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.

DVP-MVS++		99.08 2	98.89 2	99.64 3	99.17 103	99.23 7	99.69 1	98.88 51	97.32 33	99.53 9	99.47 10	97.81 3	99.94 4	98.47 22	99.72 54	99.74 37

FOURS1					99.82 1	98.66 26	99.69 1	98.95 35	97.46 23	99.39 15

CS-MVS		98.44 42	98.49 20	98.31 112	99.08 113	96.73 119	99.67 3	98.47 178	97.17 46	98.94 45	99.10 78	95.73 49	99.13 189	98.71 7	99.49 96	99.09 157

CS-MVS-test		98.49 37	98.50 17	98.46 101	99.20 101	97.05 105	99.64 4	98.50 172	97.45 25	98.88 53	99.14 72	95.25 72	99.15 186	98.83 5	99.56 86	99.20 139

DROMVSNet		98.21 60	98.11 53	98.49 98	98.34 177	97.26 99	99.61 5	98.43 186	96.78 65	98.87 54	98.84 117	93.72 106	99.01 209	98.91 3	99.50 95	99.19 143

RRT_MVS		95.98 158	95.78 152	96.56 234	96.48 303	94.22 240	99.57 6	97.92 270	95.89 102	93.95 253	98.70 132	89.27 189	98.42 274	97.23 93	93.02 267	97.04 241

mvsmamba		96.57 135	96.32 132	97.32 179	96.60 295	96.43 135	99.54 7	97.98 263	96.49 78	95.20 207	98.64 140	90.82 158	98.55 258	97.97 45	93.65 253	96.98 245

HPM-MVS		98.36 48	98.10 54	99.13 57	99.74 8	97.82 77	99.53 8	98.80 91	94.63 166	98.61 74	98.97 97	95.13 77	99.77 105	97.65 72	99.83 11	99.79 13
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MVSFormer		97.57 88	97.49 80	97.84 141	98.07 201	95.76 171	99.47 9	98.40 190	94.98 150	98.79 58	98.83 119	92.34 120	98.41 282	96.91 106	99.59 77	99.34 121

test_djsdf		96.00 157	95.69 161	96.93 203	95.72 331	95.49 181	99.47 9	98.40 190	94.98 150	94.58 221	97.86 216	89.16 193	98.41 282	96.91 106	94.12 240	96.88 260

HPM-MVS_fast		98.38 46	98.13 51	99.12 60	99.75 4	97.86 73	99.44 11	98.82 74	94.46 173	98.94 45	99.20 59	95.16 76	99.74 111	97.58 77	99.85 5	99.77 23

nrg030		96.28 148	95.72 155	97.96 137	96.90 280	98.15 61	99.39 12	98.31 205	95.47 122	94.42 231	98.35 172	92.09 130	98.69 243	97.50 85	89.05 315	97.04 241

APDe-MVS		99.02 4	98.84 4	99.55 9	99.57 35	98.96 16	99.39 12	98.93 39	97.38 30	99.41 13	99.54 1	96.66 17	99.84 57	98.86 4	99.85 5	99.87 1

3Dnovator+	94.38 6	97.43 97	96.78 112	99.38 20	97.83 216	98.52 32	99.37 14	98.71 118	97.09 53	92.99 289	99.13 73	89.36 186	99.89 39	96.97 102	99.57 81	99.71 50

FIs		96.51 137	96.12 139	97.67 160	97.13 267	97.54 87	99.36 15	99.22 15	95.89 102	94.03 251	98.35 172	91.98 133	98.44 272	96.40 136	92.76 270	97.01 243

FC-MVSNet-test		96.42 140	96.05 142	97.53 169	96.95 275	97.27 95	99.36 15	99.23 13	95.83 106	93.93 254	98.37 170	92.00 132	98.32 291	96.02 147	92.72 271	97.00 244

3Dnovator	94.51 5	97.46 92	96.93 105	99.07 63	97.78 218	97.64 82	99.35 17	99.06 23	97.02 55	93.75 264	99.16 68	89.25 190	99.92 25	97.22 94	99.75 42	99.64 76

GeoE		96.58 134	96.07 141	98.10 128	98.35 172	95.89 167	99.34 18	98.12 239	93.12 234	96.09 193	98.87 113	89.71 179	98.97 211	92.95 244	98.08 166	99.43 115

canonicalmvs		97.67 79	97.23 92	98.98 68	98.70 147	98.38 40	99.34 18	98.39 192	96.76 67	97.67 131	97.40 257	92.26 123	99.49 155	98.28 35	96.28 216	99.08 161

CP-MVS		98.57 27	98.36 27	99.19 46	99.66 28	97.86 73	99.34 18	98.87 58	95.96 100	98.60 75	99.13 73	96.05 36	99.94 4	97.77 62	99.86 1	99.77 23

EPP-MVSNet		97.46 92	97.28 90	97.99 134	98.64 153	95.38 184	99.33 21	98.31 205	93.61 214	97.19 147	99.07 87	94.05 101	99.23 177	96.89 110	98.43 154	99.37 120

XVS		98.70 10	98.49 20	99.34 26	99.70 24	98.35 48	99.29 22	98.88 51	97.40 27	98.46 79	99.20 59	95.90 44	99.89 39	97.85 56	99.74 45	99.78 16

X-MVStestdata		94.06 276	92.30 296	99.34 26	99.70 24	98.35 48	99.29 22	98.88 51	97.40 27	98.46 79	43.50 376	95.90 44	99.89 39	97.85 56	99.74 45	99.78 16

tttt0517		96.07 154	95.51 166	97.78 148	98.41 168	94.84 210	99.28 24	94.33 364	94.26 178	97.64 135	98.64 140	84.05 298	99.47 161	95.34 169	97.60 184	99.03 164

mPP-MVS		98.51 36	98.26 42	99.25 42	99.75 4	98.04 65	99.28 24	98.81 80	96.24 87	98.35 89	99.23 52	95.46 57	99.94 4	97.42 87	99.81 12	99.77 23

MSP-MVS		98.74 9	98.55 13	99.29 34	99.75 4	98.23 54	99.26 26	98.88 51	97.52 17	99.41 13	98.78 124	96.00 38	99.79 96	97.79 61	99.59 77	99.85 4
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
v7n		94.19 265	93.43 276	96.47 245	95.90 326	94.38 233	99.26 26	98.34 201	91.99 272	92.76 294	97.13 271	88.31 215	98.52 262	89.48 314	87.70 330	96.52 308

WR-MVS_H		95.05 213	94.46 217	96.81 212	96.86 282	95.82 169	99.24 28	99.24 11	93.87 194	92.53 302	96.84 304	90.37 168	98.24 301	93.24 234	87.93 328	96.38 320

HFP-MVS		98.63 17	98.40 23	99.32 31	99.72 13	98.29 51	99.23 29	98.96 33	96.10 95	98.94 45	99.17 63	96.06 34	99.92 25	97.62 74	99.78 27	99.75 32

region2R		98.61 18	98.38 25	99.29 34	99.74 8	98.16 60	99.23 29	98.93 39	96.15 90	98.94 45	99.17 63	95.91 43	99.94 4	97.55 81	99.79 23	99.78 16

ACMMPR		98.59 21	98.36 27	99.29 34	99.74 8	98.15 61	99.23 29	98.95 35	96.10 95	98.93 50	99.19 62	95.70 50	99.94 4	97.62 74	99.79 23	99.78 16

QAPM		96.29 146	95.40 167	98.96 70	97.85 215	97.60 85	99.23 29	98.93 39	89.76 326	93.11 286	99.02 90	89.11 195	99.93 19	91.99 271	99.62 72	99.34 121

MP-MVS		98.33 54	98.01 58	99.28 38	99.75 4	98.18 58	99.22 33	98.79 96	96.13 92	97.92 117	99.23 52	94.54 90	99.94 4	96.74 125	99.78 27	99.73 42
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
Vis-MVSNet		97.42 98	97.11 96	98.34 110	98.66 151	96.23 144	99.22 33	99.00 28	96.63 73	98.04 101	99.21 55	88.05 223	99.35 168	96.01 148	99.21 115	99.45 113
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CSCG		97.85 72	97.74 68	98.20 120	99.67 27	95.16 193	99.22 33	99.32 7	93.04 236	97.02 156	98.92 109	95.36 64	99.91 34	97.43 86	99.64 68	99.52 94

OpenMVS	93.04 13	95.83 168	95.00 191	98.32 111	97.18 264	97.32 93	99.21 36	98.97 31	89.96 322	91.14 323	99.05 89	86.64 250	99.92 25	93.38 229	99.47 99	97.73 224

DTE-MVSNet		93.98 278	93.26 281	96.14 264	96.06 321	94.39 232	99.20 37	98.86 64	93.06 235	91.78 317	97.81 224	85.87 264	97.58 336	90.53 294	86.17 345	96.46 317

Vis-MVSNet (Re-imp)		96.87 123	96.55 124	97.83 142	98.73 142	95.46 182	99.20 37	98.30 211	94.96 152	96.60 175	98.87 113	90.05 173	98.59 254	93.67 223	98.60 143	99.46 111

ZNCC-MVS		98.49 37	98.20 49	99.35 25	99.73 12	98.39 39	99.19 39	98.86 64	95.77 108	98.31 92	99.10 78	95.46 57	99.93 19	97.57 80	99.81 12	99.74 37

IS-MVSNet		97.22 107	96.88 107	98.25 117	98.85 135	96.36 139	99.19 39	97.97 265	95.39 126	97.23 146	98.99 96	91.11 154	98.93 220	94.60 191	98.59 144	99.47 107

PEN-MVS		94.42 252	93.73 263	96.49 243	96.28 312	94.84 210	99.17 41	99.00 28	93.51 216	92.23 311	97.83 222	86.10 260	97.90 325	92.55 257	86.92 340	96.74 276

PS-MVSNAJss		96.43 139	96.26 135	96.92 206	95.84 329	95.08 198	99.16 42	98.50 172	95.87 105	93.84 260	98.34 176	94.51 91	98.61 251	96.88 113	93.45 260	97.06 240

dcpmvs_2		98.08 61	98.59 10	96.56 234	99.57 35	90.34 320	99.15 43	98.38 195	96.82 64	99.29 20	99.49 7	95.78 48	99.57 140	98.94 2	99.86 1	99.77 23

APD-MVS_3200maxsize		98.53 35	98.33 37	99.15 56	99.50 45	97.92 72	99.15 43	98.81 80	96.24 87	99.20 26	99.37 26	95.30 68	99.80 84	97.73 64	99.67 60	99.72 46

TSAR-MVS + MP.		98.78 7	98.62 9	99.24 43	99.69 26	98.28 53	99.14 45	98.66 136	96.84 62	99.56 6	99.31 39	96.34 23	99.70 119	98.32 33	99.73 47	99.73 42
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
anonymousdsp		95.42 189	94.91 196	96.94 202	95.10 344	95.90 166	99.14 45	98.41 188	93.75 199	93.16 282	97.46 251	87.50 237	98.41 282	95.63 164	94.03 242	96.50 313

jajsoiax		95.45 187	95.03 190	96.73 215	95.42 342	94.63 219	99.14 45	98.52 164	95.74 109	93.22 280	98.36 171	83.87 303	98.65 249	96.95 105	94.04 241	96.91 256

