95.45 305	97.45 510	92.22 465	99.50 307	93.02 521

SIFT-CM-Cal		96.28 386	96.31 379	96.16 449	98.39 404	98.11 151	93.46 505	96.47 468	94.81 430	98.49 305	98.43 348	94.48 336	97.34 513	92.60 459	99.70 221	93.02 521

SIFT-UMatch		96.33 382	96.47 371	95.89 460	98.29 411	97.95 178	93.84 497	97.24 442	95.78 395	98.72 267	98.04 391	93.45 366	96.81 518	93.14 442	99.73 194	92.91 523

SIFT-NN-NCMNet		95.39 424	95.22 421	95.92 458	98.29 411	98.34 129	93.58 502	94.60 496	94.07 453	94.84 490	97.53 426	94.37 342	96.62 520	91.01 486	98.64 424	92.80 524

SIFT-NCMNet		96.30 384	96.40 375	96.03 455	97.80 452	97.68 212	92.34 515	96.94 455	95.55 403	98.84 247	98.63 319	94.17 349	97.63 509	93.57 429	99.71 212	92.77 525

SIFT-NN-UMatch		95.38 425	95.26 418	95.75 465	98.25 416	97.78 202	93.24 509	95.66 488	94.01 455	95.10 486	97.47 434	93.12 372	96.78 519	92.42 462	98.04 460	92.69 526

XFeat-NN		89.63 489	89.13 492	91.14 510	90.93 534	90.02 499	84.90 527	94.05 506	88.10 515	92.89 513	93.33 512	78.74 496	90.89 531	83.46 517	95.72 511	92.52 527

tmp_tt		78.77 496	78.73 499	78.90 514	58.45 539	74.76 538	94.20 486	78.26 537	39.16 532	86.71 528	92.82 516	80.50 487	75.19 534	86.16 512	92.29 523	86.74 528

dongtai		76.24 497	75.95 500	77.12 515	92.39 529	67.91 539	90.16 521	59.44 540	82.04 525	89.42 525	94.67 502	49.68 537	81.74 533	48.06 532	77.66 530	81.72 529

kuosan		69.30 498	68.95 501	70.34 516	87.68 536	65.00 540	91.11 518	59.90 539	69.02 529	74.46 534	88.89 528	48.58 538	68.03 535	28.61 533	72.33 533	77.99 530

wuyk23d		96.06 394	97.62 291	91.38 509	98.65 373	98.57 107	98.85 93	96.95 454	96.86 338	99.90 14	99.16 168	99.18 19	98.40 496	89.23 501	99.77 170	77.18 531

test123		17.04 501	20.11 504	7.82 517	10.25 541	4.91 542	94.80 465	4.47 542	4.93 535	10.00 537	24.28 534	9.69 539	3.64 536	10.14 534	12.43 535	14.92 532

testmvs		17.12 500	20.53 503	6.87 518	12.05 540	4.20 543	93.62 501	6.73 541	4.62 536	10.41 536	24.33 533	8.28 540	3.56 537	9.69 535	15.07 534	12.86 533

mmdepth		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

monomultidepth		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

test_blank		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

uanet_test		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

DCPMVS		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

cdsmvs_eth3d_5k		24.66 499	32.88 502	0.00 519	0.00 542	0.00 544	0.00 530	99.10 300	0.00 537	0.00 538	97.58 423	99.21 18	0.00 538	0.00 536	0.00 536	0.00 534

pcd_1.5k_mvsjas		8.17 502	10.90 505	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	98.07 126	0.00 538	0.00 536	0.00 536	0.00 534

sosnet-low-res		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

sosnet		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

uncertanet		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

Regformer		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

ab-mvs-re		8.12 503	10.83 506	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	97.48 432	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

uanet		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

WAC-MVS						90.90 488								91.37 480

FOURS1					99.73 37	99.67 2	99.43 15	99.54 125	99.43 54	99.26 154

test_one_0601					99.39 181	99.20 38		99.31 232	98.49 178	98.66 276	99.02 208	97.64 166

eth-test2					0.00 542

eth-test					0.00 542

ZD-MVS					99.01 293	98.84 85		99.07 305	94.10 451	98.05 347	98.12 383	96.36 262	99.86 144	92.70 456	99.19 370

test_241102_ONE					99.49 146	99.17 43		99.31 232	97.98 226	99.66 60	98.90 250	98.36 89	99.48 426

9.14			97.78 274		99.07 272		97.53 294	99.32 227	95.53 406	98.54 300	98.70 302	97.58 172	99.76 269	94.32 406	99.46 313

save fliter					99.11 263	97.97 174	96.53 381	99.02 318	98.24 198

test0726					99.50 138	99.21 32	98.17 181	99.35 213	97.97 227	99.26 154	99.06 196	97.61 170

test_part2					99.36 190	99.10 65				99.05 196

sam_mvs												84.29 472

MTGPA								99.20 274

test_post1							97.59 286				20.48 536	83.07 480	99.66 349	94.16 407

test_post											21.25 535	83.86 475	99.70 313

patchmatchnet-post											98.77 284	84.37 469	99.85 158

MTMP							97.93 227	91.91 521

gm-plane-assit					94.83 523	81.97 532			88.07 516		94.99 495		99.60 378	91.76 472

TEST9					98.71 350	98.08 159	95.96 420	99.03 315	91.40 491	95.85 468	97.53 426	96.52 251	99.76 269

test_8					98.67 364	98.01 167	95.91 426	99.02 318	91.64 486	95.79 471	97.50 430	96.47 253	99.76 269

agg_prior					98.68 363	97.99 170		99.01 321		95.59 472			99.77 263

test_prior4						97.97 174	95.86 427

test_prior2							95.74 434		96.48 356	96.11 461	97.63 421	95.92 289		94.16 407	99.20 367

旧先验2							95.76 433		88.56 514	97.52 388			99.66 349	94.48 397

新几何2							95.93 423

原ACMM2							95.53 440

testdata2													99.79 245	92.80 452

segment_acmp												97.02 217

testdata1							95.44 445		96.32 363

plane_prior7					99.19 241	97.87 188

plane_prior6					98.99 297	97.70 211						94.90 320

plane_prior4											97.98 396

plane_prior3						97.78 202			97.41 286	97.79 368

plane_prior2							97.77 252		98.20 206

plane_prior1					99.05 280

plane_prior						97.65 215	97.07 345		96.72 345						99.36 332

n2								0.00 543

nn								0.00 543

door-mid								99.57 106

test11								98.87 344

door								99.41 191

HQP5-MVS						96.79 290

HQP-NCC					98.67 364		96.29 398		96.05 376	95.55 475

ACMP_Plane					98.67 364		96.29 398		96.05 376	95.55 475

BP-MVS														92.82 450

HQP3-MVS								99.04 313							99.26 356

HQP2-MVS												93.84 357

NP-MVS					98.84 326	97.39 236					96.84 453

MDTV_nov1_ep13			95.22 421		97.06 489	83.20 528	97.74 260	96.16 472	94.37 443	96.99 420	98.83 271	83.95 474	99.53 407	93.90 416	97.95 463

ACMMP++_ref															99.77 170

ACMMP++															99.68 231

Test By Simon												96.52 251

High-resolution multi-view benchmark