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	98.44 277	99.65 71	95.35 367	99.82 3	99.94 3	99.83 7	99.42 112	99.94 2	98.13 125	99.96 13	99.63 36	99.96 28	100.00 1

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 74	99.87 12	98.13 149	98.08 196	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	98.80 195	99.75 34	96.59 303	97.97 226	99.86 17	98.22 202	99.88 21	99.71 22	98.59 67	99.84 177	99.73 28	99.98 12	99.98 3

fmvsm_s_conf0.1_n_2		99.20 50	99.38 28	98.65 230	99.69 61	96.08 330	97.49 301	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	98.92 171	99.58 94	96.89 288	99.48 13	99.92 8	99.92 2	98.26 336	99.80 11	98.33 96	99.91 74	99.56 41	99.95 39	99.97 4

fmvsm_s_conf0.1_n		99.16 56	99.33 37	98.64 232	99.71 49	96.10 325	97.87 239	99.85 19	98.56 176	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	98.25 299	99.76 30	95.07 383	99.05 68	99.94 3	97.78 248	99.82 34	99.84 3	98.56 73	99.71 308	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	97.77 253	99.90 12	99.33 66	99.97 3	99.66 32	99.71 3	99.96 13	99.79 19	99.99 5	99.96 8

test_f		98.67 160	98.87 111	98.05 327	99.72 45	95.59 348	98.51 135	99.81 32	96.30 372	99.78 39	99.82 5	96.14 275	98.63 501	99.82 12	99.93 57	99.95 9

test_fmvs2		98.70 147	98.97 98	97.89 340	99.54 123	94.05 420	98.55 126	99.92 8	96.78 346	99.72 47	99.78 13	96.60 252	99.67 341	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 76	99.48 44	99.92 8	99.71 22	98.07 128	99.96 13	99.53 48	100.00 1	99.93 11

test_vis3_rt		99.14 62	99.17 60	99.07 136	99.78 24	98.38 122	98.92 83	99.94 3	97.80 245	99.91 12	99.67 30	97.15 211	98.91 493	99.76 23	99.56 288	99.92 12

fmvsm_s_conf0.5_n_2		99.14 62	99.31 41	98.63 236	99.49 148	96.08 330	97.38 315	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		95.86 415	95.60 408	96.63 434	95.87 528	91.70 476	97.93 228	98.94 336	98.03 225	99.56 74	99.66 32	71.83 518	98.26 506	99.35 58	99.24 366	99.91 13

fmvsm_s_conf0.5_n_a		99.10 72	99.20 58	98.78 202	99.55 117	96.59 303	97.79 249	99.82 31	98.21 204	99.81 36	99.53 64	98.46 82	99.84 177	99.70 33	99.97 21	99.90 15

fmvsm_s_conf0.5_n_9		99.17 52	99.38 28	98.53 263	99.51 134	95.82 342	97.62 279	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 73	99.26 50	98.61 242	99.55 117	96.09 328	97.74 261	99.81 32	98.55 177	99.85 27	99.55 56	98.60 66	99.84 177	99.69 35	99.98 12	99.89 16

test_fmvsmconf_n		99.44 19	99.48 18	99.31 94	99.64 77	98.10 154	97.68 268	99.84 23	99.29 72	99.92 8	99.57 49	99.60 5	99.96 13	99.74 27	99.98 12	99.89 16

test_djsdf		99.52 13	99.51 15	99.53 38	99.86 14	98.74 91	99.39 20	99.56 118	99.11 100	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	98.80 195	99.48 156	96.56 308	97.97 226	99.69 56	99.63 28	99.84 30	99.54 62	98.21 115	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 48	99.27 74	99.90 14	99.74 18	99.68 4	99.97 6	99.55 43	99.99 5	99.88 20

fmvsm_s_conf0.5_n_8		99.13 66	99.26 50	98.74 215	99.51 134	96.44 316	97.65 274	99.65 76	99.66 23	99.78 39	99.48 75	97.92 142	99.93 53	99.72 30	99.95 39	99.87 22

fmvsm_s_conf0.5_n_7		98.83 122	99.04 87	98.20 306	99.30 210	94.83 393	97.23 333	99.36 215	98.64 160	99.84 30	99.43 88	98.10 127	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 92	98.21 143	97.82 244	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		97.91 272	98.02 254	97.58 377	98.69 367	94.10 419	98.13 186	98.90 346	97.95 231	97.32 413	99.58 47	95.95 292	98.75 498	96.41 332	99.22 370	99.87 22

jajsoiax		99.58 9	99.61 11	99.48 57	99.87 12	98.61 103	99.28 40	99.66 70	99.09 110	99.89 18	99.68 25	99.53 7	99.97 6	99.50 50	99.99 5	99.87 22

EU-MVSNet		97.66 300	98.50 173	95.13 490	99.63 83	85.84 524	98.35 161	98.21 417	98.23 200	99.54 79	99.46 80	95.02 324	99.68 336	98.24 145	99.87 100	99.87 22

fmvsm_s_conf0.5_n_3		99.22 46	99.37 31	98.78 202	99.46 162	96.58 306	97.65 274	99.72 46	99.47 47	99.86 24	99.50 68	98.94 31	99.89 97	99.75 26	99.97 21	99.86 28

UA-Net		99.47 16	99.40 27	99.70 2	99.49 148	99.29 23	99.80 4	99.72 46	99.82 8	99.04 201	99.81 8	98.05 131	99.96 13	98.85 98	99.99 5	99.86 28

fmvsm_l_conf0.5_n_9		99.32 32	99.43 24	98.98 158	99.59 92	97.18 266	97.44 310	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		98.22 237	97.99 257	98.91 173	98.66 377	96.97 280	97.89 235	94.44 506	99.54 40	98.95 221	99.14 179	93.50 373	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	98.94 165	99.65 71	97.05 275	97.80 248	99.76 39	98.70 158	99.78 39	99.11 187	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	99.02 149	99.64 77	97.28 252	97.82 244	99.76 39	98.73 151	99.82 34	99.09 196	98.81 39	99.95 25	99.86 4	99.96 28	99.83 33

mvsany_test3		98.87 112	98.92 102	98.74 215	99.38 185	96.94 284	98.58 123	99.10 308	96.49 361	99.96 4	99.81 8	98.18 118	99.45 443	98.97 89	99.79 159	99.83 33

PDCNetPlus		95.22 438	94.73 445	96.70 433	97.85 455	91.14 492	93.94 503	99.97 1	93.06 478	98.95 221	98.89 260	74.32 515	99.14 481	95.63 376	99.93 57	99.82 36

fmvsm_s_conf0.5_n_10		99.15 57	99.27 47	98.78 202	99.47 159	96.56 308	97.75 259	99.71 48	99.60 35	99.74 46	99.44 85	97.96 139	99.95 25	99.86 4	99.94 51	99.82 36

SSC-MVS		98.71 142	98.74 128	98.62 238	99.72 45	96.08 330	98.74 99	98.64 389	99.74 12	99.67 59	99.24 144	94.57 340	99.95 25	99.11 77	99.24 366	99.82 36

anonymousdsp		99.51 14	99.47 21	99.62 9	99.88 9	99.08 69	99.34 23	99.69 56	98.93 132	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 90	98.84 119	99.52 44	99.58 94	98.93 79	98.68 109	99.60 92	98.85 145	99.53 83	99.16 169	97.87 149	99.83 195	96.67 304	99.64 254	99.81 41

TestfortrainingZip a		99.09 73	98.92 102	99.61 13	99.58 94	99.17 43	98.68 109	99.27 263	98.85 145	99.61 70	99.16 169	97.14 212	99.86 144	98.39 138	99.57 284	99.81 41

fmvsm_s_conf0.5_n_4		99.01 90	99.22 54	98.38 284	99.31 206	95.48 358	97.56 290	99.73 45	98.87 140	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 49	99.10 65	99.29 36	99.53 133	99.53 41	99.46 101	99.41 94	98.23 110	99.95 25	98.89 96	99.95 39	99.81 41

VortexMVS		97.98 268	98.31 212	97.02 414	98.88 326	91.45 481	98.03 207	99.47 166	98.65 159	99.55 77	99.47 78	91.49 413	99.81 224	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	99.57 109	99.61 34	99.40 117	99.50 68	97.12 213	99.85 158	99.02 86	99.94 51	99.80 45

test_cas_vis1_n_1920		98.33 219	98.68 141	97.27 401	99.69 61	92.29 470	98.03 207	99.85 19	97.62 260	99.96 4	99.62 40	93.98 362	99.74 289	99.52 49	99.86 107	99.79 47

test_vis1_n_1920		98.40 205	98.92 102	96.81 428	99.74 37	90.76 499	98.15 184	99.91 10	98.33 189	99.89 18	99.55 56	95.07 323	99.88 115	99.76 23	99.93 57	99.79 47

CP-MVSNet		99.21 47	99.09 82	99.56 26	99.65 71	98.96 77	99.13 59	99.34 227	99.42 55	99.33 137	99.26 137	97.01 221	99.94 41	98.74 107	99.93 57	99.79 47

fmvsm_s_conf0.5_n_5		99.07 82	99.10 80	98.99 154	99.47 159	97.22 259	97.40 312	99.83 26	97.61 263	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	99.58 101	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		96.25 397	97.21 324	93.38 514	99.10 271	80.56 544	97.20 338	98.19 420	96.94 332	99.00 206	99.02 211	89.50 435	99.80 233	96.36 336	99.59 275	99.78 50

reproduce_monomvs		95.00 444	95.25 428	94.22 500	97.51 483	83.34 535	97.86 240	98.44 404	98.51 178	99.29 148	99.30 125	67.68 526	99.56 402	98.89 96	99.81 140	99.77 53

Anonymous20231211		99.27 37	99.27 47	99.26 101	99.29 212	98.18 144	99.49 12	99.51 141	99.70 15	99.80 37	99.68 25	96.84 230	99.83 195	99.21 70	99.91 80	99.77 53

PEN-MVS		99.41 24	99.34 35	99.62 9	99.73 38	99.14 57	99.29 36	99.54 129	99.62 32	99.56 74	99.42 89	98.16 122	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 49	99.24 29	99.32 26	99.55 123	99.46 49	99.50 93	99.34 115	97.30 200	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	99.81 224	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		98.52 191	98.55 164	98.43 278	99.65 71	95.59 348	98.52 130	98.77 372	99.65 25	99.52 87	99.00 226	94.34 350	99.93 53	98.65 114	98.83 416	99.76 58

patch_mono-2		98.51 192	98.63 151	98.17 309	99.38 185	94.78 395	97.36 320	99.69 56	98.16 214	98.49 311	99.29 128	97.06 216	99.97 6	98.29 144	99.91 80	99.76 58

nrg030		99.40 25	99.35 33	99.54 31	99.58 94	99.13 60	98.98 76	99.48 156	99.68 19	99.46 101	99.26 137	98.62 64	99.73 296	99.17 74	99.92 71	99.76 58

FIs		99.14 62	99.09 82	99.29 95	99.70 57	98.28 133	99.13 59	99.52 139	99.48 44	99.24 166	99.41 94	96.79 237	99.82 207	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 90	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 94	98.79 124	99.60 16	99.21 238	99.15 52	98.87 89	99.48 156	97.57 267	99.35 130	99.24 144	97.83 151	99.89 97	97.88 181	99.70 226	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 49	99.30 21	99.31 30	99.51 141	99.64 26	99.56 74	99.46 80	98.23 110	99.97 6	98.78 102	99.93 57	99.72 64

MSC_two_6792asdad				99.32 91	98.43 407	98.37 124		98.86 357					99.89 97	97.14 253	99.60 271	99.71 65

No_MVS				99.32 91	98.43 407	98.37 124		98.86 357					99.89 97	97.14 253	99.60 271	99.71 65

PMMVS2		98.07 257	98.08 248	98.04 328	99.41 179	94.59 404	94.59 482	99.40 203	97.50 276	98.82 255	98.83 275	96.83 232	99.84 177	97.50 222	99.81 140	99.71 65

Baseline_NR-MVSNet		98.98 98	98.86 115	99.36 74	99.82 19	98.55 108	97.47 306	99.57 109	99.37 60	99.21 172	99.61 43	96.76 240	99.83 195	98.06 161	99.83 126	99.71 65

XXY-MVS		99.14 62	99.15 67	99.10 128	99.76 30	97.74 208	98.85 93	99.62 87	98.48 180	99.37 125	99.49 74	98.75 47	99.86 144	98.20 150	99.80 152	99.71 65

test_0728_THIRD									98.17 211	99.08 189	99.02 211	97.89 147	99.88 115	97.07 260	99.71 217	99.70 70

MSP-MVS		98.40 205	98.00 256	99.61 13	99.57 103	99.25 28	98.57 124	99.35 221	97.55 271	99.31 146	97.71 424	94.61 339	99.88 115	96.14 351	99.19 378	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		98.53 187	98.79 124	97.74 356	99.46 162	93.62 446	96.45 390	99.34 227	99.33 66	98.93 230	98.70 307	97.90 143	99.90 81	99.12 76	99.92 71	99.69 72

NormalMVS		98.26 232	97.97 261	99.15 121	99.64 77	97.83 194	98.28 167	99.43 189	99.24 77	98.80 259	98.85 268	89.76 431	99.94 41	98.04 164	99.67 242	99.68 73

KinetiMVS		99.03 88	99.02 90	99.03 146	99.70 57	97.48 230	98.43 148	99.29 256	99.70 15	99.60 71	99.07 198	96.13 277	99.94 41	99.42 55	99.87 100	99.68 73

dcpmvs_2		98.78 133	99.11 74	97.78 349	99.56 111	93.67 443	99.06 66	99.86 17	99.50 43	99.66 60	99.26 137	97.21 208	99.99 2	98.00 169	99.91 80	99.68 73

test_0728_SECOND				99.60 16	99.50 140	99.23 30	98.02 210	99.32 235					99.88 115	96.99 267	99.63 260	99.68 73

OurMVSNet-221017-0		99.37 28	99.31 41	99.53 38	99.91 3	98.98 71	99.63 7	99.58 101	99.44 52	99.78 39	99.76 15	96.39 262	99.92 65	99.44 54	99.92 71	99.68 73

fmvsm_s_conf0.5_n_6		99.08 79	99.21 57	98.69 223	99.36 192	96.51 310	97.62 279	99.68 63	98.43 182	99.85 27	99.10 190	99.12 23	99.88 115	99.77 22	99.92 71	99.67 78

CHOSEN 1792x2688		97.49 312	97.14 329	98.54 261	99.68 64	96.09 328	96.50 387	99.62 87	91.58 496	98.84 250	98.97 235	92.36 396	99.88 115	96.76 291	99.95 39	99.67 78

reproduce_model		99.15 57	98.97 98	99.67 4	99.33 203	99.44 9	98.15 184	99.47 166	99.12 99	99.52 87	99.32 123	98.31 97	99.90 81	97.78 191	99.73 199	99.66 80

IU-MVS					99.49 148	99.15 52		98.87 352	92.97 479	99.41 114				96.76 291	99.62 264	99.66 80

test_241102_TWO								99.30 248	98.03 225	99.26 156	99.02 211	97.51 185	99.88 115	96.91 274	99.60 271	99.66 80

DPE-MVS		98.59 174	98.26 222	99.57 21	99.27 218	99.15 52	97.01 348	99.39 205	97.67 256	99.44 107	98.99 228	97.53 182	99.89 97	95.40 384	99.68 236	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	99.57 109	99.39 58	99.75 44	99.62 40	99.17 20	99.83 195	99.06 82	99.62 264	99.66 80

EI-MVSNet-UG-set		98.69 151	98.71 135	98.62 238	99.10 271	96.37 318	97.23 333	98.87 352	99.20 84	99.19 174	98.99 228	97.30 200	99.85 158	98.77 105	99.79 159	99.65 85