PS-CasMVS		94.67 235	93.99 243	96.71 216	96.68 292	95.26 190	99.13 48	99.03 26	93.68 209	92.33 309	97.95 208	85.35 274	98.10 309	93.59 225	88.16 327	96.79 271

abl_6		98.30 57	98.03 57	99.13 57	99.56 37	97.76 80	99.13 48	98.82 74	96.14 91	99.26 22	99.37 26	93.33 109	99.93 19	96.96 104	99.67 60	99.69 57

bld_raw_dy_0_64		95.74 172	95.31 178	97.03 195	96.35 309	95.76 171	99.12 50	97.37 310	95.97 99	94.70 219	98.48 156	85.80 265	98.49 264	96.55 129	93.48 257	96.84 267

CPTT-MVS		97.72 77	97.32 89	98.92 72	99.64 30	97.10 104	99.12 50	98.81 80	92.34 260	98.09 97	99.08 86	93.01 113	99.92 25	96.06 145	99.77 30	99.75 32

SR-MVS-dyc-post		98.54 33	98.35 29	99.13 57	99.49 49	97.86 73	99.11 52	98.80 91	96.49 78	99.17 30	99.35 32	95.34 65	99.82 68	97.72 65	99.65 64	99.71 50

RE-MVS-def			98.34 33		99.49 49	97.86 73	99.11 52	98.80 91	96.49 78	99.17 30	99.35 32	95.29 69		97.72 65	99.65 64	99.71 50

CP-MVSNet		94.94 222	94.30 225	96.83 210	96.72 290	95.56 177	99.11 52	98.95 35	93.89 192	92.42 308	97.90 212	87.19 241	98.12 308	94.32 201	88.21 325	96.82 270

SteuartSystems-ACMMP		98.90 6	98.75 6	99.36 24	99.22 98	98.43 38	99.10 55	98.87 58	97.38 30	99.35 17	99.40 17	97.78 5	99.87 48	97.77 62	99.85 5	99.78 16
Skip Steuart: Steuart Systems R&D Blog.
test1172		98.56 29	98.35 29	99.16 53	99.53 39	97.94 71	99.09 56	98.83 72	96.52 77	99.05 38	99.34 35	95.34 65	99.82 68	97.86 55	99.64 68	99.73 42

SR-MVS		98.57 27	98.35 29	99.24 43	99.53 39	98.18 58	99.09 56	98.82 74	96.58 74	99.10 35	99.32 37	95.39 61	99.82 68	97.70 70	99.63 70	99.72 46

GST-MVS		98.43 43	98.12 52	99.34 26	99.72 13	98.38 40	99.09 56	98.82 74	95.71 111	98.73 64	99.06 88	95.27 70	99.93 19	97.07 99	99.63 70	99.72 46

iter_conf_final		96.42 140	96.12 139	97.34 178	98.46 165	96.55 130	99.08 59	98.06 257	96.03 97	95.63 201	98.46 160	87.72 230	98.59 254	97.84 58	93.80 249	96.87 262

K. test v3		92.55 300	91.91 302	94.48 319	95.64 333	89.24 334	99.07 60	94.88 358	94.04 183	86.78 351	97.59 243	77.64 344	97.64 334	92.08 266	89.43 310	96.57 298

test2506		94.44 251	93.91 248	96.04 267	99.02 118	88.99 340	99.06 61	79.47 383	96.96 58	98.36 87	99.26 47	77.21 346	99.52 153	96.78 123	99.04 121	99.59 87

test0726					99.72 13	99.25 2	99.06 61	98.88 51	97.62 12	99.56 6	99.50 5	97.42 9

v8		94.47 249	93.77 259	96.57 233	96.36 308	94.83 212	99.05 63	98.19 224	91.92 274	93.16 282	96.97 292	88.82 206	98.48 265	91.69 278	87.79 329	96.39 319

test1111		95.94 162	95.78 152	96.41 251	98.99 124	90.12 322	99.04 64	92.45 372	96.99 57	98.03 102	99.27 46	81.40 315	99.48 159	96.87 116	99.04 121	99.63 79

SF-MVS		98.59 21	98.32 38	99.41 19	99.54 38	98.71 22	99.04 64	98.81 80	95.12 142	99.32 18	99.39 18	96.22 24	99.84 57	97.72 65	99.73 47	99.67 67

PHI-MVS		98.34 52	98.06 55	99.18 50	99.15 109	98.12 63	99.04 64	99.09 21	93.32 224	98.83 57	99.10 78	96.54 20	99.83 60	97.70 70	99.76 36	99.59 87

ECVR-MVS		95.95 160	95.71 158	96.65 221	99.02 118	90.86 309	99.03 67	91.80 373	96.96 58	98.10 96	99.26 47	81.31 316	99.51 154	96.90 109	99.04 121	99.59 87

test_part1		94.82 225	93.82 254	97.82 144	98.84 136	97.82 77	99.03 67	98.81 80	92.31 264	92.51 304	97.89 214	81.96 311	98.67 247	94.80 186	88.24 324	96.98 245

TranMVSNet+NR-MVSNet		95.14 208	94.48 215	97.11 191	96.45 305	96.36 139	99.03 67	99.03 26	95.04 148	93.58 267	97.93 210	88.27 216	98.03 316	94.13 207	86.90 341	96.95 250

ACMMP		98.23 58	97.95 61	99.09 62	99.74 8	97.62 84	99.03 67	99.41 6	95.98 98	97.60 138	99.36 30	94.45 95	99.93 19	97.14 96	98.85 133	99.70 54
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
SED-MVS		99.09 1	98.91 1	99.63 4	99.71 21	99.24 5	99.02 71	98.87 58	97.65 10	99.73 1	99.48 8	97.53 7	99.94 4	98.43 26	99.81 12	99.70 54

OPU-MVS				99.37 23	99.24 96	99.05 14	99.02 71				99.16 68	97.81 3	99.37 167	97.24 92	99.73 47	99.70 54

EIA-MVS		97.75 75	97.58 72	98.27 114	98.38 169	96.44 134	99.01 73	98.60 146	95.88 104	97.26 145	97.53 248	94.97 81	99.33 170	97.38 89	99.20 116	99.05 163

Anonymous20231211		94.10 272	93.26 281	96.61 227	99.11 112	94.28 235	99.01 73	98.88 51	86.43 347	92.81 292	97.57 245	81.66 314	98.68 246	94.83 183	89.02 317	96.88 260

mvs_tets		95.41 191	95.00 191	96.65 221	95.58 335	94.42 230	99.00 75	98.55 158	95.73 110	93.21 281	98.38 169	83.45 307	98.63 250	97.09 98	94.00 243	96.91 256

baseline		97.64 81	97.44 84	98.25 117	98.35 172	96.20 145	99.00 75	98.32 203	96.33 86	98.03 102	99.17 63	91.35 148	99.16 183	98.10 39	98.29 161	99.39 118

v10		94.29 259	93.55 271	96.51 242	96.39 307	94.80 214	98.99 77	98.19 224	91.35 292	93.02 288	96.99 290	88.09 221	98.41 282	90.50 295	88.41 323	96.33 323

PGM-MVS		98.49 37	98.23 47	99.27 41	99.72 13	98.08 64	98.99 77	99.49 5	95.43 124	99.03 39	99.32 37	95.56 53	99.94 4	96.80 121	99.77 30	99.78 16

LPG-MVS_test		95.62 180	95.34 173	96.47 245	97.46 242	93.54 259	98.99 77	98.54 160	94.67 163	94.36 233	98.77 126	85.39 272	99.11 193	95.71 160	94.15 238	96.76 274

#test#		98.54 33	98.27 41	99.32 31	99.72 13	98.29 51	98.98 80	98.96 33	95.65 115	98.94 45	99.17 63	96.06 34	99.92 25	97.21 95	99.78 27	99.75 32

DVP-MVS		99.03 3	98.83 5	99.63 4	99.72 13	99.25 2	98.97 81	98.58 153	97.62 12	99.45 11	99.46 13	97.42 9	99.94 4	98.47 22	99.81 12	99.69 57
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				99.71 1	99.72 13	99.35 1	98.97 81	98.88 51					99.94 4	98.47 22	99.81 12	99.84 6

tfpnnormal		93.66 281	92.70 290	96.55 239	96.94 276	95.94 160	98.97 81	99.19 16	91.04 304	91.38 321	97.34 258	84.94 281	98.61 251	85.45 342	89.02 317	95.11 348

V42		94.78 228	94.14 233	96.70 218	96.33 311	95.22 191	98.97 81	98.09 249	92.32 262	94.31 236	97.06 282	88.39 214	98.55 258	92.90 246	88.87 319	96.34 321

SMA-MVS		98.58 24	98.25 43	99.56 8	99.51 43	99.04 15	98.95 85	98.80 91	93.67 211	99.37 16	99.52 3	96.52 21	99.89 39	98.06 41	99.81 12	99.76 30
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
pm-mvs1		93.94 279	93.06 283	96.59 230	96.49 302	95.16 193	98.95 85	98.03 260	92.32 262	91.08 324	97.84 219	84.54 289	98.41 282	92.16 264	86.13 347	96.19 328

Anonymous20240521		91.18 310	90.44 311	93.42 330	93.70 359	88.47 347	98.94 87	97.56 289	88.46 338	89.56 338	95.08 347	77.15 348	96.97 346	83.92 350	89.55 307	94.82 353

VPA-MVSNet		95.75 171	95.11 187	97.69 158	97.24 256	97.27 95	98.94 87	99.23 13	95.13 141	95.51 203	97.32 260	85.73 266	98.91 222	97.33 91	89.55 307	96.89 259

LS3D		97.16 112	96.66 121	98.68 82	98.53 161	97.19 102	98.93 89	98.90 46	92.83 245	95.99 197	99.37 26	92.12 129	99.87 48	93.67 223	99.57 81	98.97 170

ACMM	93.85 9	95.69 177	95.38 171	96.61 227	97.61 229	93.84 248	98.91 90	98.44 183	95.25 136	94.28 237	98.47 158	86.04 263	99.12 191	95.50 167	93.95 245	96.87 262
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MTAPA		98.58 24	98.29 40	99.46 15	99.76 2	98.64 27	98.90 91	98.74 108	97.27 40	98.02 104	99.39 18	94.81 84	99.96 2	97.91 49	99.79 23	99.77 23

SD-MVS		98.64 15	98.68 7	98.53 94	99.33 69	98.36 47	98.90 91	98.85 68	97.28 36	99.72 3	99.39 18	96.63 19	97.60 335	98.17 36	99.85 5	99.64 76
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
TransMVSNet (Re)		92.67 299	91.51 304	96.15 263	96.58 297	94.65 217	98.90 91	96.73 339	90.86 307	89.46 339	97.86 216	85.62 268	98.09 311	86.45 334	81.12 356	95.71 338

EPNet		97.28 105	96.87 108	98.51 95	94.98 345	96.14 148	98.90 91	97.02 326	98.28 1	95.99 197	99.11 76	91.36 147	99.89 39	96.98 101	99.19 117	99.50 100
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MTMP							98.89 95	94.14 367

UA-Net		97.96 64	97.62 70	98.98 68	98.86 133	97.47 89	98.89 95	99.08 22	96.67 71	98.72 65	99.54 1	93.15 112	99.81 75	94.87 181	98.83 134	99.65 73

OurMVSNet-221017-0		94.21 263	94.00 241	94.85 307	95.60 334	89.22 335	98.89 95	97.43 305	95.29 133	92.18 312	98.52 154	82.86 308	98.59 254	93.46 228	91.76 279	96.74 276

thisisatest0530		96.01 156	95.36 172	97.97 135	98.38 169	95.52 180	98.88 98	94.19 366	94.04 183	97.64 135	98.31 179	83.82 305	99.46 162	95.29 173	97.70 181	98.93 174

iter_conf05		96.13 153	95.79 151	97.15 187	98.16 196	95.99 151	98.88 98	97.98 263	95.91 101	95.58 202	98.46 160	85.53 270	98.59 254	97.88 53	93.75 250	96.86 265

