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		95.28 97	95.82 80	93.66 181	96.42 230	83.08 249	97.35 12	99.28 2	96.44 28	96.20 135	99.65 2	84.10 301	98.01 291	94.06 66	98.93 140	99.87 1

LCM-MVSNet		99.43 1	99.49 1	99.24 1	99.95 1	98.13 1	99.37 1	99.57 1	99.82 1	99.86 1	99.85 1	99.52 1	99.73 1	97.58 1	99.94 1	99.85 2

mmtdpeth		95.82 69	96.02 65	95.23 103	96.91 180	88.62 117	96.49 44	99.26 3	95.07 49	93.41 275	99.29 7	90.25 204	97.27 358	94.49 55	99.01 126	99.80 3

PS-CasMVS		96.69 27	97.43 9	94.49 144	99.13 6	84.09 227	96.61 37	97.97 104	97.91 8	98.64 16	98.13 45	95.24 44	99.65 4	93.39 95	99.84 3	99.72 4

fmvsm_s_conf0.1_n_2		94.38 144	94.78 133	93.19 208	97.07 167	81.72 276	91.97 267	97.51 167	87.05 275	97.31 66	97.92 67	88.29 237	98.15 268	97.10 6	98.81 160	99.70 5

CP-MVSNet		96.19 52	96.80 23	94.38 149	98.99 19	83.82 230	96.31 61	97.53 164	97.60 10	98.34 22	97.52 100	91.98 152	99.63 7	93.08 108	99.81 8	99.70 5

FC-MVSNet-test		95.32 93	95.88 74	93.62 183	98.49 65	81.77 273	95.90 81	98.32 39	93.93 69	97.53 50	97.56 95	88.48 233	99.40 51	92.91 113	99.83 5	99.68 7

PEN-MVS		96.69 27	97.39 12	94.61 133	99.16 4	84.50 216	96.54 39	98.05 89	98.06 7	98.64 16	98.25 42	95.01 59	99.65 4	92.95 112	99.83 5	99.68 7

WR-MVS_H		96.60 32	97.05 20	95.24 102	99.02 13	86.44 175	96.78 28	98.08 82	97.42 12	98.48 19	97.86 73	91.76 158	99.63 7	94.23 63	99.84 3	99.66 9

test_djsdf		96.62 30	96.49 33	97.01 35	98.55 53	91.77 62	97.15 15	97.37 176	88.98 213	98.26 26	98.86 15	93.35 109	99.60 9	96.41 18	99.45 48	99.66 9

v7n		96.82 16	97.31 14	95.33 96	98.54 55	86.81 163	96.83 24	98.07 85	96.59 25	98.46 20	98.43 37	92.91 127	99.52 19	96.25 21	99.76 10	99.65 11

UA-Net		97.35 4	97.24 15	97.69 5	98.22 83	93.87 33	98.42 6	98.19 61	96.95 18	95.46 182	99.23 9	93.45 104	99.57 14	95.34 45	99.89 2	99.63 12

DTE-MVSNet		96.74 24	97.43 9	94.67 130	99.13 6	84.68 215	96.51 41	97.94 112	98.14 6	98.67 15	98.32 39	95.04 56	99.69 3	93.27 100	99.82 7	99.62 13

FIs		94.90 114	95.35 102	93.55 187	98.28 78	81.76 274	95.33 106	98.14 72	93.05 88	97.07 80	97.18 140	87.65 252	99.29 81	91.72 152	99.69 17	99.61 14

UniMVSNet_ETH3D		97.13 10	97.72 3	95.35 94	99.51 2	87.38 146	97.70 8	97.54 161	98.16 5	98.94 3	99.33 6	97.84 4	99.08 110	90.73 181	99.73 14	99.59 15

PS-MVSNAJss		96.01 58	96.04 63	95.89 71	98.82 30	88.51 123	95.57 97	97.88 119	88.72 221	98.81 9	98.86 15	90.77 191	99.60 9	95.43 40	99.53 39	99.57 16

anonymousdsp		96.74 24	96.42 36	97.68 7	98.00 102	94.03 28	96.97 19	97.61 152	87.68 259	98.45 21	98.77 20	94.20 88	99.50 23	96.70 13	99.40 61	99.53 17

ANet_high		94.83 117	96.28 47	90.47 348	96.65 202	73.16 432	94.33 150	98.74 13	96.39 30	98.09 33	98.93 13	93.37 108	98.70 180	90.38 192	99.68 20	99.53 17

tt0320-xc		97.00 12	97.67 5	94.98 112	98.89 23	86.94 160	96.72 31	98.46 25	98.28 4	98.86 7	99.43 4	96.80 10	98.51 219	91.79 148	99.76 10	99.50 19

Anonymous20231211		96.60 32	97.13 19	95.00 111	97.46 143	86.35 179	97.11 18	98.24 54	97.58 11	98.72 11	98.97 12	93.15 116	99.15 98	93.18 103	99.74 13	99.50 19

tt0320		96.97 13	97.64 6	94.96 114	98.89 23	86.86 162	96.85 23	98.45 26	98.29 3	98.88 6	99.45 3	96.48 13	98.54 212	91.73 151	99.72 15	99.47 21

OurMVSNet-221017-0		96.80 19	96.75 24	96.96 38	99.03 12	91.85 60	97.98 7	98.01 99	94.15 64	98.93 4	99.07 10	88.07 242	99.57 14	95.86 27	99.69 17	99.46 22

sc_t1		97.21 9	97.71 4	95.71 78	99.06 10	88.89 111	96.72 31	97.79 135	98.34 2	98.97 2	99.40 5	96.81 9	98.79 159	92.58 126	99.72 15	99.45 23

fmvsm_s_conf0.5_n_2		94.25 156	94.63 145	93.10 211	96.65 202	81.75 275	91.72 285	97.25 191	86.93 279	97.20 74	97.67 86	88.44 235	98.14 271	97.06 9	98.77 169	99.42 24

pmmvs6		96.80 19	97.36 13	95.15 108	99.12 8	87.82 139	96.68 33	97.86 122	96.10 36	98.14 30	99.28 8	97.94 3	98.21 258	91.38 164	99.69 17	99.42 24

v10		94.68 125	95.27 109	92.90 222	96.57 214	80.15 303	94.65 138	97.57 158	90.68 169	97.43 56	98.00 55	88.18 239	99.15 98	94.84 51	99.55 37	99.41 26

mvs_tets		96.83 15	96.71 25	97.17 30	98.83 29	92.51 51	96.58 38	97.61 152	87.57 261	98.80 10	98.90 14	96.50 12	99.59 13	96.15 22	99.47 44	99.40 27

v8		94.65 126	95.29 107	92.74 231	96.65 202	79.77 319	94.59 139	97.17 197	91.86 121	97.47 55	97.93 62	88.16 240	99.08 110	94.32 60	99.47 44	99.38 28

TranMVSNet+NR-MVSNet		96.07 57	96.26 48	95.50 87	98.26 80	87.69 141	93.75 177	97.86 122	95.96 41	97.48 54	97.14 145	95.33 40	99.44 33	90.79 179	99.76 10	99.38 28

nrg030		96.32 47	96.55 32	95.62 81	97.83 113	88.55 122	95.77 86	98.29 45	92.68 91	98.03 34	97.91 70	95.13 49	98.95 134	93.85 72	99.49 43	99.36 30

WR-MVS		93.49 188	93.72 185	92.80 228	97.57 136	80.03 309	90.14 341	95.68 290	93.70 74	96.62 107	95.39 286	87.21 261	99.04 120	87.50 286	99.64 25	99.33 31

jajsoiax		96.59 34	96.42 36	97.12 32	98.76 35	92.49 52	96.44 48	97.42 173	86.96 276	98.71 13	98.72 22	95.36 38	99.56 17	95.92 25	99.45 48	99.32 32

LTVRE_ROB	93.87 1	97.93 2	98.16 2	97.26 29	98.81 32	93.86 34	99.07 2	98.98 8	97.01 17	98.92 5	98.78 19	95.22 46	98.61 194	96.85 11	99.77 9	99.31 33
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
UniMVSNet_NR-MVSNet		95.35 91	95.21 110	95.76 75	97.69 127	88.59 120	92.26 258	97.84 126	94.91 52	96.80 97	95.78 261	90.42 200	99.41 43	91.60 156	99.58 33	99.29 34

Elysia		96.00 59	96.36 41	94.91 116	98.01 100	85.96 191	95.29 110	97.90 114	95.31 45	98.14 30	97.28 128	88.82 228	99.51 20	97.08 7	99.38 63	99.26 35

StellarMVS		96.00 59	96.36 41	94.91 116	98.01 100	85.96 191	95.29 110	97.90 114	95.31 45	98.14 30	97.28 128	88.82 228	99.51 20	97.08 7	99.38 63	99.26 35

DU-MVS		95.28 97	95.12 118	95.75 76	97.75 119	88.59 120	92.58 235	97.81 131	93.99 66	96.80 97	95.90 251	90.10 211	99.41 43	91.60 156	99.58 33	99.26 35

NR-MVSNet		95.28 97	95.28 108	95.26 100	97.75 119	87.21 150	95.08 120	97.37 176	93.92 71	97.65 42	95.90 251	90.10 211	99.33 76	90.11 210	99.66 23	99.26 35

Baseline_NR-MVSNet		94.47 140	95.09 122	92.60 243	98.50 64	80.82 294	92.08 262	96.68 244	93.82 72	96.29 127	98.56 29	90.10 211	97.75 323	90.10 212	99.66 23	99.24 39

v1921920		93.26 199	93.61 193	92.19 263	96.04 277	78.31 363	91.88 276	97.24 193	85.17 320	96.19 138	96.19 233	86.76 272	99.05 117	94.18 64	98.84 152	99.22 40

v1192		93.49 188	93.78 183	92.62 241	96.16 261	79.62 323	91.83 280	97.22 195	86.07 294	96.10 142	96.38 214	87.22 260	99.02 122	94.14 65	98.88 147	99.22 40

v1240		93.29 197	93.71 188	92.06 271	96.01 278	77.89 369	91.81 281	97.37 176	85.12 322	96.69 102	96.40 209	86.67 273	99.07 116	94.51 54	98.76 171	99.22 40

dcpmvs_2		93.96 171	95.01 124	90.82 337	97.60 133	74.04 427	93.68 181	98.85 9	89.80 194	97.82 36	97.01 159	91.14 182	99.21 91	90.56 185	98.59 199	99.19 43

v144192		93.20 206	93.54 197	92.16 267	96.05 273	78.26 364	91.95 268	97.14 199	84.98 327	95.96 147	96.11 241	87.08 264	99.04 120	93.79 73	98.84 152	99.17 44

TestfortrainingZip a		95.98 62	96.18 52	95.38 92	98.69 37	87.60 143	96.32 56	98.58 18	88.79 218	97.38 63	96.22 228	95.11 51	99.39 54	95.41 42	99.10 110	99.16 45

UniMVSNet (Re)		95.32 93	95.15 112	95.80 74	97.79 117	88.91 110	92.91 217	98.07 85	93.46 80	96.31 125	95.97 250	90.14 208	99.34 71	92.11 135	99.64 25	99.16 45

SixPastTwentyTwo		94.91 112	95.21 110	93.98 162	98.52 57	83.19 244	95.93 79	94.84 321	94.86 53	98.49 18	98.74 21	81.45 331	99.60 9	94.69 52	99.39 62	99.15 47

v2v482		93.29 197	93.63 191	92.29 256	96.35 240	78.82 351	91.77 284	96.28 267	88.45 232	95.70 169	96.26 225	86.02 282	98.90 138	93.02 109	98.81 160	99.14 48

fmvsm_s_conf0.5_n_4		94.26 152	94.58 147	93.31 201	96.40 232	82.73 260	92.59 234	97.41 174	86.60 280	96.33 122	97.07 152	89.91 215	98.07 281	96.88 10	98.01 271	99.13 49

v1144		93.50 187	93.81 180	92.57 244	96.28 248	79.61 324	91.86 279	96.96 213	86.95 277	95.91 151	96.32 218	87.65 252	98.96 132	93.51 84	98.88 147	99.13 49

HPM-MVS		96.81 18	96.62 29	97.36 26	98.89 23	93.53 41	97.51 10	98.44 27	92.35 102	95.95 148	96.41 208	96.71 11	99.42 37	93.99 69	99.36 66	99.13 49
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
patch_mono-2		92.46 238	92.72 226	91.71 285	96.65 202	78.91 348	88.85 380	97.17 197	83.89 340	92.45 322	96.76 179	89.86 217	97.09 371	90.24 203	98.59 199	99.12 52

MP-MVS-pluss		96.08 56	95.92 71	96.57 47	99.06 10	91.21 68	93.25 197	98.32 39	87.89 251	96.86 92	97.38 114	95.55 30	99.39 54	95.47 38	99.47 44	99.11 53
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
LPG-MVS_test		96.38 46	96.23 49	96.84 41	98.36 75	92.13 55	95.33 106	98.25 46	91.78 129	97.07 80	97.22 136	96.38 16	99.28 85	92.07 138	99.59 29	99.11 53

LGP-MVS_train				96.84 41	98.36 75	92.13 55		98.25 46	91.78 129	97.07 80	97.22 136	96.38 16	99.28 85	92.07 138	99.59 29	99.11 53

MIMVSNet1		95.52 82	95.45 94	95.72 77	99.14 5	89.02 108	96.23 68	96.87 226	93.73 73	97.87 35	98.49 33	90.73 195	99.05 117	86.43 309	99.60 27	99.10 56

VPA-MVSNet		95.14 104	95.67 86	93.58 186	97.76 118	83.15 245	94.58 141	97.58 157	93.39 81	97.05 83	98.04 52	93.25 112	98.51 219	89.75 222	99.59 29	99.08 57

TransMVSNet (Re)		95.27 100	96.04 63	92.97 215	98.37 72	81.92 272	95.07 121	96.76 236	93.97 68	97.77 38	98.57 28	95.72 24	97.90 300	88.89 248	99.23 94	99.08 57

SSC-MVS		90.16 303	92.96 214	81.78 466	97.88 110	48.48 499	90.75 317	87.69 431	96.02 40	96.70 101	97.63 90	85.60 289	97.80 314	85.73 317	98.60 198	99.06 59

MP-MVS		96.14 53	95.68 85	97.51 16	98.81 32	94.06 24	96.10 72	97.78 137	92.73 90	93.48 273	96.72 185	94.23 87	99.42 37	91.99 141	99.29 83	99.05 60
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
EI-MVSNet-UG-set		94.35 148	94.27 165	94.59 137	92.46 405	85.87 195	92.42 245	94.69 328	93.67 77	96.13 139	95.84 255	91.20 178	98.86 145	93.78 74	98.23 244	99.03 61

ACMMP		96.61 31	96.34 43	97.43 21	98.61 45	93.88 32	96.95 20	98.18 63	92.26 105	96.33 122	96.84 174	95.10 54	99.40 51	93.47 88	99.33 73	99.02 62
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
ACMMPR		96.46 38	96.14 56	97.41 23	98.60 46	93.82 36	96.30 65	97.96 106	92.35 102	95.57 175	96.61 194	94.93 64	99.41 43	93.78 74	99.15 106	99.00 63