Elysia		99.15 57	99.14 68	99.18 113	99.63 83	97.92 183	98.50 137	99.43 189	99.67 20	99.70 51	99.13 181	96.66 247	99.98 4	99.54 44	99.96 28	99.64 86

StellarMVS		99.15 57	99.14 68	99.18 113	99.63 83	97.92 183	98.50 137	99.43 189	99.67 20	99.70 51	99.13 181	96.66 247	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		98.68 157	98.70 138	98.63 236	99.09 274	96.40 317	97.23 333	98.86 357	99.20 84	99.18 179	98.97 235	97.29 202	99.85 158	98.72 109	99.78 164	99.64 86

ACMH	96.65 7	99.25 40	99.24 53	99.26 101	99.72 45	98.38 122	99.07 65	99.55 123	98.30 193	99.65 63	99.45 84	99.22 17	99.76 270	98.44 131	99.77 172	99.64 86
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DP-MVS		98.93 104	98.81 123	99.28 96	99.21 238	98.45 117	98.46 145	99.33 233	99.63 28	99.48 96	99.15 175	97.23 206	99.75 282	97.17 249	99.66 250	99.63 91

reproduce-ours		99.09 73	98.90 105	99.67 4	99.27 218	99.49 5	98.00 214	99.42 195	99.05 117	99.48 96	99.27 131	98.29 99	99.89 97	97.61 210	99.71 217	99.62 92

our_new_method		99.09 73	98.90 105	99.67 4	99.27 218	99.49 5	98.00 214	99.42 195	99.05 117	99.48 96	99.27 131	98.29 99	99.89 97	97.61 210	99.71 217	99.62 92

test_fmvs1_n		98.09 255	98.28 216	97.52 386	99.68 64	93.47 448	98.63 116	99.93 6	95.41 420	99.68 57	99.64 37	91.88 407	99.48 433	99.82 12	99.87 100	99.62 92

test1111		96.49 381	96.82 352	95.52 481	99.42 176	87.08 521	99.22 46	87.14 539	99.11 100	99.46 101	99.58 47	88.69 439	99.86 144	98.80 100	99.95 39	99.62 92

VPA-MVSNet		99.30 33	99.30 44	99.28 96	99.49 148	98.36 127	99.00 73	99.45 175	99.63 28	99.52 87	99.44 85	98.25 107	99.88 115	99.09 79	99.84 114	99.62 92

LPG-MVS_test		98.71 142	98.46 183	99.47 61	99.57 103	98.97 73	98.23 173	99.48 156	96.60 355	99.10 187	99.06 199	98.71 51	99.83 195	95.58 380	99.78 164	99.62 92

LGP-MVS_train				99.47 61	99.57 103	98.97 73		99.48 156	96.60 355	99.10 187	99.06 199	98.71 51	99.83 195	95.58 380	99.78 164	99.62 92

Test_1112_low_res		96.99 359	96.55 375	98.31 293	99.35 197	95.47 361	95.84 436	99.53 133	91.51 498	96.80 443	98.48 350	91.36 415	99.83 195	96.58 313	99.53 299	99.62 92

tt0320-xc		99.64 5	99.68 5	99.50 54	99.72 45	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 99	99.11 74	98.55 256	99.44 169	96.21 324	98.90 84	99.55 123	98.73 151	99.48 96	99.60 45	96.63 251	99.83 195	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 81	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		98.31 224	98.50 173	97.73 359	99.76 30	94.17 415	98.68 109	99.91 10	96.31 370	99.79 38	99.57 49	92.85 389	99.42 449	99.79 19	99.84 114	99.60 102

v8		99.01 90	99.16 62	98.57 249	99.47 159	96.31 321	98.90 84	99.47 166	99.03 121	99.52 87	99.57 49	96.93 226	99.81 224	99.60 37	99.98 12	99.60 102

EI-MVSNet		98.40 205	98.51 170	98.04 328	99.10 271	94.73 398	97.20 338	98.87 352	98.97 127	99.06 191	99.02 211	96.00 284	99.80 233	98.58 119	99.82 133	99.60 102

SixPastTwentyTwo		98.75 138	98.62 153	99.16 118	99.83 18	97.96 178	99.28 40	98.20 418	99.37 60	99.70 51	99.65 36	92.65 393	99.93 53	99.04 84	99.84 114	99.60 102

IterMVS-LS		98.55 182	98.70 138	98.09 319	99.48 156	94.73 398	97.22 337	99.39 205	98.97 127	99.38 121	99.31 124	96.00 284	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		97.19 342	96.60 373	98.96 162	99.62 87	97.28 252	95.17 461	99.50 146	94.21 454	99.01 205	98.32 371	86.61 454	99.99 2	97.10 258	99.84 114	99.60 102

lecture		99.25 40	99.12 71	99.62 9	99.64 77	99.40 11	98.89 88	99.51 141	99.19 89	99.37 125	99.25 142	98.36 90	99.88 115	98.23 147	99.67 242	99.59 109

tt0320		99.61 8	99.65 9	99.48 57	99.71 49	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		98.75 138	98.48 179	99.57 21	99.58 94	99.29 23	97.82 244	99.25 271	96.94 332	98.78 261	99.12 185	98.02 132	99.84 177	97.13 256	99.67 242	99.59 109

VPNet		98.87 112	98.83 120	99.01 151	99.70 57	97.62 220	98.43 148	99.35 221	99.47 47	99.28 150	99.05 206	96.72 244	99.82 207	98.09 158	99.36 340	99.59 109

WR-MVS		98.40 205	98.19 233	99.03 146	99.00 301	97.65 217	96.85 360	98.94 336	98.57 173	98.89 237	98.50 347	95.60 304	99.85 158	97.54 218	99.85 109	99.59 109

HPM-MVS		98.79 131	98.53 168	99.59 20	99.65 71	99.29 23	99.16 55	99.43 189	96.74 348	98.61 291	98.38 361	98.62 64	99.87 135	96.47 327	99.67 242	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 94	99.01 92	98.94 165	99.50 140	97.47 231	98.04 205	99.59 98	98.15 219	99.40 117	99.36 110	98.58 72	99.76 270	98.78 102	99.68 236	99.59 109

Vis-MVSNet		99.34 29	99.36 32	99.27 99	99.73 38	98.26 135	99.17 54	99.78 36	99.11 100	99.27 152	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 94	98.93 79	98.68 109	99.60 92	96.46 364	99.53 83	98.77 288		99.83 195	96.67 304	99.64 254	99.58 117

ME-MVS		98.61 170	98.33 210	99.44 65	99.24 230	98.93 79	97.45 308	99.06 314	98.14 220	99.06 191	98.77 288	96.97 224	99.82 207	96.67 304	99.64 254	99.58 117

MP-MVS-pluss		98.57 177	98.23 227	99.60 16	99.69 61	99.35 16	97.16 343	99.38 207	94.87 435	98.97 215	98.99 228	98.01 133	99.88 115	97.29 240	99.70 226	99.58 117
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
region2R		98.69 151	98.40 191	99.54 31	99.53 127	99.17 43	98.52 130	99.31 240	97.46 284	98.44 318	98.51 343	97.83 151	99.88 115	96.46 328	99.58 280	99.58 117

ACMMPR		98.70 147	98.42 189	99.54 31	99.52 131	99.14 57	98.52 130	99.31 240	97.47 279	98.56 302	98.54 338	97.75 159	99.88 115	96.57 315	99.59 275	99.58 117

PGM-MVS		98.66 161	98.37 199	99.55 28	99.53 127	99.18 42	98.23 173	99.49 154	97.01 329	98.69 275	98.88 262	98.00 134	99.89 97	95.87 364	99.59 275	99.58 117

SteuartSystems-ACMMP		98.79 131	98.54 166	99.54 31	99.73 38	99.16 48	98.23 173	99.31 240	97.92 235	98.90 234	98.90 254	98.00 134	99.88 115	96.15 350	99.72 208	99.58 117
Skip Steuart: Steuart Systems R&D Blog.
SDMVSNet		99.23 45	99.32 39	98.96 162	99.68 64	97.35 240	98.84 95	99.48 156	99.69 17	99.63 66	99.68 25	99.03 24	99.96 13	97.97 174	99.92 71	99.57 124

sd_testset		99.28 36	99.31 41	99.19 112	99.68 64	98.06 165	99.41 17	99.30 248	99.69 17	99.63 66	99.68 25	99.25 16	99.96 13	97.25 243	99.92 71	99.57 124

TranMVSNet+NR-MVSNet		99.17 52	99.07 85	99.46 63	99.37 191	98.87 84	98.39 157	99.42 195	99.42 55	99.36 128	99.06 199	98.38 89	99.95 25	98.34 141	99.90 88	99.57 124

mPP-MVS		98.64 164	98.34 205	99.54 31	99.54 123	99.17 43	98.63 116	99.24 276	97.47 279	98.09 350	98.68 311	97.62 170	99.89 97	96.22 345	99.62 264	99.57 124

PVSNet_Blended_VisFu		98.17 248	98.15 240	98.22 305	99.73 38	95.15 379	97.36 320	99.68 63	94.45 449	98.99 210	99.27 131	96.87 229	99.94 41	97.13 256	99.91 80	99.57 124

1112_ss		97.29 333	96.86 348	98.58 246	99.34 202	96.32 320	96.75 367	99.58 101	93.14 475	96.89 437	97.48 441	92.11 404	99.86 144	96.91 274	99.54 295	99.57 124

MTAPA		98.88 111	98.64 149	99.61 13	99.67 68	99.36 15	98.43 148	99.20 282	98.83 149	98.89 237	98.90 254	96.98 223	99.92 65	97.16 250	99.70 226	99.56 130

XVS		98.72 141	98.45 184	99.53 38	99.46 162	99.21 32	98.65 114	99.34 227	98.62 165	97.54 395	98.63 325	97.50 186	99.83 195	96.79 287	99.53 299	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 81	99.30 71	99.65 63	99.60 45	99.16 22	99.82 207	99.07 80	99.83 126	99.56 130

X-MVStestdata		94.32 452	92.59 474	99.53 38	99.46 162	99.21 32	98.65 114	99.34 227	98.62 165	97.54 395	45.85 541	97.50 186	99.83 195	96.79 287	99.53 299	99.56 130

HPM-MVS_fast		99.01 90	98.82 121	99.57 21	99.71 49	99.35 16	99.00 73	99.50 146	97.33 297	98.94 229	98.86 265	98.75 47	99.82 207	97.53 219	99.71 217	99.56 130

K. test v3		98.00 264	97.66 293	99.03 146	99.79 23	97.56 223	99.19 53	92.47 522	99.62 32	99.52 87	99.66 32	89.61 433	99.96 13	99.25 67	99.81 140	99.56 130

CP-MVS		98.70 147	98.42 189	99.52 44	99.36 192	99.12 62	98.72 104	99.36 215	97.54 273	98.30 330	98.40 358	97.86 150	99.89 97	96.53 324	99.72 208	99.56 130

viewmacassd2359aftdt		98.86 116	98.87 111	98.83 188	99.53 127	97.32 245	97.70 266	99.64 78	98.22 202	99.25 164	99.27 131	98.40 86	99.61 381	97.98 173	99.87 100	99.55 137

FE-MVSNET		98.59 174	98.50 173	98.87 177	99.58 94	97.30 246	98.08 196	99.74 44	96.94 332	98.97 215	99.10 190	96.94 225	99.74 289	97.33 236	99.86 107	99.55 137

ZNCC-MVS		98.68 157	98.40 191	99.54 31	99.57 103	99.21 32	98.46 145	99.29 256	97.28 304	98.11 348	98.39 359	98.00 134	99.87 135	96.86 284	99.64 254	99.55 137

v1192		98.60 172	98.66 146	98.41 280	99.27 218	95.88 338	97.52 296	99.36 215	97.41 289	99.33 137	99.20 156	96.37 265	99.82 207	99.57 39	99.92 71	99.55 137

v1240		98.55 182	98.62 153	98.32 291	99.22 236	95.58 350	97.51 298	99.45 175	97.16 320	99.45 106	99.24 144	96.12 279	99.85 158	99.60 37	99.88 95	99.55 137

UGNet		98.53 187	98.45 184	98.79 199	97.94 450	96.96 282	99.08 62	98.54 398	99.10 107	96.82 442	99.47 78	96.55 254	99.84 177	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 94	98.86 115	99.39 72	99.73 38	98.71 97	99.05 68	99.47 166	99.16 94	99.49 94	99.12 185	96.34 267	99.93 53	98.05 163	99.36 340	99.54 143

E5new		99.05 83	99.11 74	98.85 180	99.60 88	97.30 246	98.42 151	99.63 81	98.73 151	99.26 156	99.39 100	98.71 51	99.70 315	98.43 133	99.84 114	99.54 143

E6new		99.05 83	99.11 74	98.85 180	99.60 88	97.30 246	98.42 151	99.63 81	98.73 151	99.26 156	99.39 100	98.71 51	99.70 315	98.43 133	99.84 114	99.54 143

E6		99.05 83	99.11 74	98.85 180	99.60 88	97.30 246	98.42 151	99.63 81	98.73 151	99.26 156	99.39 100	98.71 51	99.70 315	98.43 133	99.84 114	99.54 143

E5		99.05 83	99.11 74	98.85 180	99.60 88	97.30 246	98.42 151	99.63 81	98.73 151	99.26 156	99.39 100	98.71 51	99.70 315	98.43 133	99.84 114	99.54 143

AstraMVS		98.16 250	98.07 250	98.41 280	99.51 134	95.86 339	98.00 214	95.14 500	98.97 127	99.43 108	99.24 144	93.25 376	99.84 177	99.21 70	99.87 100	99.54 143

WBMVS		95.18 439	94.78 441	96.37 443	97.68 470	89.74 508	95.80 437	98.73 381	97.54 273	98.30 330	98.44 354	70.06 520	99.82 207	96.62 310	99.87 100	99.54 143

test2506		92.39 486	91.89 488	93.89 506	99.38 185	82.28 540	99.32 26	66.03 547	99.08 114	98.77 264	99.57 49	66.26 530	99.84 177	98.71 110	99.95 39	99.54 143

ECVR-MVS		96.42 387	96.61 371	95.85 470	99.38 185	88.18 516	99.22 46	86.00 541	99.08 114	99.36 128	99.57 49	88.47 444	99.82 207	98.52 127	99.95 39	99.54 143

v144192		98.54 185	98.57 162	98.45 275	99.21 238	95.98 333	97.63 278	99.36 215	97.15 322	99.32 143	99.18 163	95.84 296	99.84 177	99.50 50	99.91 80	99.54 143

v1921920		98.54 185	98.60 158	98.38 284	99.20 242	95.76 346	97.56 290	99.36 215	97.23 314	99.38 121	99.17 167	96.02 282	99.84 177	99.57 39	99.90 88	99.54 143

MP-MVS		98.46 197	98.09 245	99.54 31	99.57 103	99.22 31	98.50 137	99.19 286	97.61 263	97.58 391	98.66 317	97.40 194	99.88 115	94.72 401	99.60 271	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 98	99.59 36	99.71 49	99.57 49	97.12 213	99.90 81	99.21 70	99.87 100	99.54 143

ACMMP		98.75 138	98.50 173	99.52 44	99.56 111	99.16 48	98.87 89	99.37 211	97.16 320	98.82 255	99.01 222	97.71 161	99.87 135	96.29 342	99.69 230	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		98.40 205	98.03 253	99.51 49	99.16 257	99.21 32	98.05 203	99.22 279	94.16 456	98.98 211	99.10 190	97.52 184	99.79 246	96.45 329	99.64 254	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		98.71 142	98.44 186	99.51 49	99.49 148	99.16 48	98.52 130	99.31 240	97.47 279	98.58 298	98.50 347	97.97 138	99.85 158	96.57 315	99.59 275	99.53 157