UGNet		96.78 126	96.30 133	98.19 122	98.24 184	95.89 167	98.88 98	98.93 39	97.39 29	96.81 167	97.84 219	82.60 309	99.90 37	96.53 130	99.49 96	98.79 181
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
Anonymous20240529		95.10 210	94.22 227	97.75 152	99.01 120	94.26 237	98.87 101	98.83 72	85.79 353	96.64 172	98.97 97	78.73 333	99.85 54	96.27 138	94.89 229	99.12 154

thres100view900		95.38 192	94.70 205	97.41 173	98.98 125	94.92 207	98.87 101	96.90 332	95.38 127	96.61 174	96.88 300	84.29 291	99.56 143	88.11 323	96.29 213	97.76 221

XXY-MVS		95.20 205	94.45 219	97.46 170	96.75 288	96.56 128	98.86 103	98.65 140	93.30 226	93.27 279	98.27 184	84.85 283	98.87 229	94.82 184	91.26 287	96.96 248

VDDNet		95.36 195	94.53 212	97.86 140	98.10 200	95.13 196	98.85 104	97.75 278	90.46 312	98.36 87	99.39 18	73.27 361	99.64 130	97.98 44	96.58 203	98.81 180

thres600view7		95.49 184	94.77 201	97.67 160	98.98 125	95.02 199	98.85 104	96.90 332	95.38 127	96.63 173	96.90 299	84.29 291	99.59 138	88.65 322	96.33 211	98.40 203

114514_t		96.93 120	96.27 134	98.92 72	99.50 45	97.63 83	98.85 104	98.90 46	84.80 356	97.77 122	99.11 76	92.84 114	99.66 127	94.85 182	99.77 30	99.47 107

LFMVS		95.86 166	94.98 193	98.47 100	98.87 132	96.32 141	98.84 107	96.02 346	93.40 221	98.62 73	99.20 59	74.99 355	99.63 133	97.72 65	97.20 190	99.46 111

testtj		98.33 54	97.95 61	99.47 14	99.49 49	98.70 23	98.83 108	98.86 64	95.48 121	98.91 52	99.17 63	95.48 56	99.93 19	95.80 155	99.53 92	99.76 30

alignmvs		97.56 89	97.07 99	99.01 65	98.66 151	98.37 46	98.83 108	98.06 257	96.74 68	98.00 110	97.65 237	90.80 161	99.48 159	98.37 31	96.56 204	99.19 143

DeepC-MVS	95.98 3	97.88 70	97.58 72	98.77 78	99.25 90	96.93 110	98.83 108	98.75 106	96.96 58	96.89 163	99.50 5	90.46 167	99.87 48	97.84 58	99.76 36	99.52 94
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMMP_NAP		98.61 18	98.30 39	99.55 9	99.62 32	98.95 17	98.82 111	98.81 80	95.80 107	99.16 32	99.47 10	95.37 63	99.92 25	97.89 52	99.75 42	99.79 13

casdiffmvs		97.63 82	97.41 85	98.28 113	98.33 179	96.14 148	98.82 111	98.32 203	96.38 84	97.95 112	99.21 55	91.23 152	99.23 177	98.12 38	98.37 155	99.48 105

GBi-Net		94.49 247	93.80 256	96.56 234	98.21 187	95.00 200	98.82 111	98.18 227	92.46 253	94.09 247	97.07 279	81.16 317	97.95 321	92.08 266	92.14 274	96.72 279

test1		94.49 247	93.80 256	96.56 234	98.21 187	95.00 200	98.82 111	98.18 227	92.46 253	94.09 247	97.07 279	81.16 317	97.95 321	92.08 266	92.14 274	96.72 279

FMVSNet1		93.19 293	92.07 298	96.56 234	97.54 236	95.00 200	98.82 111	98.18 227	90.38 315	92.27 310	97.07 279	73.68 360	97.95 321	89.36 316	91.30 285	96.72 279

API-MVS		97.41 99	97.25 91	97.91 138	98.70 147	96.80 115	98.82 111	98.69 122	94.53 168	98.11 95	98.28 181	94.50 94	99.57 140	94.12 208	99.49 96	97.37 234

ACMH	92.88 16	94.55 242	93.95 245	96.34 257	97.63 228	93.26 272	98.81 117	98.49 177	93.43 220	89.74 335	98.53 151	81.91 312	99.08 198	93.69 220	93.30 264	96.70 283
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Effi-MVS+-dtu		96.29 146	96.56 123	95.51 286	97.89 213	90.22 321	98.80 118	98.10 244	96.57 75	96.45 186	96.66 310	90.81 159	98.91 222	95.72 158	97.99 168	97.40 231

HQP_MVS		96.14 152	95.90 148	96.85 209	97.42 247	94.60 224	98.80 118	98.56 156	97.28 36	95.34 204	98.28 181	87.09 242	99.03 204	96.07 142	94.27 232	96.92 251

plane_prior2							98.80 118		97.28 36

APD-MVS		98.35 50	98.00 59	99.42 18	99.51 43	98.72 21	98.80 118	98.82 74	94.52 170	99.23 24	99.25 50	95.54 55	99.80 84	96.52 131	99.77 30	99.74 37
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
UniMVSNet (Re)		95.78 170	95.19 183	97.58 166	96.99 274	97.47 89	98.79 122	99.18 17	95.60 116	93.92 255	97.04 285	91.68 138	98.48 265	95.80 155	87.66 331	96.79 271

FMVSNet2		94.47 249	93.61 269	97.04 194	98.21 187	96.43 135	98.79 122	98.27 214	92.46 253	93.50 273	97.09 276	81.16 317	98.00 319	91.09 284	91.93 277	96.70 283

testgi		93.06 295	92.45 294	94.88 306	96.43 306	89.90 323	98.75 124	97.54 295	95.60 116	91.63 320	97.91 211	74.46 358	97.02 345	86.10 336	93.67 251	97.72 225

LCM-MVSNet-Re		95.22 203	95.32 176	94.91 304	98.18 193	87.85 355	98.75 124	95.66 352	95.11 143	88.96 341	96.85 303	90.26 172	97.65 333	95.65 163	98.44 152	99.22 138

SixPastTwentyTwo		93.34 287	92.86 286	94.75 311	95.67 332	89.41 333	98.75 124	96.67 343	93.89 192	90.15 333	98.25 186	80.87 321	98.27 300	90.90 289	90.64 293	96.57 298

UniMVSNet_ETH3D		94.24 262	93.33 278	96.97 200	97.19 263	93.38 268	98.74 127	98.57 154	91.21 301	93.81 261	98.58 147	72.85 362	98.77 240	95.05 179	93.93 246	98.77 184

MVS_Test		97.28 105	97.00 102	98.13 125	98.33 179	95.97 157	98.74 127	98.07 252	94.27 177	98.44 83	98.07 197	92.48 118	99.26 173	96.43 135	98.19 162	99.16 149

UniMVSNet_NR-MVSNet		95.71 174	95.15 184	97.40 175	96.84 283	96.97 108	98.74 127	99.24 11	95.16 140	93.88 257	97.72 230	91.68 138	98.31 293	95.81 153	87.25 336	96.92 251

NR-MVSNet		94.98 218	94.16 231	97.44 171	96.53 299	97.22 101	98.74 127	98.95 35	94.96 152	89.25 340	97.69 233	89.32 187	98.18 303	94.59 193	87.40 334	96.92 251

ETV-MVS		97.96 64	97.81 65	98.40 107	98.42 167	97.27 95	98.73 131	98.55 158	96.84 62	98.38 86	97.44 254	95.39 61	99.35 168	97.62 74	98.89 129	98.58 198

baseline1		95.84 167	95.12 186	98.01 133	98.49 164	95.98 152	98.73 131	97.03 324	95.37 129	96.22 190	98.19 190	89.96 175	99.16 183	94.60 191	87.48 332	98.90 176

MVSTER		96.06 155	95.72 155	97.08 193	98.23 185	95.93 163	98.73 131	98.27 214	94.86 156	95.07 208	98.09 196	88.21 217	98.54 260	96.59 127	93.46 258	96.79 271

ACMP	93.49 10	95.34 197	94.98 193	96.43 250	97.67 225	93.48 263	98.73 131	98.44 183	94.94 155	92.53 302	98.53 151	84.50 290	99.14 188	95.48 168	94.00 243	96.66 289
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HPM-MVS++		98.58 24	98.25 43	99.55 9	99.50 45	99.08 11	98.72 135	98.66 136	97.51 18	98.15 93	98.83 119	95.70 50	99.92 25	97.53 83	99.67 60	99.66 71

9.14			98.06 55		99.47 52		98.71 136	98.82 74	94.36 175	99.16 32	99.29 43	96.05 36	99.81 75	97.00 100	99.71 56

VPNet		94.99 216	94.19 229	97.40 175	97.16 265	96.57 127	98.71 136	98.97 31	95.67 113	94.84 213	98.24 187	80.36 325	98.67 247	96.46 132	87.32 335	96.96 248

MSLP-MVS++		98.56 29	98.57 11	98.55 90	99.26 89	96.80 115	98.71 136	99.05 25	97.28 36	98.84 55	99.28 44	96.47 22	99.40 165	98.52 20	99.70 57	99.47 107

ACMH+	92.99 14	94.30 258	93.77 259	95.88 277	97.81 217	92.04 289	98.71 136	98.37 196	93.99 188	90.60 329	98.47 158	80.86 322	99.05 200	92.75 250	92.40 273	96.55 302

Anonymous202405211		95.28 200	94.49 214	97.67 160	99.00 121	93.75 252	98.70 140	97.04 323	90.66 308	96.49 183	98.80 122	78.13 338	99.83 60	96.21 141	95.36 228	99.44 114

DP-MVS		96.59 132	95.93 147	98.57 88	99.34 66	96.19 147	98.70 140	98.39 192	89.45 331	94.52 223	99.35 32	91.85 135	99.85 54	92.89 248	98.88 130	99.68 63

Fast-Effi-MVS+-dtu		95.87 165	95.85 149	95.91 274	97.74 222	91.74 295	98.69 142	98.15 235	95.56 118	94.92 211	97.68 236	88.98 201	98.79 238	93.19 236	97.78 177	97.20 238

tfpn200view9		95.32 199	94.62 208	97.43 172	98.94 127	94.98 203	98.68 143	96.93 330	95.33 130	96.55 178	96.53 316	84.23 294	99.56 143	88.11 323	96.29 213	97.76 221

VDD-MVS		95.82 169	95.23 181	97.61 165	98.84 136	93.98 244	98.68 143	97.40 307	95.02 149	97.95 112	99.34 35	74.37 359	99.78 100	98.64 8	96.80 196	99.08 161

thres400		95.38 192	94.62 208	97.65 163	98.94 127	94.98 203	98.68 143	96.93 330	95.33 130	96.55 178	96.53 316	84.23 294	99.56 143	88.11 323	96.29 213	98.40 203

ETH3D-3000-0.1		98.35 50	98.00 59	99.38 20	99.47 52	98.68 25	98.67 146	98.84 69	94.66 165	99.11 34	99.25 50	95.46 57	99.81 75	96.80 121	99.73 47	99.63 79

pmmvs6		91.77 305	90.63 309	95.17 297	94.69 352	91.24 305	98.67 146	97.92 270	86.14 349	89.62 336	97.56 247	75.79 352	98.34 289	90.75 292	84.56 349	95.94 334

v2v482		94.69 230	94.03 237	96.65 221	96.17 316	94.79 215	98.67 146	98.08 250	92.72 246	94.00 252	97.16 270	87.69 234	98.45 270	92.91 245	88.87 319	96.72 279

