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.

LCM-MVSNet		99.86 1	99.86 1	99.87 1	99.99 1	99.77 1	99.77 1	99.80 2	99.97 1	99.97 1	99.95 1	99.74 1	99.98 1	99.56 1	100.00 1	99.85 3

test_fmvsmvis_n_1920		98.08 45	98.47 28	96.93 177	99.03 105	93.29 187	96.32 167	99.65 10	95.59 160	99.71 6	99.01 55	97.66 33	99.60 161	99.44 2	99.83 40	97.90 307

test_fmvsmconf0.01_n		98.57 18	98.74 17	98.06 87	99.39 44	94.63 135	96.70 149	99.82 1	95.44 169	99.64 12	99.52 7	98.96 4	99.74 77	99.38 3	99.86 28	99.81 7

mamv4		99.05 5	98.91 8	99.46 2	98.94 113	99.62 2	97.98 63	99.70 5	99.49 3	99.78 2	99.22 33	95.92 121	99.95 3	99.31 4	99.83 40	98.83 207

v7n		98.73 12	98.99 5	97.95 97	99.64 13	94.20 155	98.67 14	99.14 48	99.08 13	99.42 22	99.23 32	96.53 95	99.91 14	99.27 5	99.93 11	99.73 20

test_fmvs3		97.38 117	97.56 102	96.84 185	98.63 154	92.81 198	97.60 92	99.61 14	90.87 297	98.76 69	99.66 3	94.03 183	97.90 379	99.24 6	99.68 80	99.81 7

test_fmvsmconf0.1_n		98.41 28	98.54 26	98.03 92	99.16 80	94.61 136	96.18 177	99.73 3	95.05 185	99.60 16	99.34 24	98.68 8	99.72 88	99.21 7	99.85 35	99.76 16

test_fmvsm_n_1920		98.08 45	98.29 40	97.43 139	98.88 121	93.95 163	96.17 181	99.57 15	95.66 155	99.52 17	98.71 85	97.04 62	99.64 143	99.21 7	99.87 26	98.69 226

MM		96.87 147	96.62 159	97.62 118	97.72 268	93.30 186	96.39 159	92.61 364	97.90 54	96.76 228	98.64 93	90.46 260	99.81 37	99.16 9	99.94 8	99.76 16

test_fmvsmconf_n		98.30 33	98.41 34	97.99 95	98.94 113	94.60 137	96.00 192	99.64 13	94.99 188	99.43 21	99.18 39	98.51 10	99.71 102	99.13 10	99.84 37	99.67 26

fmvsm_l_conf0.5_n		97.68 94	97.81 73	97.27 151	98.92 117	92.71 203	95.89 202	99.41 25	93.36 238	99.00 47	98.44 113	96.46 102	99.65 139	99.09 11	99.76 56	99.45 82

fmvsm_l_conf0.5_n_a		97.60 100	97.76 79	97.11 162	98.92 117	92.28 211	95.83 205	99.32 26	93.22 244	98.91 54	98.49 106	96.31 109	99.64 143	99.07 12	99.76 56	99.40 97

fmvsm_s_conf0.1_n_a		97.80 83	98.01 53	97.18 157	99.17 79	92.51 206	96.57 153	99.15 45	93.68 230	98.89 55	99.30 27	96.42 104	99.37 235	99.03 13	99.83 40	99.66 28

fmvsm_s_conf0.1_n		97.73 88	98.02 52	96.85 183	99.09 95	91.43 237	96.37 163	99.11 51	94.19 213	99.01 45	99.25 30	96.30 110	99.38 230	99.00 14	99.88 24	99.73 20

fmvsm_s_conf0.5_n_a		97.65 95	97.83 71	97.13 161	98.80 130	92.51 206	96.25 173	99.06 64	93.67 231	98.64 73	99.00 56	96.23 114	99.36 238	98.99 15	99.80 48	99.53 53

fmvsm_s_conf0.5_n		97.62 98	97.89 64	96.80 187	98.79 132	91.44 236	96.14 182	99.06 64	94.19 213	98.82 61	98.98 59	96.22 115	99.38 230	98.98 16	99.86 28	99.58 36

mvs_tets		98.90 6	98.94 6	98.75 32	99.69 10	96.48 61	98.54 22	99.22 33	96.23 122	99.71 6	99.48 10	98.77 7	99.93 4	98.89 17	99.95 5	99.84 5

test_fmvs2		96.38 177	96.45 174	96.16 224	97.85 238	91.30 238	96.81 138	99.45 19	89.24 318	98.49 87	99.38 18	88.68 284	97.62 384	98.83 18	99.32 192	99.57 43

PS-MVSNAJss		98.53 23	98.63 21	98.21 77	99.68 11	94.82 128	98.10 55	99.21 34	96.91 94	99.75 3	99.45 13	95.82 127	99.92 6	98.80 19	99.96 4	99.89 1

jajsoiax		98.77 10	98.79 13	98.74 35	99.66 12	96.48 61	98.45 30	99.12 50	95.83 149	99.67 9	99.37 19	98.25 13	99.92 6	98.77 20	99.94 8	99.82 6

v10		97.55 104	97.97 57	96.31 217	98.60 158	89.64 265	97.44 105	99.02 78	96.60 103	98.72 72	99.16 43	93.48 196	99.72 88	98.76 21	99.92 14	99.58 36

MVSFormer		96.14 186	96.36 178	95.49 259	97.68 272	87.81 307	98.67 14	99.02 78	96.50 110	94.48 313	96.15 303	86.90 303	99.92 6	98.73 22	99.13 218	98.74 219

test_djsdf		98.73 12	98.74 17	98.69 40	99.63 14	96.30 68	98.67 14	99.02 78	96.50 110	99.32 28	99.44 14	97.43 41	99.92 6	98.73 22	99.95 5	99.86 2

OurMVSNet-221017-0		98.61 17	98.61 25	98.63 45	99.77 5	96.35 65	99.17 6	99.05 68	98.05 50	99.61 15	99.52 7	93.72 192	99.88 22	98.72 24	99.88 24	99.65 31

tt0805		97.44 112	97.56 102	97.11 162	99.55 22	96.36 64	98.66 17	95.66 321	98.31 39	97.09 205	95.45 328	97.17 54	98.50 355	98.67 25	97.45 335	96.48 368

v8		97.60 100	98.06 49	96.23 219	98.71 143	89.44 270	97.43 107	98.82 140	97.29 86	98.74 70	99.10 50	93.86 187	99.68 123	98.61 26	99.94 8	99.56 47

anonymousdsp		98.72 15	98.63 21	98.99 11	99.62 15	97.29 38	98.65 18	99.19 38	95.62 158	99.35 27	99.37 19	97.38 43	99.90 17	98.59 27	99.91 17	99.77 11

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 38	99.71 9	96.99 45	99.69 2	99.57 15	99.02 18	99.62 14	99.36 21	98.53 9	99.52 183	98.58 28	99.95 5	99.66 28
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
v1240		96.74 156	97.02 138	95.91 236	98.18 207	88.52 287	95.39 232	98.88 112	93.15 252	98.46 92	98.40 119	92.80 212	99.71 102	98.45 29	99.49 142	99.49 67

MVSMamba_PlusPlus		97.43 114	97.98 56	95.78 242	98.88 121	89.70 262	98.03 60	98.85 121	99.18 10	96.84 221	99.12 47	93.04 204	99.91 14	98.38 30	99.55 116	97.73 320

iter_conf05		97.83 77	98.49 27	95.84 239	98.88 121	89.05 278	98.87 9	99.42 22	99.18 10	99.73 4	99.12 47	93.04 204	99.91 14	98.38 30	99.78 53	98.58 237

v1192		96.83 151	97.06 135	96.15 225	98.28 193	89.29 272	95.36 234	98.77 147	93.73 226	98.11 132	98.34 124	93.02 209	99.67 131	98.35 32	99.58 104	99.50 59

v1921920		96.72 159	96.96 142	95.99 229	98.21 201	88.79 284	95.42 228	98.79 142	93.22 244	98.19 125	98.26 141	92.68 215	99.70 110	98.34 33	99.55 116	99.49 67

MVS_0304		95.71 203	95.18 219	97.33 147	94.85 379	92.82 196	95.36 234	90.89 380	95.51 164	95.61 285	97.82 193	88.39 288	99.78 47	98.23 34	99.91 17	99.40 97

Anonymous20231211		98.55 21	98.76 14	97.94 98	98.79 132	94.37 147	98.84 11	99.15 45	99.37 4	99.67 9	99.43 15	95.61 138	99.72 88	98.12 35	99.86 28	99.73 20

v144192		96.69 162	96.90 147	96.03 228	98.25 197	88.92 279	95.49 224	98.77 147	93.05 254	98.09 135	98.29 135	92.51 226	99.70 110	98.11 36	99.56 110	99.47 76

test_fmvs1_n		95.21 227	95.28 215	94.99 280	98.15 214	89.13 277	96.81 138	99.43 21	86.97 347	97.21 191	98.92 66	83.00 332	97.13 388	98.09 37	98.94 240	98.72 222

Anonymous20240521		97.07 132	97.51 107	95.76 243	99.35 49	88.18 295	97.78 78	98.40 202	97.11 89	98.34 106	99.04 54	89.58 273	99.79 44	98.09 37	99.93 11	99.30 118

v1144		96.84 148	97.08 133	96.13 226	98.42 183	89.28 273	95.41 230	98.67 169	94.21 211	97.97 150	98.31 127	93.06 203	99.65 139	98.06 39	99.62 90	99.45 82

SixPastTwentyTwo		97.49 108	97.57 101	97.26 153	99.56 20	92.33 210	98.28 41	96.97 296	98.30 41	99.45 20	99.35 23	88.43 287	99.89 20	98.01 40	99.76 56	99.54 50

test_vis1_n_1920		95.77 201	96.41 176	93.85 321	98.55 165	84.86 351	95.91 201	99.71 4	92.72 266	97.67 169	98.90 70	87.44 300	98.73 330	97.96 41	98.85 251	97.96 303

WR-MVS_H		98.65 16	98.62 23	98.75 32	99.51 28	96.61 57	98.55 21	99.17 40	99.05 16	99.17 37	98.79 76	95.47 142	99.89 20	97.95 42	99.91 17	99.75 18

UA-Net		98.88 8	98.76 14	99.22 3	99.11 92	97.89 14	99.47 3	99.32 26	99.08 13	97.87 161	99.67 2	96.47 100	99.92 6	97.88 43	99.98 2	99.85 3

test_fmvs1		94.51 263	94.60 250	94.26 315	95.91 351	87.92 302	95.35 237	99.02 78	86.56 351	96.79 223	98.52 103	82.64 334	97.00 391	97.87 44	98.71 266	97.88 309

FC-MVSNet-test		98.16 38	98.37 35	97.56 121	99.49 32	93.10 192	98.35 34	99.21 34	98.43 35	98.89 55	98.83 75	94.30 177	99.81 37	97.87 44	99.91 17	99.77 11

Vis-MVSNet		98.27 34	98.34 36	98.07 85	99.33 51	95.21 119	98.04 58	99.46 18	97.32 84	97.82 165	99.11 49	96.75 85	99.86 26	97.84 46	99.36 177	99.15 148
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
K. test v3		96.44 174	96.28 181	96.95 175	99.41 40	91.53 233	97.65 89	90.31 387	98.89 23	98.93 51	99.36 21	84.57 321	99.92 6	97.81 47	99.56 110	99.39 102

v2v482		96.78 155	97.06 135	95.95 233	98.57 162	88.77 285	95.36 234	98.26 217	95.18 179	97.85 163	98.23 145	92.58 219	99.63 147	97.80 48	99.69 76	99.45 82

PS-CasMVS		98.73 12	98.85 11	98.39 60	99.55 22	95.47 101	98.49 27	99.13 49	99.22 9	99.22 35	98.96 62	97.35 44	99.92 6	97.79 49	99.93 11	99.79 9

nrg030		98.54 22	98.62 23	98.32 64	99.22 66	95.66 91	97.90 71	99.08 60	98.31 39	99.02 44	98.74 82	97.68 30	99.61 159	97.77 50	99.85 35	99.70 24

pmmvs6		99.07 4	99.24 4	98.56 49	99.81 2	96.38 63	98.87 9	99.30 28	99.01 19	99.63 13	99.66 3	99.27 2	99.68 123	97.75 51	99.89 23	99.62 33

