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.

ANet_high		99.88 4	99.87 4	99.91 2	99.99 1	99.91 3	99.65 54	100.00 1	99.90 6	100.00 1	99.97 10	99.61 17	99.97 16	99.75 31	100.00 1	99.84 15

wuykxyi23d		99.65 41	99.64 36	99.69 78	99.92 19	99.20 185	98.89 211	99.99 2	98.73 194	99.95 16	99.80 63	99.84 4	99.99 4	99.64 37	99.98 36	99.89 9

LCM-MVSNet-Re		99.28 117	99.15 123	99.67 84	99.33 266	99.76 41	99.34 106	99.97 3	98.93 168	99.91 33	99.79 70	98.68 116	99.93 66	96.80 249	99.56 228	99.30 229

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 3	99.99 1	100.00 1	99.98 8	99.78 8	100.00 1	99.92 3	100.00 1	99.87 10

UA-Net		99.78 15	99.76 18	99.86 18	99.72 130	99.71 51	99.91 3	99.95 5	99.96 2	99.71 106	99.91 20	99.15 53	99.97 16	99.50 48	100.00 1	99.90 5

Anonymous20231211		99.83 11	99.81 10	99.89 6	99.97 4	99.95 2	99.88 4	99.93 6	99.87 13	99.94 20	99.98 8	99.55 21	99.95 41	99.21 79	99.98 36	99.78 31

testmv		99.53 65	99.51 66	99.59 126	99.73 120	99.31 156	98.48 258	99.92 7	99.57 84	99.87 51	99.79 70	99.12 58	99.91 92	99.16 91	99.99 20	99.55 146

Vis-MVSNet		99.75 19	99.74 21	99.79 34	99.88 28	99.66 70	99.69 38	99.92 7	99.67 58	99.77 86	99.75 92	99.61 17	99.98 7	99.35 62	99.98 36	99.72 46
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TDRefinement		99.72 25	99.70 28	99.77 39	99.90 25	99.85 13	99.86 7	99.92 7	99.69 53	99.78 82	99.92 17	99.37 30	99.88 139	98.93 121	99.95 65	99.60 123

LTVRE_ROB	99.19 1	99.88 4	99.87 4	99.88 12	99.91 21	99.90 4	99.96 1	99.92 7	99.90 6	99.97 6	99.87 37	99.81 7	99.95 41	99.54 44	99.99 20	99.80 25
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
Effi-MVS+		99.06 165	98.97 171	99.34 200	99.31 268	98.98 207	98.31 275	99.91 11	98.81 181	98.79 276	98.94 309	99.14 54	99.84 210	98.79 129	98.74 306	99.20 240

pmmvs6		99.86 6	99.86 6	99.83 24	99.94 15	99.90 4	99.83 8	99.91 11	99.85 19	99.94 20	99.95 12	99.73 10	99.90 109	99.65 35	99.97 47	99.69 56

PVSNet_Blended_VisFu		99.40 90	99.38 84	99.44 173	99.90 25	98.66 235	98.94 209	99.91 11	97.97 250	99.79 79	99.73 98	99.05 69	99.97 16	99.15 92	99.99 20	99.68 62

PMMVS2		99.48 70	99.45 73	99.57 136	99.76 103	98.99 206	98.09 293	99.90 14	98.95 165	99.78 82	99.58 184	99.57 20	99.93 66	99.48 49	99.95 65	99.79 30

testgi		99.29 116	99.26 112	99.37 195	99.75 111	98.81 228	98.84 220	99.89 15	98.38 221	99.75 90	99.04 297	99.36 33	99.86 178	99.08 102	99.25 276	99.45 190

test20.03		99.55 54	99.54 53	99.58 130	99.79 82	99.37 143	99.02 192	99.89 15	99.60 80	99.82 65	99.62 166	98.81 90	99.89 124	99.43 53	99.86 126	99.47 184

testus		98.15 257	98.06 250	98.40 285	99.11 298	95.95 312	96.77 340	99.89 15	95.83 314	99.23 226	98.47 332	97.50 218	99.84 210	96.58 261	99.20 281	99.39 208

mvs_tets		99.90 2	99.90 2	99.90 4	99.96 5	99.79 33	99.72 25	99.88 18	99.92 5	99.98 3	99.93 14	99.94 2	99.98 7	99.77 30	100.00 1	99.92 3

CHOSEN 1792x2688		99.39 93	99.30 101	99.65 96	99.88 28	99.25 172	98.78 231	99.88 18	98.66 198	99.96 8	99.79 70	97.45 220	99.93 66	99.34 63	99.99 20	99.78 31

Patchmatch-RL test		98.60 221	98.36 230	99.33 202	99.77 98	99.07 202	98.27 276	99.87 20	98.91 171	99.74 98	99.72 104	90.57 313	99.79 260	98.55 145	99.85 129	99.11 258

pm-mvs1		99.79 14	99.79 13	99.78 37	99.91 21	99.83 22	99.76 16	99.87 20	99.73 42	99.89 38	99.87 37	99.63 15	99.87 158	99.54 44	99.92 88	99.63 99

jajsoiax		99.89 3	99.89 3	99.89 6	99.96 5	99.78 35	99.70 29	99.86 22	99.89 10	99.98 3	99.90 23	99.94 2	99.98 7	99.75 31	100.00 1	99.90 5

v13		99.76 17	99.77 14	99.73 62	99.86 35	99.55 95	99.77 13	99.86 22	99.79 33	99.96 8	99.91 20	98.90 83	99.87 158	99.91 5	100.00 1	99.78 31

v12		99.75 19	99.77 14	99.72 67	99.85 39	99.53 98	99.75 17	99.86 22	99.78 34	99.96 8	99.90 23	98.88 86	99.86 178	99.91 5	100.00 1	99.77 34

V9		99.74 23	99.75 20	99.71 71	99.84 42	99.50 99	99.74 19	99.86 22	99.76 38	99.96 8	99.90 23	98.83 89	99.85 194	99.91 5	100.00 1	99.77 34

PM-MVS		99.36 100	99.29 106	99.58 130	99.83 46	99.66 70	98.95 206	99.86 22	98.85 176	99.81 71	99.73 98	98.40 157	99.92 83	98.36 154	99.83 143	99.17 247

TransMVSNet (Re)		99.78 15	99.77 14	99.81 27	99.91 21	99.85 13	99.75 17	99.86 22	99.70 49	99.91 33	99.89 31	99.60 19	99.87 158	99.59 39	99.74 189	99.71 49

Baseline_NR-MVSNet		99.49 68	99.37 87	99.82 25	99.91 21	99.84 18	98.83 222	99.86 22	99.68 56	99.65 125	99.88 34	97.67 209	99.87 158	99.03 105	99.86 126	99.76 37

anonymousdsp		99.80 13	99.77 14	99.90 4	99.96 5	99.88 8	99.73 21	99.85 29	99.70 49	99.92 31	99.93 14	99.45 23	99.97 16	99.36 61	100.00 1	99.85 14

PS-MVSNAJss		99.84 9	99.82 9	99.89 6	99.96 5	99.77 37	99.68 41	99.85 29	99.95 3	99.98 3	99.92 17	99.28 39	99.98 7	99.75 31	100.00 1	99.94 2

v15		99.72 25	99.73 24	99.68 81	99.82 53	99.44 116	99.70 29	99.85 29	99.72 45	99.95 16	99.88 34	98.76 104	99.84 210	99.90 9	100.00 1	99.75 40

V14		99.73 24	99.74 21	99.69 78	99.83 46	99.48 104	99.72 25	99.85 29	99.74 40	99.96 8	99.89 31	98.79 97	99.85 194	99.91 5	100.00 1	99.76 37

EU-MVSNet		99.39 93	99.62 38	98.72 273	99.88 28	96.44 305	99.56 70	99.85 29	99.90 6	99.90 35	99.85 45	98.09 178	99.83 226	99.58 41	99.95 65	99.90 5

OurMVSNet-221017-0		99.75 19	99.71 25	99.84 21	99.96 5	99.83 22	99.83 8	99.85 29	99.80 31	99.93 26	99.93 14	98.54 139	99.93 66	99.59 39	99.98 36	99.76 37

CSCG		99.37 97	99.29 106	99.60 124	99.71 133	99.46 109	99.43 82	99.85 29	98.79 184	99.41 188	99.60 176	98.92 80	99.92 83	98.02 180	99.92 88	99.43 201

PNet_i23d		97.02 291	97.87 264	94.49 337	99.69 142	84.81 356	95.18 349	99.85 29	97.83 260	99.32 212	99.57 191	95.53 271	99.47 342	96.09 276	97.74 341	99.18 245

semantic-postprocess				98.51 278	99.75 111	95.90 315		99.84 37	99.84 23	99.89 38	99.73 98	95.96 266	99.99 4	99.33 65	100.00 1	99.63 99

v11		99.75 19	99.76 18	99.71 71	99.85 39	99.49 101	99.73 21	99.84 37	99.75 39	99.95 16	99.90 23	98.93 79	99.86 178	99.92 3	100.00 1	99.77 34

Gipuma		99.57 47	99.59 43	99.49 159	99.98 3	99.71 51	99.72 25	99.84 37	99.81 28	99.94 20	99.78 79	98.91 82	99.71 293	98.41 151	99.95 65	99.05 274
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
AllTest		99.21 139	99.07 146	99.63 107	99.78 88	99.64 76	99.12 177	99.83 40	98.63 201	99.63 130	99.72 104	98.68 116	99.75 282	96.38 268	99.83 143	99.51 167

TestCases				99.63 107	99.78 88	99.64 76		99.83 40	98.63 201	99.63 130	99.72 104	98.68 116	99.75 282	96.38 268	99.83 143	99.51 167

v18		99.68 33	99.69 29	99.65 96	99.79 82	99.40 131	99.68 41	99.83 40	99.66 62	99.93 26	99.85 45	98.65 123	99.84 210	99.87 18	99.99 20	99.71 49

v17		99.70 28	99.71 25	99.67 84	99.81 61	99.44 116	99.70 29	99.83 40	99.69 53	99.94 20	99.87 37	98.70 112	99.84 210	99.88 14	99.99 20	99.73 43

v16		99.70 28	99.71 25	99.67 84	99.81 61	99.43 122	99.70 29	99.83 40	99.70 49	99.94 20	99.87 37	98.69 114	99.84 210	99.88 14	99.99 20	99.73 43

door-mid								99.83 40

IterMVS		98.97 183	99.16 121	98.42 283	99.74 117	95.64 322	98.06 298	99.83 40	99.83 26	99.85 57	99.74 94	96.10 264	99.99 4	99.27 77	100.00 1	99.63 99
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		98.91 194	98.64 205	99.73 62	99.85 39	99.47 105	98.07 297	99.83 40	98.64 200	99.89 38	99.60 176	92.57 293	100.00 1	99.33 65	99.97 47	99.72 46