DU-MVS		95.42 189	94.76 202	97.40 175	96.53 299	96.97 108	98.66 149	98.99 30	95.43 124	93.88 257	97.69 233	88.57 209	98.31 293	95.81 153	87.25 336	96.92 251

MAR-MVS		96.91 121	96.40 129	98.45 102	98.69 149	96.90 112	98.66 149	98.68 125	92.40 259	97.07 153	97.96 207	91.54 144	99.75 109	93.68 221	98.92 127	98.69 188
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
patch_mono-2		98.36 48	98.87 3	96.82 211	99.53 39	90.68 314	98.64 151	99.29 8	97.88 5	99.19 29	99.52 3	96.80 15	99.97 1	99.11 1	99.86 1	99.82 10

h-mvs33		96.17 151	95.62 164	97.81 146	99.03 117	94.45 228	98.64 151	98.75 106	97.48 20	98.67 67	98.72 131	89.76 177	99.86 53	97.95 46	81.59 355	99.11 155

VNet		97.79 74	97.40 86	98.96 70	98.88 131	97.55 86	98.63 153	98.93 39	96.74 68	99.02 40	98.84 117	90.33 170	99.83 60	98.53 14	96.66 200	99.50 100

PVSNet_Blended_VisFu		97.70 78	97.46 82	98.44 103	99.27 87	95.91 165	98.63 153	99.16 18	94.48 172	97.67 131	98.88 112	92.80 115	99.91 34	97.11 97	99.12 119	99.50 100

PAPM_NR		97.46 92	97.11 96	98.50 96	99.50 45	96.41 137	98.63 153	98.60 146	95.18 139	97.06 154	98.06 198	94.26 99	99.57 140	93.80 219	98.87 132	99.52 94

Baseline_NR-MVSNet		94.35 255	93.81 255	95.96 272	96.20 314	94.05 243	98.61 156	96.67 343	91.44 288	93.85 259	97.60 242	88.57 209	98.14 306	94.39 197	86.93 339	95.68 339

v1144		94.59 240	93.92 246	96.60 229	96.21 313	94.78 216	98.59 157	98.14 237	91.86 277	94.21 242	97.02 287	87.97 224	98.41 282	91.72 277	89.57 305	96.61 293

AllTest		95.24 202	94.65 207	96.99 197	99.25 90	93.21 274	98.59 157	98.18 227	91.36 290	93.52 270	98.77 126	84.67 286	99.72 113	89.70 309	97.87 173	98.02 216

Fast-Effi-MVS+		96.28 148	95.70 160	98.03 132	98.29 183	95.97 157	98.58 159	98.25 219	91.74 278	95.29 206	97.23 266	91.03 157	99.15 186	92.90 246	97.96 170	98.97 170

Anonymous20231206		91.66 306	91.10 306	93.33 333	94.02 358	87.35 357	98.58 159	97.26 316	90.48 311	90.16 332	96.31 321	83.83 304	96.53 356	79.36 362	89.90 301	96.12 329

v144192		94.39 254	93.70 265	96.48 244	96.06 321	94.35 234	98.58 159	98.16 234	91.45 287	94.33 235	97.02 287	87.50 237	98.45 270	91.08 285	89.11 314	96.63 291

v148		94.29 259	93.76 261	95.91 274	96.10 319	92.93 279	98.58 159	97.97 265	92.59 251	93.47 274	96.95 296	88.53 212	98.32 291	92.56 256	87.06 338	96.49 314

COLMAP_ROB	93.27 12	95.33 198	94.87 199	96.71 216	99.29 82	93.24 273	98.58 159	98.11 242	89.92 323	93.57 268	99.10 78	86.37 256	99.79 96	90.78 291	98.10 165	97.09 239
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
mvs-test1		96.60 130	96.68 120	96.37 254	97.89 213	91.81 291	98.56 164	98.10 244	96.57 75	96.52 182	97.94 209	90.81 159	99.45 163	95.72 158	98.01 167	97.86 220

FMVSNet3		94.97 219	94.26 226	97.11 191	98.18 193	96.62 122	98.56 164	98.26 218	93.67 211	94.09 247	97.10 272	84.25 293	98.01 317	92.08 266	92.14 274	96.70 283

zzz-MVS		98.55 31	98.25 43	99.46 15	99.76 2	98.64 27	98.55 166	98.74 108	97.27 40	98.02 104	99.39 18	94.81 84	99.96 2	97.91 49	99.79 23	99.77 23

F-COLMAP		97.09 116	96.80 109	97.97 135	99.45 59	94.95 206	98.55 166	98.62 145	93.02 237	96.17 192	98.58 147	94.01 102	99.81 75	93.95 214	98.90 128	99.14 152

v1921920		94.20 264	93.47 275	96.40 253	95.98 324	94.08 242	98.52 168	98.15 235	91.33 293	94.25 239	97.20 269	86.41 255	98.42 274	90.04 303	89.39 311	96.69 288

EU-MVSNet		93.66 281	94.14 233	92.25 342	95.96 325	83.38 365	98.52 168	98.12 239	94.69 161	92.61 299	98.13 194	87.36 240	96.39 358	91.82 274	90.00 300	96.98 245

TAMVS		97.02 117	96.79 111	97.70 157	98.06 203	95.31 189	98.52 168	98.31 205	93.95 190	97.05 155	98.61 142	93.49 108	98.52 262	95.33 170	97.81 175	99.29 132

LTVRE_ROB	92.95 15	94.60 238	93.90 249	96.68 220	97.41 250	94.42 230	98.52 168	98.59 148	91.69 281	91.21 322	98.35 172	84.87 282	99.04 203	91.06 286	93.44 261	96.60 294
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
TDRefinement		91.06 312	89.68 317	95.21 295	85.35 374	91.49 300	98.51 172	97.07 321	91.47 286	88.83 344	97.84 219	77.31 345	99.09 197	92.79 249	77.98 362	95.04 350

v1192		94.32 257	93.58 270	96.53 240	96.10 319	94.45 228	98.50 173	98.17 232	91.54 285	94.19 243	97.06 282	86.95 246	98.43 273	90.14 298	89.57 305	96.70 283

test_0402		91.32 308	90.27 313	94.48 319	96.60 295	91.12 306	98.50 173	97.22 317	86.10 350	88.30 346	96.98 291	77.65 343	97.99 320	78.13 366	92.94 269	94.34 355

DeepC-MVS_fast	96.70 1	98.55 31	98.34 33	99.18 50	99.25 90	98.04 65	98.50 173	98.78 99	97.72 7	98.92 51	99.28 44	95.27 70	99.82 68	97.55 81	99.77 30	99.69 57
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CNVR-MVS		98.78 7	98.56 12	99.45 17	99.32 72	98.87 19	98.47 176	98.81 80	97.72 7	98.76 61	99.16 68	97.05 13	99.78 100	98.06 41	99.66 63	99.69 57

test_yl		97.22 107	96.78 112	98.54 92	98.73 142	96.60 125	98.45 177	98.31 205	94.70 159	98.02 104	98.42 164	90.80 161	99.70 119	96.81 119	96.79 197	99.34 121

DCV-MVSNet		97.22 107	96.78 112	98.54 92	98.73 142	96.60 125	98.45 177	98.31 205	94.70 159	98.02 104	98.42 164	90.80 161	99.70 119	96.81 119	96.79 197	99.34 121

NCCC		98.61 18	98.35 29	99.38 20	99.28 86	98.61 29	98.45 177	98.76 103	97.82 6	98.45 82	98.93 107	96.65 18	99.83 60	97.38 89	99.41 106	99.71 50

v1240		94.06 276	93.29 280	96.34 257	96.03 323	93.90 246	98.44 180	98.17 232	91.18 302	94.13 246	97.01 289	86.05 261	98.42 274	89.13 319	89.50 309	96.70 283

plane_prior						94.60 224	98.44 180		96.74 68						94.22 234

MP-MVS-pluss		98.31 56	97.92 63	99.49 12	99.72 13	98.88 18	98.43 182	98.78 99	94.10 181	97.69 130	99.42 16	95.25 72	99.92 25	98.09 40	99.80 19	99.67 67
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
OPM-MVS		95.69 177	95.33 175	96.76 214	96.16 318	94.63 219	98.43 182	98.39 192	96.64 72	95.02 210	98.78 124	85.15 278	99.05 200	95.21 177	94.20 235	96.60 294
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DPE-MVS		98.92 5	98.67 8	99.65 2	99.58 34	99.20 9	98.42 184	98.91 45	97.58 15	99.54 8	99.46 13	97.10 12	99.94 4	97.64 73	99.84 10	99.83 7
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MCST-MVS		98.65 14	98.37 26	99.48 13	99.60 33	98.87 19	98.41 185	98.68 125	97.04 54	98.52 78	98.80 122	96.78 16	99.83 60	97.93 48	99.61 73	99.74 37

Regformer-3		98.59 21	98.50 17	98.86 76	99.43 61	97.05 105	98.40 186	98.68 125	97.43 26	99.06 37	99.31 39	95.80 47	99.77 105	98.62 10	99.76 36	99.78 16

Regformer-4		98.64 15	98.53 14	98.99 66	99.43 61	97.37 92	98.40 186	98.79 96	97.46 23	99.09 36	99.31 39	95.86 46	99.80 84	98.64 8	99.76 36	99.79 13

Regformer-1		98.66 13	98.51 16	99.12 60	99.35 64	97.81 79	98.37 188	98.76 103	97.49 19	99.20 26	99.21 55	96.08 33	99.79 96	98.42 28	99.73 47	99.75 32

Regformer-2		98.69 12	98.52 15	99.19 46	99.35 64	98.01 67	98.37 188	98.81 80	97.48 20	99.21 25	99.21 55	96.13 31	99.80 84	98.40 30	99.73 47	99.75 32

hse-mvs2		95.71 174	95.30 179	96.93 203	98.50 162	93.53 261	98.36 190	98.10 244	97.48 20	98.67 67	97.99 204	89.76 177	99.02 207	97.95 46	80.91 359	98.22 210

CANet		98.05 62	97.76 67	98.90 74	98.73 142	97.27 95	98.35 191	98.78 99	97.37 32	97.72 128	98.96 103	91.53 145	99.92 25	98.79 6	99.65 64	99.51 98

AUN-MVS		94.53 244	93.73 263	96.92 206	98.50 162	93.52 262	98.34 192	98.10 244	93.83 197	95.94 199	97.98 206	85.59 269	99.03 204	94.35 199	80.94 358	98.22 210

ETH3D cwj APD-0.16		97.96 64	97.52 77	99.29 34	99.05 114	98.52 32	98.33 193	98.68 125	93.18 230	98.68 66	99.13 73	94.62 88	99.83 60	96.45 133	99.55 90	99.52 94

test20.03		90.89 314	90.38 312	92.43 339	93.48 360	88.14 352	98.33 193	97.56 289	93.40 221	87.96 347	96.71 309	80.69 324	94.13 369	79.15 363	86.17 345	95.01 352

DP-MVS Recon		97.86 71	97.46 82	99.06 64	99.53 39	98.35 48	98.33 193	98.89 48	92.62 249	98.05 99	98.94 106	95.34 65	99.65 128	96.04 146	99.42 105	99.19 143

RPSCF		94.87 224	95.40 167	93.26 335	98.89 130	82.06 369	98.33 193	98.06 257	90.30 317	96.56 176	99.26 47	87.09 242	99.49 155	93.82 218	96.32 212	98.24 209

