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	98.44 281	99.65 71	95.35 373	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	98.13 151	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	98.80 197	99.75 34	96.59 307	97.97 227	99.86 17	98.22 203	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	98.65 234	99.69 61	96.08 335	97.49 302	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	98.92 173	99.58 94	96.89 292	99.48 13	99.92 8	99.92 2	98.26 341	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	98.64 236	99.71 49	96.10 330	97.87 240	99.85 19	98.56 177	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	98.25 305	99.76 30	95.07 389	99.05 68	99.94 3	97.78 250	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	98.11 153	97.77 254	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		98.67 161	98.87 111	98.05 333	99.72 45	95.59 354	98.51 135	99.81 32	96.30 377	99.78 39	99.82 5	96.14 278	98.63 507	99.82 12	99.93 57	99.95 9

test_fmvs2		98.70 147	98.97 98	97.89 346	99.54 123	94.05 426	98.55 126	99.92 8	96.78 351	99.72 47	99.78 13	96.60 254	99.67 344	99.91 2	99.90 88	99.94 10

PS-MVSNAJss		99.46 17	99.49 16	99.35 80	99.90 4	98.15 148	99.20 49	99.65 77	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	99.07 138	99.78 24	98.38 123	98.92 83	99.94 3	97.80 247	99.91 12	99.67 30	97.15 212	98.91 499	99.76 23	99.56 291	99.92 12

fmvsm_s_conf0.5_n_2		99.14 62	99.31 41	98.63 240	99.49 150	96.08 335	97.38 316	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		95.86 421	95.60 414	96.63 440	95.87 534	91.70 482	97.93 229	98.94 342	98.03 227	99.56 74	99.66 32	71.83 524	98.26 512	99.35 58	99.24 371	99.91 13

fmvsm_s_conf0.5_n_a		99.10 72	99.20 58	98.78 204	99.55 117	96.59 307	97.79 250	99.82 31	98.21 205	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	98.53 267	99.51 134	95.82 348	97.62 280	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	98.61 246	99.55 117	96.09 333	97.74 262	99.81 32	98.55 178	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	98.10 156	97.68 269	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	99.56 121	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	98.80 197	99.48 158	96.56 312	97.97 227	99.69 57	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	98.74 217	99.51 134	96.44 320	97.65 275	99.65 77	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	98.20 312	99.30 212	94.83 399	97.23 334	99.36 221	98.64 161	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	98.21 145	97.82 245	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		97.91 276	98.02 257	97.58 383	98.69 373	94.10 425	98.13 186	98.90 352	97.95 233	97.32 419	99.58 47	95.95 295	98.75 504	96.41 337	99.22 375	99.87 22

jajsoiax		99.58 9	99.61 11	99.48 57	99.87 12	98.61 103	99.28 40	99.66 71	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		97.66 306	98.50 175	95.13 496	99.63 83	85.84 530	98.35 161	98.21 423	98.23 201	99.54 79	99.46 80	95.02 328	99.68 339	98.24 147	99.87 100	99.87 22

fmvsm_s_conf0.5_n_3		99.22 46	99.37 31	98.78 204	99.46 164	96.58 310	97.65 275	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	99.49 150	99.29 23	99.80 4	99.72 46	99.82 8	99.04 202	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	98.98 160	99.59 92	97.18 270	97.44 311	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		98.22 240	97.99 260	98.91 175	98.66 383	96.97 284	97.89 236	94.44 512	99.54 40	98.95 223	99.14 180	93.50 377	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	98.94 167	99.65 71	97.05 279	97.80 249	99.76 39	98.70 159	99.78 39	99.11 188	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	99.02 151	99.64 77	97.28 256	97.82 245	99.76 39	98.73 151	99.82 34	99.09 197	98.81 39	99.95 25	99.86 4	99.96 28	99.83 33

mvsany_test3		98.87 112	98.92 102	98.74 217	99.38 187	96.94 288	98.58 123	99.10 314	96.49 366	99.96 4	99.81 8	98.18 118	99.45 449	98.97 89	99.79 159	99.83 33

PDCNetPlus		95.22 444	94.73 451	96.70 439	97.85 461	91.14 498	93.94 509	99.97 1	93.06 484	98.95 223	98.89 263	74.32 521	99.14 487	95.63 381	99.93 57	99.82 36

fmvsm_s_conf0.5_n_10		99.15 57	99.27 47	98.78 204	99.47 161	96.56 312	97.75 260	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	98.62 242	99.72 45	96.08 335	98.74 99	98.64 395	99.74 12	99.67 59	99.24 144	94.57 344	99.95 25	99.11 77	99.24 371	99.82 36

anonymousdsp		99.51 14	99.47 21	99.62 9	99.88 9	99.08 69	99.34 23	99.69 57	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	98.09 157	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 94	98.85 145	99.53 83	99.16 170	97.87 149	99.83 195	96.67 309	99.64 257	99.81 41

TestfortrainingZip a		99.09 73	98.92 102	99.61 13	99.58 94	99.17 43	98.68 109	99.27 269	98.85 145	99.61 70	99.16 170	97.14 213	99.86 144	98.39 138	99.57 287	99.81 41

fmvsm_s_conf0.5_n_4		99.01 90	99.22 54	98.38 289	99.31 208	95.48 364	97.56 291	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	99.53 136	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		97.98 272	98.31 215	97.02 420	98.88 332	91.45 487	98.03 207	99.47 170	98.65 160	99.55 77	99.47 78	91.49 419	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	98.37 125	99.30 35	99.57 111	99.61 34	99.40 117	99.50 68	97.12 214	99.85 158	99.02 86	99.94 51	99.80 45

test_cas_vis1_n_1920		98.33 222	98.68 141	97.27 407	99.69 61	92.29 476	98.03 207	99.85 19	97.62 262	99.96 4	99.62 40	93.98 366	99.74 289	99.52 49	99.86 107	99.79 47

test_vis1_n_1920		98.40 207	98.92 102	96.81 434	99.74 37	90.76 505	98.15 184	99.91 10	98.33 190	99.89 18	99.55 56	95.07 327	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	99.34 233	99.42 55	99.33 138	99.26 137	97.01 223	99.94 41	98.74 107	99.93 57	99.79 47

fmvsm_s_conf0.5_n_5		99.07 82	99.10 80	98.99 156	99.47 161	97.22 263	97.40 313	99.83 26	97.61 265	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	99.58 103	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		96.25 403	97.21 330	93.38 520	99.10 274	80.56 550	97.20 339	98.19 426	96.94 335	99.00 208	99.02 213	89.50 441	99.80 233	96.36 341	99.59 278	99.78 50

reproduce_monomvs		95.00 450	95.25 434	94.22 506	97.51 489	83.34 541	97.86 241	98.44 410	98.51 179	99.29 149	99.30 125	67.68 532	99.56 406	98.89 96	99.81 140	99.77 53

Anonymous20231211		99.27 37	99.27 47	99.26 101	99.29 214	98.18 146	99.49 12	99.51 144	99.70 15	99.80 37	99.68 25	96.84 232	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	99.54 132	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	99.55 126	99.46 49	99.50 93	99.34 115	97.30 201	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		98.52 193	98.55 165	98.43 282	99.65 71	95.59 354	98.52 130	98.77 378	99.65 25	99.52 87	99.00 229	94.34 354	99.93 53	98.65 114	98.83 421	99.76 58

patch_mono-2		98.51 194	98.63 152	98.17 315	99.38 187	94.78 401	97.36 321	99.69 57	98.16 216	98.49 316	99.29 128	97.06 217	99.97 6	98.29 145	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	99.48 159	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	98.28 135	99.13 59	99.52 142	99.48 44	99.24 167	99.41 94	96.79 239	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 92	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	99.21 240	99.15 52	98.87 89	99.48 159	97.57 269	99.35 130	99.24 144	97.83 151	99.89 97	97.88 183	99.70 227	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	99.51 144	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	98.43 413	98.37 125		98.86 363					99.89 97	97.14 258	99.60 274	99.71 65

No_MVS				99.32 91	98.43 413	98.37 125		98.86 363					99.89 97	97.14 258	99.60 274	99.71 65

PMMVS2		98.07 261	98.08 251	98.04 334	99.41 181	94.59 410	94.59 488	99.40 209	97.50 279	98.82 258	98.83 278	96.83 234	99.84 177	97.50 226	99.81 140	99.71 65

Baseline_NR-MVSNet		98.98 98	98.86 115	99.36 74	99.82 19	98.55 108	97.47 307	99.57 111	99.37 60	99.21 173	99.61 43	96.76 242	99.83 195	98.06 163	99.83 126	99.71 65

XXY-MVS		99.14 62	99.15 67	99.10 130	99.76 30	97.74 211	98.85 93	99.62 89	98.48 181	99.37 125	99.49 74	98.75 47	99.86 144	98.20 152	99.80 152	99.71 65

test_0728_THIRD									98.17 213	99.08 190	99.02 213	97.89 147	99.88 115	97.07 265	99.71 217	99.70 70

MSP-MVS		98.40 207	98.00 259	99.61 13	99.57 103	99.25 28	98.57 124	99.35 227	97.55 273	99.31 147	97.71 430	94.61 343	99.88 115	96.14 356	99.19 383	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		98.53 189	98.79 124	97.74 362	99.46 164	93.62 452	96.45 394	99.34 233	99.33 66	98.93 232	98.70 311	97.90 143	99.90 81	99.12 76	99.92 71	99.69 72

NormalMVS		98.26 235	97.97 264	99.15 123	99.64 77	97.83 196	98.28 167	99.43 193	99.24 77	98.80 262	98.85 271	89.76 437	99.94 41	98.04 166	99.67 245	99.68 73

KinetiMVS		99.03 88	99.02 90	99.03 148	99.70 57	97.48 234	98.43 148	99.29 262	99.70 15	99.60 71	99.07 199	96.13 280	99.94 41	99.42 55	99.87 100	99.68 73

dcpmvs_2		98.78 133	99.11 74	97.78 355	99.56 111	93.67 449	99.06 66	99.86 17	99.50 43	99.66 60	99.26 137	97.21 209	99.99 2	98.00 171	99.91 80	99.68 73

test_0728_SECOND				99.60 16	99.50 141	99.23 30	98.02 210	99.32 241					99.88 115	96.99 272	99.63 263	99.68 73

OurMVSNet-221017-0		99.37 28	99.31 41	99.53 38	99.91 3	98.98 71	99.63 7	99.58 103	99.44 52	99.78 39	99.76 15	96.39 264	99.92 65	99.44 54	99.92 71	99.68 73

fmvsm_s_conf0.5_n_6		99.08 79	99.21 57	98.69 227	99.36 194	96.51 314	97.62 280	99.68 64	98.43 183	99.85 27	99.10 191	99.12 23	99.88 115	99.77 22	99.92 71	99.67 78

CHOSEN 1792x2688		97.49 318	97.14 335	98.54 265	99.68 64	96.09 333	96.50 391	99.62 89	91.58 502	98.84 253	98.97 238	92.36 401	99.88 115	96.76 296	99.95 39	99.67 78

reproduce_model		99.15 57	98.97 98	99.67 4	99.33 205	99.44 9	98.15 184	99.47 170	99.12 99	99.52 87	99.32 123	98.31 97	99.90 81	97.78 193	99.73 199	99.66 80

IU-MVS					99.49 150	99.15 52		98.87 358	92.97 485	99.41 114				96.76 296	99.62 267	99.66 80

test_241102_TWO								99.30 254	98.03 227	99.26 157	99.02 213	97.51 185	99.88 115	96.91 279	99.60 274	99.66 80

DPE-MVS		98.59 175	98.26 225	99.57 21	99.27 220	99.15 52	97.01 349	99.39 211	97.67 258	99.44 107	98.99 231	97.53 182	99.89 97	95.40 390	99.68 239	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	99.57 111	99.39 58	99.75 44	99.62 40	99.17 20	99.83 195	99.06 82	99.62 267	99.66 80

EI-MVSNet-UG-set		98.69 151	98.71 135	98.62 242	99.10 274	96.37 322	97.23 334	98.87 358	99.20 84	99.19 175	98.99 231	97.30 201	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	97.92 185	98.50 137	99.43 193	99.67 20	99.70 51	99.13 182	96.66 249	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	97.92 185	98.50 137	99.43 193	99.67 20	99.70 51	99.13 182	96.66 249	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	98.63 240	99.09 277	96.40 321	97.23 334	98.86 363	99.20 84	99.18 180	98.97 238	97.29 203	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	98.38 123	99.07 65	99.55 126	98.30 194	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	99.21 240	98.45 117	98.46 145	99.33 239	99.63 28	99.48 96	99.15 176	97.23 207	99.75 282	97.17 253	99.66 253	99.63 91

reproduce-ours		99.09 73	98.90 105	99.67 4	99.27 220	99.49 5	98.00 215	99.42 200	99.05 117	99.48 96	99.27 131	98.29 99	99.89 97	97.61 214	99.71 217	99.62 92

our_new_method		99.09 73	98.90 105	99.67 4	99.27 220	99.49 5	98.00 215	99.42 200	99.05 117	99.48 96	99.27 131	98.29 99	99.89 97	97.61 214	99.71 217	99.62 92

test_fmvs1_n		98.09 259	98.28 219	97.52 392	99.68 64	93.47 454	98.63 116	99.93 6	95.41 426	99.68 57	99.64 37	91.88 413	99.48 439	99.82 12	99.87 100	99.62 92

test1111		96.49 387	96.82 358	95.52 487	99.42 178	87.08 527	99.22 46	87.14 545	99.11 100	99.46 101	99.58 47	88.69 445	99.86 144	98.80 100	99.95 39	99.62 92

VPA-MVSNet		99.30 33	99.30 44	99.28 96	99.49 150	98.36 128	99.00 73	99.45 179	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	98.46 185	99.47 61	99.57 103	98.97 73	98.23 173	99.48 159	96.60 360	99.10 188	99.06 200	98.71 51	99.83 195	95.58 385	99.78 164	99.62 92

LGP-MVS_train				99.47 61	99.57 103	98.97 73		99.48 159	96.60 360	99.10 188	99.06 200	98.71 51	99.83 195	95.58 385	99.78 164	99.62 92

Test_1112_low_res		96.99 365	96.55 381	98.31 298	99.35 199	95.47 367	95.84 442	99.53 136	91.51 504	96.80 449	98.48 355	91.36 421	99.83 195	96.58 318	99.53 303	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	98.55 260	99.44 171	96.21 329	98.90 84	99.55 126	98.73 151	99.48 96	99.60 45	96.63 253	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 82	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		98.31 227	98.50 175	97.73 365	99.76 30	94.17 421	98.68 109	99.91 10	96.31 375	99.79 38	99.57 49	92.85 394	99.42 455	99.79 19	99.84 114	99.60 102

v8		99.01 90	99.16 62	98.57 253	99.47 161	96.31 325	98.90 84	99.47 170	99.03 121	99.52 87	99.57 49	96.93 228	99.81 224	99.60 37	99.98 12	99.60 102

EI-MVSNet		98.40 207	98.51 172	98.04 334	99.10 274	94.73 404	97.20 339	98.87 358	98.97 127	99.06 192	99.02 213	96.00 287	99.80 233	98.58 119	99.82 133	99.60 102