Fast-Effi-MVS+-dtu		99.20 141	99.12 130	99.43 176	99.25 278	99.69 62	99.05 187	99.82 48	99.50 90	98.97 254	99.05 294	98.98 73	99.98 7	98.20 167	99.24 278	98.62 296

v7n		99.82 12	99.80 12	99.88 12	99.96 5	99.84 18	99.82 10	99.82 48	99.84 23	99.94 20	99.91 20	99.13 57	99.96 33	99.83 20	99.99 20	99.83 18

DSMNet-mixed		99.48 70	99.65 34	98.95 248	99.71 133	97.27 294	99.50 74	99.82 48	99.59 82	99.41 188	99.85 45	99.62 16	100.00 1	99.53 46	99.89 106	99.59 134

PVSNet_BlendedMVS		99.03 171	99.01 162	99.09 236	99.54 196	97.99 275	98.58 244	99.82 48	97.62 269	99.34 208	99.71 111	98.52 145	99.77 274	97.98 183	99.97 47	99.52 164

PVSNet_Blended		98.70 216	98.59 208	99.02 245	99.54 196	97.99 275	97.58 324	99.82 48	95.70 318	99.34 208	98.98 301	98.52 145	99.77 274	97.98 183	99.83 143	99.30 229

XXY-MVS		99.71 27	99.67 32	99.81 27	99.89 27	99.72 50	99.59 65	99.82 48	99.39 111	99.82 65	99.84 50	99.38 28	99.91 92	99.38 58	99.93 85	99.80 25

1112_ss		99.05 168	98.84 188	99.67 84	99.66 154	99.29 160	98.52 254	99.82 48	97.65 268	99.43 180	99.16 276	96.42 256	99.91 92	99.07 103	99.84 133	99.80 25

RPSCF		99.18 146	99.02 159	99.64 103	99.83 46	99.85 13	99.44 81	99.82 48	98.33 233	99.50 170	99.78 79	97.90 191	99.65 325	96.78 250	99.83 143	99.44 195

pcd1.5k->3k		49.97 328	55.52 329	33.31 341	99.95 13	0.00 359	0.00 350	99.81 56	0.00 354	0.00 355	100.00 1	99.96 1	0.00 357	0.00 354	100.00 1	99.92 3

v52		99.85 7	99.84 7	99.89 6	99.96 5	99.89 6	99.87 5	99.81 56	99.85 19	99.96 8	99.90 23	99.27 42	99.95 41	99.93 1	99.99 20	99.82 23

V4		99.85 7	99.84 7	99.88 12	99.96 5	99.89 6	99.87 5	99.81 56	99.85 19	99.96 8	99.90 23	99.27 42	99.95 41	99.93 1	100.00 1	99.82 23

test12356		98.43 237	98.39 226	98.55 277	99.46 230	96.36 306	97.32 334	99.81 56	97.60 270	99.62 137	99.37 235	94.57 277	99.89 124	97.80 193	99.92 88	99.40 206

v748		99.76 17	99.74 21	99.84 21	99.95 13	99.83 22	99.82 10	99.80 60	99.82 27	99.95 16	99.87 37	98.72 111	99.93 66	99.72 34	99.98 36	99.75 40

1111		97.29 279	96.71 298	99.04 243	99.65 156	97.72 283	98.35 270	99.80 60	99.40 109	99.66 119	99.43 225	75.10 358	99.87 158	98.98 110	99.98 36	99.52 164

.test1245		85.84 327	89.27 328	75.54 340	99.65 156	97.72 283	98.35 270	99.80 60	99.40 109	99.66 119	99.43 225	75.10 358	99.87 158	98.98 110	33.07 352	29.03 353

MVSFormer		99.41 87	99.44 75	99.31 208	99.57 182	98.40 246	99.77 13	99.80 60	99.73 42	99.63 130	99.30 253	98.02 184	99.98 7	99.43 53	99.69 204	99.55 146

test_djsdf		99.84 9	99.81 10	99.91 2	99.94 15	99.84 18	99.77 13	99.80 60	99.73 42	99.97 6	99.92 17	99.77 9	99.98 7	99.43 53	100.00 1	99.90 5

FMVSNet5		97.80 267	97.25 278	99.42 178	98.83 320	98.97 209	99.38 92	99.80 60	98.87 174	99.25 222	99.69 124	80.60 354	99.91 92	98.96 115	99.90 100	99.38 211

Test_1112_low_res		98.95 189	98.73 198	99.63 107	99.68 149	99.15 191	98.09 293	99.80 60	97.14 288	99.46 175	99.40 230	96.11 263	99.89 124	99.01 107	99.84 133	99.84 15

USDC		98.96 186	98.93 174	99.05 242	99.54 196	97.99 275	97.07 337	99.80 60	98.21 239	99.75 90	99.77 85	98.43 153	99.64 327	97.90 186	99.88 112	99.51 167

Fast-Effi-MVS+		99.02 173	98.87 183	99.46 167	99.38 247	99.50 99	99.04 189	99.79 68	97.17 286	98.62 289	98.74 322	99.34 34	99.95 41	98.32 158	99.41 258	98.92 283

ACMH	98.42 6	99.59 45	99.54 53	99.72 67	99.86 35	99.62 82	99.56 70	99.79 68	98.77 187	99.80 74	99.85 45	99.64 14	99.85 194	98.70 137	99.89 106	99.70 53
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tfpnnormal		99.43 81	99.38 84	99.60 124	99.87 32	99.75 43	99.59 65	99.78 70	99.71 47	99.90 35	99.69 124	98.85 88	99.90 109	97.25 227	99.78 173	99.15 249

FC-MVSNet-test		99.70 28	99.65 34	99.86 18	99.88 28	99.86 12	99.72 25	99.78 70	99.90 6	99.82 65	99.83 51	98.45 152	99.87 158	99.51 47	99.97 47	99.86 12

COLMAP_ROB	98.06 12	99.45 79	99.37 87	99.70 77	99.83 46	99.70 58	99.38 92	99.78 70	99.53 87	99.67 115	99.78 79	99.19 49	99.86 178	97.32 221	99.87 119	99.55 146
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test1235678		98.93 193	98.84 188	99.19 229	99.46 230	98.55 239	97.53 327	99.77 73	98.76 190	99.69 110	99.48 216	96.69 247	99.90 109	98.30 160	99.91 98	99.11 258

door								99.77 73

MIMVSNet1		99.66 36	99.62 38	99.80 29	99.94 15	99.87 9	99.69 38	99.77 73	99.78 34	99.93 26	99.89 31	97.94 189	99.92 83	99.65 35	99.98 36	99.62 112

wuyk23d		97.58 273	99.13 127	92.93 338	99.69 142	99.49 101	99.52 72	99.77 73	97.97 250	99.96 8	99.79 70	99.84 4	99.94 55	95.85 290	99.82 152	79.36 351

ACMH+	98.40 8	99.50 66	99.43 78	99.71 71	99.86 35	99.76 41	99.32 111	99.77 73	99.53 87	99.77 86	99.76 88	99.26 45	99.78 268	97.77 194	99.88 112	99.60 123

LF4IMVS		99.01 177	98.92 177	99.27 213	99.71 133	99.28 162	98.59 243	99.77 73	98.32 234	99.39 193	99.41 229	98.62 127	99.84 210	96.62 260	99.84 133	98.69 295

v8		99.68 33	99.69 29	99.65 96	99.80 69	99.40 131	99.66 49	99.76 79	99.64 67	99.93 26	99.85 45	98.66 121	99.84 210	99.88 14	99.99 20	99.71 49

abl_6		99.36 100	99.23 117	99.75 51	99.71 133	99.74 48	99.33 108	99.76 79	99.07 158	99.65 125	99.63 159	99.09 61	99.92 83	97.13 235	99.76 179	99.58 138

114514_t		98.49 232	98.11 247	99.64 103	99.73 120	99.58 89	99.24 140	99.76 79	89.94 345	99.42 182	99.56 196	97.76 202	99.86 178	97.74 196	99.82 152	99.47 184

EG-PatchMatch MVS		99.57 47	99.56 51	99.62 115	99.77 98	99.33 153	99.26 134	99.76 79	99.32 119	99.80 74	99.78 79	99.29 37	99.87 158	99.15 92	99.91 98	99.66 79

IterMVS-LS		99.41 87	99.47 69	99.25 221	99.81 61	98.09 271	98.85 219	99.76 79	99.62 71	99.83 64	99.64 152	98.54 139	99.97 16	99.15 92	99.99 20	99.68 62
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
new-patchmatchnet		99.35 102	99.57 48	98.71 274	99.82 53	96.62 303	98.55 249	99.75 84	99.50 90	99.88 46	99.87 37	99.31 35	99.88 139	99.43 53	100.00 1	99.62 112

FIs		99.65 41	99.58 45	99.84 21	99.84 42	99.85 13	99.66 49	99.75 84	99.86 16	99.74 98	99.79 70	98.27 167	99.85 194	99.37 60	99.93 85	99.83 18

v10		99.69 32	99.69 29	99.66 92	99.81 61	99.39 134	99.66 49	99.75 84	99.60 80	99.92 31	99.87 37	98.75 107	99.86 178	99.90 9	99.99 20	99.73 43

WR-MVS_H		99.61 44	99.53 61	99.87 16	99.80 69	99.83 22	99.67 46	99.75 84	99.58 83	99.85 57	99.69 124	98.18 176	99.94 55	99.28 76	99.95 65	99.83 18

TinyColmap		98.97 183	98.93 174	99.07 240	99.46 230	98.19 263	97.75 320	99.75 84	98.79 184	99.54 161	99.70 118	98.97 75	99.62 330	96.63 259	99.83 143	99.41 205

Anonymous20231206		99.35 102	99.31 96	99.47 164	99.74 117	99.06 204	99.28 130	99.74 89	99.23 134	99.72 102	99.53 205	97.63 215	99.88 139	99.11 100	99.84 133	99.48 180

XVG-OURS		99.21 139	99.06 148	99.65 96	99.82 53	99.62 82	97.87 317	99.74 89	98.36 223	99.66 119	99.68 136	99.71 11	99.90 109	96.84 247	99.88 112	99.43 201

MSDG		99.08 163	98.98 170	99.37 195	99.60 167	99.13 192	97.54 325	99.74 89	98.84 179	99.53 164	99.55 201	99.10 59	99.79 260	97.07 237	99.86 126	99.18 245

MVS_0304		99.17 149	99.10 139	99.38 191	99.08 301	98.86 225	98.46 263	99.73 92	99.53 87	99.35 204	99.30 253	97.11 239	99.96 33	99.33 65	99.99 20	99.33 223

pmmvs5		99.19 144	99.11 132	99.42 178	99.76 103	98.88 222	98.55 249	99.73 92	98.82 180	99.72 102	99.62 166	96.56 250	99.82 233	99.32 68	99.95 65	99.56 143