PGM-MVS		96.32 47	95.94 68	97.43 21	98.59 48	93.84 35	95.33 106	98.30 42	91.40 149	95.76 160	96.87 170	95.26 43	99.45 32	92.77 117	99.21 98	99.00 63

MTAPA		96.65 29	96.38 40	97.47 18	98.95 21	94.05 26	95.88 82	97.62 150	94.46 59	96.29 127	96.94 162	93.56 99	99.37 66	94.29 62	99.42 54	98.99 65

pm-mvs1		95.43 86	95.94 68	93.93 167	98.38 70	85.08 211	95.46 102	97.12 203	91.84 125	97.28 70	98.46 35	95.30 42	97.71 327	90.17 208	99.42 54	98.99 65

mPP-MVS		96.46 38	96.05 62	97.69 5	98.62 43	94.65 16	96.45 46	97.74 139	92.59 94	95.47 180	96.68 188	94.50 81	99.42 37	93.10 106	99.26 90	98.99 65

TDRefinement		97.68 3	97.60 8	97.93 2	99.02 13	95.95 8	98.61 3	98.81 10	97.41 13	97.28 70	98.46 35	94.62 76	98.84 148	94.64 53	99.53 39	98.99 65

fmvsm_s_conf0.5_n_9		95.58 80	95.91 72	94.59 137	97.25 154	86.26 181	92.96 210	97.86 122	91.88 120	97.52 51	98.13 45	91.45 169	98.54 212	97.17 4	98.99 127	98.98 69

fmvsm_s_conf0.1_n		94.19 161	94.41 154	93.52 192	97.22 158	84.37 217	93.73 178	95.26 309	84.45 334	95.76 160	98.00 55	91.85 154	97.21 362	95.62 31	97.82 287	98.98 69

EI-MVSNet-Vis-set		94.36 147	94.28 163	94.61 133	92.55 402	85.98 190	92.44 243	94.69 328	93.70 74	96.12 140	95.81 257	91.24 175	98.86 145	93.76 77	98.22 248	98.98 69

NormalMVS		94.10 163	93.36 203	96.31 55	99.01 15	90.84 76	94.70 134	97.90 114	90.98 158	93.22 289	95.73 264	78.94 351	99.12 104	90.38 192	99.42 54	98.97 72

KinetiMVS		95.09 106	95.40 99	94.15 155	97.42 146	84.35 219	93.91 172	96.69 241	94.41 60	96.67 103	97.25 131	87.67 251	99.14 100	95.78 29	98.81 160	98.97 72

MM		94.41 143	94.14 169	95.22 105	95.84 289	87.21 150	94.31 152	90.92 407	94.48 58	92.80 309	97.52 100	85.27 291	99.49 29	96.58 17	99.57 35	98.97 72

ZNCC-MVS		96.42 42	96.20 51	97.07 33	98.80 34	92.79 49	96.08 73	98.16 70	91.74 133	95.34 189	96.36 216	95.68 25	99.44 33	94.41 59	99.28 88	98.97 72

MED-MVS test				95.52 85	98.69 37	88.21 129	96.32 56	98.58 18	88.79 218	97.38 63	96.22 228		99.39 54	92.89 114	99.10 110	98.96 76

MED-MVS		96.11 54	96.31 45	95.52 85	98.69 37	88.21 129	96.32 56	98.58 18	92.48 96	97.38 63	96.22 228	95.11 51	99.39 54	92.89 114	99.10 110	98.96 76

ME-MVS		95.61 77	95.65 87	95.49 88	97.62 132	88.21 129	94.21 157	97.87 121	92.48 96	96.38 118	96.22 228	94.06 92	99.32 77	92.89 114	99.10 110	98.96 76

IS-MVSNet		94.49 139	94.35 160	94.92 115	98.25 82	86.46 174	97.13 17	94.31 336	96.24 34	96.28 129	96.36 216	82.88 313	99.35 68	88.19 269	99.52 41	98.96 76

ACMM	88.83 9	96.30 49	96.07 61	96.97 37	98.39 69	92.95 47	94.74 131	98.03 96	90.82 164	97.15 76	96.85 171	96.25 18	99.00 124	93.10 106	99.33 73	98.95 80
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.1_n_a		94.26 152	94.37 157	93.95 166	97.36 149	85.72 199	94.15 159	95.44 302	83.25 348	95.51 177	98.05 50	92.54 136	97.19 365	95.55 36	97.46 311	98.94 81

region2R		96.41 43	96.09 58	97.38 25	98.62 43	93.81 38	96.32 56	97.96 106	92.26 105	95.28 194	96.57 197	95.02 58	99.41 43	93.63 78	99.11 109	98.94 81

SMA-MVS		95.77 71	95.54 91	96.47 52	98.27 79	91.19 69	95.09 119	97.79 135	86.48 283	97.42 59	97.51 104	94.47 84	99.29 81	93.55 82	99.29 83	98.93 83
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
XVS		96.49 36	96.18 52	97.44 19	98.56 49	93.99 29	96.50 42	97.95 109	94.58 55	94.38 239	96.49 201	94.56 79	99.39 54	93.57 80	99.05 119	98.93 83

X-MVStestdata		90.70 282	88.45 335	97.44 19	98.56 49	93.99 29	96.50 42	97.95 109	94.58 55	94.38 239	26.89 498	94.56 79	99.39 54	93.57 80	99.05 119	98.93 83

VPNet		93.08 209	93.76 184	91.03 322	98.60 46	75.83 409	91.51 290	95.62 291	91.84 125	95.74 165	97.10 150	89.31 222	98.32 244	85.07 331	99.06 116	98.93 83

APDe-MVS		96.46 38	96.64 28	95.93 66	97.68 128	89.38 101	96.90 21	98.41 30	92.52 95	97.43 56	97.92 67	95.11 51	99.50 23	94.45 57	99.30 80	98.92 87
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
HPM-MVS_fast		97.01 11	96.89 21	97.39 24	99.12 8	93.92 31	97.16 14	98.17 67	93.11 86	96.48 112	97.36 118	96.92 6	99.34 71	94.31 61	99.38 63	98.92 87

test1111		90.39 294	90.61 291	89.74 368	98.04 97	71.50 445	95.59 93	79.72 487	89.41 202	95.94 149	98.14 44	70.79 412	98.81 155	88.52 262	99.32 77	98.90 89

test_0728_THIRD									93.26 84	97.40 61	97.35 121	94.69 73	99.34 71	93.88 70	99.42 54	98.89 90

MSP-MVS		95.34 92	94.63 145	97.48 17	98.67 40	94.05 26	96.41 50	98.18 63	91.26 152	95.12 209	95.15 290	86.60 275	99.50 23	93.43 94	96.81 343	98.89 90
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
GST-MVS		96.24 50	95.99 66	97.00 36	98.65 41	92.71 50	95.69 90	98.01 99	92.08 113	95.74 165	96.28 222	95.22 46	99.42 37	93.17 104	99.06 116	98.88 92

EI-MVSNet		92.99 213	93.26 208	92.19 263	92.12 417	79.21 342	92.32 252	94.67 330	91.77 131	95.24 199	95.85 253	87.14 263	98.49 221	91.99 141	98.26 240	98.86 93

IterMVS-LS		93.78 177	94.28 163	92.27 257	96.27 251	79.21 342	91.87 277	96.78 233	91.77 131	96.57 111	97.07 152	87.15 262	98.74 170	91.99 141	99.03 125	98.86 93
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH	88.36 12	96.59 34	97.43 9	94.07 160	98.56 49	85.33 207	96.33 54	98.30 42	94.66 54	98.72 11	98.30 40	97.51 5	98.00 293	94.87 50	99.59 29	98.86 93
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
V42		93.43 191	93.58 194	92.97 215	95.34 324	81.22 287	92.67 229	96.49 258	87.25 267	96.20 135	96.37 215	87.32 258	98.85 147	92.39 132	98.21 249	98.85 96

lecture		97.32 6	97.64 6	96.33 54	99.01 15	90.77 79	96.90 21	98.60 16	96.30 33	97.74 40	98.00 55	96.87 8	99.39 54	95.95 24	99.42 54	98.84 97

test_fmvs3		92.42 239	92.40 239	92.46 254	93.80 378	87.28 148	93.86 174	97.05 207	76.86 423	96.25 130	98.66 23	82.87 314	91.26 469	95.44 39	96.83 342	98.82 98

SteuartSystems-ACMMP		96.40 44	96.30 46	96.71 43	98.63 42	91.96 58	95.70 88	98.01 99	93.34 83	96.64 106	96.57 197	94.99 60	99.36 67	93.48 87	99.34 71	98.82 98
Skip Steuart: Steuart Systems R&D Blog.
fmvsm_s_conf0.5_n_3		95.20 101	95.95 67	92.94 219	96.60 212	82.18 269	93.13 202	98.39 33	91.44 147	97.16 75	97.68 84	93.03 124	97.82 311	97.54 2	98.63 194	98.81 100

VDDNet		94.03 167	94.27 165	93.31 201	98.87 26	82.36 265	95.51 101	91.78 398	97.19 15	96.32 124	98.60 27	84.24 299	98.75 167	87.09 294	98.83 157	98.81 100

ACMMP_NAP		96.21 51	96.12 57	96.49 51	98.90 22	91.42 66	94.57 142	98.03 96	90.42 179	96.37 120	97.35 121	95.68 25	99.25 88	94.44 58	99.34 71	98.80 102

RPSCF		95.58 80	94.89 127	97.62 8	97.58 135	96.30 7	95.97 78	97.53 164	92.42 98	93.41 275	97.78 75	91.21 177	97.77 319	91.06 173	97.06 330	98.80 102

E5new		94.50 134	95.15 112	92.55 245	97.04 168	80.27 299	92.96 210	98.25 46	90.18 183	95.77 157	97.45 108	94.85 68	98.59 199	91.16 168	98.73 179	98.79 104

E6new		94.50 134	95.15 112	92.55 245	97.04 168	80.28 297	92.96 210	98.25 46	90.18 183	95.76 160	97.45 108	94.86 66	98.59 199	91.16 168	98.73 179	98.79 104

E6		94.50 134	95.15 112	92.55 245	97.04 168	80.28 297	92.96 210	98.25 46	90.18 183	95.76 160	97.45 108	94.86 66	98.59 199	91.16 168	98.73 179	98.79 104

E5		94.50 134	95.15 112	92.55 245	97.04 168	80.27 299	92.96 210	98.25 46	90.18 183	95.77 157	97.45 108	94.85 68	98.59 199	91.16 168	98.73 179	98.79 104

fmvsm_s_conf0.5_n_11		94.91 112	95.44 96	93.33 200	96.45 226	83.11 248	93.56 186	98.64 14	89.76 195	95.70 169	97.97 59	92.32 142	98.08 277	95.62 31	98.95 138	98.79 104

WB-MVS		89.44 322	92.15 248	81.32 467	97.73 122	48.22 500	89.73 355	87.98 429	95.24 47	96.05 143	96.99 160	85.18 292	96.95 379	82.45 364	97.97 276	98.78 109

Anonymous20240529		95.50 83	95.83 78	94.50 142	97.33 151	85.93 193	95.19 118	96.77 235	96.64 23	97.61 46	98.05 50	93.23 113	98.79 159	88.60 259	99.04 124	98.78 109

v148		92.87 219	93.29 204	91.62 289	96.25 254	77.72 375	91.28 298	95.05 314	89.69 196	95.93 150	96.04 244	87.34 257	98.38 236	90.05 213	97.99 274	98.78 109

ACMP	88.15 13	95.71 74	95.43 97	96.54 48	98.17 86	91.73 63	94.24 154	98.08 82	89.46 201	96.61 108	96.47 202	95.85 22	99.12 104	90.45 189	99.56 36	98.77 112
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous20240521		92.86 220	93.57 195	90.74 339	96.57 214	75.50 411	94.15 159	95.60 292	89.38 203	95.90 152	97.90 72	80.39 341	97.96 297	92.60 125	99.68 20	98.75 113

KD-MVS_self_test		94.10 163	94.73 137	92.19 263	97.66 130	79.49 331	94.86 128	97.12 203	89.59 200	96.87 91	97.65 88	90.40 202	98.34 243	89.08 243	99.35 67	98.75 113

APD-MVS_3200maxsize		96.82 16	96.65 27	97.32 28	97.95 106	93.82 36	96.31 61	98.25 46	95.51 44	96.99 87	97.05 155	95.63 27	99.39 54	93.31 97	98.88 147	98.75 113

lessismore_v0				93.87 170	98.05 94	83.77 231		80.32 485		97.13 77	97.91 70	77.49 366	99.11 108	92.62 123	98.08 262	98.74 116

K. test v3		93.37 193	93.27 207	93.66 181	98.05 94	82.62 261	94.35 149	86.62 440	96.05 38	97.51 52	98.85 17	76.59 383	99.65 4	93.21 102	98.20 251	98.73 117

MSC_two_6792asdad				95.90 69	96.54 217	89.57 94		96.87 226					99.41 43	94.06 66	99.30 80	98.72 118

No_MVS				95.90 69	96.54 217	89.57 94		96.87 226					99.41 43	94.06 66	99.30 80	98.72 118

ACMH+	88.43 11	96.48 37	96.82 22	95.47 89	98.54 55	89.06 107	95.65 91	98.61 15	96.10 36	98.16 29	97.52 100	96.90 7	98.62 193	90.30 199	99.60 27	98.72 118

MGCNet		92.88 217	92.27 243	94.69 128	92.35 408	86.03 189	92.88 219	89.68 415	90.53 175	91.52 347	96.43 205	82.52 321	99.32 77	95.01 48	99.54 38	98.71 121

SDMVSNet		94.43 142	95.02 123	92.69 234	97.93 107	82.88 253	91.92 272	95.99 283	93.65 78	95.51 177	98.63 25	94.60 77	96.48 398	87.57 285	99.35 67	98.70 122

sd_testset		93.94 172	94.39 155	92.61 242	97.93 107	83.24 240	93.17 201	95.04 315	93.65 78	95.51 177	98.63 25	94.49 82	95.89 418	81.72 372	99.35 67	98.70 122

OPM-MVS		95.61 77	95.45 94	96.08 58	98.49 65	91.00 71	92.65 231	97.33 184	90.05 189	96.77 99	96.85 171	95.04 56	98.56 209	92.77 117	99.06 116	98.70 122
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
FE-MVSNET2		94.07 166	94.47 153	92.90 222	97.45 145	81.26 285	93.58 185	97.54 161	88.28 239	96.46 114	97.92 67	91.41 170	98.74 170	88.12 273	99.44 51	98.69 125

fmvsm_s_conf0.5_n		94.00 169	94.20 167	93.42 197	96.69 199	84.37 217	93.38 194	95.13 313	84.50 333	95.40 184	97.55 99	91.77 156	97.20 363	95.59 33	97.79 288	98.69 125

test2506		85.42 398	84.57 401	87.96 404	97.81 115	66.53 468	96.14 70	56.35 501	89.04 211	93.55 270	98.10 47	42.88 494	98.68 184	88.09 275	99.18 102	98.67 127