TAPA-MVS	93.98 7	95.35 196	94.56 211	97.74 153	99.13 110	94.83 212	98.33 193	98.64 141	86.62 345	96.29 189	98.61 142	94.00 103	99.29 172	80.00 360	99.41 106	99.09 157
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
IterMVS-LS		95.46 185	95.21 182	96.22 262	98.12 198	93.72 255	98.32 198	98.13 238	93.71 204	94.26 238	97.31 261	92.24 124	98.10 309	94.63 188	90.12 298	96.84 267
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
mvs_anonymous		96.70 128	96.53 126	97.18 185	98.19 191	93.78 249	98.31 199	98.19 224	94.01 186	94.47 225	98.27 184	92.08 131	98.46 269	97.39 88	97.91 171	99.31 127

WTY-MVS		97.37 102	96.92 106	98.72 80	98.86 133	96.89 114	98.31 199	98.71 118	95.26 135	97.67 131	98.56 150	92.21 126	99.78 100	95.89 150	96.85 195	99.48 105

D2MVS		95.18 206	95.08 188	95.48 287	97.10 269	92.07 287	98.30 201	99.13 20	94.02 185	92.90 290	96.73 307	89.48 182	98.73 242	94.48 196	93.60 256	95.65 340

EI-MVSNet-Vis-set		98.47 40	98.39 24	98.69 81	99.46 55	96.49 132	98.30 201	98.69 122	97.21 43	98.84 55	99.36 30	95.41 60	99.78 100	98.62 10	99.65 64	99.80 12

DSMNet-mixed		92.52 301	92.58 292	92.33 340	94.15 354	82.65 367	98.30 201	94.26 365	89.08 335	92.65 298	95.73 336	85.01 280	95.76 361	86.24 335	97.76 178	98.59 196

EI-MVSNet-UG-set		98.41 44	98.34 33	98.61 86	99.45 59	96.32 141	98.28 204	98.68 125	97.17 46	98.74 62	99.37 26	95.25 72	99.79 96	98.57 12	99.54 91	99.73 42

OMC-MVS		97.55 90	97.34 88	98.20 120	99.33 69	95.92 164	98.28 204	98.59 148	95.52 120	97.97 111	99.10 78	93.28 111	99.49 155	95.09 178	98.88 130	99.19 143

baseline2		95.11 209	94.52 213	96.87 208	96.65 294	93.56 258	98.27 206	94.10 368	93.45 219	92.02 316	97.43 255	87.45 239	99.19 181	93.88 216	97.41 188	97.87 219

PVSNet_BlendedMVS		96.73 127	96.60 122	97.12 190	99.25 90	95.35 187	98.26 207	99.26 9	94.28 176	97.94 114	97.46 251	92.74 116	99.81 75	96.88 113	93.32 263	96.20 327

BH-untuned		95.95 160	95.72 155	96.65 221	98.55 160	92.26 284	98.23 208	97.79 276	93.73 202	94.62 220	98.01 202	88.97 202	99.00 210	93.04 241	98.51 148	98.68 189

sss		97.39 100	96.98 104	98.61 86	98.60 157	96.61 124	98.22 209	98.93 39	93.97 189	98.01 108	98.48 156	91.98 133	99.85 54	96.45 133	98.15 163	99.39 118

xxxxxxxxxxxxxcwj		98.70 10	98.50 17	99.30 33	99.46 55	98.38 40	98.21 210	98.52 164	97.95 3	99.32 18	99.39 18	96.22 24	99.84 57	97.72 65	99.73 47	99.67 67

save fliter					99.46 55	98.38 40	98.21 210	98.71 118	97.95 3

WR-MVS		95.15 207	94.46 217	97.22 182	96.67 293	96.45 133	98.21 210	98.81 80	94.15 179	93.16 282	97.69 233	87.51 235	98.30 295	95.29 173	88.62 321	96.90 258

ETH3 D test6400		97.59 86	97.01 101	99.34 26	99.40 63	98.56 30	98.20 213	98.81 80	91.63 283	98.44 83	98.85 115	93.98 104	99.82 68	94.11 210	99.69 58	99.64 76

pmmvs5		93.65 283	92.97 285	95.68 283	95.49 338	92.37 283	98.20 213	97.28 314	89.66 328	92.58 300	97.26 263	82.14 310	98.09 311	93.18 237	90.95 291	96.58 296

thres200		95.25 201	94.57 210	97.28 180	98.81 138	94.92 207	98.20 213	97.11 319	95.24 138	96.54 180	96.22 327	84.58 288	99.53 150	87.93 327	96.50 207	97.39 232

CDS-MVSNet		96.99 118	96.69 118	97.90 139	98.05 204	95.98 152	98.20 213	98.33 202	93.67 211	96.95 157	98.49 155	93.54 107	98.42 274	95.24 176	97.74 179	99.31 127
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
1314		96.25 150	95.73 154	97.79 147	97.13 267	95.55 179	98.19 217	98.59 148	93.47 218	92.03 315	97.82 223	91.33 149	99.49 155	94.62 190	98.44 152	98.32 208

1121		97.37 102	96.77 116	99.16 53	99.34 66	97.99 70	98.19 217	98.68 125	90.14 320	98.01 108	98.97 97	94.80 86	99.87 48	93.36 231	99.46 102	99.61 82

MVS		94.67 235	93.54 272	98.08 129	96.88 281	96.56 128	98.19 217	98.50 172	78.05 365	92.69 297	98.02 200	91.07 156	99.63 133	90.09 299	98.36 157	98.04 215

BH-RMVSNet		95.92 164	95.32 176	97.69 158	98.32 181	94.64 218	98.19 217	97.45 303	94.56 167	96.03 195	98.61 142	85.02 279	99.12 191	90.68 293	99.06 120	99.30 130

1112_ss		96.63 129	96.00 145	98.50 96	98.56 158	96.37 138	98.18 221	98.10 244	92.92 241	94.84 213	98.43 162	92.14 128	99.58 139	94.35 199	96.51 206	99.56 93

MVS_0304		92.81 297	92.01 299	95.23 294	97.46 242	91.33 302	98.17 222	98.81 80	91.13 303	93.80 262	95.68 341	66.08 369	98.06 314	90.79 290	96.13 222	96.32 324

EPNet_dtu		95.21 204	94.95 195	95.99 269	96.17 316	90.45 318	98.16 223	97.27 315	96.77 66	93.14 285	98.33 177	90.34 169	98.42 274	85.57 340	98.81 136	99.09 157
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HY-MVS	93.96 8	96.82 125	96.23 137	98.57 88	98.46 165	97.00 107	98.14 224	98.21 221	93.95 190	96.72 170	97.99 204	91.58 140	99.76 107	94.51 195	96.54 205	98.95 173

PLC	95.07 4	97.20 110	96.78 112	98.44 103	99.29 82	96.31 143	98.14 224	98.76 103	92.41 258	96.39 187	98.31 179	94.92 83	99.78 100	94.06 212	98.77 137	99.23 137
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EG-PatchMatch MVS		91.13 311	90.12 314	94.17 326	94.73 351	89.00 339	98.13 226	97.81 275	89.22 334	85.32 358	96.46 318	67.71 366	98.42 274	87.89 328	93.82 248	95.08 349

EI-MVSNet		95.96 159	95.83 150	96.36 255	97.93 210	93.70 256	98.12 227	98.27 214	93.70 206	95.07 208	99.02 90	92.23 125	98.54 260	94.68 187	93.46 258	96.84 267

CVMVSNet		95.43 188	96.04 143	93.57 329	97.93 210	83.62 364	98.12 227	98.59 148	95.68 112	96.56 176	99.02 90	87.51 235	97.51 339	93.56 227	97.44 186	99.60 85

TSAR-MVS + GP.		98.38 46	98.24 46	98.81 77	99.22 98	97.25 100	98.11 229	98.29 213	97.19 45	98.99 44	99.02 90	96.22 24	99.67 126	98.52 20	98.56 146	99.51 98

XVG-ACMP-BASELINE		94.54 243	94.14 233	95.75 282	96.55 298	91.65 297	98.11 229	98.44 183	94.96 152	94.22 241	97.90 212	79.18 332	99.11 193	94.05 213	93.85 247	96.48 315

CNLPA		97.45 95	97.03 100	98.73 79	99.05 114	97.44 91	98.07 231	98.53 162	95.32 132	96.80 168	98.53 151	93.32 110	99.72 113	94.31 202	99.31 113	99.02 165

diffmvs		97.58 87	97.40 86	98.13 125	98.32 181	95.81 170	98.06 232	98.37 196	96.20 89	98.74 62	98.89 111	91.31 150	99.25 174	98.16 37	98.52 147	99.34 121

CHOSEN 1792x2688		97.12 114	96.80 109	98.08 129	99.30 79	94.56 226	98.05 233	99.71 1	93.57 215	97.09 150	98.91 110	88.17 218	99.89 39	96.87 116	99.56 86	99.81 11

HQP-NCC					97.20 260		98.05 233		96.43 81	94.45 226

ACMP_Plane					97.20 260		98.05 233		96.43 81	94.45 226

HQP-MVS		95.72 173	95.40 167	96.69 219	97.20 260	94.25 238	98.05 233	98.46 179	96.43 81	94.45 226	97.73 228	86.75 248	98.96 215	95.30 171	94.18 236	96.86 265

MIMVSNet1		89.67 323	88.28 327	93.82 327	92.81 364	91.08 307	98.01 237	97.45 303	87.95 340	87.90 348	95.87 333	67.63 367	94.56 368	78.73 365	88.18 326	95.83 336

AdaColmap		97.15 113	96.70 117	98.48 99	99.16 107	96.69 121	98.01 237	98.89 48	94.44 174	96.83 164	98.68 135	90.69 164	99.76 107	94.36 198	99.29 114	98.98 169

FMVSNet5		91.81 304	90.92 307	94.49 318	97.21 259	92.09 286	98.00 239	97.55 294	89.31 333	90.86 326	95.61 342	74.48 357	95.32 364	85.57 340	89.70 303	96.07 331

CANet_DTU		96.96 119	96.55 124	98.21 119	98.17 195	96.07 150	97.98 240	98.21 221	97.24 42	97.13 149	98.93 107	86.88 247	99.91 34	95.00 180	99.37 110	98.66 192

MVP-Stereo		94.28 261	93.92 246	95.35 292	94.95 346	92.60 282	97.97 241	97.65 282	91.61 284	90.68 328	97.09 276	86.32 257	98.42 274	89.70 309	99.34 111	95.02 351
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
KD-MVS_self_test		90.38 317	89.38 320	93.40 332	92.85 363	88.94 341	97.95 242	97.94 268	90.35 316	90.25 331	93.96 355	79.82 327	95.94 360	84.62 349	76.69 364	95.33 343

MVS_111021_LR		98.34 52	98.23 47	98.67 83	99.27 87	96.90 112	97.95 242	99.58 3	97.14 49	98.44 83	99.01 94	95.03 80	99.62 136	97.91 49	99.75 42	99.50 100

TEST9					99.31 74	98.50 34	97.92 244	98.73 112	92.63 248	97.74 125	98.68 135	96.20 27	99.80 84

train_agg		97.97 63	97.52 77	99.33 30	99.31 74	98.50 34	97.92 244	98.73 112	92.98 238	97.74 125	98.68 135	96.20 27	99.80 84	96.59 127	99.57 81	99.68 63

CDPH-MVS		97.94 68	97.49 80	99.28 38	99.47 52	98.44 36	97.91 246	98.67 133	92.57 252	98.77 60	98.85 115	95.93 42	99.72 113	95.56 165	99.69 58	99.68 63