ACMH	93.61 9	98.44 26	98.76 14	97.51 126	99.43 37	93.54 179	98.23 45	99.05 68	97.40 80	99.37 25	99.08 52	98.79 6	99.47 198	97.74 52	99.71 72	99.50 59
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_f		95.82 200	95.88 201	95.66 249	97.61 284	93.21 191	95.61 220	98.17 231	86.98 346	98.42 95	99.47 11	90.46 260	94.74 401	97.71 53	98.45 287	99.03 173

DTE-MVSNet		98.79 9	98.86 9	98.59 47	99.55 22	96.12 73	98.48 29	99.10 53	99.36 5	99.29 30	99.06 53	97.27 48	99.93 4	97.71 53	99.91 17	99.70 24

test_vis1_n		95.67 206	95.89 200	95.03 277	98.18 207	89.89 260	96.94 131	99.28 30	88.25 334	98.20 121	98.92 66	86.69 306	97.19 387	97.70 55	98.82 255	98.00 301

EC-MVSNet		97.90 70	97.94 60	97.79 106	98.66 149	95.14 120	98.31 38	99.66 9	97.57 68	95.95 270	97.01 256	96.99 66	99.82 35	97.66 56	99.64 87	98.39 255

PEN-MVS		98.75 11	98.85 11	98.44 56	99.58 18	95.67 90	98.45 30	99.15 45	99.33 6	99.30 29	99.00 56	97.27 48	99.92 6	97.64 57	99.92 14	99.75 18

CP-MVSNet		98.42 27	98.46 29	98.30 67	99.46 34	95.22 117	98.27 43	98.84 126	99.05 16	99.01 45	98.65 92	95.37 145	99.90 17	97.57 58	99.91 17	99.77 11

EI-MVSNet-UG-set		97.32 123	97.40 112	97.09 166	97.34 306	92.01 225	95.33 239	97.65 271	97.74 59	98.30 114	98.14 154	95.04 154	99.69 118	97.55 59	99.52 130	99.58 36

ANet_high		98.31 32	98.94 6	96.41 212	99.33 51	89.64 265	97.92 69	99.56 17	99.27 7	99.66 11	99.50 9	97.67 31	99.83 34	97.55 59	99.98 2	99.77 11

CS-MVS		98.09 44	98.01 53	98.32 64	98.45 180	96.69 53	98.52 25	99.69 6	98.07 49	96.07 266	97.19 244	96.88 77	99.86 26	97.50 61	99.73 65	98.41 252

EI-MVSNet-Vis-set		97.32 123	97.39 113	97.11 162	97.36 303	92.08 223	95.34 238	97.65 271	97.74 59	98.29 115	98.11 160	95.05 153	99.68 123	97.50 61	99.50 139	99.56 47

EU-MVSNet		94.25 269	94.47 258	93.60 327	98.14 216	82.60 371	97.24 115	92.72 361	85.08 365	98.48 89	98.94 64	82.59 335	98.76 328	97.47 63	99.53 125	99.44 92

V42		97.04 133	97.16 129	96.68 196	98.59 160	91.05 242	96.33 166	98.36 207	94.60 200	97.99 146	98.30 131	93.32 198	99.62 152	97.40 64	99.53 125	99.38 104

KD-MVS_self_test		97.86 75	98.07 47	97.25 154	99.22 66	92.81 198	97.55 97	98.94 100	97.10 90	98.85 58	98.88 72	95.03 155	99.67 131	97.39 65	99.65 85	99.26 130

lessismore_v0				97.05 169	99.36 48	92.12 219		84.07 404		98.77 68	98.98 59	85.36 315	99.74 77	97.34 66	99.37 174	99.30 118

FIs		97.93 64	98.07 47	97.48 134	99.38 46	92.95 195	98.03 60	99.11 51	98.04 51	98.62 75	98.66 89	93.75 191	99.78 47	97.23 67	99.84 37	99.73 20

UniMVSNet_ETH3D		99.12 3	99.28 3	98.65 43	99.77 5	96.34 66	99.18 5	99.20 36	99.67 2	99.73 4	99.65 5	99.15 3	99.86 26	97.22 68	99.92 14	99.77 11

MVS_Test		96.27 181	96.79 153	94.73 295	96.94 324	86.63 328	96.18 177	98.33 211	94.94 189	96.07 266	98.28 136	95.25 149	99.26 265	97.21 69	97.90 310	98.30 268

TDRefinement		98.90 6	98.86 9	99.02 7	99.54 25	98.06 9	99.34 4	99.44 20	98.85 24	99.00 47	99.20 35	97.42 42	99.59 162	97.21 69	99.76 56	99.40 97

EG-PatchMatch MVS		97.69 92	97.79 75	97.40 143	99.06 99	93.52 180	95.96 197	98.97 96	94.55 204	98.82 61	98.76 81	97.31 46	99.29 259	97.20 71	99.44 155	99.38 104

VPA-MVSNet		98.27 34	98.46 29	97.70 112	99.06 99	93.80 168	97.76 81	99.00 87	98.40 36	99.07 43	98.98 59	96.89 75	99.75 68	97.19 72	99.79 50	99.55 49

test_vis3_rt		97.04 133	96.98 139	97.23 156	98.44 181	95.88 81	96.82 137	99.67 7	90.30 306	99.27 31	99.33 26	94.04 182	96.03 398	97.14 73	97.83 313	99.78 10

UniMVSNet (Re)		97.83 77	97.65 89	98.35 63	98.80 130	95.86 83	95.92 200	99.04 75	97.51 72	98.22 120	97.81 195	94.68 165	99.78 47	97.14 73	99.75 63	99.41 96

pm-mvs1		98.47 25	98.67 19	97.86 102	99.52 27	94.58 138	98.28 41	99.00 87	97.57 68	99.27 31	99.22 33	98.32 12	99.50 188	97.09 75	99.75 63	99.50 59

baseline		97.44 112	97.78 78	96.43 209	98.52 169	90.75 250	96.84 135	99.03 76	96.51 109	97.86 162	98.02 173	96.67 87	99.36 238	97.09 75	99.47 148	99.19 142

IterMVS-SCA-FT		95.86 198	96.19 184	94.85 288	97.68 272	85.53 339	92.42 347	97.63 275	96.99 91	98.36 103	98.54 102	87.94 292	99.75 68	97.07 77	99.08 226	99.27 129

balanced_conf03		96.88 146	97.29 119	95.63 250	97.66 277	89.47 269	97.95 66	98.89 105	95.94 140	97.77 168	98.55 100	92.23 230	99.68 123	97.05 78	99.61 96	97.73 320

UniMVSNet_NR-MVSNet		97.83 77	97.65 89	98.37 61	98.72 140	95.78 84	95.66 214	99.02 78	98.11 47	98.31 112	97.69 206	94.65 167	99.85 29	97.02 79	99.71 72	99.48 73

DU-MVS		97.79 84	97.60 98	98.36 62	98.73 138	95.78 84	95.65 216	98.87 114	97.57 68	98.31 112	97.83 190	94.69 163	99.85 29	97.02 79	99.71 72	99.46 78

casdiffmvs_mvg		97.83 77	98.11 44	97.00 174	98.57 162	92.10 222	95.97 195	99.18 39	97.67 67	99.00 47	98.48 110	97.64 34	99.50 188	96.96 81	99.54 121	99.40 97
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EI-MVSNet		96.63 165	96.93 143	95.74 244	97.26 311	88.13 298	95.29 243	97.65 271	96.99 91	97.94 153	98.19 150	92.55 221	99.58 164	96.91 82	99.56 110	99.50 59

IterMVS-LS		96.92 142	97.29 119	95.79 241	98.51 171	88.13 298	95.10 250	98.66 171	96.99 91	98.46 92	98.68 88	92.55 221	99.74 77	96.91 82	99.79 50	99.50 59
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CS-MVS-test		97.91 68	97.84 68	98.14 81	98.52 169	96.03 78	98.38 33	99.67 7	98.11 47	95.50 289	96.92 262	96.81 83	99.87 24	96.87 84	99.76 56	98.51 245

test_cas_vis1_n_1920		95.34 221	95.67 207	94.35 311	98.21 201	86.83 326	95.61 220	99.26 31	90.45 304	98.17 126	98.96 62	84.43 322	98.31 369	96.74 85	99.17 213	97.90 307

test1111		94.53 262	94.81 239	93.72 324	99.06 99	81.94 376	98.31 38	83.87 405	96.37 115	98.49 87	99.17 42	81.49 337	99.73 83	96.64 86	99.86 28	99.49 67

APDe-MVS		98.14 39	98.03 51	98.47 55	98.72 140	96.04 76	98.07 57	99.10 53	95.96 138	98.59 79	98.69 87	96.94 69	99.81 37	96.64 86	99.58 104	99.57 43
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MP-MVS-pluss		97.69 92	97.36 115	98.70 39	99.50 31	96.84 48	95.38 233	98.99 90	92.45 272	98.11 132	98.31 127	97.25 51	99.77 57	96.60 88	99.62 90	99.48 73
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
mvs_anonymous		95.36 220	96.07 190	93.21 337	96.29 337	81.56 378	94.60 274	97.66 269	93.30 241	96.95 215	98.91 69	93.03 208	99.38 230	96.60 88	97.30 340	98.69 226

casdiffmvs		97.50 107	97.81 73	96.56 203	98.51 171	91.04 243	95.83 205	99.09 58	97.23 87	98.33 109	98.30 131	97.03 63	99.37 235	96.58 90	99.38 173	99.28 125
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TransMVSNet (Re)		98.38 29	98.67 19	97.51 126	99.51 28	93.39 185	98.20 50	98.87 114	98.23 43	99.48 18	99.27 29	98.47 11	99.55 175	96.52 91	99.53 125	99.60 34

HPM-MVS_fast		98.32 31	98.13 42	98.88 24	99.54 25	97.48 31	98.35 34	99.03 76	95.88 145	97.88 158	98.22 148	98.15 16	99.74 77	96.50 92	99.62 90	99.42 94

MIMVSNet1		98.51 24	98.45 31	98.67 41	99.72 8	96.71 51	98.76 12	98.89 105	98.49 34	99.38 24	99.14 46	95.44 144	99.84 32	96.47 93	99.80 48	99.47 76

TranMVSNet+NR-MVSNet		98.33 30	98.30 39	98.43 57	99.07 98	95.87 82	96.73 147	99.05 68	98.67 27	98.84 59	98.45 111	97.58 38	99.88 22	96.45 94	99.86 28	99.54 50

MGCFI-Net		97.20 128	97.23 124	97.08 167	97.68 272	93.71 172	97.79 77	99.09 58	97.40 80	96.59 238	93.96 352	97.67 31	99.35 242	96.43 95	98.50 284	98.17 283

test2506		89.86 345	89.16 350	91.97 365	98.95 110	76.83 400	98.54 22	61.07 414	96.20 123	97.07 206	99.16 43	55.19 408	99.69 118	96.43 95	99.83 40	99.38 104

Gipuma		98.07 47	98.31 37	97.36 145	99.76 7	96.28 69	98.51 26	99.10 53	98.76 26	96.79 223	99.34 24	96.61 91	98.82 321	96.38 97	99.50 139	96.98 348
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVSTER		94.21 272	93.93 277	95.05 276	95.83 357	86.46 329	95.18 248	97.65 271	92.41 273	97.94 153	98.00 177	72.39 382	99.58 164	96.36 98	99.56 110	99.12 158

GeoE		97.75 87	97.70 82	97.89 100	98.88 121	94.53 139	97.10 123	98.98 93	95.75 153	97.62 170	97.59 212	97.61 37	99.77 57	96.34 99	99.44 155	99.36 110

sasdasda		97.23 126	97.21 126	97.30 149	97.65 279	94.39 144	97.84 74	99.05 68	97.42 75	96.68 231	93.85 354	97.63 35	99.33 247	96.29 100	98.47 285	98.18 281

canonicalmvs		97.23 126	97.21 126	97.30 149	97.65 279	94.39 144	97.84 74	99.05 68	97.42 75	96.68 231	93.85 354	97.63 35	99.33 247	96.29 100	98.47 285	98.18 281

testf1		98.57 18	98.45 31	98.93 19	99.79 3	98.78 3	97.69 86	99.42 22	97.69 64	98.92 52	98.77 79	97.80 25	99.25 267	96.27 102	99.69 76	98.76 217

APD_test2		98.57 18	98.45 31	98.93 19	99.79 3	98.78 3	97.69 86	99.42 22	97.69 64	98.92 52	98.77 79	97.80 25	99.25 267	96.27 102	99.69 76	98.76 217

alignmvs		96.01 192	95.52 213	97.50 130	97.77 260	94.71 130	96.07 186	96.84 299	97.48 73	96.78 227	94.28 350	85.50 314	99.40 223	96.22 104	98.73 265	98.40 253

tttt0517		93.31 298	92.56 305	95.57 253	98.71 143	87.86 304	97.44 105	87.17 399	95.79 150	97.47 181	96.84 266	64.12 396	99.81 37	96.20 105	99.32 192	99.02 176

