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.

test_fmvs3		99.12 51	99.41 19	98.25 231	99.76 31	95.07 284	99.05 64	99.94 2	97.78 176	99.82 21	99.84 2	98.56 54	99.71 246	99.96 1	99.96 25	99.97 3

test_fmvs2		98.70 103	98.97 65	97.89 258	99.54 98	94.05 311	98.55 108	99.92 6	96.78 258	99.72 31	99.78 8	96.60 189	99.67 267	99.91 2	99.90 69	99.94 7

test_fmvsmvis_n_1920		99.26 32	99.49 12	98.54 204	99.66 64	96.97 220	98.00 175	99.85 15	99.24 59	99.92 8	99.50 59	99.39 11	99.95 22	99.89 3	99.98 12	98.71 306

fmvsm_l_conf0.5_n		99.21 39	99.28 34	99.02 132	99.64 70	97.28 202	97.82 198	99.76 29	98.73 108	99.82 21	99.09 139	98.81 32	99.95 22	99.86 4	99.96 25	99.83 22

fmvsm_l_conf0.5_n_a		99.19 41	99.27 35	98.94 142	99.65 65	97.05 216	97.80 201	99.76 29	98.70 111	99.78 26	99.11 133	98.79 34	99.95 22	99.85 5	99.96 25	99.83 22

test_fmvsm_n_1920		99.33 26	99.45 18	98.99 135	99.57 81	97.73 178	97.93 182	99.83 20	99.22 60	99.93 6	99.30 94	99.42 10	99.96 11	99.85 5	99.99 5	99.29 212

MVS_0304		98.10 183	97.88 198	98.76 170	98.82 257	96.50 236	97.90 187	91.35 399	99.56 26	98.32 239	99.13 130	96.06 210	99.93 40	99.84 7	99.97 19	99.85 19

test_fmvsmconf0.01_n		99.57 7	99.63 7	99.36 64	99.87 12	98.13 131	98.08 161	99.95 1	99.45 36	99.98 2	99.75 11	99.80 1	99.97 4	99.82 8	99.99 5	99.99 1

test_fmvs1_n		98.09 186	98.28 154	97.52 291	99.68 58	93.47 333	98.63 99	99.93 4	95.41 312	99.68 39	99.64 32	91.88 309	99.48 339	99.82 8	99.87 77	99.62 67

test_f		98.67 114	98.87 71	98.05 248	99.72 44	95.59 262	98.51 117	99.81 24	96.30 282	99.78 26	99.82 4	96.14 206	98.63 395	99.82 8	99.93 44	99.95 6

LCM-MVSNet		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 10	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 11	100.00 1	99.85 19

MM		98.22 174	97.99 187	98.91 147	98.66 291	96.97 220	97.89 189	94.44 381	99.54 27	98.95 157	99.14 129	93.50 284	99.92 50	99.80 12	99.96 25	99.85 19

test_fmvsmconf0.1_n		99.49 12	99.54 10	99.34 73	99.78 25	98.11 132	97.77 205	99.90 9	99.33 50	99.97 3	99.66 27	99.71 3	99.96 11	99.79 13	99.99 5	99.96 5

test_vis1_n		98.31 163	98.50 120	97.73 274	99.76 31	94.17 309	98.68 96	99.91 7	96.31 280	99.79 25	99.57 42	92.85 296	99.42 351	99.79 13	99.84 85	99.60 74

test_fmvs1		97.72 215	97.94 192	97.07 315	98.66 291	92.39 351	97.68 216	99.81 24	95.20 316	99.54 56	99.44 71	91.56 311	99.41 352	99.78 15	99.77 124	99.40 173

test_vis1_n_1920		98.40 150	98.92 68	96.81 328	99.74 37	90.76 377	98.15 153	99.91 7	98.33 131	99.89 15	99.55 48	95.07 246	99.88 83	99.76 16	99.93 44	99.79 30

test_vis3_rt		99.14 46	99.17 43	99.07 120	99.78 25	98.38 109	98.92 77	99.94 2	97.80 174	99.91 11	99.67 25	97.15 156	98.91 390	99.76 16	99.56 210	99.92 9

test_fmvsmconf_n		99.44 15	99.48 14	99.31 83	99.64 70	98.10 134	97.68 216	99.84 18	99.29 55	99.92 8	99.57 42	99.60 5	99.96 11	99.74 18	99.98 12	99.89 11

fmvsm_s_conf0.1_n_a		99.17 42	99.30 32	98.80 160	99.75 35	96.59 234	97.97 181	99.86 13	98.22 142	99.88 17	99.71 17	98.59 50	99.84 137	99.73 19	99.98 12	99.98 2

v7n		99.53 9	99.57 9	99.41 60	99.88 9	98.54 100	99.45 10	99.61 51	99.66 13	99.68 39	99.66 27	98.44 61	99.95 22	99.73 19	99.96 25	99.75 43

fmvsm_s_conf0.1_n		99.16 45	99.33 26	98.64 181	99.71 47	96.10 247	97.87 193	99.85 15	98.56 123	99.90 12	99.68 20	98.69 41	99.85 120	99.72 21	99.98 12	99.97 3

fmvsm_s_conf0.5_n_a		99.10 53	99.20 41	98.78 166	99.55 93	96.59 234	97.79 202	99.82 22	98.21 143	99.81 23	99.53 54	98.46 60	99.84 137	99.70 22	99.97 19	99.90 10

v10		98.97 66	99.11 52	98.55 201	99.44 129	96.21 246	98.90 78	99.55 73	98.73 108	99.48 68	99.60 39	96.63 188	99.83 154	99.70 22	99.99 5	99.61 73

fmvsm_s_conf0.5_n		99.09 54	99.26 37	98.61 189	99.55 93	96.09 250	97.74 210	99.81 24	98.55 124	99.85 19	99.55 48	98.60 49	99.84 137	99.69 24	99.98 12	99.89 11

v1240		98.55 132	98.62 104	98.32 225	99.22 171	95.58 264	97.51 239	99.45 110	97.16 239	99.45 74	99.24 105	96.12 208	99.85 120	99.60 25	99.88 74	99.55 104

v8		99.01 60	99.16 45	98.57 196	99.47 124	96.31 242	98.90 78	99.47 104	99.03 89	99.52 62	99.57 42	96.93 168	99.81 177	99.60 25	99.98 12	99.60 74

v1921920		98.54 134	98.60 109	98.38 221	99.20 177	95.76 261	97.56 233	99.36 138	97.23 233	99.38 87	99.17 120	96.02 212	99.84 137	99.57 27	99.90 69	99.54 108

v1192		98.60 124	98.66 98	98.41 218	99.27 161	95.88 256	97.52 237	99.36 138	97.41 211	99.33 97	99.20 112	96.37 200	99.82 164	99.57 27	99.92 55	99.55 104

mvs_tets		99.63 5	99.67 5	99.49 48	99.88 9	98.61 92	99.34 20	99.71 34	99.27 57	99.90 12	99.74 13	99.68 4	99.97 4	99.55 29	99.99 5	99.88 14

PS-MVSNAJss		99.46 14	99.49 12	99.35 70	99.90 4	98.15 128	99.20 45	99.65 46	99.48 32	99.92 8	99.71 17	98.07 88	99.96 11	99.53 30	100.00 1	99.93 8

test_cas_vis1_n_1920		98.33 160	98.68 95	97.27 305	99.69 56	92.29 354	98.03 169	99.85 15	97.62 186	99.96 4	99.62 34	93.98 277	99.74 233	99.52 31	99.86 80	99.79 30

v144192		98.54 134	98.57 112	98.45 214	99.21 173	95.98 253	97.63 224	99.36 138	97.15 241	99.32 103	99.18 116	95.84 226	99.84 137	99.50 32	99.91 63	99.54 108

jajsoiax		99.58 6	99.61 8	99.48 51	99.87 12	98.61 92	99.28 37	99.66 45	99.09 83	99.89 15	99.68 20	99.53 7	99.97 4	99.50 32	99.99 5	99.87 16

v1144		98.60 124	98.66 98	98.41 218	99.36 147	95.90 255	97.58 231	99.34 149	97.51 198	99.27 108	99.15 126	96.34 202	99.80 184	99.47 34	99.93 44	99.51 120

RRT_MVS		99.09 54	98.94 66	99.55 23	99.87 12	98.82 78	99.48 9	98.16 318	99.49 31	99.59 52	99.65 30	94.79 258	99.95 22	99.45 35	99.96 25	99.88 14

OurMVSNet-221017-0		99.37 24	99.31 30	99.53 34	99.91 3	98.98 65	99.63 6	99.58 55	99.44 38	99.78 26	99.76 10	96.39 197	99.92 50	99.44 36	99.92 55	99.68 54

tt0805		98.69 106	98.62 104	98.90 150	99.75 35	99.30 17	99.15 53	96.97 348	98.86 103	98.87 178	97.62 323	98.63 46	98.96 387	99.41 37	98.29 338	98.45 327

pmmvs6		99.67 3	99.70 3	99.60 11	99.90 4	99.27 22	99.53 7	99.76 29	99.64 15	99.84 20	99.83 3	99.50 8	99.87 100	99.36 38	99.92 55	99.64 63

v2v482		98.56 128	98.62 104	98.37 222	99.42 135	95.81 259	97.58 231	99.16 215	97.90 167	99.28 106	99.01 161	95.98 219	99.79 197	99.33 39	99.90 69	99.51 120

mvsmamba		99.24 37	99.15 50	99.49 48	99.83 19	98.85 74	99.41 13	99.55 73	99.54 27	99.40 83	99.52 57	95.86 225	99.91 59	99.32 40	99.95 32	99.70 51

ANet_high		99.57 7	99.67 5	99.28 85	99.89 6	98.09 135	99.14 54	99.93 4	99.82 3	99.93 6	99.81 5	99.17 18	99.94 35	99.31 41	100.00 1	99.82 25

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 21	99.85 17	99.11 59	99.90 1	99.78 27	99.63 17	99.78 26	99.67 25	99.48 9	99.81 177	99.30 42	99.97 19	99.77 35
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
MVSFormer		98.26 170	98.43 133	97.77 266	98.88 246	93.89 323	99.39 17	99.56 69	99.11 73	98.16 248	98.13 288	93.81 280	99.97 4	99.26 43	99.57 207	99.43 158

test_djsdf		99.52 10	99.51 11	99.53 34	99.86 15	98.74 82	99.39 17	99.56 69	99.11 73	99.70 35	99.73 15	99.00 22	99.97 4	99.26 43	99.98 12	99.89 11

Anonymous20240521		98.69 106	98.87 71	98.16 239	99.77 28	95.11 283	99.08 58	99.44 114	99.34 49	99.33 97	99.55 48	94.10 276	99.94 35	99.25 45	99.96 25	99.42 161

K. test v3		98.00 192	97.66 214	99.03 130	99.79 24	97.56 187	99.19 49	92.47 393	99.62 20	99.52 62	99.66 27	89.61 324	99.96 11	99.25 45	99.81 99	99.56 97

KD-MVS_self_test		99.25 33	99.18 42	99.44 57	99.63 74	99.06 64	98.69 95	99.54 78	99.31 52	99.62 51	99.53 54	97.36 144	99.86 108	99.24 47	99.71 154	99.39 175

Anonymous20231211		99.27 30	99.27 35	99.26 90	99.29 158	98.18 126	99.49 8	99.51 85	99.70 8	99.80 24	99.68 20	96.84 172	99.83 154	99.21 48	99.91 63	99.77 35

V42		98.78 90	98.78 81	98.76 170	99.44 129	97.04 217	98.27 140	99.19 204	97.87 169	99.25 116	99.16 122	96.84 172	99.78 208	99.21 48	99.84 85	99.46 146

MIMVSNet1		99.38 23	99.32 28	99.55 23	99.86 15	99.19 37	99.41 13	99.59 53	99.59 23	99.71 33	99.57 42	97.12 157	99.90 64	99.21 48	99.87 77	99.54 108

nrg030		99.40 21	99.35 23	99.54 27	99.58 77	99.13 55	98.98 71	99.48 96	99.68 11	99.46 71	99.26 100	98.62 47	99.73 238	99.17 51	99.92 55	99.76 39

SSC-MVS		98.71 99	98.74 83	98.62 186	99.72 44	96.08 252	98.74 87	98.64 296	99.74 6	99.67 41	99.24 105	94.57 262	99.95 22	99.11 52	99.24 267	99.82 25

anonymousdsp		99.51 11	99.47 16	99.62 6	99.88 9	99.08 63	99.34 20	99.69 37	98.93 98	99.65 45	99.72 16	98.93 26	99.95 22	99.11 52	100.00 1	99.82 25