MVS_111021_HR		98.47 40	98.34 33	98.88 75	99.22 98	97.32 93	97.91 246	99.58 3	97.20 44	98.33 90	99.00 95	95.99 39	99.64 130	98.05 43	99.76 36	99.69 57

PatchMatch-RL		96.59 132	96.03 144	98.27 114	99.31 74	96.51 131	97.91 246	99.06 23	93.72 203	96.92 161	98.06 198	88.50 213	99.65 128	91.77 276	99.00 125	98.66 192

OpenMVS_ROB	86.42 20	89.00 327	87.43 332	93.69 328	93.08 362	89.42 332	97.91 246	96.89 334	78.58 364	85.86 355	94.69 349	69.48 364	98.29 298	77.13 367	93.29 265	93.36 364

test_8					99.29 82	98.44 36	97.89 250	98.72 114	92.98 238	97.70 129	98.66 138	96.20 27	99.80 84

ab-mvs		96.42 140	95.71 158	98.55 90	98.63 154	96.75 118	97.88 251	98.74 108	93.84 195	96.54 180	98.18 191	85.34 275	99.75 109	95.93 149	96.35 210	99.15 150

jason		97.32 104	97.08 98	98.06 131	97.45 246	95.59 175	97.87 252	97.91 272	94.79 158	98.55 77	98.83 119	91.12 153	99.23 177	97.58 77	99.60 74	99.34 121
jason: jason.
xiu_mvs_v1_base_debu		97.60 83	97.56 74	97.72 154	98.35 172	95.98 152	97.86 253	98.51 167	97.13 50	99.01 41	98.40 166	91.56 141	99.80 84	98.53 14	98.68 138	97.37 234

xiu_mvs_v1_base		97.60 83	97.56 74	97.72 154	98.35 172	95.98 152	97.86 253	98.51 167	97.13 50	99.01 41	98.40 166	91.56 141	99.80 84	98.53 14	98.68 138	97.37 234

xiu_mvs_v1_base_debi		97.60 83	97.56 74	97.72 154	98.35 172	95.98 152	97.86 253	98.51 167	97.13 50	99.01 41	98.40 166	91.56 141	99.80 84	98.53 14	98.68 138	97.37 234

test_prior4						98.01 67	97.86 253

agg_prior1		97.95 67	97.51 79	99.28 38	99.30 79	98.38 40	97.81 257	98.72 114	93.16 232	97.57 139	98.66 138	96.14 30	99.81 75	96.63 126	99.56 86	99.66 71

FA-MVS(test-final)		96.41 143	95.94 146	97.82 144	98.21 187	95.20 192	97.80 258	97.58 287	93.21 228	97.36 143	97.70 231	89.47 183	99.56 143	94.12 208	97.99 168	98.71 187

test_prior3		98.22 59	97.90 64	99.19 46	99.31 74	98.22 55	97.80 258	98.84 69	96.12 93	97.89 119	98.69 133	95.96 40	99.70 119	96.89 110	99.60 74	99.65 73

test_prior2							97.80 258		96.12 93	97.89 119	98.69 133	95.96 40		96.89 110	99.60 74

XVG-OURS-SEG-HR		96.51 137	96.34 130	97.02 196	98.77 140	93.76 250	97.79 261	98.50 172	95.45 123	96.94 158	99.09 84	87.87 228	99.55 149	96.76 124	95.83 226	97.74 223

MS-PatchMatch		93.84 280	93.63 268	94.46 321	96.18 315	89.45 331	97.76 262	98.27 214	92.23 266	92.13 313	97.49 249	79.50 329	98.69 243	89.75 307	99.38 109	95.25 344

DELS-MVS		98.40 45	98.20 49	98.99 66	99.00 121	97.66 81	97.75 263	98.89 48	97.71 9	98.33 90	98.97 97	94.97 81	99.88 47	98.42 28	99.76 36	99.42 117
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
MG-MVS		97.81 73	97.60 71	98.44 103	99.12 111	95.97 157	97.75 263	98.78 99	96.89 61	98.46 79	99.22 54	93.90 105	99.68 125	94.81 185	99.52 94	99.67 67

Test_1112_low_res		96.34 145	95.66 163	98.36 109	98.56 158	95.94 160	97.71 265	98.07 252	92.10 270	94.79 217	97.29 262	91.75 137	99.56 143	94.17 206	96.50 207	99.58 91

BH-w/o		95.38 192	95.08 188	96.26 261	98.34 177	91.79 292	97.70 266	97.43 305	92.87 243	94.24 240	97.22 267	88.66 207	98.84 232	91.55 280	97.70 181	98.16 213

lupinMVS		97.44 96	97.22 93	98.12 127	98.07 201	95.76 171	97.68 267	97.76 277	94.50 171	98.79 58	98.61 142	92.34 120	99.30 171	97.58 77	99.59 77	99.31 127

原ACMM2							97.67 268

LF4IMVS		93.14 294	92.79 288	94.20 324	95.88 327	88.67 344	97.66 269	97.07 321	93.81 198	91.71 318	97.65 237	77.96 340	98.81 236	91.47 281	91.92 278	95.12 347

EGC-MVSNET		75.22 338	69.54 341	92.28 341	94.81 349	89.58 329	97.64 270	96.50 345	1.82 381	5.57 382	95.74 334	68.21 365	96.26 359	73.80 370	91.71 280	90.99 366

新几何2							97.64 270

MDA-MVSNet-bldmvs		89.97 321	88.35 326	94.83 309	95.21 343	91.34 301	97.64 270	97.51 297	88.36 339	71.17 371	96.13 329	79.22 331	96.63 355	83.65 351	86.27 344	96.52 308

pmmvs-eth3d		90.36 318	89.05 323	94.32 323	91.10 368	92.12 285	97.63 273	96.95 329	88.86 336	84.91 359	93.13 358	78.32 335	96.74 350	88.70 321	81.81 354	94.09 359

TR-MVS		94.94 222	94.20 228	97.17 186	97.75 219	94.14 241	97.59 274	97.02 326	92.28 265	95.75 200	97.64 239	83.88 302	98.96 215	89.77 306	96.15 221	98.40 203

无先验							97.58 275	98.72 114	91.38 289				99.87 48	93.36 231		99.60 85

旧先验2							97.57 276		91.30 295	98.67 67			99.80 84	95.70 162

CostFormer		94.95 220	94.73 204	95.60 285	97.28 254	89.06 337	97.53 277	96.89 334	89.66 328	96.82 166	96.72 308	86.05 261	98.95 219	95.53 166	96.13 222	98.79 181

XVG-OURS		96.55 136	96.41 128	96.99 197	98.75 141	93.76 250	97.50 278	98.52 164	95.67 113	96.83 164	99.30 42	88.95 203	99.53 150	95.88 151	96.26 217	97.69 226

xiu_mvs_v2_base		97.66 80	97.70 69	97.56 168	98.61 156	95.46 182	97.44 279	98.46 179	97.15 48	98.65 72	98.15 192	94.33 97	99.80 84	97.84 58	98.66 142	97.41 230

tpm		94.13 269	93.80 256	95.12 298	96.50 301	87.91 354	97.44 279	95.89 351	92.62 249	96.37 188	96.30 322	84.13 297	98.30 295	93.24 234	91.66 282	99.14 152

DeepPCF-MVS	96.37 2	97.93 69	98.48 22	96.30 259	99.00 121	89.54 330	97.43 281	98.87 58	98.16 2	99.26 22	99.38 25	96.12 32	99.64 130	98.30 34	99.77 30	99.72 46

test222					99.23 97	97.17 103	97.40 282	98.66 136	88.68 337	98.05 99	98.96 103	94.14 100			99.53 92	99.61 82

pmmvs4		94.69 230	93.99 243	96.81 212	95.74 330	95.94 160	97.40 282	97.67 281	90.42 314	93.37 276	97.59 243	89.08 196	98.20 302	92.97 243	91.67 281	96.30 325

test0.0.03 1		94.08 274	93.51 273	95.80 279	95.53 337	92.89 280	97.38 284	95.97 348	95.11 143	92.51 304	96.66 310	87.71 231	96.94 347	87.03 331	93.67 251	97.57 228

HyFIR lowres test		96.90 122	96.49 127	98.14 123	99.33 69	95.56 177	97.38 284	99.65 2	92.34 260	97.61 137	98.20 189	89.29 188	99.10 196	96.97 102	97.60 184	99.77 23

Effi-MVS+		97.12 114	96.69 118	98.39 108	98.19 191	96.72 120	97.37 286	98.43 186	93.71 204	97.65 134	98.02 200	92.20 127	99.25 174	96.87 116	97.79 176	99.19 143

N_pmnet		87.12 331	87.77 330	85.17 351	95.46 339	61.92 378	97.37 286	70.66 384	85.83 352	88.73 345	96.04 331	85.33 276	97.76 332	80.02 359	90.48 294	95.84 335

PAPR		96.84 124	96.24 136	98.65 84	98.72 146	96.92 111	97.36 288	98.57 154	93.33 223	96.67 171	97.57 245	94.30 98	99.56 143	91.05 288	98.59 144	99.47 107

PMMVS		96.60 130	96.33 131	97.41 173	97.90 212	93.93 245	97.35 289	98.41 188	92.84 244	97.76 123	97.45 253	91.10 155	99.20 180	96.26 139	97.91 171	99.11 155

PS-MVSNAJ		97.73 76	97.77 66	97.62 164	98.68 150	95.58 176	97.34 290	98.51 167	97.29 35	98.66 71	97.88 215	94.51 91	99.90 37	97.87 54	99.17 118	97.39 232

SCA		95.46 185	95.13 185	96.46 248	97.67 225	91.29 304	97.33 291	97.60 286	94.68 162	96.92 161	97.10 272	83.97 300	98.89 226	92.59 254	98.32 160	99.20 139

testdata1							97.32 292		96.34 85

ET-MVSNet_ETH3D		94.13 269	92.98 284	97.58 166	98.22 186	96.20 145	97.31 293	95.37 353	94.53 168	79.56 365	97.63 241	86.51 251	97.53 338	96.91 106	90.74 292	99.02 165

tpm2		94.19 265	93.76 261	95.46 289	97.23 257	89.04 338	97.31 293	96.85 338	87.08 344	96.21 191	96.79 306	83.75 306	98.74 241	92.43 262	96.23 219	98.59 196

PVSNet_Blended		97.38 101	97.12 95	98.14 123	99.25 90	95.35 187	97.28 295	99.26 9	93.13 233	97.94 114	98.21 188	92.74 116	99.81 75	96.88 113	99.40 108	99.27 134

CLD-MVS		95.62 180	95.34 173	96.46 248	97.52 239	93.75 252	97.27 296	98.46 179	95.53 119	94.42 231	98.00 203	86.21 258	98.97 211	96.25 140	94.37 230	96.66 289
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
EPMVS		94.99 216	94.48 215	96.52 241	97.22 258	91.75 294	97.23 297	91.66 374	94.11 180	97.28 144	96.81 305	85.70 267	98.84 232	93.04 241	97.28 189	98.97 170

miper_lstm_enhance		94.33 256	94.07 236	95.11 299	97.75 219	90.97 308	97.22 298	98.03 260	91.67 282	92.76 294	96.97 292	90.03 174	97.78 331	92.51 259	89.64 304	96.56 300

YYNet1		90.70 316	89.39 319	94.62 315	94.79 350	90.65 315	97.20 299	97.46 301	87.54 342	72.54 369	95.74 334	86.51 251	96.66 354	86.00 337	86.76 343	96.54 303