DeepC-MVS	95.41 4	97.82 81	97.70 82	98.16 78	98.78 135	95.72 86	96.23 175	99.02 78	93.92 223	98.62 75	98.99 58	97.69 29	99.62 152	96.18 106	99.87 26	99.15 148
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MTAPA		98.14 39	97.84 68	99.06 4	99.44 36	97.90 13	97.25 113	98.73 154	97.69 64	97.90 156	97.96 179	95.81 131	99.82 35	96.13 107	99.61 96	99.45 82

ZNCC-MVS		97.92 65	97.62 96	98.83 26	99.32 53	97.24 40	97.45 104	98.84 126	95.76 151	96.93 216	97.43 223	97.26 50	99.79 44	96.06 108	99.53 125	99.45 82

Patchmatch-RL test		94.66 255	94.49 256	95.19 269	98.54 167	88.91 280	92.57 340	98.74 153	91.46 289	98.32 110	97.75 200	77.31 360	98.81 323	96.06 108	99.61 96	97.85 311

ACMMP_NAP		97.89 71	97.63 94	98.67 41	99.35 49	96.84 48	96.36 164	98.79 142	95.07 184	97.88 158	98.35 123	97.24 52	99.72 88	96.05 110	99.58 104	99.45 82

v148		96.58 168	96.97 140	95.42 262	98.63 154	87.57 311	95.09 251	97.90 253	95.91 144	98.24 118	97.96 179	93.42 197	99.39 227	96.04 111	99.52 130	99.29 124

ACMM	93.33 11	98.05 48	97.79 75	98.85 25	99.15 83	97.55 27	96.68 150	98.83 132	95.21 176	98.36 103	98.13 156	98.13 18	99.62 152	96.04 111	99.54 121	99.39 102
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
VDD-MVS		97.37 119	97.25 122	97.74 109	98.69 147	94.50 142	97.04 127	95.61 325	98.59 30	98.51 84	98.72 83	92.54 223	99.58 164	96.02 113	99.49 142	99.12 158

IterMVS		95.42 219	95.83 202	94.20 316	97.52 290	83.78 363	92.41 348	97.47 280	95.49 166	98.06 140	98.49 106	87.94 292	99.58 164	96.02 113	99.02 233	99.23 136
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs		96.04 190	96.23 182	95.46 261	97.35 304	88.03 301	93.42 319	99.08 60	94.09 219	96.66 234	96.93 260	93.85 188	99.29 259	96.01 115	98.67 269	99.06 170
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PM-MVS		97.36 121	97.10 131	98.14 81	98.91 119	96.77 50	96.20 176	98.63 177	93.82 224	98.54 82	98.33 125	93.98 184	99.05 300	95.99 116	99.45 154	98.61 235

Baseline_NR-MVSNet		97.72 90	97.79 75	97.50 130	99.56 20	93.29 187	95.44 226	98.86 117	98.20 45	98.37 100	99.24 31	94.69 163	99.55 175	95.98 117	99.79 50	99.65 31

ECVR-MVS		94.37 268	94.48 257	94.05 320	98.95 110	83.10 366	98.31 38	82.48 407	96.20 123	98.23 119	99.16 43	81.18 340	99.66 137	95.95 118	99.83 40	99.38 104

3Dnovator	96.53 2	97.61 99	97.64 92	97.50 130	97.74 266	93.65 177	98.49 27	98.88 112	96.86 96	97.11 199	98.55 100	95.82 127	99.73 83	95.94 119	99.42 166	99.13 153

PatchT		93.75 285	93.57 282	94.29 314	95.05 377	87.32 317	96.05 187	92.98 357	97.54 71	94.25 316	98.72 83	75.79 368	99.24 271	95.92 120	95.81 369	96.32 370

NR-MVSNet		97.96 54	97.86 67	98.26 69	98.73 138	95.54 94	98.14 53	98.73 154	97.79 55	99.42 22	97.83 190	94.40 175	99.78 47	95.91 121	99.76 56	99.46 78

h-mvs33		96.29 180	95.63 210	98.26 69	98.50 174	96.11 74	96.90 133	97.09 291	96.58 105	97.21 191	98.19 150	84.14 323	99.78 47	95.89 122	96.17 366	98.89 198

hse-mvs2		95.77 201	95.09 223	97.79 106	97.84 243	95.51 96	95.66 214	95.43 330	96.58 105	97.21 191	96.16 302	84.14 323	99.54 178	95.89 122	96.92 343	98.32 264

MSC_two_6792asdad				98.22 74	97.75 263	95.34 109		98.16 235					99.75 68	95.87 124	99.51 135	99.57 43

No_MVS				98.22 74	97.75 263	95.34 109		98.16 235					99.75 68	95.87 124	99.51 135	99.57 43

new-patchmatchnet		95.67 206	96.58 163	92.94 346	97.48 293	80.21 386	92.96 329	98.19 230	94.83 192	98.82 61	98.79 76	93.31 199	99.51 187	95.83 126	99.04 232	99.12 158

FMVSNet1		97.95 58	98.08 46	97.56 121	99.14 90	93.67 173	98.23 45	98.66 171	97.41 79	99.00 47	99.19 36	95.47 142	99.73 83	95.83 126	99.76 56	99.30 118

patch_mono-2		96.59 166	96.93 143	95.55 256	98.88 121	87.12 320	94.47 277	99.30 28	94.12 216	96.65 236	98.41 116	94.98 158	99.87 24	95.81 128	99.78 53	99.66 28

DVP-MVS++		97.96 54	97.90 61	98.12 83	97.75 263	95.40 102	99.03 7	98.89 105	96.62 101	98.62 75	98.30 131	96.97 67	99.75 68	95.70 129	99.25 203	99.21 138

test_0728_THIRD									96.62 101	98.40 97	98.28 136	97.10 56	99.71 102	95.70 129	99.62 90	99.58 36

EGC-MVSNET		83.08 373	77.93 376	98.53 51	99.57 19	97.55 27	98.33 37	98.57 184	4.71 411	10.38 412	98.90 70	95.60 139	99.50 188	95.69 131	99.61 96	98.55 241

RPMNet		94.68 254	94.60 250	94.90 285	95.44 369	88.15 296	96.18 177	98.86 117	97.43 74	94.10 320	98.49 106	79.40 347	99.76 62	95.69 131	95.81 369	96.81 359

TSAR-MVS + MP.		97.42 115	97.23 124	98.00 94	99.38 46	95.00 124	97.63 91	98.20 225	93.00 256	98.16 127	98.06 169	95.89 122	99.72 88	95.67 133	99.10 224	99.28 125
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
XVS		97.96 54	97.63 94	98.94 16	99.15 83	97.66 20	97.77 79	98.83 132	97.42 75	96.32 252	97.64 208	96.49 98	99.72 88	95.66 134	99.37 174	99.45 82

X-MVStestdata		92.86 305	90.83 332	98.94 16	99.15 83	97.66 20	97.77 79	98.83 132	97.42 75	96.32 252	36.50 409	96.49 98	99.72 88	95.66 134	99.37 174	99.45 82

3Dnovator+	96.13 3	97.73 88	97.59 99	98.15 80	98.11 220	95.60 92	98.04 58	98.70 163	98.13 46	96.93 216	98.45 111	95.30 148	99.62 152	95.64 136	98.96 237	99.24 135

DELS-MVS		96.17 185	96.23 182	95.99 229	97.55 289	90.04 257	92.38 350	98.52 187	94.13 215	96.55 243	97.06 251	94.99 157	99.58 164	95.62 137	99.28 199	98.37 257
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
HFP-MVS		97.94 61	97.64 92	98.83 26	99.15 83	97.50 30	97.59 94	98.84 126	96.05 131	97.49 177	97.54 215	97.07 59	99.70 110	95.61 138	99.46 151	99.30 118

ACMMPR		97.95 58	97.62 96	98.94 16	99.20 75	97.56 26	97.59 94	98.83 132	96.05 131	97.46 182	97.63 209	96.77 84	99.76 62	95.61 138	99.46 151	99.49 67

UGNet		96.81 153	96.56 165	97.58 120	96.64 329	93.84 167	97.75 82	97.12 290	96.47 113	93.62 336	98.88 72	93.22 201	99.53 180	95.61 138	99.69 76	99.36 110
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
HPM-MVS		98.11 43	97.83 71	98.92 22	99.42 39	97.46 32	98.57 19	99.05 68	95.43 170	97.41 184	97.50 219	97.98 19	99.79 44	95.58 141	99.57 107	99.50 59
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
dcpmvs_2		97.12 130	97.99 55	94.51 305	99.11 92	84.00 361	97.75 82	99.65 10	97.38 82	99.14 38	98.42 115	95.16 151	99.96 2	95.52 142	99.78 53	99.58 36

SR-MVS-dyc-post		98.14 39	97.84 68	99.02 7	98.81 128	98.05 10	97.55 97	98.86 117	97.77 56	98.20 121	98.07 164	96.60 93	99.76 62	95.49 143	99.20 208	99.26 130

RE-MVS-def			97.88 66		98.81 128	98.05 10	97.55 97	98.86 117	97.77 56	98.20 121	98.07 164	96.94 69		95.49 143	99.20 208	99.26 130

Anonymous20240529		97.96 54	98.04 50	97.71 111	98.69 147	94.28 153	97.86 73	98.31 215	98.79 25	99.23 34	98.86 74	95.76 133	99.61 159	95.49 143	99.36 177	99.23 136

DVP-MVS		97.78 85	97.65 89	98.16 78	99.24 61	95.51 96	96.74 143	98.23 221	95.92 142	98.40 97	98.28 136	97.06 60	99.71 102	95.48 146	99.52 130	99.26 130
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				98.25 72	99.23 63	95.49 100	96.74 143	98.89 105					99.75 68	95.48 146	99.52 130	99.53 53

region2R		97.92 65	97.59 99	98.92 22	99.22 66	97.55 27	97.60 92	98.84 126	96.00 136	97.22 189	97.62 210	96.87 79	99.76 62	95.48 146	99.43 163	99.46 78

pmmvs-eth3d		96.49 171	96.18 185	97.42 141	98.25 197	94.29 150	94.77 268	98.07 247	89.81 313	97.97 150	98.33 125	93.11 202	99.08 297	95.46 149	99.84 37	98.89 198

SED-MVS		97.94 61	97.90 61	98.07 85	99.22 66	95.35 107	96.79 140	98.83 132	96.11 128	99.08 41	98.24 143	97.87 23	99.72 88	95.44 150	99.51 135	99.14 151

test_241102_TWO								98.83 132	96.11 128	98.62 75	98.24 143	96.92 73	99.72 88	95.44 150	99.49 142	99.49 67

APD-MVS_3200maxsize		98.13 42	97.90 61	98.79 30	98.79 132	97.31 37	97.55 97	98.92 102	97.72 61	98.25 117	98.13 156	97.10 56	99.75 68	95.44 150	99.24 206	99.32 113

xiu_mvs_v1_base_debu		95.62 208	95.96 195	94.60 299	98.01 225	88.42 288	93.99 299	98.21 222	92.98 257	95.91 272	94.53 344	96.39 105	99.72 88	95.43 153	98.19 297	95.64 379

xiu_mvs_v1_base		95.62 208	95.96 195	94.60 299	98.01 225	88.42 288	93.99 299	98.21 222	92.98 257	95.91 272	94.53 344	96.39 105	99.72 88	95.43 153	98.19 297	95.64 379

xiu_mvs_v1_base_debi		95.62 208	95.96 195	94.60 299	98.01 225	88.42 288	93.99 299	98.21 222	92.98 257	95.91 272	94.53 344	96.39 105	99.72 88	95.43 153	98.19 297	95.64 379

c3_l		95.20 228	95.32 214	94.83 290	96.19 342	86.43 331	91.83 359	98.35 210	93.47 235	97.36 185	97.26 240	88.69 283	99.28 261	95.41 156	99.36 177	98.78 213

mvsany_test3		96.21 183	95.93 198	97.05 169	97.40 301	94.33 149	95.76 208	94.20 344	89.10 319	99.36 26	99.60 6	93.97 185	97.85 380	95.40 157	98.63 274	98.99 180