SixPastTwentyTwo		98.75 138	98.62 154	99.16 118	99.83 18	97.96 180	99.28 40	98.20 424	99.37 60	99.70 51	99.65 36	92.65 398	99.93 53	99.04 84	99.84 114	99.60 102

IterMVS-LS		98.55 184	98.70 138	98.09 325	99.48 158	94.73 404	97.22 338	99.39 211	98.97 127	99.38 121	99.31 124	96.00 287	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		97.19 348	96.60 379	98.96 164	99.62 87	97.28 256	95.17 467	99.50 149	94.21 460	99.01 207	98.32 376	86.61 460	99.99 2	97.10 263	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	99.51 144	99.19 89	99.37 125	99.25 142	98.36 90	99.88 115	98.23 149	99.67 245	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	98.48 181	99.57 21	99.58 94	99.29 23	97.82 245	99.25 277	96.94 335	98.78 264	99.12 186	98.02 132	99.84 177	97.13 261	99.67 245	99.59 109

VPNet		98.87 112	98.83 120	99.01 153	99.70 57	97.62 224	98.43 148	99.35 227	99.47 47	99.28 151	99.05 207	96.72 246	99.82 207	98.09 160	99.36 345	99.59 109

WR-MVS		98.40 207	98.19 236	99.03 148	99.00 306	97.65 220	96.85 362	98.94 342	98.57 174	98.89 239	98.50 352	95.60 308	99.85 158	97.54 222	99.85 109	99.59 109

HPM-MVS		98.79 131	98.53 169	99.59 20	99.65 71	99.29 23	99.16 55	99.43 193	96.74 353	98.61 296	98.38 366	98.62 64	99.87 135	96.47 332	99.67 245	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	98.94 167	99.50 141	97.47 235	98.04 205	99.59 100	98.15 221	99.40 117	99.36 110	98.58 72	99.76 270	98.78 102	99.68 239	99.59 109

Vis-MVSNet		99.34 29	99.36 32	99.27 99	99.73 38	98.26 137	99.17 54	99.78 36	99.11 100	99.27 153	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 94	96.46 369	99.53 83	98.77 291		99.83 195	96.67 309	99.64 257	99.58 117

ME-MVS		98.61 171	98.33 213	99.44 65	99.24 232	98.93 79	97.45 309	99.06 320	98.14 222	99.06 192	98.77 291	96.97 226	99.82 207	96.67 309	99.64 257	99.58 117

MP-MVS-pluss		98.57 178	98.23 230	99.60 16	99.69 61	99.35 16	97.16 344	99.38 213	94.87 441	98.97 217	98.99 231	98.01 133	99.88 115	97.29 244	99.70 227	99.58 117
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
region2R		98.69 151	98.40 193	99.54 31	99.53 127	99.17 43	98.52 130	99.31 246	97.46 287	98.44 323	98.51 348	97.83 151	99.88 115	96.46 333	99.58 283	99.58 117

ACMMPR		98.70 147	98.42 191	99.54 31	99.52 131	99.14 57	98.52 130	99.31 246	97.47 282	98.56 307	98.54 343	97.75 159	99.88 115	96.57 320	99.59 278	99.58 117

PGM-MVS		98.66 162	98.37 202	99.55 28	99.53 127	99.18 42	98.23 173	99.49 157	97.01 332	98.69 279	98.88 265	98.00 134	99.89 97	95.87 369	99.59 278	99.58 117

SteuartSystems-ACMMP		98.79 131	98.54 167	99.54 31	99.73 38	99.16 48	98.23 173	99.31 246	97.92 237	98.90 236	98.90 257	98.00 134	99.88 115	96.15 355	99.72 208	99.58 117
Skip Steuart: Steuart Systems R&D Blog.
SDMVSNet		99.23 45	99.32 39	98.96 164	99.68 64	97.35 244	98.84 95	99.48 159	99.69 17	99.63 66	99.68 25	99.03 24	99.96 13	97.97 176	99.92 71	99.57 124

sd_testset		99.28 36	99.31 41	99.19 112	99.68 64	98.06 167	99.41 17	99.30 254	99.69 17	99.63 66	99.68 25	99.25 16	99.96 13	97.25 247	99.92 71	99.57 124

TranMVSNet+NR-MVSNet		99.17 52	99.07 85	99.46 63	99.37 193	98.87 84	98.39 157	99.42 200	99.42 55	99.36 128	99.06 200	98.38 89	99.95 25	98.34 142	99.90 88	99.57 124

mPP-MVS		98.64 165	98.34 208	99.54 31	99.54 123	99.17 43	98.63 116	99.24 282	97.47 282	98.09 355	98.68 315	97.62 170	99.89 97	96.22 350	99.62 267	99.57 124

PVSNet_Blended_VisFu		98.17 251	98.15 243	98.22 311	99.73 38	95.15 385	97.36 321	99.68 64	94.45 455	98.99 212	99.27 131	96.87 231	99.94 41	97.13 261	99.91 80	99.57 124

1112_ss		97.29 339	96.86 354	98.58 250	99.34 204	96.32 324	96.75 369	99.58 103	93.14 481	96.89 443	97.48 447	92.11 409	99.86 144	96.91 279	99.54 299	99.57 124

MTAPA		98.88 111	98.64 150	99.61 13	99.67 68	99.36 15	98.43 148	99.20 288	98.83 149	98.89 239	98.90 257	96.98 225	99.92 65	97.16 254	99.70 227	99.56 130

XVS		98.72 141	98.45 186	99.53 38	99.46 164	99.21 32	98.65 114	99.34 233	98.62 166	97.54 400	98.63 330	97.50 186	99.83 195	96.79 292	99.53 303	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 82	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		94.32 458	92.59 480	99.53 38	99.46 164	99.21 32	98.65 114	99.34 233	98.62 166	97.54 400	45.85 547	97.50 186	99.83 195	96.79 292	99.53 303	99.56 130

HPM-MVS_fast		99.01 90	98.82 121	99.57 21	99.71 49	99.35 16	99.00 73	99.50 149	97.33 300	98.94 231	98.86 268	98.75 47	99.82 207	97.53 223	99.71 217	99.56 130

K. test v3		98.00 268	97.66 297	99.03 148	99.79 23	97.56 227	99.19 53	92.47 528	99.62 32	99.52 87	99.66 32	89.61 439	99.96 13	99.25 67	99.81 140	99.56 130

CP-MVS		98.70 147	98.42 191	99.52 44	99.36 194	99.12 62	98.72 104	99.36 221	97.54 276	98.30 335	98.40 363	97.86 150	99.89 97	96.53 329	99.72 208	99.56 130

viewmacassd2359aftdt		98.86 116	98.87 111	98.83 190	99.53 127	97.32 249	97.70 267	99.64 79	98.22 203	99.25 165	99.27 131	98.40 86	99.61 385	97.98 175	99.87 100	99.55 137

FE-MVSNET		98.59 175	98.50 175	98.87 179	99.58 94	97.30 250	98.08 196	99.74 44	96.94 335	98.97 217	99.10 191	96.94 227	99.74 289	97.33 240	99.86 107	99.55 137

ZNCC-MVS		98.68 157	98.40 193	99.54 31	99.57 103	99.21 32	98.46 145	99.29 262	97.28 307	98.11 353	98.39 364	98.00 134	99.87 135	96.86 289	99.64 257	99.55 137

v1192		98.60 173	98.66 146	98.41 285	99.27 220	95.88 344	97.52 297	99.36 221	97.41 292	99.33 138	99.20 156	96.37 268	99.82 207	99.57 39	99.92 71	99.55 137

v1240		98.55 184	98.62 154	98.32 296	99.22 238	95.58 356	97.51 299	99.45 179	97.16 323	99.45 106	99.24 144	96.12 282	99.85 158	99.60 37	99.88 95	99.55 137

UGNet		98.53 189	98.45 186	98.79 201	97.94 456	96.96 286	99.08 62	98.54 404	99.10 107	96.82 448	99.47 78	96.55 256	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	99.47 170	99.16 94	99.49 94	99.12 186	96.34 270	99.93 53	98.05 165	99.36 345	99.54 143

E5new		99.05 83	99.11 74	98.85 182	99.60 88	97.30 250	98.42 151	99.63 82	98.73 151	99.26 157	99.39 100	98.71 51	99.70 317	98.43 133	99.84 114	99.54 143

E6new		99.05 83	99.11 74	98.85 182	99.60 88	97.30 250	98.42 151	99.63 82	98.73 151	99.26 157	99.39 100	98.71 51	99.70 317	98.43 133	99.84 114	99.54 143

E6		99.05 83	99.11 74	98.85 182	99.60 88	97.30 250	98.42 151	99.63 82	98.73 151	99.26 157	99.39 100	98.71 51	99.70 317	98.43 133	99.84 114	99.54 143

E5		99.05 83	99.11 74	98.85 182	99.60 88	97.30 250	98.42 151	99.63 82	98.73 151	99.26 157	99.39 100	98.71 51	99.70 317	98.43 133	99.84 114	99.54 143

AstraMVS		98.16 253	98.07 253	98.41 285	99.51 134	95.86 345	98.00 215	95.14 506	98.97 127	99.43 108	99.24 144	93.25 381	99.84 177	99.21 70	99.87 100	99.54 143

WBMVS		95.18 445	94.78 447	96.37 449	97.68 476	89.74 514	95.80 443	98.73 387	97.54 276	98.30 335	98.44 359	70.06 526	99.82 207	96.62 315	99.87 100	99.54 143

test2506		92.39 492	91.89 494	93.89 512	99.38 187	82.28 546	99.32 26	66.03 553	99.08 114	98.77 267	99.57 49	66.26 536	99.84 177	98.71 110	99.95 39	99.54 143

ECVR-MVS		96.42 393	96.61 377	95.85 476	99.38 187	88.18 522	99.22 46	86.00 547	99.08 114	99.36 128	99.57 49	88.47 450	99.82 207	98.52 127	99.95 39	99.54 143

v144192		98.54 187	98.57 163	98.45 279	99.21 240	95.98 338	97.63 279	99.36 221	97.15 325	99.32 144	99.18 163	95.84 299	99.84 177	99.50 50	99.91 80	99.54 143

v1921920		98.54 187	98.60 159	98.38 289	99.20 244	95.76 352	97.56 291	99.36 221	97.23 317	99.38 121	99.17 168	96.02 285	99.84 177	99.57 39	99.90 88	99.54 143

MP-MVS		98.46 199	98.09 248	99.54 31	99.57 103	99.22 31	98.50 137	99.19 292	97.61 265	97.58 396	98.66 321	97.40 195	99.88 115	94.72 407	99.60 274	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	99.59 100	99.59 36	99.71 49	99.57 49	97.12 214	99.90 81	99.21 70	99.87 100	99.54 143

ACMMP		98.75 138	98.50 175	99.52 44	99.56 111	99.16 48	98.87 89	99.37 217	97.16 323	98.82 258	99.01 225	97.71 161	99.87 135	96.29 347	99.69 233	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
DKM-HiRes		98.14 254	97.80 281	99.16 118	99.51 134	98.40 120	96.70 373	99.63 82	97.55 273	97.45 410	98.74 298	93.27 380	99.54 417	97.78 193	99.55 296	99.53 157

SMA-MVS		98.40 207	98.03 256	99.51 49	99.16 260	99.21 32	98.05 203	99.22 285	94.16 462	98.98 213	99.10 191	97.52 184	99.79 246	96.45 334	99.64 257	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	98.44 188	99.51 49	99.49 150	99.16 48	98.52 130	99.31 246	97.47 282	98.58 303	98.50 352	97.97 138	99.85 158	96.57 320	99.59 278	99.53 157

UniMVSNet_NR-MVSNet		98.86 116	98.68 141	99.40 71	99.17 258	98.74 91	97.68 269	99.40 209	99.14 98	99.06 192	98.59 338	96.71 247	99.93 53	98.57 121	99.77 172	99.53 157

E4		98.87 112	98.88 108	98.81 194	99.52 131	97.23 260	97.62 280	99.61 92	98.58 172	99.18 180	99.33 118	98.29 99	99.69 327	97.99 174	99.83 126	99.52 161

GST-MVS		98.61 171	98.30 216	99.52 44	99.51 134	99.20 38	98.26 171	99.25 277	97.44 290	98.67 283	98.39 364	97.68 162	99.85 158	96.00 361	99.51 309	99.52 161

MGCNet		97.44 323	97.01 343	98.72 221	96.42 525	96.74 302	97.20 339	91.97 535	98.46 182	98.30 335	98.79 287	92.74 396	99.91 74	99.30 62	99.94 51	99.52 161

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	98.24 147	99.84 114	99.52 161

FE-MVSNET2		99.15 57	99.22 54	98.94 167	99.70 57	97.49 231	98.62 118	99.67 70	98.85 145	99.34 135	99.54 62	98.47 77	99.81 224	98.93 92	99.91 80	99.51 165

v1144		98.60 173	98.66 146	98.41 285	99.36 194	95.90 342	97.58 289	99.34 233	97.51 278	99.27 153	99.15 176	96.34 270	99.80 233	99.47 53	99.93 57	99.51 165

v2v482		98.56 180	98.62 154	98.37 292	99.42 178	95.81 349	97.58 289	99.16 303	97.90 239	99.28 151	99.01 225	95.98 292	99.79 246	99.33 59	99.90 88	99.51 165

CPTT-MVS		97.84 291	97.36 319	99.27 99	99.31 208	98.46 116	98.29 166	99.27 269	94.90 440	97.83 379	98.37 367	94.90 330	99.84 177	93.85 435	99.54 299	99.51 165

casdiffseed414692147		99.09 73	99.12 71	99.01 153	99.55 117	97.91 187	98.30 165	99.68 64	99.04 119	99.19 175	99.37 104	98.98 28	99.61 385	98.13 156	99.83 126	99.50 169

viewdifsd2359ckpt11		98.84 119	99.04 87	98.24 307	99.56 111	95.51 359	97.38 316	99.70 54	99.16 94	99.57 72	99.40 97	98.26 105	99.71 308	98.55 125	99.82 133	99.50 169

viewmsd2359difaftdt		98.84 119	99.04 87	98.24 307	99.56 111	95.51 359	97.38 316	99.70 54	99.16 94	99.57 72	99.40 97	98.26 105	99.71 308	98.55 125	99.82 133	99.50 169

LuminaMVS		98.39 214	98.20 232	98.98 160	99.50 141	97.49 231	97.78 251	97.69 439	98.75 150	99.49 94	99.25 142	92.30 404	99.94 41	99.14 75	99.88 95	99.50 169

DU-MVS		98.82 125	98.63 152	99.39 72	99.16 260	98.74 91	97.54 295	99.25 277	98.84 148	99.06 192	98.76 296	96.76 242	99.93 53	98.57 121	99.77 172	99.50 169

NR-MVSNet		98.95 102	98.82 121	99.36 74	99.16 260	98.72 96	99.22 46	99.20 288	99.10 107	99.72 47	98.76 296	96.38 266	99.86 144	98.00 171	99.82 133	99.50 169

casdiffmvs_mvg		99.12 69	99.16 62	98.99 156	99.43 176	97.73 213	98.00 215	99.62 89	99.22 80	99.55 77	99.22 152	98.93 33	99.75 282	98.66 113	99.81 140	99.50 169
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	99.58 103	99.11 100	99.53 83	99.18 163	98.81 39	99.67 344	96.71 304	99.77 172	99.50 169