VPA-MVSNet		99.30 28	99.30 32	99.28 85	99.49 115	98.36 114	99.00 68	99.45 110	99.63 17	99.52 62	99.44 71	98.25 71	99.88 83	99.09 54	99.84 85	99.62 67

pm-mvs1		99.44 15	99.48 14	99.33 78	99.80 22	98.63 89	99.29 33	99.63 47	99.30 54	99.65 45	99.60 39	99.16 20	99.82 164	99.07 55	99.83 92	99.56 97

TransMVSNet (Re)		99.44 15	99.47 16	99.36 64	99.80 22	98.58 95	99.27 39	99.57 62	99.39 43	99.75 30	99.62 34	99.17 18	99.83 154	99.06 56	99.62 187	99.66 58

EC-MVSNet		99.09 54	99.05 59	99.20 99	99.28 159	98.93 71	99.24 41	99.84 18	99.08 85	98.12 253	98.37 270	98.72 38	99.90 64	99.05 57	99.77 124	98.77 300

SixPastTwentyTwo		98.75 95	98.62 104	99.16 105	99.83 19	97.96 155	99.28 37	98.20 315	99.37 45	99.70 35	99.65 30	92.65 299	99.93 40	99.04 58	99.84 85	99.60 74

CS-MVS		99.13 49	99.10 54	99.24 95	99.06 212	99.15 47	99.36 19	99.88 11	99.36 48	98.21 245	98.46 262	98.68 42	99.93 40	99.03 59	99.85 81	98.64 315

FC-MVSNet-test		99.27 30	99.25 38	99.34 73	99.77 28	98.37 111	99.30 32	99.57 62	99.61 22	99.40 83	99.50 59	97.12 157	99.85 120	99.02 60	99.94 40	99.80 29

UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 18	99.34 15	99.69 4	99.58 55	99.90 2	99.86 18	99.78 8	99.58 6	99.95 22	99.00 61	99.95 32	99.78 33

lessismore_v0				98.97 138	99.73 38	97.53 189		86.71 407		99.37 89	99.52 57	89.93 322	99.92 50	98.99 62	99.72 149	99.44 154

mvsany_test3		98.87 78	98.92 68	98.74 177	99.38 140	96.94 224	98.58 105	99.10 226	96.49 270	99.96 4	99.81 5	98.18 80	99.45 346	98.97 63	99.79 114	99.83 22

Vis-MVSNet		99.34 25	99.36 22	99.27 88	99.73 38	98.26 118	99.17 50	99.78 27	99.11 73	99.27 108	99.48 64	98.82 31	99.95 22	98.94 64	99.93 44	99.59 80
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CS-MVS-test		99.13 49	99.09 55	99.26 90	99.13 197	98.97 66	99.31 27	99.88 11	99.44 38	98.16 248	98.51 254	98.64 44	99.93 40	98.91 65	99.85 81	98.88 283

mvs_anonymous		97.83 211	98.16 171	96.87 324	98.18 336	91.89 358	97.31 253	98.90 258	97.37 215	98.83 182	99.46 66	96.28 203	99.79 197	98.90 66	98.16 345	98.95 270

WR-MVS_H		99.33 26	99.22 40	99.65 5	99.71 47	99.24 25	99.32 23	99.55 73	99.46 35	99.50 67	99.34 87	97.30 146	99.93 40	98.90 66	99.93 44	99.77 35

PS-CasMVS		99.40 21	99.33 26	99.62 6	99.71 47	99.10 60	99.29 33	99.53 81	99.53 29	99.46 71	99.41 76	98.23 73	99.95 22	98.89 68	99.95 32	99.81 28

UA-Net		99.47 13	99.40 20	99.70 2	99.49 115	99.29 19	99.80 3	99.72 33	99.82 3	99.04 143	99.81 5	98.05 91	99.96 11	98.85 69	99.99 5	99.86 18

new-patchmatchnet		98.35 156	98.74 83	97.18 308	99.24 166	92.23 356	96.42 303	99.48 96	98.30 134	99.69 37	99.53 54	97.44 140	99.82 164	98.84 70	99.77 124	99.49 127

test1111		96.49 291	96.82 263	95.52 360	99.42 135	87.08 393	99.22 42	87.14 406	99.11 73	99.46 71	99.58 41	88.69 330	99.86 108	98.80 71	99.95 32	99.62 67

PEN-MVS		99.41 20	99.34 25	99.62 6	99.73 38	99.14 52	99.29 33	99.54 78	99.62 20	99.56 53	99.42 73	98.16 84	99.96 11	98.78 72	99.93 44	99.77 35

DTE-MVSNet		99.43 18	99.35 23	99.66 4	99.71 47	99.30 17	99.31 27	99.51 85	99.64 15	99.56 53	99.46 66	98.23 73	99.97 4	98.78 72	99.93 44	99.72 45

EG-PatchMatch MVS		98.99 62	99.01 61	98.94 142	99.50 108	97.47 191	98.04 168	99.59 53	98.15 154	99.40 83	99.36 82	98.58 53	99.76 221	98.78 72	99.68 167	99.59 80

EI-MVSNet-UG-set		98.69 106	98.71 89	98.62 186	99.10 201	96.37 239	97.23 259	98.87 263	99.20 64	99.19 122	98.99 165	97.30 146	99.85 120	98.77 75	99.79 114	99.65 62

test_vis1_rt		97.75 213	97.72 209	97.83 261	98.81 260	96.35 240	97.30 254	99.69 37	94.61 327	97.87 269	98.05 297	96.26 204	98.32 398	98.74 76	98.18 342	98.82 288

CP-MVSNet		99.21 39	99.09 55	99.56 21	99.65 65	98.96 70	99.13 55	99.34 149	99.42 41	99.33 97	99.26 100	97.01 165	99.94 35	98.74 76	99.93 44	99.79 30

EI-MVSNet-Vis-set		98.68 111	98.70 92	98.63 185	99.09 204	96.40 238	97.23 259	98.86 268	99.20 64	99.18 126	98.97 171	97.29 148	99.85 120	98.72 78	99.78 119	99.64 63

test2506		92.39 362	91.89 364	93.89 378	99.38 140	82.28 408	99.32 23	66.03 414	99.08 85	98.77 191	99.57 42	66.26 404	99.84 137	98.71 79	99.95 32	99.54 108

baseline		98.96 68	99.02 60	98.76 170	99.38 140	97.26 204	98.49 120	99.50 87	98.86 103	99.19 122	99.06 140	98.23 73	99.69 255	98.71 79	99.76 135	99.33 201

FIs		99.14 46	99.09 55	99.29 84	99.70 54	98.28 117	99.13 55	99.52 84	99.48 32	99.24 117	99.41 76	96.79 178	99.82 164	98.69 81	99.88 74	99.76 39

casdiffmvs_mvg		99.12 51	99.16 45	98.99 135	99.43 134	97.73 178	98.00 175	99.62 48	99.22 60	99.55 55	99.22 109	98.93 26	99.75 228	98.66 82	99.81 99	99.50 123
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WB-MVS		98.52 139	98.55 113	98.43 216	99.65 65	95.59 262	98.52 112	98.77 283	99.65 14	99.52 62	99.00 164	94.34 268	99.93 40	98.65 83	98.83 311	99.76 39

IterMVS-SCA-FT		97.85 208	98.18 167	96.87 324	99.27 161	91.16 372	95.53 346	99.25 189	99.10 80	99.41 80	99.35 83	93.10 289	99.96 11	98.65 83	99.94 40	99.49 127

UniMVSNet (Re)		98.87 78	98.71 89	99.35 70	99.24 166	98.73 85	97.73 212	99.38 130	98.93 98	99.12 128	98.73 219	96.77 179	99.86 108	98.63 85	99.80 109	99.46 146

EI-MVSNet		98.40 150	98.51 118	98.04 249	99.10 201	94.73 292	97.20 263	98.87 263	98.97 94	99.06 136	99.02 152	96.00 214	99.80 184	98.58 86	99.82 95	99.60 74

IterMVS-LS		98.55 132	98.70 92	98.09 241	99.48 122	94.73 292	97.22 262	99.39 128	98.97 94	99.38 87	99.31 93	96.00 214	99.93 40	98.58 86	99.97 19	99.60 74
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MVS_Test		98.18 179	98.36 144	97.67 276	98.48 312	94.73 292	98.18 149	99.02 242	97.69 181	98.04 261	99.11 133	97.22 153	99.56 314	98.57 88	98.90 309	98.71 306

UniMVSNet_NR-MVSNet		98.86 81	98.68 95	99.40 62	99.17 188	98.74 82	97.68 216	99.40 126	99.14 72	99.06 136	98.59 246	96.71 185	99.93 40	98.57 88	99.77 124	99.53 115

DU-MVS		98.82 84	98.63 102	99.39 63	99.16 190	98.74 82	97.54 235	99.25 189	98.84 106	99.06 136	98.76 216	96.76 181	99.93 40	98.57 88	99.77 124	99.50 123

UGNet		98.53 136	98.45 130	98.79 163	97.94 349	96.96 222	99.08 58	98.54 300	99.10 80	96.82 333	99.47 65	96.55 191	99.84 137	98.56 91	99.94 40	99.55 104
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
ECVR-MVS		96.42 293	96.61 277	95.85 352	99.38 140	88.18 389	99.22 42	86.00 408	99.08 85	99.36 92	99.57 42	88.47 335	99.82 164	98.52 92	99.95 32	99.54 108

iter_conf05		96.54 287	96.07 293	97.92 255	97.90 352	94.50 299	97.87 193	99.14 221	97.73 178	98.89 170	98.95 178	75.75 393	99.87 100	98.50 93	99.92 55	99.40 173

IterMVS		97.73 214	98.11 176	96.57 333	99.24 166	90.28 380	95.52 348	99.21 198	98.86 103	99.33 97	99.33 89	93.11 288	99.94 35	98.49 94	99.94 40	99.48 137
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
casdiffmvs		98.95 69	99.00 62	98.81 158	99.38 140	97.33 199	97.82 198	99.57 62	99.17 71	99.35 94	99.17 120	98.35 68	99.69 255	98.46 95	99.73 142	99.41 164
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVSTER		96.86 274	96.55 281	97.79 264	97.91 351	94.21 307	97.56 233	98.87 263	97.49 201	99.06 136	99.05 147	80.72 376	99.80 184	98.44 96	99.82 95	99.37 184

ACMH	96.65 7	99.25 33	99.24 39	99.26 90	99.72 44	98.38 109	99.07 61	99.55 73	98.30 134	99.65 45	99.45 70	99.22 15	99.76 221	98.44 96	99.77 124	99.64 63
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FMVSNet1		99.17 42	99.17 43	99.17 102	99.55 93	98.24 120	99.20 45	99.44 114	99.21 62	99.43 76	99.55 48	97.82 107	99.86 108	98.42 98	99.89 73	99.41 164

v148		98.45 145	98.60 109	98.00 251	99.44 129	94.98 285	97.44 245	99.06 231	98.30 134	99.32 103	98.97 171	96.65 187	99.62 292	98.37 99	99.85 81	99.39 175

GeoE		99.05 58	98.99 64	99.25 93	99.44 129	98.35 115	98.73 90	99.56 69	98.42 127	98.91 167	98.81 208	98.94 25	99.91 59	98.35 100	99.73 142	99.49 127

VDD-MVS		98.56 128	98.39 140	99.07 120	99.13 197	98.07 141	98.59 104	97.01 346	99.59 23	99.11 129	99.27 98	94.82 253	99.79 197	98.34 101	99.63 184	99.34 196

TranMVSNet+NR-MVSNet		99.17 42	99.07 58	99.46 56	99.37 146	98.87 73	98.39 132	99.42 123	99.42 41	99.36 92	99.06 140	98.38 64	99.95 22	98.34 101	99.90 69	99.57 91

pmmvs5		97.64 221	97.49 226	98.08 244	99.14 195	95.12 282	96.70 290	99.05 234	93.77 346	98.62 207	98.83 203	93.23 285	99.75 228	98.33 103	99.76 135	99.36 190

patch_mono-2		98.51 140	98.63 102	98.17 237	99.38 140	94.78 289	97.36 249	99.69 37	98.16 153	98.49 226	99.29 95	97.06 160	99.97 4	98.29 104	99.91 63	99.76 39

