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.

MVS_111021_HR		98.72 31	98.62 29	99.01 88	99.36 107	97.18 124	99.93 97	99.90 1	96.81 67	98.67 134	99.77 70	93.92 104	99.89 117	99.27 73	99.94 59	99.96 74

MVS_111021_LR		98.42 52	98.38 41	98.53 129	99.39 105	95.79 187	99.87 130	99.86 2	96.70 70	98.78 125	99.79 62	92.03 163	99.90 112	99.17 77	99.86 79	99.88 97

CHOSEN 1792x2688		96.81 152	96.53 151	97.64 195	98.91 149	93.07 287	99.65 217	99.80 3	95.64 109	95.39 255	98.86 222	84.35 291	99.90 112	96.98 193	99.16 144	99.95 82

HyFIR lowres test		96.66 164	96.43 156	97.36 224	99.05 128	93.91 267	99.70 207	99.80 3	90.54 319	96.26 230	98.08 282	92.15 160	98.23 297	96.84 200	95.46 268	99.93 87

test2506		97.53 114	97.19 120	98.58 121	98.66 167	96.90 139	98.81 348	99.77 5	94.93 125	97.95 169	98.96 201	92.51 150	99.20 200	94.93 236	98.15 182	99.64 135

MM		98.83 24	98.53 33	99.76 10	99.59 91	99.33 8	99.99 5	99.76 6	98.39 4	99.39 88	99.80 58	90.49 191	99.96 75	99.89 21	99.43 129	99.98 56

thres100view900		96.74 159	95.92 184	99.18 62	98.90 150	98.77 46	99.74 186	99.71 7	92.59 243	95.84 242	98.86 222	89.25 208	99.50 179	93.84 265	94.57 282	99.27 220

tfpn200view9		96.79 153	95.99 172	99.19 61	98.94 140	98.82 38	99.78 168	99.71 7	92.86 224	96.02 238	98.87 220	89.33 206	99.50 179	93.84 265	94.57 282	99.27 220

thres600view7		96.69 162	95.87 187	99.14 72	98.90 150	98.78 45	99.74 186	99.71 7	92.59 243	95.84 242	98.86 222	89.25 208	99.50 179	93.44 278	94.50 285	99.16 229

thres400		96.78 155	95.99 172	99.16 68	98.94 140	98.82 38	99.78 168	99.71 7	92.86 224	96.02 238	98.87 220	89.33 206	99.50 179	93.84 265	94.57 282	99.16 229

thres200		96.96 145	96.21 165	99.22 58	98.97 138	98.84 37	99.85 144	99.71 7	93.17 209	96.26 230	98.88 213	89.87 199	99.51 177	94.26 256	94.91 278	99.31 211

PVSNet	91.05 13	97.13 135	96.69 145	98.45 137	99.52 98	95.81 186	99.95 72	99.65 12	94.73 135	99.04 113	99.21 172	84.48 289	99.95 84	94.92 237	98.74 163	99.58 155

PVSNet_0	88.03 19	91.80 324	90.27 338	96.38 261	98.27 201	90.46 356	99.94 90	99.61 13	93.99 174	86.26 396	97.39 304	71.13 406	99.89 117	98.77 105	67.05 456	98.79 261

WTY-MVS		98.10 76	97.60 98	99.60 23	98.92 145	99.28 17	99.89 124	99.52 14	95.58 111	98.24 161	99.39 148	93.33 120	99.74 155	97.98 156	95.58 267	99.78 114

HY-MVS	92.50 7	97.79 99	97.17 122	99.63 18	98.98 137	99.32 9	97.49 407	99.52 14	95.69 108	98.32 155	97.41 302	93.32 121	99.77 149	98.08 149	95.75 258	99.81 108

EPNet		98.49 45	98.40 39	98.77 104	99.62 90	96.80 144	99.90 114	99.51 16	97.60 34	99.20 99	99.36 151	93.71 112	99.91 110	97.99 154	98.71 164	99.61 146
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PGM-MVS		98.34 58	98.13 60	98.99 89	99.92 35	97.00 134	99.75 183	99.50 17	93.90 181	99.37 89	99.76 72	93.24 126	100.00 1	97.75 171	99.96 46	99.98 56