SymmetryMVS		98.05 263	97.71 292	99.09 134	99.29 214	97.83 196	98.28 167	97.64 444	99.24 77	98.80 262	98.85 271	89.76 437	99.94 41	98.04 166	99.50 317	99.49 177

DVP-MVS++		98.90 108	98.70 138	99.51 49	98.43 413	99.15 52	99.43 15	99.32 241	98.17 213	99.26 157	99.02 213	98.18 118	99.88 115	97.07 265	99.45 326	99.49 177

PC_three_1452									93.27 478	99.40 117	98.54 343	98.22 113	97.00 531	95.17 395	99.45 326	99.49 177

GeoE		99.05 83	98.99 96	99.25 104	99.44 171	98.35 129	98.73 103	99.56 121	98.42 184	98.91 235	98.81 284	98.94 31	99.91 74	98.35 141	99.73 199	99.49 177

h-mvs33		97.77 297	97.33 322	99.10 130	99.21 240	97.84 195	98.35 161	98.57 401	99.11 100	98.58 303	99.02 213	88.65 448	99.96 13	98.11 158	96.34 513	99.49 177

IterMVS-SCA-FT		97.85 290	98.18 238	96.87 430	99.27 220	91.16 497	95.53 452	99.25 277	99.10 107	99.41 114	99.35 111	93.10 387	99.96 13	98.65 114	99.94 51	99.49 177

new-patchmatchnet		98.35 217	98.74 128	97.18 411	99.24 232	92.23 478	96.42 398	99.48 159	98.30 194	99.69 55	99.53 64	97.44 193	99.82 207	98.84 99	99.77 172	99.49 177

APD-MVS		98.10 256	97.67 294	99.42 67	99.11 272	98.93 79	97.76 257	99.28 266	94.97 438	98.72 274	98.77 291	97.04 218	99.85 158	93.79 436	99.54 299	99.49 177
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EPP-MVSNet		98.30 228	98.04 255	99.07 138	99.56 111	97.83 196	99.29 36	98.07 430	99.03 121	98.59 301	99.13 182	92.16 406	99.90 81	96.87 287	99.68 239	99.49 177

DeepC-MVS	97.60 4	98.97 99	98.93 101	99.10 130	99.35 199	97.98 176	98.01 213	99.46 175	97.56 271	99.54 79	99.50 68	98.97 29	99.84 177	98.06 163	99.92 71	99.49 177
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	99.37 217	97.62 262	99.04 202	98.96 242	98.84 37	99.79 246	97.43 234	99.65 255	99.49 177
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
RoMa-HiRes		98.68 157	98.52 170	99.16 118	99.50 141	98.35 129	98.01 213	99.71 48	96.94 335	99.35 130	98.66 321	96.38 266	99.63 372	98.39 138	99.71 217	99.48 188

guyue		98.01 267	97.93 270	98.26 303	99.45 169	95.48 364	98.08 196	96.24 486	98.89 138	99.34 135	99.14 180	91.32 422	99.82 207	99.07 80	99.83 126	99.48 188

DVP-MVS		98.77 136	98.52 170	99.52 44	99.50 141	99.21 32	98.02 210	98.84 367	97.97 231	99.08 190	99.02 213	97.61 172	99.88 115	96.99 272	99.63 263	99.48 188
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	98.43 189	99.57 21	99.18 256	99.35 16	98.36 160	99.29 262	98.29 197	98.88 243	98.85 271	97.53 182	99.87 135	96.14 356	99.31 357	99.48 188

TSAR-MVS + MP.		98.63 167	98.49 180	99.06 144	99.64 77	97.90 189	98.51 135	98.94 342	96.96 333	99.24 167	98.89 263	97.83 151	99.81 224	96.88 286	99.49 321	99.48 188
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
VDDNet		98.21 243	97.95 265	99.01 153	99.58 94	97.74 211	99.01 71	97.29 455	99.67 20	98.97 217	99.50 68	90.45 431	99.80 233	97.88 183	99.20 380	99.48 188

IterMVS		97.73 299	98.11 247	96.57 442	99.24 232	90.28 508	95.52 454	99.21 286	98.86 142	99.33 138	99.33 118	93.11 386	99.94 41	98.49 128	99.94 51	99.48 188
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IS-MVSNet		98.19 246	97.90 274	99.08 136	99.57 103	97.97 177	99.31 30	98.32 417	99.01 123	98.98 213	99.03 212	91.59 415	99.79 246	95.49 388	99.80 152	99.48 188

ACMP	95.32 15	98.41 204	98.09 248	99.36 74	99.51 134	98.79 89	97.68 269	99.38 213	95.76 407	98.81 260	98.82 281	98.36 90	99.82 207	94.75 404	99.77 172	99.48 188
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
cashybrid2		99.12 69	99.12 71	99.09 134	99.53 127	98.08 161	98.34 163	99.66 71	99.35 64	99.35 130	99.23 150	98.39 88	99.72 306	98.46 129	99.81 140	99.47 197

MCST-MVS		98.00 268	97.63 301	99.10 130	99.24 232	98.17 147	96.89 361	98.73 387	95.66 409	97.92 369	97.70 432	97.17 211	99.66 357	96.18 354	99.23 374	99.47 197

3Dnovator+	97.89 3	98.69 151	98.51 172	99.24 106	98.81 347	98.40 120	99.02 70	99.19 292	98.99 124	98.07 357	99.28 129	97.11 216	99.84 177	96.84 290	99.32 355	99.47 197

hybridcas		99.08 79	99.13 70	98.92 173	99.54 123	97.61 225	98.22 177	99.66 71	99.27 74	99.40 117	99.24 144	98.47 77	99.70 317	98.59 118	99.80 152	99.46 200

diffmvs_AUTHOR		98.50 195	98.59 161	98.23 310	99.35 199	95.48 364	96.61 383	99.60 94	98.37 185	98.90 236	99.00 229	97.37 197	99.76 270	98.22 150	99.85 109	99.46 200

HPM-MVS++		98.10 256	97.64 299	99.48 57	99.09 277	99.13 60	97.52 297	98.75 384	97.46 287	96.90 442	97.83 423	96.01 286	99.84 177	95.82 373	99.35 348	99.46 200

V42		98.78 133	98.78 126	98.76 211	99.44 171	97.04 280	98.27 170	99.19 292	97.87 241	99.25 165	99.16 170	96.84 232	99.78 258	99.21 70	99.84 114	99.46 200

APD-MVS_3200maxsize		98.84 119	98.61 158	99.53 38	99.19 248	99.27 26	98.49 140	99.33 239	98.64 161	99.03 205	98.98 236	97.89 147	99.85 158	96.54 328	99.42 337	99.46 200

UniMVSNet (Re)		98.87 112	98.71 135	99.35 80	99.24 232	98.73 94	97.73 264	99.38 213	98.93 132	99.12 184	98.73 300	96.77 240	99.86 144	98.63 116	99.80 152	99.46 200

SR-MVS-dyc-post		98.81 127	98.55 165	99.57 21	99.20 244	99.38 12	98.48 143	99.30 254	98.64 161	98.95 223	98.96 242	97.49 189	99.86 144	96.56 324	99.39 341	99.45 206

RE-MVS-def			98.58 162		99.20 244	99.38 12	98.48 143	99.30 254	98.64 161	98.95 223	98.96 242	97.75 159		96.56 324	99.39 341	99.45 206

HQP_MVS		97.99 271	97.67 294	98.93 170	99.19 248	97.65 220	97.77 254	99.27 269	98.20 209	97.79 382	97.98 410	94.90 330	99.70 317	94.42 416	99.51 309	99.45 206

plane_prior5								99.27 269					99.70 317	94.42 416	99.51 309	99.45 206

lessismore_v0				98.97 162	99.73 38	97.53 230		86.71 546		99.37 125	99.52 67	89.93 434	99.92 65	98.99 88	99.72 208	99.44 210

TAMVS		98.24 239	98.05 254	98.80 197	99.07 281	97.18 270	97.88 237	98.81 372	96.66 359	99.17 183	99.21 154	94.81 336	99.77 264	96.96 277	99.88 95	99.44 210

DeepPCF-MVS	96.93 5	98.32 223	98.01 258	99.23 108	98.39 418	98.97 73	95.03 471	99.18 296	96.88 343	99.33 138	98.78 289	98.16 122	99.28 477	96.74 299	99.62 267	99.44 210

3Dnovator	98.27 2	98.81 127	98.73 130	99.05 145	98.76 354	97.81 204	99.25 43	99.30 254	98.57 174	98.55 309	99.33 118	97.95 140	99.90 81	97.16 254	99.67 245	99.44 210

E2		98.70 147	98.68 141	98.73 219	99.40 183	97.10 277	97.48 303	99.57 111	98.09 224	99.00 208	99.20 156	97.90 143	99.67 344	97.73 204	99.77 172	99.43 214

E3		98.69 151	98.68 141	98.73 219	99.40 183	97.10 277	97.48 303	99.57 111	98.09 224	99.00 208	99.20 156	97.90 143	99.67 344	97.73 204	99.77 172	99.43 214

MVSFormer		98.26 235	98.43 189	97.77 356	98.88 332	93.89 442	99.39 20	99.56 121	99.11 100	98.16 347	98.13 395	93.81 370	99.97 6	99.26 65	99.57 287	99.43 214

jason		97.45 322	97.35 320	97.76 359	99.24 232	93.93 438	95.86 439	98.42 413	94.24 459	98.50 315	98.13 395	94.82 334	99.91 74	97.22 249	99.73 199	99.43 214
jason: jason.
NCCC		97.86 285	97.47 314	99.05 145	98.61 388	98.07 164	96.98 352	98.90 352	97.63 261	97.04 432	97.93 416	95.99 291	99.66 357	95.31 391	98.82 423	99.43 214

Anonymous20240521		98.69 151	98.87 111	98.16 318	99.77 27	95.11 388	99.08 62	99.44 187	99.34 65	99.33 138	99.55 56	94.10 365	99.94 41	99.25 67	99.96 28	99.42 219

MVS_111021_HR		98.25 238	98.08 251	98.75 213	99.09 277	97.46 237	95.97 430	99.27 269	97.60 267	97.99 365	98.25 384	98.15 124	99.38 461	96.87 287	99.57 287	99.42 219

COLMAP_ROB	96.50 10	98.99 94	98.85 118	99.41 69	99.58 94	99.10 65	98.74 99	99.56 121	99.09 110	99.33 138	99.19 159	98.40 86	99.72 306	95.98 363	99.76 188	99.42 219
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	99.49 150	99.17 43	98.10 193	99.31 246	98.03 227	99.66 60	99.02 213	98.36 90	99.88 115	96.91 279	99.62 267	99.41 222

OPU-MVS				98.82 192	98.59 393	98.30 134	98.10 193				98.52 347	98.18 118	98.75 504	94.62 408	99.48 322	99.41 222

our_test_3		97.39 328	97.73 289	96.34 450	98.70 368	89.78 513	94.61 487	98.97 341	96.50 365	99.04 202	98.85 271	95.98 292	99.84 177	97.26 246	99.67 245	99.41 222

casdiffmvs		98.95 102	99.00 94	98.81 194	99.38 187	97.33 246	97.82 245	99.57 111	99.17 93	99.35 130	99.17 168	98.35 94	99.69 327	98.46 129	99.73 199	99.41 222
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		97.60 309	97.67 294	97.39 403	99.04 291	93.04 461	95.27 463	98.38 416	97.25 311	98.92 234	98.95 246	95.48 314	99.73 296	96.99 272	98.74 428	99.41 222

MDA-MVSNet_test_wron		97.60 309	97.66 297	97.41 402	99.04 291	93.09 457	95.27 463	98.42 413	97.26 310	98.88 243	98.95 246	95.43 316	99.73 296	97.02 268	98.72 430	99.41 222

GBi-Net		98.65 163	98.47 183	99.17 115	98.90 326	98.24 139	99.20 49	99.44 187	98.59 169	98.95 223	99.55 56	94.14 361	99.86 144	97.77 196	99.69 233	99.41 222

test1		98.65 163	98.47 183	99.17 115	98.90 326	98.24 139	99.20 49	99.44 187	98.59 169	98.95 223	99.55 56	94.14 361	99.86 144	97.77 196	99.69 233	99.41 222

FMVSNet1		99.17 52	99.17 60	99.17 115	99.55 117	98.24 139	99.20 49	99.44 187	99.21 82	99.43 108	99.55 56	97.82 154	99.86 144	98.42 137	99.89 94	99.41 222

test_fmvs1		97.72 300	97.94 268	97.07 419	98.66 383	92.39 473	97.68 269	99.81 32	95.20 433	99.54 79	99.44 85	91.56 417	99.41 456	99.78 21	99.77 172	99.40 231

viewdifsd2359ckpt07		98.71 142	98.86 115	98.26 303	99.43 176	95.65 353	97.20 339	99.66 71	99.20 84	99.29 149	99.01 225	98.29 99	99.73 296	97.92 179	99.75 192	99.39 232

viewmanbaseed2359cas		98.58 177	98.54 167	98.70 225	99.28 217	97.13 276	97.47 307	99.55 126	97.55 273	98.96 222	98.92 251	97.77 157	99.59 394	97.59 217	99.77 172	99.39 232

KD-MVS_self_test		99.25 40	99.18 59	99.44 65	99.63 83	99.06 70	98.69 108	99.54 132	99.31 69	99.62 69	99.53 64	97.36 198	99.86 144	99.24 69	99.71 217	99.39 232

v148		98.45 201	98.60 159	98.00 337	99.44 171	94.98 391	97.44 311	99.06 320	98.30 194	99.32 144	98.97 238	96.65 251	99.62 377	98.37 140	99.85 109	99.39 232

test20.03		98.78 133	98.77 127	98.78 204	99.46 164	97.20 266	97.78 251	99.24 282	99.04 119	99.41 114	98.90 257	97.65 165	99.76 270	97.70 207	99.79 159	99.39 232

CDPH-MVS		97.26 340	96.66 372	99.07 138	99.00 306	98.15 148	96.03 427	99.01 335	91.21 508	97.79 382	97.85 421	96.89 230	99.69 327	92.75 469	99.38 344	99.39 232

EPNet		96.14 407	95.44 423	98.25 305	90.76 550	95.50 363	97.92 232	94.65 509	98.97 127	92.98 526	98.85 271	89.12 443	99.87 135	95.99 362	99.68 239	99.39 232
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNVR-MVS		98.17 251	97.87 276	99.07 138	98.67 378	98.24 139	97.01 349	98.93 345	97.25 311	97.62 392	98.34 371	97.27 204	99.57 403	96.42 336	99.33 352	99.39 232

DeepC-MVS_fast	96.85 6	98.30 228	98.15 243	98.75 213	98.61 388	97.23 260	97.76 257	99.09 316	97.31 304	98.75 270	98.66 321	97.56 177	99.64 369	96.10 360	99.55 296	99.39 232
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
dtuplus		98.32 223	98.39 196	98.10 323	99.15 264	95.29 377	96.68 375	99.51 144	97.32 302	99.18 180	99.15 176	97.61 172	99.62 377	97.19 251	99.74 195	99.38 241