PS-CasMVS		99.66 36	99.58 45	99.89 6	99.80 69	99.85 13	99.66 49	99.73 92	99.62 71	99.84 60	99.71 111	98.62 127	99.96 33	99.30 71	99.96 59	99.86 12

PEN-MVS		99.66 36	99.59 43	99.89 6	99.83 46	99.87 9	99.66 49	99.73 92	99.70 49	99.84 60	99.73 98	98.56 133	99.96 33	99.29 74	99.94 77	99.83 18

XVG-OURS-SEG-HR		99.16 151	98.99 167	99.66 92	99.84 42	99.64 76	98.25 278	99.73 92	98.39 220	99.63 130	99.43 225	99.70 12	99.90 109	97.34 220	98.64 311	99.44 195

LPG-MVS_test		99.22 136	99.05 152	99.74 55	99.82 53	99.63 80	99.16 164	99.73 92	97.56 272	99.64 127	99.69 124	99.37 30	99.89 124	96.66 257	99.87 119	99.69 56

LGP-MVS_train				99.74 55	99.82 53	99.63 80		99.73 92	97.56 272	99.64 127	99.69 124	99.37 30	99.89 124	96.66 257	99.87 119	99.69 56

MVS_111021_LR		99.13 155	99.03 158	99.42 178	99.58 173	99.32 155	97.91 316	99.73 92	98.68 197	99.31 214	99.48 216	99.09 61	99.66 318	97.70 198	99.77 177	99.29 232

ITE_SJBPF				99.38 191	99.63 160	99.44 116		99.73 92	98.56 206	99.33 210	99.53 205	98.88 86	99.68 308	96.01 282	99.65 217	99.02 277

PGM-MVS		99.20 141	99.01 162	99.77 39	99.75 111	99.71 51	99.16 164	99.72 101	97.99 248	99.42 182	99.60 176	98.81 90	99.93 66	96.91 243	99.74 189	99.66 79

MDA-MVSNet-bldmvs		99.06 165	99.05 152	99.07 240	99.80 69	97.83 281	98.89 211	99.72 101	99.29 120	99.63 130	99.70 118	96.47 254	99.89 124	98.17 173	99.82 152	99.50 173

XVG-ACMP-BASELINE		99.23 128	99.10 139	99.63 107	99.82 53	99.58 89	98.83 222	99.72 101	98.36 223	99.60 144	99.71 111	98.92 80	99.91 92	97.08 236	99.84 133	99.40 206

DTE-MVSNet		99.68 33	99.61 41	99.88 12	99.80 69	99.87 9	99.67 46	99.71 104	99.72 45	99.84 60	99.78 79	98.67 119	99.97 16	99.30 71	99.95 65	99.80 25

MVS_111021_HR		99.12 157	99.02 159	99.40 186	99.50 210	99.11 194	97.92 314	99.71 104	98.76 190	99.08 244	99.47 219	99.17 51	99.54 338	97.85 190	99.76 179	99.54 153

DeepC-MVS	98.90 4	99.62 43	99.61 41	99.67 84	99.72 130	99.44 116	99.24 140	99.71 104	99.27 123	99.93 26	99.90 23	99.70 12	99.93 66	98.99 108	99.99 20	99.64 95
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
nrg030		99.70 28	99.66 33	99.82 25	99.76 103	99.84 18	99.61 60	99.70 107	99.93 4	99.78 82	99.68 136	99.10 59	99.78 268	99.45 51	99.96 59	99.83 18

VPNet		99.46 77	99.37 87	99.71 71	99.82 53	99.59 87	99.48 78	99.70 107	99.81 28	99.69 110	99.58 184	97.66 213	99.86 178	99.17 88	99.44 249	99.67 69

HPM-MVS_fast		99.43 81	99.30 101	99.80 29	99.83 46	99.81 28	99.52 72	99.70 107	98.35 228	99.51 168	99.50 214	99.31 35	99.88 139	98.18 171	99.84 133	99.69 56

GBi-Net		99.42 84	99.31 96	99.73 62	99.49 215	99.77 37	99.68 41	99.70 107	99.44 101	99.62 137	99.83 51	97.21 233	99.90 109	98.96 115	99.90 100	99.53 156

test1		99.42 84	99.31 96	99.73 62	99.49 215	99.77 37	99.68 41	99.70 107	99.44 101	99.62 137	99.83 51	97.21 233	99.90 109	98.96 115	99.90 100	99.53 156

FMVSNet1		99.66 36	99.63 37	99.73 62	99.78 88	99.77 37	99.68 41	99.70 107	99.67 58	99.82 65	99.83 51	98.98 73	99.90 109	99.24 78	99.97 47	99.53 156

APDe-MVS		99.48 70	99.36 90	99.85 20	99.55 195	99.81 28	99.50 74	99.69 113	98.99 162	99.75 90	99.71 111	98.79 97	99.93 66	98.46 149	99.85 129	99.80 25

VPA-MVSNet		99.66 36	99.62 38	99.79 34	99.68 149	99.75 43	99.62 56	99.69 113	99.85 19	99.80 74	99.81 61	98.81 90	99.91 92	99.47 50	99.88 112	99.70 53

OpenMVS	98.12 10	98.23 254	97.89 263	99.26 218	99.19 287	99.26 168	99.65 54	99.69 113	91.33 343	98.14 316	99.77 85	98.28 166	99.96 33	95.41 309	99.55 234	98.58 300

UnsupCasMVSNet_bld		98.55 227	98.27 236	99.40 186	99.56 193	99.37 143	97.97 309	99.68 116	97.49 277	99.08 244	99.35 245	95.41 272	99.82 233	97.70 198	98.19 332	99.01 278

test_0402		99.22 136	99.14 124	99.45 171	99.79 82	99.43 122	99.28 130	99.68 116	99.54 85	99.40 192	99.56 196	99.07 66	99.82 233	96.01 282	99.96 59	99.11 258

LS3D		99.24 127	99.11 132	99.61 118	98.38 340	99.79 33	99.57 68	99.68 116	99.61 75	99.15 238	99.71 111	98.70 112	99.91 92	97.54 210	99.68 206	99.13 256

HPM-MVS		99.25 124	99.07 146	99.78 37	99.81 61	99.75 43	99.61 60	99.67 119	97.72 263	99.35 204	99.25 263	99.23 46	99.92 83	97.21 231	99.82 152	99.67 69

CR-MVSNet		98.35 247	98.20 241	98.83 262	99.05 304	98.12 267	99.30 121	99.67 119	97.39 281	99.16 236	99.79 70	91.87 299	99.91 92	98.78 132	98.77 302	98.44 306

Patchmtry		98.78 210	98.54 215	99.49 159	98.89 314	99.19 187	99.32 111	99.67 119	99.65 65	99.72 102	99.79 70	91.87 299	99.95 41	98.00 182	99.97 47	99.33 223

UnsupCasMVSNet_eth		98.83 203	98.57 212	99.59 126	99.68 149	99.45 114	98.99 199	99.67 119	99.48 92	99.55 158	99.36 240	94.92 273	99.86 178	98.95 119	96.57 346	99.45 190

Effi-MVS+-dtu		99.07 164	98.92 177	99.52 152	98.89 314	99.78 35	99.15 166	99.66 123	99.34 116	98.92 264	99.24 268	97.69 206	99.98 7	98.11 176	99.28 272	98.81 291

xiu_mvs_v1_base_debu		99.23 128	99.34 92	98.91 252	99.59 170	98.23 260	98.47 259	99.66 123	99.61 75	99.68 112	98.94 309	99.39 24	99.97 16	99.18 85	99.55 234	98.51 303

mvs-test1		98.83 203	98.70 200	99.22 225	98.89 314	99.65 74	98.88 213	99.66 123	99.34 116	98.29 305	98.94 309	97.69 206	99.96 33	98.11 176	98.54 321	98.04 323

xiu_mvs_v1_base		99.23 128	99.34 92	98.91 252	99.59 170	98.23 260	98.47 259	99.66 123	99.61 75	99.68 112	98.94 309	99.39 24	99.97 16	99.18 85	99.55 234	98.51 303

pmmvs-eth3d		99.48 70	99.47 69	99.51 155	99.77 98	99.41 130	98.81 226	99.66 123	99.42 108	99.75 90	99.66 146	99.20 48	99.76 276	98.98 110	99.99 20	99.36 218

xiu_mvs_v1_base_debi		99.23 128	99.34 92	98.91 252	99.59 170	98.23 260	98.47 259	99.66 123	99.61 75	99.68 112	98.94 309	99.39 24	99.97 16	99.18 85	99.55 234	98.51 303

canonicalmvs		99.02 173	99.00 164	99.09 236	99.10 300	98.70 232	99.61 60	99.66 123	99.63 70	98.64 288	97.65 346	99.04 70	99.54 338	98.79 129	98.92 291	99.04 275

pmmvs3		98.08 261	97.80 266	98.91 252	99.41 240	97.69 286	97.87 317	99.66 123	95.87 313	99.50 170	99.51 211	90.35 315	99.97 16	98.55 145	99.47 246	99.08 268

ACMP	97.51 14	99.05 168	98.84 188	99.67 84	99.78 88	99.55 95	98.88 213	99.66 123	97.11 291	99.47 173	99.60 176	99.07 66	99.89 124	96.18 274	99.85 129	99.58 138
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v1240		99.56 50	99.58 45	99.51 155	99.80 69	99.00 205	99.00 196	99.65 132	99.15 147	99.90 35	99.75 92	99.09 61	99.88 139	99.90 9	99.96 59	99.67 69

ACMMP		99.25 124	99.08 142	99.74 55	99.79 82	99.68 65	99.50 74	99.65 132	98.07 244	99.52 166	99.69 124	98.57 132	99.92 83	97.18 233	99.79 168	99.63 99
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
PHI-MVS		99.11 160	98.95 173	99.59 126	99.13 293	99.59 87	99.17 158	99.65 132	97.88 254	99.25 222	99.46 222	98.97 75	99.80 257	97.26 226	99.82 152	99.37 215

F-COLMAP		98.74 213	98.45 218	99.62 115	99.57 182	99.47 105	98.84 220	99.65 132	96.31 307	98.93 262	99.19 275	97.68 208	99.87 158	96.52 263	99.37 263	99.53 156

ACMM	98.09 11	99.46 77	99.38 84	99.72 67	99.80 69	99.69 62	99.13 176	99.65 132	98.99 162	99.64 127	99.72 104	99.39 24	99.86 178	98.23 164	99.81 160	99.60 123
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CVMVSNet		98.61 220	98.88 182	97.80 307	99.58 173	93.60 334	99.26 134	99.64 137	99.66 62	99.72 102	99.67 142	93.26 287	99.93 66	99.30 71	99.81 160	99.87 10

diffmvs		98.94 192	98.87 183	99.13 233	99.37 249	98.90 219	99.25 138	99.64 137	97.55 274	99.04 249	99.58 184	97.23 232	99.64 327	98.73 135	99.44 249	98.86 287