MDA-MVSNet_test_wron		90.71 315	89.38 320	94.68 313	94.83 348	90.78 312	97.19 300	97.46 301	87.60 341	72.41 370	95.72 338	86.51 251	96.71 353	85.92 338	86.80 342	96.56 300

IterMVS-SCA-FT		94.11 271	93.87 251	94.85 307	97.98 209	90.56 317	97.18 301	98.11 242	93.75 199	92.58 300	97.48 250	83.97 300	97.41 340	92.48 261	91.30 285	96.58 296

IterMVS		94.09 273	93.85 253	94.80 310	97.99 207	90.35 319	97.18 301	98.12 239	93.68 209	92.46 307	97.34 258	84.05 298	97.41 340	92.51 259	91.33 284	96.62 292
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FE-MVS		95.62 180	94.90 197	97.78 148	98.37 171	94.92 207	97.17 303	97.38 309	90.95 306	97.73 127	97.70 231	85.32 277	99.63 133	91.18 283	98.33 158	98.79 181

DPM-MVS		97.55 90	96.99 103	99.23 45	99.04 116	98.55 31	97.17 303	98.35 199	94.85 157	97.93 116	98.58 147	95.07 79	99.71 118	92.60 252	99.34 111	99.43 115

c3_l		94.79 227	94.43 221	95.89 276	97.75 219	93.12 277	97.16 305	98.03 260	92.23 266	93.46 275	97.05 284	91.39 146	98.01 317	93.58 226	89.21 313	96.53 305

new-patchmatchnet		88.50 328	87.45 331	91.67 344	90.31 370	85.89 361	97.16 305	97.33 311	89.47 330	83.63 361	92.77 359	76.38 349	95.06 366	82.70 353	77.29 363	94.06 360

UnsupCasMVSNet_eth		90.99 313	89.92 316	94.19 325	94.08 355	89.83 324	97.13 307	98.67 133	93.69 207	85.83 356	96.19 328	75.15 354	96.74 350	89.14 318	79.41 360	96.00 332

IB-MVS	91.98 17	93.27 289	91.97 300	97.19 184	97.47 241	93.41 266	97.09 308	95.99 347	93.32 224	92.47 306	95.73 336	78.06 339	99.53 150	94.59 193	82.98 350	98.62 195
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
cl____		94.51 246	94.01 240	96.02 268	97.58 231	93.40 267	97.05 309	97.96 267	91.73 280	92.76 294	97.08 278	89.06 197	98.13 307	92.61 251	90.29 297	96.52 308

DIV-MVS_self_test		94.52 245	94.03 237	95.99 269	97.57 235	93.38 268	97.05 309	97.94 268	91.74 278	92.81 292	97.10 272	89.12 194	98.07 313	92.60 252	90.30 296	96.53 305

miper_ehance_all_eth		95.01 214	94.69 206	95.97 271	97.70 224	93.31 270	97.02 311	98.07 252	92.23 266	93.51 272	96.96 294	91.85 135	98.15 305	93.68 221	91.16 288	96.44 318

CMPMVS	66.06 21	89.70 322	89.67 318	89.78 346	93.19 361	76.56 371	97.00 312	98.35 199	80.97 362	81.57 363	97.75 227	74.75 356	98.61 251	89.85 305	93.63 254	94.17 357
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
tpmrst		95.63 179	95.69 161	95.44 290	97.54 236	88.54 346	96.97 313	97.56 289	93.50 217	97.52 141	96.93 298	89.49 181	99.16 183	95.25 175	96.42 209	98.64 194

dp		94.15 268	93.90 249	94.90 305	97.31 253	86.82 360	96.97 313	97.19 318	91.22 300	96.02 196	96.61 315	85.51 271	99.02 207	90.00 304	94.30 231	98.85 177

cl22		94.68 232	94.19 229	96.13 265	98.11 199	93.60 257	96.94 315	98.31 205	92.43 257	93.32 278	96.87 302	86.51 251	98.28 299	94.10 211	91.16 288	96.51 311

PM-MVS		87.77 329	86.55 333	91.40 345	91.03 369	83.36 366	96.92 316	95.18 356	91.28 297	86.48 354	93.42 357	53.27 373	96.74 350	89.43 315	81.97 353	94.11 358

TinyColmap		92.31 302	91.53 303	94.65 314	96.92 277	89.75 325	96.92 316	96.68 342	90.45 313	89.62 336	97.85 218	76.06 351	98.81 236	86.74 332	92.51 272	95.41 342

our_test_3		93.65 283	93.30 279	94.69 312	95.45 340	89.68 328	96.91 318	97.65 282	91.97 273	91.66 319	96.88 300	89.67 180	97.93 324	88.02 326	91.49 283	96.48 315

test-LLR		95.10 210	94.87 199	95.80 279	96.77 285	89.70 326	96.91 318	95.21 354	95.11 143	94.83 215	95.72 338	87.71 231	98.97 211	93.06 239	98.50 149	98.72 185

TESTMET0.1,1		94.18 267	93.69 266	95.63 284	96.92 277	89.12 336	96.91 318	94.78 359	93.17 231	94.88 212	96.45 319	78.52 334	98.92 221	93.09 238	98.50 149	98.85 177

test-mter		94.08 274	93.51 273	95.80 279	96.77 285	89.70 326	96.91 318	95.21 354	92.89 242	94.83 215	95.72 338	77.69 341	98.97 211	93.06 239	98.50 149	98.72 185

USDC		93.33 288	92.71 289	95.21 295	96.83 284	90.83 311	96.91 318	97.50 298	93.84 195	90.72 327	98.14 193	77.69 341	98.82 235	89.51 313	93.21 266	95.97 333

MDTV_nov1_ep13_2view						84.26 363	96.89 323		90.97 305	97.90 118		89.89 176		93.91 215		99.18 148

ppachtmachnet_test		93.22 291	92.63 291	94.97 303	95.45 340	90.84 310	96.88 324	97.88 273	90.60 309	92.08 314	97.26 263	88.08 222	97.86 330	85.12 344	90.33 295	96.22 326

tpmvs		94.60 238	94.36 224	95.33 293	97.46 242	88.60 345	96.88 324	97.68 280	91.29 296	93.80 262	96.42 320	88.58 208	99.24 176	91.06 286	96.04 224	98.17 212

MDTV_nov1_ep13			95.40 167		97.48 240	88.34 349	96.85 326	97.29 313	93.74 201	97.48 142	97.26 263	89.18 192	99.05 200	91.92 273	97.43 187

PatchmatchNet		95.71 174	95.52 165	96.29 260	97.58 231	90.72 313	96.84 327	97.52 296	94.06 182	97.08 151	96.96 294	89.24 191	98.90 225	92.03 270	98.37 155	99.26 135
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MSDG		95.93 163	95.30 179	97.83 142	98.90 129	95.36 185	96.83 328	98.37 196	91.32 294	94.43 230	98.73 130	90.27 171	99.60 137	90.05 302	98.82 135	98.52 199

thisisatest0515		95.61 183	94.89 198	97.76 151	98.15 197	95.15 195	96.77 329	94.41 362	92.95 240	97.18 148	97.43 255	84.78 284	99.45 163	94.63 188	97.73 180	98.68 189

GA-MVS		94.81 226	94.03 237	97.14 188	97.15 266	93.86 247	96.76 330	97.58 287	94.00 187	94.76 218	97.04 285	80.91 320	98.48 265	91.79 275	96.25 218	99.09 157

tpm cat1		93.36 285	92.80 287	95.07 301	97.58 231	87.97 353	96.76 330	97.86 274	82.17 361	93.53 269	96.04 331	86.13 259	99.13 189	89.24 317	95.87 225	98.10 214

eth_miper_zixun_eth		94.68 232	94.41 222	95.47 288	97.64 227	91.71 296	96.73 332	98.07 252	92.71 247	93.64 265	97.21 268	90.54 166	98.17 304	93.38 229	89.76 302	96.54 303

test_post1							96.68 333				30.43 380	87.85 229	98.69 243	92.59 254

pmmvs3		86.67 332	84.86 335	92.11 343	88.16 371	87.19 359	96.63 334	94.75 360	79.88 363	87.22 350	92.75 360	66.56 368	95.20 365	81.24 357	76.56 365	93.96 361

miper_enhance_ethall		95.10 210	94.75 203	96.12 266	97.53 238	93.73 254	96.61 335	98.08 250	92.20 269	93.89 256	96.65 312	92.44 119	98.30 295	94.21 205	91.16 288	96.34 321

testmvs		21.48 347	24.95 350	11.09 363	14.89 385	6.47 387	96.56 336	9.87 386	7.55 379	17.93 379	39.02 377	9.43 386	5.90 382	16.56 380	12.72 379	20.91 377

test123		20.95 348	23.72 351	12.64 362	13.54 386	8.19 386	96.55 337	6.13 387	7.48 380	16.74 380	37.98 378	12.97 383	6.05 381	16.69 379	5.43 380	23.68 376

CL-MVSNet_self_test		90.11 319	89.14 322	93.02 337	91.86 366	88.23 351	96.51 338	98.07 252	90.49 310	90.49 330	94.41 350	84.75 285	95.34 363	80.79 358	74.95 366	95.50 341

GG-mvs-BLEND				96.59 230	96.34 310	94.98 203	96.51 338	88.58 378		93.10 287	94.34 354	80.34 326	98.05 315	89.53 312	96.99 193	96.74 276

new_pmnet		90.06 320	89.00 324	93.22 336	94.18 353	88.32 350	96.42 340	96.89 334	86.19 348	85.67 357	93.62 356	77.18 347	97.10 344	81.61 356	89.29 312	94.23 356

PVSNet	91.96 18	96.35 144	96.15 138	96.96 201	99.17 103	92.05 288	96.08 341	98.68 125	93.69 207	97.75 124	97.80 225	88.86 204	99.69 124	94.26 204	99.01 124	99.15 150

ADS-MVSNet2		94.58 241	94.40 223	95.11 299	98.00 205	88.74 343	96.04 342	97.30 312	90.15 318	96.47 184	96.64 313	87.89 226	97.56 337	90.08 300	97.06 191	99.02 165

ADS-MVSNet		95.00 215	94.45 219	96.63 225	98.00 205	91.91 290	96.04 342	97.74 279	90.15 318	96.47 184	96.64 313	87.89 226	98.96 215	90.08 300	97.06 191	99.02 165

PAPM		94.95 220	94.00 241	97.78 148	97.04 271	95.65 174	96.03 344	98.25 219	91.23 299	94.19 243	97.80 225	91.27 151	98.86 231	82.61 354	97.61 183	98.84 179

cascas		94.63 237	93.86 252	96.93 203	96.91 279	94.27 236	96.00 345	98.51 167	85.55 354	94.54 222	96.23 325	84.20 296	98.87 229	95.80 155	96.98 194	97.66 227

gg-mvs-nofinetune		92.21 303	90.58 310	97.13 189	96.75 288	95.09 197	95.85 346	89.40 377	85.43 355	94.50 224	81.98 370	80.80 323	98.40 288	92.16 264	98.33 158	97.88 218

FPMVS		77.62 337	77.14 337	79.05 355	79.25 378	60.97 379	95.79 347	95.94 349	65.96 369	67.93 372	94.40 351	37.73 378	88.88 374	68.83 371	88.46 322	87.29 368

CHOSEN 280x420		97.18 111	97.18 94	97.20 183	98.81 138	93.27 271	95.78 348	99.15 19	95.25 136	96.79 169	98.11 195	92.29 122	99.07 199	98.56 13	99.85 5	99.25 136