UniMVSNet_NR-MVSNet		98.86 116	98.68 141	99.40 71	99.17 255	98.74 91	97.68 268	99.40 203	99.14 98	99.06 191	98.59 333	96.71 245	99.93 53	98.57 121	99.77 172	99.53 157

E4		98.87 112	98.88 108	98.81 192	99.52 131	97.23 256	97.62 279	99.61 90	98.58 171	99.18 179	99.33 118	98.29 99	99.69 325	97.99 172	99.83 126	99.52 160

GST-MVS		98.61 170	98.30 213	99.52 44	99.51 134	99.20 38	98.26 171	99.25 271	97.44 287	98.67 279	98.39 359	97.68 162	99.85 158	96.00 356	99.51 305	99.52 160

MGCNet		97.44 317	97.01 337	98.72 219	96.42 519	96.74 298	97.20 338	91.97 529	98.46 181	98.30 330	98.79 284	92.74 391	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 48	99.38 59	99.53 83	99.61 43	98.64 61	99.80 233	98.24 145	99.84 114	99.52 160

FE-MVSNET2		99.15 57	99.22 54	98.94 165	99.70 57	97.49 227	98.62 118	99.67 69	98.85 145	99.34 134	99.54 62	98.47 77	99.81 224	98.93 92	99.91 80	99.51 164

v1144		98.60 172	98.66 146	98.41 280	99.36 192	95.90 337	97.58 288	99.34 227	97.51 275	99.27 152	99.15 175	96.34 267	99.80 233	99.47 53	99.93 57	99.51 164

v2v482		98.56 178	98.62 153	98.37 287	99.42 176	95.81 343	97.58 288	99.16 297	97.90 237	99.28 150	99.01 222	95.98 289	99.79 246	99.33 59	99.90 88	99.51 164

CPTT-MVS		97.84 287	97.36 313	99.27 99	99.31 206	98.46 116	98.29 166	99.27 263	94.90 434	97.83 374	98.37 362	94.90 326	99.84 177	93.85 429	99.54 295	99.51 164

casdiffseed414692147		99.09 73	99.12 71	99.01 151	99.55 117	97.91 185	98.30 165	99.68 63	99.04 119	99.19 174	99.37 104	98.98 28	99.61 381	98.13 154	99.83 126	99.50 168

viewdifsd2359ckpt11		98.84 119	99.04 87	98.24 301	99.56 111	95.51 353	97.38 315	99.70 53	99.16 94	99.57 72	99.40 97	98.26 105	99.71 308	98.55 125	99.82 133	99.50 168

viewmsd2359difaftdt		98.84 119	99.04 87	98.24 301	99.56 111	95.51 353	97.38 315	99.70 53	99.16 94	99.57 72	99.40 97	98.26 105	99.71 308	98.55 125	99.82 133	99.50 168

LuminaMVS		98.39 211	98.20 229	98.98 158	99.50 140	97.49 227	97.78 250	97.69 433	98.75 150	99.49 94	99.25 142	92.30 399	99.94 41	99.14 75	99.88 95	99.50 168

DU-MVS		98.82 125	98.63 151	99.39 72	99.16 257	98.74 91	97.54 294	99.25 271	98.84 148	99.06 191	98.76 293	96.76 240	99.93 53	98.57 121	99.77 172	99.50 168

NR-MVSNet		98.95 102	98.82 121	99.36 74	99.16 257	98.72 96	99.22 46	99.20 282	99.10 107	99.72 47	98.76 293	96.38 264	99.86 144	98.00 169	99.82 133	99.50 168

casdiffmvs_mvg		99.12 69	99.16 62	98.99 154	99.43 174	97.73 210	98.00 214	99.62 87	99.22 80	99.55 77	99.22 152	98.93 33	99.75 282	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 79	99.00 94	99.33 89	99.71 49	98.83 86	98.60 121	99.58 101	99.11 100	99.53 83	99.18 163	98.81 39	99.67 341	96.71 299	99.77 172	99.50 168

SymmetryMVS		98.05 259	97.71 288	99.09 132	99.29 212	97.83 194	98.28 167	97.64 438	99.24 77	98.80 259	98.85 268	89.76 431	99.94 41	98.04 164	99.50 313	99.49 176

DVP-MVS++		98.90 108	98.70 138	99.51 49	98.43 407	99.15 52	99.43 15	99.32 235	98.17 211	99.26 156	99.02 211	98.18 118	99.88 115	97.07 260	99.45 321	99.49 176

PC_three_1452									93.27 472	99.40 117	98.54 338	98.22 113	97.00 525	95.17 389	99.45 321	99.49 176

GeoE		99.05 83	98.99 96	99.25 104	99.44 169	98.35 128	98.73 103	99.56 118	98.42 183	98.91 233	98.81 281	98.94 31	99.91 74	98.35 140	99.73 199	99.49 176

h-mvs33		97.77 291	97.33 316	99.10 128	99.21 238	97.84 193	98.35 161	98.57 395	99.11 100	98.58 298	99.02 211	88.65 442	99.96 13	98.11 156	96.34 507	99.49 176

IterMVS-SCA-FT		97.85 286	98.18 235	96.87 424	99.27 218	91.16 491	95.53 446	99.25 271	99.10 107	99.41 114	99.35 111	93.10 382	99.96 13	98.65 114	99.94 51	99.49 176

new-patchmatchnet		98.35 214	98.74 128	97.18 405	99.24 230	92.23 472	96.42 394	99.48 156	98.30 193	99.69 55	99.53 64	97.44 192	99.82 207	98.84 99	99.77 172	99.49 176

APD-MVS		98.10 252	97.67 290	99.42 67	99.11 269	98.93 79	97.76 256	99.28 260	94.97 432	98.72 271	98.77 288	97.04 217	99.85 158	93.79 430	99.54 295	99.49 176
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EPP-MVSNet		98.30 225	98.04 252	99.07 136	99.56 111	97.83 194	99.29 36	98.07 424	99.03 121	98.59 296	99.13 181	92.16 401	99.90 81	96.87 282	99.68 236	99.49 176

DeepC-MVS	97.60 4	98.97 99	98.93 101	99.10 128	99.35 197	97.98 174	98.01 213	99.46 171	97.56 269	99.54 79	99.50 68	98.97 29	99.84 177	98.06 161	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	98.91 106	98.73 130	99.48 57	99.55 117	99.14 57	98.07 200	99.37 211	97.62 260	99.04 201	98.96 239	98.84 37	99.79 246	97.43 230	99.65 252	99.49 176
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
guyue		98.01 263	97.93 267	98.26 297	99.45 167	95.48 358	98.08 196	96.24 480	98.89 138	99.34 134	99.14 179	91.32 416	99.82 207	99.07 80	99.83 126	99.48 187

DVP-MVS		98.77 136	98.52 169	99.52 44	99.50 140	99.21 32	98.02 210	98.84 361	97.97 229	99.08 189	99.02 211	97.61 172	99.88 115	96.99 267	99.63 260	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		98.71 142	98.43 187	99.57 21	99.18 253	99.35 16	98.36 160	99.29 256	98.29 196	98.88 241	98.85 268	97.53 182	99.87 135	96.14 351	99.31 352	99.48 187

TSAR-MVS + MP.		98.63 166	98.49 178	99.06 142	99.64 77	97.90 187	98.51 135	98.94 336	96.96 330	99.24 166	98.89 260	97.83 151	99.81 224	96.88 281	99.49 316	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		98.21 240	97.95 262	99.01 151	99.58 94	97.74 208	99.01 71	97.29 449	99.67 20	98.97 215	99.50 68	90.45 425	99.80 233	97.88 181	99.20 375	99.48 187

IterMVS		97.73 293	98.11 244	96.57 436	99.24 230	90.28 502	95.52 448	99.21 280	98.86 142	99.33 137	99.33 118	93.11 381	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		98.19 243	97.90 271	99.08 134	99.57 103	97.97 175	99.31 30	98.32 411	99.01 123	98.98 211	99.03 210	91.59 409	99.79 246	95.49 382	99.80 152	99.48 187

ACMP	95.32 15	98.41 202	98.09 245	99.36 74	99.51 134	98.79 89	97.68 268	99.38 207	95.76 402	98.81 257	98.82 278	98.36 90	99.82 207	94.75 398	99.77 172	99.48 187
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
cashybrid2		99.12 69	99.12 71	99.09 132	99.53 127	98.08 159	98.34 163	99.66 70	99.35 64	99.35 130	99.23 150	98.39 88	99.72 306	98.46 129	99.81 140	99.47 195

MCST-MVS		98.00 264	97.63 297	99.10 128	99.24 230	98.17 145	96.89 359	98.73 381	95.66 404	97.92 364	97.70 426	97.17 210	99.66 354	96.18 349	99.23 369	99.47 195

3Dnovator+	97.89 3	98.69 151	98.51 170	99.24 106	98.81 341	98.40 120	99.02 70	99.19 286	98.99 124	98.07 352	99.28 129	97.11 215	99.84 177	96.84 285	99.32 350	99.47 195

hybridcas		99.08 79	99.13 70	98.92 171	99.54 123	97.61 221	98.22 177	99.66 70	99.27 74	99.40 117	99.24 144	98.47 77	99.70 315	98.59 118	99.80 152	99.46 198

diffmvs_AUTHOR		98.50 193	98.59 160	98.23 304	99.35 197	95.48 358	96.61 379	99.60 92	98.37 184	98.90 234	99.00 226	97.37 196	99.76 270	98.22 148	99.85 109	99.46 198

HPM-MVS++		98.10 252	97.64 295	99.48 57	99.09 274	99.13 60	97.52 296	98.75 378	97.46 284	96.90 436	97.83 417	96.01 283	99.84 177	95.82 368	99.35 343	99.46 198

V42		98.78 133	98.78 126	98.76 209	99.44 169	97.04 276	98.27 170	99.19 286	97.87 239	99.25 164	99.16 169	96.84 230	99.78 258	99.21 70	99.84 114	99.46 198

APD-MVS_3200maxsize		98.84 119	98.61 157	99.53 38	99.19 245	99.27 26	98.49 140	99.33 233	98.64 160	99.03 204	98.98 233	97.89 147	99.85 158	96.54 323	99.42 332	99.46 198

UniMVSNet (Re)		98.87 112	98.71 135	99.35 80	99.24 230	98.73 94	97.73 263	99.38 207	98.93 132	99.12 183	98.73 296	96.77 238	99.86 144	98.63 116	99.80 152	99.46 198

SR-MVS-dyc-post		98.81 127	98.55 164	99.57 21	99.20 242	99.38 12	98.48 143	99.30 248	98.64 160	98.95 221	98.96 239	97.49 189	99.86 144	96.56 319	99.39 336	99.45 204

RE-MVS-def			98.58 161		99.20 242	99.38 12	98.48 143	99.30 248	98.64 160	98.95 221	98.96 239	97.75 159		96.56 319	99.39 336	99.45 204

HQP_MVS		97.99 267	97.67 290	98.93 168	99.19 245	97.65 217	97.77 253	99.27 263	98.20 208	97.79 377	97.98 405	94.90 326	99.70 315	94.42 410	99.51 305	99.45 204

plane_prior5								99.27 263					99.70 315	94.42 410	99.51 305	99.45 204

lessismore_v0				98.97 160	99.73 38	97.53 226		86.71 540		99.37 125	99.52 67	89.93 428	99.92 65	98.99 88	99.72 208	99.44 208

TAMVS		98.24 236	98.05 251	98.80 195	99.07 278	97.18 266	97.88 236	98.81 366	96.66 354	99.17 182	99.21 154	94.81 332	99.77 264	96.96 272	99.88 95	99.44 208

DeepPCF-MVS	96.93 5	98.32 220	98.01 255	99.23 108	98.39 412	98.97 73	95.03 465	99.18 290	96.88 338	99.33 137	98.78 286	98.16 122	99.28 471	96.74 294	99.62 264	99.44 208

3Dnovator	98.27 2	98.81 127	98.73 130	99.05 143	98.76 348	97.81 202	99.25 43	99.30 248	98.57 173	98.55 304	99.33 118	97.95 140	99.90 81	97.16 250	99.67 242	99.44 208

E2		98.70 147	98.68 141	98.73 217	99.40 181	97.10 273	97.48 302	99.57 109	98.09 222	99.00 206	99.20 156	97.90 143	99.67 341	97.73 201	99.77 172	99.43 212

E3		98.69 151	98.68 141	98.73 217	99.40 181	97.10 273	97.48 302	99.57 109	98.09 222	99.00 206	99.20 156	97.90 143	99.67 341	97.73 201	99.77 172	99.43 212

MVSFormer		98.26 232	98.43 187	97.77 350	98.88 326	93.89 436	99.39 20	99.56 118	99.11 100	98.16 342	98.13 390	93.81 366	99.97 6	99.26 65	99.57 284	99.43 212

jason		97.45 316	97.35 314	97.76 353	99.24 230	93.93 432	95.86 433	98.42 407	94.24 453	98.50 310	98.13 390	94.82 330	99.91 74	97.22 245	99.73 199	99.43 212
jason: jason.
NCCC		97.86 281	97.47 308	99.05 143	98.61 382	98.07 162	96.98 351	98.90 346	97.63 259	97.04 426	97.93 410	95.99 288	99.66 354	95.31 385	98.82 418	99.43 212

Anonymous20240521		98.69 151	98.87 111	98.16 312	99.77 27	95.11 382	99.08 62	99.44 183	99.34 65	99.33 137	99.55 56	94.10 361	99.94 41	99.25 67	99.96 28	99.42 217

MVS_111021_HR		98.25 235	98.08 248	98.75 211	99.09 274	97.46 233	95.97 424	99.27 263	97.60 265	97.99 360	98.25 379	98.15 124	99.38 455	96.87 282	99.57 284	99.42 217

COLMAP_ROB	96.50 10	98.99 94	98.85 118	99.41 69	99.58 94	99.10 65	98.74 99	99.56 118	99.09 110	99.33 137	99.19 159	98.40 86	99.72 306	95.98 358	99.76 188	99.42 217
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SED-MVS		98.91 106	98.72 132	99.49 55	99.49 148	99.17 43	98.10 193	99.31 240	98.03 225	99.66 60	99.02 211	98.36 90	99.88 115	96.91 274	99.62 264	99.41 220

OPU-MVS				98.82 190	98.59 387	98.30 132	98.10 193				98.52 342	98.18 118	98.75 498	94.62 402	99.48 317	99.41 220

our_test_3		97.39 322	97.73 285	96.34 444	98.70 362	89.78 507	94.61 481	98.97 335	96.50 360	99.04 201	98.85 268	95.98 289	99.84 177	97.26 242	99.67 242	99.41 220

casdiffmvs		98.95 102	99.00 94	98.81 192	99.38 185	97.33 242	97.82 244	99.57 109	99.17 93	99.35 130	99.17 167	98.35 94	99.69 325	98.46 129	99.73 199	99.41 220
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		97.60 303	97.67 290	97.39 397	99.04 287	93.04 455	95.27 457	98.38 410	97.25 308	98.92 232	98.95 243	95.48 310	99.73 296	96.99 267	98.74 422	99.41 220

MDA-MVSNet_test_wron		97.60 303	97.66 293	97.41 396	99.04 287	93.09 451	95.27 457	98.42 407	97.26 307	98.88 241	98.95 243	95.43 312	99.73 296	97.02 263	98.72 424	99.41 220