ECVR-MVS		90.12 305	90.16 300	90.00 364	97.81 115	72.68 438	95.76 87	78.54 490	89.04 211	95.36 188	98.10 47	70.51 414	98.64 190	87.10 293	99.18 102	98.67 127

viewmacassd2359aftdt		93.83 175	94.36 159	92.24 260	96.45 226	79.58 328	91.60 287	97.96 106	89.14 210	95.05 214	97.09 151	93.69 97	98.48 226	89.79 219	98.43 216	98.65 129

casdiffmvs_mvg		95.10 105	95.62 88	93.53 190	96.25 254	83.23 241	92.66 230	98.19 61	93.06 87	97.49 53	97.15 144	94.78 71	98.71 179	92.27 133	98.72 183	98.65 129
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GBi-Net		93.21 204	92.96 214	93.97 163	95.40 320	84.29 220	95.99 75	96.56 253	88.63 223	95.10 210	98.53 30	81.31 333	98.98 126	86.74 297	98.38 224	98.65 129

test1		93.21 204	92.96 214	93.97 163	95.40 320	84.29 220	95.99 75	96.56 253	88.63 223	95.10 210	98.53 30	81.31 333	98.98 126	86.74 297	98.38 224	98.65 129

FMVSNet1		94.84 116	95.13 117	93.97 163	97.60 133	84.29 220	95.99 75	96.56 253	92.38 99	97.03 84	98.53 30	90.12 209	98.98 126	88.78 253	99.16 105	98.65 129

EPP-MVSNet		93.91 173	93.68 190	94.59 137	98.08 91	85.55 203	97.44 11	94.03 343	94.22 63	94.94 219	96.19 233	82.07 325	99.57 14	87.28 291	98.89 145	98.65 129

fmvsm_s_conf0.5_n_a		94.02 168	94.08 172	93.84 172	96.72 197	85.73 198	93.65 184	95.23 311	83.30 346	95.13 208	97.56 95	92.22 146	97.17 366	95.51 37	97.41 313	98.64 135

IU-MVS					98.51 58	86.66 169		96.83 230	72.74 452	95.83 155				93.00 110	99.29 83	98.64 135

SF-MVS		95.88 67	95.88 74	95.87 72	98.12 88	89.65 93	95.58 96	98.56 21	91.84 125	96.36 121	96.68 188	94.37 85	99.32 77	92.41 131	99.05 119	98.64 135

casdiffmvs		94.32 150	94.80 130	92.85 225	96.05 273	81.44 283	92.35 249	98.05 89	91.53 141	95.75 164	96.80 175	93.35 109	98.49 221	91.01 176	98.32 233	98.64 135
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TSAR-MVS + MP.		94.96 111	94.75 134	95.57 83	98.86 27	88.69 114	96.37 51	96.81 231	85.23 318	94.75 227	97.12 147	91.85 154	99.40 51	93.45 90	98.33 231	98.62 139
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
E4		94.00 169	94.53 151	92.42 255	96.78 193	79.99 311	91.33 297	98.16 70	89.69 196	95.27 195	97.16 141	93.94 95	98.64 190	89.99 214	98.42 218	98.61 140

HQP_MVS		94.26 152	93.93 178	95.23 103	97.71 124	88.12 132	94.56 143	97.81 131	91.74 133	93.31 280	95.59 271	86.93 268	98.95 134	89.26 235	98.51 209	98.60 141

plane_prior5								97.81 131					98.95 134	89.26 235	98.51 209	98.60 141

CP-MVS		96.44 41	96.08 60	97.54 14	98.29 77	94.62 17	96.80 26	98.08 82	92.67 93	95.08 213	96.39 213	94.77 72	99.42 37	93.17 104	99.44 51	98.58 143

SSC-MVS3.2		89.88 314	91.06 277	86.31 434	95.90 285	63.76 482	82.68 473	92.43 384	91.42 148	92.37 328	94.58 320	86.34 277	96.60 394	84.35 342	99.50 42	98.57 144

BP-MVS1		91.77 259	91.10 276	93.75 176	96.42 230	83.40 236	94.10 163	91.89 395	91.27 151	93.36 279	94.85 304	64.43 443	99.29 81	94.88 49	98.74 177	98.56 145

tttt0517		89.81 316	88.90 326	92.55 245	97.00 174	79.73 322	95.03 123	83.65 466	89.88 192	95.30 191	94.79 309	53.64 472	99.39 54	91.99 141	98.79 167	98.54 146

test_0728_SECOND				94.88 119	98.55 53	86.72 166	95.20 116	98.22 58					99.38 64	93.44 91	99.31 78	98.53 147

reproduce_model		97.35 4	97.24 15	97.70 4	98.44 67	95.08 11	95.88 82	98.50 22	96.62 24	98.27 23	97.93 62	94.57 78	99.50 23	95.57 35	99.35 67	98.52 148

viewdifsd2359ckpt07		93.63 180	94.33 161	91.55 292	96.19 259	77.86 370	90.11 344	97.74 139	90.76 166	96.11 141	96.61 194	94.37 85	98.27 250	88.82 251	98.23 244	98.51 149

test_vis3_rt		90.40 292	90.03 304	91.52 295	92.58 400	88.95 109	90.38 333	97.72 142	73.30 447	97.79 37	97.51 104	77.05 373	87.10 487	89.03 244	94.89 403	98.50 150

SR-MVS		96.70 26	96.42 36	97.54 14	98.05 94	94.69 14	96.13 71	98.07 85	95.17 48	96.82 96	96.73 184	95.09 55	99.43 36	92.99 111	98.71 185	98.50 150

test_241102_TWO								98.10 79	91.95 115	97.54 48	97.25 131	95.37 36	99.35 68	93.29 98	99.25 91	98.49 152

HFP-MVS		96.39 45	96.17 55	97.04 34	98.51 58	93.37 42	96.30 65	97.98 102	92.35 102	95.63 172	96.47 202	95.37 36	99.27 87	93.78 74	99.14 107	98.48 153

3Dnovator+	92.74 2	95.86 68	95.77 82	96.13 57	96.81 189	90.79 78	96.30 65	97.82 130	96.13 35	94.74 228	97.23 134	91.33 172	99.16 97	93.25 101	98.30 237	98.46 154

XVG-OURS-SEG-HR		95.38 90	95.00 125	96.51 49	98.10 90	94.07 23	92.46 241	98.13 73	90.69 168	93.75 261	96.25 226	98.03 2	97.02 376	92.08 137	95.55 378	98.45 155

ttmdpeth		86.91 389	86.57 381	87.91 408	89.68 463	74.24 424	91.49 291	87.09 436	79.84 392	89.46 396	97.86 73	65.42 437	91.04 470	81.57 374	96.74 348	98.44 156

baseline		94.26 152	94.80 130	92.64 236	96.08 270	80.99 291	93.69 180	98.04 95	90.80 165	94.89 222	96.32 218	93.19 114	98.48 226	91.68 154	98.51 209	98.43 157

E2		93.53 185	93.96 175	92.25 258	96.39 233	79.76 320	91.06 307	98.05 89	88.58 228	94.71 231	96.64 190	93.08 119	98.57 205	89.16 239	97.97 276	98.42 158

E3		93.53 185	93.96 175	92.25 258	96.39 233	79.76 320	91.06 307	98.05 89	88.58 228	94.71 231	96.64 190	93.07 121	98.57 205	89.16 239	97.97 276	98.42 158

fmvsm_l_conf0.5_n_3		95.19 102	95.36 101	94.68 129	96.79 192	87.49 144	93.05 205	98.38 34	87.21 269	96.59 109	97.76 80	94.20 88	98.11 272	95.90 26	98.40 219	98.42 158

viewdifsd2359ckpt11		93.36 194	93.99 173	91.48 296	95.50 316	78.39 359	90.47 327	96.69 241	88.59 226	96.03 145	96.88 168	93.48 102	97.63 333	90.20 206	98.07 263	98.41 161

viewmsd2359difaftdt		93.36 194	93.99 173	91.48 296	95.50 316	78.39 359	90.47 327	96.69 241	88.59 226	96.03 145	96.88 168	93.48 102	97.63 333	90.20 206	98.07 263	98.41 161

DPE-MVS		95.89 66	95.88 74	95.92 68	97.93 107	89.83 91	93.46 190	98.30 42	92.37 100	97.75 39	96.95 161	95.14 48	99.51 20	91.74 150	99.28 88	98.41 161
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
AstraMVS		92.75 225	92.73 224	92.79 229	97.02 172	81.48 282	92.88 219	90.62 411	87.99 248	96.48 112	96.71 186	82.02 326	98.48 226	92.44 130	98.46 214	98.40 164

fmvsm_s_conf0.5_n_8		94.70 123	95.34 103	92.78 230	96.77 194	81.50 281	92.64 232	98.50 22	91.51 144	97.22 73	97.93 62	88.07 242	98.45 230	96.62 16	98.80 164	98.39 165

viewmanbaseed2359cas		93.08 209	93.43 201	92.01 274	95.69 301	79.29 338	91.15 301	97.70 143	87.45 263	94.18 245	96.12 240	92.31 143	98.37 240	88.58 260	97.73 291	98.38 166

reproduce-ours		97.28 7	97.19 17	97.57 11	98.37 72	94.84 12	95.57 97	98.40 31	96.36 31	98.18 27	97.78 75	95.47 32	99.50 23	95.26 46	99.33 73	98.36 167

our_new_method		97.28 7	97.19 17	97.57 11	98.37 72	94.84 12	95.57 97	98.40 31	96.36 31	98.18 27	97.78 75	95.47 32	99.50 23	95.26 46	99.33 73	98.36 167

tfpnnormal		94.27 151	94.87 128	92.48 252	97.71 124	80.88 293	94.55 145	95.41 305	93.70 74	96.67 103	97.72 81	91.40 171	98.18 262	87.45 287	99.18 102	98.36 167

GDP-MVS		91.56 265	90.83 284	93.77 175	96.34 241	83.65 232	93.66 182	98.12 75	87.32 266	92.98 303	94.71 312	63.58 449	99.30 80	92.61 124	98.14 255	98.35 170

VDD-MVS		94.37 146	94.37 157	94.40 148	97.49 140	86.07 188	93.97 169	93.28 364	94.49 57	96.24 131	97.78 75	87.99 246	98.79 159	88.92 246	99.14 107	98.34 171

XVG-ACMP-BASELINE		95.68 75	95.34 103	96.69 44	98.40 68	93.04 44	94.54 146	98.05 89	90.45 178	96.31 125	96.76 179	92.91 127	98.72 173	91.19 167	99.42 54	98.32 172

CNVR-MVS		94.58 130	94.29 162	95.46 90	96.94 177	89.35 102	91.81 281	96.80 232	89.66 198	93.90 258	95.44 280	92.80 131	98.72 173	92.74 119	98.52 207	98.32 172

fmvsm_s_conf0.5_n_7		93.61 182	93.94 177	92.63 239	96.11 267	82.76 258	90.81 314	97.55 160	86.57 281	93.14 295	97.69 83	90.17 207	96.83 387	94.46 56	98.93 140	98.31 174

COLMAP_ROB	91.06 5	96.75 23	96.62 29	97.13 31	98.38 70	94.31 20	96.79 27	98.32 39	96.69 21	96.86 92	97.56 95	95.48 31	98.77 166	90.11 210	99.44 51	98.31 174
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
XVG-OURS		94.72 121	94.12 170	96.50 50	98.00 102	94.23 21	91.48 292	98.17 67	90.72 167	95.30 191	96.47 202	87.94 247	96.98 377	91.41 163	97.61 302	98.30 176

viewcassd2359sk11		93.16 207	93.51 199	92.13 269	96.07 271	79.59 325	90.88 311	97.97 104	87.82 253	94.23 242	96.19 233	92.31 143	98.53 216	88.58 260	97.51 306	98.28 177

EPNet		89.80 317	88.25 344	94.45 146	83.91 494	86.18 185	93.87 173	87.07 438	91.16 156	80.64 481	94.72 311	78.83 353	98.89 140	85.17 324	98.89 145	98.28 177
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsmconf0.01_n		95.90 65	96.09 58	95.31 99	97.30 153	89.21 103	94.24 154	98.76 12	86.25 288	97.56 47	98.66 23	95.73 23	98.44 232	97.35 3	98.99 127	98.27 179

reproduce_monomvs		87.13 384	86.90 373	87.84 410	90.92 446	68.15 460	91.19 300	93.75 353	85.84 302	94.21 244	95.83 256	42.99 491	97.10 370	89.46 227	97.88 284	98.26 180

VortexMVS		92.13 252	92.56 233	90.85 335	94.54 356	76.17 402	92.30 255	96.63 248	86.20 290	96.66 105	96.79 176	79.87 344	98.16 266	91.27 166	98.76 171	98.24 181

GeoE		94.55 131	94.68 142	94.15 155	97.23 156	85.11 210	94.14 161	97.34 183	88.71 222	95.26 196	95.50 276	94.65 75	99.12 104	90.94 177	98.40 219	98.23 182

NCCC		94.08 165	93.54 197	95.70 80	96.49 223	89.90 90	92.39 247	96.91 219	90.64 170	92.33 332	94.60 318	90.58 199	98.96 132	90.21 205	97.70 296	98.23 182

LuminaMVS		93.43 191	93.18 209	94.16 154	97.32 152	85.29 208	93.36 195	93.94 348	88.09 246	97.12 78	96.43 205	80.11 342	98.98 126	93.53 83	98.76 171	98.21 184

XXY-MVS		92.58 233	93.16 211	90.84 336	97.75 119	79.84 315	91.87 277	96.22 273	85.94 296	95.53 176	97.68 84	92.69 133	94.48 444	83.21 352	97.51 306	98.21 184

guyue		92.60 231	92.62 230	92.52 251	96.73 195	81.00 290	93.00 207	91.83 397	88.28 239	96.38 118	96.23 227	80.71 339	98.37 240	92.06 140	98.37 229	98.20 186

CDPH-MVS		92.67 228	91.83 258	95.18 107	96.94 177	88.46 125	90.70 320	97.07 206	77.38 417	92.34 331	95.08 296	92.67 134	98.88 141	85.74 316	98.57 201	98.20 186

test_fmvsmconf0.1_n		95.61 77	95.72 84	95.26 100	96.85 185	89.20 104	93.51 188	98.60 16	85.68 307	97.42 59	98.30 40	95.34 39	98.39 233	96.85 11	98.98 129	98.19 188

testf1		96.77 21	96.49 33	97.60 9	99.01 15	96.70 3	96.31 61	98.33 37	94.96 50	97.30 67	97.93 62	96.05 20	97.90 300	89.32 229	99.23 94	98.19 188

APD_test2		96.77 21	96.49 33	97.60 9	99.01 15	96.70 3	96.31 61	98.33 37	94.96 50	97.30 67	97.93 62	96.05 20	97.90 300	89.32 229	99.23 94	98.19 188

E3new		92.83 221	93.10 212	92.04 272	95.78 295	79.45 332	90.76 316	97.90 114	87.23 268	93.79 260	95.70 267	91.55 162	98.49 221	88.17 271	96.99 337	98.16 191

new-patchmatchnet		88.97 337	90.79 287	83.50 459	94.28 363	55.83 495	85.34 451	93.56 359	86.18 292	95.47 180	95.73 264	83.10 310	96.51 397	85.40 321	98.06 265	98.16 191

viewdifsd2359ckpt09		92.60 231	92.34 242	93.36 198	95.94 283	83.36 237	92.35 249	97.93 113	83.17 352	92.92 306	94.66 315	89.87 216	98.57 205	86.51 307	97.71 295	98.15 193