MIMVSNet		93.26 290	92.21 297	96.41 251	97.73 223	93.13 276	95.65 349	97.03 324	91.27 298	94.04 250	96.06 330	75.33 353	97.19 343	86.56 333	96.23 219	98.92 175

KD-MVS_2432*1600		89.61 324	87.96 328	94.54 316	94.06 356	91.59 298	95.59 350	97.63 284	89.87 324	88.95 342	94.38 352	78.28 336	96.82 348	84.83 345	68.05 370	95.21 345

miper_refine_blended		89.61 324	87.96 328	94.54 316	94.06 356	91.59 298	95.59 350	97.63 284	89.87 324	88.95 342	94.38 352	78.28 336	96.82 348	84.83 345	68.05 370	95.21 345

PCF-MVS	93.45 11	94.68 232	93.43 276	98.42 106	98.62 155	96.77 117	95.48 352	98.20 223	84.63 357	93.34 277	98.32 178	88.55 211	99.81 75	84.80 347	98.96 126	98.68 189
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
JIA-IIPM		93.35 286	92.49 293	95.92 273	96.48 303	90.65 315	95.01 353	96.96 328	85.93 351	96.08 194	87.33 367	87.70 233	98.78 239	91.35 282	95.58 227	98.34 206

CR-MVSNet		94.76 229	94.15 232	96.59 230	97.00 272	93.43 264	94.96 354	97.56 289	92.46 253	96.93 159	96.24 323	88.15 219	97.88 329	87.38 329	96.65 201	98.46 201

RPMNet		92.81 297	91.34 305	97.24 181	97.00 272	93.43 264	94.96 354	98.80 91	82.27 360	96.93 159	92.12 363	86.98 245	99.82 68	76.32 368	96.65 201	98.46 201

UnsupCasMVSNet_bld		87.17 330	85.12 334	93.31 334	91.94 365	88.77 342	94.92 356	98.30 211	84.30 358	82.30 362	90.04 364	63.96 371	97.25 342	85.85 339	74.47 368	93.93 362

PVSNet_0	88.72 19	91.28 309	90.03 315	95.00 302	97.99 207	87.29 358	94.84 357	98.50 172	92.06 271	89.86 334	95.19 344	79.81 328	99.39 166	92.27 263	69.79 369	98.33 207

Patchmatch-test		94.42 252	93.68 267	96.63 225	97.60 230	91.76 293	94.83 358	97.49 300	89.45 331	94.14 245	97.10 272	88.99 198	98.83 234	85.37 343	98.13 164	99.29 132

Patchmtry		93.22 291	92.35 295	95.84 278	96.77 285	93.09 278	94.66 359	97.56 289	87.37 343	92.90 290	96.24 323	88.15 219	97.90 325	87.37 330	90.10 299	96.53 305

PatchT		93.06 295	91.97 300	96.35 256	96.69 291	92.67 281	94.48 360	97.08 320	86.62 345	97.08 151	92.23 362	87.94 225	97.90 325	78.89 364	96.69 199	98.49 200

LCM-MVSNet		78.70 334	76.24 339	86.08 349	77.26 380	71.99 375	94.34 361	96.72 340	61.62 371	76.53 366	89.33 365	33.91 380	92.78 371	81.85 355	74.60 367	93.46 363

PMMVS2		77.95 336	75.44 340	85.46 350	82.54 375	74.95 373	94.23 362	93.08 370	72.80 368	74.68 367	87.38 366	36.36 379	91.56 372	73.95 369	63.94 372	89.87 367

MVS-HIRNet		89.46 326	88.40 325	92.64 338	97.58 231	82.15 368	94.16 363	93.05 371	75.73 367	90.90 325	82.52 369	79.42 330	98.33 290	83.53 352	98.68 138	97.43 229

Patchmatch-RL test		91.49 307	90.85 308	93.41 331	91.37 367	84.40 362	92.81 364	95.93 350	91.87 276	87.25 349	94.87 348	88.99 198	96.53 356	92.54 258	82.00 352	99.30 130

ambc				89.49 347	86.66 372	75.78 372	92.66 365	96.72 340		86.55 353	92.50 361	46.01 374	97.90 325	90.32 296	82.09 351	94.80 354

EMVS		64.07 343	63.26 346	66.53 360	81.73 377	58.81 382	91.85 366	84.75 380	51.93 375	59.09 375	75.13 374	43.32 376	79.09 378	42.03 377	39.47 375	61.69 374

E-PMN		64.94 342	64.25 344	67.02 359	82.28 376	59.36 381	91.83 367	85.63 379	52.69 373	60.22 374	77.28 373	41.06 377	80.12 377	46.15 376	41.14 374	61.57 375

ANet_high		69.08 339	65.37 343	80.22 354	65.99 382	71.96 376	90.91 368	90.09 376	82.62 359	49.93 377	78.39 372	29.36 381	81.75 375	62.49 373	38.52 376	86.95 370

tmp_tt		68.90 340	66.97 342	74.68 357	50.78 384	59.95 380	87.13 369	83.47 381	38.80 377	62.21 373	96.23 325	64.70 370	76.91 379	88.91 320	30.49 377	87.19 369

MVE	62.14 22	63.28 344	59.38 347	74.99 356	74.33 381	65.47 377	85.55 370	80.50 382	52.02 374	51.10 376	75.00 375	10.91 385	80.50 376	51.60 375	53.40 373	78.99 371
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	61.03 23	65.95 341	63.57 345	73.09 358	57.90 383	51.22 384	85.05 371	93.93 369	54.45 372	44.32 378	83.57 368	13.22 382	89.15 373	58.68 374	81.00 357	78.91 372
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_method		79.03 333	78.17 336	81.63 353	86.06 373	54.40 383	82.75 372	96.89 334	39.54 376	80.98 364	95.57 343	58.37 372	94.73 367	84.74 348	78.61 361	95.75 337

Gipuma		78.40 335	76.75 338	83.38 352	95.54 336	80.43 370	79.42 373	97.40 307	64.67 370	73.46 368	80.82 371	45.65 375	93.14 370	66.32 372	87.43 333	76.56 373
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
wuyk23d		30.17 345	30.18 349	30.16 361	78.61 379	43.29 385	66.79 374	14.21 385	17.31 378	14.82 381	11.93 381	11.55 384	41.43 380	37.08 378	19.30 378	5.76 378

test_blank		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

uanet_test		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

DCPMVS		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

cdsmvs_eth3d_5k		23.98 346	31.98 348	0.00 364	0.00 387	0.00 388	0.00 375	98.59 148	0.00 382	0.00 383	98.61 142	90.60 165	0.00 383	0.00 381	0.00 381	0.00 379

pcd_1.5k_mvsjas		7.88 350	10.50 353	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	94.51 91	0.00 383	0.00 381	0.00 381	0.00 379

sosnet-low-res		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

sosnet		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

uncertanet		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

Regformer		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

ab-mvs-re		8.20 349	10.94 352	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	98.43 162	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

uanet		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

MSC_two_6792asdad				99.62 6	99.17 103	99.08 11		98.63 143					99.94 4	98.53 14	99.80 19	99.86 2

PC_three_1452									95.08 147	99.60 5	99.16 68	97.86 2	98.47 268	97.52 84	99.72 54	99.74 37

No_MVS				99.62 6	99.17 103	99.08 11		98.63 143					99.94 4	98.53 14	99.80 19	99.86 2

test_one_0601					99.66 28	99.25 2		98.86 64	97.55 16	99.20 26	99.47 10	97.57 6

eth-test2					0.00 387

eth-test					0.00 387

ZD-MVS					99.46 55	98.70 23		98.79 96	93.21 228	98.67 67	98.97 97	95.70 50	99.83 60	96.07 142	99.58 80

IU-MVS					99.71 21	99.23 7		98.64 141	95.28 134	99.63 4				98.35 32	99.81 12	99.83 7

test_241102_TWO								98.87 58	97.65 10	99.53 9	99.48 8	97.34 11	99.94 4	98.43 26	99.80 19	99.83 7

test_241102_ONE					99.71 21	99.24 5		98.87 58	97.62 12	99.73 1	99.39 18	97.53 7	99.74 111

test_0728_THIRD									97.32 33	99.45 11	99.46 13	97.88 1	99.94 4	98.47 22	99.86 1	99.85 4

GSMVS																99.20 139

test_part2					99.63 31	99.18 10				99.27 21

sam_mvs1												89.45 184				99.20 139

sam_mvs												88.99 198

MTGPA								98.74 108

test_post											31.83 379	88.83 205	98.91 222

patchmatchnet-post											95.10 346	89.42 185	98.89 226

gm-plane-assit					95.88 327	87.47 356			89.74 327		96.94 297		99.19 181	93.32 233

test9_res														96.39 137	99.57 81	99.69 57

agg_prior2														95.87 152	99.57 81	99.68 63

agg_prior					99.30 79	98.38 40		98.72 114		97.57 139			99.81 75

TestCases				96.99 197	99.25 90	93.21 274		98.18 227	91.36 290	93.52 270	98.77 126	84.67 286	99.72 113	89.70 309	97.87 173	98.02 216

test_prior				99.19 46	99.31 74	98.22 55		98.84 69					99.70 119			99.65 73

新几何1				99.16 53	99.34 66	98.01 67		98.69 122	90.06 321	98.13 94	98.95 105	94.60 89	99.89 39	91.97 272	99.47 99	99.59 87

旧先验1					99.29 82	97.48 88		98.70 121			99.09 84	95.56 53			99.47 99	99.61 82

原ACMM1				98.65 84	99.32 72	96.62 122		98.67 133	93.27 227	97.81 121	98.97 97	95.18 75	99.83 60	93.84 217	99.46 102	99.50 100

testdata2													99.89 39	91.65 279

segment_acmp												96.85 14

testdata				98.26 116	99.20 101	95.36 185		98.68 125	91.89 275	98.60 75	99.10 78	94.44 96	99.82 68	94.27 203	99.44 104	99.58 91

test12				99.18 50	99.16 107	98.19 57		98.53 162		98.07 98		95.13 77	99.72 113		99.56 86	99.63 79

plane_prior7					97.42 247	94.63 219

plane_prior6					97.35 252	94.61 222						87.09 242

plane_prior5								98.56 156					99.03 204	96.07 142	94.27 232	96.92 251

plane_prior4											98.28 181

plane_prior3						94.61 222			97.02 55	95.34 204

plane_prior1					97.37 251

n2								0.00 388

nn								0.00 388

door-mid								94.37 363

lessismore_v0				94.45 322	94.93 347	88.44 348		91.03 375		86.77 352	97.64 239	76.23 350	98.42 274	90.31 297	85.64 348	96.51 311

LGP-MVS_train				96.47 245	97.46 242	93.54 259		98.54 160	94.67 163	94.36 233	98.77 126	85.39 272	99.11 193	95.71 160	94.15 238	96.76 274

test11								98.66 136

door								94.64 361

HQP5-MVS						94.25 238

BP-MVS														95.30 171

HQP4-MVS										94.45 226			98.96 215			96.87 262

HQP3-MVS								98.46 179							94.18 236

HQP2-MVS												86.75 248

NP-MVS					97.28 254	94.51 227					97.73 228

ACMMP++_ref															92.97 268

ACMMP++															93.61 255

Test By Simon												94.64 87

ITE_SJBPF				95.44 290	97.42 247	91.32 303		97.50 298	95.09 146	93.59 266	98.35 172	81.70 313	98.88 228	89.71 308	93.39 262	96.12 329

DeepMVS_CX				86.78 348	97.09 270	72.30 374		95.17 357	75.92 366	84.34 360	95.19 344	70.58 363	95.35 362	79.98 361	89.04 316	92.68 365

High-resolution multi-view benchmark