EU-MVSNet		97.66 220	98.50 120	95.13 366	99.63 74	85.84 396	98.35 136	98.21 314	98.23 141	99.54 56	99.46 66	95.02 247	99.68 264	98.24 105	99.87 77	99.87 16

TDRefinement		99.42 19	99.38 21	99.55 23	99.76 31	99.33 16	99.68 5	99.71 34	99.38 44	99.53 60	99.61 37	98.64 44	99.80 184	98.24 105	99.84 85	99.52 118

DELS-MVS		98.27 168	98.20 164	98.48 211	98.86 248	96.70 232	95.60 344	99.20 200	97.73 178	98.45 229	98.71 222	97.50 135	99.82 164	98.21 107	99.59 198	98.93 275
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
XXY-MVS		99.14 46	99.15 50	99.10 114	99.76 31	97.74 176	98.85 83	99.62 48	98.48 126	99.37 89	99.49 63	98.75 36	99.86 108	98.20 108	99.80 109	99.71 46

MGCFI-Net		98.34 157	98.28 154	98.51 207	98.47 313	97.59 186	98.96 72	99.48 96	99.18 70	97.40 305	95.50 375	98.66 43	99.50 333	98.18 109	98.71 319	98.44 329

alignmvs		97.35 241	96.88 258	98.78 166	98.54 307	98.09 135	97.71 213	97.69 331	99.20 64	97.59 288	95.90 367	88.12 338	99.55 317	98.18 109	98.96 304	98.70 309

Syy-MVS		96.04 302	95.56 307	97.49 294	97.10 386	94.48 300	96.18 318	96.58 358	95.65 301	94.77 378	92.29 403	91.27 314	99.36 358	98.17 111	98.05 353	98.63 316

VNet		98.42 147	98.30 152	98.79 163	98.79 264	97.29 201	98.23 143	98.66 293	99.31 52	98.85 179	98.80 209	94.80 256	99.78 208	98.13 112	99.13 284	99.31 207

h-mvs33		97.77 212	97.33 237	99.10 114	99.21 173	97.84 164	98.35 136	98.57 299	99.11 73	98.58 215	99.02 152	88.65 333	99.96 11	98.11 113	96.34 385	99.49 127

hse-mvs2		97.46 233	97.07 248	98.64 181	98.73 269	97.33 199	97.45 244	97.64 334	99.11 73	98.58 215	97.98 301	88.65 333	99.79 197	98.11 113	97.39 368	98.81 292

VPNet		98.87 78	98.83 76	99.01 133	99.70 54	97.62 185	98.43 128	99.35 143	99.47 34	99.28 106	99.05 147	96.72 184	99.82 164	98.09 115	99.36 247	99.59 80

sasdasda		98.34 157	98.26 158	98.58 193	98.46 315	97.82 168	98.96 72	99.46 106	99.19 68	97.46 300	95.46 378	98.59 50	99.46 344	98.08 116	98.71 319	98.46 324

canonicalmvs		98.34 157	98.26 158	98.58 193	98.46 315	97.82 168	98.96 72	99.46 106	99.19 68	97.46 300	95.46 378	98.59 50	99.46 344	98.08 116	98.71 319	98.46 324

Baseline_NR-MVSNet		98.98 65	98.86 74	99.36 64	99.82 21	98.55 97	97.47 243	99.57 62	99.37 45	99.21 120	99.61 37	96.76 181	99.83 154	98.06 118	99.83 92	99.71 46

DeepC-MVS	97.60 4	98.97 66	98.93 67	99.10 114	99.35 151	97.98 151	98.01 174	99.46 106	97.56 194	99.54 56	99.50 59	98.97 23	99.84 137	98.06 118	99.92 55	99.49 127
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
xiu_mvs_v1_base_debu		97.86 203	98.17 168	96.92 321	98.98 225	93.91 320	96.45 300	99.17 212	97.85 171	98.41 233	97.14 344	98.47 57	99.92 50	98.02 120	99.05 290	96.92 384

xiu_mvs_v1_base		97.86 203	98.17 168	96.92 321	98.98 225	93.91 320	96.45 300	99.17 212	97.85 171	98.41 233	97.14 344	98.47 57	99.92 50	98.02 120	99.05 290	96.92 384

xiu_mvs_v1_base_debi		97.86 203	98.17 168	96.92 321	98.98 225	93.91 320	96.45 300	99.17 212	97.85 171	98.41 233	97.14 344	98.47 57	99.92 50	98.02 120	99.05 290	96.92 384

dcpmvs_2		98.78 90	99.11 52	97.78 265	99.56 89	93.67 329	99.06 62	99.86 13	99.50 30	99.66 42	99.26 100	97.21 154	99.99 2	98.00 123	99.91 63	99.68 54

NR-MVSNet		98.95 69	98.82 77	99.36 64	99.16 190	98.72 87	99.22 42	99.20 200	99.10 80	99.72 31	98.76 216	96.38 199	99.86 108	98.00 123	99.82 95	99.50 123

SDMVSNet		99.23 38	99.32 28	98.96 139	99.68 58	97.35 198	98.84 85	99.48 96	99.69 9	99.63 48	99.68 20	99.03 21	99.96 11	97.97 125	99.92 55	99.57 91

FMVSNet2		98.49 141	98.40 137	98.75 173	98.90 240	97.14 215	98.61 102	99.13 222	98.59 118	99.19 122	99.28 96	94.14 272	99.82 164	97.97 125	99.80 109	99.29 212

diffmvs		98.22 174	98.24 161	98.17 237	99.00 221	95.44 270	96.38 305	99.58 55	97.79 175	98.53 223	98.50 258	96.76 181	99.74 233	97.95 127	99.64 181	99.34 196
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Anonymous20240529		98.93 71	98.87 71	99.12 110	99.19 180	98.22 125	99.01 66	98.99 248	99.25 58	99.54 56	99.37 79	97.04 161	99.80 184	97.89 128	99.52 222	99.35 194

pmmvs-eth3d		98.47 143	98.34 147	98.86 152	99.30 157	97.76 174	97.16 266	99.28 180	95.54 305	99.42 79	99.19 113	97.27 149	99.63 289	97.89 128	99.97 19	99.20 229

Patchmatch-RL test		97.26 248	97.02 251	97.99 252	99.52 103	95.53 266	96.13 321	99.71 34	97.47 202	99.27 108	99.16 122	84.30 363	99.62 292	97.89 128	99.77 124	98.81 292

VDDNet		98.21 176	97.95 190	99.01 133	99.58 77	97.74 176	99.01 66	97.29 341	99.67 12	98.97 154	99.50 59	90.45 319	99.80 184	97.88 131	99.20 273	99.48 137

APDe-MVS		98.99 62	98.79 80	99.60 11	99.21 173	99.15 47	98.87 80	99.48 96	97.57 192	99.35 94	99.24 105	97.83 104	99.89 74	97.88 131	99.70 159	99.75 43
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CANet		97.87 202	97.76 204	98.19 236	97.75 357	95.51 267	96.76 286	99.05 234	97.74 177	96.93 322	98.21 284	95.59 232	99.89 74	97.86 133	99.93 44	99.19 234

testf1		99.25 33	99.16 45	99.51 43	99.89 6	99.63 3	98.71 93	99.69 37	98.90 100	99.43 76	99.35 83	98.86 28	99.67 267	97.81 134	99.81 99	99.24 222

APD_test2		99.25 33	99.16 45	99.51 43	99.89 6	99.63 3	98.71 93	99.69 37	98.90 100	99.43 76	99.35 83	98.86 28	99.67 267	97.81 134	99.81 99	99.24 222

PM-MVS		98.82 84	98.72 87	99.12 110	99.64 70	98.54 100	97.98 178	99.68 42	97.62 186	99.34 96	99.18 116	97.54 129	99.77 215	97.79 136	99.74 139	99.04 255

tttt0517		95.64 315	94.98 324	97.64 280	99.36 147	93.81 325	98.72 91	90.47 401	98.08 156	98.67 200	98.34 274	73.88 395	99.92 50	97.77 137	99.51 224	99.20 229

GBi-Net		98.65 116	98.47 127	99.17 102	98.90 240	98.24 120	99.20 45	99.44 114	98.59 118	98.95 157	99.55 48	94.14 272	99.86 108	97.77 137	99.69 162	99.41 164

test1		98.65 116	98.47 127	99.17 102	98.90 240	98.24 120	99.20 45	99.44 114	98.59 118	98.95 157	99.55 48	94.14 272	99.86 108	97.77 137	99.69 162	99.41 164

FMVSNet3		97.50 229	97.24 240	98.29 229	98.08 342	95.83 258	97.86 195	98.91 257	97.89 168	98.95 157	98.95 178	87.06 339	99.81 177	97.77 137	99.69 162	99.23 224

UnsupCasMVSNet_eth		97.89 199	97.60 219	98.75 173	99.31 154	97.17 212	97.62 225	99.35 143	98.72 110	98.76 193	98.68 228	92.57 300	99.74 233	97.76 141	95.60 393	99.34 196

test20.03		98.78 90	98.77 82	98.78 166	99.46 125	97.20 209	97.78 203	99.24 194	99.04 88	99.41 80	98.90 187	97.65 117	99.76 221	97.70 142	99.79 114	99.39 175

Gipuma		99.03 59	99.16 45	98.64 181	99.94 2	98.51 102	99.32 23	99.75 32	99.58 25	98.60 211	99.62 34	98.22 76	99.51 332	97.70 142	99.73 142	97.89 360
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PatchT		96.65 283	96.35 285	97.54 289	97.40 378	95.32 274	97.98 178	96.64 357	99.33 50	96.89 329	99.42 73	84.32 362	99.81 177	97.69 144	97.49 362	97.48 378

mvsany_test1		97.60 224	97.54 221	97.77 266	97.72 358	95.35 273	95.36 354	97.13 344	94.13 340	99.71 33	99.33 89	97.93 100	99.30 368	97.60 145	98.94 306	98.67 314

D2MVS		97.84 209	97.84 201	97.83 261	99.14 195	94.74 291	96.94 275	98.88 261	95.84 297	98.89 170	98.96 174	94.40 266	99.69 255	97.55 146	99.95 32	99.05 251

MSLP-MVS++		98.02 190	98.14 174	97.64 280	98.58 302	95.19 279	97.48 241	99.23 196	97.47 202	97.90 267	98.62 242	97.04 161	98.81 393	97.55 146	99.41 241	98.94 274

WR-MVS		98.40 150	98.19 166	99.03 130	99.00 221	97.65 182	96.85 281	98.94 250	98.57 121	98.89 170	98.50 258	95.60 231	99.85 120	97.54 148	99.85 81	99.59 80

HPM-MVS_fast		99.01 60	98.82 77	99.57 16	99.71 47	99.35 12	99.00 68	99.50 87	97.33 218	98.94 164	98.86 197	98.75 36	99.82 164	97.53 149	99.71 154	99.56 97

RPMNet		97.02 266	96.93 253	97.30 303	97.71 360	94.22 305	98.11 157	99.30 169	99.37 45	96.91 325	99.34 87	86.72 341	99.87 100	97.53 149	97.36 371	97.81 365

PMMVS2		98.07 188	98.08 180	98.04 249	99.41 137	94.59 298	94.59 377	99.40 126	97.50 199	98.82 185	98.83 203	96.83 174	99.84 137	97.50 151	99.81 99	99.71 46

LFMVS		97.20 254	96.72 269	98.64 181	98.72 271	96.95 223	98.93 76	94.14 387	99.74 6	98.78 188	99.01 161	84.45 360	99.73 238	97.44 152	99.27 262	99.25 219

ACMM	96.08 12	98.91 73	98.73 85	99.48 51	99.55 93	99.14 52	98.07 163	99.37 134	97.62 186	99.04 143	98.96 174	98.84 30	99.79 197	97.43 153	99.65 179	99.49 127
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CHOSEN 280x420		95.51 319	95.47 308	95.65 358	98.25 331	88.27 388	93.25 394	98.88 261	93.53 349	94.65 381	97.15 343	86.17 346	99.93 40	97.41 154	99.93 44	98.73 305

CR-MVSNet		96.28 297	95.95 295	97.28 304	97.71 360	94.22 305	98.11 157	98.92 255	92.31 365	96.91 325	99.37 79	85.44 354	99.81 177	97.39 155	97.36 371	97.81 365