HQP4-MVS										88.81 406			98.61 194			98.15 193

HQP-MVS		92.09 253	91.49 266	93.88 169	96.36 237	84.89 213	91.37 293	97.31 185	87.16 270	88.81 406	93.40 363	84.76 296	98.60 197	86.55 305	97.73 291	98.14 195

DVP-MVS		95.82 69	96.18 52	94.72 126	98.51 58	86.69 167	95.20 116	97.00 210	91.85 122	97.40 61	97.35 121	95.58 28	99.34 71	93.44 91	99.31 78	98.13 196
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
ambc				92.98 214	96.88 182	83.01 251	95.92 80	96.38 263		96.41 117	97.48 106	88.26 238	97.80 314	89.96 216	98.93 140	98.12 197

test_fmvsmconf_n		95.43 86	95.50 92	95.22 105	96.48 225	89.19 105	93.23 199	98.36 36	85.61 310	96.92 90	98.02 54	95.23 45	98.38 236	96.69 14	98.95 138	98.09 198

fmvsm_s_conf0.5_n_6		94.14 162	94.54 150	92.95 217	96.51 221	82.74 259	92.71 227	98.13 73	86.56 282	96.44 115	96.85 171	88.51 232	98.05 284	96.03 23	99.09 114	98.06 199

eth_miper_zixun_eth		90.72 281	90.61 291	91.05 321	92.04 420	76.84 390	86.91 419	96.67 245	85.21 319	94.41 237	93.92 347	79.53 347	98.26 251	89.76 221	97.02 332	98.06 199

FMVSNet2		92.78 223	92.73 224	92.95 217	95.40 320	81.98 271	94.18 158	95.53 300	88.63 223	96.05 143	97.37 115	81.31 333	98.81 155	87.38 290	98.67 191	98.06 199

OMC-MVS		94.22 158	93.69 189	95.81 73	97.25 154	91.27 67	92.27 257	97.40 175	87.10 274	94.56 234	95.42 281	93.74 96	98.11 272	86.62 302	98.85 151	98.06 199

DVP-MVS++		95.93 63	96.34 43	94.70 127	96.54 217	86.66 169	98.45 4	98.22 58	93.26 84	97.54 48	97.36 118	93.12 117	99.38 64	93.88 70	98.68 189	98.04 203

PC_three_1452									75.31 434	95.87 154	95.75 263	92.93 126	96.34 408	87.18 292	98.68 189	98.04 203

c3_l		91.32 272	91.42 267	91.00 325	92.29 410	76.79 391	87.52 406	96.42 261	85.76 305	94.72 230	93.89 349	82.73 317	98.16 266	90.93 178	98.55 202	98.04 203

EG-PatchMatch MVS		94.54 132	94.67 143	94.14 157	97.87 112	86.50 171	92.00 266	96.74 237	88.16 245	96.93 89	97.61 91	93.04 123	97.90 300	91.60 156	98.12 257	98.03 206

MVS_111021_HR		93.63 180	93.42 202	94.26 152	96.65 202	86.96 159	89.30 369	96.23 271	88.36 238	93.57 269	94.60 318	93.45 104	97.77 319	90.23 204	98.38 224	98.03 206

SR-MVS-dyc-post		96.84 14	96.60 31	97.56 13	98.07 92	95.27 9	96.37 51	98.12 75	95.66 42	97.00 85	97.03 156	94.85 68	99.42 37	93.49 85	98.84 152	98.00 208

RE-MVS-def			96.66 26		98.07 92	95.27 9	96.37 51	98.12 75	95.66 42	97.00 85	97.03 156	95.40 35		93.49 85	98.84 152	98.00 208

thisisatest0530		88.69 346	87.52 358	92.20 262	96.33 243	79.36 336	92.81 221	84.01 465	86.44 284	93.67 266	92.68 382	53.62 473	99.25 88	89.65 224	98.45 215	98.00 208

Vis-MVSNet (Re-imp)		90.42 291	90.16 300	91.20 316	97.66 130	77.32 380	94.33 150	87.66 432	91.20 154	92.99 301	95.13 292	75.40 388	98.28 246	77.86 410	99.19 100	97.99 211

SSM_0404		94.38 144	94.69 138	93.43 196	97.16 161	83.23 241	93.95 170	97.84 126	91.46 145	95.70 169	96.56 199	92.50 140	99.08 110	88.83 249	98.23 244	97.98 212

agg_prior2														87.06 295	98.36 230	97.98 212

AllTest		94.88 115	94.51 152	96.00 59	98.02 98	92.17 53	95.26 112	98.43 28	90.48 176	95.04 215	96.74 182	92.54 136	97.86 308	85.11 329	98.98 129	97.98 212

TestCases				96.00 59	98.02 98	92.17 53		98.43 28	90.48 176	95.04 215	96.74 182	92.54 136	97.86 308	85.11 329	98.98 129	97.98 212

SymmetryMVS		93.26 199	92.36 241	95.97 61	97.13 164	90.84 76	94.70 134	91.61 401	90.98 158	93.22 289	95.73 264	78.94 351	99.12 104	90.38 192	98.53 205	97.97 216

MVSTER		89.32 324	88.75 329	91.03 322	90.10 459	76.62 397	90.85 312	94.67 330	82.27 367	95.24 199	95.79 258	61.09 459	98.49 221	90.49 188	98.26 240	97.97 216

SED-MVS		96.00 59	96.41 39	94.76 124	98.51 58	86.97 157	95.21 114	98.10 79	91.95 115	97.63 43	97.25 131	96.48 13	99.35 68	93.29 98	99.29 83	97.95 218

OPU-MVS				95.15 108	96.84 186	89.43 98	95.21 114				95.66 269	93.12 117	98.06 283	86.28 312	98.61 196	97.95 218

MVStest1		84.79 404	84.06 407	86.98 420	77.73 501	74.76 414	91.08 306	85.63 450	77.70 415	96.86 92	97.97 59	41.05 498	88.24 485	92.22 134	96.28 358	97.94 220

mamba_0408		93.60 183	93.72 185	93.27 204	96.65 202	82.79 255	88.81 383	97.68 144	90.62 172	95.19 203	96.01 246	91.54 166	99.08 110	88.63 257	98.32 233	97.93 221

SSM_04072		93.25 202	93.72 185	91.84 278	96.65 202	82.79 255	88.81 383	97.68 144	90.62 172	95.19 203	96.01 246	91.54 166	94.81 440	88.63 257	98.32 233	97.93 221

SSM_0407		94.23 157	94.56 149	93.24 206	96.65 202	82.79 255	93.66 182	97.84 126	91.46 145	95.19 203	96.56 199	92.50 140	98.99 125	88.83 249	98.32 233	97.93 221

test_prior				94.61 133	95.95 281	87.23 149		97.36 181					98.68 184			97.93 221

DeepC-MVS	91.39 4	95.43 86	95.33 105	95.71 78	97.67 129	90.17 87	93.86 174	98.02 98	87.35 264	96.22 133	97.99 58	94.48 83	99.05 117	92.73 120	99.68 20	97.93 221
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
usedtu_dtu_shiyan2		93.15 208	92.40 239	95.41 91	98.56 49	90.53 83	94.71 133	94.14 341	92.10 112	93.73 264	96.94 162	89.66 219	97.77 319	72.97 451	98.81 160	97.92 226

RRT-MVS		92.28 245	93.01 213	90.07 360	94.06 370	73.01 434	95.36 103	97.88 119	92.24 107	95.16 206	97.52 100	78.51 359	99.29 81	90.55 186	95.83 372	97.92 226

UGNet		93.08 209	92.50 235	94.79 123	93.87 375	87.99 135	95.07 121	94.26 339	90.64 170	87.33 434	97.67 86	86.89 270	98.49 221	88.10 274	98.71 185	97.91 228
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
CANet		92.38 241	91.99 252	93.52 192	93.82 377	83.46 235	91.14 302	97.00 210	89.81 193	86.47 438	94.04 341	87.90 248	99.21 91	89.50 226	98.27 239	97.90 229

HPM-MVS++		95.02 108	94.39 155	96.91 40	97.88 110	93.58 40	94.09 164	96.99 212	91.05 157	92.40 325	95.22 289	91.03 186	99.25 88	92.11 135	98.69 188	97.90 229

CS-MVS		95.77 71	95.58 90	96.37 53	96.84 186	91.72 64	96.73 30	99.06 7	94.23 62	92.48 320	94.79 309	93.56 99	99.49 29	93.47 88	99.05 119	97.89 231

WBMVS		84.00 412	83.48 412	85.56 439	92.71 398	61.52 486	83.82 468	89.38 417	79.56 399	90.74 365	93.20 369	48.21 477	97.28 356	75.63 431	98.10 260	97.88 232

testgi		90.38 295	91.34 270	87.50 413	97.49 140	71.54 444	89.43 364	95.16 312	88.38 235	94.54 235	94.68 314	92.88 129	93.09 460	71.60 459	97.85 286	97.88 232

test_0402		95.73 73	96.22 50	94.26 152	98.19 85	85.77 197	93.24 198	97.24 193	96.88 20	97.69 41	97.77 79	94.12 90	99.13 103	91.54 160	99.29 83	97.88 232

viewdifsd2359ckpt13		92.57 235	92.48 237	92.83 226	95.60 309	82.35 267	91.80 283	97.49 169	85.04 325	93.14 295	95.41 284	90.94 187	98.25 252	86.68 300	96.24 361	97.87 235

miper_lstm_enhance		89.90 313	89.80 309	90.19 359	91.37 437	77.50 377	83.82 468	95.00 316	84.84 330	93.05 299	94.96 300	76.53 384	95.20 434	89.96 216	98.67 191	97.86 236

MCST-MVS		92.91 215	92.51 234	94.10 159	97.52 138	85.72 199	91.36 296	97.13 201	80.33 390	92.91 307	94.24 334	91.23 176	98.72 173	89.99 214	97.93 281	97.86 236

Vis-MVSNet		95.50 83	95.48 93	95.56 84	98.11 89	89.40 100	95.35 104	98.22 58	92.36 101	94.11 246	98.07 49	92.02 150	99.44 33	93.38 96	97.67 298	97.85 238
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_fmvs2		90.62 287	90.40 297	91.29 309	91.93 424	85.46 205	92.70 228	96.48 259	74.44 438	94.91 221	97.59 92	75.52 387	90.57 472	93.44 91	96.56 351	97.84 239

fmvsm_s_conf0.5_n_5		94.50 134	94.80 130	93.60 184	96.80 190	84.93 212	92.81 221	97.59 156	85.27 317	96.85 95	97.29 126	91.48 168	98.05 284	96.67 15	98.47 213	97.83 240

test9_res														88.16 272	98.40 219	97.83 240

VNet		92.67 228	92.96 214	91.79 281	96.27 251	80.15 303	91.95 268	94.98 317	92.19 109	94.52 236	96.07 243	87.43 256	97.39 352	84.83 333	98.38 224	97.83 240

diffmvs		91.74 260	91.93 254	91.15 319	93.06 390	78.17 365	88.77 386	97.51 167	86.28 287	92.42 324	93.96 346	88.04 244	97.46 345	90.69 183	96.67 349	97.82 243
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
FMVSNet3		90.78 279	90.32 299	92.16 267	93.03 392	79.92 314	92.54 236	94.95 318	86.17 293	95.10 210	96.01 246	69.97 416	98.75 167	86.74 297	98.38 224	97.82 243

CPTT-MVS		94.74 120	94.12 170	96.60 46	98.15 87	93.01 45	95.84 84	97.66 147	89.21 209	93.28 283	95.46 278	88.89 227	98.98 126	89.80 218	98.82 158	97.80 245

diffmvs_AUTHOR		92.34 243	92.70 227	91.26 311	94.20 364	78.42 356	89.12 374	97.60 154	87.16 270	93.17 294	95.50 276	88.66 230	97.57 337	91.30 165	97.61 302	97.79 246

APD_test1		95.91 64	95.42 98	97.36 26	98.82 30	96.62 6	95.64 92	97.64 148	93.38 82	95.89 153	97.23 134	93.35 109	97.66 330	88.20 268	98.66 193	97.79 246

cl22		89.02 333	88.50 334	90.59 346	89.76 461	76.45 399	86.62 429	94.03 343	82.98 356	92.65 314	92.49 384	72.05 407	97.53 339	88.93 245	97.02 332	97.78 248

Anonymous202405211		92.58 233	92.50 235	92.83 226	96.55 216	83.22 243	92.43 244	91.64 400	94.10 65	95.59 174	96.64 190	81.88 330	97.50 341	85.12 328	98.52 207	97.77 249

cl____		90.65 285	90.56 293	90.91 333	91.85 426	76.98 388	86.75 424	95.36 307	85.53 312	94.06 250	94.89 302	77.36 371	97.98 296	90.27 201	98.98 129	97.76 250

DIV-MVS_self_test		90.65 285	90.56 293	90.91 333	91.85 426	76.99 387	86.75 424	95.36 307	85.52 314	94.06 250	94.89 302	77.37 370	97.99 295	90.28 200	98.97 134	97.76 250

test12				94.43 147	95.95 281	86.75 165		96.24 270		89.76 391		89.79 218	98.79 159		97.95 280	97.75 252

test_fmvsm_n_1920		94.72 121	94.74 136	94.67 130	96.30 247	88.62 117	93.19 200	98.07 85	85.63 309	97.08 79	97.35 121	90.86 188	97.66 330	95.70 30	98.48 212	97.74 253

train_agg		92.71 227	91.83 258	95.35 94	96.45 226	89.46 96	90.60 323	96.92 217	79.37 401	90.49 369	94.39 329	91.20 178	98.88 141	88.66 256	98.43 216	97.72 254

IterMVS-SCA-FT		91.65 262	91.55 262	91.94 276	93.89 374	79.22 341	87.56 403	93.51 360	91.53 141	95.37 187	96.62 193	78.65 355	98.90 138	91.89 145	94.95 402	97.70 255

3Dnovator	92.54 3	94.80 119	94.90 126	94.47 145	95.47 318	87.06 154	96.63 36	97.28 190	91.82 128	94.34 241	97.41 112	90.60 198	98.65 189	92.47 129	98.11 258	97.70 255

PVSNet_BlendedMVS		90.35 297	89.96 305	91.54 294	94.81 341	78.80 353	90.14 341	96.93 215	79.43 400	88.68 413	95.06 297	86.27 279	98.15 268	80.27 387	98.04 267	97.68 257

Effi-MVS+-dtu		93.90 174	92.60 232	97.77 3	94.74 348	96.67 5	94.00 167	95.41 305	89.94 190	91.93 343	92.13 396	90.12 209	98.97 131	87.68 284	97.48 309	97.67 258

LFMVS		91.33 271	91.16 275	91.82 280	96.27 251	79.36 336	95.01 124	85.61 453	96.04 39	94.82 224	97.06 154	72.03 408	98.46 229	84.96 332	98.70 187	97.65 259

FE-MVSNET		92.02 255	92.22 245	91.41 300	96.63 210	79.08 344	91.53 289	96.84 229	85.52 314	95.16 206	96.14 238	83.97 302	97.50 341	85.48 320	98.75 175	97.64 260