OMC-MVS		98.90 196	98.72 199	99.44 173	99.39 244	99.42 126	98.58 244	99.64 137	97.31 284	99.44 176	99.62 166	98.59 131	99.69 300	96.17 275	99.79 168	99.22 236

MP-MVS-pluss		99.14 154	98.92 177	99.80 29	99.83 46	99.83 22	98.61 240	99.63 140	96.84 295	99.44 176	99.58 184	98.81 90	99.91 92	97.70 198	99.82 152	99.67 69
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TranMVSNet+NR-MVSNet		99.54 59	99.47 69	99.76 42	99.58 173	99.64 76	99.30 121	99.63 140	99.61 75	99.71 106	99.56 196	98.76 104	99.96 33	99.14 98	99.92 88	99.68 62

DP-MVS Recon		98.50 230	98.23 238	99.31 208	99.49 215	99.46 109	98.56 248	99.63 140	94.86 330	98.85 271	99.37 235	97.81 198	99.59 335	96.08 277	99.44 249	98.88 285

cdsmvs_eth3d_5k		24.88 331	33.17 331	0.00 344	0.00 358	0.00 359	0.00 350	99.62 143	0.00 354	0.00 355	99.13 278	99.82 6	0.00 357	0.00 354	0.00 355	0.00 355

v144192		99.55 54	99.54 53	99.58 130	99.78 88	99.20 185	99.11 178	99.62 143	99.18 140	99.89 38	99.72 104	98.66 121	99.87 158	99.88 14	99.97 47	99.66 79

CP-MVS		99.23 128	99.05 152	99.75 51	99.66 154	99.66 70	99.38 92	99.62 143	98.38 221	99.06 248	99.27 259	98.79 97	99.94 55	97.51 212	99.82 152	99.66 79

TAPA-MVS	97.92 13	98.03 263	97.55 275	99.46 167	99.47 226	99.44 116	98.50 256	99.62 143	86.79 346	99.07 247	99.26 261	98.26 168	99.62 330	97.28 225	99.73 195	99.31 228
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
v1921920		99.56 50	99.57 48	99.55 145	99.75 111	99.11 194	99.05 187	99.61 147	99.15 147	99.88 46	99.71 111	99.08 64	99.87 158	99.90 9	99.97 47	99.66 79

v1144		99.54 59	99.53 61	99.59 126	99.79 82	99.28 162	99.10 179	99.61 147	99.20 138	99.84 60	99.73 98	98.67 119	99.84 210	99.86 19	99.98 36	99.64 95

v1141		99.54 59	99.52 63	99.57 136	99.78 88	99.27 166	99.15 166	99.61 147	99.26 127	99.89 38	99.69 124	98.56 133	99.82 233	99.82 23	99.97 47	99.63 99

v1neww		99.55 54	99.54 53	99.61 118	99.80 69	99.39 134	99.32 111	99.61 147	99.18 140	99.87 51	99.69 124	98.64 125	99.82 233	99.79 26	99.94 77	99.60 123

v7new		99.55 54	99.54 53	99.61 118	99.80 69	99.39 134	99.32 111	99.61 147	99.18 140	99.87 51	99.69 124	98.64 125	99.82 233	99.79 26	99.94 77	99.60 123

XVS		99.27 122	99.11 132	99.75 51	99.71 133	99.71 51	99.37 96	99.61 147	99.29 120	98.76 279	99.47 219	98.47 149	99.88 139	97.62 205	99.73 195	99.67 69

X-MVStestdata		96.09 316	94.87 324	99.75 51	99.71 133	99.71 51	99.37 96	99.61 147	99.29 120	98.76 279	61.30 358	98.47 149	99.88 139	97.62 205	99.73 195	99.67 69

divwei89l23v2f112		99.54 59	99.52 63	99.57 136	99.78 88	99.27 166	99.15 166	99.61 147	99.26 127	99.89 38	99.69 124	98.56 133	99.82 233	99.82 23	99.96 59	99.63 99

v1		99.54 59	99.52 63	99.58 130	99.77 98	99.28 162	99.15 166	99.61 147	99.26 127	99.88 46	99.68 136	98.56 133	99.82 233	99.82 23	99.97 47	99.63 99

SD-MVS		99.01 177	99.30 101	98.15 294	99.50 210	99.40 131	98.94 209	99.61 147	99.22 137	99.75 90	99.82 58	99.54 22	95.51 354	97.48 213	99.87 119	99.54 153

APD-MVS_3200maxsize		99.31 113	99.16 121	99.74 55	99.53 199	99.75 43	99.27 133	99.61 147	99.19 139	99.57 148	99.64 152	98.76 104	99.90 109	97.29 223	99.62 220	99.56 143

UniMVSNet_NR-MVSNet		99.37 97	99.25 114	99.72 67	99.47 226	99.56 92	98.97 204	99.61 147	99.43 106	99.67 115	99.28 257	97.85 196	99.95 41	99.17 88	99.81 160	99.65 89

CP-MVSNet		99.54 59	99.43 78	99.87 16	99.76 103	99.82 27	99.57 68	99.61 147	99.54 85	99.80 74	99.64 152	97.79 200	99.95 41	99.21 79	99.94 77	99.84 15

DP-MVS		99.48 70	99.39 82	99.74 55	99.57 182	99.62 82	99.29 129	99.61 147	99.87 13	99.74 98	99.76 88	98.69 114	99.87 158	98.20 167	99.80 165	99.75 40

v1192		99.57 47	99.57 48	99.57 136	99.77 98	99.22 179	99.04 189	99.60 161	99.18 140	99.87 51	99.72 104	99.08 64	99.85 194	99.89 13	99.98 36	99.66 79

v6		99.55 54	99.54 53	99.61 118	99.80 69	99.39 134	99.32 111	99.60 161	99.18 140	99.87 51	99.68 136	98.65 123	99.82 233	99.79 26	99.95 65	99.61 117

UniMVSNet (Re)		99.37 97	99.26 112	99.68 81	99.51 205	99.58 89	98.98 203	99.60 161	99.43 106	99.70 108	99.36 240	97.70 204	99.88 139	99.20 82	99.87 119	99.59 134

SteuartSystems-ACMMP		99.30 114	99.14 124	99.76 42	99.87 32	99.66 70	99.18 152	99.60 161	98.55 207	99.57 148	99.67 142	99.03 71	99.94 55	97.01 239	99.80 165	99.69 56
Skip Steuart: Steuart Systems R&D Blog.
HFP-MVS		99.25 124	99.08 142	99.76 42	99.73 120	99.70 58	99.31 118	99.59 165	98.36 223	99.36 202	99.37 235	98.80 94	99.91 92	97.43 216	99.75 182	99.68 62

v148		99.40 90	99.41 80	99.39 189	99.76 103	98.94 212	99.09 183	99.59 165	99.17 145	99.81 71	99.61 173	98.41 155	99.69 300	99.32 68	99.94 77	99.53 156

region2R		99.23 128	99.05 152	99.77 39	99.76 103	99.70 58	99.31 118	99.59 165	98.41 218	99.32 212	99.36 240	98.73 110	99.93 66	97.29 223	99.74 189	99.67 69

#test#		99.12 157	98.90 180	99.76 42	99.73 120	99.70 58	99.10 179	99.59 165	97.60 270	99.36 202	99.37 235	98.80 94	99.91 92	96.84 247	99.75 182	99.68 62

v7		99.56 50	99.54 53	99.61 118	99.80 69	99.39 134	99.30 121	99.59 165	99.14 149	99.82 65	99.72 104	98.75 107	99.84 210	99.83 20	99.94 77	99.61 117

V42		99.56 50	99.54 53	99.63 107	99.79 82	99.46 109	99.39 86	99.59 165	99.24 132	99.86 56	99.70 118	98.55 137	99.82 233	99.79 26	99.95 65	99.60 123

ACMMPR		99.23 128	99.06 148	99.76 42	99.74 117	99.69 62	99.31 118	99.59 165	98.36 223	99.35 204	99.38 234	98.61 129	99.93 66	97.43 216	99.75 182	99.67 69

CMPMVS	77.52 23	98.50 230	98.19 244	99.41 185	98.33 341	99.56 92	99.01 194	99.59 165	95.44 321	99.57 148	99.80 63	95.64 268	99.46 345	96.47 267	99.92 88	99.21 239
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v2v482		99.50 66	99.47 69	99.58 130	99.78 88	99.25 172	99.14 171	99.58 173	99.25 130	99.81 71	99.62 166	98.24 169	99.84 210	99.83 20	99.97 47	99.64 95

APD-MVS		98.87 200	98.59 208	99.71 71	99.50 210	99.62 82	99.01 194	99.57 174	96.80 297	99.54 161	99.63 159	98.29 165	99.91 92	95.24 312	99.71 201	99.61 117
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
FMVSNet2		99.35 102	99.28 108	99.55 145	99.49 215	99.35 150	99.45 79	99.57 174	99.44 101	99.70 108	99.74 94	97.21 233	99.87 158	99.03 105	99.94 77	99.44 195

TAMVS		99.49 68	99.45 73	99.63 107	99.48 221	99.42 126	99.45 79	99.57 174	99.66 62	99.78 82	99.83 51	97.85 196	99.86 178	99.44 52	99.96 59	99.61 117

cascas		96.99 292	96.82 290	97.48 314	97.57 350	95.64 322	96.43 344	99.56 177	91.75 341	97.13 341	97.61 347	95.58 270	98.63 351	96.68 256	99.11 283	98.18 320

Vis-MVSNet (Re-imp)		98.77 211	98.58 210	99.34 200	99.78 88	98.88 222	99.61 60	99.56 177	99.11 152	99.24 225	99.56 196	93.00 291	99.78 268	97.43 216	99.89 106	99.35 220

3Dnovator	99.15 2	99.43 81	99.36 90	99.65 96	99.39 244	99.42 126	99.70 29	99.56 177	99.23 134	99.35 204	99.80 63	99.17 51	99.95 41	98.21 166	99.84 133	99.59 134

MVP-Stereo		99.16 151	99.08 142	99.43 176	99.48 221	99.07 202	99.08 184	99.55 180	98.63 201	99.31 214	99.68 136	98.19 175	99.78 268	98.18 171	99.58 227	99.45 190
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
mvs_anonymous		99.28 117	99.39 82	98.94 249	99.19 287	97.81 282	99.02 192	99.55 180	99.78 34	99.85 57	99.80 63	98.24 169	99.86 178	99.57 42	99.50 242	99.15 249