Anonymous202405211		97.90 197	97.50 225	99.08 118	98.90 240	98.25 119	98.53 111	96.16 364	98.87 102	99.11 129	98.86 197	90.40 320	99.78 208	97.36 156	99.31 255	99.19 234

CANet_DTU		97.26 248	97.06 249	97.84 260	97.57 366	94.65 296	96.19 317	98.79 280	97.23 233	95.14 375	98.24 281	93.22 286	99.84 137	97.34 157	99.84 85	99.04 255

Anonymous20231206		98.21 176	98.21 163	98.20 235	99.51 105	95.43 271	98.13 154	99.32 156	96.16 285	98.93 165	98.82 206	96.00 214	99.83 154	97.32 158	99.73 142	99.36 190

MP-MVS-pluss		98.57 127	98.23 162	99.60 11	99.69 56	99.35 12	97.16 266	99.38 130	94.87 323	98.97 154	98.99 165	98.01 93	99.88 83	97.29 159	99.70 159	99.58 86
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
FMVSNet5		96.01 303	95.20 320	98.41 218	97.53 371	96.10 247	98.74 87	99.50 87	97.22 236	98.03 262	99.04 149	69.80 397	99.88 83	97.27 160	99.71 154	99.25 219

our_test_3		97.39 239	97.73 208	96.34 338	98.70 278	89.78 382	94.61 376	98.97 249	96.50 269	99.04 143	98.85 200	95.98 219	99.84 137	97.26 161	99.67 173	99.41 164

sd_testset		99.28 29	99.31 30	99.19 101	99.68 58	98.06 144	99.41 13	99.30 169	99.69 9	99.63 48	99.68 20	99.25 14	99.96 11	97.25 162	99.92 55	99.57 91

jason		97.45 235	97.35 235	97.76 269	99.24 166	93.93 319	95.86 335	98.42 306	94.24 337	98.50 225	98.13 288	94.82 253	99.91 59	97.22 163	99.73 142	99.43 158
jason: jason.
miper_lstm_enhance		97.18 256	97.16 244	97.25 307	98.16 337	92.85 342	95.15 360	99.31 161	97.25 227	98.74 196	98.78 212	90.07 321	99.78 208	97.19 164	99.80 109	99.11 246

DP-MVS		98.93 71	98.81 79	99.28 85	99.21 173	98.45 106	98.46 125	99.33 154	99.63 17	99.48 68	99.15 126	97.23 152	99.75 228	97.17 165	99.66 178	99.63 66

MTAPA		98.88 77	98.64 101	99.61 9	99.67 62	99.36 11	98.43 128	99.20 200	98.83 107	98.89 170	98.90 187	96.98 167	99.92 50	97.16 166	99.70 159	99.56 97

TSAR-MVS + GP.		98.18 179	97.98 188	98.77 169	98.71 274	97.88 160	96.32 309	98.66 293	96.33 278	99.23 119	98.51 254	97.48 139	99.40 353	97.16 166	99.46 234	99.02 258

3Dnovator	98.27 2	98.81 86	98.73 85	99.05 127	98.76 265	97.81 171	99.25 40	99.30 169	98.57 121	98.55 220	99.33 89	97.95 99	99.90 64	97.16 166	99.67 173	99.44 154

MSC_two_6792asdad				99.32 80	98.43 319	98.37 111		98.86 268					99.89 74	97.14 169	99.60 194	99.71 46

No_MVS				99.32 80	98.43 319	98.37 111		98.86 268					99.89 74	97.14 169	99.60 194	99.71 46

ACMMP_NAP		98.75 95	98.48 125	99.57 16	99.58 77	99.29 19	97.82 198	99.25 189	96.94 249	98.78 188	99.12 132	98.02 92	99.84 137	97.13 171	99.67 173	99.59 80

PVSNet_Blended_VisFu		98.17 181	98.15 172	98.22 234	99.73 38	95.15 280	97.36 249	99.68 42	94.45 333	98.99 149	99.27 98	96.87 171	99.94 35	97.13 171	99.91 63	99.57 91

HyFIR lowres test		97.19 255	96.60 279	98.96 139	99.62 76	97.28 202	95.17 358	99.50 87	94.21 338	99.01 147	98.32 277	86.61 342	99.99 2	97.10 173	99.84 85	99.60 74

EGC-MVSNET		85.24 372	80.54 375	99.34 73	99.77 28	99.20 34	99.08 58	99.29 177	12.08 408	20.84 409	99.42 73	97.55 128	99.85 120	97.08 174	99.72 149	98.96 269

DVP-MVS++		98.90 75	98.70 92	99.51 43	98.43 319	99.15 47	99.43 11	99.32 156	98.17 150	99.26 112	99.02 152	98.18 80	99.88 83	97.07 175	99.45 236	99.49 127

test_0728_THIRD									98.17 150	99.08 134	99.02 152	97.89 101	99.88 83	97.07 175	99.71 154	99.70 51

eth_miper_zixun_eth		97.23 252	97.25 239	97.17 310	98.00 345	92.77 344	94.71 370	99.18 208	97.27 225	98.56 218	98.74 218	91.89 308	99.69 255	97.06 177	99.81 99	99.05 251

MDA-MVSNet_test_wron		97.60 224	97.66 214	97.41 300	99.04 216	93.09 336	95.27 355	98.42 306	97.26 226	98.88 174	98.95 178	95.43 238	99.73 238	97.02 178	98.72 317	99.41 164

cl____		97.02 266	96.83 262	97.58 284	97.82 355	94.04 313	94.66 373	99.16 215	97.04 244	98.63 205	98.71 222	88.68 332	99.69 255	97.00 179	99.81 99	99.00 262

DIV-MVS_self_test		97.02 266	96.84 261	97.58 284	97.82 355	94.03 314	94.66 373	99.16 215	97.04 244	98.63 205	98.71 222	88.69 330	99.69 255	97.00 179	99.81 99	99.01 259

DVP-MVS		98.77 93	98.52 117	99.52 39	99.50 108	99.21 28	98.02 171	98.84 272	97.97 160	99.08 134	99.02 152	97.61 123	99.88 83	96.99 181	99.63 184	99.48 137
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
test_0728_SECOND				99.60 11	99.50 108	99.23 26	98.02 171	99.32 156					99.88 83	96.99 181	99.63 184	99.68 54

YYNet1		97.60 224	97.67 211	97.39 301	99.04 216	93.04 340	95.27 355	98.38 309	97.25 227	98.92 166	98.95 178	95.48 237	99.73 238	96.99 181	98.74 315	99.41 164

pmmvs4		97.58 227	97.28 238	98.51 207	98.84 252	96.93 225	95.40 353	98.52 302	93.60 348	98.61 209	98.65 235	95.10 245	99.60 299	96.97 184	99.79 114	98.99 263

TAMVS		98.24 173	98.05 182	98.80 160	99.07 208	97.18 211	97.88 190	98.81 277	96.66 264	99.17 127	99.21 110	94.81 255	99.77 215	96.96 185	99.88 74	99.44 154

c3_l		97.36 240	97.37 233	97.31 302	98.09 341	93.25 335	95.01 363	99.16 215	97.05 243	98.77 191	98.72 221	92.88 294	99.64 286	96.93 186	99.76 135	99.05 251

SED-MVS		98.91 73	98.72 87	99.49 48	99.49 115	99.17 39	98.10 159	99.31 161	98.03 157	99.66 42	99.02 152	98.36 65	99.88 83	96.91 187	99.62 187	99.41 164

test_241102_TWO								99.30 169	98.03 157	99.26 112	99.02 152	97.51 134	99.88 83	96.91 187	99.60 194	99.66 58

ET-MVSNet_ETH3D		94.30 336	93.21 346	97.58 284	98.14 338	94.47 301	94.78 369	93.24 392	94.72 325	89.56 403	95.87 368	78.57 388	99.81 177	96.91 187	97.11 377	98.46 324

N_pmnet		97.63 222	97.17 243	98.99 135	99.27 161	97.86 162	95.98 326	93.41 390	95.25 314	99.47 70	98.90 187	95.63 230	99.85 120	96.91 187	99.73 142	99.27 215

1112_ss		97.29 247	96.86 259	98.58 193	99.34 153	96.32 241	96.75 287	99.58 55	93.14 354	96.89 329	97.48 330	92.11 306	99.86 108	96.91 187	99.54 215	99.57 91

thisisatest0530		95.27 322	94.45 331	97.74 272	99.19 180	94.37 303	97.86 195	90.20 402	97.17 238	98.22 244	97.65 320	73.53 396	99.90 64	96.90 192	99.35 249	98.95 270

Fast-Effi-MVS+-dtu		98.27 168	98.09 177	98.81 158	98.43 319	98.11 132	97.61 227	99.50 87	98.64 112	97.39 307	97.52 328	98.12 87	99.95 22	96.90 192	98.71 319	98.38 336

TSAR-MVS + MP.		98.63 120	98.49 124	99.06 126	99.64 70	97.90 159	98.51 117	98.94 250	96.96 247	99.24 117	98.89 193	97.83 104	99.81 177	96.88 194	99.49 232	99.48 137
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MVS_111021_HR		98.25 172	98.08 180	98.75 173	99.09 204	97.46 192	95.97 327	99.27 183	97.60 190	97.99 263	98.25 280	98.15 86	99.38 357	96.87 195	99.57 207	99.42 161

EPP-MVSNet		98.30 164	98.04 183	99.07 120	99.56 89	97.83 165	99.29 33	98.07 322	99.03 89	98.59 213	99.13 130	92.16 305	99.90 64	96.87 195	99.68 167	99.49 127

ZNCC-MVS		98.68 111	98.40 137	99.54 27	99.57 81	99.21 28	98.46 125	99.29 177	97.28 224	98.11 254	98.39 267	98.00 94	99.87 100	96.86 197	99.64 181	99.55 104

MS-PatchMatch		97.68 218	97.75 205	97.45 297	98.23 334	93.78 326	97.29 255	98.84 272	96.10 287	98.64 204	98.65 235	96.04 211	99.36 358	96.84 198	99.14 282	99.20 229

3Dnovator+	97.89 3	98.69 106	98.51 118	99.24 95	98.81 260	98.40 107	99.02 65	99.19 204	98.99 92	98.07 257	99.28 96	97.11 159	99.84 137	96.84 198	99.32 253	99.47 144

miper_ehance_all_eth		97.06 263	97.03 250	97.16 312	97.83 354	93.06 337	94.66 373	99.09 228	95.99 292	98.69 198	98.45 263	92.73 298	99.61 298	96.79 200	99.03 294	98.82 288

XVS		98.72 98	98.45 130	99.53 34	99.46 125	99.21 28	98.65 97	99.34 149	98.62 116	97.54 293	98.63 240	97.50 135	99.83 154	96.79 200	99.53 219	99.56 97

X-MVStestdata		94.32 334	92.59 352	99.53 34	99.46 125	99.21 28	98.65 97	99.34 149	98.62 116	97.54 293	45.85 406	97.50 135	99.83 154	96.79 200	99.53 219	99.56 97

lupinMVS		97.06 263	96.86 259	97.65 278	98.88 246	93.89 323	95.48 349	97.97 324	93.53 349	98.16 248	97.58 324	93.81 280	99.91 59	96.77 203	99.57 207	99.17 240

IU-MVS					99.49 115	99.15 47		98.87 263	92.97 356	99.41 80				96.76 204	99.62 187	99.66 58

CHOSEN 1792x2688		97.49 231	97.14 247	98.54 204	99.68 58	96.09 250	96.50 298	99.62 48	91.58 371	98.84 181	98.97 171	92.36 302	99.88 83	96.76 204	99.95 32	99.67 57

ppachtmachnet_test		97.50 229	97.74 206	96.78 330	98.70 278	91.23 371	94.55 378	99.05 234	96.36 277	99.21 120	98.79 211	96.39 197	99.78 208	96.74 206	99.82 95	99.34 196

DeepPCF-MVS	96.93 5	98.32 161	98.01 185	99.23 97	98.39 324	98.97 66	95.03 362	99.18 208	96.88 252	99.33 97	98.78 212	98.16 84	99.28 372	96.74 206	99.62 187	99.44 154

EIA-MVS		98.00 192	97.74 206	98.80 160	98.72 271	98.09 135	98.05 166	99.60 52	97.39 213	96.63 340	95.55 373	97.68 114	99.80 184	96.73 208	99.27 262	98.52 322