SF-MVS		98.53 189	98.27 222	99.32 91	99.31 208	98.75 90	98.19 178	99.41 204	96.77 352	98.83 255	98.90 257	97.80 155	99.82 207	95.68 379	99.52 306	99.38 241

test9_res														93.28 452	99.15 388	99.38 241

hybridnocas07		98.32 223	98.37 202	98.17 315	99.14 266	95.51 359	96.67 377	99.56 121	97.85 243	98.75 270	98.95 246	96.65 251	99.63 372	98.00 171	99.78 164	99.37 244

BP-MVS1		97.40 327	96.97 345	98.71 223	99.07 281	96.81 297	98.34 163	97.18 459	98.58 172	98.17 344	98.61 335	84.01 488	99.94 41	98.97 89	99.78 164	99.37 244

OPM-MVS		98.56 180	98.32 214	99.25 104	99.41 181	98.73 94	97.13 346	99.18 296	97.10 326	98.75 270	98.92 251	98.18 118	99.65 364	96.68 308	99.56 291	99.37 244
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
agg_prior2														92.50 476	99.16 386	99.37 244

AllTest		98.44 202	98.20 232	99.16 118	99.50 141	98.55 108	98.25 172	99.58 103	96.80 349	98.88 243	99.06 200	97.65 165	99.57 403	94.45 414	99.61 272	99.37 244

TestCases				99.16 118	99.50 141	98.55 108		99.58 103	96.80 349	98.88 243	99.06 200	97.65 165	99.57 403	94.45 414	99.61 272	99.37 244

MDA-MVSNet-bldmvs		97.94 275	97.91 273	98.06 331	99.44 171	94.96 392	96.63 381	99.15 308	98.35 187	98.83 255	99.11 188	94.31 356	99.85 158	96.60 317	98.72 430	99.37 244

MVSTER		96.86 370	96.55 381	97.79 354	97.91 458	94.21 419	97.56 291	98.87 358	97.49 281	99.06 192	99.05 207	80.72 501	99.80 233	98.44 131	99.82 133	99.37 244

dtuonlycased		97.70 302	98.19 236	96.24 455	99.75 34	89.51 515	94.69 483	99.64 79	98.23 201	99.46 101	98.57 340	98.25 107	99.85 158	95.65 380	99.44 333	99.36 252

viewcassd2359sk11		98.55 184	98.51 172	98.67 230	99.29 214	96.99 283	97.39 314	99.54 132	97.73 253	98.81 260	99.08 198	97.55 178	99.66 357	97.52 225	99.67 245	99.36 252

pmmvs5		97.64 307	97.49 310	98.08 328	99.14 266	95.12 387	96.70 373	99.05 324	93.77 472	98.62 294	98.83 278	93.23 382	99.75 282	98.33 144	99.76 188	99.36 252

Anonymous20231206		98.21 243	98.21 231	98.20 312	99.51 134	95.43 369	98.13 186	99.32 241	96.16 384	98.93 232	98.82 281	96.00 287	99.83 195	97.32 242	99.73 199	99.36 252

train_agg		97.10 353	96.45 388	99.07 138	98.71 364	98.08 161	95.96 432	99.03 329	91.64 500	95.85 483	97.53 441	96.47 259	99.76 270	93.67 439	99.16 386	99.36 252

PVSNet_BlendedMVS		97.55 314	97.53 307	97.60 381	98.92 322	93.77 446	96.64 380	99.43 193	94.49 450	97.62 392	99.18 163	96.82 235	99.67 344	94.73 405	99.93 57	99.36 252

nocashy02		98.57 178	98.66 146	98.31 298	99.20 244	95.89 343	96.92 359	99.57 111	98.71 158	99.02 206	99.04 209	97.48 190	99.71 308	98.28 146	99.70 227	99.35 258

hybrid		98.22 240	98.27 222	98.08 328	99.13 269	95.24 379	96.61 383	99.53 136	97.43 291	98.46 320	98.97 238	96.75 245	99.65 364	97.84 188	99.69 233	99.35 258

Anonymous20240529		98.93 104	98.87 111	99.12 126	99.19 248	98.22 144	99.01 71	98.99 338	99.25 76	99.54 79	99.37 104	97.04 218	99.80 233	97.89 180	99.52 306	99.35 258

F-COLMAP		97.30 337	96.68 368	99.14 124	99.19 248	98.39 122	97.27 333	99.30 254	92.93 486	96.62 458	98.00 408	95.73 302	99.68 339	92.62 472	98.46 450	99.35 258

viewdifsd2359ckpt13		98.39 214	98.29 218	98.70 225	99.26 229	97.19 267	97.51 299	99.48 159	96.94 335	98.58 303	98.82 281	97.47 192	99.55 411	97.21 250	99.33 352	99.34 262

ppachtmachnet_test		97.50 315	97.74 286	96.78 436	98.70 368	91.23 496	94.55 489	99.05 324	96.36 372	99.21 173	98.79 287	96.39 264	99.78 258	96.74 299	99.82 133	99.34 262

VDD-MVS		98.56 180	98.39 196	99.07 138	99.13 269	98.07 164	98.59 122	97.01 464	99.59 36	99.11 185	99.27 131	94.82 334	99.79 246	98.34 142	99.63 263	99.34 262

testgi		98.32 223	98.39 196	98.13 320	99.57 103	95.54 357	97.78 251	99.49 157	97.37 297	99.19 175	97.65 434	98.96 30	99.49 435	96.50 331	98.99 409	99.34 262

diffmvs		98.22 240	98.24 229	98.17 315	99.00 306	95.44 368	96.38 400	99.58 103	97.79 249	98.53 312	98.50 352	96.76 242	99.74 289	97.95 178	99.64 257	99.34 262
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		97.89 279	97.60 303	98.75 213	99.31 208	97.17 272	97.62 280	99.35 227	98.72 157	98.76 269	98.68 315	92.57 399	99.74 289	97.76 200	95.60 527	99.34 262

onestephybrid01		98.40 207	98.39 196	98.42 283	99.05 289	96.23 327	96.73 371	99.41 204	98.18 212	98.65 286	99.02 213	97.02 221	99.69 327	97.73 204	99.70 227	99.33 268

dtuonly		96.49 387	97.28 323	94.10 508	98.80 350	83.27 542	93.66 515	99.48 159	95.10 434	97.87 374	98.30 378	95.61 307	99.68 339	96.98 275	99.75 192	99.33 268

viewmambaseed2359dif		98.19 246	98.26 225	97.99 339	99.02 302	95.03 390	96.59 386	99.53 136	96.21 379	99.00 208	98.99 231	97.62 170	99.61 385	97.62 213	99.72 208	99.33 268

baseline		98.96 101	99.02 90	98.76 211	99.38 187	97.26 258	98.49 140	99.50 149	98.86 142	99.19 175	99.06 200	98.23 110	99.69 327	98.71 110	99.76 188	99.33 268

MG-MVS		96.77 374	96.61 377	97.26 408	98.31 423	93.06 458	95.93 435	98.12 429	96.45 370	97.92 369	98.73 300	93.77 372	99.39 459	91.19 499	99.04 400	99.33 268

DKM		98.18 248	97.95 265	98.85 182	99.35 199	98.31 133	96.68 375	99.69 57	96.90 341	98.61 296	98.77 291	94.41 349	98.93 497	97.32 242	99.84 114	99.32 273

HQP4-MVS										95.56 489			99.54 417			99.32 273

CDS-MVSNet		97.69 303	97.35 320	98.69 227	98.73 358	97.02 282	96.92 359	98.75 384	95.89 397	98.59 301	98.67 317	92.08 410	99.74 289	96.72 302	99.81 140	99.32 273
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HQP-MVS		97.00 364	96.49 384	98.55 260	98.67 378	96.79 298	96.29 407	99.04 327	96.05 387	95.55 490	96.84 468	93.84 368	99.54 417	92.82 465	99.26 369	99.32 273

RPSCF		98.62 170	98.36 204	99.42 67	99.65 71	99.42 10	98.55 126	99.57 111	97.72 255	98.90 236	99.26 137	96.12 282	99.52 424	95.72 376	99.71 217	99.32 273

E3new		98.41 204	98.34 208	98.62 242	99.19 248	96.90 291	97.32 324	99.50 149	97.40 294	98.63 290	98.92 251	97.21 209	99.65 364	97.34 238	99.52 306	99.31 278

MVP-Stereo		98.08 260	97.92 271	98.57 253	98.96 314	96.79 298	97.90 235	99.18 296	96.41 371	98.46 320	98.95 246	95.93 296	99.60 389	96.51 330	98.98 412	99.31 278
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 207	98.68 141	97.54 390	98.96 314	97.99 173	97.88 237	99.36 221	98.20 209	99.63 66	99.04 209	98.76 46	95.33 542	96.56 324	99.74 195	99.31 278
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		98.42 203	98.30 216	98.79 201	98.79 353	97.29 255	98.23 173	98.66 392	99.31 69	98.85 250	98.80 285	94.80 337	99.78 258	98.13 156	99.13 391	99.31 278

test_prior				98.95 166	98.69 373	97.95 181		99.03 329					99.59 394			99.30 282

USDC		97.41 326	97.40 315	97.44 400	98.94 316	93.67 449	95.17 467	99.53 136	94.03 468	98.97 217	99.10 191	95.29 319	99.34 466	95.84 372	99.73 199	99.30 282

viewdifsd2359ckpt09		98.13 255	97.92 271	98.77 209	99.18 256	97.35 244	97.29 328	99.53 136	95.81 404	98.09 355	98.47 356	96.34 270	99.66 357	97.02 268	99.51 309	99.29 284

test_fmvsm_n_1920		99.33 30	99.45 23	98.99 156	99.57 103	97.73 213	97.93 229	99.83 26	99.22 80	99.93 6	99.30 125	99.42 11	99.96 13	99.85 6	99.99 5	99.29 284

FMVSNet2		98.49 196	98.40 193	98.75 213	98.90 326	97.14 275	98.61 120	99.13 310	98.59 169	99.19 175	99.28 129	94.14 361	99.82 207	97.97 176	99.80 152	99.29 284

RoMa-SfM		98.46 199	98.27 222	99.02 151	99.35 199	98.32 132	97.56 291	99.70 54	95.88 398	99.38 121	98.65 324	96.41 262	99.46 446	97.78 193	99.71 217	99.28 287

gbinet_0.2-2-1-0.02		95.44 437	94.55 452	98.14 319	95.99 533	95.34 375	94.71 479	98.29 419	96.00 392	96.05 480	90.50 542	84.99 477	99.79 246	97.33 240	97.07 504	99.28 287

XVG-OURS-SEG-HR		98.49 196	98.28 219	99.14 124	99.49 150	98.83 86	96.54 387	99.48 159	97.32 302	99.11 185	98.61 335	99.33 15	99.30 473	96.23 349	98.38 452	99.28 287

mamba_0408		98.80 129	98.88 108	98.55 260	99.27 220	96.50 315	98.00 215	99.60 94	98.93 132	99.22 170	98.84 276	98.59 67	99.89 97	97.74 202	99.72 208	99.27 290

SSM_04072		98.80 129	98.88 108	98.56 258	99.27 220	96.50 315	98.00 215	99.60 94	98.93 132	99.22 170	98.84 276	98.59 67	99.90 81	97.74 202	99.72 208	99.27 290

SSM_0407		98.86 116	98.96 100	98.55 260	99.27 220	96.50 315	98.04 205	99.66 71	99.09 110	99.22 170	99.02 213	98.79 43	99.87 135	97.87 185	99.72 208	99.27 290

test12				98.93 170	98.58 395	97.83 196		98.66 392		96.53 463		95.51 312	99.69 327		99.13 391	99.27 290

DSMNet-mixed		97.42 325	97.60 303	96.87 430	99.15 264	91.46 486	98.54 128	99.12 311	92.87 489	97.58 396	99.63 39	96.21 276	99.90 81	95.74 375	99.54 299	99.27 290

N_pmnet		97.63 308	97.17 331	98.99 156	99.27 220	97.86 193	95.98 429	93.41 525	95.25 430	99.47 100	98.90 257	95.63 306	99.85 158	96.91 279	99.73 199	99.27 290

ambc				98.24 307	98.82 344	95.97 340	98.62 118	99.00 337		99.27 153	99.21 154	96.99 224	99.50 431	96.55 327	99.50 317	99.26 296

DenseAffine		98.10 256	97.86 277	98.84 188	99.32 206	97.93 184	96.62 382	99.76 39	96.68 358	98.65 286	98.72 302	94.46 347	99.33 468	96.76 296	99.75 192	99.25 297

LFMVS		97.20 347	96.72 365	98.64 236	98.72 360	96.95 287	98.93 82	94.14 520	99.74 12	98.78 264	99.01 225	84.45 483	99.73 296	97.44 233	99.27 365	99.25 297

FMVSNet5		96.01 412	95.20 438	98.41 285	97.53 484	96.10 330	98.74 99	99.50 149	97.22 320	98.03 362	99.04 209	69.80 527	99.88 115	97.27 245	99.71 217	99.25 297

BH-RMVSNet		96.83 371	96.58 380	97.58 383	98.47 406	94.05 426	96.67 377	97.36 449	96.70 357	97.87 374	97.98 410	95.14 325	99.44 451	90.47 509	98.58 445	99.25 297

testf1		99.25 40	99.16 62	99.51 49	99.89 6	99.63 3	98.71 106	99.69 57	98.90 136	99.43 108	99.35 111	98.86 35	99.67 344	97.81 190	99.81 140	99.24 301

APD_test2		99.25 40	99.16 62	99.51 49	99.89 6	99.63 3	98.71 106	99.69 57	98.90 136	99.43 108	99.35 111	98.86 35	99.67 344	97.81 190	99.81 140	99.24 301

SSM_0404		98.90 108	99.01 92	98.57 253	99.42 178	96.59 307	98.13 186	99.66 71	99.09 110	99.30 148	99.02 213	98.79 43	99.89 97	97.87 185	99.80 152	99.23 303

旧先验1					98.82 344	97.45 238		98.76 380			98.34 371	95.50 313			99.01 406	99.23 303

test222					98.92 322	96.93 289	95.54 451	98.78 377	85.72 535	96.86 446	98.11 398	94.43 348			99.10 396	99.23 303

XVG-ACMP-BASELINE		98.56 180	98.34 208	99.22 109	99.54 123	98.59 105	97.71 265	99.46 175	97.25 311	98.98 213	98.99 231	97.54 180	99.84 177	95.88 366	99.74 195	99.23 303

FMVSNet3		97.50 315	97.24 327	98.29 301	98.08 449	95.83 347	97.86 241	98.91 351	97.89 240	98.95 223	98.95 246	87.06 457	99.81 224	97.77 196	99.69 233	99.23 303

icg_test_0407_2		98.20 245	98.38 200	97.65 374	99.03 294	94.03 429	95.78 444	99.45 179	98.16 216	99.06 192	98.71 304	98.27 103	99.68 339	97.50 226	99.45 326	99.22 308

IMVS_0407		98.39 214	98.64 150	97.66 372	99.03 294	94.03 429	98.10 193	99.45 179	98.16 216	99.06 192	98.71 304	98.27 103	99.71 308	97.50 226	99.45 326	99.22 308