ACMMP		97.74 103	97.44 107	98.66 112	99.92 35	96.13 177	99.18 297	99.45 18	94.84 131	96.41 227	99.71 97	91.40 170	99.99 39	97.99 154	98.03 189	99.87 99
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
MG-MVS		98.91 22	98.65 27	99.68 17	99.94 16	99.07 25	99.64 221	99.44 19	97.33 44	99.00 115	99.72 94	94.03 102	99.98 50	98.73 108	100.00 1	100.00 1

EPMVS		96.53 171	96.01 171	98.09 161	98.43 188	96.12 179	96.36 431	99.43 20	93.53 193	97.64 182	95.04 394	94.41 83	98.38 281	91.13 312	98.11 185	99.75 117

CHOSEN 280x420		99.01 17	99.03 10	98.95 94	99.38 106	98.87 34	98.46 373	99.42 21	97.03 57	99.02 114	99.09 182	99.35 2	98.21 298	99.73 45	99.78 88	99.77 115

D2MVS		92.76 301	92.59 297	93.27 368	95.13 367	89.54 374	99.69 210	99.38 22	92.26 262	87.59 375	94.61 409	85.05 277	97.79 320	91.59 306	88.01 337	92.47 423

sss		97.57 113	97.03 127	99.18 62	98.37 192	98.04 82	99.73 193	99.38 22	93.46 196	98.76 130	99.06 187	91.21 172	99.89 117	96.33 211	97.01 226	99.62 142

PAPM		98.60 37	98.42 38	99.14 72	96.05 338	98.96 27	99.90 114	99.35 24	96.68 71	98.35 154	99.66 115	96.45 35	98.51 264	99.45 65	99.89 74	99.96 74

MGCNet		99.06 14	98.84 20	99.72 14	99.76 72	99.21 22	99.99 5	99.34 25	98.70 2	99.44 80	99.75 80	93.24 126	99.99 39	99.94 14	99.41 131	99.95 82

UGNet		95.33 222	94.57 234	97.62 199	98.55 176	94.85 232	98.67 362	99.32 26	95.75 106	96.80 212	96.27 341	72.18 399	99.96 75	94.58 249	99.05 151	98.04 287
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
test_yl		97.83 92	97.37 111	99.21 59	99.18 118	97.98 85	99.64 221	99.27 27	91.43 289	97.88 174	98.99 195	95.84 45	99.84 137	98.82 101	95.32 273	99.79 111

DCV-MVSNet		97.83 92	97.37 111	99.21 59	99.18 118	97.98 85	99.64 221	99.27 27	91.43 289	97.88 174	98.99 195	95.84 45	99.84 137	98.82 101	95.32 273	99.79 111

SymmetryMVS		97.64 110	97.46 104	98.17 153	98.74 161	95.39 209	99.61 228	99.26 29	96.52 76	98.61 138	99.31 156	92.73 141	99.67 167	96.77 201	95.63 265	99.45 185

lecture		98.67 33	98.46 36	99.28 52	99.86 57	97.88 91	99.97 39	99.25 30	96.07 96	99.79 35	99.70 100	92.53 149	99.98 50	99.51 59	99.48 121	99.97 66

testing3-2		97.72 106	97.43 109	98.60 117	98.55 176	97.11 130	100.00 1	99.23 31	93.78 185	97.90 171	98.73 233	95.50 52	99.69 163	98.53 121	94.63 280	98.99 247

VNet		97.21 131	96.57 150	99.13 76	98.97 138	97.82 94	99.03 318	99.21 32	94.31 158	99.18 102	98.88 213	86.26 255	99.89 117	98.93 92	94.32 286	99.69 126

testing3		93.92 269	94.23 242	92.99 376	97.54 260	90.23 360	99.99 5	99.16 33	90.57 318	91.33 307	98.63 245	92.99 132	92.52 453	82.46 407	95.39 271	96.22 320

PVSNet_BlendedMVS		96.05 194	95.82 188	96.72 248	99.59 91	96.99 135	99.95 72	99.10 34	94.06 171	98.27 157	95.80 354	89.00 214	99.95 84	99.12 78	87.53 346	93.24 408