CDS-MVSNet		97.69 217	97.35 235	98.69 178	98.73 269	97.02 219	96.92 279	98.75 287	95.89 296	98.59 213	98.67 230	92.08 307	99.74 233	96.72 209	99.81 99	99.32 203
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CSCG		98.68 111	98.50 120	99.20 99	99.45 128	98.63 89	98.56 107	99.57 62	97.87 169	98.85 179	98.04 298	97.66 116	99.84 137	96.72 209	99.81 99	99.13 244

ACMH+	96.62 9	99.08 57	99.00 62	99.33 78	99.71 47	98.83 76	98.60 103	99.58 55	99.11 73	99.53 60	99.18 116	98.81 32	99.67 267	96.71 211	99.77 124	99.50 123

MVS_111021_LR		98.30 164	98.12 175	98.83 155	99.16 190	98.03 146	96.09 323	99.30 169	97.58 191	98.10 255	98.24 281	98.25 71	99.34 362	96.69 212	99.65 179	99.12 245

OPM-MVS		98.56 128	98.32 151	99.25 93	99.41 137	98.73 85	97.13 268	99.18 208	97.10 242	98.75 194	98.92 183	98.18 80	99.65 283	96.68 213	99.56 210	99.37 184
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Effi-MVS+-dtu		98.26 170	97.90 196	99.35 70	98.02 344	99.49 5	98.02 171	99.16 215	98.29 137	97.64 284	97.99 300	96.44 196	99.95 22	96.66 214	98.93 307	98.60 318

Effi-MVS+		98.02 190	97.82 202	98.62 186	98.53 309	97.19 210	97.33 251	99.68 42	97.30 222	96.68 338	97.46 332	98.56 54	99.80 184	96.63 215	98.20 341	98.86 285

MDA-MVSNet-bldmvs		97.94 196	97.91 195	98.06 246	99.44 129	94.96 286	96.63 293	99.15 220	98.35 129	98.83 182	99.11 133	94.31 269	99.85 120	96.60 216	98.72 317	99.37 184

Test_1112_low_res		96.99 270	96.55 281	98.31 227	99.35 151	95.47 269	95.84 338	99.53 81	91.51 373	96.80 334	98.48 261	91.36 313	99.83 154	96.58 217	99.53 219	99.62 67

LS3D		98.63 120	98.38 142	99.36 64	97.25 382	99.38 8	99.12 57	99.32 156	99.21 62	98.44 230	98.88 194	97.31 145	99.80 184	96.58 217	99.34 251	98.92 276

APD_test1		98.83 83	98.66 98	99.34 73	99.78 25	99.47 6	98.42 130	99.45 110	98.28 139	98.98 150	99.19 113	97.76 110	99.58 309	96.57 219	99.55 213	98.97 267

HFP-MVS		98.71 99	98.44 132	99.51 43	99.49 115	99.16 43	98.52 112	99.31 161	97.47 202	98.58 215	98.50 258	97.97 98	99.85 120	96.57 219	99.59 198	99.53 115

ACMMPR		98.70 103	98.42 135	99.54 27	99.52 103	99.14 52	98.52 112	99.31 161	97.47 202	98.56 218	98.54 250	97.75 111	99.88 83	96.57 219	99.59 198	99.58 86

sss		97.21 253	96.93 253	98.06 246	98.83 254	95.22 278	96.75 287	98.48 304	94.49 329	97.27 310	97.90 307	92.77 297	99.80 184	96.57 219	99.32 253	99.16 243

SR-MVS-dyc-post		98.81 86	98.55 113	99.57 16	99.20 177	99.38 8	98.48 123	99.30 169	98.64 112	98.95 157	98.96 174	97.49 138	99.86 108	96.56 223	99.39 243	99.45 150

RE-MVS-def			98.58 111		99.20 177	99.38 8	98.48 123	99.30 169	98.64 112	98.95 157	98.96 174	97.75 111		96.56 223	99.39 243	99.45 150

SD-MVS		98.40 150	98.68 95	97.54 289	98.96 228	97.99 148	97.88 190	99.36 138	98.20 147	99.63 48	99.04 149	98.76 35	95.33 407	96.56 223	99.74 139	99.31 207
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
ambc				98.24 233	98.82 257	95.97 254	98.62 101	99.00 247		99.27 108	99.21 110	96.99 166	99.50 333	96.55 226	99.50 231	99.26 218

APD-MVS_3200maxsize		98.84 82	98.61 108	99.53 34	99.19 180	99.27 22	98.49 120	99.33 154	98.64 112	99.03 146	98.98 169	97.89 101	99.85 120	96.54 227	99.42 240	99.46 146

CP-MVS		98.70 103	98.42 135	99.52 39	99.36 147	99.12 57	98.72 91	99.36 138	97.54 197	98.30 240	98.40 266	97.86 103	99.89 74	96.53 228	99.72 149	99.56 97

MVP-Stereo		98.08 187	97.92 194	98.57 196	98.96 228	96.79 228	97.90 187	99.18 208	96.41 276	98.46 228	98.95 178	95.93 222	99.60 299	96.51 229	98.98 302	99.31 207
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
testgi		98.32 161	98.39 140	98.13 240	99.57 81	95.54 265	97.78 203	99.49 94	97.37 215	99.19 122	97.65 320	98.96 24	99.49 336	96.50 230	98.99 300	99.34 196

HPM-MVS		98.79 88	98.53 116	99.59 15	99.65 65	99.29 19	99.16 51	99.43 120	96.74 260	98.61 209	98.38 269	98.62 47	99.87 100	96.47 231	99.67 173	99.59 80
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
region2R		98.69 106	98.40 137	99.54 27	99.53 101	99.17 39	98.52 112	99.31 161	97.46 207	98.44 230	98.51 254	97.83 104	99.88 83	96.46 232	99.58 203	99.58 86

SMA-MVS		98.40 150	98.03 184	99.51 43	99.16 190	99.21 28	98.05 166	99.22 197	94.16 339	98.98 150	99.10 136	97.52 133	99.79 197	96.45 233	99.64 181	99.53 115
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
CNVR-MVS		98.17 181	97.87 199	99.07 120	98.67 286	98.24 120	97.01 271	98.93 252	97.25 227	97.62 285	98.34 274	97.27 149	99.57 311	96.42 234	99.33 252	99.39 175

CL-MVSNet_self_test		97.44 236	97.22 241	98.08 244	98.57 304	95.78 260	94.30 383	98.79 280	96.58 267	98.60 211	98.19 286	94.74 260	99.64 286	96.41 235	98.84 310	98.82 288

cl22		95.79 310	95.39 314	96.98 318	96.77 393	92.79 343	94.40 381	98.53 301	94.59 328	97.89 268	98.17 287	82.82 372	99.24 374	96.37 236	99.03 294	98.92 276

PS-MVSNAJ		97.08 262	97.39 231	96.16 349	98.56 305	92.46 349	95.24 357	98.85 271	97.25 227	97.49 298	95.99 364	98.07 88	99.90 64	96.37 236	98.67 325	96.12 396

CVMVSNet		96.25 298	97.21 242	93.38 384	99.10 201	80.56 411	97.20 263	98.19 317	96.94 249	99.00 148	99.02 152	89.50 326	99.80 184	96.36 238	99.59 198	99.78 33

xiu_mvs_v2_base		97.16 258	97.49 226	96.17 347	98.54 307	92.46 349	95.45 350	98.84 272	97.25 227	97.48 299	96.49 355	98.31 70	99.90 64	96.34 239	98.68 324	96.15 395

AUN-MVS		96.24 299	95.45 310	98.60 191	98.70 278	97.22 207	97.38 247	97.65 332	95.95 294	95.53 370	97.96 305	82.11 375	99.79 197	96.31 240	97.44 365	98.80 297

miper_enhance_ethall		96.01 303	95.74 298	96.81 328	96.41 399	92.27 355	93.69 392	98.89 260	91.14 378	98.30 240	97.35 339	90.58 318	99.58 309	96.31 240	99.03 294	98.60 318

ACMMP		98.75 95	98.50 120	99.52 39	99.56 89	99.16 43	98.87 80	99.37 134	97.16 239	98.82 185	99.01 161	97.71 113	99.87 100	96.29 242	99.69 162	99.54 108
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
iter_conf05_11		96.72 279	96.30 288	97.97 253	97.97 346	96.24 245	94.99 364	96.19 363	96.45 274	96.77 336	96.84 348	91.46 312	99.78 208	96.27 243	99.78 119	97.90 358

bld_raw_dy_0_64		97.62 223	97.51 224	97.96 254	97.97 346	96.28 243	98.20 147	99.82 22	96.46 273	99.37 89	97.12 347	92.42 301	99.70 250	96.27 243	99.97 19	97.90 358

ETV-MVS		98.03 189	97.86 200	98.56 200	98.69 283	98.07 141	97.51 239	99.50 87	98.10 155	97.50 297	95.51 374	98.41 62	99.88 83	96.27 243	99.24 267	97.71 372

XVG-OURS-SEG-HR		98.49 141	98.28 154	99.14 108	99.49 115	98.83 76	96.54 295	99.48 96	97.32 220	99.11 129	98.61 244	99.33 13	99.30 368	96.23 246	98.38 334	99.28 214

GA-MVS		95.86 308	95.32 317	97.49 294	98.60 297	94.15 310	93.83 390	97.93 325	95.49 307	96.68 338	97.42 334	83.21 368	99.30 368	96.22 247	98.55 332	99.01 259

mPP-MVS		98.64 118	98.34 147	99.54 27	99.54 98	99.17 39	98.63 99	99.24 194	97.47 202	98.09 256	98.68 228	97.62 122	99.89 74	96.22 247	99.62 187	99.57 91

Fast-Effi-MVS+		97.67 219	97.38 232	98.57 196	98.71 274	97.43 195	97.23 259	99.45 110	94.82 324	96.13 354	96.51 354	98.52 56	99.91 59	96.19 249	98.83 311	98.37 338

pmmvs3		95.03 326	94.40 332	96.93 320	97.70 362	92.53 348	95.08 361	97.71 330	88.57 391	97.71 280	98.08 295	79.39 383	99.82 164	96.19 249	99.11 288	98.43 331

MCST-MVS		98.00 192	97.63 217	99.10 114	99.24 166	98.17 127	96.89 280	98.73 290	95.66 300	97.92 265	97.70 318	97.17 155	99.66 278	96.18 251	99.23 269	99.47 144

SteuartSystems-ACMMP		98.79 88	98.54 115	99.54 27	99.73 38	99.16 43	98.23 143	99.31 161	97.92 165	98.90 168	98.90 187	98.00 94	99.88 83	96.15 252	99.72 149	99.58 86
Skip Steuart: Steuart Systems R&D Blog.
SR-MVS		98.71 99	98.43 133	99.57 16	99.18 187	99.35 12	98.36 135	99.29 177	98.29 137	98.88 174	98.85 200	97.53 131	99.87 100	96.14 253	99.31 255	99.48 137

MSP-MVS		98.40 150	98.00 186	99.61 9	99.57 81	99.25 24	98.57 106	99.35 143	97.55 196	99.31 105	97.71 316	94.61 261	99.88 83	96.14 253	99.19 276	99.70 51
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
FA-MVS(test-final)		96.99 270	96.82 263	97.50 293	98.70 278	94.78 289	99.34 20	96.99 347	95.07 317	98.48 227	99.33 89	88.41 336	99.65 283	96.13 255	98.92 308	98.07 351

DeepC-MVS_fast	96.85 6	98.30 164	98.15 172	98.75 173	98.61 295	97.23 205	97.76 208	99.09 228	97.31 221	98.75 194	98.66 233	97.56 127	99.64 286	96.10 256	99.55 213	99.39 175
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
GST-MVS		98.61 123	98.30 152	99.52 39	99.51 105	99.20 34	98.26 141	99.25 189	97.44 210	98.67 200	98.39 267	97.68 114	99.85 120	96.00 257	99.51 224	99.52 118

EPNet		96.14 300	95.44 311	98.25 231	90.76 411	95.50 268	97.92 184	94.65 379	98.97 94	92.98 395	98.85 200	89.12 328	99.87 100	95.99 258	99.68 167	99.39 175
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
COLMAP_ROB	96.50 10	98.99 62	98.85 75	99.41 60	99.58 77	99.10 60	98.74 87	99.56 69	99.09 83	99.33 97	99.19 113	98.40 63	99.72 245	95.98 259	99.76 135	99.42 161
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Patchmtry		97.35 241	96.97 252	98.50 210	97.31 381	96.47 237	98.18 149	98.92 255	98.95 97	98.78 188	99.37 79	85.44 354	99.85 120	95.96 260	99.83 92	99.17 240

tfpnnormal		98.90 75	98.90 70	98.91 147	99.67 62	97.82 168	99.00 68	99.44 114	99.45 36	99.51 66	99.24 105	98.20 79	99.86 108	95.92 261	99.69 162	99.04 255