GBi-Net		98.65 162	98.47 181	99.17 115	98.90 320	98.24 137	99.20 49	99.44 183	98.59 168	98.95 221	99.55 56	94.14 357	99.86 144	97.77 193	99.69 230	99.41 220

test1		98.65 162	98.47 181	99.17 115	98.90 320	98.24 137	99.20 49	99.44 183	98.59 168	98.95 221	99.55 56	94.14 357	99.86 144	97.77 193	99.69 230	99.41 220

FMVSNet1		99.17 52	99.17 60	99.17 115	99.55 117	98.24 137	99.20 49	99.44 183	99.21 82	99.43 108	99.55 56	97.82 154	99.86 144	98.42 137	99.89 94	99.41 220

test_fmvs1		97.72 294	97.94 265	97.07 413	98.66 377	92.39 467	97.68 268	99.81 32	95.20 427	99.54 79	99.44 85	91.56 411	99.41 450	99.78 21	99.77 172	99.40 229

viewdifsd2359ckpt07		98.71 142	98.86 115	98.26 297	99.43 174	95.65 347	97.20 338	99.66 70	99.20 84	99.29 148	99.01 222	98.29 99	99.73 296	97.92 177	99.75 192	99.39 230

viewmanbaseed2359cas		98.58 176	98.54 166	98.70 221	99.28 215	97.13 272	97.47 306	99.55 123	97.55 271	98.96 220	98.92 248	97.77 157	99.59 390	97.59 213	99.77 172	99.39 230

KD-MVS_self_test		99.25 40	99.18 59	99.44 65	99.63 83	99.06 70	98.69 108	99.54 129	99.31 69	99.62 69	99.53 64	97.36 197	99.86 144	99.24 69	99.71 217	99.39 230

v148		98.45 199	98.60 158	98.00 331	99.44 169	94.98 385	97.44 310	99.06 314	98.30 193	99.32 143	98.97 235	96.65 249	99.62 373	98.37 139	99.85 109	99.39 230

test20.03		98.78 133	98.77 127	98.78 202	99.46 162	97.20 262	97.78 250	99.24 276	99.04 119	99.41 114	98.90 254	97.65 165	99.76 270	97.70 203	99.79 159	99.39 230

CDPH-MVS		97.26 334	96.66 366	99.07 136	99.00 301	98.15 146	96.03 421	99.01 329	91.21 502	97.79 377	97.85 415	96.89 228	99.69 325	92.75 463	99.38 339	99.39 230

EPNet		96.14 401	95.44 417	98.25 299	90.76 544	95.50 357	97.92 231	94.65 503	98.97 127	92.98 520	98.85 268	89.12 437	99.87 135	95.99 357	99.68 236	99.39 230
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNVR-MVS		98.17 248	97.87 273	99.07 136	98.67 372	98.24 137	97.01 348	98.93 339	97.25 308	97.62 387	98.34 366	97.27 203	99.57 399	96.42 331	99.33 347	99.39 230

DeepC-MVS_fast	96.85 6	98.30 225	98.15 240	98.75 211	98.61 382	97.23 256	97.76 256	99.09 310	97.31 301	98.75 267	98.66 317	97.56 177	99.64 366	96.10 355	99.55 293	99.39 230
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
dtuplus		98.32 220	98.39 194	98.10 317	99.15 261	95.29 371	96.68 371	99.51 141	97.32 299	99.18 179	99.15 175	97.61 172	99.62 373	97.19 247	99.74 195	99.38 239

SF-MVS		98.53 187	98.27 219	99.32 91	99.31 206	98.75 90	98.19 178	99.41 199	96.77 347	98.83 252	98.90 254	97.80 155	99.82 207	95.68 374	99.52 302	99.38 239

test9_res														93.28 446	99.15 383	99.38 239

hybridnocas07		98.32 220	98.37 199	98.17 309	99.14 263	95.51 353	96.67 373	99.56 118	97.85 241	98.75 267	98.95 243	96.65 249	99.63 369	98.00 169	99.78 164	99.37 242

BP-MVS1		97.40 321	96.97 339	98.71 220	99.07 278	96.81 293	98.34 163	97.18 453	98.58 171	98.17 339	98.61 330	84.01 482	99.94 41	98.97 89	99.78 164	99.37 242

OPM-MVS		98.56 178	98.32 211	99.25 104	99.41 179	98.73 94	97.13 345	99.18 290	97.10 323	98.75 267	98.92 248	98.18 118	99.65 361	96.68 303	99.56 288	99.37 242
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
agg_prior2														92.50 470	99.16 381	99.37 242

AllTest		98.44 200	98.20 229	99.16 118	99.50 140	98.55 108	98.25 172	99.58 101	96.80 344	98.88 241	99.06 199	97.65 165	99.57 399	94.45 408	99.61 269	99.37 242

TestCases				99.16 118	99.50 140	98.55 108		99.58 101	96.80 344	98.88 241	99.06 199	97.65 165	99.57 399	94.45 408	99.61 269	99.37 242

MDA-MVSNet-bldmvs		97.94 271	97.91 270	98.06 325	99.44 169	94.96 386	96.63 377	99.15 302	98.35 186	98.83 252	99.11 187	94.31 352	99.85 158	96.60 312	98.72 424	99.37 242

MVSTER		96.86 364	96.55 375	97.79 348	97.91 452	94.21 413	97.56 290	98.87 352	97.49 278	99.06 191	99.05 206	80.72 495	99.80 233	98.44 131	99.82 133	99.37 242

dtuonlycased		97.70 296	98.19 233	96.24 449	99.75 34	89.51 509	94.69 477	99.64 78	98.23 200	99.46 101	98.57 335	98.25 107	99.85 158	95.65 375	99.44 328	99.36 250

viewcassd2359sk11		98.55 182	98.51 170	98.67 226	99.29 212	96.99 279	97.39 313	99.54 129	97.73 251	98.81 257	99.08 197	97.55 178	99.66 354	97.52 221	99.67 242	99.36 250

pmmvs5		97.64 301	97.49 305	98.08 322	99.14 263	95.12 381	96.70 370	99.05 318	93.77 466	98.62 289	98.83 275	93.23 377	99.75 282	98.33 143	99.76 188	99.36 250

Anonymous20231206		98.21 240	98.21 228	98.20 306	99.51 134	95.43 363	98.13 186	99.32 235	96.16 379	98.93 230	98.82 278	96.00 284	99.83 195	97.32 238	99.73 199	99.36 250

train_agg		97.10 347	96.45 382	99.07 136	98.71 358	98.08 159	95.96 426	99.03 323	91.64 494	95.85 477	97.53 435	96.47 257	99.76 270	93.67 433	99.16 381	99.36 250

PVSNet_BlendedMVS		97.55 308	97.53 302	97.60 375	98.92 316	93.77 440	96.64 376	99.43 189	94.49 444	97.62 387	99.18 163	96.82 233	99.67 341	94.73 399	99.93 57	99.36 250

hybrid		98.22 237	98.27 219	98.08 322	99.13 266	95.24 373	96.61 379	99.53 133	97.43 288	98.46 315	98.97 235	96.75 243	99.65 361	97.84 186	99.69 230	99.35 256

Anonymous20240529		98.93 104	98.87 111	99.12 124	99.19 245	98.22 142	99.01 71	98.99 332	99.25 76	99.54 79	99.37 104	97.04 217	99.80 233	97.89 178	99.52 302	99.35 256

F-COLMAP		97.30 331	96.68 362	99.14 122	99.19 245	98.39 121	97.27 332	99.30 248	92.93 480	96.62 452	98.00 403	95.73 299	99.68 336	92.62 466	98.46 444	99.35 256

viewdifsd2359ckpt13		98.39 211	98.29 215	98.70 221	99.26 227	97.19 263	97.51 298	99.48 156	96.94 332	98.58 298	98.82 278	97.47 191	99.55 406	97.21 246	99.33 347	99.34 259

ppachtmachnet_test		97.50 309	97.74 282	96.78 430	98.70 362	91.23 490	94.55 483	99.05 318	96.36 367	99.21 172	98.79 284	96.39 262	99.78 258	96.74 294	99.82 133	99.34 259

VDD-MVS		98.56 178	98.39 194	99.07 136	99.13 266	98.07 162	98.59 122	97.01 458	99.59 36	99.11 184	99.27 131	94.82 330	99.79 246	98.34 141	99.63 260	99.34 259

testgi		98.32 220	98.39 194	98.13 314	99.57 103	95.54 351	97.78 250	99.49 154	97.37 294	99.19 174	97.65 428	98.96 30	99.49 429	96.50 326	98.99 404	99.34 259

diffmvs		98.22 237	98.24 226	98.17 309	99.00 301	95.44 362	96.38 396	99.58 101	97.79 247	98.53 307	98.50 347	96.76 240	99.74 289	97.95 176	99.64 254	99.34 259
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		97.89 275	97.60 299	98.75 211	99.31 206	97.17 268	97.62 279	99.35 221	98.72 157	98.76 266	98.68 311	92.57 394	99.74 289	97.76 197	95.60 521	99.34 259

dtuonly		96.49 381	97.28 317	94.10 502	98.80 344	83.27 536	93.66 509	99.48 156	95.10 428	97.87 369	98.30 373	95.61 303	99.68 336	96.98 270	99.75 192	99.33 265

viewmambaseed2359dif		98.19 243	98.26 222	97.99 333	99.02 297	95.03 384	96.59 382	99.53 133	96.21 374	99.00 206	98.99 228	97.62 170	99.61 381	97.62 209	99.72 208	99.33 265

baseline		98.96 101	99.02 90	98.76 209	99.38 185	97.26 254	98.49 140	99.50 146	98.86 142	99.19 174	99.06 199	98.23 110	99.69 325	98.71 110	99.76 188	99.33 265

MG-MVS		96.77 368	96.61 371	97.26 402	98.31 417	93.06 452	95.93 429	98.12 423	96.45 365	97.92 364	98.73 296	93.77 368	99.39 453	91.19 493	99.04 395	99.33 265

DKM		98.18 245	97.95 262	98.85 180	99.35 197	98.31 131	96.68 371	99.69 56	96.90 337	98.61 291	98.77 288	94.41 345	98.93 491	97.32 238	99.84 114	99.32 269

HQP4-MVS										95.56 483			99.54 412			99.32 269

CDS-MVSNet		97.69 297	97.35 314	98.69 223	98.73 352	97.02 278	96.92 358	98.75 378	95.89 392	98.59 296	98.67 313	92.08 405	99.74 289	96.72 297	99.81 140	99.32 269
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HQP-MVS		97.00 358	96.49 378	98.55 256	98.67 372	96.79 294	96.29 403	99.04 321	96.05 382	95.55 484	96.84 462	93.84 364	99.54 412	92.82 459	99.26 364	99.32 269

RPSCF		98.62 169	98.36 201	99.42 67	99.65 71	99.42 10	98.55 126	99.57 109	97.72 253	98.90 234	99.26 137	96.12 279	99.52 418	95.72 371	99.71 217	99.32 269

E3new		98.41 202	98.34 205	98.62 238	99.19 245	96.90 287	97.32 323	99.50 146	97.40 291	98.63 285	98.92 248	97.21 208	99.65 361	97.34 234	99.52 302	99.31 274

MVP-Stereo		98.08 256	97.92 268	98.57 249	98.96 308	96.79 294	97.90 234	99.18 290	96.41 366	98.46 315	98.95 243	95.93 293	99.60 385	96.51 325	98.98 407	99.31 274
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 205	98.68 141	97.54 384	98.96 308	97.99 171	97.88 236	99.36 215	98.20 208	99.63 66	99.04 208	98.76 46	95.33 536	96.56 319	99.74 195	99.31 274
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		98.42 201	98.30 213	98.79 199	98.79 347	97.29 251	98.23 173	98.66 386	99.31 69	98.85 248	98.80 282	94.80 333	99.78 258	98.13 154	99.13 386	99.31 274

test_prior				98.95 164	98.69 367	97.95 179		99.03 323					99.59 390			99.30 278

USDC		97.41 320	97.40 309	97.44 394	98.94 310	93.67 443	95.17 461	99.53 133	94.03 462	98.97 215	99.10 190	95.29 315	99.34 460	95.84 367	99.73 199	99.30 278

viewdifsd2359ckpt09		98.13 251	97.92 268	98.77 207	99.18 253	97.35 240	97.29 327	99.53 133	95.81 399	98.09 350	98.47 351	96.34 267	99.66 354	97.02 263	99.51 305	99.29 280

test_fmvsm_n_1920		99.33 30	99.45 23	98.99 154	99.57 103	97.73 210	97.93 228	99.83 26	99.22 80	99.93 6	99.30 125	99.42 11	99.96 13	99.85 6	99.99 5	99.29 280

FMVSNet2		98.49 194	98.40 191	98.75 211	98.90 320	97.14 271	98.61 120	99.13 304	98.59 168	99.19 174	99.28 129	94.14 357	99.82 207	97.97 174	99.80 152	99.29 280

RoMa-SfM		98.46 197	98.27 219	99.02 149	99.35 197	98.32 130	97.56 290	99.70 53	95.88 393	99.38 121	98.65 319	96.41 260	99.46 440	97.78 191	99.71 217	99.28 283

gbinet_0.2-2-1-0.02		95.44 431	94.55 446	98.14 313	95.99 527	95.34 369	94.71 473	98.29 413	96.00 387	96.05 474	90.50 536	84.99 471	99.79 246	97.33 236	97.07 498	99.28 283

XVG-OURS-SEG-HR		98.49 194	98.28 216	99.14 122	99.49 148	98.83 86	96.54 383	99.48 156	97.32 299	99.11 184	98.61 330	99.33 15	99.30 467	96.23 344	98.38 446	99.28 283

mamba_0408		98.80 129	98.88 108	98.55 256	99.27 218	96.50 311	98.00 214	99.60 92	98.93 132	99.22 169	98.84 273	98.59 67	99.89 97	97.74 199	99.72 208	99.27 286

SSM_04072		98.80 129	98.88 108	98.56 254	99.27 218	96.50 311	98.00 214	99.60 92	98.93 132	99.22 169	98.84 273	98.59 67	99.90 81	97.74 199	99.72 208	99.27 286

SSM_0407		98.86 116	98.96 100	98.55 256	99.27 218	96.50 311	98.04 205	99.66 70	99.09 110	99.22 169	99.02 211	98.79 43	99.87 135	97.87 183	99.72 208	99.27 286

test12				98.93 168	98.58 389	97.83 194		98.66 386		96.53 457		95.51 308	99.69 325		99.13 386	99.27 286

DSMNet-mixed		97.42 319	97.60 299	96.87 424	99.15 261	91.46 480	98.54 128	99.12 305	92.87 483	97.58 391	99.63 39	96.21 273	99.90 81	95.74 370	99.54 295	99.27 286

N_pmnet		97.63 302	97.17 325	98.99 154	99.27 218	97.86 191	95.98 423	93.41 519	95.25 424	99.47 100	98.90 254	95.63 302	99.85 158	96.91 274	99.73 199	99.27 286

ambc				98.24 301	98.82 338	95.97 335	98.62 118	99.00 331		99.27 152	99.21 154	96.99 222	99.50 425	96.55 322	99.50 313	99.26 292

DenseAffine		98.10 252	97.86 274	98.84 186	99.32 204	97.93 182	96.62 378	99.76 39	96.68 353	98.65 282	98.72 298	94.46 343	99.33 462	96.76 291	99.75 192	99.25 293

LFMVS		97.20 341	96.72 359	98.64 232	98.72 354	96.95 283	98.93 82	94.14 514	99.74 12	98.78 261	99.01 222	84.45 477	99.73 296	97.44 229	99.27 360	99.25 293

FMVSNet5		96.01 406	95.20 432	98.41 280	97.53 478	96.10 325	98.74 99	99.50 146	97.22 317	98.03 357	99.04 208	69.80 521	99.88 115	97.27 241	99.71 217	99.25 293