PVSNet_Blended		97.94 82	97.64 96	98.83 99	99.59 91	96.99 135	100.00 1	99.10 34	95.38 116	98.27 157	99.08 183	89.00 214	99.95 84	99.12 78	99.25 140	99.57 157

UniMVSNet_NR-MVSNet		92.95 297	92.11 304	95.49 284	94.61 377	95.28 218	99.83 156	99.08 36	91.49 284	89.21 347	96.86 322	87.14 239	96.73 380	93.20 280	77.52 420	94.46 330

CSCG		97.10 136	97.04 126	97.27 229	99.89 49	91.92 318	99.90 114	99.07 37	88.67 359	95.26 259	99.82 53	93.17 129	99.98 50	98.15 144	99.47 124	99.90 95

PatchMatch-RL		96.04 195	95.40 203	97.95 168	99.59 91	95.22 222	99.52 248	99.07 37	93.96 176	96.49 223	98.35 269	82.28 306	99.82 141	90.15 334	99.22 143	98.81 260

VPA-MVSNet		92.70 303	91.55 316	96.16 266	95.09 368	96.20 173	98.88 339	99.00 39	91.02 304	91.82 302	95.29 385	76.05 376	97.96 313	95.62 225	81.19 391	94.30 344

SDMVSNet		94.80 237	93.96 252	97.33 227	98.92 145	95.42 206	99.59 233	98.99 40	92.41 252	92.55 295	97.85 293	75.81 377	98.93 220	97.90 160	91.62 307	97.64 299

CVMVSNet		94.68 245	94.94 224	93.89 352	96.80 316	86.92 405	99.06 311	98.98 41	94.45 146	94.23 275	99.02 190	85.60 266	95.31 425	90.91 319	95.39 271	99.43 189

UniMVSNet (Re)		93.07 295	92.13 303	95.88 274	94.84 372	96.24 172	99.88 127	98.98 41	92.49 250	89.25 344	95.40 375	87.09 240	97.14 350	93.13 284	78.16 415	94.26 346

fmvsm_s_conf0.5_n		97.80 97	97.85 85	97.67 192	99.06 127	94.41 249	99.98 21	98.97 43	97.34 42	99.63 57	99.69 104	87.27 237	99.97 63	99.62 55	99.06 150	98.62 269

h-mvs33		94.92 234	94.36 238	96.59 252	98.85 154	91.29 338	98.93 333	98.94 44	95.90 99	98.77 127	98.42 267	90.89 184	99.77 149	97.80 164	70.76 444	98.72 266

tfpnnormal		89.29 376	87.61 383	94.34 334	94.35 382	94.13 260	98.95 330	98.94 44	83.94 416	84.47 409	95.51 369	74.84 386	97.39 333	77.05 438	80.41 402	91.48 433

MVS		96.60 166	95.56 198	99.72 14	96.85 313	99.22 21	98.31 382	98.94 44	91.57 282	90.90 311	99.61 123	86.66 249	99.96 75	97.36 178	99.88 77	99.99 24

WR-MVS_H		91.30 331	90.35 335	94.15 338	94.17 386	92.62 303	99.17 298	98.94 44	88.87 354	86.48 392	94.46 414	84.36 290	96.61 385	88.19 356	78.51 413	93.21 409

FIs		94.10 265	93.43 269	96.11 267	94.70 375	96.82 141	99.58 235	98.93 48	92.54 246	89.34 342	97.31 305	87.62 229	97.10 354	94.22 258	86.58 350	94.40 336

fmvsm_s_conf0.5_n_a		97.73 105	97.72 90	97.77 186	98.63 171	94.26 256	99.96 53	98.92 49	97.18 52	99.75 40	99.69 104	87.00 243	99.97 63	99.46 64	98.89 155	99.08 239

test_fmvsm_n_1920		98.44 49	98.61 30	97.92 172	99.27 114	95.18 224	100.00 1	98.90 50	98.05 20	99.80 26	99.73 91	92.64 144	99.99 39	99.58 57	99.51 117	98.59 270