ACMMP		98.05 48	97.75 81	98.93 19	99.23 63	97.60 23	98.09 56	98.96 97	95.75 153	97.91 155	98.06 169	96.89 75	99.76 62	95.32 158	99.57 107	99.43 93
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
miper_lstm_enhance		94.81 246	94.80 240	94.85 288	96.16 344	86.45 330	91.14 372	98.20 225	93.49 234	97.03 208	97.37 233	84.97 318	99.26 265	95.28 159	99.56 110	98.83 207

MSLP-MVS++		96.42 176	96.71 155	95.57 253	97.82 246	90.56 254	95.71 209	98.84 126	94.72 195	96.71 230	97.39 229	94.91 160	98.10 377	95.28 159	99.02 233	98.05 296

SteuartSystems-ACMMP		98.02 50	97.76 79	98.79 30	99.43 37	97.21 42	97.15 119	98.90 104	96.58 105	98.08 137	97.87 188	97.02 64	99.76 62	95.25 161	99.59 102	99.40 97
Skip Steuart: Steuart Systems R&D Blog.
SD-MVS		97.37 119	97.70 82	96.35 214	98.14 216	95.13 121	96.54 155	98.92 102	95.94 140	99.19 36	98.08 162	97.74 28	95.06 399	95.24 162	99.54 121	98.87 204
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
IU-MVS					99.22 66	95.40 102		98.14 238	85.77 359	98.36 103				95.23 163	99.51 135	99.49 67

CP-MVS		97.92 65	97.56 102	98.99 11	98.99 108	97.82 16	97.93 68	98.96 97	96.11 128	96.89 219	97.45 221	96.85 80	99.78 47	95.19 164	99.63 89	99.38 104

LS3D		97.77 86	97.50 109	98.57 48	96.24 338	97.58 25	98.45 30	98.85 121	98.58 31	97.51 175	97.94 182	95.74 134	99.63 147	95.19 164	98.97 236	98.51 245

SMA-MVS		97.48 109	97.11 130	98.60 46	98.83 127	96.67 54	96.74 143	98.73 154	91.61 285	98.48 89	98.36 122	96.53 95	99.68 123	95.17 166	99.54 121	99.45 82
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
CR-MVSNet		93.29 299	92.79 297	94.78 293	95.44 369	88.15 296	96.18 177	97.20 285	84.94 370	94.10 320	98.57 97	77.67 355	99.39 227	95.17 166	95.81 369	96.81 359

OPM-MVS		97.54 105	97.25 122	98.41 58	99.11 92	96.61 57	95.24 245	98.46 192	94.58 203	98.10 134	98.07 164	97.09 58	99.39 227	95.16 168	99.44 155	99.21 138
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
mPP-MVS		97.91 68	97.53 105	99.04 5	99.22 66	97.87 15	97.74 84	98.78 146	96.04 133	97.10 200	97.73 203	96.53 95	99.78 47	95.16 168	99.50 139	99.46 78

DIV-MVS_self_test		94.73 247	94.64 246	95.01 278	95.86 355	87.00 322	91.33 366	98.08 243	93.34 239	97.10 200	97.34 235	84.02 325	99.31 252	95.15 170	99.55 116	98.72 222

cl____		94.73 247	94.64 246	95.01 278	95.85 356	87.00 322	91.33 366	98.08 243	93.34 239	97.10 200	97.33 236	84.01 326	99.30 255	95.14 171	99.56 110	98.71 225

MSP-MVS		97.45 111	96.92 145	99.03 6	99.26 57	97.70 19	97.66 88	98.89 105	95.65 156	98.51 84	96.46 289	92.15 232	99.81 37	95.14 171	98.58 279	99.58 36
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
VDDNet		96.98 139	96.84 148	97.41 142	99.40 43	93.26 189	97.94 67	95.31 333	99.26 8	98.39 99	99.18 39	87.85 297	99.62 152	95.13 173	99.09 225	99.35 112

CANet		95.86 198	95.65 209	96.49 206	96.41 335	90.82 247	94.36 279	98.41 200	94.94 189	92.62 364	96.73 275	92.68 215	99.71 102	95.12 174	99.60 100	98.94 186

CNVR-MVS		96.92 142	96.55 166	98.03 92	98.00 229	95.54 94	94.87 263	98.17 231	94.60 200	96.38 249	97.05 252	95.67 136	99.36 238	95.12 174	99.08 226	99.19 142

eth_miper_zixun_eth		94.89 242	94.93 230	94.75 294	95.99 350	86.12 334	91.35 365	98.49 190	93.40 236	97.12 198	97.25 241	86.87 305	99.35 242	95.08 176	98.82 255	98.78 213

bld_raw_conf03		96.30 179	96.50 172	95.71 247	97.70 270	89.70 262	98.03 60	98.85 121	92.51 271	96.84 221	98.43 114	91.53 245	99.70 110	95.07 177	99.55 116	97.73 320

GST-MVS		97.82 81	97.49 110	98.81 28	99.23 63	97.25 39	97.16 118	98.79 142	95.96 138	97.53 173	97.40 225	96.93 71	99.77 57	95.04 178	99.35 182	99.42 94

DP-MVS		97.87 73	97.89 64	97.81 105	98.62 156	94.82 128	97.13 122	98.79 142	98.98 20	98.74 70	98.49 106	95.80 132	99.49 193	95.04 178	99.44 155	99.11 161

D2MVS		95.18 229	95.17 220	95.21 268	97.76 261	87.76 309	94.15 291	97.94 251	89.77 314	96.99 211	97.68 207	87.45 299	99.14 285	95.03 180	99.81 45	98.74 219

SSC-MVS		95.92 195	97.03 137	92.58 355	99.28 55	78.39 391	96.68 150	95.12 335	98.90 22	99.11 40	98.66 89	91.36 248	99.68 123	95.00 181	99.16 214	99.67 26

SR-MVS		98.00 51	97.66 88	99.01 9	98.77 136	97.93 12	97.38 109	98.83 132	97.32 84	98.06 140	97.85 189	96.65 88	99.77 57	95.00 181	99.11 222	99.32 113

FMVSNet2		96.72 159	96.67 158	96.87 182	97.96 231	91.88 227	97.15 119	98.06 248	95.59 160	98.50 86	98.62 94	89.51 277	99.65 139	94.99 183	99.60 100	99.07 168

SDMVSNet		97.97 52	98.26 41	97.11 162	99.41 40	92.21 214	96.92 132	98.60 179	98.58 31	98.78 64	99.39 16	97.80 25	99.62 152	94.98 184	99.86 28	99.52 55

miper_ehance_all_eth		94.69 252	94.70 243	94.64 296	95.77 361	86.22 333	91.32 368	98.24 220	91.67 283	97.05 207	96.65 279	88.39 288	99.22 275	94.88 185	98.34 291	98.49 248

XVG-OURS-SEG-HR		97.38 117	97.07 134	98.30 67	99.01 107	97.41 35	94.66 272	99.02 78	95.20 177	98.15 129	97.52 217	98.83 5	98.43 360	94.87 186	96.41 359	99.07 168

MVS_111021_HR		96.73 158	96.54 168	97.27 151	98.35 188	93.66 176	93.42 319	98.36 207	94.74 194	96.58 239	96.76 274	96.54 94	98.99 307	94.87 186	99.27 201	99.15 148

test_0402		97.84 76	97.97 57	97.47 135	99.19 77	94.07 158	96.71 148	98.73 154	98.66 28	98.56 81	98.41 116	96.84 81	99.69 118	94.82 188	99.81 45	98.64 230

MVS_111021_LR		96.82 152	96.55 166	97.62 118	98.27 195	95.34 109	93.81 309	98.33 211	94.59 202	96.56 241	96.63 280	96.61 91	98.73 330	94.80 189	99.34 185	98.78 213

WR-MVS		96.90 144	96.81 150	97.16 158	98.56 164	92.20 217	94.33 280	98.12 240	97.34 83	98.20 121	97.33 236	92.81 211	99.75 68	94.79 190	99.81 45	99.54 50

ACMH+	93.58 10	98.23 37	98.31 37	97.98 96	99.39 44	95.22 117	97.55 97	99.20 36	98.21 44	99.25 33	98.51 105	98.21 14	99.40 223	94.79 190	99.72 69	99.32 113

thisisatest0530		92.71 308	91.76 316	95.56 255	98.42 183	88.23 293	96.03 189	87.35 398	94.04 220	96.56 241	95.47 327	64.03 397	99.77 57	94.78 192	99.11 222	98.68 229

PGM-MVS		97.88 72	97.52 106	98.96 14	99.20 75	97.62 22	97.09 124	99.06 64	95.45 167	97.55 172	97.94 182	97.11 55	99.78 47	94.77 193	99.46 151	99.48 73

TSAR-MVS + GP.		96.47 173	96.12 186	97.49 133	97.74 266	95.23 114	94.15 291	96.90 298	93.26 242	98.04 143	96.70 276	94.41 174	98.89 316	94.77 193	99.14 216	98.37 257

Syy-MVS		92.09 319	91.80 315	92.93 347	95.19 374	82.65 369	92.46 344	91.35 374	90.67 301	91.76 372	87.61 401	85.64 313	98.50 355	94.73 195	96.84 347	97.65 326

VNet		96.84 148	96.83 149	96.88 181	98.06 221	92.02 224	96.35 165	97.57 277	97.70 63	97.88 158	97.80 196	92.40 228	99.54 178	94.73 195	98.96 237	99.08 166

APD_test1		97.95 58	97.68 86	98.75 32	99.60 16	98.60 6	97.21 117	99.08 60	96.57 108	98.07 139	98.38 120	96.22 115	99.14 285	94.71 197	99.31 195	98.52 244

VPNet		97.26 125	97.49 110	96.59 199	99.47 33	90.58 252	96.27 169	98.53 186	97.77 56	98.46 92	98.41 116	94.59 168	99.68 123	94.61 198	99.29 198	99.52 55

GBi-Net		96.99 136	96.80 151	97.56 121	97.96 231	93.67 173	98.23 45	98.66 171	95.59 160	97.99 146	99.19 36	89.51 277	99.73 83	94.60 199	99.44 155	99.30 118

test1		96.99 136	96.80 151	97.56 121	97.96 231	93.67 173	98.23 45	98.66 171	95.59 160	97.99 146	99.19 36	89.51 277	99.73 83	94.60 199	99.44 155	99.30 118

FMVSNet3		95.26 226	94.94 228	96.22 221	96.53 332	90.06 256	95.99 193	97.66 269	94.11 217	97.99 146	97.91 186	80.22 346	99.63 147	94.60 199	99.44 155	98.96 183

SF-MVS		97.60 100	97.39 113	98.22 74	98.93 115	95.69 88	97.05 126	99.10 53	95.32 173	97.83 164	97.88 187	96.44 103	99.72 88	94.59 202	99.39 172	99.25 134

XXY-MVS		97.54 105	97.70 82	97.07 168	99.46 34	92.21 214	97.22 116	99.00 87	94.93 191	98.58 80	98.92 66	97.31 46	99.41 221	94.44 203	99.43 163	99.59 35

UnsupCasMVSNet_eth		95.91 196	95.73 206	96.44 208	98.48 177	91.52 234	95.31 241	98.45 193	95.76 151	97.48 179	97.54 215	89.53 276	98.69 336	94.43 204	94.61 384	99.13 153

LPG-MVS_test		97.94 61	97.67 87	98.74 35	99.15 83	97.02 43	97.09 124	99.02 78	95.15 180	98.34 106	98.23 145	97.91 21	99.70 110	94.41 205	99.73 65	99.50 59

LGP-MVS_train				98.74 35	99.15 83	97.02 43		99.02 78	95.15 180	98.34 106	98.23 145	97.91 21	99.70 110	94.41 205	99.73 65	99.50 59

DeepPCF-MVS	94.58 5	96.90 144	96.43 175	98.31 66	97.48 293	97.23 41	92.56 341	98.60 179	92.84 263	98.54 82	97.40 225	96.64 90	98.78 325	94.40 207	99.41 170	98.93 190

XVG-ACMP-BASELINE		97.58 103	97.28 121	98.49 53	99.16 80	96.90 47	96.39 159	98.98 93	95.05 185	98.06 140	98.02 173	95.86 123	99.56 171	94.37 208	99.64 87	99.00 177

RPSCF		97.87 73	97.51 107	98.95 15	99.15 83	98.43 7	97.56 96	99.06 64	96.19 125	98.48 89	98.70 86	94.72 162	99.24 271	94.37 208	99.33 190	99.17 145