BH-RMVSNet		96.83 365	96.58 374	97.58 377	98.47 400	94.05 420	96.67 373	97.36 443	96.70 352	97.87 369	97.98 405	95.14 321	99.44 445	90.47 503	98.58 439	99.25 293

testf1		99.25 40	99.16 62	99.51 49	99.89 6	99.63 3	98.71 106	99.69 56	98.90 136	99.43 108	99.35 111	98.86 35	99.67 341	97.81 188	99.81 140	99.24 297

APD_test2		99.25 40	99.16 62	99.51 49	99.89 6	99.63 3	98.71 106	99.69 56	98.90 136	99.43 108	99.35 111	98.86 35	99.67 341	97.81 188	99.81 140	99.24 297

SSM_0404		98.90 108	99.01 92	98.57 249	99.42 176	96.59 303	98.13 186	99.66 70	99.09 110	99.30 147	99.02 211	98.79 43	99.89 97	97.87 183	99.80 152	99.23 299

旧先验1					98.82 338	97.45 234		98.76 374			98.34 366	95.50 309			99.01 401	99.23 299

test222					98.92 316	96.93 285	95.54 445	98.78 371	85.72 529	96.86 440	98.11 393	94.43 344			99.10 391	99.23 299

XVG-ACMP-BASELINE		98.56 178	98.34 205	99.22 109	99.54 123	98.59 105	97.71 264	99.46 171	97.25 308	98.98 211	98.99 228	97.54 180	99.84 177	95.88 361	99.74 195	99.23 299

FMVSNet3		97.50 309	97.24 321	98.29 295	98.08 443	95.83 341	97.86 240	98.91 345	97.89 238	98.95 221	98.95 243	87.06 451	99.81 224	97.77 193	99.69 230	99.23 299

icg_test_0407_2		98.20 242	98.38 197	97.65 368	99.03 290	94.03 423	95.78 438	99.45 175	98.16 214	99.06 191	98.71 300	98.27 103	99.68 336	97.50 222	99.45 321	99.22 304

IMVS_0407		98.39 211	98.64 149	97.66 366	99.03 290	94.03 423	98.10 193	99.45 175	98.16 214	99.06 191	98.71 300	98.27 103	99.71 308	97.50 222	99.45 321	99.22 304

IMVS_0404		98.07 257	98.20 229	97.69 361	99.03 290	94.03 423	96.67 373	99.45 175	98.16 214	98.03 357	98.71 300	96.80 236	99.82 207	97.50 222	99.45 321	99.22 304

IMVS_0403		98.34 215	98.56 163	97.66 366	99.03 290	94.03 423	97.98 222	99.45 175	98.16 214	98.89 237	98.71 300	97.90 143	99.74 289	97.50 222	99.45 321	99.22 304

无先验							95.74 440	98.74 380	89.38 515				99.73 296	92.38 473		99.22 304

blended_shiyan8		95.98 409	95.33 423	97.94 336	97.05 499	94.87 392	95.34 455	98.59 392	96.17 375	97.09 422	92.39 527	87.62 450	99.76 270	97.65 206	96.05 518	99.20 309

tttt0517		95.64 423	94.98 436	97.64 371	99.36 192	93.81 438	98.72 104	90.47 533	98.08 224	98.67 279	98.34 366	73.88 516	99.92 65	97.77 193	99.51 305	99.20 309

pmmvs-eth3d		98.47 196	98.34 205	98.86 179	99.30 210	97.76 206	97.16 343	99.28 260	95.54 411	99.42 112	99.19 159	97.27 203	99.63 369	97.89 178	99.97 21	99.20 309

MS-PatchMatch		97.68 298	97.75 281	97.45 393	98.23 429	93.78 439	97.29 327	98.84 361	96.10 381	98.64 284	98.65 319	96.04 281	99.36 456	96.84 285	99.14 384	99.20 309

新几何1				98.91 173	98.94 310	97.76 206		98.76 374	87.58 526	96.75 445	98.10 394	94.80 333	99.78 258	92.73 464	99.00 402	99.20 309

PHI-MVS		98.29 228	97.95 262	99.34 83	98.44 405	99.16 48	98.12 190	99.38 207	96.01 386	98.06 353	98.43 355	97.80 155	99.67 341	95.69 373	99.58 280	99.20 309

blended_shiyan6		95.99 408	95.33 423	97.95 335	97.06 497	94.89 390	95.34 455	98.58 393	96.17 375	97.06 424	92.41 526	87.64 449	99.76 270	97.64 207	96.09 512	99.19 315

GDP-MVS		97.50 309	97.11 332	98.67 226	99.02 297	96.85 291	98.16 183	99.71 48	98.32 191	98.52 309	98.54 338	83.39 486	99.95 25	98.79 101	99.56 288	99.19 315

Anonymous202405211		97.90 273	97.50 304	99.08 134	98.90 320	98.25 136	98.53 129	96.16 481	98.87 140	99.11 184	98.86 265	90.40 426	99.78 258	97.36 233	99.31 352	99.19 315

CANet		97.87 280	97.76 280	98.19 308	97.75 461	95.51 353	96.76 366	99.05 318	97.74 250	96.93 430	98.21 384	95.59 305	99.89 97	97.86 185	99.93 57	99.19 315

XVG-OURS		98.53 187	98.34 205	99.11 126	99.50 140	98.82 88	95.97 424	99.50 146	97.30 302	99.05 199	98.98 233	99.35 14	99.32 464	95.72 371	99.68 236	99.18 319

WTY-MVS		96.67 371	96.27 390	97.87 343	98.81 341	94.61 403	96.77 365	97.92 428	94.94 433	97.12 419	97.74 423	91.11 418	99.82 207	93.89 426	98.15 460	99.18 319

Vis-MVSNet (Re-imp)		97.46 314	97.16 326	98.34 290	99.55 117	96.10 325	98.94 81	98.44 404	98.32 191	98.16 342	98.62 328	88.76 438	99.73 296	93.88 427	99.79 159	99.18 319

TinyColmap		97.89 275	97.98 258	97.60 375	98.86 329	94.35 409	96.21 408	99.44 183	97.45 286	99.06 191	98.88 262	97.99 137	99.28 471	94.38 414	99.58 280	99.18 319

wanda-best-256-512		95.48 429	94.74 443	97.68 362	96.53 513	94.12 417	94.17 495	98.57 395	95.84 395	96.71 446	91.16 532	86.05 461	99.76 270	97.57 214	96.09 512	99.17 323

FE-blended-shiyan7		95.48 429	94.74 443	97.68 362	96.53 513	94.12 417	94.17 495	98.57 395	95.84 395	96.71 446	91.16 532	86.05 461	99.76 270	97.57 214	96.09 512	99.17 323

usedtu_blend_shiyan5		96.20 400	95.62 406	97.94 336	96.53 513	94.93 387	98.83 96	99.59 98	98.89 138	96.71 446	91.16 532	86.05 461	99.73 296	96.70 300	96.09 512	99.17 323

testdata				98.09 319	98.93 312	95.40 364		98.80 368	90.08 511	97.45 405	98.37 362	95.26 316	99.70 315	93.58 437	98.95 410	99.17 323

lupinMVS		97.06 352	96.86 348	97.65 368	98.88 326	93.89 436	95.48 449	97.97 426	93.53 469	98.16 342	97.58 432	93.81 366	99.91 74	96.77 290	99.57 284	99.17 323

Patchmtry		97.35 326	96.97 339	98.50 270	97.31 490	96.47 314	98.18 179	98.92 343	98.95 131	98.78 261	99.37 104	85.44 469	99.85 158	95.96 359	99.83 126	99.17 323

usedtu_dtu_shiyan1		97.37 323	97.13 330	98.11 315	99.03 290	95.40 364	94.47 485	98.99 332	96.87 339	97.97 361	97.81 418	92.12 402	99.75 282	97.49 227	99.43 330	99.16 329

FE-MVSNET3		97.37 323	97.13 330	98.11 315	99.03 290	95.40 364	94.47 485	98.99 332	96.87 339	97.97 361	97.81 418	92.12 402	99.75 282	97.49 227	99.43 330	99.16 329

SD_0403		96.28 394	95.83 398	97.64 371	98.72 354	94.30 410	98.87 89	98.77 372	97.80 245	96.53 457	98.02 402	97.34 198	99.47 436	76.93 536	99.48 317	99.16 329

RRT-MVS		97.88 278	97.98 258	97.61 374	98.15 436	93.77 440	98.97 77	99.64 78	99.16 94	98.69 275	99.42 89	91.60 408	99.89 97	97.63 208	98.52 443	99.16 329

sss		97.21 340	96.93 341	98.06 325	98.83 335	95.22 377	96.75 367	98.48 403	94.49 444	97.27 414	97.90 411	92.77 390	99.80 233	96.57 315	99.32 350	99.16 329

CSCG		98.68 157	98.50 173	99.20 110	99.45 167	98.63 100	98.56 125	99.57 109	97.87 239	98.85 248	98.04 400	97.66 164	99.84 177	96.72 297	99.81 140	99.13 334

MVS_111021_LR		98.30 225	98.12 243	98.83 188	99.16 257	98.03 167	96.09 418	99.30 248	97.58 266	98.10 349	98.24 381	98.25 107	99.34 460	96.69 302	99.65 252	99.12 335

miper_lstm_enhance		97.18 343	97.16 326	97.25 403	98.16 435	92.85 458	95.15 463	99.31 240	97.25 308	98.74 270	98.78 286	90.07 427	99.78 258	97.19 247	99.80 152	99.11 336

testing3		93.51 468	92.09 481	97.75 354	98.60 384	94.40 407	97.32 323	95.26 499	97.56 269	96.79 444	95.50 493	53.57 545	99.77 264	95.26 387	98.97 408	99.08 337

原ACMM1				98.35 289	98.90 320	96.25 322		98.83 365	92.48 487	96.07 472	98.10 394	95.39 313	99.71 308	92.61 467	98.99 404	99.08 337

QAPM		97.31 329	96.81 354	98.82 190	98.80 344	97.49 227	99.06 66	99.19 286	90.22 509	97.69 383	99.16 169	96.91 227	99.90 81	90.89 499	99.41 333	99.07 339

PAPM_NR		96.82 367	96.32 386	98.30 294	99.07 278	96.69 301	97.48 302	98.76 374	95.81 399	96.61 453	96.47 472	94.12 360	99.17 478	90.82 501	97.78 474	99.06 340

eth_miper_zixun_eth		97.23 338	97.25 320	97.17 407	98.00 447	92.77 460	94.71 473	99.18 290	97.27 306	98.56 302	98.74 295	91.89 406	99.69 325	97.06 262	99.81 140	99.05 341

D2MVS		97.84 287	97.84 276	97.83 345	99.14 263	94.74 397	96.94 354	98.88 350	95.84 395	98.89 237	98.96 239	94.40 347	99.69 325	97.55 216	99.95 39	99.05 341

c3_l		97.36 325	97.37 312	97.31 398	98.09 442	93.25 450	95.01 466	99.16 297	97.05 325	98.77 264	98.72 298	92.88 387	99.64 366	96.93 273	99.76 188	99.05 341

PLC	94.65 16	96.51 378	95.73 402	98.85 180	98.75 350	97.91 185	96.42 394	99.06 314	90.94 506	95.59 481	97.38 448	94.41 345	99.59 390	90.93 497	98.04 469	99.05 341
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tfpnnormal		98.90 108	98.90 105	98.91 173	99.67 68	97.82 199	99.00 73	99.44 183	99.45 50	99.51 92	99.24 144	98.20 117	99.86 144	95.92 360	99.69 230	99.04 345

CANet_DTU		97.26 334	97.06 334	97.84 344	97.57 473	94.65 402	96.19 410	98.79 369	97.23 314	95.14 494	98.24 381	93.22 378	99.84 177	97.34 234	99.84 114	99.04 345

PM-MVS		98.82 125	98.72 132	99.12 124	99.64 77	98.54 111	97.98 222	99.68 63	97.62 260	99.34 134	99.18 163	97.54 180	99.77 264	97.79 190	99.74 195	99.04 345

TestfortrainingZip				98.97 160	98.30 418	98.43 119	98.68 109	98.26 414	97.76 249	98.86 247	98.16 389	95.15 320	99.47 436		97.55 479	99.02 348

TSAR-MVS + GP.		98.18 245	97.98 258	98.77 207	98.71 358	97.88 189	96.32 401	98.66 386	96.33 368	99.23 168	98.51 343	97.48 190	99.40 451	97.16 250	99.46 319	99.02 348

DIV-MVS_self_test		97.02 355	96.84 350	97.58 377	97.82 458	94.03 423	94.66 478	99.16 297	97.04 326	98.63 285	98.71 300	88.69 439	99.69 325	97.00 265	99.81 140	99.01 350

GA-MVS		95.86 415	95.32 425	97.49 389	98.60 384	94.15 416	93.83 506	97.93 427	95.49 413	96.68 449	97.42 446	83.21 487	99.30 467	96.22 345	98.55 441	99.01 350

OMC-MVS		97.88 278	97.49 305	99.04 145	98.89 325	98.63 100	96.94 354	99.25 271	95.02 430	98.53 307	98.51 343	97.27 203	99.47 436	93.50 441	99.51 305	99.01 350

cl____		97.02 355	96.83 351	97.58 377	97.82 458	94.04 422	94.66 478	99.16 297	97.04 326	98.63 285	98.71 300	88.68 441	99.69 325	97.00 265	99.81 140	99.00 353

pmmvs4		97.58 306	97.28 317	98.51 266	98.84 333	96.93 285	95.40 453	98.52 401	93.60 468	98.61 291	98.65 319	95.10 322	99.60 385	96.97 271	99.79 159	98.99 354

blend_shiyan4		92.09 492	90.16 499	97.88 341	96.78 507	94.93 387	95.24 459	98.58 393	96.22 373	96.07 472	91.42 531	63.46 540	99.73 296	96.70 300	76.98 540	98.98 355

EPNet_dtu		94.93 445	94.78 441	95.38 486	93.58 535	87.68 518	96.78 364	95.69 495	97.35 296	89.14 535	98.09 396	88.15 447	99.49 429	94.95 395	99.30 356	98.98 355
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t		96.50 380	95.77 400	98.69 223	99.48 156	97.43 237	97.84 243	99.55 123	81.42 535	96.51 461	98.58 334	95.53 306	99.67 341	93.41 444	99.58 280	98.98 355

PVSNet_Blended		96.88 362	96.68 362	97.47 392	98.92 316	93.77 440	94.71 473	99.43 189	90.98 505	97.62 387	97.36 450	96.82 233	99.67 341	94.73 399	99.56 288	98.98 355

ArgMatch-SfM		97.96 270	97.72 286	98.66 228	99.02 297	97.33 242	96.49 388	99.52 139	95.46 415	98.71 274	98.29 376	96.14 275	99.69 325	96.30 340	99.56 288	98.97 359

APD_test1		98.83 122	98.66 146	99.34 83	99.78 24	99.47 8	98.42 151	99.45 175	98.28 198	98.98 211	99.19 159	97.76 158	99.58 397	96.57 315	99.55 293	98.97 359

PAPR		95.29 435	94.47 447	97.75 354	97.50 484	95.14 380	94.89 470	98.71 383	91.39 500	95.35 491	95.48 495	94.57 340	99.14 481	84.95 523	97.37 489	98.97 359