CPTT-MVS		98.74 213	98.44 219	99.64 103	99.61 166	99.38 140	99.18 152	99.55 180	96.49 305	99.27 219	99.37 235	97.11 239	99.92 83	95.74 295	99.67 212	99.62 112

CLD-MVS		98.76 212	98.57 212	99.33 202	99.57 182	98.97 209	97.53 327	99.55 180	96.41 306	99.27 219	99.13 278	99.07 66	99.78 268	96.73 254	99.89 106	99.23 235
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
HQP_MVS		98.90 196	98.68 202	99.55 145	99.58 173	99.24 175	98.80 227	99.54 184	98.94 166	99.14 239	99.25 263	97.24 230	99.82 233	95.84 291	99.78 173	99.60 123

plane_prior5								99.54 184					99.82 233	95.84 291	99.78 173	99.60 123

mPP-MVS		99.19 144	99.00 164	99.76 42	99.76 103	99.68 65	99.38 92	99.54 184	98.34 232	99.01 251	99.50 214	98.53 143	99.93 66	97.18 233	99.78 173	99.66 79

CDS-MVSNet		99.22 136	99.13 127	99.50 157	99.35 252	99.11 194	98.96 205	99.54 184	99.46 99	99.61 142	99.70 118	96.31 258	99.83 226	99.34 63	99.88 112	99.55 146
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PatchMatch-RL		98.68 217	98.47 217	99.30 210	99.44 234	99.28 162	98.14 287	99.54 184	97.12 290	99.11 242	99.25 263	97.80 199	99.70 294	96.51 264	99.30 270	98.93 282

test_part1								99.53 189				98.40 157			99.68 206	99.66 79

ESAPD		98.87 200	98.58 210	99.74 55	99.62 164	99.67 67	98.74 233	99.53 189	97.71 264	99.55 158	99.57 191	98.40 157	99.90 109	94.47 321	99.68 206	99.66 79

ACMMP_Plus		99.28 117	99.11 132	99.79 34	99.75 111	99.81 28	98.95 206	99.53 189	98.27 237	99.53 164	99.73 98	98.75 107	99.87 158	97.70 198	99.83 143	99.68 62

MPTG		99.30 114	99.14 124	99.80 29	99.81 61	99.81 28	98.73 236	99.53 189	99.27 123	99.42 182	99.63 159	98.21 172	99.95 41	97.83 191	99.79 168	99.65 89

MTGPA								99.53 189

MTAPA		99.35 102	99.20 120	99.80 29	99.81 61	99.81 28	99.33 108	99.53 189	99.27 123	99.42 182	99.63 159	98.21 172	99.95 41	97.83 191	99.79 168	99.65 89

Regformer-4		99.45 79	99.44 75	99.50 157	99.52 201	98.94 212	99.17 158	99.53 189	99.64 67	99.76 89	99.60 176	98.96 78	99.90 109	98.91 122	99.84 133	99.67 69

Regformer-2		99.34 107	99.27 110	99.53 150	99.41 240	99.10 197	98.99 199	99.53 189	99.47 96	99.66 119	99.52 207	98.80 94	99.89 124	98.31 159	99.74 189	99.60 123

DU-MVS		99.33 110	99.21 119	99.71 71	99.43 236	99.56 92	98.83 222	99.53 189	99.38 112	99.67 115	99.36 240	97.67 209	99.95 41	99.17 88	99.81 160	99.63 99

DELS-MVS		99.34 107	99.30 101	99.48 162	99.51 205	99.36 146	98.12 289	99.53 189	99.36 115	99.41 188	99.61 173	99.22 47	99.87 158	99.21 79	99.68 206	99.20 240
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
no-one		99.28 117	99.23 117	99.45 171	99.87 32	99.08 200	98.95 206	99.52 199	98.88 173	99.77 86	99.83 51	97.78 201	99.90 109	98.46 149	99.99 20	99.38 211

QAPM		98.40 242	97.99 253	99.65 96	99.39 244	99.47 105	99.67 46	99.52 199	91.70 342	98.78 278	99.80 63	98.55 137	99.95 41	94.71 319	99.75 182	99.53 156

xiu_mvs_v2_base		99.02 173	99.11 132	98.77 266	99.37 249	98.09 271	98.13 288	99.51 201	99.47 96	99.42 182	98.54 329	99.38 28	99.97 16	98.83 126	99.33 267	98.24 315

PS-MVSNAJ		99.00 180	99.08 142	98.76 267	99.37 249	98.10 270	98.00 303	99.51 201	99.47 96	99.41 188	98.50 331	99.28 39	99.97 16	98.83 126	99.34 265	98.20 319

PLC	97.35 16	98.36 244	97.99 253	99.48 162	99.32 267	99.24 175	98.50 256	99.51 201	95.19 326	98.58 293	98.96 306	96.95 244	99.83 226	95.63 302	99.25 276	99.37 215
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MP-MVS		99.06 165	98.83 191	99.76 42	99.76 103	99.71 51	99.32 111	99.50 204	98.35 228	98.97 254	99.48 216	98.37 160	99.92 83	95.95 288	99.75 182	99.63 99

NR-MVSNet		99.40 90	99.31 96	99.68 81	99.43 236	99.55 95	99.73 21	99.50 204	99.46 99	99.88 46	99.36 240	97.54 216	99.87 158	98.97 114	99.87 119	99.63 99

new_pmnet		98.88 199	98.89 181	98.84 260	99.70 140	97.62 288	98.15 285	99.50 204	97.98 249	99.62 137	99.54 203	98.15 177	99.94 55	97.55 209	99.84 133	98.95 280

3Dnovator+	98.92 3	99.35 102	99.24 115	99.67 84	99.35 252	99.47 105	99.62 56	99.50 204	99.44 101	99.12 241	99.78 79	98.77 103	99.94 55	97.87 188	99.72 200	99.62 112

MVS_Test		99.28 117	99.31 96	99.19 229	99.35 252	98.79 230	99.36 98	99.49 208	99.17 145	99.21 230	99.67 142	98.78 100	99.66 318	99.09 101	99.66 215	99.10 262

OPM-MVS		99.26 123	99.13 127	99.63 107	99.70 140	99.61 86	98.58 244	99.48 209	98.50 211	99.52 166	99.63 159	99.14 54	99.76 276	97.89 187	99.77 177	99.51 167

Regformer-1		99.32 112	99.27 110	99.47 164	99.41 240	98.95 211	98.99 199	99.48 209	99.48 92	99.66 119	99.52 207	98.78 100	99.87 158	98.36 154	99.74 189	99.60 123

FMVSNet3		98.80 208	98.63 206	99.32 206	99.13 293	98.72 231	99.10 179	99.48 209	99.23 134	99.62 137	99.64 152	92.57 293	99.86 178	98.96 115	99.90 100	99.39 208

OpenMVS_ROB	97.31 17	97.36 278	96.84 288	98.89 257	99.29 273	99.45 114	98.87 215	99.48 209	86.54 348	99.44 176	99.74 94	97.34 227	99.86 178	91.61 333	99.28 272	97.37 340

MSLP-MVS++		99.05 168	99.09 141	98.91 252	99.21 283	98.36 250	98.82 225	99.47 213	98.85 176	98.90 267	99.56 196	98.78 100	99.09 348	98.57 143	99.68 206	99.26 233

DeepPCF-MVS	98.42 6	99.18 146	99.02 159	99.67 84	99.22 282	99.75 43	97.25 335	99.47 213	98.72 195	99.66 119	99.70 118	99.29 37	99.63 329	98.07 179	99.81 160	99.62 112

PMVS	92.94 21	98.82 205	98.81 193	98.85 258	99.84 42	97.99 275	99.20 150	99.47 213	99.71 47	99.42 182	99.82 58	98.09 178	99.47 342	93.88 329	99.85 129	99.07 272
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
ambc				99.20 228	99.35 252	98.53 240	99.17 158	99.46 216		99.67 115	99.80 63	98.46 151	99.70 294	97.92 185	99.70 203	99.38 211

EI-MVSNet-UG-set		99.48 70	99.50 67	99.42 178	99.57 182	98.65 237	99.24 140	99.46 216	99.68 56	99.80 74	99.66 146	98.99 72	99.89 124	99.19 83	99.90 100	99.72 46

EI-MVSNet-Vis-set		99.47 76	99.49 68	99.42 178	99.57 182	98.66 235	99.24 140	99.46 216	99.67 58	99.79 79	99.65 151	98.97 75	99.89 124	99.15 92	99.89 106	99.71 49

EI-MVSNet		99.38 95	99.44 75	99.21 226	99.58 173	98.09 271	99.26 134	99.46 216	99.62 71	99.75 90	99.67 142	98.54 139	99.85 194	99.15 92	99.92 88	99.68 62

MVSTER		98.47 234	98.22 239	99.24 223	99.06 303	98.35 251	99.08 184	99.46 216	99.27 123	99.75 90	99.66 146	88.61 323	99.85 194	99.14 98	99.92 88	99.52 164

CHOSEN 280x420		98.41 240	98.41 224	98.40 285	99.34 262	95.89 316	96.94 338	99.44 221	98.80 183	99.25 222	99.52 207	93.51 285	99.98 7	98.94 120	99.98 36	99.32 227

Regformer-3		99.41 87	99.41 80	99.40 186	99.52 201	98.70 232	99.17 158	99.44 221	99.62 71	99.75 90	99.60 176	98.90 83	99.85 194	98.89 123	99.84 133	99.65 89

PCF-MVS	96.03 18	96.73 302	95.86 313	99.33 202	99.44 234	99.16 189	96.87 339	99.44 221	86.58 347	98.95 260	99.40 230	94.38 279	99.88 139	87.93 344	99.80 165	98.95 280
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
testing_2		99.58 46	99.56 51	99.62 115	99.81 61	99.44 116	99.14 171	99.43 224	99.69 53	99.82 65	99.79 70	99.14 54	99.79 260	99.31 70	99.95 65	99.63 99

ab-mvs		99.33 110	99.28 108	99.47 164	99.57 182	99.39 134	99.78 12	99.43 224	98.87 174	99.57 148	99.82 58	98.06 181	99.87 158	98.69 138	99.73 195	99.15 249

AdaColmap		98.60 221	98.35 231	99.38 191	99.12 295	99.22 179	98.67 239	99.42 226	97.84 259	98.81 273	99.27 259	97.32 228	99.81 252	95.14 313	99.53 239	99.10 262

CANet		99.11 160	99.05 152	99.28 211	98.83 320	98.56 238	98.71 238	99.41 227	99.25 130	99.23 226	99.22 272	97.66 213	99.94 55	99.19 83	99.97 47	99.33 223

TEST9					99.35 252	99.35 150	98.11 291	99.41 227	94.83 332	97.92 323	98.99 298	98.02 184	99.85 194

train_agg		98.35 247	97.95 257	99.57 136	99.35 252	99.35 150	98.11 291	99.41 227	94.90 328	97.92 323	98.99 298	98.02 184	99.85 194	95.38 310	99.44 249	99.50 173