CSCG		97.40 116	97.30 118	97.69 114	98.95 110	94.83 127	97.28 112	98.99 90	96.35 118	98.13 131	95.95 314	95.99 119	99.66 137	94.36 210	99.73 65	98.59 236

HPM-MVS++		96.99 136	96.38 177	98.81 28	98.64 150	97.59 24	95.97 195	98.20 225	95.51 164	95.06 298	96.53 285	94.10 181	99.70 110	94.29 211	99.15 215	99.13 153

XVG-OURS		97.12 130	96.74 154	98.26 69	98.99 108	97.45 33	93.82 307	99.05 68	95.19 178	98.32 110	97.70 205	95.22 150	98.41 361	94.27 212	98.13 300	98.93 190

jason		94.39 267	94.04 273	95.41 264	98.29 191	87.85 306	92.74 336	96.75 304	85.38 364	95.29 293	96.15 303	88.21 291	99.65 139	94.24 213	99.34 185	98.74 219
jason: jason.
CVMVSNet		92.33 314	92.79 297	90.95 371	97.26 311	75.84 403	95.29 243	92.33 366	81.86 381	96.27 256	98.19 150	81.44 338	98.46 359	94.23 214	98.29 294	98.55 241

EIA-MVS		96.04 190	95.77 205	96.85 183	97.80 251	92.98 194	96.12 183	99.16 41	94.65 198	93.77 331	91.69 383	95.68 135	99.67 131	94.18 215	98.85 251	97.91 306

ET-MVSNet_ETH3D		91.12 331	89.67 343	95.47 260	96.41 335	89.15 276	91.54 362	90.23 388	89.07 320	86.78 402	92.84 367	69.39 391	99.44 208	94.16 216	96.61 356	97.82 313

cl22		93.25 300	92.84 296	94.46 307	94.30 387	86.00 335	91.09 374	96.64 308	90.74 298	95.79 277	96.31 297	78.24 352	98.77 326	94.15 217	98.34 291	98.62 233

MCST-MVS		96.24 182	95.80 203	97.56 121	98.75 137	94.13 157	94.66 272	98.17 231	90.17 309	96.21 260	96.10 308	95.14 152	99.43 210	94.13 218	98.85 251	99.13 153

COLMAP_ROB	94.48 6	98.25 36	98.11 44	98.64 44	99.21 73	97.35 36	97.96 64	99.16 41	98.34 38	98.78 64	98.52 103	97.32 45	99.45 205	94.08 219	99.67 82	99.13 153
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous202405211		96.34 178	95.98 194	97.43 139	98.25 197	93.85 166	96.74 143	94.41 342	97.72 61	98.37 100	98.03 172	87.15 302	99.53 180	94.06 220	99.07 228	98.92 193

Effi-MVS+-dtu		96.81 153	96.09 188	98.99 11	96.90 326	98.69 5	96.42 158	98.09 242	95.86 147	95.15 296	95.54 325	94.26 178	99.81 37	94.06 220	98.51 283	98.47 249

ambc				96.56 203	98.23 200	91.68 232	97.88 72	98.13 239		98.42 95	98.56 99	94.22 179	99.04 301	94.05 222	99.35 182	98.95 184

our_test_3		94.20 274	94.58 253	93.07 339	96.16 344	81.20 381	90.42 381	96.84 299	90.72 299	97.14 196	97.13 246	90.47 259	99.11 292	94.04 223	98.25 295	98.91 194

pmmvs5		94.63 257	94.34 264	95.50 258	97.63 283	88.34 291	94.02 297	97.13 289	87.15 343	95.22 295	97.15 245	87.50 298	99.27 264	93.99 224	99.26 202	98.88 202

DPE-MVS		97.64 96	97.35 116	98.50 52	98.85 126	96.18 70	95.21 247	98.99 90	95.84 148	98.78 64	98.08 162	96.84 81	99.81 37	93.98 225	99.57 107	99.52 55
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ppachtmachnet_test		94.49 264	94.84 236	93.46 330	96.16 344	82.10 373	90.59 379	97.48 279	90.53 303	97.01 210	97.59 212	91.01 252	99.36 238	93.97 226	99.18 212	98.94 186

tfpnnormal		97.72 90	97.97 57	96.94 176	99.26 57	92.23 213	97.83 76	98.45 193	98.25 42	99.13 39	98.66 89	96.65 88	99.69 118	93.92 227	99.62 90	98.91 194

LFMVS		95.32 223	94.88 234	96.62 197	98.03 222	91.47 235	97.65 89	90.72 383	99.11 12	97.89 157	98.31 127	79.20 348	99.48 196	93.91 228	99.12 221	98.93 190

EPP-MVSNet		96.84 148	96.58 163	97.65 116	99.18 78	93.78 170	98.68 13	96.34 309	97.91 53	97.30 186	98.06 169	88.46 286	99.85 29	93.85 229	99.40 171	99.32 113

Fast-Effi-MVS+-dtu		96.44 174	96.12 186	97.39 144	97.18 314	94.39 144	95.46 225	98.73 154	96.03 135	94.72 306	94.92 338	96.28 113	99.69 118	93.81 230	97.98 305	98.09 286

PHI-MVS		96.96 140	96.53 169	98.25 72	97.48 293	96.50 60	96.76 142	98.85 121	93.52 233	96.19 262	96.85 265	95.94 120	99.42 212	93.79 231	99.43 163	98.83 207

miper_enhance_ethall		93.14 302	92.78 299	94.20 316	93.65 396	85.29 343	89.97 385	97.85 256	85.05 366	96.15 265	94.56 343	85.74 311	99.14 285	93.74 232	98.34 291	98.17 283

DeepC-MVS_fast	94.34 7	96.74 156	96.51 171	97.44 138	97.69 271	94.15 156	96.02 190	98.43 196	93.17 251	97.30 186	97.38 231	95.48 141	99.28 261	93.74 232	99.34 185	98.88 202
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AUN-MVS		93.95 283	92.69 301	97.74 109	97.80 251	95.38 104	95.57 223	95.46 329	91.26 293	92.64 362	96.10 308	74.67 371	99.55 175	93.72 234	96.97 342	98.30 268

MP-MVS		97.64 96	97.18 128	99.00 10	99.32 53	97.77 18	97.49 103	98.73 154	96.27 119	95.59 286	97.75 200	96.30 110	99.78 47	93.70 235	99.48 146	99.45 82
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PVSNet_Blended_VisFu		95.95 194	95.80 203	96.42 210	99.28 55	90.62 251	95.31 241	99.08 60	88.40 331	96.97 214	98.17 153	92.11 234	99.78 47	93.64 236	99.21 207	98.86 205

lupinMVS		93.77 284	93.28 286	95.24 267	97.68 272	87.81 307	92.12 353	96.05 312	84.52 373	94.48 313	95.06 334	86.90 303	99.63 147	93.62 237	99.13 218	98.27 272

NCCC		96.52 170	95.99 193	98.10 84	97.81 247	95.68 89	95.00 259	98.20 225	95.39 171	95.40 292	96.36 295	93.81 189	99.45 205	93.55 238	98.42 289	99.17 145

test_vis1_rt		94.03 280	93.65 280	95.17 271	95.76 362	93.42 183	93.97 302	98.33 211	84.68 371	93.17 349	95.89 316	92.53 225	94.79 400	93.50 239	94.97 380	97.31 342

WB-MVS		95.50 212	96.62 159	92.11 364	99.21 73	77.26 399	96.12 183	95.40 331	98.62 29	98.84 59	98.26 141	91.08 251	99.50 188	93.37 240	98.70 267	99.58 36

ETV-MVS		96.13 187	95.90 199	96.82 186	97.76 261	93.89 164	95.40 231	98.95 99	95.87 146	95.58 287	91.00 389	96.36 108	99.72 88	93.36 241	98.83 254	96.85 355

FA-MVS(test-final)		94.91 240	94.89 233	94.99 280	97.51 291	88.11 300	98.27 43	95.20 334	92.40 274	96.68 231	98.60 95	83.44 328	99.28 261	93.34 242	98.53 280	97.59 331

MDA-MVSNet_test_wron		94.73 247	94.83 238	94.42 308	97.48 293	85.15 346	90.28 383	95.87 318	92.52 268	97.48 179	97.76 197	91.92 241	99.17 282	93.32 243	96.80 351	98.94 186

YYNet1		94.73 247	94.84 236	94.41 309	97.47 297	85.09 348	90.29 382	95.85 319	92.52 268	97.53 173	97.76 197	91.97 238	99.18 278	93.31 244	96.86 346	98.95 184

pmmvs4		94.82 245	94.19 269	96.70 194	97.42 300	92.75 202	92.09 355	96.76 303	86.80 349	95.73 282	97.22 242	89.28 280	98.89 316	93.28 245	99.14 216	98.46 251

CANet_DTU		94.65 256	94.21 268	95.96 231	95.90 352	89.68 264	93.92 304	97.83 260	93.19 247	90.12 385	95.64 322	88.52 285	99.57 170	93.27 246	99.47 148	98.62 233

ACMP	92.54 13	97.47 110	97.10 131	98.55 50	99.04 104	96.70 52	96.24 174	98.89 105	93.71 227	97.97 150	97.75 200	97.44 40	99.63 147	93.22 247	99.70 75	99.32 113
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Effi-MVS+		96.19 184	96.01 191	96.71 193	97.43 299	92.19 218	96.12 183	99.10 53	95.45 167	93.33 347	94.71 341	97.23 53	99.56 171	93.21 248	97.54 329	98.37 257

MDA-MVSNet-bldmvs		95.69 204	95.67 207	95.74 244	98.48 177	88.76 286	92.84 331	97.25 283	96.00 136	97.59 171	97.95 181	91.38 247	99.46 201	93.16 249	96.35 361	98.99 180

IS-MVSNet		96.93 141	96.68 157	97.70 112	99.25 60	94.00 161	98.57 19	96.74 305	98.36 37	98.14 130	97.98 178	88.23 290	99.71 102	93.10 250	99.72 69	99.38 104

9.14			96.69 156		98.53 168		96.02 190	98.98 93	93.23 243	97.18 194	97.46 220	96.47 100	99.62 152	92.99 251	99.32 192

MS-PatchMatch		94.83 244	94.91 232	94.57 302	96.81 327	87.10 321	94.23 286	97.34 282	88.74 326	97.14 196	97.11 248	91.94 240	98.23 373	92.99 251	97.92 308	98.37 257

Patchmtry		95.03 237	94.59 252	96.33 215	94.83 381	90.82 247	96.38 162	97.20 285	96.59 104	97.49 177	98.57 97	77.67 355	99.38 230	92.95 253	99.62 90	98.80 211

sd_testset		97.97 52	98.12 43	97.51 126	99.41 40	93.44 182	97.96 64	98.25 218	98.58 31	98.78 64	99.39 16	98.21 14	99.56 171	92.65 254	99.86 28	99.52 55

Fast-Effi-MVS+		95.49 213	95.07 224	96.75 191	97.67 276	92.82 196	94.22 287	98.60 179	91.61 285	93.42 345	92.90 365	96.73 86	99.70 110	92.60 255	97.89 311	97.74 319

HQP_MVS		96.66 164	96.33 180	97.68 115	98.70 145	94.29 150	96.50 156	98.75 151	96.36 116	96.16 263	96.77 272	91.91 242	99.46 201	92.59 256	99.20 208	99.28 125

plane_prior5								98.75 151					99.46 201	92.59 256	99.20 208	99.28 125

mvsany_test1		93.47 294	93.03 290	94.79 292	94.05 393	92.12 219	90.82 377	90.01 391	85.02 368	97.26 188	98.28 136	93.57 194	97.03 389	92.51 258	95.75 374	95.23 385

GA-MVS		92.83 306	92.15 310	94.87 287	96.97 321	87.27 318	90.03 384	96.12 311	91.83 282	94.05 323	94.57 342	76.01 367	98.97 313	92.46 259	97.34 338	98.36 262

mvsmamba		94.91 240	94.41 262	96.40 213	97.65 279	91.30 238	97.92 69	95.32 332	91.50 288	95.54 288	98.38 120	83.06 331	99.68 123	92.46 259	97.84 312	98.23 275

CPTT-MVS		96.69 162	96.08 189	98.49 53	98.89 120	96.64 56	97.25 113	98.77 147	92.89 262	96.01 269	97.13 246	92.23 230	99.67 131	92.24 261	99.34 185	99.17 145

EPNet		93.72 286	92.62 304	97.03 172	87.61 412	92.25 212	96.27 169	91.28 376	96.74 99	87.65 398	97.39 229	85.00 317	99.64 143	92.14 262	99.48 146	99.20 141
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PC_three_1452									87.24 342	98.37 100	97.44 222	97.00 65	96.78 395	92.01 263	99.25 203	99.21 138