XVG-ACMP-BASELINE		98.56 128	98.34 147	99.22 98	99.54 98	98.59 94	97.71 213	99.46 106	97.25 227	98.98 150	98.99 165	97.54 129	99.84 137	95.88 262	99.74 139	99.23 224

tpm		94.67 330	94.34 334	95.66 357	97.68 365	88.42 386	97.88 190	94.90 377	94.46 331	96.03 359	98.56 249	78.66 386	99.79 197	95.88 262	95.01 396	98.78 299

ab-mvs		98.41 148	98.36 144	98.59 192	99.19 180	97.23 205	99.32 23	98.81 277	97.66 183	98.62 207	99.40 78	96.82 175	99.80 184	95.88 262	99.51 224	98.75 303

test-LLR		93.90 343	93.85 337	94.04 375	96.53 396	84.62 402	94.05 387	92.39 394	96.17 283	94.12 386	95.07 382	82.30 373	99.67 267	95.87 265	98.18 342	97.82 363

test-mter		92.33 365	91.76 366	94.04 375	96.53 396	84.62 402	94.05 387	92.39 394	94.00 344	94.12 386	95.07 382	65.63 406	99.67 267	95.87 265	98.18 342	97.82 363

PGM-MVS		98.66 115	98.37 143	99.55 23	99.53 101	99.18 38	98.23 143	99.49 94	97.01 246	98.69 198	98.88 194	98.00 94	99.89 74	95.87 265	99.59 198	99.58 86

USDC		97.41 238	97.40 230	97.44 298	98.94 230	93.67 329	95.17 358	99.53 81	94.03 343	98.97 154	99.10 136	95.29 240	99.34 362	95.84 268	99.73 142	99.30 210

HPM-MVS++		98.10 183	97.64 216	99.48 51	99.09 204	99.13 55	97.52 237	98.75 287	97.46 207	96.90 328	97.83 311	96.01 213	99.84 137	95.82 269	99.35 249	99.46 146

TESTMET0.1,1		92.19 367	91.77 365	93.46 382	96.48 398	82.80 407	94.05 387	91.52 398	94.45 333	94.00 389	94.88 388	66.65 402	99.56 314	95.78 270	98.11 348	98.02 353

DSMNet-mixed		97.42 237	97.60 219	96.87 324	99.15 194	91.46 362	98.54 110	99.12 223	92.87 359	97.58 289	99.63 33	96.21 205	99.90 64	95.74 271	99.54 215	99.27 215

XVG-OURS		98.53 136	98.34 147	99.11 112	99.50 108	98.82 78	95.97 327	99.50 87	97.30 222	99.05 141	98.98 169	99.35 12	99.32 365	95.72 272	99.68 167	99.18 236

RPSCF		98.62 122	98.36 144	99.42 58	99.65 65	99.42 7	98.55 108	99.57 62	97.72 180	98.90 168	99.26 100	96.12 208	99.52 328	95.72 272	99.71 154	99.32 203

PHI-MVS		98.29 167	97.95 190	99.34 73	98.44 318	99.16 43	98.12 156	99.38 130	96.01 291	98.06 258	98.43 264	97.80 108	99.67 267	95.69 274	99.58 203	99.20 229

SF-MVS		98.53 136	98.27 157	99.32 80	99.31 154	98.75 81	98.19 148	99.41 124	96.77 259	98.83 182	98.90 187	97.80 108	99.82 164	95.68 275	99.52 222	99.38 182

test_0402		98.76 94	98.71 89	98.93 144	99.56 89	98.14 130	98.45 127	99.34 149	99.28 56	98.95 157	98.91 184	98.34 69	99.79 197	95.63 276	99.91 63	98.86 285

tpmrst		95.07 325	95.46 309	93.91 377	97.11 385	84.36 404	97.62 225	96.96 349	94.98 319	96.35 351	98.80 209	85.46 353	99.59 303	95.60 277	96.23 387	97.79 368

PMMVS		96.51 288	95.98 294	98.09 241	97.53 371	95.84 257	94.92 366	98.84 272	91.58 371	96.05 358	95.58 372	95.68 229	99.66 278	95.59 278	98.09 349	98.76 302

LPG-MVS_test		98.71 99	98.46 129	99.47 54	99.57 81	98.97 66	98.23 143	99.48 96	96.60 265	99.10 132	99.06 140	98.71 39	99.83 154	95.58 279	99.78 119	99.62 67

LGP-MVS_train				99.47 54	99.57 81	98.97 66		99.48 96	96.60 265	99.10 132	99.06 140	98.71 39	99.83 154	95.58 279	99.78 119	99.62 67

IS-MVSNet		98.19 178	97.90 196	99.08 118	99.57 81	97.97 152	99.31 27	98.32 310	99.01 91	98.98 150	99.03 151	91.59 310	99.79 197	95.49 281	99.80 109	99.48 137

baseline1		95.96 306	95.44 311	97.52 291	98.51 311	93.99 317	98.39 132	96.09 366	98.21 143	98.40 237	97.76 314	86.88 340	99.63 289	95.42 282	89.27 405	98.95 270

DPE-MVS		98.59 126	98.26 158	99.57 16	99.27 161	99.15 47	97.01 271	99.39 128	97.67 182	99.44 75	98.99 165	97.53 131	99.89 74	95.40 283	99.68 167	99.66 58
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
NCCC		97.86 203	97.47 229	99.05 127	98.61 295	98.07 141	96.98 273	98.90 258	97.63 185	97.04 318	97.93 306	95.99 218	99.66 278	95.31 284	98.82 313	99.43 158

testing3		93.51 348	92.09 357	97.75 270	98.60 297	94.40 302	97.32 252	95.26 376	97.56 194	96.79 335	95.50 375	53.57 413	99.77 215	95.26 285	98.97 303	99.08 247

PC_three_1452									93.27 352	99.40 83	98.54 250	98.22 76	97.00 403	95.17 286	99.45 236	99.49 127

Patchmatch-test		96.55 286	96.34 286	97.17 310	98.35 325	93.06 337	98.40 131	97.79 327	97.33 218	98.41 233	98.67 230	83.68 367	99.69 255	95.16 287	99.31 255	98.77 300

EPMVS		93.72 346	93.27 345	95.09 368	96.04 403	87.76 390	98.13 154	85.01 409	94.69 326	96.92 323	98.64 238	78.47 390	99.31 366	95.04 288	96.46 384	98.20 344

UnsupCasMVSNet_bld		97.30 245	96.92 255	98.45 214	99.28 159	96.78 231	96.20 316	99.27 183	95.42 309	98.28 242	98.30 278	93.16 287	99.71 246	94.99 289	97.37 369	98.87 284

PatchmatchNet		95.58 316	95.67 302	95.30 365	97.34 380	87.32 392	97.65 222	96.65 356	95.30 313	97.07 316	98.69 226	84.77 357	99.75 228	94.97 290	98.64 326	98.83 287
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPNet_dtu		94.93 328	94.78 329	95.38 364	93.58 408	87.68 391	96.78 284	95.69 374	97.35 217	89.14 404	98.09 294	88.15 337	99.49 336	94.95 291	99.30 258	98.98 264
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_yl		96.69 280	96.29 289	97.90 256	98.28 329	95.24 276	97.29 255	97.36 337	98.21 143	98.17 246	97.86 308	86.27 344	99.55 317	94.87 292	98.32 335	98.89 280

DCV-MVSNet		96.69 280	96.29 289	97.90 256	98.28 329	95.24 276	97.29 255	97.36 337	98.21 143	98.17 246	97.86 308	86.27 344	99.55 317	94.87 292	98.32 335	98.89 280

ACMP	95.32 15	98.41 148	98.09 177	99.36 64	99.51 105	98.79 80	97.68 216	99.38 130	95.76 299	98.81 187	98.82 206	98.36 65	99.82 164	94.75 294	99.77 124	99.48 137
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PVSNet_BlendedMVS		97.55 228	97.53 222	97.60 282	98.92 236	93.77 327	96.64 292	99.43 120	94.49 329	97.62 285	99.18 116	96.82 175	99.67 267	94.73 295	99.93 44	99.36 190

PVSNet_Blended		96.88 273	96.68 272	97.47 296	98.92 236	93.77 327	94.71 370	99.43 120	90.98 379	97.62 285	97.36 338	96.82 175	99.67 267	94.73 295	99.56 210	98.98 264

MP-MVS		98.46 144	98.09 177	99.54 27	99.57 81	99.22 27	98.50 119	99.19 204	97.61 189	97.58 289	98.66 233	97.40 142	99.88 83	94.72 297	99.60 194	99.54 108
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
OPU-MVS				98.82 156	98.59 300	98.30 116	98.10 159				98.52 253	98.18 80	98.75 394	94.62 298	99.48 233	99.41 164

LF4IMVS		97.90 197	97.69 210	98.52 206	99.17 188	97.66 181	97.19 265	99.47 104	96.31 280	97.85 272	98.20 285	96.71 185	99.52 328	94.62 298	99.72 149	98.38 336

CostFormer		93.97 342	93.78 339	94.51 371	97.53 371	85.83 397	97.98 178	95.96 368	89.29 389	94.99 377	98.63 240	78.63 387	99.62 292	94.54 300	96.50 383	98.09 350

thisisatest0515		94.12 340	93.16 347	96.97 319	98.60 297	92.90 341	93.77 391	90.61 400	94.10 341	96.91 325	95.87 368	74.99 394	99.80 184	94.52 301	99.12 287	98.20 344

旧先验2							95.76 339		88.56 392	97.52 295			99.66 278	94.48 302

CLD-MVS		97.49 231	97.16 244	98.48 211	99.07 208	97.03 218	94.71 370	99.21 198	94.46 331	98.06 258	97.16 342	97.57 126	99.48 339	94.46 303	99.78 119	98.95 270
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
AllTest		98.44 146	98.20 164	99.16 105	99.50 108	98.55 97	98.25 142	99.58 55	96.80 256	98.88 174	99.06 140	97.65 117	99.57 311	94.45 304	99.61 192	99.37 184

TestCases				99.16 105	99.50 108	98.55 97		99.58 55	96.80 256	98.88 174	99.06 140	97.65 117	99.57 311	94.45 304	99.61 192	99.37 184

HQP_MVS		97.99 195	97.67 211	98.93 144	99.19 180	97.65 182	97.77 205	99.27 183	98.20 147	97.79 276	97.98 301	94.90 249	99.70 250	94.42 306	99.51 224	99.45 150

plane_prior5								99.27 183					99.70 250	94.42 306	99.51 224	99.45 150

JIA-IIPM		95.52 318	95.03 323	97.00 316	96.85 391	94.03 314	96.93 277	95.82 370	99.20 64	94.63 382	99.71 17	83.09 369	99.60 299	94.42 306	94.64 397	97.36 381

cascas		94.79 329	94.33 335	96.15 350	96.02 404	92.36 353	92.34 399	99.26 188	85.34 398	95.08 376	94.96 387	92.96 293	98.53 396	94.41 309	98.59 330	97.56 377

TinyColmap		97.89 199	97.98 188	97.60 282	98.86 248	94.35 304	96.21 315	99.44 114	97.45 209	99.06 136	98.88 194	97.99 97	99.28 372	94.38 310	99.58 203	99.18 236

9.14			97.78 203		99.07 208		97.53 236	99.32 156	95.53 306	98.54 222	98.70 225	97.58 125	99.76 221	94.32 311	99.46 234

test_post1							97.59 230				20.48 410	83.07 370	99.66 278	94.16 312

SCA		96.41 294	96.66 275	95.67 356	98.24 332	88.35 387	95.85 337	96.88 353	96.11 286	97.67 283	98.67 230	93.10 289	99.85 120	94.16 312	99.22 270	98.81 292

test_prior2							95.74 340		96.48 271	96.11 355	97.63 322	95.92 223		94.16 312	99.20 273

tpmvs		95.02 327	95.25 318	94.33 372	96.39 400	85.87 395	98.08 161	96.83 354	95.46 308	95.51 371	98.69 226	85.91 349	99.53 324	94.16 312	96.23 387	97.58 376