UnsupCasMVSNet_eth		90.33 298	90.34 298	90.28 353	94.64 354	80.24 301	89.69 357	95.88 284	85.77 304	93.94 257	95.69 268	81.99 327	92.98 462	84.21 343	91.30 462	97.62 261

CLD-MVS		91.82 257	91.41 268	93.04 212	96.37 235	83.65 232	86.82 423	97.29 188	84.65 332	92.27 333	89.67 431	92.20 148	97.85 310	83.95 347	99.47 44	97.62 261
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
testing3-2		83.95 413	84.22 405	83.13 461	96.28 248	54.34 498	88.51 392	83.01 472	92.19 109	89.09 402	90.98 413	45.51 483	97.44 347	74.38 440	98.01 271	97.60 263

viewmambaseed2359dif		90.77 280	90.81 285	90.64 343	93.46 382	77.04 384	88.83 381	96.29 266	80.79 388	92.21 335	95.11 293	88.99 225	97.28 356	85.39 323	96.20 363	97.59 264

SPE-MVS-test		95.32 93	95.10 121	95.96 62	96.86 184	90.75 80	96.33 54	99.20 4	93.99 66	91.03 359	93.73 354	93.52 101	99.55 18	91.81 147	99.45 48	97.58 265

MDA-MVSNet-bldmvs		91.04 275	90.88 281	91.55 292	94.68 352	80.16 302	85.49 449	92.14 390	90.41 180	94.93 220	95.79 258	85.10 293	96.93 382	85.15 326	94.19 424	97.57 266

DP-MVS		95.62 76	95.84 77	94.97 113	97.16 161	88.62 117	94.54 146	97.64 148	96.94 19	96.58 110	97.32 125	93.07 121	98.72 173	90.45 189	98.84 152	97.57 266

APD-MVS		95.00 109	94.69 138	95.93 66	97.38 147	90.88 74	94.59 139	97.81 131	89.22 208	95.46 182	96.17 237	93.42 107	99.34 71	89.30 231	98.87 150	97.56 268
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
FMVSNet5		87.82 363	86.56 382	91.62 289	92.31 409	79.81 318	93.49 189	94.81 324	83.26 347	91.36 350	96.93 164	52.77 474	97.49 344	76.07 427	98.03 268	97.55 269

CL-MVSNet_self_test		90.04 311	89.90 307	90.47 348	95.24 327	77.81 371	86.60 430	92.62 379	85.64 308	93.25 287	93.92 347	83.84 303	96.06 413	79.93 395	98.03 268	97.53 270

EC-MVSNet		95.44 85	95.62 88	94.89 118	96.93 179	87.69 141	96.48 45	99.14 6	93.93 69	92.77 311	94.52 322	93.95 94	99.49 29	93.62 79	99.22 97	97.51 271

QAPM		92.88 217	92.77 220	93.22 207	95.82 291	83.31 238	96.45 46	97.35 182	83.91 339	93.75 261	96.77 177	89.25 223	98.88 141	84.56 337	97.02 332	97.49 272

fmvsm_l_conf0.5_n_9		94.51 133	95.11 119	92.72 232	96.70 198	83.14 246	91.91 273	97.89 118	88.44 233	97.30 67	97.57 93	91.60 160	97.54 338	95.82 28	98.74 177	97.47 273

Patchmtry		90.11 306	89.92 306	90.66 342	90.35 456	77.00 386	92.96 210	92.81 372	90.25 182	94.74 228	96.93 164	67.11 425	97.52 340	85.17 324	98.98 129	97.46 274

EGC-MVSNET		80.97 439	75.73 457	96.67 45	98.85 28	94.55 18	96.83 24	96.60 249	2.44 500	5.32 501	98.25 42	92.24 145	98.02 290	91.85 146	99.21 98	97.45 275

miper_ehance_all_eth		90.48 289	90.42 296	90.69 340	91.62 433	76.57 398	86.83 422	96.18 275	83.38 345	94.06 250	92.66 383	82.20 323	98.04 286	89.79 219	97.02 332	97.45 275

LS3D		96.11 54	95.83 78	96.95 39	94.75 345	94.20 22	97.34 13	97.98 102	97.31 14	95.32 190	96.77 177	93.08 119	99.20 94	91.79 148	98.16 253	97.44 277

fmvsm_s_conf0.5_n_10		94.63 127	95.11 119	93.18 209	96.28 248	83.51 234	93.00 207	98.25 46	88.37 237	97.43 56	97.70 82	88.90 226	98.63 192	97.15 5	98.90 144	97.41 278

D2MVS		89.93 312	89.60 314	90.92 331	94.03 371	78.40 357	88.69 388	94.85 320	78.96 408	93.08 297	95.09 295	74.57 390	96.94 380	88.19 269	98.96 136	97.41 278

PHI-MVS		94.34 149	93.80 182	95.95 63	95.65 305	91.67 65	94.82 129	97.86 122	87.86 252	93.04 300	94.16 338	91.58 161	98.78 163	90.27 201	98.96 136	97.41 278

ITE_SJBPF				95.95 63	97.34 150	93.36 43		96.55 256	91.93 117	94.82 224	95.39 286	91.99 151	97.08 372	85.53 319	97.96 279	97.41 278

SD-MVS		95.19 102	95.73 83	93.55 187	96.62 211	88.88 113	94.67 136	98.05 89	91.26 152	97.25 72	96.40 209	95.42 34	94.36 448	92.72 121	99.19 100	97.40 282
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
test20.03		90.80 278	90.85 283	90.63 344	95.63 307	79.24 340	89.81 353	92.87 371	89.90 191	94.39 238	96.40 209	85.77 283	95.27 433	73.86 445	99.05 119	97.39 283

F-COLMAP		92.28 245	91.06 277	95.95 63	97.52 138	91.90 59	93.53 187	97.18 196	83.98 338	88.70 412	94.04 341	88.41 236	98.55 211	80.17 391	95.99 367	97.39 283

DeepPCF-MVS	90.46 6	94.20 159	93.56 196	96.14 56	95.96 280	92.96 46	89.48 362	97.46 171	85.14 321	96.23 132	95.42 281	93.19 114	98.08 277	90.37 195	98.76 171	97.38 285

mvs_anonymous		90.37 296	91.30 271	87.58 412	92.17 416	68.00 461	89.84 352	94.73 327	83.82 341	93.22 289	97.40 113	87.54 254	97.40 351	87.94 280	95.05 400	97.34 286

alignmvs		93.26 199	92.85 218	94.50 142	95.70 300	87.45 145	93.45 191	95.76 287	91.58 138	95.25 198	92.42 389	81.96 328	98.72 173	91.61 155	97.87 285	97.33 287

DeepC-MVS_fast	89.96 7	93.73 178	93.44 200	94.60 136	96.14 264	87.90 136	93.36 195	97.14 199	85.53 312	93.90 258	95.45 279	91.30 174	98.59 199	89.51 225	98.62 195	97.31 288
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
pmmvs-eth3d		91.54 266	90.73 289	93.99 161	95.76 298	87.86 138	90.83 313	93.98 347	78.23 413	94.02 253	96.22 228	82.62 320	96.83 387	86.57 303	98.33 231	97.29 289

testing3		83.66 415	82.52 420	87.08 417	95.84 289	65.84 473	89.80 354	77.17 494	88.17 244	90.84 363	88.63 441	30.95 502	98.11 272	84.05 344	97.19 322	97.28 290

MGCFI-Net		94.44 141	94.67 143	93.75 176	95.56 312	85.47 204	95.25 113	98.24 54	91.53 141	95.04 215	92.21 393	94.94 63	98.54 212	91.56 159	97.66 299	97.24 291

IterMVS		90.18 302	90.16 300	90.21 357	93.15 388	75.98 405	87.56 403	92.97 370	86.43 285	94.09 247	96.40 209	78.32 360	97.43 348	87.87 281	94.69 410	97.23 292
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
sasdasda		94.59 128	94.69 138	94.30 150	95.60 309	87.03 155	95.59 93	98.24 54	91.56 139	95.21 201	92.04 398	94.95 61	98.66 186	91.45 161	97.57 304	97.20 293

canonicalmvs		94.59 128	94.69 138	94.30 150	95.60 309	87.03 155	95.59 93	98.24 54	91.56 139	95.21 201	92.04 398	94.95 61	98.66 186	91.45 161	97.57 304	97.20 293

test_fmvs1_n		88.73 345	88.38 337	89.76 367	92.06 419	82.53 262	92.30 255	96.59 251	71.14 462	92.58 317	95.41 284	68.55 419	89.57 480	91.12 172	95.66 375	97.18 295

fmvsm_l_conf0.5_n		93.79 176	93.81 180	93.73 178	96.16 261	86.26 181	92.46 241	96.72 238	81.69 376	95.77 157	97.11 148	90.83 190	97.82 311	95.58 34	97.99 274	97.11 296

icg_test_0407_2		91.18 274	91.92 255	88.94 383	95.19 329	76.72 392	84.66 459	96.89 220	85.92 297	93.55 270	94.50 323	91.06 183	92.99 461	88.49 263	97.07 326	97.10 297

IMVS_0407		92.28 245	92.83 219	90.63 344	95.19 329	76.72 392	92.79 224	96.89 220	85.92 297	93.55 270	94.50 323	91.06 183	98.07 281	88.49 263	97.07 326	97.10 297

IMVS_0404		90.67 284	91.06 277	89.50 371	95.19 329	76.72 392	86.58 431	96.89 220	85.92 297	89.17 399	94.50 323	85.77 283	94.67 441	88.49 263	97.07 326	97.10 297

IMVS_0403		92.20 250	92.70 227	90.69 340	95.19 329	76.72 392	92.39 247	96.89 220	85.92 297	93.66 267	94.50 323	90.18 206	98.24 254	88.49 263	97.07 326	97.10 297

fmvsm_l_conf0.5_n_a		93.59 184	93.63 191	93.49 194	96.10 268	85.66 201	92.32 252	96.57 252	81.32 381	95.63 172	97.14 145	90.19 205	97.73 326	95.37 44	98.03 268	97.07 301

ppachtmachnet_test		88.61 347	88.64 330	88.50 395	91.76 428	70.99 448	84.59 460	92.98 369	79.30 405	92.38 326	93.53 361	79.57 346	97.45 346	86.50 308	97.17 323	97.07 301

MVS_111021_LR		93.66 179	93.28 206	94.80 122	96.25 254	90.95 72	90.21 338	95.43 304	87.91 249	93.74 263	94.40 328	92.88 129	96.38 404	90.39 191	98.28 238	97.07 301

HyFIR lowres test		87.19 382	85.51 395	92.24 260	97.12 166	80.51 295	85.03 453	96.06 278	66.11 483	91.66 346	92.98 374	70.12 415	99.14 100	75.29 432	95.23 394	97.07 301

h-mvs33		92.89 216	91.99 252	95.58 82	96.97 175	90.55 82	93.94 171	94.01 346	89.23 206	93.95 255	96.19 233	76.88 379	99.14 100	91.02 174	95.71 374	97.04 305

CANet_DTU		89.85 315	89.17 318	91.87 277	92.20 414	80.02 310	90.79 315	95.87 285	86.02 295	82.53 471	91.77 402	80.01 343	98.57 205	85.66 318	97.70 296	97.01 306

MVS_Test		92.57 235	93.29 204	90.40 351	93.53 381	75.85 406	92.52 237	96.96 213	88.73 220	92.35 329	96.70 187	90.77 191	98.37 240	92.53 127	95.49 380	96.99 307

usedtu_dtu_shiyan1		89.18 325	88.59 331	90.95 329	94.75 345	77.79 372	86.25 436	94.63 332	81.61 377	90.88 360	92.24 392	77.03 374	98.08 277	82.62 358	97.27 317	96.97 308

FE-MVSNET3		89.18 325	88.59 331	90.95 329	94.75 345	77.79 372	86.25 436	94.63 332	81.61 377	90.88 360	92.25 391	77.03 374	98.08 277	82.62 358	97.27 317	96.97 308

LCM-MVSNet-Re		94.20 159	94.58 147	93.04 212	95.91 284	83.13 247	93.79 176	99.19 5	92.00 114	98.84 8	98.04 52	93.64 98	99.02 122	81.28 379	98.54 204	96.96 310

CSCG		94.69 124	94.75 134	94.52 141	97.55 137	87.87 137	95.01 124	97.57 158	92.68 91	96.20 135	93.44 362	91.92 153	98.78 163	89.11 242	99.24 93	96.92 311

gbinet_0.2-2-1-0.02		88.14 358	86.86 375	91.99 275	90.70 448	80.51 295	87.36 410	93.01 368	83.45 344	90.38 373	82.42 483	72.73 399	98.54 212	85.40 321	96.27 359	96.90 312

Fast-Effi-MVS+-dtu		92.77 224	92.16 246	94.58 140	94.66 353	88.25 127	92.05 263	96.65 246	89.62 199	90.08 382	91.23 409	92.56 135	98.60 197	86.30 311	96.27 359	96.90 312

test_fmvsmvis_n_1920		95.08 107	95.40 99	94.13 158	96.66 201	87.75 140	93.44 192	98.49 24	85.57 311	98.27 23	97.11 148	94.11 91	97.75 323	96.26 20	98.72 183	96.89 314

114514_t		90.51 288	89.80 309	92.63 239	98.00 102	82.24 268	93.40 193	97.29 188	65.84 484	89.40 397	94.80 308	86.99 266	98.75 167	83.88 348	98.61 196	96.89 314

Effi-MVS+		92.79 222	92.74 222	92.94 219	95.10 333	83.30 239	94.00 167	97.53 164	91.36 150	89.35 398	90.65 422	94.01 93	98.66 186	87.40 289	95.30 391	96.88 316

CMPMVS	68.83 22	87.28 378	85.67 394	92.09 270	88.77 473	85.42 206	90.31 336	94.38 335	70.02 471	88.00 422	93.30 365	73.78 396	94.03 453	75.96 429	96.54 352	96.83 317
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
hse-mvs2		92.24 249	91.20 272	95.38 92	96.16 261	90.65 81	92.52 237	92.01 394	89.23 206	93.95 255	92.99 373	76.88 379	98.69 182	91.02 174	96.03 365	96.81 318

miper_enhance_ethall		88.42 351	87.87 353	90.07 360	88.67 474	75.52 410	85.10 452	95.59 296	75.68 428	92.49 319	89.45 434	78.96 350	97.88 304	87.86 282	97.02 332	96.81 318

EIA-MVS		92.35 242	92.03 250	93.30 203	95.81 293	83.97 228	92.80 223	98.17 67	87.71 257	89.79 390	87.56 450	91.17 181	99.18 96	87.97 279	97.27 317	96.77 320

MVP-Stereo		90.07 309	88.92 324	93.54 189	96.31 245	86.49 172	90.93 310	95.59 296	79.80 393	91.48 348	95.59 271	80.79 337	97.39 352	78.57 408	91.19 463	96.76 321
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
AUN-MVS		90.05 310	88.30 340	95.32 98	96.09 269	90.52 84	92.42 245	92.05 393	82.08 370	88.45 416	92.86 375	65.76 435	98.69 182	88.91 247	96.07 364	96.75 322