APD-MVS		97.00 135	96.53 169	98.41 58	98.55 165	96.31 67	96.32 167	98.77 147	92.96 261	97.44 183	97.58 214	95.84 124	99.74 77	91.96 264	99.35 182	99.19 142
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CL-MVSNet_self_test		95.04 235	94.79 241	95.82 240	97.51 291	89.79 261	91.14 372	96.82 301	93.05 254	96.72 229	96.40 293	90.82 255	99.16 283	91.95 265	98.66 271	98.50 247

test_prior2							93.33 323		94.21 211	94.02 325	96.25 299	93.64 193		91.90 266	98.96 237

test-LLR		89.97 343	89.90 341	90.16 375	94.24 389	74.98 404	89.89 386	89.06 392	92.02 277	89.97 386	90.77 391	73.92 374	98.57 348	91.88 267	97.36 336	96.92 350

test-mter		87.92 363	87.17 364	90.16 375	94.24 389	74.98 404	89.89 386	89.06 392	86.44 352	89.97 386	90.77 391	54.96 410	98.57 348	91.88 267	97.36 336	96.92 350

MVP-Stereo		95.69 204	95.28 215	96.92 178	98.15 214	93.03 193	95.64 219	98.20 225	90.39 305	96.63 237	97.73 203	91.63 244	99.10 295	91.84 269	97.31 339	98.63 232
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
testing3		89.72 347	88.26 356	94.10 319	97.66 277	84.30 359	94.80 265	88.25 396	94.66 197	95.07 297	92.51 373	41.15 414	99.43 210	91.81 270	98.44 288	98.55 241

1112_ss		94.12 275	93.42 284	96.23 219	98.59 160	90.85 246	94.24 285	98.85 121	85.49 360	92.97 353	94.94 336	86.01 309	99.64 143	91.78 271	97.92 308	98.20 279

train_agg		95.46 217	94.66 244	97.88 101	97.84 243	95.23 114	93.62 313	98.39 203	87.04 344	93.78 329	95.99 310	94.58 169	99.52 183	91.76 272	98.90 244	98.89 198

LF4IMVS		96.07 188	95.63 210	97.36 145	98.19 204	95.55 93	95.44 226	98.82 140	92.29 275	95.70 283	96.55 283	92.63 218	98.69 336	91.75 273	99.33 190	97.85 311

N_pmnet		95.18 229	94.23 266	98.06 87	97.85 238	96.55 59	92.49 342	91.63 372	89.34 316	98.09 135	97.41 224	90.33 263	99.06 299	91.58 274	99.31 195	98.56 239

AllTest		97.20 128	96.92 145	98.06 87	99.08 96	96.16 71	97.14 121	99.16 41	94.35 208	97.78 166	98.07 164	95.84 124	99.12 289	91.41 275	99.42 166	98.91 194

TestCases				98.06 87	99.08 96	96.16 71		99.16 41	94.35 208	97.78 166	98.07 164	95.84 124	99.12 289	91.41 275	99.42 166	98.91 194

test9_res														91.29 277	98.89 247	99.00 177

xiu_mvs_v2_base		94.22 270	94.63 248	92.99 344	97.32 309	84.84 352	92.12 353	97.84 258	91.96 279	94.17 318	93.43 356	96.07 118	99.71 102	91.27 278	97.48 332	94.42 389

PS-MVSNAJ		94.10 276	94.47 258	93.00 343	97.35 304	84.88 350	91.86 358	97.84 258	91.96 279	94.17 318	92.50 374	95.82 127	99.71 102	91.27 278	97.48 332	94.40 390

tpm		91.08 333	90.85 331	91.75 367	95.33 372	78.09 392	95.03 258	91.27 377	88.75 325	93.53 340	97.40 225	71.24 384	99.30 255	91.25 280	93.87 388	97.87 310

OPU-MVS				97.64 117	98.01 225	95.27 112	96.79 140				97.35 234	96.97 67	98.51 354	91.21 281	99.25 203	99.14 151

ZD-MVS					98.43 182	95.94 80		98.56 185	90.72 299	96.66 234	97.07 250	95.02 156	99.74 77	91.08 282	98.93 242

tpmrst		90.31 338	90.61 336	89.41 379	94.06 392	72.37 410	95.06 255	93.69 347	88.01 336	92.32 367	96.86 264	77.45 357	98.82 321	91.04 283	87.01 402	97.04 347

sss		94.22 270	93.72 279	95.74 244	97.71 269	89.95 259	93.84 306	96.98 295	88.38 332	93.75 332	95.74 318	87.94 292	98.89 316	91.02 284	98.10 301	98.37 257

ITE_SJBPF				97.85 103	98.64 150	96.66 55		98.51 189	95.63 157	97.22 189	97.30 238	95.52 140	98.55 351	90.97 285	98.90 244	98.34 263

Test_1112_low_res		93.53 293	92.86 294	95.54 257	98.60 158	88.86 282	92.75 334	98.69 164	82.66 380	92.65 361	96.92 262	84.75 319	99.56 171	90.94 286	97.76 316	98.19 280

TESTMET0.1,1		87.20 369	86.57 369	89.07 380	93.62 397	72.84 409	89.89 386	87.01 400	85.46 362	89.12 392	90.20 394	56.00 405	97.72 383	90.91 287	96.92 343	96.64 363

FMVSNet5		93.39 296	92.35 306	96.50 205	95.83 357	90.81 249	97.31 110	98.27 216	92.74 265	96.27 256	98.28 136	62.23 398	99.67 131	90.86 288	99.36 177	99.03 173

PatchmatchNet		91.98 322	91.87 312	92.30 361	94.60 384	79.71 387	95.12 249	93.59 352	89.52 315	93.61 337	97.02 254	77.94 353	99.18 278	90.84 289	94.57 386	98.01 300
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CLD-MVS		95.47 216	95.07 224	96.69 195	98.27 195	92.53 205	91.36 364	98.67 169	91.22 294	95.78 279	94.12 351	95.65 137	98.98 309	90.81 290	99.72 69	98.57 238
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
cascas		91.89 323	91.35 320	93.51 329	94.27 388	85.60 338	88.86 394	98.61 178	79.32 393	92.16 368	91.44 385	89.22 281	98.12 376	90.80 291	97.47 334	96.82 358

test20.03		96.58 168	96.61 161	96.48 207	98.49 175	91.72 231	95.68 213	97.69 266	96.81 97	98.27 116	97.92 185	94.18 180	98.71 333	90.78 292	99.66 84	99.00 177

test_yl		94.40 265	94.00 274	95.59 251	96.95 322	89.52 267	94.75 269	95.55 327	96.18 126	96.79 223	96.14 305	81.09 341	99.18 278	90.75 293	97.77 314	98.07 289

DCV-MVSNet		94.40 265	94.00 274	95.59 251	96.95 322	89.52 267	94.75 269	95.55 327	96.18 126	96.79 223	96.14 305	81.09 341	99.18 278	90.75 293	97.77 314	98.07 289

EPMVS		89.26 351	88.55 353	91.39 369	92.36 405	79.11 390	95.65 216	79.86 408	88.60 328	93.12 350	96.53 285	70.73 388	98.10 377	90.75 293	89.32 399	96.98 348

旧先验2							93.35 322		77.95 398	95.77 281			98.67 340	90.74 296

USDC		94.56 260	94.57 255	94.55 303	97.78 259	86.43 331	92.75 334	98.65 176	85.96 355	96.91 218	97.93 184	90.82 255	98.74 329	90.71 297	99.59 102	98.47 249

OpenMVS	94.22 8	95.48 215	95.20 217	96.32 216	97.16 315	91.96 226	97.74 84	98.84 126	87.26 341	94.36 315	98.01 175	93.95 186	99.67 131	90.70 298	98.75 261	97.35 341

Patchmatch-test		93.60 291	93.25 287	94.63 297	96.14 348	87.47 313	96.04 188	94.50 341	93.57 232	96.47 245	96.97 257	76.50 363	98.61 345	90.67 299	98.41 290	97.81 315

thisisatest0515		90.43 337	89.18 349	94.17 318	97.07 319	85.44 340	89.75 390	87.58 397	88.28 333	93.69 335	91.72 382	65.27 395	99.58 164	90.59 300	98.67 269	97.50 336

DP-MVS Recon		95.55 211	95.13 221	96.80 187	98.51 171	93.99 162	94.60 274	98.69 164	90.20 308	95.78 279	96.21 301	92.73 214	98.98 309	90.58 301	98.86 250	97.42 338

TinyColmap		96.00 193	96.34 179	94.96 282	97.90 236	87.91 303	94.13 294	98.49 190	94.41 206	98.16 127	97.76 197	96.29 112	98.68 339	90.52 302	99.42 166	98.30 268

BP-MVS														90.51 303

HQP-MVS		95.17 231	94.58 253	96.92 178	97.85 238	92.47 208	94.26 281	98.43 196	93.18 248	92.86 355	95.08 332	90.33 263	99.23 273	90.51 303	98.74 262	99.05 172

OMC-MVS		96.48 172	96.00 192	97.91 99	98.30 190	96.01 79	94.86 264	98.60 179	91.88 281	97.18 194	97.21 243	96.11 117	99.04 301	90.49 305	99.34 185	98.69 226

ab-mvs		96.59 166	96.59 162	96.60 198	98.64 150	92.21 214	98.35 34	97.67 267	94.45 205	96.99 211	98.79 76	94.96 159	99.49 193	90.39 306	99.07 228	98.08 287

HyFIR lowres test		93.72 286	92.65 302	96.91 180	98.93 115	91.81 230	91.23 370	98.52 187	82.69 379	96.46 246	96.52 287	80.38 345	99.90 17	90.36 307	98.79 257	99.03 173

agg_prior2														90.34 308	98.90 244	99.10 165

LCM-MVSNet-Re		97.33 122	97.33 117	97.32 148	98.13 219	93.79 169	96.99 129	99.65 10	96.74 99	99.47 19	98.93 65	96.91 74	99.84 32	90.11 309	99.06 231	98.32 264

CDS-MVSNet		94.88 243	94.12 271	97.14 160	97.64 282	93.57 178	93.96 303	97.06 293	90.05 310	96.30 255	96.55 283	86.10 308	99.47 198	90.10 310	99.31 195	98.40 253
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CDPH-MVS		95.45 218	94.65 245	97.84 104	98.28 193	94.96 125	93.73 311	98.33 211	85.03 367	95.44 290	96.60 281	95.31 147	99.44 208	90.01 311	99.13 218	99.11 161

baseline1		93.14 302	92.64 303	94.62 298	97.34 306	87.20 319	96.67 152	93.02 356	94.71 196	96.51 244	95.83 317	81.64 336	98.60 347	90.00 312	88.06 401	98.07 289

TAPA-MVS	93.32 12	94.93 239	94.23 266	97.04 171	98.18 207	94.51 140	95.22 246	98.73 154	81.22 386	96.25 258	95.95 314	93.80 190	98.98 309	89.89 313	98.87 248	97.62 328
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PMMVS		92.39 311	91.08 326	96.30 218	93.12 400	92.81 198	90.58 380	95.96 316	79.17 394	91.85 371	92.27 375	90.29 267	98.66 341	89.85 314	96.68 355	97.43 337

PVSNet_BlendedMVS		95.02 238	94.93 230	95.27 266	97.79 256	87.40 315	94.14 293	98.68 166	88.94 323	94.51 311	98.01 175	93.04 204	99.30 255	89.77 315	99.49 142	99.11 161

PVSNet_Blended		93.96 281	93.65 280	94.91 283	97.79 256	87.40 315	91.43 363	98.68 166	84.50 374	94.51 311	94.48 347	93.04 204	99.30 255	89.77 315	98.61 276	98.02 299

MSDG		95.33 222	95.13 221	95.94 235	97.40 301	91.85 228	91.02 375	98.37 206	95.30 174	96.31 254	95.99 310	94.51 172	98.38 364	89.59 317	97.65 326	97.60 330

PMVS	89.60 17	96.71 161	96.97 140	95.95 233	99.51 28	97.81 17	97.42 108	97.49 278	97.93 52	95.95 270	98.58 96	96.88 77	96.91 392	89.59 317	99.36 177	93.12 397
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_post1							94.98 260				10.37 413	76.21 366	99.04 301	89.47 319