EGC-MVSNET		85.24 503	80.54 506	99.34 83	99.77 27	99.20 38	99.08 62	99.29 256	12.08 543	20.84 544	99.42 89	97.55 178	99.85 158	97.08 259	99.72 208	98.96 362

thisisatest0530		95.27 436	94.45 448	97.74 356	99.19 245	94.37 408	97.86 240	90.20 534	97.17 319	98.22 337	97.65 428	73.53 517	99.90 81	96.90 279	99.35 343	98.95 363

mvs_anonymous		97.83 289	98.16 239	96.87 424	98.18 432	91.89 474	97.31 325	98.90 346	97.37 294	98.83 252	99.46 80	96.28 270	99.79 246	98.90 94	98.16 459	98.95 363

baseline1		95.96 412	95.44 417	97.52 386	98.51 398	93.99 430	98.39 157	96.09 485	98.21 204	98.40 326	97.76 422	86.88 452	99.63 369	95.42 383	89.27 534	98.95 363

CLD-MVS		97.49 312	97.16 326	98.48 272	99.07 278	97.03 277	94.71 473	99.21 280	94.46 446	98.06 353	97.16 456	97.57 176	99.48 433	94.46 407	99.78 164	98.95 363
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MSLP-MVS++		98.02 261	98.14 242	97.64 371	98.58 389	95.19 378	97.48 302	99.23 278	97.47 279	97.90 366	98.62 328	97.04 217	98.81 496	97.55 216	99.41 333	98.94 367

DELS-MVS		98.27 230	98.20 229	98.48 272	98.86 329	96.70 300	95.60 444	99.20 282	97.73 251	98.45 317	98.71 300	97.50 186	99.82 207	98.21 149	99.59 275	98.93 368
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		95.79 418	95.39 420	96.98 417	96.77 508	92.79 459	94.40 488	98.53 399	94.59 443	97.89 367	98.17 387	82.82 491	99.24 473	96.37 334	99.03 396	98.92 369

LS3D		98.63 166	98.38 197	99.36 74	97.25 491	99.38 12	99.12 61	99.32 235	99.21 82	98.44 318	98.88 262	97.31 199	99.80 233	96.58 313	99.34 345	98.92 369

CMPMVS	75.91 23	96.29 393	95.44 417	98.84 186	96.25 522	98.69 98	97.02 347	99.12 305	88.90 518	97.83 374	98.86 265	89.51 434	98.90 494	91.92 477	99.51 305	98.92 369
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LCM-MVSNet-Re		98.64 164	98.48 179	99.11 126	98.85 332	98.51 113	98.49 140	99.83 26	98.37 184	99.69 55	99.46 80	98.21 115	99.92 65	94.13 420	99.30 356	98.91 372

mvsmamba		97.57 307	97.26 319	98.51 266	98.69 367	96.73 299	98.74 99	97.25 450	97.03 328	97.88 368	99.23 150	90.95 419	99.87 135	96.61 311	99.00 402	98.91 372

DPM-MVS		96.32 391	95.59 410	98.51 266	98.76 348	97.21 261	94.54 484	98.26 414	91.94 493	96.37 465	97.25 454	93.06 384	99.43 447	91.42 488	98.74 422	98.89 374

test_yl		96.69 369	96.29 388	97.90 338	98.28 421	95.24 373	97.29 327	97.36 443	98.21 204	98.17 339	97.86 413	86.27 456	99.55 406	94.87 396	98.32 448	98.89 374

DCV-MVSNet		96.69 369	96.29 388	97.90 338	98.28 421	95.24 373	97.29 327	97.36 443	98.21 204	98.17 339	97.86 413	86.27 456	99.55 406	94.87 396	98.32 448	98.89 374

SPE-MVS-test		99.13 66	99.09 82	99.26 101	99.13 266	98.97 73	99.31 30	99.88 15	99.44 52	98.16 342	98.51 343	98.64 61	99.93 53	98.91 93	99.85 109	98.88 377

UnsupCasMVSNet_bld		97.30 331	96.92 343	98.45 275	99.28 215	96.78 297	96.20 409	99.27 263	95.42 417	98.28 334	98.30 373	93.16 379	99.71 308	94.99 392	97.37 489	98.87 378

Effi-MVS+		98.02 261	97.82 277	98.62 238	98.53 396	97.19 263	97.33 322	99.68 63	97.30 302	96.68 449	97.46 444	98.56 73	99.80 233	96.63 309	98.20 455	98.86 379

test_0402		98.76 137	98.71 135	98.93 168	99.56 111	98.14 148	98.45 147	99.34 227	99.28 73	98.95 221	98.91 251	98.34 95	99.79 246	95.63 376	99.91 80	98.86 379

PMatch-SfM		97.89 275	97.64 295	98.66 228	99.26 227	97.44 236	96.08 419	99.51 141	96.72 349	98.47 314	99.13 181	93.62 372	99.70 315	97.14 253	98.80 419	98.83 381

PatchmatchNet		95.58 425	95.67 405	95.30 489	97.34 488	87.32 520	97.65 274	96.65 472	95.30 421	97.07 423	98.69 309	84.77 474	99.75 282	94.97 394	98.64 433	98.83 381
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
testing3-2		93.78 464	93.91 455	93.39 513	98.82 338	81.72 542	97.76 256	95.28 498	98.60 167	96.54 456	96.66 467	65.85 533	99.62 373	96.65 308	98.99 404	98.82 383

test_vis1_rt		97.75 292	97.72 286	97.83 345	98.81 341	96.35 319	97.30 326	99.69 56	94.61 442	97.87 369	98.05 399	96.26 271	98.32 505	98.74 107	98.18 456	98.82 383

CL-MVSNet_self_test		97.44 317	97.22 323	98.08 322	98.57 391	95.78 345	94.30 491	98.79 369	96.58 357	98.60 294	98.19 386	94.74 336	99.64 366	96.41 332	98.84 415	98.82 383

miper_ehance_all_eth		97.06 352	97.03 335	97.16 409	97.83 457	93.06 452	94.66 478	99.09 310	95.99 388	98.69 275	98.45 353	92.73 392	99.61 381	96.79 287	99.03 396	98.82 383

MIMVSNet		96.62 374	96.25 391	97.71 360	99.04 287	94.66 401	99.16 55	96.92 466	97.23 314	97.87 369	99.10 190	86.11 460	99.65 361	91.65 483	99.21 373	98.82 383

hse-mvs2		97.46 314	97.07 333	98.64 232	98.73 352	97.33 242	97.45 308	97.64 438	99.11 100	98.58 298	97.98 405	88.65 442	99.79 246	98.11 156	97.39 488	98.81 388

GSMVS																98.81 388

sam_mvs1												84.74 475				98.81 388

SCA		96.41 388	96.66 366	95.67 476	98.24 426	88.35 514	95.85 435	96.88 467	96.11 380	97.67 384	98.67 313	93.10 382	99.85 158	94.16 416	99.22 370	98.81 388

Patchmatch-RL test		97.26 334	97.02 336	97.99 333	99.52 131	95.53 352	96.13 415	99.71 48	97.47 279	99.27 152	99.16 169	84.30 480	99.62 373	97.89 178	99.77 172	98.81 388

AUN-MVS		96.24 399	95.45 416	98.60 244	98.70 362	97.22 259	97.38 315	97.65 436	95.95 390	95.53 488	97.96 409	82.11 494	99.79 246	96.31 338	97.44 485	98.80 393

ITE_SJBPF				98.87 177	99.22 236	98.48 115		99.35 221	97.50 276	98.28 334	98.60 332	97.64 168	99.35 459	93.86 428	99.27 360	98.79 394

tpm		94.67 447	94.34 452	95.66 477	97.68 470	88.42 513	97.88 236	94.90 501	94.46 446	96.03 476	98.56 337	78.66 506	99.79 246	95.88 361	95.01 524	98.78 395

Patchmatch-test		96.55 377	96.34 385	97.17 407	98.35 414	93.06 452	98.40 156	97.79 429	97.33 297	98.41 321	98.67 313	83.68 485	99.69 325	95.16 390	99.31 352	98.77 396

EC-MVSNet		99.09 73	99.05 86	99.20 110	99.28 215	98.93 79	99.24 44	99.84 23	99.08 114	98.12 347	98.37 362	98.72 50	99.90 81	99.05 83	99.77 172	98.77 396

PMMVS		96.51 378	95.98 394	98.09 319	97.53 478	95.84 340	94.92 468	98.84 361	91.58 496	96.05 474	95.58 490	95.68 301	99.66 354	95.59 379	98.09 463	98.76 398

test_method		79.78 504	79.50 507	80.62 522	80.21 547	45.76 550	70.82 538	98.41 409	31.08 542	80.89 542	97.71 424	84.85 473	97.37 521	91.51 487	80.03 538	98.75 399

ab-mvs		98.41 202	98.36 201	98.59 245	99.19 245	97.23 256	99.32 26	98.81 366	97.66 257	98.62 289	99.40 97	96.82 233	99.80 233	95.88 361	99.51 305	98.75 399

ELoFTR		97.81 290	97.74 282	98.04 328	99.39 183	95.79 344	97.28 331	99.58 101	94.13 457	99.38 121	99.37 104	93.31 375	99.60 385	97.23 244	99.96 28	98.74 401

CHOSEN 280x420		95.51 428	95.47 414	95.65 478	98.25 424	88.27 515	93.25 517	98.88 350	93.53 469	94.65 503	97.15 457	86.17 458	99.93 53	97.41 231	99.93 57	98.73 402

test_fmvsmvis_n_1920		99.26 39	99.49 16	98.54 261	99.66 70	96.97 280	98.00 214	99.85 19	99.24 77	99.92 8	99.50 68	99.39 12	99.95 25	99.89 3	99.98 12	98.71 403

MVS_Test		98.18 245	98.36 201	97.67 364	98.48 399	94.73 398	98.18 179	99.02 326	97.69 254	98.04 356	99.11 187	97.22 207	99.56 402	98.57 121	98.90 414	98.71 403

PVSNet	93.40 17	95.67 421	95.70 403	95.57 479	98.83 335	88.57 512	92.50 522	97.72 431	92.69 485	96.49 464	96.44 473	93.72 369	99.43 447	93.61 434	99.28 359	98.71 403

alignmvs		97.35 326	96.88 347	98.78 202	98.54 394	98.09 155	97.71 264	97.69 433	99.20 84	97.59 390	95.90 484	88.12 448	99.55 406	98.18 151	98.96 409	98.70 406

ADS-MVSNet2		95.43 432	94.98 436	96.76 431	98.14 437	91.74 475	97.92 231	97.76 430	90.23 507	96.51 461	98.91 251	85.61 466	99.85 158	92.88 457	96.90 499	98.69 407

ADS-MVSNet		95.24 437	94.93 439	96.18 454	98.14 437	90.10 504	97.92 231	97.32 448	90.23 507	96.51 461	98.91 251	85.61 466	99.74 289	92.88 457	96.90 499	98.69 407

MDTV_nov1_ep13_2view						74.92 546	97.69 267		90.06 512	97.75 380		85.78 465		93.52 439		98.69 407

LoFTR		97.97 269	97.79 278	98.53 263	98.80 344	97.47 231	97.01 348	99.55 123	95.55 409	99.46 101	99.22 152	94.22 355	99.44 445	96.45 329	99.82 133	98.68 410

MSDG		97.71 295	97.52 303	98.28 296	98.91 319	96.82 292	94.42 487	99.37 211	97.65 258	98.37 327	98.29 376	97.40 194	99.33 462	94.09 421	99.22 370	98.68 410

mvsany_test1		97.60 303	97.54 301	97.77 350	97.72 462	95.35 367	95.36 454	97.13 456	94.13 457	99.71 49	99.33 118	97.93 141	99.30 467	97.60 212	98.94 411	98.67 412

CS-MVS		99.13 66	99.10 80	99.24 106	99.06 283	99.15 52	99.36 22	99.88 15	99.36 63	98.21 338	98.46 352	98.68 58	99.93 53	99.03 85	99.85 109	98.64 413

Syy-MVS		96.04 404	95.56 412	97.49 389	97.10 495	94.48 405	96.18 412	96.58 474	95.65 405	94.77 500	92.29 529	91.27 417	99.36 456	98.17 153	98.05 467	98.63 414

myMVS_eth3d		91.92 494	90.45 495	96.30 445	97.10 495	90.90 495	96.18 412	96.58 474	95.65 405	94.77 500	92.29 529	53.88 544	99.36 456	89.59 509	98.05 467	98.63 414

BridgeMVS		98.63 166	98.72 132	98.38 284	98.66 377	96.68 302	98.90 84	99.42 195	98.99 124	98.97 215	99.19 159	95.81 297	99.85 158	98.77 105	99.77 172	98.60 416

miper_enhance_ethall		96.01 406	95.74 401	96.81 428	96.41 520	92.27 471	93.69 508	98.89 349	91.14 503	98.30 330	97.35 451	90.58 424	99.58 397	96.31 338	99.03 396	98.60 416

Effi-MVS+-dtu		98.26 232	97.90 271	99.35 80	98.02 446	99.49 5	98.02 210	99.16 297	98.29 196	97.64 385	97.99 404	96.44 259	99.95 25	96.66 307	98.93 412	98.60 416

new_pmnet		96.99 359	96.76 356	97.67 364	98.72 354	94.89 390	95.95 428	98.20 418	92.62 486	98.55 304	98.54 338	94.88 329	99.52 418	93.96 424	99.44 328	98.59 419

MVSMamba_PlusPlus		98.83 122	98.98 97	98.36 288	99.32 204	96.58 306	98.90 84	99.41 199	99.75 10	98.72 271	99.50 68	96.17 274	99.94 41	99.27 64	99.78 164	98.57 420

testing91		93.32 472	92.27 478	96.47 439	97.54 476	91.25 488	96.17 414	96.76 470	97.18 318	93.65 518	93.50 518	65.11 535	99.63 369	93.04 452	97.45 484	98.53 421

EIA-MVS		98.00 264	97.74 282	98.80 195	98.72 354	98.09 155	98.05 203	99.60 92	97.39 292	96.63 451	95.55 491	97.68 162	99.80 233	96.73 296	99.27 360	98.52 422

PatchMatch-RL		97.24 337	96.78 355	98.61 242	99.03 290	97.83 194	96.36 398	99.06 314	93.49 471	97.36 412	97.78 420	95.75 298	99.49 429	93.44 443	98.77 420	98.52 422

sasdasda		98.34 215	98.26 222	98.58 246	98.46 402	97.82 199	98.96 78	99.46 171	99.19 89	97.46 402	95.46 496	98.59 67	99.46 440	98.08 159	98.71 426	98.46 424

ET-MVSNet_ETH3D		94.30 454	93.21 466	97.58 377	98.14 437	94.47 406	94.78 472	93.24 521	94.72 439	89.56 533	95.87 485	78.57 508	99.81 224	96.91 274	97.11 497	98.46 424

canonicalmvs		98.34 215	98.26 222	98.58 246	98.46 402	97.82 199	98.96 78	99.46 171	99.19 89	97.46 402	95.46 496	98.59 67	99.46 440	98.08 159	98.71 426	98.46 424

UBG		93.25 474	92.32 476	96.04 462	97.72 462	90.16 503	95.92 431	95.91 489	96.03 385	93.95 515	93.04 523	69.60 522	99.52 418	90.72 502	97.98 471	98.45 427

tt0805		98.69 151	98.62 153	98.90 176	99.75 34	99.30 21	99.15 57	96.97 461	98.86 142	98.87 246	97.62 431	98.63 63	98.96 489	99.41 56	98.29 452	98.45 427

TAPA-MVS	96.21 11	96.63 373	95.95 396	98.65 230	98.93 312	98.09 155	96.93 356	99.28 260	83.58 532	98.13 346	97.78 420	96.13 277	99.40 451	93.52 439	99.29 358	98.45 427
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MGCFI-Net		98.34 215	98.28 216	98.51 266	98.47 400	97.59 222	98.96 78	99.48 156	99.18 92	97.40 408	95.50 493	98.66 59	99.50 425	98.18 151	98.71 426	98.44 430