PAPM_NR		91.03 276	90.81 285	91.68 287	96.73 195	81.10 289	93.72 179	96.35 265	88.19 243	88.77 410	92.12 397	85.09 294	97.25 359	82.40 365	93.90 429	96.68 323

FA-MVS(test-final)		91.81 258	91.85 257	91.68 287	94.95 336	79.99 311	96.00 74	93.44 362	87.80 254	94.02 253	97.29 126	77.60 365	98.45 230	88.04 277	97.49 308	96.61 324

balanced_ft_v1		92.65 230	93.17 210	91.10 320	94.47 358	77.32 380	96.67 34	96.70 240	88.23 241	93.70 265	97.16 141	83.33 307	99.41 43	90.51 187	97.76 289	96.57 325

UnsupCasMVSNet_bld		88.50 348	88.03 351	89.90 365	95.52 314	78.88 349	87.39 409	94.02 345	79.32 404	93.06 298	94.02 343	80.72 338	94.27 449	75.16 434	93.08 447	96.54 326

TAPA-MVS	88.58 10	92.49 237	91.75 260	94.73 125	96.50 222	89.69 92	92.91 217	97.68 144	78.02 414	92.79 310	94.10 339	90.85 189	97.96 297	84.76 335	98.16 253	96.54 326
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
blended_shiyan6		88.42 351	87.43 360	91.40 301	92.37 406	79.43 334	87.41 408	93.91 351	82.51 363	91.17 356	85.44 465	74.34 392	98.24 254	84.38 341	95.32 387	96.53 328

blended_shiyan8		88.43 350	87.44 359	91.40 301	92.37 406	79.45 332	87.43 407	93.92 350	82.51 363	91.24 355	85.42 466	74.35 391	98.23 256	84.43 340	95.28 392	96.52 329

pmmvs5		87.87 361	87.14 368	90.07 360	93.26 387	76.97 389	88.89 378	92.18 387	73.71 444	88.36 417	93.89 349	76.86 381	96.73 391	80.32 386	96.81 343	96.51 330

thres600view7		87.66 366	87.10 371	89.36 376	96.05 273	73.17 431	92.72 225	85.31 456	91.89 119	93.29 282	90.97 414	63.42 450	98.39 233	73.23 448	96.99 337	96.51 330

thres400		87.20 381	86.52 384	89.24 380	95.77 296	72.94 435	91.89 274	86.00 445	90.84 162	92.61 315	89.80 426	63.93 446	98.28 246	71.27 461	96.54 352	96.51 330

TSAR-MVS + GP.		93.07 212	92.41 238	95.06 110	95.82 291	90.87 75	90.97 309	92.61 380	88.04 247	94.61 233	93.79 353	88.08 241	97.81 313	89.41 228	98.39 223	96.50 333

SD_0403		88.79 342	88.88 327	88.51 394	95.89 287	72.58 439	94.27 153	95.24 310	83.77 343	87.92 425	94.38 331	87.70 250	96.47 400	66.36 476	94.40 414	96.49 334

YYNet1		88.17 356	88.24 345	87.93 406	92.21 413	73.62 429	80.75 479	88.77 419	82.51 363	94.99 218	95.11 293	82.70 318	93.70 454	83.33 350	93.83 430	96.48 335

mvsmamba		90.24 301	89.43 315	92.64 236	95.52 314	82.36 265	96.64 35	92.29 385	81.77 374	92.14 337	96.28 222	70.59 413	99.10 109	84.44 339	95.22 395	96.47 336

MDA-MVSNet_test_wron		88.16 357	88.23 346	87.93 406	92.22 412	73.71 428	80.71 480	88.84 418	82.52 362	94.88 223	95.14 291	82.70 318	93.61 455	83.28 351	93.80 431	96.46 337

MVSFormer		92.18 251	92.23 244	92.04 272	94.74 348	80.06 307	97.15 15	97.37 176	88.98 213	88.83 404	92.79 378	77.02 376	99.60 9	96.41 18	96.75 346	96.46 337

jason		89.17 328	88.32 339	91.70 286	95.73 299	80.07 306	88.10 395	93.22 365	71.98 456	90.09 378	92.79 378	78.53 358	98.56 209	87.43 288	97.06 330	96.46 337
jason: jason.
CHOSEN 1792x2688		87.19 382	85.92 393	91.00 325	97.13 164	79.41 335	84.51 461	95.60 292	64.14 487	90.07 383	94.81 306	78.26 361	97.14 369	73.34 447	95.38 385	96.46 337

Anonymous20231206		88.77 343	88.29 341	90.20 358	96.31 245	78.81 352	89.56 360	93.49 361	74.26 441	92.38 326	95.58 274	82.21 322	95.43 428	72.07 455	98.75 175	96.34 341

wanda-best-256-512		87.53 371	86.39 387	90.97 327	91.29 439	78.39 359	85.63 447	93.75 353	81.91 372	90.09 378	83.30 478	72.25 403	98.18 262	83.96 345	95.32 387	96.33 342

FE-blended-shiyan7		87.53 371	86.39 387	90.97 327	91.29 439	78.39 359	85.63 447	93.75 353	81.91 372	90.09 378	83.30 478	72.25 403	98.18 262	83.96 345	95.32 387	96.33 342

usedtu_blend_shiyan5		89.08 331	88.33 338	91.34 305	91.29 439	79.59 325	94.02 165	97.13 201	90.07 188	90.09 378	83.30 478	72.25 403	98.10 275	81.45 376	95.32 387	96.33 342

旧先验1					96.20 257	84.17 225		94.82 322			95.57 275	89.57 220			97.89 283	96.32 345

DELS-MVS		92.05 254	92.16 246	91.72 284	94.44 359	80.13 305	87.62 400	97.25 191	87.34 265	92.22 334	93.18 370	89.54 221	98.73 172	89.67 223	98.20 251	96.30 346
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
PLC	85.34 15	90.40 292	88.92 324	94.85 120	96.53 220	90.02 88	91.58 288	96.48 259	80.16 391	86.14 440	92.18 394	85.73 285	98.25 252	76.87 420	94.61 412	96.30 346
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVSMamba_PlusPlus		94.82 118	95.89 73	91.62 289	97.82 114	78.88 349	96.52 40	97.60 154	97.14 16	94.23 242	98.48 34	87.01 265	99.71 2	95.43 40	98.80 164	96.28 348

testing91		83.56 417	82.45 421	86.91 423	92.92 395	67.29 462	86.33 435	88.07 428	86.22 289	84.26 455	85.76 462	48.15 478	97.17 366	76.27 426	94.08 428	96.27 349

PAPR		87.65 367	86.77 378	90.27 354	92.85 397	77.38 379	88.56 391	96.23 271	76.82 425	84.98 449	89.75 430	86.08 281	97.16 368	72.33 454	93.35 439	96.26 350

balanced_conf03		93.45 190	94.17 168	91.28 310	95.81 293	78.40 357	96.20 69	97.48 170	88.56 231	95.29 193	97.20 139	85.56 290	99.21 91	92.52 128	98.91 143	96.24 351

TestfortrainingZip				93.68 180	95.25 326	86.20 184	96.32 56	96.38 263	92.81 89	92.13 338	93.87 352	87.28 259	98.61 194		95.07 399	96.23 352

our_test_3		87.55 370	87.59 357	87.44 414	91.76 428	70.48 449	83.83 467	90.55 412	79.79 394	92.06 341	92.17 395	78.63 357	95.63 421	84.77 334	94.73 408	96.22 353

Fast-Effi-MVS+		91.28 273	90.86 282	92.53 250	95.45 319	82.53 262	89.25 372	96.52 257	85.00 326	89.91 386	88.55 443	92.94 125	98.84 148	84.72 336	95.44 382	96.22 353

EPNet_dtu		85.63 396	84.37 402	89.40 375	86.30 485	74.33 422	91.64 286	88.26 423	84.84 330	72.96 492	89.85 424	71.27 411	97.69 328	76.60 422	97.62 301	96.18 355
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
LF4IMVS		92.72 226	92.02 251	94.84 121	95.65 305	91.99 57	92.92 216	96.60 249	85.08 324	92.44 323	93.62 357	86.80 271	96.35 406	86.81 296	98.25 242	96.18 355

testing99		82.94 423	81.72 425	86.59 426	92.55 402	66.53 468	86.08 441	85.70 448	85.47 316	83.95 458	85.70 463	45.87 482	97.07 374	76.58 423	93.56 435	96.17 357

pmmvs4		88.95 338	87.70 356	92.70 233	94.30 362	85.60 202	87.22 412	92.16 389	74.62 437	89.75 392	94.19 336	77.97 363	96.41 402	82.71 356	96.36 356	96.09 358

MG-MVS		89.54 319	89.80 309	88.76 387	94.88 337	72.47 441	89.60 358	92.44 383	85.82 303	89.48 395	95.98 249	82.85 315	97.74 325	81.87 369	95.27 393	96.08 359

ab-mvs		92.40 240	92.62 230	91.74 283	97.02 172	81.65 277	95.84 84	95.50 301	86.95 277	92.95 305	97.56 95	90.70 196	97.50 341	79.63 398	97.43 312	96.06 360

baseline2		83.38 418	81.54 428	88.90 384	91.38 436	72.84 437	88.78 385	81.22 480	78.97 407	79.82 483	87.56 450	61.73 457	97.80 314	74.30 442	90.05 469	96.05 361

N_pmnet		88.90 339	87.25 365	93.83 173	94.40 361	93.81 38	84.73 455	87.09 436	79.36 403	93.26 285	92.43 388	79.29 349	91.68 467	77.50 416	97.22 321	96.00 362

WB-MVSnew		84.20 410	83.89 410	85.16 445	91.62 433	66.15 472	88.44 394	81.00 481	76.23 427	87.98 423	87.77 449	84.98 295	93.35 458	62.85 485	94.10 427	95.98 363

test_vis1_n_1920		89.45 321	89.85 308	88.28 399	93.59 380	76.71 396	90.67 321	97.78 137	79.67 397	90.30 376	96.11 241	76.62 382	92.17 465	90.31 198	93.57 434	95.96 364

GA-MVS		87.70 364	86.82 376	90.31 352	93.27 386	77.22 383	84.72 457	92.79 374	85.11 323	89.82 388	90.07 423	66.80 428	97.76 322	84.56 337	94.27 420	95.96 364

test_yl		90.11 306	89.73 312	91.26 311	94.09 368	79.82 316	90.44 329	92.65 377	90.90 160	93.19 292	93.30 365	73.90 394	98.03 287	82.23 366	96.87 340	95.93 366

DCV-MVSNet		90.11 306	89.73 312	91.26 311	94.09 368	79.82 316	90.44 329	92.65 377	90.90 160	93.19 292	93.30 365	73.90 394	98.03 287	82.23 366	96.87 340	95.93 366

PM-MVS		93.33 196	92.67 229	95.33 96	96.58 213	94.06 24	92.26 258	92.18 387	85.92 297	96.22 133	96.61 194	85.64 288	95.99 416	90.35 196	98.23 244	95.93 366

ET-MVSNet_ETH3D		86.15 393	84.27 404	91.79 281	93.04 391	81.28 284	87.17 414	86.14 443	79.57 398	83.65 460	88.66 440	57.10 465	98.18 262	87.74 283	95.40 383	95.90 369

TAMVS		90.16 303	89.05 320	93.49 194	96.49 223	86.37 177	90.34 335	92.55 381	80.84 387	92.99 301	94.57 321	81.94 329	98.20 259	73.51 446	98.21 249	95.90 369

blend_shiyan4		83.29 419	80.66 437	91.19 317	91.86 425	79.59 325	87.05 416	93.91 351	82.66 359	89.60 394	83.36 477	42.82 496	98.10 275	81.45 376	73.26 493	95.87 371

baseline1		87.62 368	87.31 362	88.54 392	94.71 351	74.27 423	93.10 204	88.20 425	86.20 290	92.18 336	93.04 371	73.21 397	95.52 423	79.32 402	85.82 479	95.83 372

WTY-MVS		86.93 388	86.50 386	88.24 400	94.96 335	74.64 416	87.19 413	92.07 392	78.29 412	88.32 418	91.59 406	78.06 362	94.27 449	74.88 435	93.15 444	95.80 373

PVSNet_Blended_VisFu		91.63 263	91.20 272	92.94 219	97.73 122	83.95 229	92.14 261	97.46 171	78.85 410	92.35 329	94.98 299	84.16 300	99.08 110	86.36 310	96.77 345	95.79 374

lupinMVS		88.34 354	87.31 362	91.45 298	94.74 348	80.06 307	87.23 411	92.27 386	71.10 463	88.83 404	91.15 410	77.02 376	98.53 216	86.67 301	96.75 346	95.76 375

DP-MVS Recon		92.31 244	91.88 256	93.60 184	97.18 160	86.87 161	91.10 304	97.37 176	84.92 328	92.08 340	94.08 340	88.59 231	98.20 259	83.50 349	98.14 255	95.73 376

FE-MVS		89.06 332	88.29 341	91.36 304	94.78 343	79.57 329	96.77 29	90.99 405	84.87 329	92.96 304	96.29 220	60.69 461	98.80 158	80.18 390	97.11 325	95.71 377

CDS-MVSNet		89.55 318	88.22 347	93.53 190	95.37 323	86.49 172	89.26 370	93.59 357	79.76 395	91.15 357	92.31 390	77.12 372	98.38 236	77.51 415	97.92 282	95.71 377
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
原ACMM1				92.87 224	96.91 180	84.22 223		97.01 209	76.84 424	89.64 393	94.46 327	88.00 245	98.70 180	81.53 375	98.01 271	95.70 379

thisisatest0515		84.72 405	82.99 417	89.90 365	92.96 394	75.33 412	84.36 462	83.42 468	77.37 418	88.27 419	86.65 455	53.94 471	98.72 173	82.56 361	97.40 314	95.67 380

ETV-MVS		92.99 213	92.74 222	93.72 179	95.86 288	86.30 180	92.33 251	97.84 126	91.70 136	92.81 308	86.17 460	92.22 146	99.19 95	88.03 278	97.73 291	95.66 381

TinyColmap		92.00 256	92.76 221	89.71 369	95.62 308	77.02 385	90.72 319	96.17 276	87.70 258	95.26 196	96.29 220	92.54 136	96.45 401	81.77 370	98.77 169	95.66 381

PCF-MVS	84.52 17	89.12 329	87.71 355	93.34 199	96.06 272	85.84 196	86.58 431	97.31 185	68.46 477	93.61 268	93.89 349	87.51 255	98.52 218	67.85 472	98.11 258	95.66 381
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
USDC		89.02 333	89.08 319	88.84 386	95.07 334	74.50 420	88.97 376	96.39 262	73.21 448	93.27 284	96.28 222	82.16 324	96.39 403	77.55 414	98.80 164	95.62 384

ETVMVS		79.85 449	77.94 456	85.59 438	92.97 393	66.20 471	86.13 440	80.99 482	81.41 379	83.52 463	83.89 474	41.81 497	94.98 439	56.47 490	94.25 421	95.61 385