IMVS_0404		98.07 261	98.20 232	97.69 367	99.03 294	94.03 429	96.67 377	99.45 179	98.16 216	98.03 362	98.71 304	96.80 238	99.82 207	97.50 226	99.45 326	99.22 308

IMVS_0403		98.34 218	98.56 164	97.66 372	99.03 294	94.03 429	97.98 223	99.45 179	98.16 216	98.89 239	98.71 304	97.90 143	99.74 289	97.50 226	99.45 326	99.22 308

无先验							95.74 446	98.74 386	89.38 521				99.73 296	92.38 479		99.22 308

blended_shiyan8		95.98 415	95.33 429	97.94 342	97.05 505	94.87 398	95.34 461	98.59 398	96.17 380	97.09 428	92.39 533	87.62 456	99.76 270	97.65 210	96.05 524	99.20 313

tttt0517		95.64 429	94.98 442	97.64 377	99.36 194	93.81 444	98.72 104	90.47 539	98.08 226	98.67 283	98.34 371	73.88 522	99.92 65	97.77 196	99.51 309	99.20 313

pmmvs-eth3d		98.47 198	98.34 208	98.86 181	99.30 212	97.76 209	97.16 344	99.28 266	95.54 417	99.42 112	99.19 159	97.27 204	99.63 372	97.89 180	99.97 21	99.20 313

MS-PatchMatch		97.68 304	97.75 285	97.45 399	98.23 435	93.78 445	97.29 328	98.84 367	96.10 386	98.64 289	98.65 324	96.04 284	99.36 462	96.84 290	99.14 389	99.20 313

新几何1				98.91 175	98.94 316	97.76 209		98.76 380	87.58 532	96.75 451	98.10 399	94.80 337	99.78 258	92.73 470	99.00 407	99.20 313

PHI-MVS		98.29 231	97.95 265	99.34 83	98.44 411	99.16 48	98.12 190	99.38 213	96.01 391	98.06 358	98.43 360	97.80 155	99.67 344	95.69 378	99.58 283	99.20 313

blended_shiyan6		95.99 414	95.33 429	97.95 341	97.06 503	94.89 396	95.34 461	98.58 399	96.17 380	97.06 430	92.41 532	87.64 455	99.76 270	97.64 211	96.09 518	99.19 319

GDP-MVS		97.50 315	97.11 338	98.67 230	99.02 302	96.85 295	98.16 183	99.71 48	98.32 192	98.52 314	98.54 343	83.39 492	99.95 25	98.79 101	99.56 291	99.19 319

Anonymous202405211		97.90 277	97.50 309	99.08 136	98.90 326	98.25 138	98.53 129	96.16 487	98.87 140	99.11 185	98.86 268	90.40 432	99.78 258	97.36 237	99.31 357	99.19 319

CANet		97.87 284	97.76 284	98.19 314	97.75 467	95.51 359	96.76 368	99.05 324	97.74 252	96.93 436	98.21 389	95.59 309	99.89 97	97.86 187	99.93 57	99.19 319

XVG-OURS		98.53 189	98.34 208	99.11 128	99.50 141	98.82 88	95.97 430	99.50 149	97.30 305	99.05 200	98.98 236	99.35 14	99.32 470	95.72 376	99.68 239	99.18 323

WTY-MVS		96.67 377	96.27 396	97.87 349	98.81 347	94.61 409	96.77 367	97.92 434	94.94 439	97.12 425	97.74 429	91.11 424	99.82 207	93.89 432	98.15 466	99.18 323

Vis-MVSNet (Re-imp)		97.46 320	97.16 332	98.34 295	99.55 117	96.10 330	98.94 81	98.44 410	98.32 192	98.16 347	98.62 333	88.76 444	99.73 296	93.88 433	99.79 159	99.18 323

TinyColmap		97.89 279	97.98 261	97.60 381	98.86 335	94.35 415	96.21 413	99.44 187	97.45 289	99.06 192	98.88 265	97.99 137	99.28 477	94.38 420	99.58 283	99.18 323

wanda-best-256-512		95.48 435	94.74 449	97.68 368	96.53 519	94.12 423	94.17 501	98.57 401	95.84 400	96.71 452	91.16 538	86.05 467	99.76 270	97.57 218	96.09 518	99.17 327

FE-blended-shiyan7		95.48 435	94.74 449	97.68 368	96.53 519	94.12 423	94.17 501	98.57 401	95.84 400	96.71 452	91.16 538	86.05 467	99.76 270	97.57 218	96.09 518	99.17 327

usedtu_blend_shiyan5		96.20 406	95.62 412	97.94 342	96.53 519	94.93 393	98.83 96	99.59 100	98.89 138	96.71 452	91.16 538	86.05 467	99.73 296	96.70 305	96.09 518	99.17 327

testdata				98.09 325	98.93 318	95.40 370		98.80 374	90.08 517	97.45 410	98.37 367	95.26 320	99.70 317	93.58 443	98.95 415	99.17 327

lupinMVS		97.06 358	96.86 354	97.65 374	98.88 332	93.89 442	95.48 455	97.97 432	93.53 475	98.16 347	97.58 438	93.81 370	99.91 74	96.77 295	99.57 287	99.17 327

Patchmtry		97.35 332	96.97 345	98.50 274	97.31 496	96.47 318	98.18 179	98.92 349	98.95 131	98.78 264	99.37 104	85.44 475	99.85 158	95.96 364	99.83 126	99.17 327

usedtu_dtu_shiyan1		97.37 329	97.13 336	98.11 321	99.03 294	95.40 370	94.47 491	98.99 338	96.87 344	97.97 366	97.81 424	92.12 407	99.75 282	97.49 231	99.43 335	99.16 333

FE-MVSNET3		97.37 329	97.13 336	98.11 321	99.03 294	95.40 370	94.47 491	98.99 338	96.87 344	97.97 366	97.81 424	92.12 407	99.75 282	97.49 231	99.43 335	99.16 333

SD_0403		96.28 400	95.83 404	97.64 377	98.72 360	94.30 416	98.87 89	98.77 378	97.80 247	96.53 463	98.02 407	97.34 199	99.47 442	76.93 542	99.48 322	99.16 333

RRT-MVS		97.88 282	97.98 261	97.61 380	98.15 442	93.77 446	98.97 77	99.64 79	99.16 94	98.69 279	99.42 89	91.60 414	99.89 97	97.63 212	98.52 449	99.16 333

sss		97.21 346	96.93 347	98.06 331	98.83 341	95.22 383	96.75 369	98.48 409	94.49 450	97.27 420	97.90 417	92.77 395	99.80 233	96.57 320	99.32 355	99.16 333

CSCG		98.68 157	98.50 175	99.20 110	99.45 169	98.63 100	98.56 125	99.57 111	97.87 241	98.85 250	98.04 405	97.66 164	99.84 177	96.72 302	99.81 140	99.13 338

MVS_111021_LR		98.30 228	98.12 246	98.83 190	99.16 260	98.03 169	96.09 423	99.30 254	97.58 268	98.10 354	98.24 386	98.25 107	99.34 466	96.69 307	99.65 255	99.12 339

miper_lstm_enhance		97.18 349	97.16 332	97.25 409	98.16 441	92.85 464	95.15 469	99.31 246	97.25 311	98.74 273	98.78 289	90.07 433	99.78 258	97.19 251	99.80 152	99.11 340

testing3		93.51 474	92.09 487	97.75 360	98.60 390	94.40 413	97.32 324	95.26 505	97.56 271	96.79 450	95.50 499	53.57 551	99.77 264	95.26 393	98.97 413	99.08 341

原ACMM1				98.35 294	98.90 326	96.25 326		98.83 371	92.48 493	96.07 478	98.10 399	95.39 317	99.71 308	92.61 473	98.99 409	99.08 341

QAPM		97.31 335	96.81 360	98.82 192	98.80 350	97.49 231	99.06 66	99.19 292	90.22 515	97.69 388	99.16 170	96.91 229	99.90 81	90.89 505	99.41 338	99.07 343

PAPM_NR		96.82 373	96.32 392	98.30 300	99.07 281	96.69 305	97.48 303	98.76 380	95.81 404	96.61 459	96.47 478	94.12 364	99.17 484	90.82 507	97.78 480	99.06 344

eth_miper_zixun_eth		97.23 344	97.25 326	97.17 413	98.00 453	92.77 466	94.71 479	99.18 296	97.27 309	98.56 307	98.74 298	91.89 412	99.69 327	97.06 267	99.81 140	99.05 345

D2MVS		97.84 291	97.84 279	97.83 351	99.14 266	94.74 403	96.94 355	98.88 356	95.84 400	98.89 239	98.96 242	94.40 351	99.69 327	97.55 220	99.95 39	99.05 345

c3_l		97.36 331	97.37 318	97.31 404	98.09 448	93.25 456	95.01 472	99.16 303	97.05 328	98.77 267	98.72 302	92.88 392	99.64 369	96.93 278	99.76 188	99.05 345

PLC	94.65 16	96.51 384	95.73 408	98.85 182	98.75 356	97.91 187	96.42 398	99.06 320	90.94 512	95.59 487	97.38 454	94.41 349	99.59 394	90.93 503	98.04 475	99.05 345
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	98.91 175	99.67 68	97.82 201	99.00 73	99.44 187	99.45 50	99.51 92	99.24 144	98.20 117	99.86 144	95.92 365	99.69 233	99.04 349

CANet_DTU		97.26 340	97.06 340	97.84 350	97.57 479	94.65 408	96.19 415	98.79 375	97.23 317	95.14 500	98.24 386	93.22 383	99.84 177	97.34 238	99.84 114	99.04 349

PM-MVS		98.82 125	98.72 132	99.12 126	99.64 77	98.54 111	97.98 223	99.68 64	97.62 262	99.34 135	99.18 163	97.54 180	99.77 264	97.79 192	99.74 195	99.04 349

TestfortrainingZip				98.97 162	98.30 424	98.43 119	98.68 109	98.26 420	97.76 251	98.86 249	98.16 394	95.15 324	99.47 442		97.55 485	99.02 352

TSAR-MVS + GP.		98.18 248	97.98 261	98.77 209	98.71 364	97.88 191	96.32 405	98.66 392	96.33 373	99.23 169	98.51 348	97.48 190	99.40 457	97.16 254	99.46 324	99.02 352

DIV-MVS_self_test		97.02 361	96.84 356	97.58 383	97.82 464	94.03 429	94.66 484	99.16 303	97.04 329	98.63 290	98.71 304	88.69 445	99.69 327	97.00 270	99.81 140	99.01 354

GA-MVS		95.86 421	95.32 431	97.49 395	98.60 390	94.15 422	93.83 512	97.93 433	95.49 419	96.68 455	97.42 452	83.21 493	99.30 473	96.22 350	98.55 447	99.01 354

OMC-MVS		97.88 282	97.49 310	99.04 147	98.89 331	98.63 100	96.94 355	99.25 277	95.02 436	98.53 312	98.51 348	97.27 204	99.47 442	93.50 447	99.51 309	99.01 354

cl____		97.02 361	96.83 357	97.58 383	97.82 464	94.04 428	94.66 484	99.16 303	97.04 329	98.63 290	98.71 304	88.68 447	99.69 327	97.00 270	99.81 140	99.00 357

pmmvs4		97.58 312	97.28 323	98.51 270	98.84 339	96.93 289	95.40 459	98.52 407	93.60 474	98.61 296	98.65 324	95.10 326	99.60 389	96.97 276	99.79 159	98.99 358

blend_shiyan4		92.09 498	90.16 505	97.88 347	96.78 513	94.93 393	95.24 465	98.58 399	96.22 378	96.07 478	91.42 537	63.46 546	99.73 296	96.70 305	76.98 546	98.98 359

EPNet_dtu		94.93 451	94.78 447	95.38 492	93.58 541	87.68 524	96.78 366	95.69 501	97.35 299	89.14 541	98.09 401	88.15 453	99.49 435	94.95 401	99.30 361	98.98 359
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t		96.50 386	95.77 406	98.69 227	99.48 158	97.43 241	97.84 244	99.55 126	81.42 541	96.51 467	98.58 339	95.53 310	99.67 344	93.41 450	99.58 283	98.98 359

PVSNet_Blended		96.88 368	96.68 368	97.47 398	98.92 322	93.77 446	94.71 479	99.43 193	90.98 511	97.62 392	97.36 456	96.82 235	99.67 344	94.73 405	99.56 291	98.98 359

ArgMatch-SfM		97.96 274	97.72 290	98.66 232	99.02 302	97.33 246	96.49 392	99.52 142	95.46 421	98.71 278	98.29 381	96.14 278	99.69 327	96.30 345	99.56 291	98.97 363

APD_test1		98.83 122	98.66 146	99.34 83	99.78 24	99.47 8	98.42 151	99.45 179	98.28 199	98.98 213	99.19 159	97.76 158	99.58 401	96.57 320	99.55 296	98.97 363

PAPR		95.29 441	94.47 453	97.75 360	97.50 490	95.14 386	94.89 476	98.71 389	91.39 506	95.35 497	95.48 501	94.57 344	99.14 487	84.95 529	97.37 495	98.97 363

EGC-MVSNET		85.24 509	80.54 512	99.34 83	99.77 27	99.20 38	99.08 62	99.29 262	12.08 549	20.84 550	99.42 89	97.55 178	99.85 158	97.08 264	99.72 208	98.96 366

thisisatest0530		95.27 442	94.45 454	97.74 362	99.19 248	94.37 414	97.86 241	90.20 540	97.17 322	98.22 342	97.65 434	73.53 523	99.90 81	96.90 284	99.35 348	98.95 367

mvs_anonymous		97.83 293	98.16 242	96.87 430	98.18 438	91.89 480	97.31 326	98.90 352	97.37 297	98.83 255	99.46 80	96.28 273	99.79 246	98.90 94	98.16 465	98.95 367

baseline1		95.96 418	95.44 423	97.52 392	98.51 404	93.99 436	98.39 157	96.09 491	98.21 205	98.40 331	97.76 428	86.88 458	99.63 372	95.42 389	89.27 540	98.95 367

CLD-MVS		97.49 318	97.16 332	98.48 276	99.07 281	97.03 281	94.71 479	99.21 286	94.46 452	98.06 358	97.16 462	97.57 176	99.48 439	94.46 413	99.78 164	98.95 367
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MSLP-MVS++		98.02 265	98.14 245	97.64 377	98.58 395	95.19 384	97.48 303	99.23 284	97.47 282	97.90 371	98.62 333	97.04 218	98.81 502	97.55 220	99.41 338	98.94 371

DELS-MVS		98.27 233	98.20 232	98.48 276	98.86 335	96.70 304	95.60 450	99.20 288	97.73 253	98.45 322	98.71 304	97.50 186	99.82 207	98.21 151	99.59 278	98.93 372
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
ArgMatch-Sym		97.83 293	97.54 305	98.71 223	98.98 310	97.65 220	96.25 412	99.43 193	95.60 412	98.85 250	97.98 410	95.72 303	99.56 406	95.54 387	99.50 317	98.92 373

cl22		95.79 424	95.39 426	96.98 423	96.77 514	92.79 465	94.40 494	98.53 405	94.59 449	97.89 372	98.17 392	82.82 497	99.24 479	96.37 339	99.03 401	98.92 373