BH-untuned		96.83 365	96.75 358	97.08 411	98.74 351	93.33 449	96.71 369	98.26 414	96.72 349	98.44 318	97.37 449	95.20 317	99.47 436	91.89 478	97.43 486	98.44 430

WB-MVSnew		95.73 420	95.57 411	96.23 451	96.70 510	90.70 500	96.07 420	93.86 516	95.60 407	97.04 426	95.45 500	96.00 284	99.55 406	91.04 494	98.31 450	98.43 432

pmmvs3		95.03 442	94.40 450	96.93 420	97.70 467	92.53 464	95.08 464	97.71 432	88.57 521	97.71 381	98.08 397	79.39 502	99.82 207	96.19 347	99.11 390	98.43 432

DP-MVS Recon		97.33 328	96.92 343	98.57 249	99.09 274	97.99 171	96.79 362	99.35 221	93.18 474	97.71 381	98.07 398	95.00 325	99.31 465	93.97 423	99.13 386	98.42 434

testing99		93.04 478	91.98 486	96.23 451	97.53 478	90.70 500	96.35 399	95.94 488	96.87 339	93.41 519	93.43 520	63.84 537	99.59 390	93.24 448	97.19 494	98.40 435

ETVMVS		92.60 484	91.08 493	97.18 405	97.70 467	93.65 445	96.54 383	95.70 493	96.51 358	94.68 502	92.39 527	61.80 541	99.50 425	86.97 516	97.41 487	98.40 435

Fast-Effi-MVS+-dtu		98.27 230	98.09 245	98.81 192	98.43 407	98.11 151	97.61 284	99.50 146	98.64 160	97.39 410	97.52 438	98.12 126	99.95 25	96.90 279	98.71 426	98.38 437

LF4IMVS		97.90 273	97.69 289	98.52 265	99.17 255	97.66 215	97.19 342	99.47 166	96.31 370	97.85 373	98.20 385	96.71 245	99.52 418	94.62 402	99.72 208	98.38 437

testing11		93.08 477	92.02 483	96.26 448	97.56 474	90.83 497	96.32 401	95.70 493	96.47 363	92.66 523	93.73 515	64.36 536	99.59 390	93.77 431	97.57 478	98.37 439

Fast-Effi-MVS+		97.67 299	97.38 311	98.57 249	98.71 358	97.43 237	97.23 333	99.45 175	94.82 437	96.13 469	96.51 469	98.52 75	99.91 74	96.19 347	98.83 416	98.37 439

test0.0.03 1		94.51 449	93.69 459	96.99 416	96.05 524	93.61 447	94.97 467	93.49 518	96.17 375	97.57 393	94.88 507	82.30 492	99.01 488	93.60 436	94.17 528	98.37 439

UWE-MVS		92.38 487	91.76 490	94.21 501	97.16 493	84.65 529	95.42 452	88.45 537	95.96 389	96.17 468	95.84 487	66.36 529	99.71 308	91.87 479	98.64 433	98.28 442

FE-MVS		95.66 422	94.95 438	97.77 350	98.53 396	95.28 372	99.40 19	96.09 485	93.11 476	97.96 363	99.26 137	79.10 504	99.77 264	92.40 472	98.71 426	98.27 443

baseline2		93.73 465	92.83 472	96.42 441	97.70 467	91.28 487	96.84 361	89.77 535	93.96 465	92.44 525	95.93 483	79.14 503	99.77 264	92.94 454	96.76 503	98.21 444

thisisatest0515		94.12 459	93.16 467	96.97 418	98.60 384	92.90 457	93.77 507	90.61 532	94.10 459	96.91 433	95.87 485	74.99 514	99.80 233	94.52 405	99.12 389	98.20 445

EPMVS		93.72 466	93.27 465	95.09 492	96.04 525	87.76 517	98.13 186	85.01 542	94.69 440	96.92 431	98.64 323	78.47 510	99.31 465	95.04 391	96.46 506	98.20 445

balanced_ft_v1		98.28 229	98.35 204	98.10 317	98.08 443	96.23 323	99.23 45	99.26 269	98.34 187	97.46 402	99.42 89	95.38 314	99.88 115	98.60 117	99.34 345	98.17 447

dp		93.47 469	93.59 461	93.13 516	96.64 511	81.62 543	97.66 272	96.42 478	92.80 484	96.11 470	98.64 323	78.55 509	99.59 390	93.31 445	92.18 533	98.16 448

CNLPA		97.17 344	96.71 360	98.55 256	98.56 392	98.05 166	96.33 400	98.93 339	96.91 336	97.06 424	97.39 447	94.38 348	99.45 443	91.66 482	99.18 380	98.14 449

dmvs_re		95.98 409	95.39 420	97.74 356	98.86 329	97.45 234	98.37 159	95.69 495	97.95 231	96.56 455	95.95 482	90.70 423	97.68 516	88.32 512	96.13 511	98.11 450

HY-MVS	95.94 13	95.90 414	95.35 422	97.55 383	97.95 449	94.79 394	98.81 98	96.94 464	92.28 490	95.17 493	98.57 335	89.90 429	99.75 282	91.20 492	97.33 493	98.10 451

CostFormer		93.97 461	93.78 458	94.51 497	97.53 478	85.83 525	97.98 222	95.96 487	89.29 516	94.99 497	98.63 325	78.63 507	99.62 373	94.54 404	96.50 505	98.09 452

FA-MVS(test-final)		96.99 359	96.82 352	97.50 388	98.70 362	94.78 395	99.34 23	96.99 459	95.07 429	98.48 313	99.33 118	88.41 445	99.65 361	96.13 353	98.92 413	98.07 453

AdaColmap		97.14 346	96.71 360	98.46 274	98.34 415	97.80 203	96.95 353	98.93 339	95.58 408	96.92 431	97.66 427	95.87 295	99.53 414	90.97 496	99.14 384	98.04 454

KD-MVS_2432*1600		92.87 482	91.99 484	95.51 482	91.37 540	89.27 510	94.07 498	98.14 421	95.42 417	97.25 415	96.44 473	67.86 524	99.24 473	91.28 490	96.08 516	98.02 455

miper_refine_blended		92.87 482	91.99 484	95.51 482	91.37 540	89.27 510	94.07 498	98.14 421	95.42 417	97.25 415	96.44 473	67.86 524	99.24 473	91.28 490	96.08 516	98.02 455

TESTMET0.1,1		92.19 491	91.77 489	93.46 510	96.48 518	82.80 539	94.05 500	91.52 531	94.45 449	94.00 513	94.88 507	66.65 528	99.56 402	95.78 369	98.11 462	98.02 455

testing222		91.96 493	90.37 496	96.72 432	97.47 485	92.59 462	96.11 417	94.76 502	96.83 343	92.90 521	92.87 524	57.92 543	99.55 406	86.93 517	97.52 480	98.00 458

PCF-MVS	92.86 18	94.36 451	93.00 470	98.42 279	98.70 362	97.56 223	93.16 519	99.11 307	79.59 536	97.55 394	97.43 445	92.19 400	99.73 296	79.85 533	99.45 321	97.97 459
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS-28		90.22 497	89.28 500	93.02 517	94.50 534	82.87 538	96.52 386	87.51 538	95.21 426	92.36 526	96.04 479	71.57 519	98.25 507	72.04 538	97.77 475	97.94 460

myMVS_eth3d28		92.92 481	92.31 477	94.77 493	97.84 456	87.59 519	96.19 410	96.11 483	97.08 324	94.27 506	93.49 519	66.07 532	98.78 497	91.78 480	97.93 473	97.92 461

OpenMVS	96.65 7	97.09 349	96.68 362	98.32 291	98.32 416	97.16 269	98.86 92	99.37 211	89.48 514	96.29 467	99.15 175	96.56 253	99.90 81	92.90 456	99.20 375	97.89 462

Gipuma		99.03 88	99.16 62	98.64 232	99.94 2	98.51 113	99.32 26	99.75 43	99.58 38	98.60 294	99.62 40	98.22 113	99.51 424	97.70 203	99.73 199	97.89 462
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PVSNet_0	89.98 21	91.15 496	90.30 498	93.70 508	97.72 462	84.34 533	90.24 529	97.42 441	90.20 510	93.79 516	93.09 522	90.90 421	98.89 495	86.57 520	72.76 541	97.87 464

test-LLR		93.90 462	93.85 456	94.04 503	96.53 513	84.62 530	94.05 500	92.39 523	96.17 375	94.12 509	95.07 501	82.30 492	99.67 341	95.87 364	98.18 456	97.82 465

test-mter		92.33 489	91.76 490	94.04 503	96.53 513	84.62 530	94.05 500	92.39 523	94.00 464	94.12 509	95.07 501	65.63 534	99.67 341	95.87 364	98.18 456	97.82 465

tpm2		93.09 476	92.58 475	94.62 496	97.56 474	86.53 522	97.66 272	95.79 492	86.15 528	94.07 511	98.23 383	75.95 512	99.53 414	90.91 498	96.86 502	97.81 467

CR-MVSNet		96.28 394	95.95 396	97.28 400	97.71 465	94.22 411	98.11 191	98.92 343	92.31 489	96.91 433	99.37 104	85.44 469	99.81 224	97.39 232	97.36 491	97.81 467

RPMNet		97.02 355	96.93 341	97.30 399	97.71 465	94.22 411	98.11 191	99.30 248	99.37 60	96.91 433	99.34 115	86.72 453	99.87 135	97.53 219	97.36 491	97.81 467

tpmrst		95.07 441	95.46 415	93.91 505	97.11 494	84.36 532	97.62 279	96.96 462	94.98 431	96.35 466	98.80 282	85.46 468	99.59 390	95.60 378	96.23 509	97.79 470

ALIKED-LG		97.10 347	96.63 368	98.50 270	97.96 448	98.68 99	97.75 259	99.68 63	95.86 394	98.36 329	98.33 370	91.58 410	99.04 483	90.87 500	99.31 352	97.77 471

PAPM		91.88 495	90.34 497	96.51 437	98.06 445	92.56 463	92.44 523	97.17 454	86.35 527	90.38 532	96.01 480	86.61 454	99.21 476	70.65 539	95.43 522	97.75 472

SP-LightGlue		97.22 339	97.01 337	97.88 341	97.33 489	97.19 263	96.38 396	99.08 312	97.28 304	96.53 457	97.50 439	92.36 396	98.70 500	97.84 186	98.76 421	97.74 473

FPMVS		93.44 470	92.23 479	97.08 411	99.25 229	97.86 191	95.61 443	97.16 455	92.90 482	93.76 517	98.65 319	75.94 513	95.66 534	79.30 534	97.49 482	97.73 474

MAR-MVS		96.47 384	95.70 403	98.79 199	97.92 451	99.12 62	98.28 167	98.60 391	92.16 491	95.54 487	96.17 478	94.77 335	99.52 418	89.62 507	98.23 453	97.72 475
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		98.03 260	97.86 274	98.56 254	98.69 367	98.07 162	97.51 298	99.50 146	98.10 221	97.50 399	95.51 492	98.41 85	99.88 115	96.27 343	99.24 366	97.71 476

thres600view7		94.45 450	93.83 457	96.29 446	99.06 283	91.53 479	97.99 221	94.24 512	98.34 187	97.44 406	95.01 503	79.84 498	99.67 341	84.33 524	98.23 453	97.66 477

thres400		94.14 458	93.44 462	96.24 449	98.93 312	91.44 482	97.60 285	94.29 509	97.94 233	97.10 420	94.31 513	79.67 500	99.62 373	83.05 527	98.08 464	97.66 477

IB-MVS	91.63 19	92.24 490	90.90 494	96.27 447	97.22 492	91.24 489	94.36 490	93.33 520	92.37 488	92.24 527	94.58 512	66.20 531	99.89 97	93.16 450	94.63 526	97.66 477
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		95.02 443	95.25 428	94.33 498	96.39 521	85.87 523	98.08 196	96.83 469	95.46 415	95.51 489	98.69 309	85.91 464	99.53 414	94.16 416	96.23 509	97.58 480

cascas		94.79 446	94.33 453	96.15 459	96.02 526	92.36 469	92.34 524	99.26 269	85.34 530	95.08 496	94.96 506	92.96 386	98.53 503	94.41 413	98.59 438	97.56 481

MatchFormer		97.07 351	96.92 343	97.49 389	98.44 405	95.92 336	96.79 362	99.14 303	93.08 477	99.32 143	99.10 190	93.89 363	99.03 484	92.78 462	99.78 164	97.52 482

PatchT		96.65 372	96.35 384	97.54 384	97.40 486	95.32 370	97.98 222	96.64 473	99.33 66	96.89 437	99.42 89	84.32 479	99.81 224	97.69 205	97.49 482	97.48 483

TR-MVS		95.55 426	95.12 434	96.86 427	97.54 476	93.94 431	96.49 388	96.53 476	94.36 452	97.03 428	96.61 468	94.26 354	99.16 479	86.91 518	96.31 508	97.47 484

SP-SuperGlue		97.31 329	97.23 322	97.57 382	96.96 501	97.24 255	96.26 407	98.76 374	97.68 255	96.88 439	97.85 415	94.32 351	98.01 510	97.76 197	98.57 440	97.45 485

dmvs_testset		92.94 480	92.21 480	95.13 490	98.59 387	90.99 494	97.65 274	92.09 525	96.95 331	94.00 513	93.55 517	92.34 398	96.97 526	72.20 537	92.52 531	97.43 486

MonoMVSNet		96.25 397	96.53 377	95.39 485	96.57 512	91.01 493	98.82 97	97.68 435	98.57 173	98.03 357	99.37 104	90.92 420	97.78 515	94.99 392	93.88 529	97.38 487

JIA-IIPM		95.52 427	95.03 435	97.00 415	96.85 505	94.03 423	96.93 356	95.82 490	99.20 84	94.63 504	99.71 22	83.09 488	99.60 385	94.42 410	94.64 525	97.36 488

SP-MNN		96.46 385	96.24 392	97.10 410	96.71 509	95.98 333	96.00 422	97.33 447	95.82 398	94.93 498	97.10 461	93.70 370	98.01 510	96.30 340	98.30 451	97.30 489

MASt3R-SfM		96.02 405	95.82 399	96.60 435	97.03 500	94.90 389	94.26 493	98.53 399	88.40 523	98.41 321	98.67 313	92.39 395	97.62 518	95.31 385	99.41 333	97.29 490

ALIKED-MNN		95.97 411	95.30 426	98.00 331	97.66 472	98.12 150	96.98 351	99.41 199	91.11 504	94.04 512	97.30 452	91.56 411	98.61 502	89.99 505	99.63 260	97.28 491

BH-w/o		95.13 440	94.89 440	95.86 469	98.20 430	91.31 485	95.65 442	97.37 442	93.64 467	96.52 460	95.70 489	93.04 385	99.02 486	88.10 513	95.82 519	97.24 492

tpm cat1		93.29 473	93.13 469	93.75 507	97.39 487	84.74 528	97.39 313	97.65 436	83.39 533	94.16 508	98.41 357	82.86 490	99.39 453	91.56 486	95.35 523	97.14 493

SP-NN		94.67 447	94.44 449	95.36 487	95.12 531	95.23 376	94.27 492	96.10 484	94.46 446	90.91 530	95.76 488	91.47 414	93.87 538	95.23 388	96.62 504	97.00 494