SCA		93.38 297	93.52 283	92.96 345	96.24 338	81.40 380	93.24 325	94.00 345	91.58 287	94.57 309	96.97 257	87.94 292	99.42 212	89.47 319	97.66 325	98.06 293

tpmvs		90.79 336	90.87 330	90.57 374	92.75 404	76.30 401	95.79 207	93.64 351	91.04 296	91.91 370	96.26 298	77.19 361	98.86 320	89.38 321	89.85 398	96.56 366

Anonymous20231206		95.27 225	95.06 226	95.88 237	98.72 140	89.37 271	95.70 210	97.85 256	88.00 337	96.98 213	97.62 210	91.95 239	99.34 245	89.21 322	99.53 125	98.94 186

CHOSEN 1792x2688		94.10 276	93.41 285	96.18 223	99.16 80	90.04 257	92.15 352	98.68 166	79.90 391	96.22 259	97.83 190	87.92 296	99.42 212	89.18 323	99.65 85	99.08 166

114514_t		93.96 281	93.22 288	96.19 222	99.06 99	90.97 245	95.99 193	98.94 100	73.88 404	93.43 344	96.93 260	92.38 229	99.37 235	89.09 324	99.28 199	98.25 274

pmmvs3		90.00 341	88.90 351	93.32 331	94.20 391	85.34 341	91.25 369	92.56 365	78.59 395	93.82 328	95.17 331	67.36 394	98.69 336	89.08 325	98.03 304	95.92 374

testdata				95.70 248	98.16 212	90.58 252		97.72 265	80.38 389	95.62 284	97.02 254	92.06 237	98.98 309	89.06 326	98.52 281	97.54 333

MDTV_nov1_ep13			91.28 322		94.31 386	73.51 408	94.80 265	93.16 355	86.75 350	93.45 343	97.40 225	76.37 364	98.55 351	88.85 327	96.43 358

PMMVS2		93.66 289	94.07 272	92.45 359	97.57 286	80.67 384	86.46 397	96.00 314	93.99 221	97.10 200	97.38 231	89.90 270	97.82 381	88.76 328	99.47 148	98.86 205

QAPM		95.88 197	95.57 212	96.80 187	97.90 236	91.84 229	98.18 52	98.73 154	88.41 330	96.42 247	98.13 156	94.73 161	99.75 68	88.72 329	98.94 240	98.81 210

CHOSEN 280x420		89.98 342	89.19 348	92.37 360	95.60 366	81.13 382	86.22 398	97.09 291	81.44 385	87.44 399	93.15 357	73.99 372	99.47 198	88.69 330	99.07 228	96.52 367

testgi		96.07 188	96.50 172	94.80 291	99.26 57	87.69 310	95.96 197	98.58 183	95.08 183	98.02 145	96.25 299	97.92 20	97.60 385	88.68 331	98.74 262	99.11 161

CostFormer		89.75 346	89.25 344	91.26 370	94.69 383	78.00 394	95.32 240	91.98 369	81.50 384	90.55 379	96.96 259	71.06 386	98.89 316	88.59 332	92.63 392	96.87 353

UnsupCasMVSNet_bld		94.72 251	94.26 265	96.08 227	98.62 156	90.54 255	93.38 321	98.05 249	90.30 306	97.02 209	96.80 271	89.54 274	99.16 283	88.44 333	96.18 365	98.56 239

TAMVS		95.49 213	94.94 228	97.16 158	98.31 189	93.41 184	95.07 254	96.82 301	91.09 295	97.51 175	97.82 193	89.96 269	99.42 212	88.42 334	99.44 155	98.64 230

Vis-MVSNet (Re-imp)		95.11 232	94.85 235	95.87 238	99.12 91	89.17 274	97.54 102	94.92 337	96.50 110	96.58 239	97.27 239	83.64 327	99.48 196	88.42 334	99.67 82	98.97 182

EPNet_dtu		91.39 330	90.75 333	93.31 332	90.48 409	82.61 370	94.80 265	92.88 358	93.39 237	81.74 406	94.90 339	81.36 339	99.11 292	88.28 336	98.87 248	98.21 278
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
JIA-IIPM		91.79 324	90.69 334	95.11 272	93.80 395	90.98 244	94.16 290	91.78 371	96.38 114	90.30 383	99.30 27	72.02 383	98.90 315	88.28 336	90.17 397	95.45 383

新几何1				97.25 154	98.29 191	94.70 132		97.73 264	77.98 397	94.83 305	96.67 278	92.08 236	99.45 205	88.17 338	98.65 273	97.61 329

testdata2													99.46 201	87.84 339

FE-MVS		92.95 304	92.22 308	95.11 272	97.21 313	88.33 292	98.54 22	93.66 350	89.91 312	96.21 260	98.14 154	70.33 389	99.50 188	87.79 340	98.24 296	97.51 334

无先验							93.20 326	97.91 252	80.78 387				99.40 223	87.71 341		97.94 305

WTY-MVS		93.55 292	93.00 292	95.19 269	97.81 247	87.86 304	93.89 305	96.00 314	89.02 321	94.07 322	95.44 329	86.27 307	99.33 247	87.69 342	96.82 349	98.39 255

原ACMM1				96.58 200	98.16 212	92.12 219		98.15 237	85.90 357	93.49 341	96.43 290	92.47 227	99.38 230	87.66 343	98.62 275	98.23 275

BH-untuned		94.69 252	94.75 242	94.52 304	97.95 234	87.53 312	94.07 296	97.01 294	93.99 221	97.10 200	95.65 321	92.65 217	98.95 314	87.60 344	96.74 352	97.09 345

PAPM_NR		94.61 258	94.17 270	95.96 231	98.36 187	91.23 240	95.93 199	97.95 250	92.98 257	93.42 345	94.43 348	90.53 258	98.38 364	87.60 344	96.29 363	98.27 272

testing99		89.21 352	88.04 358	92.70 353	95.78 360	81.00 383	92.65 339	92.03 367	93.20 246	89.90 388	90.08 397	55.25 406	99.14 285	87.54 346	95.95 368	97.97 302

DPM-MVS		93.68 288	92.77 300	96.42 210	97.91 235	92.54 204	91.17 371	97.47 280	84.99 369	93.08 351	94.74 340	89.90 270	99.00 305	87.54 346	98.09 302	97.72 323

MG-MVS		94.08 278	94.00 274	94.32 312	97.09 318	85.89 336	93.19 327	95.96 316	92.52 268	94.93 304	97.51 218	89.54 274	98.77 326	87.52 348	97.71 320	98.31 266

F-COLMAP		95.30 224	94.38 263	98.05 91	98.64 150	96.04 76	95.61 220	98.66 171	89.00 322	93.22 348	96.40 293	92.90 210	99.35 242	87.45 349	97.53 330	98.77 216

PatchMatch-RL		94.61 258	93.81 278	97.02 173	98.19 204	95.72 86	93.66 312	97.23 284	88.17 335	94.94 303	95.62 323	91.43 246	98.57 348	87.36 350	97.68 323	96.76 361

testing11		88.93 354	87.63 362	92.80 350	95.87 354	81.49 379	92.48 343	91.54 373	91.62 284	88.27 396	90.24 393	55.12 409	99.11 292	87.30 351	96.28 364	97.81 315

IB-MVS	85.98 20	88.63 357	86.95 367	93.68 326	95.12 376	84.82 353	90.85 376	90.17 389	87.55 340	88.48 395	91.34 386	58.01 399	99.59 162	87.24 352	93.80 389	96.63 365
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		89.67 348	88.55 353	93.04 340	95.90 352	81.80 377	92.71 338	93.71 346	93.71 227	90.18 384	90.15 395	57.11 400	99.22 275	87.17 353	96.32 362	98.12 285

dp		88.08 361	88.05 357	88.16 386	92.85 402	68.81 412	94.17 289	92.88 358	85.47 361	91.38 375	96.14 305	68.87 392	98.81 323	86.88 354	83.80 405	96.87 353

1314		92.38 312	92.30 307	92.64 354	95.42 371	85.15 346	95.86 203	96.97 296	85.40 363	90.62 377	93.06 363	91.12 250	97.80 382	86.74 355	95.49 377	94.97 387

CNLPA		95.04 235	94.47 258	96.75 191	97.81 247	95.25 113	94.12 295	97.89 254	94.41 206	94.57 309	95.69 319	90.30 266	98.35 367	86.72 356	98.76 260	96.64 363

baseline2		89.65 349	88.44 355	93.25 334	95.62 365	82.71 368	93.82 307	85.94 402	88.89 324	87.35 400	92.54 372	71.23 385	99.33 247	86.01 357	94.60 385	97.72 323

BH-RMVSNet		94.56 260	94.44 261	94.91 283	97.57 286	87.44 314	93.78 310	96.26 310	93.69 229	96.41 248	96.50 288	92.10 235	99.00 305	85.96 358	97.71 320	98.31 266

E-PMN		89.52 350	89.78 342	88.73 381	93.14 399	77.61 395	83.26 403	92.02 368	94.82 193	93.71 333	93.11 358	75.31 369	96.81 393	85.81 359	96.81 350	91.77 400

API-MVS		95.09 234	95.01 227	95.31 265	96.61 330	94.02 160	96.83 136	97.18 287	95.60 159	95.79 277	94.33 349	94.54 171	98.37 366	85.70 360	98.52 281	93.52 394

AdaColmap		95.11 232	94.62 249	96.58 200	97.33 308	94.45 143	94.92 261	98.08 243	93.15 252	93.98 327	95.53 326	94.34 176	99.10 295	85.69 361	98.61 276	96.20 373

ADS-MVSNet2		91.47 329	90.51 337	94.36 310	95.51 367	85.63 337	95.05 256	95.70 320	83.46 377	92.69 359	96.84 266	79.15 349	99.41 221	85.66 362	90.52 395	98.04 297

ADS-MVSNet		90.95 335	90.26 339	93.04 340	95.51 367	82.37 372	95.05 256	93.41 353	83.46 377	92.69 359	96.84 266	79.15 349	98.70 334	85.66 362	90.52 395	98.04 297

MDTV_nov1_ep13_2view						57.28 414	94.89 262		80.59 388	94.02 325		78.66 351		85.50 364		97.82 313

WAC-MVS						79.32 388								85.41 365

OpenMVS_ROB	91.80 14	93.64 290	93.05 289	95.42 262	97.31 310	91.21 241	95.08 253	96.68 307	81.56 383	96.88 220	96.41 291	90.44 262	99.25 267	85.39 366	97.67 324	95.80 377

KD-MVS_2432*1600		88.93 354	87.74 359	92.49 356	88.04 410	81.99 374	89.63 391	95.62 323	91.35 291	95.06 298	93.11 358	56.58 402	98.63 343	85.19 367	95.07 378	96.85 355

miper_refine_blended		88.93 354	87.74 359	92.49 356	88.04 410	81.99 374	89.63 391	95.62 323	91.35 291	95.06 298	93.11 358	56.58 402	98.63 343	85.19 367	95.07 378	96.85 355

PVSNet	86.72 19	91.10 332	90.97 329	91.49 368	97.56 288	78.04 393	87.17 396	94.60 340	84.65 372	92.34 366	92.20 377	87.37 301	98.47 358	85.17 369	97.69 322	97.96 303

PLC	91.02 16	94.05 279	92.90 293	97.51 126	98.00 229	95.12 122	94.25 284	98.25 218	86.17 353	91.48 374	95.25 330	91.01 252	99.19 277	85.02 370	96.69 354	98.22 277
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
gm-plane-assit					91.79 406	71.40 411			81.67 382		90.11 396		98.99 307	84.86 371

CMPMVS	73.10 23	92.74 307	91.39 319	96.77 190	93.57 398	94.67 133	94.21 288	97.67 267	80.36 390	93.61 337	96.60 281	82.85 333	97.35 386	84.86 371	98.78 258	98.29 271
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		92.34 313	91.69 317	94.32 312	96.23 340	89.16 275	92.27 351	92.88 358	84.39 376	95.29 293	96.35 296	85.66 312	96.74 396	84.53 373	97.56 328	97.05 346

tpm cat1		88.01 362	87.33 363	90.05 378	94.48 385	76.28 402	94.47 277	94.35 343	73.84 405	89.26 391	95.61 324	73.64 376	98.30 370	84.13 374	86.20 403	95.57 382

MAR-MVS		94.21 272	93.03 290	97.76 108	96.94 324	97.44 34	96.97 130	97.15 288	87.89 339	92.00 369	92.73 370	92.14 233	99.12 289	83.92 375	97.51 331	96.73 362
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
DSMNet-mixed		92.19 316	91.83 313	93.25 334	96.18 343	83.68 364	96.27 169	93.68 349	76.97 401	92.54 365	99.18 39	89.20 282	98.55 351	83.88 376	98.60 278	97.51 334