LS3D		98.63 167	98.38 200	99.36 74	97.25 497	99.38 12	99.12 61	99.32 241	99.21 82	98.44 323	98.88 265	97.31 200	99.80 233	96.58 318	99.34 350	98.92 373

CMPMVS	75.91 23	96.29 399	95.44 423	98.84 188	96.25 528	98.69 98	97.02 348	99.12 311	88.90 524	97.83 379	98.86 268	89.51 440	98.90 500	91.92 483	99.51 309	98.92 373
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LCM-MVSNet-Re		98.64 165	98.48 181	99.11 128	98.85 338	98.51 113	98.49 140	99.83 26	98.37 185	99.69 55	99.46 80	98.21 115	99.92 65	94.13 426	99.30 361	98.91 377

mvsmamba		97.57 313	97.26 325	98.51 270	98.69 373	96.73 303	98.74 99	97.25 456	97.03 331	97.88 373	99.23 150	90.95 425	99.87 135	96.61 316	99.00 407	98.91 377

DPM-MVS		96.32 397	95.59 416	98.51 270	98.76 354	97.21 265	94.54 490	98.26 420	91.94 499	96.37 471	97.25 460	93.06 389	99.43 453	91.42 494	98.74 428	98.89 379

test_yl		96.69 375	96.29 394	97.90 344	98.28 427	95.24 379	97.29 328	97.36 449	98.21 205	98.17 344	97.86 419	86.27 462	99.55 411	94.87 402	98.32 454	98.89 379

DCV-MVSNet		96.69 375	96.29 394	97.90 344	98.28 427	95.24 379	97.29 328	97.36 449	98.21 205	98.17 344	97.86 419	86.27 462	99.55 411	94.87 402	98.32 454	98.89 379

SPE-MVS-test		99.13 66	99.09 82	99.26 101	99.13 269	98.97 73	99.31 30	99.88 15	99.44 52	98.16 347	98.51 348	98.64 61	99.93 53	98.91 93	99.85 109	98.88 382

UnsupCasMVSNet_bld		97.30 337	96.92 349	98.45 279	99.28 217	96.78 301	96.20 414	99.27 269	95.42 423	98.28 339	98.30 378	93.16 384	99.71 308	94.99 398	97.37 495	98.87 383

Effi-MVS+		98.02 265	97.82 280	98.62 242	98.53 402	97.19 267	97.33 323	99.68 64	97.30 305	96.68 455	97.46 450	98.56 73	99.80 233	96.63 314	98.20 461	98.86 384

test_0402		98.76 137	98.71 135	98.93 170	99.56 111	98.14 150	98.45 147	99.34 233	99.28 73	98.95 223	98.91 254	98.34 95	99.79 246	95.63 381	99.91 80	98.86 384

PMatch-SfM		97.89 279	97.64 299	98.66 232	99.26 229	97.44 240	96.08 424	99.51 144	96.72 354	98.47 319	99.13 182	93.62 376	99.70 317	97.14 258	98.80 424	98.83 386

PatchmatchNet		95.58 431	95.67 411	95.30 495	97.34 494	87.32 526	97.65 275	96.65 478	95.30 427	97.07 429	98.69 313	84.77 480	99.75 282	94.97 400	98.64 439	98.83 386
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
testing3-2		93.78 470	93.91 461	93.39 519	98.82 344	81.72 548	97.76 257	95.28 504	98.60 168	96.54 462	96.66 473	65.85 539	99.62 377	96.65 313	98.99 409	98.82 388

test_vis1_rt		97.75 298	97.72 290	97.83 351	98.81 347	96.35 323	97.30 327	99.69 57	94.61 448	97.87 374	98.05 404	96.26 274	98.32 511	98.74 107	98.18 462	98.82 388

CL-MVSNet_self_test		97.44 323	97.22 329	98.08 328	98.57 397	95.78 351	94.30 497	98.79 375	96.58 362	98.60 299	98.19 391	94.74 340	99.64 369	96.41 337	98.84 420	98.82 388

miper_ehance_all_eth		97.06 358	97.03 341	97.16 415	97.83 463	93.06 458	94.66 484	99.09 316	95.99 393	98.69 279	98.45 358	92.73 397	99.61 385	96.79 292	99.03 401	98.82 388

MIMVSNet		96.62 380	96.25 397	97.71 366	99.04 291	94.66 407	99.16 55	96.92 472	97.23 317	97.87 374	99.10 191	86.11 466	99.65 364	91.65 489	99.21 378	98.82 388

hse-mvs2		97.46 320	97.07 339	98.64 236	98.73 358	97.33 246	97.45 309	97.64 444	99.11 100	98.58 303	97.98 410	88.65 448	99.79 246	98.11 158	97.39 494	98.81 393

GSMVS																98.81 393

sam_mvs1												84.74 481				98.81 393

SCA		96.41 394	96.66 372	95.67 482	98.24 432	88.35 520	95.85 441	96.88 473	96.11 385	97.67 389	98.67 317	93.10 387	99.85 158	94.16 422	99.22 375	98.81 393

Patchmatch-RL test		97.26 340	97.02 342	97.99 339	99.52 131	95.53 358	96.13 420	99.71 48	97.47 282	99.27 153	99.16 170	84.30 486	99.62 377	97.89 180	99.77 172	98.81 393

AUN-MVS		96.24 405	95.45 422	98.60 248	98.70 368	97.22 263	97.38 316	97.65 442	95.95 395	95.53 494	97.96 415	82.11 500	99.79 246	96.31 343	97.44 491	98.80 398

ITE_SJBPF				98.87 179	99.22 238	98.48 115		99.35 227	97.50 279	98.28 339	98.60 337	97.64 168	99.35 465	93.86 434	99.27 365	98.79 399

tpm		94.67 453	94.34 458	95.66 483	97.68 476	88.42 519	97.88 237	94.90 507	94.46 452	96.03 482	98.56 342	78.66 512	99.79 246	95.88 366	95.01 530	98.78 400

Patchmatch-test		96.55 383	96.34 391	97.17 413	98.35 420	93.06 458	98.40 156	97.79 435	97.33 300	98.41 326	98.67 317	83.68 491	99.69 327	95.16 396	99.31 357	98.77 401

EC-MVSNet		99.09 73	99.05 86	99.20 110	99.28 217	98.93 79	99.24 44	99.84 23	99.08 114	98.12 352	98.37 367	98.72 50	99.90 81	99.05 83	99.77 172	98.77 401

PMMVS		96.51 384	95.98 400	98.09 325	97.53 484	95.84 346	94.92 474	98.84 367	91.58 502	96.05 480	95.58 496	95.68 305	99.66 357	95.59 384	98.09 469	98.76 403

test_method		79.78 510	79.50 513	80.62 528	80.21 553	45.76 556	70.82 544	98.41 415	31.08 548	80.89 548	97.71 430	84.85 479	97.37 527	91.51 493	80.03 544	98.75 404

ab-mvs		98.41 204	98.36 204	98.59 249	99.19 248	97.23 260	99.32 26	98.81 372	97.66 259	98.62 294	99.40 97	96.82 235	99.80 233	95.88 366	99.51 309	98.75 404

ELoFTR		97.81 295	97.74 286	98.04 334	99.39 185	95.79 350	97.28 332	99.58 103	94.13 463	99.38 121	99.37 104	93.31 379	99.60 389	97.23 248	99.96 28	98.74 406

CHOSEN 280x420		95.51 434	95.47 420	95.65 484	98.25 430	88.27 521	93.25 523	98.88 356	93.53 475	94.65 509	97.15 463	86.17 464	99.93 53	97.41 235	99.93 57	98.73 407

test_fmvsmvis_n_1920		99.26 39	99.49 16	98.54 265	99.66 70	96.97 284	98.00 215	99.85 19	99.24 77	99.92 8	99.50 68	99.39 12	99.95 25	99.89 3	99.98 12	98.71 408

MVS_Test		98.18 248	98.36 204	97.67 370	98.48 405	94.73 404	98.18 179	99.02 332	97.69 256	98.04 361	99.11 188	97.22 208	99.56 406	98.57 121	98.90 419	98.71 408

PVSNet	93.40 17	95.67 427	95.70 409	95.57 485	98.83 341	88.57 518	92.50 528	97.72 437	92.69 491	96.49 470	96.44 479	93.72 373	99.43 453	93.61 440	99.28 364	98.71 408

alignmvs		97.35 332	96.88 353	98.78 204	98.54 400	98.09 157	97.71 265	97.69 439	99.20 84	97.59 395	95.90 490	88.12 454	99.55 411	98.18 153	98.96 414	98.70 411

PMatch-Up-SfM		97.79 296	97.48 313	98.72 221	99.03 294	97.78 206	96.05 426	99.48 159	96.90 341	98.72 274	99.18 163	92.00 411	99.71 308	97.15 257	98.77 425	98.69 412

ADS-MVSNet2		95.43 438	94.98 442	96.76 437	98.14 443	91.74 481	97.92 232	97.76 436	90.23 513	96.51 467	98.91 254	85.61 472	99.85 158	92.88 463	96.90 505	98.69 412

ADS-MVSNet		95.24 443	94.93 445	96.18 460	98.14 443	90.10 510	97.92 232	97.32 454	90.23 513	96.51 467	98.91 254	85.61 472	99.74 289	92.88 463	96.90 505	98.69 412

MDTV_nov1_ep13_2view						74.92 552	97.69 268		90.06 518	97.75 385		85.78 471		93.52 445		98.69 412

LoFTR		97.97 273	97.79 282	98.53 267	98.80 350	97.47 235	97.01 349	99.55 126	95.55 415	99.46 101	99.22 152	94.22 359	99.44 451	96.45 334	99.82 133	98.68 416

MSDG		97.71 301	97.52 308	98.28 302	98.91 325	96.82 296	94.42 493	99.37 217	97.65 260	98.37 332	98.29 381	97.40 195	99.33 468	94.09 427	99.22 375	98.68 416

mvsany_test1		97.60 309	97.54 305	97.77 356	97.72 468	95.35 373	95.36 460	97.13 462	94.13 463	99.71 49	99.33 118	97.93 141	99.30 473	97.60 216	98.94 416	98.67 418

CS-MVS		99.13 66	99.10 80	99.24 106	99.06 286	99.15 52	99.36 22	99.88 15	99.36 63	98.21 343	98.46 357	98.68 58	99.93 53	99.03 85	99.85 109	98.64 419

Syy-MVS		96.04 410	95.56 418	97.49 395	97.10 501	94.48 411	96.18 417	96.58 480	95.65 410	94.77 506	92.29 535	91.27 423	99.36 462	98.17 155	98.05 473	98.63 420

myMVS_eth3d		91.92 500	90.45 501	96.30 451	97.10 501	90.90 501	96.18 417	96.58 480	95.65 410	94.77 506	92.29 535	53.88 550	99.36 462	89.59 515	98.05 473	98.63 420

BridgeMVS		98.63 167	98.72 132	98.38 289	98.66 383	96.68 306	98.90 84	99.42 200	98.99 124	98.97 217	99.19 159	95.81 300	99.85 158	98.77 105	99.77 172	98.60 422

miper_enhance_ethall		96.01 412	95.74 407	96.81 434	96.41 526	92.27 477	93.69 514	98.89 355	91.14 509	98.30 335	97.35 457	90.58 430	99.58 401	96.31 343	99.03 401	98.60 422

Effi-MVS+-dtu		98.26 235	97.90 274	99.35 80	98.02 452	99.49 5	98.02 210	99.16 303	98.29 197	97.64 390	97.99 409	96.44 261	99.95 25	96.66 312	98.93 417	98.60 422

new_pmnet		96.99 365	96.76 362	97.67 370	98.72 360	94.89 396	95.95 434	98.20 424	92.62 492	98.55 309	98.54 343	94.88 333	99.52 424	93.96 430	99.44 333	98.59 425

MVSMamba_PlusPlus		98.83 122	98.98 97	98.36 293	99.32 206	96.58 310	98.90 84	99.41 204	99.75 10	98.72 274	99.50 68	96.17 277	99.94 41	99.27 64	99.78 164	98.57 426

testing91		93.32 478	92.27 484	96.47 445	97.54 482	91.25 494	96.17 419	96.76 476	97.18 321	93.65 524	93.50 524	65.11 541	99.63 372	93.04 458	97.45 490	98.53 427

EIA-MVS		98.00 268	97.74 286	98.80 197	98.72 360	98.09 157	98.05 203	99.60 94	97.39 295	96.63 457	95.55 497	97.68 162	99.80 233	96.73 301	99.27 365	98.52 428

PatchMatch-RL		97.24 343	96.78 361	98.61 246	99.03 294	97.83 196	96.36 402	99.06 320	93.49 477	97.36 418	97.78 426	95.75 301	99.49 435	93.44 449	98.77 425	98.52 428

sasdasda		98.34 218	98.26 225	98.58 250	98.46 408	97.82 201	98.96 78	99.46 175	99.19 89	97.46 407	95.46 502	98.59 67	99.46 446	98.08 161	98.71 432	98.46 430

ET-MVSNet_ETH3D		94.30 460	93.21 472	97.58 383	98.14 443	94.47 412	94.78 478	93.24 527	94.72 445	89.56 539	95.87 491	78.57 514	99.81 224	96.91 279	97.11 503	98.46 430

canonicalmvs		98.34 218	98.26 225	98.58 250	98.46 408	97.82 201	98.96 78	99.46 175	99.19 89	97.46 407	95.46 502	98.59 67	99.46 446	98.08 161	98.71 432	98.46 430

UBG		93.25 480	92.32 482	96.04 468	97.72 468	90.16 509	95.92 437	95.91 495	96.03 390	93.95 521	93.04 529	69.60 528	99.52 424	90.72 508	97.98 477	98.45 433

tt0805		98.69 151	98.62 154	98.90 178	99.75 34	99.30 21	99.15 57	96.97 467	98.86 142	98.87 248	97.62 437	98.63 63	98.96 495	99.41 56	98.29 458	98.45 433

TAPA-MVS	96.21 11	96.63 379	95.95 402	98.65 234	98.93 318	98.09 157	96.93 357	99.28 266	83.58 538	98.13 351	97.78 426	96.13 280	99.40 457	93.52 445	99.29 363	98.45 433
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MGCFI-Net		98.34 218	98.28 219	98.51 270	98.47 406	97.59 226	98.96 78	99.48 159	99.18 92	97.40 414	95.50 499	98.66 59	99.50 431	98.18 153	98.71 432	98.44 436

BH-untuned		96.83 371	96.75 364	97.08 417	98.74 357	93.33 455	96.71 372	98.26 420	96.72 354	98.44 323	97.37 455	95.20 321	99.47 442	91.89 484	97.43 492	98.44 436

WB-MVSnew		95.73 426	95.57 417	96.23 457	96.70 516	90.70 506	96.07 425	93.86 522	95.60 412	97.04 432	95.45 506	96.00 287	99.55 411	91.04 500	98.31 456	98.43 438

pmmvs3		95.03 448	94.40 456	96.93 426	97.70 473	92.53 470	95.08 470	97.71 438	88.57 527	97.71 386	98.08 402	79.39 508	99.82 207	96.19 352	99.11 395	98.43 438