OpenMVS	89.45 8	92.27 248	92.13 249	92.68 235	94.53 357	84.10 226	95.70 88	97.03 208	82.44 366	91.14 358	96.42 207	88.47 234	98.38 236	85.95 314	97.47 310	95.55 386

myMVS_eth3d28		80.97 439	80.42 440	82.62 463	93.35 384	58.25 493	84.70 458	85.62 452	86.31 286	84.04 457	85.20 469	46.00 481	94.07 452	62.93 484	95.65 376	95.53 387

sss		87.23 379	86.82 376	88.46 397	93.96 372	77.94 366	86.84 421	92.78 375	77.59 416	87.61 431	91.83 401	78.75 354	91.92 466	77.84 411	94.20 422	95.52 388

test_cas_vis1_n_1920		88.25 355	88.27 343	88.20 401	92.19 415	78.92 347	89.45 363	95.44 302	75.29 435	93.23 288	95.65 270	71.58 409	90.23 476	88.05 276	93.55 436	95.44 389

ADS-MVSNet2		84.01 411	82.20 424	89.41 374	89.04 470	76.37 401	87.57 401	90.98 406	72.71 453	84.46 452	92.45 385	68.08 421	96.48 398	70.58 466	83.97 481	95.38 390

ADS-MVSNet		82.25 427	81.55 427	84.34 452	89.04 470	65.30 474	87.57 401	85.13 460	72.71 453	84.46 452	92.45 385	68.08 421	92.33 464	70.58 466	83.97 481	95.38 390

testing222		80.54 444	78.53 452	86.58 427	92.54 404	68.60 459	86.24 438	82.72 474	83.78 342	82.68 470	84.24 473	39.25 500	95.94 417	60.25 486	95.09 398	95.20 392

tt0805		95.42 89	95.93 70	93.86 171	98.75 36	88.47 124	97.68 9	94.29 337	96.48 26	95.38 185	93.63 356	94.89 65	97.94 299	95.38 43	96.92 339	95.17 393

tpm		84.38 408	84.08 406	85.30 443	90.47 454	63.43 483	89.34 367	85.63 450	77.24 421	87.62 430	95.03 298	61.00 460	97.30 355	79.26 403	91.09 465	95.16 394

1112_ss		88.42 351	87.41 361	91.45 298	96.69 199	80.99 291	89.72 356	96.72 238	73.37 446	87.00 436	90.69 420	77.38 369	98.20 259	81.38 378	93.72 432	95.15 395

testing11		81.98 432	80.52 439	86.38 432	92.69 399	67.13 463	85.79 444	84.80 461	82.16 369	81.19 480	85.41 467	45.24 484	96.88 385	74.14 443	93.24 441	95.14 396

UWE-MVS		80.29 446	79.10 447	83.87 456	91.97 423	59.56 490	86.50 434	77.43 493	75.40 432	87.79 428	88.10 447	44.08 488	96.90 384	64.23 480	96.36 356	95.14 396

BH-RMVSNet		90.47 290	90.44 295	90.56 347	95.21 328	78.65 355	89.15 373	93.94 348	88.21 242	92.74 312	94.22 335	86.38 276	97.88 304	78.67 407	95.39 384	95.14 396

UBG		80.28 447	78.94 450	84.31 453	92.86 396	61.77 485	83.87 466	83.31 471	77.33 419	82.78 469	83.72 475	47.60 480	96.06 413	65.47 479	93.48 437	95.11 399

Test_1112_low_res		87.50 374	86.58 380	90.25 355	96.80 190	77.75 374	87.53 405	96.25 269	69.73 473	86.47 438	93.61 358	75.67 386	97.88 304	79.95 393	93.20 442	95.11 399

MIMVSNet		87.13 384	86.54 383	88.89 385	96.05 273	76.11 403	94.39 148	88.51 421	81.37 380	88.27 419	96.75 181	72.38 402	95.52 423	65.71 478	95.47 381	95.03 401

Gipuma		95.31 96	95.80 81	93.81 174	97.99 105	90.91 73	96.42 49	97.95 109	96.69 21	91.78 344	98.85 17	91.77 156	95.49 425	91.72 152	99.08 115	95.02 402
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MSLP-MVS++		93.25 202	93.88 179	91.37 303	96.34 241	82.81 254	93.11 203	97.74 139	89.37 204	94.08 248	95.29 288	90.40 202	96.35 406	90.35 196	98.25 242	94.96 403

test_vis1_n		89.01 335	89.01 322	89.03 381	92.57 401	82.46 264	92.62 233	96.06 278	73.02 450	90.40 372	95.77 262	74.86 389	89.68 478	90.78 180	94.98 401	94.95 404

MSDG		90.82 277	90.67 290	91.26 311	94.16 365	83.08 249	86.63 428	96.19 274	90.60 174	91.94 342	91.89 400	89.16 224	95.75 420	80.96 384	94.51 413	94.95 404

test_fmvs1		87.59 369	87.27 364	88.54 392	88.32 475	81.26 285	90.43 332	95.72 289	70.55 468	91.70 345	94.63 316	68.13 420	89.42 482	90.59 184	95.34 386	94.94 406

Syy-MVS		84.81 403	84.93 397	84.42 451	91.71 430	63.36 484	85.89 442	81.49 478	81.03 382	85.13 446	81.64 485	77.44 367	95.00 436	85.94 315	94.12 425	94.91 407

myMVS_eth3d		79.62 450	78.26 453	83.72 457	91.71 430	61.25 488	85.89 442	81.49 478	81.03 382	85.13 446	81.64 485	32.12 501	95.00 436	71.17 464	94.12 425	94.91 407

无先验							89.94 348	95.75 288	70.81 466				98.59 199	81.17 382		94.81 409

mvsany_test3		89.11 330	88.21 348	91.83 279	91.30 438	90.25 86	88.09 396	78.76 488	76.37 426	96.43 116	98.39 38	83.79 304	90.43 475	86.57 303	94.20 422	94.80 410

thres100view900		87.35 377	86.89 374	88.72 388	96.14 264	73.09 433	93.00 207	85.31 456	92.13 111	93.26 285	90.96 415	63.42 450	98.28 246	71.27 461	96.54 352	94.79 411

tfpn200view9		87.05 386	86.52 384	88.67 389	95.77 296	72.94 435	91.89 274	86.00 445	90.84 162	92.61 315	89.80 426	63.93 446	98.28 246	71.27 461	96.54 352	94.79 411

GSMVS																94.75 413

sam_mvs1												66.64 431				94.75 413

SCA		87.43 375	87.21 366	88.10 403	92.01 421	71.98 443	89.43 364	88.11 427	82.26 368	88.71 411	92.83 376	78.65 355	97.59 335	79.61 399	93.30 440	94.75 413

MS-PatchMatch		88.05 359	87.75 354	88.95 382	93.28 385	77.93 367	87.88 398	92.49 382	75.42 431	92.57 318	93.59 359	80.44 340	94.24 451	81.28 379	92.75 450	94.69 416

PatchmatchNet		85.22 399	84.64 399	86.98 420	89.51 467	69.83 456	90.52 325	87.34 435	78.87 409	87.22 435	92.74 380	66.91 427	96.53 395	81.77 370	86.88 477	94.58 417
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EU-MVSNet		87.39 376	86.71 379	89.44 373	93.40 383	76.11 403	94.93 127	90.00 414	57.17 493	95.71 168	97.37 115	64.77 442	97.68 329	92.67 122	94.37 417	94.52 418

PVSNet	76.22 20	82.89 424	82.37 422	84.48 450	93.96 372	64.38 480	78.60 484	88.61 420	71.50 460	84.43 454	86.36 459	74.27 393	94.60 443	69.87 468	93.69 433	94.46 419

PVSNet_Blended		88.74 344	88.16 350	90.46 350	94.81 341	78.80 353	86.64 427	96.93 215	74.67 436	88.68 413	89.18 438	86.27 279	98.15 268	80.27 387	96.00 366	94.44 420

CNLPA		91.72 261	91.20 272	93.26 205	96.17 260	91.02 70	91.14 302	95.55 299	90.16 187	90.87 362	93.56 360	86.31 278	94.40 447	79.92 397	97.12 324	94.37 421

cascas		87.02 387	86.28 390	89.25 379	91.56 435	76.45 399	84.33 463	96.78 233	71.01 464	86.89 437	85.91 461	81.35 332	96.94 380	83.09 353	95.60 377	94.35 422

DPM-MVS		89.35 323	88.40 336	92.18 266	96.13 266	84.20 224	86.96 418	96.15 277	75.40 432	87.36 433	91.55 407	83.30 308	98.01 291	82.17 368	96.62 350	94.32 423

MAR-MVS		90.32 299	88.87 328	94.66 132	94.82 340	91.85 60	94.22 156	94.75 326	80.91 384	87.52 432	88.07 448	86.63 274	97.87 307	76.67 421	96.21 362	94.25 424
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
CR-MVSNet		87.89 360	87.12 370	90.22 356	91.01 444	78.93 345	92.52 237	92.81 372	73.08 449	89.10 400	96.93 164	67.11 425	97.64 332	88.80 252	92.70 451	94.08 425

RPMNet		90.31 300	90.14 303	90.81 338	91.01 444	78.93 345	92.52 237	98.12 75	91.91 118	89.10 400	96.89 167	68.84 418	99.41 43	90.17 208	92.70 451	94.08 425

MDTV_nov1_ep13_2view						42.48 503	88.45 393		67.22 480	83.56 462		66.80 428		72.86 452		94.06 427

test-LLR		83.58 416	83.17 415	84.79 448	89.68 463	66.86 466	83.08 470	84.52 462	83.07 354	82.85 467	84.78 471	62.86 453	93.49 456	82.85 354	94.86 404	94.03 428

test-mter		81.21 437	80.01 445	84.79 448	89.68 463	66.86 466	83.08 470	84.52 462	73.85 443	82.85 467	84.78 471	43.66 489	93.49 456	82.85 354	94.86 404	94.03 428

新几何1				93.17 210	97.16 161	87.29 147		94.43 334	67.95 478	91.29 351	94.94 301	86.97 267	98.23 256	81.06 383	97.75 290	93.98 430

test222					96.95 176	85.27 209	88.83 381	93.61 356	65.09 486	90.74 365	94.85 304	84.62 298			97.36 315	93.91 431

PMMVS2		81.31 435	83.44 413	74.92 476	90.52 452	46.49 502	69.19 492	85.23 459	84.30 337	87.95 424	94.71 312	76.95 378	84.36 493	64.07 481	98.09 261	93.89 432

Patchmatch-test		86.10 394	86.01 391	86.38 432	90.63 450	74.22 425	89.57 359	86.69 439	85.73 306	89.81 389	92.83 376	65.24 440	91.04 470	77.82 413	95.78 373	93.88 433

Patchmatch-RL test		88.81 341	88.52 333	89.69 370	95.33 325	79.94 313	86.22 439	92.71 376	78.46 411	95.80 156	94.18 337	66.25 433	95.33 431	89.22 237	98.53 205	93.78 434

test0.0.03 1		82.48 426	81.47 429	85.48 441	89.70 462	73.57 430	84.73 455	81.64 477	83.07 354	88.13 421	86.61 456	62.86 453	89.10 484	66.24 477	90.29 468	93.77 435

OpenMVS_ROB	85.12 16	89.52 320	89.05 320	90.92 331	94.58 355	81.21 288	91.10 304	93.41 363	77.03 422	93.41 275	93.99 345	83.23 309	97.80 314	79.93 395	94.80 407	93.74 436

testdata				91.03 322	96.87 183	82.01 270		94.28 338	71.55 459	92.46 321	95.42 281	85.65 287	97.38 354	82.64 357	97.27 317	93.70 437

test_vis1_rt		85.58 397	84.58 400	88.60 391	87.97 476	86.76 164	85.45 450	93.59 357	66.43 481	87.64 429	89.20 437	79.33 348	85.38 491	81.59 373	89.98 470	93.66 438

IB-MVS	77.21 19	83.11 420	81.05 431	89.29 377	91.15 442	75.85 406	85.66 446	86.00 445	79.70 396	82.02 475	86.61 456	48.26 476	98.39 233	77.84 411	92.22 456	93.63 439
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
xiu_mvs_v1_base_debu		91.47 268	91.52 263	91.33 306	95.69 301	81.56 278	89.92 349	96.05 280	83.22 349	91.26 352	90.74 417	91.55 162	98.82 150	89.29 232	95.91 368	93.62 440

xiu_mvs_v1_base		91.47 268	91.52 263	91.33 306	95.69 301	81.56 278	89.92 349	96.05 280	83.22 349	91.26 352	90.74 417	91.55 162	98.82 150	89.29 232	95.91 368	93.62 440

xiu_mvs_v1_base_debi		91.47 268	91.52 263	91.33 306	95.69 301	81.56 278	89.92 349	96.05 280	83.22 349	91.26 352	90.74 417	91.55 162	98.82 150	89.29 232	95.91 368	93.62 440

tpmrst		82.85 425	82.93 418	82.64 462	87.65 477	58.99 492	90.14 341	87.90 430	75.54 430	83.93 459	91.63 405	66.79 430	95.36 429	81.21 381	81.54 487	93.57 443

PatchT		87.51 373	88.17 349	85.55 440	90.64 449	66.91 465	92.02 265	86.09 444	92.20 108	89.05 403	97.16 141	64.15 445	96.37 405	89.21 238	92.98 449	93.37 444

CostFormer		83.09 421	82.21 423	85.73 437	89.27 469	67.01 464	90.35 334	86.47 441	70.42 469	83.52 463	93.23 368	61.18 458	96.85 386	77.21 418	88.26 475	93.34 445

thres200		85.85 395	85.18 396	87.88 409	94.44 359	72.52 440	89.08 375	86.21 442	88.57 230	91.44 349	88.40 444	64.22 444	98.00 293	68.35 470	95.88 371	93.12 446

KD-MVS_2432*1600		82.17 429	80.75 435	86.42 430	82.04 498	70.09 452	81.75 476	90.80 408	82.56 360	90.37 374	89.30 435	42.90 492	96.11 411	74.47 438	92.55 453	93.06 447

miper_refine_blended		82.17 429	80.75 435	86.42 430	82.04 498	70.09 452	81.75 476	90.80 408	82.56 360	90.37 374	89.30 435	42.90 492	96.11 411	74.47 438	92.55 453	93.06 447

HY-MVS	82.50 18	86.81 390	85.93 392	89.47 372	93.63 379	77.93 367	94.02 165	91.58 402	75.68 428	83.64 461	93.64 355	77.40 368	97.42 349	71.70 458	92.07 458	93.05 449

UWE-MVS-28		74.73 458	73.18 459	79.35 472	85.42 490	55.55 496	87.63 399	65.92 498	74.39 439	77.33 487	88.19 446	47.63 479	89.48 481	39.01 496	93.14 445	93.03 450

EPMVS		81.17 438	80.37 441	83.58 458	85.58 488	65.08 477	90.31 336	71.34 496	77.31 420	85.80 442	91.30 408	59.38 462	92.70 463	79.99 392	82.34 486	92.96 451

tpmvs		84.22 409	83.97 408	84.94 446	87.09 482	65.18 475	91.21 299	88.35 422	82.87 357	85.21 444	90.96 415	65.24 440	96.75 390	79.60 401	85.25 480	92.90 452