LCM-MVSNet-Re		98.64 118	98.48 125	99.11 112	98.85 251	98.51 102	98.49 120	99.83 20	98.37 128	99.69 37	99.46 66	98.21 78	99.92 50	94.13 316	99.30 258	98.91 279

MSDG		97.71 216	97.52 223	98.28 230	98.91 239	96.82 227	94.42 380	99.37 134	97.65 184	98.37 238	98.29 279	97.40 142	99.33 364	94.09 317	99.22 270	98.68 313

MVS-HIRNet		94.32 334	95.62 303	90.42 388	98.46 315	75.36 412	96.29 311	89.13 404	95.25 314	95.38 372	99.75 11	92.88 294	99.19 378	94.07 318	99.39 243	96.72 389

DP-MVS Recon		97.33 243	96.92 255	98.57 196	99.09 204	97.99 148	96.79 283	99.35 143	93.18 353	97.71 280	98.07 296	95.00 248	99.31 366	93.97 319	99.13 284	98.42 333

new_pmnet		96.99 270	96.76 267	97.67 276	98.72 271	94.89 287	95.95 331	98.20 315	92.62 362	98.55 220	98.54 250	94.88 252	99.52 328	93.96 320	99.44 239	98.59 320

MDTV_nov1_ep13			95.22 319		97.06 388	83.20 406	97.74 210	96.16 364	94.37 335	96.99 321	98.83 203	83.95 365	99.53 324	93.90 321	97.95 356

WTY-MVS		96.67 282	96.27 291	97.87 259	98.81 260	94.61 297	96.77 285	97.92 326	94.94 321	97.12 313	97.74 315	91.11 315	99.82 164	93.89 322	98.15 346	99.18 236

Vis-MVSNet (Re-imp)		97.46 233	97.16 244	98.34 224	99.55 93	96.10 247	98.94 75	98.44 305	98.32 133	98.16 248	98.62 242	88.76 329	99.73 238	93.88 323	99.79 114	99.18 236

ITE_SJBPF				98.87 151	99.22 171	98.48 104		99.35 143	97.50 199	98.28 242	98.60 245	97.64 120	99.35 361	93.86 324	99.27 262	98.79 298

CPTT-MVS		97.84 209	97.36 234	99.27 88	99.31 154	98.46 105	98.29 138	99.27 183	94.90 322	97.83 273	98.37 270	94.90 249	99.84 137	93.85 325	99.54 215	99.51 120

APD-MVS		98.10 183	97.67 211	99.42 58	99.11 199	98.93 71	97.76 208	99.28 180	94.97 320	98.72 197	98.77 214	97.04 161	99.85 120	93.79 326	99.54 215	99.49 127
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
testing11		93.08 355	92.02 359	96.26 342	97.56 367	90.83 376	96.32 309	95.70 372	96.47 272	92.66 397	93.73 394	64.36 408	99.59 303	93.77 327	97.57 360	98.37 338

train_agg		97.10 260	96.45 284	99.07 120	98.71 274	98.08 139	95.96 329	99.03 239	91.64 369	95.85 360	97.53 326	96.47 194	99.76 221	93.67 328	99.16 279	99.36 190

PVSNet	93.40 17	95.67 313	95.70 300	95.57 359	98.83 254	88.57 385	92.50 397	97.72 329	92.69 361	96.49 349	96.44 358	93.72 283	99.43 349	93.61 329	99.28 261	98.71 306

test0.0.03 1		94.51 331	93.69 340	96.99 317	96.05 402	93.61 332	94.97 365	93.49 389	96.17 283	97.57 291	94.88 388	82.30 373	99.01 386	93.60 330	94.17 400	98.37 338

testdata				98.09 241	98.93 232	95.40 272		98.80 279	90.08 385	97.45 302	98.37 270	95.26 241	99.70 250	93.58 331	98.95 305	99.17 240

MDTV_nov1_ep13_2view						74.92 413	97.69 215		90.06 386	97.75 279		85.78 350		93.52 332		98.69 310

TAPA-MVS	96.21 11	96.63 284	95.95 295	98.65 180	98.93 232	98.09 135	96.93 277	99.28 180	83.58 400	98.13 252	97.78 312	96.13 207	99.40 353	93.52 332	99.29 260	98.45 327
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
OMC-MVS		97.88 201	97.49 226	99.04 129	98.89 245	98.63 89	96.94 275	99.25 189	95.02 318	98.53 223	98.51 254	97.27 149	99.47 342	93.50 334	99.51 224	99.01 259

PatchMatch-RL		97.24 251	96.78 266	98.61 189	99.03 219	97.83 165	96.36 306	99.06 231	93.49 351	97.36 309	97.78 312	95.75 227	99.49 336	93.44 335	98.77 314	98.52 322

114514_t		96.50 290	95.77 297	98.69 178	99.48 122	97.43 195	97.84 197	99.55 73	81.42 402	96.51 346	98.58 247	95.53 233	99.67 267	93.41 336	99.58 203	98.98 264

dp		93.47 349	93.59 342	93.13 386	96.64 395	81.62 410	97.66 220	96.42 361	92.80 360	96.11 355	98.64 238	78.55 389	99.59 303	93.31 337	92.18 404	98.16 346

test9_res														93.28 338	99.15 281	99.38 182

testing99		93.04 356	91.98 362	96.23 344	97.53 371	90.70 378	96.35 307	95.94 369	96.87 253	93.41 394	93.43 398	63.84 409	99.59 303	93.24 339	97.19 374	98.40 334

IB-MVS	91.63 19	92.24 366	90.90 370	96.27 341	97.22 383	91.24 370	94.36 382	93.33 391	92.37 364	92.24 399	94.58 391	66.20 405	99.89 74	93.16 340	94.63 398	97.66 373
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
testing91		93.32 351	92.27 354	96.47 336	97.54 369	91.25 369	96.17 320	96.76 355	97.18 237	93.65 393	93.50 397	65.11 407	99.63 289	93.04 341	97.45 364	98.53 321

baseline2		93.73 345	92.83 351	96.42 337	97.70 362	91.28 368	96.84 282	89.77 403	93.96 345	92.44 398	95.93 366	79.14 384	99.77 215	92.94 342	96.76 382	98.21 343

OpenMVS	96.65 7	97.09 261	96.68 272	98.32 225	98.32 327	97.16 213	98.86 82	99.37 134	89.48 387	96.29 352	99.15 126	96.56 190	99.90 64	92.90 343	99.20 273	97.89 360

ADS-MVSNet2		95.43 320	94.98 324	96.76 331	98.14 338	91.74 359	97.92 184	97.76 328	90.23 381	96.51 346	98.91 184	85.61 351	99.85 120	92.88 344	96.90 378	98.69 310

ADS-MVSNet		95.24 323	94.93 327	96.18 346	98.14 338	90.10 381	97.92 184	97.32 340	90.23 381	96.51 346	98.91 184	85.61 351	99.74 233	92.88 344	96.90 378	98.69 310

BP-MVS														92.82 346

HQP-MVS		97.00 269	96.49 283	98.55 201	98.67 286	96.79 228	96.29 311	99.04 237	96.05 288	95.55 366	96.84 348	93.84 278	99.54 322	92.82 346	99.26 265	99.32 203

testdata2													99.79 197	92.80 348

CDPH-MVS		97.26 248	96.66 275	99.07 120	99.00 221	98.15 128	96.03 325	99.01 245	91.21 377	97.79 276	97.85 310	96.89 170	99.69 255	92.75 349	99.38 246	99.39 175

新几何1				98.91 147	98.94 230	97.76 174		98.76 284	87.58 394	96.75 337	98.10 292	94.80 256	99.78 208	92.73 350	99.00 299	99.20 229

ZD-MVS					99.01 220	98.84 75		99.07 230	94.10 341	98.05 260	98.12 290	96.36 201	99.86 108	92.70 351	99.19 276

F-COLMAP		97.30 245	96.68 272	99.14 108	99.19 180	98.39 108	97.27 258	99.30 169	92.93 357	96.62 341	98.00 299	95.73 228	99.68 264	92.62 352	98.46 333	99.35 194

原ACMM1				98.35 223	98.90 240	96.25 244		98.83 276	92.48 363	96.07 357	98.10 292	95.39 239	99.71 246	92.61 353	98.99 300	99.08 247

agg_prior2														92.50 354	99.16 279	99.37 184

FE-MVS		95.66 314	94.95 326	97.77 266	98.53 309	95.28 275	99.40 16	96.09 366	93.11 355	97.96 264	99.26 100	79.10 385	99.77 215	92.40 355	98.71 319	98.27 342

无先验							95.74 340	98.74 289	89.38 388				99.73 238	92.38 356		99.22 228

CMPMVS	75.91 23	96.29 296	95.44 311	98.84 154	96.25 401	98.69 88	97.02 270	99.12 223	88.90 390	97.83 273	98.86 197	89.51 325	98.90 391	91.92 357	99.51 224	98.92 276
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
BH-untuned		96.83 275	96.75 268	97.08 313	98.74 268	93.33 334	96.71 289	98.26 312	96.72 261	98.44 230	97.37 337	95.20 242	99.47 342	91.89 358	97.43 366	98.44 329

UWE-MVS		92.38 363	91.76 366	94.21 374	97.16 384	84.65 401	95.42 352	88.45 405	95.96 293	96.17 353	95.84 370	66.36 403	99.71 246	91.87 359	98.64 326	98.28 341

gm-plane-assit					94.83 406	81.97 409			88.07 393		94.99 385		99.60 299	91.76 360

CNLPA		97.17 257	96.71 270	98.55 201	98.56 305	98.05 145	96.33 308	98.93 252	96.91 251	97.06 317	97.39 335	94.38 267	99.45 346	91.66 361	99.18 278	98.14 347

MIMVSNet		96.62 285	96.25 292	97.71 275	99.04 216	94.66 295	99.16 51	96.92 352	97.23 233	97.87 269	99.10 136	86.11 348	99.65 283	91.65 362	99.21 272	98.82 288

1314		95.74 311	95.60 304	96.17 347	97.53 371	92.75 345	98.07 163	98.31 311	91.22 376	94.25 384	96.68 352	95.53 233	99.03 383	91.64 363	97.18 375	96.74 388

PMVS	91.26 20	97.86 203	97.94 192	97.65 278	99.71 47	97.94 157	98.52 112	98.68 292	98.99 92	97.52 295	99.35 83	97.41 141	98.18 399	91.59 364	99.67 173	96.82 387
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tpm cat1		93.29 352	93.13 349	93.75 379	97.39 379	84.74 400	97.39 246	97.65 332	83.39 401	94.16 385	98.41 265	82.86 371	99.39 355	91.56 365	95.35 395	97.14 383

test_method		79.78 373	79.50 376	80.62 389	80.21 412	45.76 415	70.82 403	98.41 308	31.08 407	80.89 408	97.71 316	84.85 356	97.37 402	91.51 366	80.03 406	98.75 303

DPM-MVS		96.32 295	95.59 305	98.51 207	98.76 265	97.21 208	94.54 379	98.26 312	91.94 368	96.37 350	97.25 340	93.06 291	99.43 349	91.42 367	98.74 315	98.89 280

WAC-MVS						90.90 374								91.37 368

KD-MVS_2432*1600		92.87 358	91.99 360	95.51 361	91.37 409	89.27 383	94.07 385	98.14 319	95.42 309	97.25 311	96.44 358	67.86 399	99.24 374	91.28 369	96.08 390	98.02 353

miper_refine_blended		92.87 358	91.99 360	95.51 361	91.37 409	89.27 383	94.07 385	98.14 319	95.42 309	97.25 311	96.44 358	67.86 399	99.24 374	91.28 369	96.08 390	98.02 353

HY-MVS	95.94 13	95.90 307	95.35 316	97.55 288	97.95 348	94.79 288	98.81 86	96.94 351	92.28 366	95.17 374	98.57 248	89.90 323	99.75 228	91.20 371	97.33 373	98.10 349

MG-MVS		96.77 278	96.61 277	97.26 306	98.31 328	93.06 337	95.93 332	98.12 321	96.45 274	97.92 265	98.73 219	93.77 282	99.39 355	91.19 372	99.04 293	99.33 201

WB-MVSnew		95.73 312	95.57 306	96.23 344	96.70 394	90.70 378	96.07 324	93.86 388	95.60 303	97.04 318	95.45 381	96.00 214	99.55 317	91.04 373	98.31 337	98.43 331