DP-MVS Recon		97.33 334	96.92 349	98.57 253	99.09 277	97.99 173	96.79 364	99.35 227	93.18 480	97.71 386	98.07 403	95.00 329	99.31 471	93.97 429	99.13 391	98.42 440

testing99		93.04 484	91.98 492	96.23 457	97.53 484	90.70 506	96.35 403	95.94 494	96.87 344	93.41 525	93.43 526	63.84 543	99.59 394	93.24 454	97.19 500	98.40 441

ETVMVS		92.60 490	91.08 499	97.18 411	97.70 473	93.65 451	96.54 387	95.70 499	96.51 363	94.68 508	92.39 533	61.80 547	99.50 431	86.97 522	97.41 493	98.40 441

Fast-Effi-MVS+-dtu		98.27 233	98.09 248	98.81 194	98.43 413	98.11 153	97.61 285	99.50 149	98.64 161	97.39 416	97.52 444	98.12 126	99.95 25	96.90 284	98.71 432	98.38 443

LF4IMVS		97.90 277	97.69 293	98.52 269	99.17 258	97.66 218	97.19 343	99.47 170	96.31 375	97.85 378	98.20 390	96.71 247	99.52 424	94.62 408	99.72 208	98.38 443

testing11		93.08 483	92.02 489	96.26 454	97.56 480	90.83 503	96.32 405	95.70 499	96.47 368	92.66 529	93.73 521	64.36 542	99.59 394	93.77 437	97.57 484	98.37 445

Fast-Effi-MVS+		97.67 305	97.38 317	98.57 253	98.71 364	97.43 241	97.23 334	99.45 179	94.82 443	96.13 475	96.51 475	98.52 75	99.91 74	96.19 352	98.83 421	98.37 445

test0.0.03 1		94.51 455	93.69 465	96.99 422	96.05 530	93.61 453	94.97 473	93.49 524	96.17 380	97.57 398	94.88 513	82.30 498	99.01 494	93.60 442	94.17 534	98.37 445

UWE-MVS		92.38 493	91.76 496	94.21 507	97.16 499	84.65 535	95.42 458	88.45 543	95.96 394	96.17 474	95.84 493	66.36 535	99.71 308	91.87 485	98.64 439	98.28 448

FE-MVS		95.66 428	94.95 444	97.77 356	98.53 402	95.28 378	99.40 19	96.09 491	93.11 482	97.96 368	99.26 137	79.10 510	99.77 264	92.40 478	98.71 432	98.27 449

baseline2		93.73 471	92.83 478	96.42 447	97.70 473	91.28 493	96.84 363	89.77 541	93.96 471	92.44 531	95.93 489	79.14 509	99.77 264	92.94 460	96.76 509	98.21 450

thisisatest0515		94.12 465	93.16 473	96.97 424	98.60 390	92.90 463	93.77 513	90.61 538	94.10 465	96.91 439	95.87 491	74.99 520	99.80 233	94.52 411	99.12 394	98.20 451

EPMVS		93.72 472	93.27 471	95.09 498	96.04 531	87.76 523	98.13 186	85.01 548	94.69 446	96.92 437	98.64 328	78.47 516	99.31 471	95.04 397	96.46 512	98.20 451

balanced_ft_v1		98.28 232	98.35 207	98.10 323	98.08 449	96.23 327	99.23 45	99.26 275	98.34 188	97.46 407	99.42 89	95.38 318	99.88 115	98.60 117	99.34 350	98.17 453

dp		93.47 475	93.59 467	93.13 522	96.64 517	81.62 549	97.66 273	96.42 484	92.80 490	96.11 476	98.64 328	78.55 515	99.59 394	93.31 451	92.18 539	98.16 454

CNLPA		97.17 350	96.71 366	98.55 260	98.56 398	98.05 168	96.33 404	98.93 345	96.91 340	97.06 430	97.39 453	94.38 352	99.45 449	91.66 488	99.18 385	98.14 455

dmvs_re		95.98 415	95.39 426	97.74 362	98.86 335	97.45 238	98.37 159	95.69 501	97.95 233	96.56 461	95.95 488	90.70 429	97.68 522	88.32 518	96.13 517	98.11 456

HY-MVS	95.94 13	95.90 420	95.35 428	97.55 389	97.95 455	94.79 400	98.81 98	96.94 470	92.28 496	95.17 499	98.57 340	89.90 435	99.75 282	91.20 498	97.33 499	98.10 457

CostFormer		93.97 467	93.78 464	94.51 503	97.53 484	85.83 531	97.98 223	95.96 493	89.29 522	94.99 503	98.63 330	78.63 513	99.62 377	94.54 410	96.50 511	98.09 458

FA-MVS(test-final)		96.99 365	96.82 358	97.50 394	98.70 368	94.78 401	99.34 23	96.99 465	95.07 435	98.48 318	99.33 118	88.41 451	99.65 364	96.13 358	98.92 418	98.07 459

AdaColmap		97.14 352	96.71 366	98.46 278	98.34 421	97.80 205	96.95 354	98.93 345	95.58 414	96.92 437	97.66 433	95.87 298	99.53 420	90.97 502	99.14 389	98.04 460

KD-MVS_2432*1600		92.87 488	91.99 490	95.51 488	91.37 546	89.27 516	94.07 504	98.14 427	95.42 423	97.25 421	96.44 479	67.86 530	99.24 479	91.28 496	96.08 522	98.02 461

miper_refine_blended		92.87 488	91.99 490	95.51 488	91.37 546	89.27 516	94.07 504	98.14 427	95.42 423	97.25 421	96.44 479	67.86 530	99.24 479	91.28 496	96.08 522	98.02 461

TESTMET0.1,1		92.19 497	91.77 495	93.46 516	96.48 524	82.80 545	94.05 506	91.52 537	94.45 455	94.00 519	94.88 513	66.65 534	99.56 406	95.78 374	98.11 468	98.02 461

testing222		91.96 499	90.37 502	96.72 438	97.47 491	92.59 468	96.11 422	94.76 508	96.83 348	92.90 527	92.87 530	57.92 549	99.55 411	86.93 523	97.52 486	98.00 464

PCF-MVS	92.86 18	94.36 457	93.00 476	98.42 283	98.70 368	97.56 227	93.16 525	99.11 313	79.59 542	97.55 399	97.43 451	92.19 405	99.73 296	79.85 539	99.45 326	97.97 465
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS-28		90.22 503	89.28 506	93.02 523	94.50 540	82.87 544	96.52 390	87.51 544	95.21 432	92.36 532	96.04 485	71.57 525	98.25 513	72.04 544	97.77 481	97.94 466

myMVS_eth3d28		92.92 487	92.31 483	94.77 499	97.84 462	87.59 525	96.19 415	96.11 489	97.08 327	94.27 512	93.49 525	66.07 538	98.78 503	91.78 486	97.93 479	97.92 467

OpenMVS	96.65 7	97.09 355	96.68 368	98.32 296	98.32 422	97.16 273	98.86 92	99.37 217	89.48 520	96.29 473	99.15 176	96.56 255	99.90 81	92.90 462	99.20 380	97.89 468

Gipuma		99.03 88	99.16 62	98.64 236	99.94 2	98.51 113	99.32 26	99.75 43	99.58 38	98.60 299	99.62 40	98.22 113	99.51 430	97.70 207	99.73 199	97.89 468
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PVSNet_0	89.98 21	91.15 502	90.30 504	93.70 514	97.72 468	84.34 539	90.24 535	97.42 447	90.20 516	93.79 522	93.09 528	90.90 427	98.89 501	86.57 526	72.76 547	97.87 470

test-LLR		93.90 468	93.85 462	94.04 509	96.53 519	84.62 536	94.05 506	92.39 529	96.17 380	94.12 515	95.07 507	82.30 498	99.67 344	95.87 369	98.18 462	97.82 471

test-mter		92.33 495	91.76 496	94.04 509	96.53 519	84.62 536	94.05 506	92.39 529	94.00 470	94.12 515	95.07 507	65.63 540	99.67 344	95.87 369	98.18 462	97.82 471

tpm2		93.09 482	92.58 481	94.62 502	97.56 480	86.53 528	97.66 273	95.79 498	86.15 534	94.07 517	98.23 388	75.95 518	99.53 420	90.91 504	96.86 508	97.81 473

CR-MVSNet		96.28 400	95.95 402	97.28 406	97.71 471	94.22 417	98.11 191	98.92 349	92.31 495	96.91 439	99.37 104	85.44 475	99.81 224	97.39 236	97.36 497	97.81 473

RPMNet		97.02 361	96.93 347	97.30 405	97.71 471	94.22 417	98.11 191	99.30 254	99.37 60	96.91 439	99.34 115	86.72 459	99.87 135	97.53 223	97.36 497	97.81 473

tpmrst		95.07 447	95.46 421	93.91 511	97.11 500	84.36 538	97.62 280	96.96 468	94.98 437	96.35 472	98.80 285	85.46 474	99.59 394	95.60 383	96.23 515	97.79 476

ALIKED-LG		97.10 353	96.63 374	98.50 274	97.96 454	98.68 99	97.75 260	99.68 64	95.86 399	98.36 334	98.33 375	91.58 416	99.04 489	90.87 506	99.31 357	97.77 477

PAPM		91.88 501	90.34 503	96.51 443	98.06 451	92.56 469	92.44 529	97.17 460	86.35 533	90.38 538	96.01 486	86.61 460	99.21 482	70.65 545	95.43 528	97.75 478

SP-LightGlue		97.22 345	97.01 343	97.88 347	97.33 495	97.19 267	96.38 400	99.08 318	97.28 307	96.53 463	97.50 445	92.36 401	98.70 506	97.84 188	98.76 427	97.74 479

FPMVS		93.44 476	92.23 485	97.08 417	99.25 231	97.86 193	95.61 449	97.16 461	92.90 488	93.76 523	98.65 324	75.94 519	95.66 540	79.30 540	97.49 488	97.73 480

MAR-MVS		96.47 390	95.70 409	98.79 201	97.92 457	99.12 62	98.28 167	98.60 397	92.16 497	95.54 493	96.17 484	94.77 339	99.52 424	89.62 513	98.23 459	97.72 481
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		98.03 264	97.86 277	98.56 258	98.69 373	98.07 164	97.51 299	99.50 149	98.10 223	97.50 404	95.51 498	98.41 85	99.88 115	96.27 348	99.24 371	97.71 482

thres600view7		94.45 456	93.83 463	96.29 452	99.06 286	91.53 485	97.99 222	94.24 518	98.34 188	97.44 412	95.01 509	79.84 504	99.67 344	84.33 530	98.23 459	97.66 483

thres400		94.14 464	93.44 468	96.24 455	98.93 318	91.44 488	97.60 286	94.29 515	97.94 235	97.10 426	94.31 519	79.67 506	99.62 377	83.05 533	98.08 470	97.66 483

IB-MVS	91.63 19	92.24 496	90.90 500	96.27 453	97.22 498	91.24 495	94.36 496	93.33 526	92.37 494	92.24 533	94.58 518	66.20 537	99.89 97	93.16 456	94.63 532	97.66 483
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		95.02 449	95.25 434	94.33 504	96.39 527	85.87 529	98.08 196	96.83 475	95.46 421	95.51 495	98.69 313	85.91 470	99.53 420	94.16 422	96.23 515	97.58 486

cascas		94.79 452	94.33 459	96.15 465	96.02 532	92.36 475	92.34 530	99.26 275	85.34 536	95.08 502	94.96 512	92.96 391	98.53 509	94.41 419	98.59 444	97.56 487

MatchFormer		97.07 357	96.92 349	97.49 395	98.44 411	95.92 341	96.79 364	99.14 309	93.08 483	99.32 144	99.10 191	93.89 367	99.03 490	92.78 468	99.78 164	97.52 488

PatchT		96.65 378	96.35 390	97.54 390	97.40 492	95.32 376	97.98 223	96.64 479	99.33 66	96.89 443	99.42 89	84.32 485	99.81 224	97.69 209	97.49 488	97.48 489

TR-MVS		95.55 432	95.12 440	96.86 433	97.54 482	93.94 437	96.49 392	96.53 482	94.36 458	97.03 434	96.61 474	94.26 358	99.16 485	86.91 524	96.31 514	97.47 490

SP-SuperGlue		97.31 335	97.23 328	97.57 388	96.96 507	97.24 259	96.26 411	98.76 380	97.68 257	96.88 445	97.85 421	94.32 355	98.01 516	97.76 200	98.57 446	97.45 491

dmvs_testset		92.94 486	92.21 486	95.13 496	98.59 393	90.99 500	97.65 275	92.09 531	96.95 334	94.00 519	93.55 523	92.34 403	96.97 532	72.20 543	92.52 537	97.43 492

MonoMVSNet		96.25 403	96.53 383	95.39 491	96.57 518	91.01 499	98.82 97	97.68 441	98.57 174	98.03 362	99.37 104	90.92 426	97.78 521	94.99 398	93.88 535	97.38 493

JIA-IIPM		95.52 433	95.03 441	97.00 421	96.85 511	94.03 429	96.93 357	95.82 496	99.20 84	94.63 510	99.71 22	83.09 494	99.60 389	94.42 416	94.64 531	97.36 494

SP-MNN		96.46 391	96.24 398	97.10 416	96.71 515	95.98 338	96.00 428	97.33 453	95.82 403	94.93 504	97.10 467	93.70 374	98.01 516	96.30 345	98.30 457	97.30 495

MASt3R-SfM		96.02 411	95.82 405	96.60 441	97.03 506	94.90 395	94.26 499	98.53 405	88.40 529	98.41 326	98.67 317	92.39 400	97.62 524	95.31 391	99.41 338	97.29 496

ALIKED-MNN		95.97 417	95.30 432	98.00 337	97.66 478	98.12 152	96.98 352	99.41 204	91.11 510	94.04 518	97.30 458	91.56 417	98.61 508	89.99 511	99.63 263	97.28 497

BH-w/o		95.13 446	94.89 446	95.86 475	98.20 436	91.31 491	95.65 448	97.37 448	93.64 473	96.52 466	95.70 495	93.04 390	99.02 492	88.10 519	95.82 525	97.24 498

tpm cat1		93.29 479	93.13 475	93.75 513	97.39 493	84.74 534	97.39 314	97.65 442	83.39 539	94.16 514	98.41 362	82.86 496	99.39 459	91.56 492	95.35 529	97.14 499

SP-NN		94.67 453	94.44 455	95.36 493	95.12 537	95.23 382	94.27 498	96.10 490	94.46 452	90.91 536	95.76 494	91.47 420	93.87 544	95.23 394	96.62 510	97.00 500

SP-DiffGlue		96.87 369	96.76 362	97.21 410	95.17 536	96.88 294	96.12 421	98.93 345	96.51 363	98.37 332	97.55 440	93.65 375	97.83 519	96.11 359	98.45 451	96.92 501

xiu_mvs_v1_base_debu		97.86 285	98.17 239	96.92 427	98.98 310	93.91 439	96.45 394	99.17 300	97.85 243	98.41 326	97.14 464	98.47 77	99.92 65	98.02 168	99.05 397	96.92 501

xiu_mvs_v1_base		97.86 285	98.17 239	96.92 427	98.98 310	93.91 439	96.45 394	99.17 300	97.85 243	98.41 326	97.14 464	98.47 77	99.92 65	98.02 168	99.05 397	96.92 501

xiu_mvs_v1_base_debi		97.86 285	98.17 239	96.92 427	98.98 310	93.91 439	96.45 394	99.17 300	97.85 243	98.41 326	97.14 464	98.47 77	99.92 65	98.02 168	99.05 397	96.92 501