MonoMVSNet		88.46 349	89.28 316	85.98 436	90.52 452	70.07 454	95.31 109	94.81 324	88.38 235	93.47 274	96.13 239	73.21 397	95.07 435	82.61 360	89.12 471	92.81 453

BH-untuned		90.68 283	90.90 280	90.05 363	95.98 279	79.57 329	90.04 345	94.94 319	87.91 249	94.07 249	93.00 372	87.76 249	97.78 318	79.19 404	95.17 396	92.80 454

AdaColmap		91.63 263	91.36 269	92.47 253	95.56 312	86.36 178	92.24 260	96.27 268	88.88 217	89.90 387	92.69 381	91.65 159	98.32 244	77.38 417	97.64 300	92.72 455

CVMVSNet		85.16 400	84.72 398	86.48 428	92.12 417	70.19 450	92.32 252	88.17 426	56.15 494	90.64 368	95.85 253	67.97 423	96.69 392	88.78 253	90.52 467	92.56 456

tpm2		81.46 434	80.35 442	84.80 447	89.90 460	65.14 476	90.44 329	85.36 455	65.82 485	82.05 474	92.44 387	57.94 464	96.69 392	70.71 465	88.49 474	92.56 456

PAPM		81.91 433	80.11 444	87.31 416	93.87 375	72.32 442	84.02 465	93.22 365	69.47 474	76.13 489	89.84 425	72.15 406	97.23 360	53.27 492	89.02 472	92.37 458

TESTMET0.1,1		79.09 452	78.04 454	82.25 464	87.52 479	64.03 481	83.08 470	80.62 484	70.28 470	80.16 482	83.22 481	44.13 487	90.56 473	79.95 393	93.36 438	92.15 459

DSMNet-mixed		82.21 428	81.56 426	84.16 454	89.57 466	70.00 455	90.65 322	77.66 492	54.99 495	83.30 465	97.57 93	77.89 364	90.50 474	66.86 475	95.54 379	91.97 460

xiu_mvs_v2_base		89.00 336	89.19 317	88.46 397	94.86 339	74.63 417	86.97 417	95.60 292	80.88 385	87.83 426	88.62 442	91.04 185	98.81 155	82.51 363	94.38 416	91.93 461

PS-MVSNAJ		88.86 340	88.99 323	88.48 396	94.88 337	74.71 415	86.69 426	95.60 292	80.88 385	87.83 426	87.37 453	90.77 191	98.82 150	82.52 362	94.37 417	91.93 461

tpm cat1		80.61 443	79.46 446	84.07 455	88.78 472	65.06 478	89.26 370	88.23 424	62.27 490	81.90 476	89.66 432	62.70 455	95.29 432	71.72 457	80.60 488	91.86 463

dp		79.28 451	78.62 451	81.24 468	85.97 487	56.45 494	86.91 419	85.26 458	72.97 451	81.45 479	89.17 439	56.01 469	95.45 427	73.19 449	76.68 492	91.82 464

dmvs_re		84.69 406	83.94 409	86.95 422	92.24 411	82.93 252	89.51 361	87.37 434	84.38 336	85.37 443	85.08 470	72.44 401	86.59 488	68.05 471	91.03 466	91.33 465

JIA-IIPM		85.08 401	83.04 416	91.19 317	87.56 478	86.14 186	89.40 366	84.44 464	88.98 213	82.20 472	97.95 61	56.82 467	96.15 409	76.55 424	83.45 483	91.30 466

TR-MVS		87.70 364	87.17 367	89.27 378	94.11 367	79.26 339	88.69 388	91.86 396	81.94 371	90.69 367	89.79 428	82.82 316	97.42 349	72.65 453	91.98 459	91.14 467

1314		86.46 392	86.33 389	86.87 424	91.65 432	74.54 418	91.94 270	94.10 342	74.28 440	84.78 451	87.33 454	83.03 312	95.00 436	78.72 406	91.16 464	91.06 468

0.4-1-1-0.1		77.15 455	73.55 458	87.95 405	85.49 489	75.84 408	80.59 481	82.87 473	73.51 445	73.61 491	68.65 492	42.84 495	97.22 361	75.20 433	79.18 489	90.80 469

new_pmnet		81.22 436	81.01 433	81.86 465	90.92 446	70.15 451	84.03 464	80.25 486	70.83 465	85.97 441	89.78 429	67.93 424	84.65 492	67.44 473	91.90 460	90.78 470

PatchMatch-RL		89.18 325	88.02 352	92.64 236	95.90 285	92.87 48	88.67 390	91.06 404	80.34 389	90.03 384	91.67 404	83.34 306	94.42 446	76.35 425	94.84 406	90.64 471

API-MVS		91.52 267	91.61 261	91.26 311	94.16 365	86.26 181	94.66 137	94.82 322	91.17 155	92.13 338	91.08 412	90.03 214	97.06 375	79.09 405	97.35 316	90.45 472

0.3-1-1-0.015		75.73 457	71.83 463	87.44 414	83.47 496	74.98 413	78.69 483	83.38 470	72.24 455	70.43 494	65.81 493	39.55 499	97.08 372	74.57 436	78.30 491	90.28 473

0.4-1-1-0.2		75.80 456	72.05 462	87.04 418	82.70 497	74.17 426	77.51 485	83.48 467	71.80 457	71.57 493	65.16 494	43.07 490	96.96 378	74.34 441	78.78 490	90.00 474

BH-w/o		87.21 380	87.02 372	87.79 411	94.77 344	77.27 382	87.90 397	93.21 367	81.74 375	89.99 385	88.39 445	83.47 305	96.93 382	71.29 460	92.43 455	89.15 475

PMVS	87.21 14	94.97 110	95.33 105	93.91 168	98.97 20	97.16 2	95.54 100	95.85 286	96.47 27	93.40 278	97.46 107	95.31 41	95.47 426	86.18 313	98.78 168	89.11 476
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
gg-mvs-nofinetune		82.10 431	81.02 432	85.34 442	87.46 480	71.04 446	94.74 131	67.56 497	96.44 28	79.43 484	98.99 11	45.24 484	96.15 409	67.18 474	92.17 457	88.85 477

CHOSEN 280x420		80.04 448	77.97 455	86.23 435	90.13 458	74.53 419	72.87 490	89.59 416	66.38 482	76.29 488	85.32 468	56.96 466	95.36 429	69.49 469	94.72 409	88.79 478

pmmvs3		80.83 441	78.96 449	86.45 429	87.23 481	77.48 378	84.87 454	82.31 475	63.83 488	85.03 448	89.50 433	49.66 475	93.10 459	73.12 450	95.10 397	88.78 479

test_f		86.65 391	87.13 369	85.19 444	90.28 457	86.11 187	86.52 433	91.66 399	69.76 472	95.73 167	97.21 138	69.51 417	81.28 494	89.15 241	94.40 414	88.17 480

PMMVS		83.00 422	81.11 430	88.66 390	83.81 495	86.44 175	82.24 475	85.65 449	61.75 491	82.07 473	85.64 464	79.75 345	91.59 468	75.99 428	93.09 446	87.94 481

mvsany_test1		83.91 414	82.93 418	86.84 425	86.18 486	85.93 193	81.11 478	75.03 495	70.80 467	88.57 415	94.63 316	83.08 311	87.38 486	80.39 385	86.57 478	87.21 482

dmvs_testset		78.23 454	78.99 448	75.94 475	91.99 422	55.34 497	88.86 379	78.70 489	82.69 358	81.64 478	79.46 487	75.93 385	85.74 490	48.78 494	82.85 485	86.76 483

MVS		84.98 402	84.30 403	87.01 419	91.03 443	77.69 376	91.94 270	94.16 340	59.36 492	84.23 456	87.50 452	85.66 286	96.80 389	71.79 456	93.05 448	86.54 484

MVE	59.87 23	73.86 460	72.65 461	77.47 474	87.00 484	74.35 421	61.37 494	60.93 500	67.27 479	69.69 495	86.49 458	81.24 336	72.33 497	56.45 491	83.45 483	85.74 485
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
GG-mvs-BLEND				83.24 460	85.06 492	71.03 447	94.99 126	65.55 499		74.09 490	75.51 490	44.57 486	94.46 445	59.57 488	87.54 476	84.24 486

FPMVS		84.50 407	83.28 414	88.16 402	96.32 244	94.49 19	85.76 445	85.47 454	83.09 353	85.20 445	94.26 333	63.79 448	86.58 489	63.72 482	91.88 461	83.40 487

E-PMN		80.72 442	80.86 434	80.29 470	85.11 491	68.77 458	72.96 489	81.97 476	87.76 256	83.25 466	83.01 482	62.22 456	89.17 483	77.15 419	94.31 419	82.93 488

EMVS		80.35 445	80.28 443	80.54 469	84.73 493	69.07 457	72.54 491	80.73 483	87.80 254	81.66 477	81.73 484	62.89 452	89.84 477	75.79 430	94.65 411	82.71 489

PVSNet_0	70.34 21	74.58 459	72.96 460	79.47 471	90.63 450	66.24 470	73.26 488	83.40 469	63.67 489	78.02 485	78.35 489	72.53 400	89.59 479	56.68 489	60.05 496	82.57 490

test_method		50.44 462	48.94 465	54.93 478	39.68 504	12.38 507	28.59 495	90.09 413	6.82 498	41.10 500	78.41 488	54.41 470	70.69 498	50.12 493	51.26 497	81.72 491

MVS-HIRNet		78.83 453	80.60 438	73.51 477	93.07 389	47.37 501	87.10 415	78.00 491	68.94 475	77.53 486	97.26 130	71.45 410	94.62 442	63.28 483	88.74 473	78.55 492

wuyk23d		87.83 362	90.79 287	78.96 473	90.46 455	88.63 116	92.72 225	90.67 410	91.65 137	98.68 14	97.64 89	96.06 19	77.53 495	59.84 487	99.41 60	70.73 493

dongtai		53.72 461	53.79 464	53.51 480	79.69 500	36.70 504	77.18 486	32.53 506	71.69 458	68.63 496	60.79 495	26.65 503	73.11 496	30.67 498	36.29 498	50.73 494

DeepMVS_CX				53.83 479	70.38 502	64.56 479		48.52 503	33.01 497	65.50 497	74.21 491	56.19 468	46.64 500	38.45 497	70.07 494	50.30 495

kuosan		43.63 463	44.25 467	41.78 481	66.04 503	34.37 505	75.56 487	32.62 505	53.25 496	50.46 499	51.18 496	25.28 504	49.13 499	13.44 499	30.41 499	41.84 496

tmp_tt		37.97 464	44.33 466	18.88 482	11.80 505	21.54 506	63.51 493	45.66 504	4.23 499	51.34 498	50.48 497	59.08 463	22.11 501	44.50 495	68.35 495	13.00 497

test123		9.49 466	12.01 469	1.91 483	2.87 506	1.30 508	82.38 474	1.34 508	1.36 501	2.84 502	6.56 500	2.45 505	0.97 502	2.73 500	5.56 500	3.47 498

testmvs		9.02 467	11.42 470	1.81 484	2.77 507	1.13 509	79.44 482	1.90 507	1.18 502	2.65 503	6.80 499	1.95 506	0.87 503	2.62 501	3.45 501	3.44 499

mmdepth		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

monomultidepth		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

test_blank		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

uanet_test		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

DCPMVS		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

cdsmvs_eth3d_5k		23.35 465	31.13 468	0.00 485	0.00 508	0.00 510	0.00 496	95.58 298	0.00 503	0.00 504	91.15 410	93.43 106	0.00 504	0.00 502	0.00 502	0.00 500

pcd_1.5k_mvsjas		7.56 468	10.09 471	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	90.77 191	0.00 504	0.00 502	0.00 502	0.00 500

sosnet-low-res		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

sosnet		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

uncertanet		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

Regformer		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

ab-mvs-re		7.56 468	10.08 472	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	90.69 420	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

uanet		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

WAC-MVS						61.25 488								74.55 437

FOURS1					99.21 3	94.68 15	98.45 4	98.81 10	97.73 9	98.27 23

test_one_0601					98.26 80	87.14 152		98.18 63	94.25 61	96.99 87	97.36 118	95.13 49

eth-test2					0.00 508

eth-test					0.00 508

ZD-MVS					97.23 156	90.32 85		97.54 161	84.40 335	94.78 226	95.79 258	92.76 132	99.39 54	88.72 255	98.40 219

test_241102_ONE					98.51 58	86.97 157		98.10 79	91.85 122	97.63 43	97.03 156	96.48 13	98.95 134

9.14			94.81 129		97.49 140		94.11 162	98.37 35	87.56 262	95.38 185	96.03 245	94.66 74	99.08 110	90.70 182	98.97 134

save fliter					97.46 143	88.05 134	92.04 264	97.08 205	87.63 260

test0726					98.51 58	86.69 167	95.34 105	98.18 63	91.85 122	97.63 43	97.37 115	95.58 28

test_part2					98.21 84	89.41 99				96.72 100

sam_mvs												66.41 432

MTGPA								97.62 150

test_post1							90.21 338				5.85 502	65.36 438	96.00 415	79.61 399

test_post											6.07 501	65.74 436	95.84 419

patchmatchnet-post											91.71 403	66.22 434	97.59 335

MTMP							94.82 129	54.62 502

gm-plane-assit					87.08 483	59.33 491			71.22 461		83.58 476		97.20 363	73.95 444

TEST9					96.45 226	89.46 96	90.60 323	96.92 217	79.09 406	90.49 369	94.39 329	91.31 173	98.88 141

test_8					96.37 235	89.14 106	90.51 326	96.89 220	79.37 401	90.42 371	94.36 332	91.20 178	98.82 150

agg_prior					96.20 257	88.89 111		96.88 225		90.21 377			98.78 163

test_prior4						89.91 89	90.74 318

test_prior2							90.21 338		89.33 205	90.77 364	94.81 306	90.41 201		88.21 267	98.55 202

旧先验2							90.00 347		68.65 476	92.71 313			96.52 396	85.15 326

新几何2							90.02 346

原ACMM2							89.34 367

testdata2													98.03 287	80.24 389

segment_acmp												92.14 149

testdata1							88.96 377		88.44 233

plane_prior7					97.71 124	88.68 115

plane_prior6					97.21 159	88.23 128						86.93 268

plane_prior4											95.59 271

plane_prior3						88.43 126			90.35 181	93.31 280

plane_prior2							94.56 143		91.74 133

plane_prior1					97.38 147

plane_prior						88.12 132	93.01 206		88.98 213						98.06 265

n2								0.00 509

nn								0.00 509

door-mid								92.13 391

test11								96.65 246

door								91.26 403

HQP5-MVS						84.89 213

HQP-NCC					96.36 237		91.37 293		87.16 270	88.81 406

ACMP_Plane					96.36 237		91.37 293		87.16 270	88.81 406

BP-MVS														86.55 305

HQP3-MVS								97.31 185							97.73 291

HQP2-MVS												84.76 296

NP-MVS					96.82 188	87.10 153					93.40 363

MDTV_nov1_ep13			83.88 411		89.42 468	61.52 486	88.74 387	87.41 433	73.99 442	84.96 450	94.01 344	65.25 439	95.53 422	78.02 409	93.16 443

ACMMP++_ref															98.82 158

ACMMP++															99.25 91

Test By Simon												90.61 197

High-resolution multi-view benchmark