AdaColmap		97.14 259	96.71 270	98.46 213	98.34 326	97.80 172	96.95 274	98.93 252	95.58 304	96.92 323	97.66 319	95.87 224	99.53 324	90.97 374	99.14 282	98.04 352

PLC	94.65 16	96.51 288	95.73 299	98.85 153	98.75 267	97.91 158	96.42 303	99.06 231	90.94 380	95.59 363	97.38 336	94.41 265	99.59 303	90.93 375	98.04 355	99.05 251
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm2		93.09 354	92.58 353	94.62 370	97.56 367	86.53 394	97.66 220	95.79 371	86.15 396	94.07 388	98.23 283	75.95 391	99.53 324	90.91 376	96.86 381	97.81 365

QAPM		97.31 244	96.81 265	98.82 156	98.80 263	97.49 190	99.06 62	99.19 204	90.22 383	97.69 282	99.16 122	96.91 169	99.90 64	90.89 377	99.41 241	99.07 249

PAPM_NR		96.82 277	96.32 287	98.30 228	99.07 208	96.69 233	97.48 241	98.76 284	95.81 298	96.61 342	96.47 357	94.12 275	99.17 379	90.82 378	97.78 357	99.06 250

BH-RMVSNet		96.83 275	96.58 280	97.58 284	98.47 313	94.05 311	96.67 291	97.36 337	96.70 263	97.87 269	97.98 301	95.14 244	99.44 348	90.47 379	98.58 331	99.25 219

API-MVS		97.04 265	96.91 257	97.42 299	97.88 353	98.23 124	98.18 149	98.50 303	97.57 192	97.39 307	96.75 351	96.77 179	99.15 381	90.16 380	99.02 297	94.88 401

E-PMN		94.17 338	94.37 333	93.58 381	96.86 390	85.71 398	90.11 401	97.07 345	98.17 150	97.82 275	97.19 341	84.62 359	98.94 388	89.77 381	97.68 359	96.09 397

MAR-MVS		96.47 292	95.70 300	98.79 163	97.92 350	99.12 57	98.28 139	98.60 298	92.16 367	95.54 369	96.17 362	94.77 259	99.52 328	89.62 382	98.23 339	97.72 371
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
myMVS_eth3d		91.92 369	90.45 371	96.30 339	97.10 386	90.90 374	96.18 318	96.58 358	95.65 301	94.77 378	92.29 403	53.88 412	99.36 358	89.59 383	98.05 353	98.63 316

wuyk23d		96.06 301	97.62 218	91.38 387	98.65 294	98.57 96	98.85 83	96.95 350	96.86 254	99.90 12	99.16 122	99.18 17	98.40 397	89.23 384	99.77 124	77.18 405

OpenMVS_ROB	95.38 14	95.84 309	95.18 321	97.81 263	98.41 323	97.15 214	97.37 248	98.62 297	83.86 399	98.65 203	98.37 270	94.29 270	99.68 264	88.41 385	98.62 329	96.60 390

dmvs_re		95.98 305	95.39 314	97.74 272	98.86 248	97.45 193	98.37 134	95.69 374	97.95 162	96.56 343	95.95 365	90.70 317	97.68 401	88.32 386	96.13 389	98.11 348

BH-w/o		95.13 324	94.89 328	95.86 351	98.20 335	91.31 366	95.65 342	97.37 336	93.64 347	96.52 345	95.70 371	93.04 292	99.02 384	88.10 387	95.82 392	97.24 382

EMVS		93.83 344	94.02 336	93.23 385	96.83 392	84.96 399	89.77 402	96.32 362	97.92 165	97.43 304	96.36 361	86.17 346	98.93 389	87.68 388	97.73 358	95.81 398

gg-mvs-nofinetune		92.37 364	91.20 368	95.85 352	95.80 405	92.38 352	99.31 27	81.84 411	99.75 5	91.83 400	99.74 13	68.29 398	99.02 384	87.15 389	97.12 376	96.16 394

ETVMVS		92.60 360	91.08 369	97.18 308	97.70 362	93.65 331	96.54 295	95.70 372	96.51 268	94.68 380	92.39 402	61.80 410	99.50 333	86.97 390	97.41 367	98.40 334

testing222		91.96 368	90.37 372	96.72 332	97.47 377	92.59 346	96.11 322	94.76 378	96.83 255	92.90 396	92.87 400	57.92 411	99.55 317	86.93 391	97.52 361	98.00 356

TR-MVS		95.55 317	95.12 322	96.86 327	97.54 369	93.94 318	96.49 299	96.53 360	94.36 336	97.03 320	96.61 353	94.26 271	99.16 380	86.91 392	96.31 386	97.47 379

PVSNet_0	89.98 21	91.15 371	90.30 374	93.70 380	97.72 358	84.34 405	90.24 400	97.42 335	90.20 384	93.79 391	93.09 399	90.90 316	98.89 392	86.57 393	72.76 407	97.87 362

tmp_tt		78.77 374	78.73 377	78.90 390	58.45 413	74.76 414	94.20 384	78.26 413	39.16 406	86.71 406	92.82 401	80.50 377	75.19 409	86.16 394	92.29 403	86.74 404

PAPR		95.29 321	94.47 330	97.75 270	97.50 376	95.14 281	94.89 367	98.71 291	91.39 375	95.35 373	95.48 377	94.57 262	99.14 382	84.95 395	97.37 369	98.97 267

thres600view7		94.45 332	93.83 338	96.29 340	99.06 212	91.53 361	97.99 177	94.24 385	98.34 130	97.44 303	95.01 384	79.84 379	99.67 267	84.33 396	98.23 339	97.66 373

MVS		93.19 353	92.09 357	96.50 335	96.91 389	94.03 314	98.07 163	98.06 323	68.01 404	94.56 383	96.48 356	95.96 221	99.30 368	83.84 397	96.89 380	96.17 393

thres100view900		94.19 337	93.67 341	95.75 355	99.06 212	91.35 365	98.03 169	94.24 385	98.33 131	97.40 305	94.98 386	79.84 379	99.62 292	83.05 398	98.08 350	96.29 391

tfpn200view9		94.03 341	93.44 343	95.78 354	98.93 232	91.44 363	97.60 228	94.29 383	97.94 163	97.10 314	94.31 392	79.67 381	99.62 292	83.05 398	98.08 350	96.29 391

thres400		94.14 339	93.44 343	96.24 343	98.93 232	91.44 363	97.60 228	94.29 383	97.94 163	97.10 314	94.31 392	79.67 381	99.62 292	83.05 398	98.08 350	97.66 373

thres200		93.72 346	93.14 348	95.46 363	98.66 291	91.29 367	96.61 294	94.63 380	97.39 213	96.83 332	93.71 395	79.88 378	99.56 314	82.40 401	98.13 347	95.54 400

GG-mvs-BLEND				94.76 369	94.54 407	92.13 357	99.31 27	80.47 412		88.73 405	91.01 405	67.59 401	98.16 400	82.30 402	94.53 399	93.98 402

MVE	83.40 22	92.50 361	91.92 363	94.25 373	98.83 254	91.64 360	92.71 396	83.52 410	95.92 295	86.46 407	95.46 378	95.20 242	95.40 406	80.51 403	98.64 326	95.73 399
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PCF-MVS	92.86 18	94.36 333	93.00 350	98.42 217	98.70 278	97.56 187	93.16 395	99.11 225	79.59 403	97.55 292	97.43 333	92.19 304	99.73 238	79.85 404	99.45 236	97.97 357
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
FPMVS		93.44 350	92.23 355	97.08 313	99.25 165	97.86 162	95.61 343	97.16 343	92.90 358	93.76 392	98.65 235	75.94 392	95.66 405	79.30 405	97.49 362	97.73 370

DeepMVS_CX				93.44 383	98.24 332	94.21 307		94.34 382	64.28 405	91.34 401	94.87 390	89.45 327	92.77 408	77.54 406	93.14 401	93.35 403

dmvs_testset		92.94 357	92.21 356	95.13 366	98.59 300	90.99 373	97.65 222	92.09 396	96.95 248	94.00 389	93.55 396	92.34 303	96.97 404	72.20 407	92.52 402	97.43 380

PAPM		91.88 370	90.34 373	96.51 334	98.06 343	92.56 347	92.44 398	97.17 342	86.35 395	90.38 402	96.01 363	86.61 342	99.21 377	70.65 408	95.43 394	97.75 369

test123		17.04 377	20.11 380	7.82 391	10.25 415	4.91 416	94.80 368	4.47 416	4.93 409	10.00 411	24.28 408	9.69 414	3.64 410	10.14 409	12.43 409	14.92 406

testmvs		17.12 376	20.53 379	6.87 392	12.05 414	4.20 417	93.62 393	6.73 415	4.62 410	10.41 410	24.33 407	8.28 415	3.56 411	9.69 410	15.07 408	12.86 407

test_blank		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet_test		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

DCPMVS		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

cdsmvs_eth3d_5k		24.66 375	32.88 378	0.00 393	0.00 416	0.00 418	0.00 404	99.10 226	0.00 411	0.00 412	97.58 324	99.21 16	0.00 412	0.00 411	0.00 410	0.00 408

pcd_1.5k_mvsjas		8.17 378	10.90 381	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	98.07 88	0.00 412	0.00 411	0.00 410	0.00 408

sosnet-low-res		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

sosnet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uncertanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

Regformer		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

ab-mvs-re		8.12 379	10.83 382	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	97.48 330	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

FOURS1					99.73 38	99.67 2	99.43 11	99.54 78	99.43 40	99.26 112

test_one_0601					99.39 139	99.20 34		99.31 161	98.49 125	98.66 202	99.02 152	97.64 120

eth-test2					0.00 416

eth-test					0.00 416

test_241102_ONE					99.49 115	99.17 39		99.31 161	97.98 159	99.66 42	98.90 187	98.36 65	99.48 339

save fliter					99.11 199	97.97 152	96.53 297	99.02 242	98.24 140

test0726					99.50 108	99.21 28	98.17 152	99.35 143	97.97 160	99.26 112	99.06 140	97.61 123

GSMVS																98.81 292

test_part2					99.36 147	99.10 60				99.05 141

sam_mvs1												84.74 358				98.81 292

sam_mvs												84.29 364

MTGPA								99.20 200

test_post											21.25 409	83.86 366	99.70 250

patchmatchnet-post											98.77 214	84.37 361	99.85 120

MTMP							97.93 182	91.91 397

TEST9					98.71 274	98.08 139	95.96 329	99.03 239	91.40 374	95.85 360	97.53 326	96.52 192	99.76 221

test_8					98.67 286	98.01 147	95.91 334	99.02 242	91.64 369	95.79 362	97.50 329	96.47 194	99.76 221

agg_prior					98.68 285	97.99 148		99.01 245		95.59 363			99.77 215

test_prior4						97.97 152	95.86 335

test_prior				98.95 141	98.69 283	97.95 156		99.03 239					99.59 303			99.30 210

新几何2							95.93 332

旧先验1					98.82 257	97.45 193		98.76 284			98.34 274	95.50 236			99.01 298	99.23 224

原ACMM2							95.53 346

test222					98.92 236	96.93 225	95.54 345	98.78 282	85.72 397	96.86 331	98.11 291	94.43 264			99.10 289	99.23 224

segment_acmp												97.02 164

testdata1							95.44 351		96.32 279

test12				98.93 144	98.58 302	97.83 165		98.66 293		96.53 344		95.51 235	99.69 255		99.13 284	99.27 215

plane_prior7					99.19 180	97.87 161

plane_prior6					98.99 224	97.70 180						94.90 249

plane_prior4											97.98 301

plane_prior3						97.78 173			97.41 211	97.79 276

plane_prior2							97.77 205		98.20 147

plane_prior1					99.05 215

plane_prior						97.65 182	97.07 269		96.72 261						99.36 247

n2								0.00 417

nn								0.00 417

door-mid								99.57 62

test11								98.87 263

door								99.41 124

HQP5-MVS						96.79 228

HQP-NCC					98.67 286		96.29 311		96.05 288	95.55 366

ACMP_Plane					98.67 286		96.29 311		96.05 288	95.55 366

HQP4-MVS										95.56 365			99.54 322			99.32 203

HQP3-MVS								99.04 237							99.26 265

HQP2-MVS												93.84 278

NP-MVS					98.84 252	97.39 197					96.84 348

ACMMP++_ref															99.77 124

ACMMP++															99.68 167

Test By Simon												96.52 192

High-resolution multi-view benchmark