CDPH-MVS		98.56 225	98.20 241	99.61 118	99.50 210	99.46 109	98.32 274	99.41 227	95.22 324	99.21 230	99.10 284	98.34 162	99.82 233	95.09 315	99.66 215	99.56 143

Test4		98.65 218	98.44 219	99.27 213	99.57 182	98.86 225	98.43 266	99.41 227	98.85 176	99.57 148	98.95 308	93.05 289	99.75 282	98.57 143	99.56 228	99.19 242

CNLPA		98.57 224	98.34 232	99.28 211	99.18 289	99.10 197	98.34 272	99.41 227	98.48 213	98.52 296	98.98 301	97.05 241	99.78 268	95.59 303	99.50 242	98.96 279

test_8					99.34 262	99.31 156	98.08 296	99.40 233	94.90 328	97.87 327	98.97 304	98.02 184	99.84 210

PVSNet_0	95.53 19	95.85 321	95.31 320	97.47 315	98.78 327	93.48 335	95.72 345	99.40 233	96.18 309	97.37 337	97.73 345	95.73 267	99.58 336	95.49 305	81.40 351	99.36 218

DeepC-MVS_fast	98.47 5	99.23 128	99.12 130	99.56 142	99.28 275	99.22 179	98.99 199	99.40 233	99.08 157	99.58 146	99.64 152	98.90 83	99.83 226	97.44 215	99.75 182	99.63 99
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
agg_prior3		98.24 252	97.81 265	99.53 150	99.34 262	99.26 168	98.09 293	99.39 236	94.21 336	97.77 332	98.96 306	97.74 203	99.84 210	95.38 310	99.44 249	99.50 173

agg_prior1		98.33 250	97.92 259	99.57 136	99.35 252	99.36 146	97.99 305	99.39 236	94.85 331	97.76 333	98.98 301	98.03 182	99.85 194	95.49 305	99.44 249	99.51 167

agg_prior					99.35 252	99.36 146		99.39 236		97.76 333			99.85 194

test_prior3		98.62 219	98.34 232	99.46 167	99.35 252	99.22 179	97.95 310	99.39 236	97.87 255	98.05 318	99.05 294	97.90 191	99.69 300	95.99 284	99.49 244	99.48 180

test_prior				99.46 167	99.35 252	99.22 179		99.39 236					99.69 300			99.48 180

jason		99.16 151	99.11 132	99.32 206	99.75 111	98.44 243	98.26 277	99.39 236	98.70 196	99.74 98	99.30 253	98.54 139	99.97 16	98.48 148	99.82 152	99.55 146
jason: jason.
WR-MVS		99.11 160	98.93 174	99.66 92	99.30 272	99.42 126	98.42 267	99.37 242	99.04 159	99.57 148	99.20 274	96.89 245	99.86 178	98.66 141	99.87 119	99.70 53

HQP3-MVS								99.37 242							99.67 212

HQP-MVS		98.36 244	98.02 252	99.39 189	99.31 268	98.94 212	97.98 306	99.37 242	97.45 278	98.15 312	98.83 315	96.67 248	99.70 294	94.73 317	99.67 212	99.53 156

TSAR-MVS + MP.		99.34 107	99.24 115	99.63 107	99.82 53	99.37 143	99.26 134	99.35 245	98.77 187	99.57 148	99.70 118	99.27 42	99.88 139	97.71 197	99.75 182	99.65 89

UGNet		99.38 95	99.34 92	99.49 159	98.90 310	98.90 219	99.70 29	99.35 245	99.86 16	98.57 294	99.81 61	98.50 148	99.93 66	99.38 58	99.98 36	99.66 79
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
PVSNet	97.47 15	98.42 239	98.44 219	98.35 287	99.46 230	96.26 307	96.70 342	99.34 247	97.68 267	99.00 252	99.13 278	97.40 222	99.72 289	97.59 208	99.68 206	99.08 268

MS-PatchMatch		99.00 180	98.97 171	99.09 236	99.11 298	98.19 263	98.76 232	99.33 248	98.49 212	99.44 176	99.58 184	98.21 172	99.69 300	98.20 167	99.62 220	99.39 208

MDA-MVSNet_test_wron		98.95 189	98.99 167	98.85 258	99.64 158	97.16 296	98.23 279	99.33 248	98.93 168	99.56 155	99.66 146	97.39 224	99.83 226	98.29 161	99.88 112	99.55 146

YYNet1		98.95 189	98.99 167	98.84 260	99.64 158	97.14 297	98.22 280	99.32 250	98.92 170	99.59 145	99.66 146	97.40 222	99.83 226	98.27 163	99.90 100	99.55 146

tpm cat1		96.78 301	96.98 284	96.16 335	98.85 319	90.59 352	99.08 184	99.32 250	92.37 340	97.73 335	99.46 222	91.15 303	99.69 300	96.07 278	98.80 299	98.21 317

sss		98.90 196	98.77 196	99.27 213	99.48 221	98.44 243	98.72 237	99.32 250	97.94 252	99.37 201	99.35 245	96.31 258	99.91 92	98.85 125	99.63 219	99.47 184

PMMVS		98.49 232	98.29 235	99.11 234	98.96 307	98.42 245	97.54 325	99.32 250	97.53 276	98.47 301	98.15 336	97.88 194	99.82 233	97.46 214	99.24 278	99.09 265

CANet_DTU		98.91 194	98.85 186	99.09 236	98.79 325	98.13 266	98.18 282	99.31 254	99.48 92	98.86 270	99.51 211	96.56 250	99.95 41	99.05 104	99.95 65	99.19 242

HSP-MVS		99.01 177	98.76 197	99.76 42	99.78 88	99.73 49	99.35 99	99.31 254	98.54 208	99.54 161	98.99 298	96.81 246	99.93 66	96.97 241	99.53 239	99.61 117

VNet		99.18 146	99.06 148	99.56 142	99.24 280	99.36 146	99.33 108	99.31 254	99.67 58	99.47 173	99.57 191	96.48 253	99.84 210	99.15 92	99.30 270	99.47 184

testdata				99.42 178	99.51 205	98.93 216		99.30 257	96.20 308	98.87 269	99.40 230	98.33 164	99.89 124	96.29 271	99.28 272	99.44 195

test222					99.51 205	99.08 200	97.83 319	99.29 258	95.21 325	98.68 286	99.31 250	97.28 229			99.38 261	99.43 201

TSAR-MVS + GP.		99.12 157	99.04 157	99.38 191	99.34 262	99.16 189	98.15 285	99.29 258	98.18 241	99.63 130	99.62 166	99.18 50	99.68 308	98.20 167	99.74 189	99.30 229

test11								99.29 258

PAPM_NR		98.36 244	98.04 251	99.33 202	99.48 221	98.93 216	98.79 230	99.28 261	97.54 275	98.56 295	98.57 327	97.12 238	99.69 300	94.09 327	98.90 293	99.38 211

原ACMM1				99.37 195	99.47 226	98.87 224		99.27 262	96.74 298	98.26 307	99.32 248	97.93 190	99.82 233	95.96 287	99.38 261	99.43 201

CNVR-MVS		98.99 182	98.80 195	99.56 142	99.25 278	99.43 122	98.54 252	99.27 262	98.58 205	98.80 275	99.43 225	98.53 143	99.70 294	97.22 229	99.59 226	99.54 153

新几何1				99.52 152	99.50 210	99.22 179		99.26 264	95.66 320	98.60 291	99.28 257	97.67 209	99.89 124	95.95 288	99.32 268	99.45 190

旧先验1					99.49 215	99.29 160		99.26 264			99.39 233	97.67 209			99.36 264	99.46 188

DeepMVS_CX				97.98 297	99.69 142	96.95 299		99.26 264	75.51 350	95.74 349	98.28 334	96.47 254	99.62 330	91.23 335	97.89 339	97.38 339

pmmvs4		99.13 155	99.06 148	99.36 198	99.57 182	99.10 197	98.01 301	99.25 267	98.78 186	99.58 146	99.44 224	98.24 169	99.76 276	98.74 134	99.93 85	99.22 236

NCCC		98.82 205	98.57 212	99.58 130	99.21 283	99.31 156	98.61 240	99.25 267	98.65 199	98.43 302	99.26 261	97.86 195	99.81 252	96.55 262	99.27 275	99.61 117

PAPR		97.56 274	97.07 280	99.04 243	98.80 324	98.11 269	97.63 322	99.25 267	94.56 334	98.02 321	98.25 335	97.43 221	99.68 308	90.90 336	98.74 306	99.33 223

EPP-MVSNet		99.17 149	99.00 164	99.66 92	99.80 69	99.43 122	99.70 29	99.24 270	99.48 92	99.56 155	99.77 85	94.89 274	99.93 66	98.72 136	99.89 106	99.63 99

无先验							98.01 301	99.23 271	95.83 314				99.85 194	95.79 293		99.44 195

1121		98.56 225	98.24 237	99.52 152	99.49 215	99.24 175	99.30 121	99.22 272	95.77 316	98.52 296	99.29 256	97.39 224	99.85 194	95.79 293	99.34 265	99.46 188

MG-MVS		98.52 229	98.39 226	98.94 249	99.15 290	97.39 293	98.18 282	99.21 273	98.89 172	99.23 226	99.63 159	97.37 226	99.74 286	94.22 325	99.61 224	99.69 56

HPM-MVS++		98.96 186	98.70 200	99.74 55	99.52 201	99.71 51	98.86 216	99.19 274	98.47 214	98.59 292	99.06 293	98.08 180	99.91 92	96.94 242	99.60 225	99.60 123

lupinMVS		98.96 186	98.87 183	99.24 223	99.57 182	98.40 246	98.12 289	99.18 275	98.28 236	99.63 130	99.13 278	98.02 184	99.97 16	98.22 165	99.69 204	99.35 220

API-MVS		98.38 243	98.39 226	98.35 287	98.83 320	99.26 168	99.14 171	99.18 275	98.59 204	98.66 287	98.78 319	98.61 129	99.57 337	94.14 326	99.56 228	96.21 347

test12				99.54 149	99.29 273	99.33 153		99.16 277		98.43 302		97.54 216	99.82 233		99.47 246	99.48 180

IS-MVSNet		99.03 171	98.85 186	99.55 145	99.80 69	99.25 172	99.73 21	99.15 278	99.37 113	99.61 142	99.71 111	94.73 276	99.81 252	97.70 198	99.88 112	99.58 138

SixPastTwentyTwo		99.42 84	99.30 101	99.76 42	99.92 19	99.67 67	99.70 29	99.14 279	99.65 65	99.89 38	99.90 23	96.20 261	99.94 55	99.42 57	99.92 88	99.67 69