EMVS		89.06 353	89.22 345	88.61 382	93.00 401	77.34 397	82.91 404	90.92 379	94.64 199	92.63 363	91.81 381	76.30 365	97.02 390	83.83 377	96.90 345	91.48 401

HY-MVS	91.43 15	92.58 309	91.81 314	94.90 285	96.49 333	88.87 281	97.31 110	94.62 339	85.92 356	90.50 380	96.84 266	85.05 316	99.40 223	83.77 378	95.78 372	96.43 369

test0.0.03 1		90.11 339	89.21 346	92.83 349	93.89 394	86.87 325	91.74 360	88.74 395	92.02 277	94.71 307	91.14 388	73.92 374	94.48 402	83.75 379	92.94 390	97.16 344

tpm2		88.47 358	87.69 361	90.79 372	94.98 378	77.34 397	95.09 251	91.83 370	77.51 400	89.40 390	96.41 291	67.83 393	98.73 330	83.58 380	92.60 393	96.29 371

myMVS_eth3d		87.16 370	85.61 373	91.82 366	95.19 374	79.32 388	92.46 344	91.35 374	90.67 301	91.76 372	87.61 401	41.96 413	98.50 355	82.66 381	96.84 347	97.65 326

MVS-HIRNet		88.40 359	90.20 340	82.99 388	97.01 320	60.04 413	93.11 328	85.61 403	84.45 375	88.72 394	99.09 51	84.72 320	98.23 373	82.52 382	96.59 357	90.69 403

UWE-MVS		87.57 366	86.72 368	90.13 377	95.21 373	73.56 407	91.94 357	83.78 406	88.73 327	93.00 352	92.87 366	55.22 407	99.25 267	81.74 383	97.96 306	97.59 331

BH-w/o		92.14 317	91.94 311	92.73 352	97.13 317	85.30 342	92.46 344	95.64 322	89.33 317	94.21 317	92.74 369	89.60 272	98.24 372	81.68 384	94.66 383	94.66 388

MIMVSNet		93.42 295	92.86 294	95.10 274	98.17 210	88.19 294	98.13 54	93.69 347	92.07 276	95.04 301	98.21 149	80.95 343	99.03 304	81.42 385	98.06 303	98.07 289

TR-MVS		92.54 310	92.20 309	93.57 328	96.49 333	86.66 327	93.51 317	94.73 338	89.96 311	94.95 302	93.87 353	90.24 268	98.61 345	81.18 386	94.88 381	95.45 383

dmvs_re		92.08 320	91.27 323	94.51 305	97.16 315	92.79 201	95.65 216	92.64 363	94.11 217	92.74 358	90.98 390	83.41 329	94.44 403	80.72 387	94.07 387	96.29 371

thres600view7		92.03 321	91.43 318	93.82 322	98.19 204	84.61 354	96.27 169	90.39 384	96.81 97	96.37 250	93.11 358	73.44 380	99.49 193	80.32 388	97.95 307	97.36 339

WB-MVSnew		91.50 328	91.29 321	92.14 363	94.85 379	80.32 385	93.29 324	88.77 394	88.57 329	94.03 324	92.21 376	92.56 220	98.28 371	80.21 389	97.08 341	97.81 315

PAPR		92.22 315	91.27 323	95.07 275	95.73 364	88.81 283	91.97 356	97.87 255	85.80 358	90.91 376	92.73 370	91.16 249	98.33 368	79.48 390	95.76 373	98.08 287

MVS		90.02 340	89.20 347	92.47 358	94.71 382	86.90 324	95.86 203	96.74 305	64.72 406	90.62 377	92.77 368	92.54 223	98.39 363	79.30 391	95.56 376	92.12 398

gg-mvs-nofinetune		88.28 360	86.96 366	92.23 362	92.84 403	84.44 356	98.19 51	74.60 410	99.08 13	87.01 401	99.47 11	56.93 401	98.23 373	78.91 392	95.61 375	94.01 392

thres100view900		91.76 325	91.26 325	93.26 333	98.21 201	84.50 355	96.39 159	90.39 384	96.87 95	96.33 251	93.08 362	73.44 380	99.42 212	78.85 393	97.74 317	95.85 375

tfpn200view9		91.55 327	91.00 327	93.21 337	98.02 223	84.35 357	95.70 210	90.79 381	96.26 120	95.90 275	92.13 378	73.62 377	99.42 212	78.85 393	97.74 317	95.85 375

thres400		91.68 326	91.00 327	93.71 325	98.02 223	84.35 357	95.70 210	90.79 381	96.26 120	95.90 275	92.13 378	73.62 377	99.42 212	78.85 393	97.74 317	97.36 339

thres200		91.00 334	90.42 338	92.77 351	97.47 297	83.98 362	94.01 298	91.18 378	95.12 182	95.44 290	91.21 387	73.93 373	99.31 252	77.76 396	97.63 327	95.01 386

wuyk23d		93.25 300	95.20 217	87.40 387	96.07 349	95.38 104	97.04 127	94.97 336	95.33 172	99.70 8	98.11 160	98.14 17	91.94 405	77.76 396	99.68 80	74.89 405

test_method		66.88 374	66.13 377	69.11 390	62.68 415	25.73 418	49.76 406	96.04 313	14.32 410	64.27 410	91.69 383	73.45 379	88.05 407	76.06 398	66.94 407	93.54 393

testing222		87.35 367	85.50 374	92.93 347	95.79 359	82.83 367	92.40 349	90.10 390	92.80 264	88.87 393	89.02 398	48.34 412	98.70 334	75.40 399	96.74 352	97.27 343

ETVMVS		87.62 365	85.75 372	93.22 336	96.15 347	83.26 365	92.94 330	90.37 386	91.39 290	90.37 381	88.45 399	51.93 411	98.64 342	73.76 400	96.38 360	97.75 318

PCF-MVS	89.43 18	92.12 318	90.64 335	96.57 202	97.80 251	93.48 181	89.88 389	98.45 193	74.46 403	96.04 268	95.68 320	90.71 257	99.31 252	73.73 401	99.01 235	96.91 352
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet_0	81.89 21	84.49 372	83.21 375	88.34 383	95.76 362	74.97 406	83.49 402	92.70 362	78.47 396	87.94 397	86.90 404	83.38 330	96.63 397	73.44 402	66.86 408	93.40 395

GG-mvs-BLEND				90.60 373	91.00 407	84.21 360	98.23 45	72.63 413		82.76 404	84.11 405	56.14 404	96.79 394	72.20 403	92.09 394	90.78 402

FPMVS		89.92 344	88.63 352	93.82 322	98.37 186	96.94 46	91.58 361	93.34 354	88.00 337	90.32 382	97.10 249	70.87 387	91.13 406	71.91 404	96.16 367	93.39 396

MVE	73.61 22	86.48 371	85.92 370	88.18 385	96.23 340	85.28 344	81.78 405	75.79 409	86.01 354	82.53 405	91.88 380	92.74 213	87.47 408	71.42 405	94.86 382	91.78 399
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		57.23 376	62.50 379	41.44 393	34.77 416	49.21 417	83.93 401	60.22 415	15.31 409	71.11 409	79.37 406	70.09 390	44.86 412	64.76 406	82.93 406	30.25 408

PAPM		87.64 364	85.84 371	93.04 340	96.54 331	84.99 349	88.42 395	95.57 326	79.52 392	83.82 403	93.05 364	80.57 344	98.41 361	62.29 407	92.79 391	95.71 378

dmvs_testset		87.30 368	86.99 365	88.24 384	96.71 328	77.48 396	94.68 271	86.81 401	92.64 267	89.61 389	87.01 403	85.91 310	93.12 404	61.04 408	88.49 400	94.13 391

DeepMVS_CX				77.17 389	90.94 408	85.28 344		74.08 412	52.51 408	80.87 408	88.03 400	75.25 370	70.63 410	59.23 409	84.94 404	75.62 404

dongtai		63.43 375	63.37 378	63.60 391	83.91 413	53.17 415	85.14 399	43.40 417	77.91 399	80.96 407	79.17 407	36.36 415	77.10 409	37.88 410	45.63 409	60.54 406

kuosan		54.81 377	54.94 380	54.42 392	74.43 414	50.03 416	84.98 400	44.27 416	61.80 407	62.49 411	70.43 408	35.16 416	58.04 411	19.30 411	41.61 410	55.19 407

test123		12.59 379	15.49 382	3.87 394	6.07 417	2.55 419	90.75 378	2.59 419	2.52 412	5.20 414	13.02 411	4.96 417	1.85 414	5.20 412	9.09 411	7.23 409

testmvs		12.33 380	15.23 383	3.64 395	5.77 418	2.23 420	88.99 393	3.62 418	2.30 413	5.29 413	13.09 410	4.52 418	1.95 413	5.16 413	8.32 412	6.75 410

test_blank		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet_test		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

DCPMVS		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

cdsmvs_eth3d_5k		24.22 378	32.30 381	0.00 396	0.00 419	0.00 421	0.00 407	98.10 241	0.00 414	0.00 415	95.06 334	97.54 39	0.00 415	0.00 414	0.00 413	0.00 411

pcd_1.5k_mvsjas		7.98 381	10.65 384	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	95.82 127	0.00 415	0.00 414	0.00 413	0.00 411

sosnet-low-res		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

sosnet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uncertanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

Regformer		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

ab-mvs-re		7.91 382	10.55 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	94.94 336	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

FOURS1					99.59 17	98.20 8	99.03 7	99.25 32	98.96 21	98.87 57

test_one_0601					99.05 103	95.50 99		98.87 114	97.21 88	98.03 144	98.30 131	96.93 71

eth-test2					0.00 419

eth-test					0.00 419

test_241102_ONE					99.22 66	95.35 107		98.83 132	96.04 133	99.08 41	98.13 156	97.87 23	99.33 247

save fliter					98.48 177	94.71 130	94.53 276	98.41 200	95.02 187

test0726					99.24 61	95.51 96	96.89 134	98.89 105	95.92 142	98.64 73	98.31 127	97.06 60

GSMVS																98.06 293

test_part2					99.03 105	96.07 75				98.08 137

sam_mvs1												77.80 354				98.06 293

sam_mvs												77.38 358

MTGPA								98.73 154

test_post											10.87 412	76.83 362	99.07 298

patchmatchnet-post											96.84 266	77.36 359	99.42 212

MTMP							96.55 154	74.60 410

TEST9					97.84 243	95.23 114	93.62 313	98.39 203	86.81 348	93.78 329	95.99 310	94.68 165	99.52 183

test_8					97.81 247	95.07 123	93.54 316	98.38 205	87.04 344	93.71 333	95.96 313	94.58 169	99.52 183

agg_prior					97.80 251	94.96 125		98.36 207		93.49 341			99.53 180

test_prior4						95.38 104	93.61 315

test_prior				97.46 136	97.79 256	94.26 154		98.42 199					99.34 245			98.79 212

新几何2							93.43 318

旧先验1					97.80 251	93.87 165		97.75 263			97.04 253	93.57 194			98.68 268	98.72 222

原ACMM2							92.82 332

test222					98.17 210	93.24 190	92.74 336	97.61 276	75.17 402	94.65 308	96.69 277	90.96 254			98.66 271	97.66 325

segment_acmp												95.34 146

testdata1							92.77 333		93.78 225

test12				97.46 136	97.61 284	94.07 158		97.78 262		93.57 339		93.31 199	99.42 212		98.78 258	98.89 198

plane_prior7					98.70 145	94.67 133

plane_prior6					98.38 185	94.37 147						91.91 242

plane_prior4											96.77 272

plane_prior3						94.51 140			95.29 175	96.16 263

plane_prior2							96.50 156		96.36 116

plane_prior1					98.49 175

plane_prior						94.29 150	95.42 228		94.31 210						98.93 242

n2								0.00 420

nn								0.00 420

door-mid								98.17 231

test11								98.08 243

door								97.81 261

HQP5-MVS						92.47 208

HQP-NCC					97.85 238		94.26 281		93.18 248	92.86 355

ACMP_Plane					97.85 238		94.26 281		93.18 248	92.86 355

HQP4-MVS										92.87 354			99.23 273			99.06 170

HQP3-MVS								98.43 196							98.74 262

HQP2-MVS												90.33 263

NP-MVS					98.14 216	93.72 171					95.08 332

ACMMP++_ref															99.52 130

ACMMP++															99.55 116

Test By Simon												94.51 172

High-resolution multi-view benchmark