SP-DiffGlue		96.87 363	96.76 356	97.21 404	95.17 530	96.88 290	96.12 416	98.93 339	96.51 358	98.37 327	97.55 434	93.65 371	97.83 513	96.11 354	98.45 445	96.92 495

xiu_mvs_v1_base_debu		97.86 281	98.17 236	96.92 421	98.98 305	93.91 433	96.45 390	99.17 294	97.85 241	98.41 321	97.14 458	98.47 77	99.92 65	98.02 166	99.05 392	96.92 495

xiu_mvs_v1_base		97.86 281	98.17 236	96.92 421	98.98 305	93.91 433	96.45 390	99.17 294	97.85 241	98.41 321	97.14 458	98.47 77	99.92 65	98.02 166	99.05 392	96.92 495

xiu_mvs_v1_base_debi		97.86 281	98.17 236	96.92 421	98.98 305	93.91 433	96.45 390	99.17 294	97.85 241	98.41 321	97.14 458	98.47 77	99.92 65	98.02 166	99.05 392	96.92 495

PMVS	91.26 20	97.86 281	97.94 265	97.65 368	99.71 49	97.94 181	98.52 130	98.68 384	98.99 124	97.52 397	99.35 111	97.41 193	98.18 508	91.59 485	99.67 242	96.82 499
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
0.4-1-1-0.1		88.42 499	85.91 502	95.94 465	93.08 536	91.54 478	90.99 528	92.04 527	89.96 513	84.83 539	83.25 538	63.75 538	99.52 418	93.25 447	82.07 535	96.75 500

1314		95.74 419	95.60 408	96.17 455	97.53 478	92.75 461	98.07 200	98.31 412	91.22 501	94.25 507	96.68 466	95.53 306	99.03 484	91.64 484	97.18 495	96.74 501

MVS-HIRNet		94.32 452	95.62 406	90.42 521	98.46 402	75.36 545	96.29 403	89.13 536	95.25 424	95.38 490	99.75 16	92.88 387	99.19 477	94.07 422	99.39 336	96.72 502

OpenMVS_ROB	95.38 14	95.84 417	95.18 433	97.81 347	98.41 411	97.15 270	97.37 319	98.62 390	83.86 531	98.65 282	98.37 362	94.29 353	99.68 336	88.41 511	98.62 437	96.60 503

ALIKED-NN		94.29 455	93.41 464	96.94 419	96.18 523	97.66 215	94.90 469	98.68 384	88.85 519	90.43 531	96.81 464	89.82 430	96.59 531	86.67 519	98.33 447	96.58 504

0.3-1-1-0.015		87.27 501	84.50 505	95.57 479	91.70 539	90.77 498	89.41 534	92.04 527	88.98 517	82.46 541	81.35 539	60.36 542	99.50 425	92.96 453	81.23 537	96.45 505

0.4-1-1-0.2		87.49 500	84.89 503	95.31 488	91.33 542	90.08 505	88.47 535	92.07 526	88.70 520	84.06 540	81.08 540	63.62 539	99.49 429	92.93 455	81.71 536	96.37 506

thres100view900		94.19 456	93.67 460	95.75 473	99.06 283	91.35 484	98.03 207	94.24 512	98.33 189	97.40 408	94.98 505	79.84 498	99.62 373	83.05 527	98.08 464	96.29 507

tfpn200view9		94.03 460	93.44 462	95.78 472	98.93 312	91.44 482	97.60 285	94.29 509	97.94 233	97.10 420	94.31 513	79.67 500	99.62 373	83.05 527	98.08 464	96.29 507

MVS		93.19 475	92.09 481	96.50 438	96.91 503	94.03 423	98.07 200	98.06 425	68.01 539	94.56 505	96.48 471	95.96 291	99.30 467	83.84 525	96.89 501	96.17 509

gg-mvs-nofinetune		92.37 488	91.20 492	95.85 470	95.80 529	92.38 468	99.31 30	81.84 544	99.75 10	91.83 528	99.74 18	68.29 523	99.02 486	87.15 515	97.12 496	96.16 510

xiu_mvs_v2_base		97.16 345	97.49 305	96.17 455	98.54 394	92.46 465	95.45 450	98.84 361	97.25 308	97.48 401	96.49 470	98.31 97	99.90 81	96.34 337	98.68 431	96.15 511

PS-MVSNAJ		97.08 350	97.39 310	96.16 457	98.56 392	92.46 465	95.24 459	98.85 360	97.25 308	97.49 400	95.99 481	98.07 128	99.90 81	96.37 334	98.67 432	96.12 512

E-PMN		94.17 457	94.37 451	93.58 509	96.86 504	85.71 526	90.11 531	97.07 457	98.17 211	97.82 376	97.19 455	84.62 476	98.94 490	89.77 506	97.68 477	96.09 513

EMVS		93.83 463	94.02 454	93.23 515	96.83 506	84.96 527	89.77 532	96.32 479	97.92 235	97.43 407	96.36 476	86.17 458	98.93 491	87.68 514	97.73 476	95.81 514

MVE	83.40 22	92.50 485	91.92 487	94.25 499	98.83 335	91.64 477	92.71 520	83.52 543	95.92 391	86.46 538	95.46 496	95.20 317	95.40 535	80.51 532	98.64 433	95.73 515
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
thres200		93.72 466	93.14 468	95.46 484	98.66 377	91.29 486	96.61 379	94.63 504	97.39 292	96.83 441	93.71 516	79.88 497	99.56 402	82.40 530	98.13 461	95.54 516

GLUNet-SfM		86.26 502	84.68 504	91.01 520	80.58 546	83.56 534	78.04 537	93.59 517	76.70 537	95.29 492	94.72 510	77.51 511	94.26 537	66.39 540	99.33 347	95.20 517

API-MVS		97.04 354	96.91 346	97.42 395	97.88 453	98.23 141	98.18 179	98.50 402	97.57 267	97.39 410	96.75 465	96.77 238	99.15 480	90.16 504	99.02 399	94.88 518

GG-mvs-BLEND				94.76 494	94.54 533	92.13 473	99.31 30	80.47 545		88.73 536	91.01 535	67.59 527	98.16 509	82.30 531	94.53 527	93.98 519

SIFT-PointCN		96.45 386	96.47 379	96.39 442	98.13 440	97.54 225	93.31 516	97.23 452	94.67 441	98.68 278	98.32 371	94.64 338	97.81 514	93.50 441	99.77 172	93.83 520

XFeat-MNN		93.41 471	92.98 471	94.68 495	92.63 537	92.92 456	89.72 533	95.81 491	92.10 492	97.23 417	96.29 477	84.95 472	97.31 523	89.60 508	98.54 442	93.81 521

SIFT-ConvMatch		96.57 375	96.62 369	96.43 440	98.20 430	98.27 134	93.88 504	96.88 467	95.29 422	98.88 241	98.25 379	95.18 319	97.43 520	93.22 449	99.83 126	93.59 522

SIFT-NCM-Cal		96.56 376	96.68 362	96.20 453	98.27 423	98.44 118	94.40 488	96.67 471	95.29 422	97.63 386	98.17 387	96.40 261	96.59 531	93.61 434	99.66 250	93.57 523

SIFT-MNN		95.92 413	95.97 395	95.74 475	98.18 432	98.00 169	94.17 495	96.99 459	95.74 403	97.16 418	97.90 411	90.71 422	95.79 533	93.71 432	99.21 373	93.44 524

SIFT-NN-PointCN		96.06 402	96.11 393	95.91 467	97.88 453	97.73 210	93.49 512	97.51 440	93.22 473	96.57 454	98.26 378	96.23 272	96.60 530	92.54 469	99.27 360	93.40 525

DeepMVS_CX				93.44 512	98.24 426	94.21 413		94.34 508	64.28 540	91.34 529	94.87 509	89.45 436	92.77 539	77.54 535	93.14 530	93.35 526

SIFT-NN-CMatch		95.63 424	95.48 413	96.08 461	98.24 426	98.00 169	92.71 520	94.29 509	94.20 455	95.85 477	97.26 453	95.72 300	97.01 524	91.99 476	99.02 399	93.23 527

SIFT-NN		92.96 479	92.79 473	93.46 510	96.92 502	96.45 315	91.89 526	94.39 507	92.91 481	92.54 524	95.46 496	88.26 446	90.71 541	85.22 522	97.52 480	93.22 528

SIFT-PCN-Cal		96.34 389	96.46 381	96.01 464	98.17 434	96.89 288	93.48 513	97.35 446	94.84 436	99.35 130	98.30 373	94.70 337	97.92 512	92.03 475	99.88 95	93.21 529

SIFT-UM-Cal		96.49 381	96.62 369	96.12 460	98.13 440	97.89 188	93.35 515	98.44 404	95.48 414	98.63 285	98.34 366	95.45 311	97.45 519	92.22 474	99.50 313	93.02 530

SIFT-CM-Cal		96.28 394	96.31 387	96.16 457	98.39 412	98.11 151	93.46 514	96.47 477	94.81 438	98.49 311	98.43 355	94.48 342	97.34 522	92.60 468	99.70 226	93.02 530

SIFT-UMatch		96.33 390	96.47 379	95.89 468	98.29 419	97.95 179	93.84 505	97.24 451	95.78 401	98.72 271	98.04 400	93.45 374	96.81 527	93.14 451	99.73 199	92.91 532

SIFT-NN-NCMNet		95.39 433	95.22 430	95.92 466	98.29 419	98.34 129	93.58 511	94.60 505	94.07 461	94.84 499	97.53 435	94.37 349	96.62 529	91.01 495	98.64 433	92.80 533

SIFT-NCMNet		96.30 392	96.40 383	96.03 463	97.80 460	97.68 214	92.34 524	96.94 464	95.55 409	98.84 250	98.63 325	94.17 356	97.63 517	93.57 438	99.71 217	92.77 534

SIFT-NN-UMatch		95.38 434	95.26 427	95.75 473	98.25 424	97.78 204	93.24 518	95.66 497	94.01 463	95.10 495	97.47 443	93.12 380	96.78 528	92.42 471	98.04 469	92.69 535

XFeat-NN		89.63 498	89.13 501	91.14 519	90.93 543	90.02 506	84.90 536	94.05 515	88.10 524	92.89 522	93.33 521	78.74 505	90.89 540	83.46 526	95.72 520	92.52 536

tmp_tt		78.77 505	78.73 508	78.90 523	58.45 548	74.76 547	94.20 494	78.26 546	39.16 541	86.71 537	92.82 525	80.50 496	75.19 543	86.16 521	92.29 532	86.74 537

dongtai		76.24 506	75.95 509	77.12 524	92.39 538	67.91 548	90.16 530	59.44 549	82.04 534	89.42 534	94.67 511	49.68 546	81.74 542	48.06 541	77.66 539	81.72 538

kuosan		69.30 507	68.95 510	70.34 525	87.68 545	65.00 549	91.11 527	59.90 548	69.02 538	74.46 543	88.89 537	48.58 547	68.03 544	28.61 542	72.33 542	77.99 539

wuyk23d		96.06 402	97.62 298	91.38 518	98.65 381	98.57 107	98.85 93	96.95 463	96.86 342	99.90 14	99.16 169	99.18 19	98.40 504	89.23 510	99.77 172	77.18 540

test123		17.04 510	20.11 513	7.82 526	10.25 550	4.91 551	94.80 471	4.47 551	4.93 544	10.00 546	24.28 543	9.69 548	3.64 545	10.14 543	12.43 544	14.92 541

testmvs		17.12 509	20.53 512	6.87 527	12.05 549	4.20 552	93.62 510	6.73 550	4.62 545	10.41 545	24.33 542	8.28 549	3.56 546	9.69 544	15.07 543	12.86 542

mmdepth		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

monomultidepth		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

test_blank		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

uanet_test		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

DCPMVS		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

cdsmvs_eth3d_5k		24.66 508	32.88 511	0.00 528	0.00 551	0.00 553	0.00 539	99.10 308	0.00 546	0.00 547	97.58 432	99.21 18	0.00 547	0.00 545	0.00 545	0.00 543

pcd_1.5k_mvsjas		8.17 511	10.90 514	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	98.07 128	0.00 547	0.00 545	0.00 545	0.00 543

sosnet-low-res		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

sosnet		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

uncertanet		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

Regformer		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

ab-mvs-re		8.12 512	10.83 515	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	97.48 441	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

uanet		0.00 513	0.00 516	0.00 528	0.00 551	0.00 553	0.00 539	0.00 552	0.00 546	0.00 547	0.00 546	0.00 550	0.00 547	0.00 545	0.00 545	0.00 543

WAC-MVS						90.90 495								91.37 489

FOURS1					99.73 38	99.67 2	99.43 15	99.54 129	99.43 54	99.26 156

test_one_0601					99.39 183	99.20 38		99.31 240	98.49 179	98.66 281	99.02 211	97.64 168

eth-test2					0.00 551

eth-test					0.00 551

ZD-MVS					99.01 300	98.84 85		99.07 313	94.10 459	98.05 355	98.12 392	96.36 266	99.86 144	92.70 465	99.19 378

test_241102_ONE					99.49 148	99.17 43		99.31 240	97.98 228	99.66 60	98.90 254	98.36 90	99.48 433

9.14			97.78 279		99.07 278		97.53 295	99.32 235	95.53 412	98.54 306	98.70 307	97.58 175	99.76 270	94.32 415	99.46 319

save fliter					99.11 269	97.97 175	96.53 385	99.02 326	98.24 199

test0726					99.50 140	99.21 32	98.17 182	99.35 221	97.97 229	99.26 156	99.06 199	97.61 172

test_part2					99.36 192	99.10 65				99.05 199

sam_mvs												84.29 481

MTGPA								99.20 282

test_post1							97.59 287				20.48 545	83.07 489	99.66 354	94.16 416

test_post											21.25 544	83.86 484	99.70 315

patchmatchnet-post											98.77 288	84.37 478	99.85 158

MTMP							97.93 228	91.91 530

gm-plane-assit					94.83 532	81.97 541			88.07 525		94.99 504		99.60 385	91.76 481

TEST9					98.71 358	98.08 159	95.96 426	99.03 323	91.40 499	95.85 477	97.53 435	96.52 255	99.76 270

test_8					98.67 372	98.01 168	95.91 432	99.02 326	91.64 494	95.79 480	97.50 439	96.47 257	99.76 270

agg_prior					98.68 371	97.99 171		99.01 329		95.59 481			99.77 264

test_prior4						97.97 175	95.86 433

test_prior2							95.74 440		96.48 362	96.11 470	97.63 430	95.92 294		94.16 416	99.20 375

旧先验2							95.76 439		88.56 522	97.52 397			99.66 354	94.48 406

新几何2							95.93 429

原ACMM2							95.53 446

testdata2													99.79 246	92.80 461

segment_acmp												97.02 220

testdata1							95.44 451		96.32 369

plane_prior7					99.19 245	97.87 190

plane_prior6					98.99 304	97.70 213						94.90 326

plane_prior4											97.98 405

plane_prior3						97.78 204			97.41 289	97.79 377

plane_prior2							97.77 253		98.20 208

plane_prior1					99.05 286

plane_prior						97.65 217	97.07 346		96.72 349						99.36 340

n2								0.00 552

nn								0.00 552

door-mid								99.57 109

test11								98.87 352

door								99.41 199

HQP5-MVS						96.79 294

HQP-NCC					98.67 372		96.29 403		96.05 382	95.55 484

ACMP_Plane					98.67 372		96.29 403		96.05 382	95.55 484

BP-MVS														92.82 459

HQP3-MVS								99.04 321							99.26 364

HQP2-MVS												93.84 364

NP-MVS					98.84 333	97.39 239					96.84 462

MDTV_nov1_ep13			95.22 430		97.06 497	83.20 537	97.74 261	96.16 481	94.37 451	96.99 429	98.83 275	83.95 483	99.53 414	93.90 425	97.95 472

ACMMP++_ref															99.77 172

ACMMP++															99.68 236

Test By Simon												96.52 255

High-resolution multi-view benchmark