MAR-MVS		98.24 252	97.92 259	99.19 229	98.78 327	99.65 74	99.17 158	99.14 279	95.36 322	98.04 320	98.81 317	97.47 219	99.72 289	95.47 307	99.06 285	98.21 317
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
WTY-MVS		98.59 223	98.37 229	99.26 218	99.43 236	98.40 246	98.74 233	99.13 281	98.10 243	99.21 230	99.24 268	94.82 275	99.90 109	97.86 189	98.77 302	99.49 179

Patchmatch-test		98.10 260	97.98 255	98.48 282	99.27 277	96.48 304	99.40 85	99.07 282	98.81 181	99.23 226	99.57 191	90.11 317	99.87 158	96.69 255	99.64 218	99.09 265

MCST-MVS		99.02 173	98.81 193	99.65 96	99.58 173	99.49 101	98.58 244	99.07 282	98.40 219	99.04 249	99.25 263	98.51 147	99.80 257	97.31 222	99.51 241	99.65 89

1314		98.00 264	97.90 262	98.27 292	98.90 310	97.45 292	99.30 121	99.06 284	94.98 327	97.21 340	99.12 282	98.43 153	99.67 313	95.58 304	98.56 320	97.71 335

GA-MVS		97.99 265	97.68 272	98.93 251	99.52 201	98.04 274	97.19 336	99.05 285	98.32 234	98.81 273	98.97 304	89.89 320	99.41 346	98.33 157	99.05 286	99.34 222

tpmp4_e23		96.11 315	96.06 308	96.27 332	98.90 310	90.70 351	99.34 106	99.03 286	93.72 337	96.56 343	99.31 250	83.63 347	99.75 282	96.06 279	98.02 337	98.35 309

E-PMN		97.14 290	97.43 276	96.27 332	98.79 325	91.62 345	95.54 346	99.01 287	99.44 101	98.88 268	99.12 282	92.78 292	99.68 308	94.30 324	99.03 288	97.50 337

BH-untuned		98.22 255	98.09 248	98.58 276	99.38 247	97.24 295	98.55 249	98.98 288	97.81 261	99.20 235	98.76 320	97.01 242	99.65 325	94.83 316	98.33 327	98.86 287

tpmvs		97.39 276	97.69 271	96.52 330	98.41 339	91.76 343	99.30 121	98.94 289	97.74 262	97.85 328	99.55 201	92.40 296	99.73 288	96.25 273	98.73 308	98.06 322

MVS		95.72 323	94.63 326	98.99 246	98.56 336	97.98 280	99.30 121	98.86 290	72.71 351	97.30 338	99.08 285	98.34 162	99.74 286	89.21 341	98.33 327	99.26 233

ADS-MVSNet		97.72 270	97.67 273	97.86 305	99.14 291	94.65 330	99.22 146	98.86 290	96.97 292	98.25 308	99.64 152	90.90 307	99.84 210	96.51 264	99.56 228	99.08 268

tpmrst		97.73 269	98.07 249	96.73 326	98.71 332	92.00 340	99.10 179	98.86 290	98.52 209	98.92 264	99.54 203	91.90 297	99.82 233	98.02 180	99.03 288	98.37 308

PatchT		98.45 236	98.32 234	98.83 262	98.94 308	98.29 258	99.24 140	98.82 293	99.84 23	99.08 244	99.76 88	91.37 302	99.94 55	98.82 128	99.00 290	98.26 313

FPMVS		96.32 311	95.50 318	98.79 265	99.60 167	98.17 265	98.46 263	98.80 294	97.16 287	96.28 344	99.63 159	82.19 349	99.09 348	88.45 343	98.89 294	99.10 262

RPMNet		98.53 228	98.44 219	98.83 262	99.05 304	98.12 267	99.30 121	98.78 295	99.86 16	99.16 236	99.74 94	92.53 295	99.91 92	98.75 133	98.77 302	98.44 306

ADS-MVSNet2		97.78 268	97.66 274	98.12 295	99.14 291	95.36 325	99.22 146	98.75 296	96.97 292	98.25 308	99.64 152	90.90 307	99.94 55	96.51 264	99.56 228	99.08 268

LP		98.34 249	98.44 219	98.05 296	98.88 317	95.31 327	99.28 130	98.74 297	99.12 151	98.98 253	99.79 70	93.40 286	99.93 66	98.38 152	99.41 258	98.90 284

HY-MVS	98.23 9	98.21 256	97.95 257	98.99 246	99.03 306	98.24 259	99.61 60	98.72 298	96.81 296	98.73 281	99.51 211	94.06 281	99.86 178	96.91 243	98.20 330	98.86 287

test2356		95.99 319	95.26 322	98.18 293	96.93 352	95.53 324	95.31 347	98.71 299	95.67 319	98.48 300	97.83 340	80.72 352	99.88 139	95.47 307	98.21 329	99.11 258

VDDNet		98.97 183	98.82 192	99.42 178	99.71 133	98.81 228	99.62 56	98.68 300	99.81 28	99.38 200	99.80 63	94.25 280	99.85 194	98.79 129	99.32 268	99.59 134

CostFormer		96.71 303	96.79 291	96.46 331	98.90 310	90.71 350	99.41 83	98.68 300	94.69 333	98.14 316	99.34 247	86.32 343	99.80 257	97.60 207	98.07 335	98.88 285

EMVS		96.96 293	97.28 277	95.99 336	98.76 329	91.03 348	95.26 348	98.61 302	99.34 116	98.92 264	98.88 314	93.79 282	99.66 318	92.87 330	99.05 286	97.30 341

MIMVSNet		98.43 237	98.20 241	99.11 234	99.53 199	98.38 249	99.58 67	98.61 302	98.96 164	99.33 210	99.76 88	90.92 306	99.81 252	97.38 219	99.76 179	99.15 249

MTMP								98.59 304

BH-w/o		97.20 285	97.01 283	97.76 308	99.08 301	95.69 321	98.03 300	98.52 305	95.76 317	97.96 322	98.02 337	95.62 269	99.47 342	92.82 331	97.25 344	98.12 321

tpm2		96.35 310	96.22 305	96.73 326	98.88 317	91.75 344	99.21 149	98.51 306	93.27 339	97.89 325	99.21 273	84.83 346	99.70 294	96.04 280	98.18 333	98.75 294

JIA-IIPM		98.06 262	97.92 259	98.50 281	98.59 335	97.02 298	98.80 227	98.51 306	99.88 12	97.89 325	99.87 37	91.89 298	99.90 109	98.16 174	97.68 342	98.59 298

Patchmatch-test1		98.13 258	98.40 225	97.31 320	99.20 286	92.99 336	98.17 284	98.49 308	98.24 238	99.10 243	99.52 207	96.01 265	99.83 226	97.22 229	99.62 220	99.12 257

PAPM		95.61 324	94.71 325	98.31 290	99.12 295	96.63 302	96.66 343	98.46 309	90.77 344	96.25 345	98.68 324	93.01 290	99.69 300	81.60 351	97.86 340	98.62 296

PatchFormer-LS_test		96.95 294	97.07 280	96.62 329	98.76 329	91.85 342	99.18 152	98.45 310	97.29 285	97.73 335	97.22 354	88.77 322	99.76 276	98.13 175	98.04 336	98.25 314

alignmvs		98.28 251	97.96 256	99.25 221	99.12 295	98.93 216	99.03 191	98.42 311	99.64 67	98.72 282	97.85 339	90.86 309	99.62 330	98.88 124	99.13 282	99.19 242

PatchmatchNet		97.65 271	97.80 266	97.18 321	98.82 323	92.49 338	99.17 158	98.39 312	98.12 242	98.79 276	99.58 184	90.71 311	99.89 124	97.23 228	99.41 258	99.16 248
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
dp		96.86 296	97.07 280	96.24 334	98.68 334	90.30 353	99.19 151	98.38 313	97.35 283	98.23 310	99.59 182	87.23 328	99.82 233	96.27 272	98.73 308	98.59 298

VDD-MVS		99.20 141	99.11 132	99.44 173	99.43 236	98.98 207	99.50 74	98.32 314	99.80 31	99.56 155	99.69 124	96.99 243	99.85 194	98.99 108	99.73 195	99.50 173

BH-RMVSNet		98.41 240	98.14 246	99.21 226	99.21 283	98.47 242	98.60 242	98.26 315	98.35 228	98.93 262	99.31 250	97.20 236	99.66 318	94.32 323	99.10 284	99.51 167

EPNet_dtu		97.62 272	97.79 268	97.11 323	96.67 353	92.31 339	98.51 255	98.04 316	99.24 132	95.77 348	99.47 219	93.78 283	99.66 318	98.98 110	99.62 220	99.37 215
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MDTV_nov1_ep13			97.73 270		98.70 333	90.83 349	99.15 166	98.02 317	98.51 210	98.82 272	99.61 173	90.98 305	99.66 318	96.89 245	98.92 291

test_normal		98.82 205	98.67 203	99.27 213	99.56 193	98.83 227	98.22 280	98.01 318	99.03 160	99.49 172	99.24 268	96.21 260	99.76 276	98.69 138	99.56 228	99.22 236

EPNet		98.13 258	97.77 269	99.18 232	94.57 354	97.99 275	99.24 140	97.96 319	99.74 40	97.29 339	99.62 166	93.13 288	99.97 16	98.59 142	99.83 143	99.58 138
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tpm		97.15 288	96.95 285	97.75 309	98.91 309	94.24 332	99.32 111	97.96 319	97.71 264	98.29 305	99.32 248	86.72 335	99.92 83	98.10 178	96.24 348	99.09 265

DI_MVS_plusplus_test		98.80 208	98.65 204	99.27 213	99.57 182	98.90 219	98.44 265	97.95 321	99.02 161	99.51 168	99.23 271	96.18 262	99.76 276	98.52 147	99.42 256	99.14 253

TR-MVS		97.44 275	97.15 279	98.32 289	98.53 337	97.46 291	98.47 259	97.91 322	96.85 294	98.21 311	98.51 330	96.42 256	99.51 340	92.16 332	97.29 343	97.98 328

tmp_tt		95.75 322	95.42 319	96.76 324	89.90 355	94.42 331	98.86 216	97.87 323	78.01 349	99.30 218	99.69 124	97.70 204	95.89 353	99.29 74	98.14 334	99.95 1