PMVS	91.26 20	97.86 285	97.94 268	97.65 374	99.71 49	97.94 183	98.52 130	98.68 390	98.99 124	97.52 402	99.35 111	97.41 194	98.18 514	91.59 491	99.67 245	96.82 505
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
0.4-1-1-0.1		88.42 505	85.91 508	95.94 471	93.08 542	91.54 484	90.99 534	92.04 533	89.96 519	84.83 545	83.25 544	63.75 544	99.52 424	93.25 453	82.07 541	96.75 506

1314		95.74 425	95.60 414	96.17 461	97.53 484	92.75 467	98.07 200	98.31 418	91.22 507	94.25 513	96.68 472	95.53 310	99.03 490	91.64 490	97.18 501	96.74 507

MVS-HIRNet		94.32 458	95.62 412	90.42 527	98.46 408	75.36 551	96.29 407	89.13 542	95.25 430	95.38 496	99.75 16	92.88 392	99.19 483	94.07 428	99.39 341	96.72 508

OpenMVS_ROB	95.38 14	95.84 423	95.18 439	97.81 353	98.41 417	97.15 274	97.37 320	98.62 396	83.86 537	98.65 286	98.37 367	94.29 357	99.68 339	88.41 517	98.62 443	96.60 509

ALIKED-NN		94.29 461	93.41 470	96.94 425	96.18 529	97.66 218	94.90 475	98.68 390	88.85 525	90.43 537	96.81 470	89.82 436	96.59 537	86.67 525	98.33 453	96.58 510

0.3-1-1-0.015		87.27 507	84.50 511	95.57 485	91.70 545	90.77 504	89.41 540	92.04 533	88.98 523	82.46 547	81.35 545	60.36 548	99.50 431	92.96 459	81.23 543	96.45 511

0.4-1-1-0.2		87.49 506	84.89 509	95.31 494	91.33 548	90.08 511	88.47 541	92.07 532	88.70 526	84.06 546	81.08 546	63.62 545	99.49 435	92.93 461	81.71 542	96.37 512

thres100view900		94.19 462	93.67 466	95.75 479	99.06 286	91.35 490	98.03 207	94.24 518	98.33 190	97.40 414	94.98 511	79.84 504	99.62 377	83.05 533	98.08 470	96.29 513

tfpn200view9		94.03 466	93.44 468	95.78 478	98.93 318	91.44 488	97.60 286	94.29 515	97.94 235	97.10 426	94.31 519	79.67 506	99.62 377	83.05 533	98.08 470	96.29 513

MVS		93.19 481	92.09 487	96.50 444	96.91 509	94.03 429	98.07 200	98.06 431	68.01 545	94.56 511	96.48 477	95.96 294	99.30 473	83.84 531	96.89 507	96.17 515

gg-mvs-nofinetune		92.37 494	91.20 498	95.85 476	95.80 535	92.38 474	99.31 30	81.84 550	99.75 10	91.83 534	99.74 18	68.29 529	99.02 492	87.15 521	97.12 502	96.16 516

xiu_mvs_v2_base		97.16 351	97.49 310	96.17 461	98.54 400	92.46 471	95.45 456	98.84 367	97.25 311	97.48 406	96.49 476	98.31 97	99.90 81	96.34 342	98.68 437	96.15 517

PS-MVSNAJ		97.08 356	97.39 316	96.16 463	98.56 398	92.46 471	95.24 465	98.85 366	97.25 311	97.49 405	95.99 487	98.07 128	99.90 81	96.37 339	98.67 438	96.12 518

E-PMN		94.17 463	94.37 457	93.58 515	96.86 510	85.71 532	90.11 537	97.07 463	98.17 213	97.82 381	97.19 461	84.62 482	98.94 496	89.77 512	97.68 483	96.09 519

EMVS		93.83 469	94.02 460	93.23 521	96.83 512	84.96 533	89.77 538	96.32 485	97.92 237	97.43 413	96.36 482	86.17 464	98.93 497	87.68 520	97.73 482	95.81 520

MVE	83.40 22	92.50 491	91.92 493	94.25 505	98.83 341	91.64 483	92.71 526	83.52 549	95.92 396	86.46 544	95.46 502	95.20 321	95.40 541	80.51 538	98.64 439	95.73 521
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
thres200		93.72 472	93.14 474	95.46 490	98.66 383	91.29 492	96.61 383	94.63 510	97.39 295	96.83 447	93.71 522	79.88 503	99.56 406	82.40 536	98.13 467	95.54 522

GLUNet-SfM		86.26 508	84.68 510	91.01 526	80.58 552	83.56 540	78.04 543	93.59 523	76.70 543	95.29 498	94.72 516	77.51 517	94.26 543	66.39 546	99.33 352	95.20 523

API-MVS		97.04 360	96.91 352	97.42 401	97.88 459	98.23 143	98.18 179	98.50 408	97.57 269	97.39 416	96.75 471	96.77 240	99.15 486	90.16 510	99.02 404	94.88 524

GG-mvs-BLEND				94.76 500	94.54 539	92.13 479	99.31 30	80.47 551		88.73 542	91.01 541	67.59 533	98.16 515	82.30 537	94.53 533	93.98 525

SIFT-PointCN		96.45 392	96.47 385	96.39 448	98.13 446	97.54 229	93.31 522	97.23 458	94.67 447	98.68 282	98.32 376	94.64 342	97.81 520	93.50 447	99.77 172	93.83 526

XFeat-MNN		93.41 477	92.98 477	94.68 501	92.63 543	92.92 462	89.72 539	95.81 497	92.10 498	97.23 423	96.29 483	84.95 478	97.31 529	89.60 514	98.54 448	93.81 527

SIFT-ConvMatch		96.57 381	96.62 375	96.43 446	98.20 436	98.27 136	93.88 510	96.88 473	95.29 428	98.88 243	98.25 384	95.18 323	97.43 526	93.22 455	99.83 126	93.59 528

SIFT-NCM-Cal		96.56 382	96.68 368	96.20 459	98.27 429	98.44 118	94.40 494	96.67 477	95.29 428	97.63 391	98.17 392	96.40 263	96.59 537	93.61 440	99.66 253	93.57 529

SIFT-MNN		95.92 419	95.97 401	95.74 481	98.18 438	98.00 171	94.17 501	96.99 465	95.74 408	97.16 424	97.90 417	90.71 428	95.79 539	93.71 438	99.21 378	93.44 530

SIFT-NN-PointCN		96.06 408	96.11 399	95.91 473	97.88 459	97.73 213	93.49 518	97.51 446	93.22 479	96.57 460	98.26 383	96.23 275	96.60 536	92.54 475	99.27 365	93.40 531

DeepMVS_CX				93.44 518	98.24 432	94.21 419		94.34 514	64.28 546	91.34 535	94.87 515	89.45 442	92.77 545	77.54 541	93.14 536	93.35 532

SIFT-NN-CMatch		95.63 430	95.48 419	96.08 467	98.24 432	98.00 171	92.71 526	94.29 515	94.20 461	95.85 483	97.26 459	95.72 303	97.01 530	91.99 482	99.02 404	93.23 533

SIFT-NN		92.96 485	92.79 479	93.46 516	96.92 508	96.45 319	91.89 532	94.39 513	92.91 487	92.54 530	95.46 502	88.26 452	90.71 547	85.22 528	97.52 486	93.22 534

SIFT-PCN-Cal		96.34 395	96.46 387	96.01 470	98.17 440	96.89 292	93.48 519	97.35 452	94.84 442	99.35 130	98.30 378	94.70 341	97.92 518	92.03 481	99.88 95	93.21 535

SIFT-UM-Cal		96.49 387	96.62 375	96.12 466	98.13 446	97.89 190	93.35 521	98.44 410	95.48 420	98.63 290	98.34 371	95.45 315	97.45 525	92.22 480	99.50 317	93.02 536

SIFT-CM-Cal		96.28 400	96.31 393	96.16 463	98.39 418	98.11 153	93.46 520	96.47 483	94.81 444	98.49 316	98.43 360	94.48 346	97.34 528	92.60 474	99.70 227	93.02 536

SIFT-UMatch		96.33 396	96.47 385	95.89 474	98.29 425	97.95 181	93.84 511	97.24 457	95.78 406	98.72 274	98.04 405	93.45 378	96.81 533	93.14 457	99.73 199	92.91 538

SIFT-NN-NCMNet		95.39 439	95.22 436	95.92 472	98.29 425	98.34 131	93.58 517	94.60 511	94.07 467	94.84 505	97.53 441	94.37 353	96.62 535	91.01 501	98.64 439	92.80 539

SIFT-NCMNet		96.30 398	96.40 389	96.03 469	97.80 466	97.68 217	92.34 530	96.94 470	95.55 415	98.84 253	98.63 330	94.17 360	97.63 523	93.57 444	99.71 217	92.77 540

SIFT-NN-UMatch		95.38 440	95.26 433	95.75 479	98.25 430	97.78 206	93.24 524	95.66 503	94.01 469	95.10 501	97.47 449	93.12 385	96.78 534	92.42 477	98.04 475	92.69 541

XFeat-NN		89.63 504	89.13 507	91.14 525	90.93 549	90.02 512	84.90 542	94.05 521	88.10 530	92.89 528	93.33 527	78.74 511	90.89 546	83.46 532	95.72 526	92.52 542

tmp_tt		78.77 511	78.73 514	78.90 529	58.45 554	74.76 553	94.20 500	78.26 552	39.16 547	86.71 543	92.82 531	80.50 502	75.19 549	86.16 527	92.29 538	86.74 543

dongtai		76.24 512	75.95 515	77.12 530	92.39 544	67.91 554	90.16 536	59.44 555	82.04 540	89.42 540	94.67 517	49.68 552	81.74 548	48.06 547	77.66 545	81.72 544

kuosan		69.30 513	68.95 516	70.34 531	87.68 551	65.00 555	91.11 533	59.90 554	69.02 544	74.46 549	88.89 543	48.58 553	68.03 550	28.61 548	72.33 548	77.99 545

wuyk23d		96.06 408	97.62 302	91.38 524	98.65 387	98.57 107	98.85 93	96.95 469	96.86 347	99.90 14	99.16 170	99.18 19	98.40 510	89.23 516	99.77 172	77.18 546

test123		17.04 516	20.11 519	7.82 532	10.25 556	4.91 557	94.80 477	4.47 557	4.93 550	10.00 552	24.28 549	9.69 554	3.64 551	10.14 549	12.43 550	14.92 547

testmvs		17.12 515	20.53 518	6.87 533	12.05 555	4.20 558	93.62 516	6.73 556	4.62 551	10.41 551	24.33 548	8.28 555	3.56 552	9.69 550	15.07 549	12.86 548

mmdepth		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

monomultidepth		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

test_blank		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

uanet_test		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

DCPMVS		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

cdsmvs_eth3d_5k		24.66 514	32.88 517	0.00 534	0.00 557	0.00 559	0.00 545	99.10 314	0.00 552	0.00 553	97.58 438	99.21 18	0.00 553	0.00 551	0.00 551	0.00 549

pcd_1.5k_mvsjas		8.17 517	10.90 520	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	98.07 128	0.00 553	0.00 551	0.00 551	0.00 549

sosnet-low-res		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

sosnet		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

uncertanet		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

Regformer		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

ab-mvs-re		8.12 518	10.83 521	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	97.48 447	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

uanet		0.00 519	0.00 522	0.00 534	0.00 557	0.00 559	0.00 545	0.00 558	0.00 552	0.00 553	0.00 552	0.00 556	0.00 553	0.00 551	0.00 551	0.00 549

WAC-MVS						90.90 501								91.37 495

FOURS1					99.73 38	99.67 2	99.43 15	99.54 132	99.43 54	99.26 157

test_one_0601					99.39 185	99.20 38		99.31 246	98.49 180	98.66 285	99.02 213	97.64 168

eth-test2					0.00 557

eth-test					0.00 557

ZD-MVS					99.01 305	98.84 85		99.07 319	94.10 465	98.05 360	98.12 397	96.36 269	99.86 144	92.70 471	99.19 383

test_241102_ONE					99.49 150	99.17 43		99.31 246	97.98 230	99.66 60	98.90 257	98.36 90	99.48 439

9.14			97.78 283		99.07 281		97.53 296	99.32 241	95.53 418	98.54 311	98.70 311	97.58 175	99.76 270	94.32 421	99.46 324

save fliter					99.11 272	97.97 177	96.53 389	99.02 332	98.24 200

test0726					99.50 141	99.21 32	98.17 182	99.35 227	97.97 231	99.26 157	99.06 200	97.61 172

test_part2					99.36 194	99.10 65				99.05 200

sam_mvs												84.29 487

MTGPA								99.20 288

test_post1							97.59 288				20.48 551	83.07 495	99.66 357	94.16 422

test_post											21.25 550	83.86 490	99.70 317

patchmatchnet-post											98.77 291	84.37 484	99.85 158

MTMP							97.93 229	91.91 536

gm-plane-assit					94.83 538	81.97 547			88.07 531		94.99 510		99.60 389	91.76 487

TEST9					98.71 364	98.08 161	95.96 432	99.03 329	91.40 505	95.85 483	97.53 441	96.52 257	99.76 270

test_8					98.67 378	98.01 170	95.91 438	99.02 332	91.64 500	95.79 486	97.50 445	96.47 259	99.76 270

agg_prior					98.68 377	97.99 173		99.01 335		95.59 487			99.77 264

test_prior4						97.97 177	95.86 439

test_prior2							95.74 446		96.48 367	96.11 476	97.63 436	95.92 297		94.16 422	99.20 380

旧先验2							95.76 445		88.56 528	97.52 402			99.66 357	94.48 412

新几何2							95.93 435

原ACMM2							95.53 452

testdata2													99.79 246	92.80 467

segment_acmp												97.02 221

testdata1							95.44 457		96.32 374

plane_prior7					99.19 248	97.87 192

plane_prior6					98.99 309	97.70 216						94.90 330

plane_prior4											97.98 410

plane_prior3						97.78 206			97.41 292	97.79 382

plane_prior2							97.77 254		98.20 209

plane_prior1					99.05 289

plane_prior						97.65 220	97.07 347		96.72 354						99.36 345

n2								0.00 558

nn								0.00 558

door-mid								99.57 111

test11								98.87 358

door								99.41 204

HQP5-MVS						96.79 298

HQP-NCC					98.67 378		96.29 407		96.05 387	95.55 490

ACMP_Plane					98.67 378		96.29 407		96.05 387	95.55 490

BP-MVS														92.82 465

HQP3-MVS								99.04 327							99.26 369

HQP2-MVS												93.84 368

NP-MVS					98.84 339	97.39 243					96.84 468

MDTV_nov1_ep13			95.22 436		97.06 503	83.20 543	97.74 262	96.16 487	94.37 457	96.99 435	98.83 278	83.95 489	99.53 420	93.90 431	97.95 478

ACMMP++_ref															99.77 172

ACMMP++															99.68 239

Test By Simon												96.52 257

High-resolution multi-view benchmark