DWT-MVSNet_test		96.03 318	95.80 315	96.71 328	98.50 338	91.93 341	99.25 138	97.87 323	95.99 311	96.81 342	97.61 347	81.02 351	99.66 318	97.20 232	97.98 338	98.54 301

view600		96.86 296	96.52 299	97.88 301	99.69 142	95.87 317	99.39 86	97.68 325	99.11 152	98.96 256	97.82 341	87.40 324	99.79 260	89.78 337	98.83 295	97.98 328

view800		96.86 296	96.52 299	97.88 301	99.69 142	95.87 317	99.39 86	97.68 325	99.11 152	98.96 256	97.82 341	87.40 324	99.79 260	89.78 337	98.83 295	97.98 328

conf0.05thres1000		96.86 296	96.52 299	97.88 301	99.69 142	95.87 317	99.39 86	97.68 325	99.11 152	98.96 256	97.82 341	87.40 324	99.79 260	89.78 337	98.83 295	97.98 328

tfpn		96.86 296	96.52 299	97.88 301	99.69 142	95.87 317	99.39 86	97.68 325	99.11 152	98.96 256	97.82 341	87.40 324	99.79 260	89.78 337	98.83 295	97.98 328

conf200view11		96.43 307	96.03 309	97.63 312	99.63 160	95.93 313	99.18 152	97.57 329	98.75 192	98.70 284	97.31 351	87.04 329	99.67 313	87.62 345	98.51 322	97.30 341

thres100view900		96.39 309	96.03 309	97.47 315	99.63 160	95.93 313	99.18 152	97.57 329	98.75 192	98.70 284	97.31 351	87.04 329	99.67 313	87.62 345	98.51 322	96.81 345

thres600view7		96.60 305	96.16 306	97.93 299	99.63 160	96.09 311	99.18 152	97.57 329	98.77 187	98.72 282	97.32 350	87.04 329	99.72 289	88.57 342	98.62 312	97.98 328

thres200		96.09 316	95.68 317	97.33 319	99.48 221	96.22 308	98.53 253	97.57 329	98.06 245	98.37 304	96.73 357	86.84 334	99.61 334	86.99 349	98.57 313	96.16 348

tfpn200view9		96.30 312	95.89 311	97.53 313	99.58 173	96.11 309	99.00 196	97.54 333	98.43 215	98.52 296	96.98 355	86.85 332	99.67 313	87.62 345	98.51 322	96.81 345

thres400		96.40 308	95.89 311	97.92 300	99.58 173	96.11 309	99.00 196	97.54 333	98.43 215	98.52 296	96.98 355	86.85 332	99.67 313	87.62 345	98.51 322	97.98 328

test0.0.03 1		97.37 277	96.91 287	98.74 272	97.72 347	97.57 289	97.60 323	97.36 335	98.00 246	99.21 230	98.02 337	90.04 318	99.79 260	98.37 153	95.89 349	98.86 287

LFMVS		98.46 235	98.19 244	99.26 218	99.24 280	98.52 241	99.62 56	96.94 336	99.87 13	99.31 214	99.58 184	91.04 304	99.81 252	98.68 140	99.42 256	99.45 190

testpf		94.48 326	95.31 320	91.99 339	97.22 351	89.64 354	98.86 216	96.52 337	94.36 335	96.09 347	98.76 320	82.21 348	98.73 350	97.05 238	96.74 345	87.60 350

test-LLR		97.15 288	96.95 285	97.74 310	98.18 344	95.02 328	97.38 330	96.10 338	98.00 246	97.81 329	98.58 325	90.04 318	99.91 92	97.69 203	98.78 300	98.31 311

test-mter		96.23 314	95.73 316	97.74 310	98.18 344	95.02 328	97.38 330	96.10 338	97.90 253	97.81 329	98.58 325	79.12 356	99.91 92	97.69 203	98.78 300	98.31 311

IB-MVS	95.41 20	95.30 325	94.46 327	97.84 306	98.76 329	95.33 326	97.33 333	96.07 340	96.02 310	95.37 350	97.41 349	76.17 357	99.96 33	97.54 210	95.44 350	98.22 316
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
TESTMET0.1,1		96.24 313	95.84 314	97.41 317	98.24 342	93.84 333	97.38 330	95.84 341	98.43 215	97.81 329	98.56 328	79.77 355	99.89 124	97.77 194	98.77 302	98.52 302

conf0.01		97.19 286	96.74 292	98.51 278	99.73 120	98.35 251	99.35 99	95.78 342	96.54 299	99.39 193	99.08 285	86.57 337	99.88 139	95.69 296	98.57 313	97.30 341

conf0.002		97.19 286	96.74 292	98.51 278	99.73 120	98.35 251	99.35 99	95.78 342	96.54 299	99.39 193	99.08 285	86.57 337	99.88 139	95.69 296	98.57 313	97.30 341

thresconf0.02		97.25 281	96.74 292	98.75 268	99.73 120	98.35 251	99.35 99	95.78 342	96.54 299	99.39 193	99.08 285	86.57 337	99.88 139	95.69 296	98.57 313	98.02 324

tfpn_n400		97.25 281	96.74 292	98.75 268	99.73 120	98.35 251	99.35 99	95.78 342	96.54 299	99.39 193	99.08 285	86.57 337	99.88 139	95.69 296	98.57 313	98.02 324

tfpnconf		97.25 281	96.74 292	98.75 268	99.73 120	98.35 251	99.35 99	95.78 342	96.54 299	99.39 193	99.08 285	86.57 337	99.88 139	95.69 296	98.57 313	98.02 324

tfpnview11		97.25 281	96.74 292	98.75 268	99.73 120	98.35 251	99.35 99	95.78 342	96.54 299	99.39 193	99.08 285	86.57 337	99.88 139	95.69 296	98.57 313	98.02 324

MVE	92.54 22	96.66 304	96.11 307	98.31 290	99.68 149	97.55 290	97.94 312	95.60 348	99.37 113	90.68 352	98.70 323	96.56 250	98.61 352	86.94 350	99.55 234	98.77 293
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tfpn1000		97.28 280	96.83 289	98.64 275	99.67 153	97.68 287	99.41 83	95.47 349	97.14 288	99.43 180	99.07 292	85.87 344	99.88 139	96.78 250	98.67 310	98.34 310

tfpn_ndepth		96.93 295	96.43 303	98.42 283	99.60 167	97.72 283	99.22 146	95.16 350	95.91 312	99.26 221	98.79 318	85.56 345	99.87 158	96.03 281	98.35 326	97.68 336

K. test v3		98.87 200	98.60 207	99.69 78	99.93 18	99.46 109	99.74 19	94.97 351	99.78 34	99.88 46	99.88 34	93.66 284	99.97 16	99.61 38	99.95 65	99.64 95

N_pmnet		98.73 215	98.53 216	99.35 199	99.72 130	98.67 234	98.34 272	94.65 352	98.35 228	99.79 79	99.68 136	98.03 182	99.93 66	98.28 162	99.92 88	99.44 195

MVS-HIRNet		97.86 266	98.22 239	96.76 324	99.28 275	91.53 346	98.38 269	92.60 353	99.13 150	99.31 214	99.96 11	97.18 237	99.68 308	98.34 156	99.83 143	99.07 272

lessismore_v0				99.64 103	99.86 35	99.38 140		90.66 354		99.89 38	99.83 51	94.56 278	99.97 16	99.56 43	99.92 88	99.57 142

EPMVS		96.53 306	96.32 304	97.17 322	98.18 344	92.97 337	99.39 86	89.95 355	98.21 239	98.61 290	99.59 182	86.69 336	99.72 289	96.99 240	99.23 280	98.81 291

gg-mvs-nofinetune		95.87 320	95.17 323	97.97 298	98.19 343	96.95 299	99.69 38	89.23 356	99.89 10	96.24 346	99.94 13	81.19 350	99.51 340	93.99 328	98.20 330	97.44 338

GG-mvs-BLEND				97.36 318	97.59 348	96.87 301	99.70 29	88.49 357		94.64 351	97.26 353	80.66 353	99.12 347	91.50 334	96.50 347	96.08 349

testmvs		28.94 330	33.33 330	15.79 343	26.03 356	9.81 358	96.77 340	15.67 358	11.55 353	23.87 354	50.74 361	19.03 361	8.53 356	23.21 353	33.07 352	29.03 353

test123		29.31 329	33.05 332	18.08 342	25.93 357	12.24 357	97.53 327	10.93 359	11.78 352	24.21 353	50.08 362	21.04 360	8.60 355	23.51 352	32.43 354	33.39 352

pcd_1.5k_mvsjas		16.61 332	22.14 333	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	100.00 1	99.28 39	0.00 357	0.00 354	0.00 355	0.00 355

sosnet-low-res		8.33 333	11.11 334	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	100.00 1	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

sosnet		8.33 333	11.11 334	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	100.00 1	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

uncertanet		8.33 333	11.11 334	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	100.00 1	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

Regformer		8.33 333	11.11 334	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	100.00 1	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

n2								0.00 360

nn								0.00 360

ab-mvs-re		8.26 338	11.02 339	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	99.16 276	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

uanet		8.33 333	11.11 334	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	100.00 1	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

GSMVS																99.14 253

test_part3							98.74 233		97.71 264		99.57 191		99.90 109	94.47 321

test_part2					99.62 164	99.67 67				99.55 158

sam_mvs1												90.81 310				99.14 253

sam_mvs												90.52 314

test_post1							99.14 171				51.63 360	89.54 321	99.82 233	96.86 246

test_post											52.41 359	90.25 316	99.86 178

patchmatchnet-post											99.62 166	90.58 312	99.94 55

gm-plane-assit					97.59 348	89.02 355			93.47 338		98.30 333		99.84 210	96.38 268

test9_res														95.10 314	99.44 249	99.50 173

agg_prior2														94.58 320	99.46 248	99.50 173

test_prior4						99.19 187	98.00 303

test_prior2							97.95 310		97.87 255	98.05 318	99.05 294	97.90 191		95.99 284	99.49 244

旧先验2							97.94 312		95.33 323	98.94 261			99.88 139	96.75 252

新几何2							98.04 299

原ACMM2							97.92 314

testdata2													99.89 124	95.99 284

segment_acmp												98.37 160

testdata1							97.72 321		97.86 258

plane_prior7					99.58 173	99.38 140

plane_prior6					99.47 226	99.26 168						97.24 230

plane_prior4											99.25 263

plane_prior3						99.31 156			98.36 223	99.14 239

plane_prior2							98.80 227		98.94 166

plane_prior1					99.51 205

plane_prior						99.24 175	98.42 267		97.87 255						99.71 201

HQP5-MVS						98.94 212

HQP-NCC					99.31 268		97.98 306		97.45 278	98.15 312

ACMP_Plane					99.31 268		97.98 306		97.45 278	98.15 312

BP-MVS														94.73 317

HQP4-MVS										98.15 312			99.70 294			99.53 156

HQP2-MVS												96.67 248

NP-MVS					99.40 243	99.13 192					98.83 315

MDTV_nov1_ep13_2view						91.44 347	99.14 171		97.37 282	99.21 230		91.78 301		96.75 252		99.03 276

ACMMP++_ref															99.94 77

ACMMP++															99.79 168

Test By Simon												98.41 155

High-resolution multi-view benchmark