EPNet_dtu		95.71 209	95.39 204	96.66 250	98.92 145	93.41 281	99.57 238	98.90 50	96.19 94	97.52 184	98.56 254	92.65 143	97.36 334	77.89 433	98.33 174	99.20 227
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
patch_mono-2		98.24 69	99.12 5	95.59 283	99.67 87	86.91 406	99.95 72	98.89 52	97.60 34	99.90 6	99.76 72	96.54 34	99.98 50	99.94 14	99.82 85	99.88 97

FC-MVSNet-test		93.81 274	93.15 282	95.80 279	94.30 383	96.20 173	99.42 265	98.89 52	92.33 257	89.03 352	97.27 307	87.39 235	96.83 376	93.20 280	86.48 351	94.36 338

MED-MVS test				99.60 23	99.96 8	98.79 41	99.97 39	98.88 54	96.36 88	99.07 109	99.93 11		100.00 1	99.98 9	99.96 46	99.99 24

MED-MVS		99.15 8	99.00 12	99.60 23	99.96 8	98.79 41	99.97 39	98.88 54	95.89 101	99.07 109	99.93 11	97.36 17	100.00 1	99.98 9	99.96 46	99.99 24

TestfortrainingZip a		99.09 10	98.87 19	99.76 10	99.96 8	99.27 18	99.97 39	98.88 54	96.36 88	99.07 109	99.93 11	97.36 17	100.00 1	98.32 133	99.96 46	100.00 1

baseline2		96.71 161	96.49 152	97.37 222	95.63 361	95.96 182	99.74 186	98.88 54	92.94 220	91.61 303	98.97 199	97.72 6	98.62 258	94.83 241	98.08 188	97.53 306

API-MVS		97.86 88	97.66 94	98.47 134	99.52 98	95.41 207	99.47 258	98.87 58	91.68 280	98.84 121	99.85 37	92.34 156	99.99 39	98.44 126	99.96 46	100.00 1

fmvsm_l_conf0.5_n		98.94 19	98.84 20	99.25 55	99.17 120	97.81 95	99.98 21	98.86 59	98.25 5	99.90 6	99.76 72	94.21 97	99.97 63	99.87 25	99.52 114	99.98 56

1314		96.84 151	95.96 178	99.48 39	96.74 321	98.52 62	98.31 382	98.86 59	95.82 103	89.91 324	98.98 197	87.49 233	99.96 75	97.80 164	99.73 91	99.96 74

MSLP-MVS++		99.13 9	99.01 11	99.49 36	99.94 16	98.46 66	99.98 21	98.86 59	97.10 53	99.80 26	99.94 4	95.92 43	100.00 1	99.51 59	100.00 1	100.00 1

reproduce_monomvs		95.38 220	95.07 218	96.32 263	99.32 111	96.60 153	99.76 179	98.85 62	96.65 72	87.83 372	96.05 351	99.52 1	98.11 303	96.58 207	81.07 396	94.25 348

fmvsm_l_conf0.5_n_a		99.00 18	98.91 15	99.28 52	99.21 116	97.91 90	99.98 21	98.85 62	98.25 5	99.92 4	99.75 80	94.72 74	99.97 63	99.87 25	99.64 97	99.95 82

sd_testset		93.55 283	92.83 287	95.74 281	98.92 145	90.89 346	98.24 386	98.85 62	92.41 252	92.55 295	97.85 293	71.07 407	98.68 250	93.93 262	91.62 307	97.64 299

AdaColmap		97.23 130	96.80 139	98.51 132	99.99 1	95.60 199	99.09 304	98.84 65	93.32 202	96.74 213	99.72 94	86.04 258	100.00 1	98.01 152	99.43 129	99.94 86

test_fmvsmconf_n		98.43 51	98.32 47	98.78 102	98.12 214	96.41 160	99.99 5	98.83 66	98.22 7	99.67 51	99.64 118	91.11 177	99.94 93	99.67 52	99.62 100	99.98 56

fmvsm_s_conf0.5_n_8		98.38 57	98.05 66	99.35 49	99.20 117	98.12 76	99.98 21	98.81 67	98.22 7	99.80 26	99.71 97	87.37 236	99.97 63	99.91 19	99.48 121	99.97 66

fmvsm_s_conf0.5_n_3		97.95 81	97.66 94	98.81 100	98.99 135	98.07 79	99.98 21	98.81 67	98.18 12	99.89 10	99.70 100	84.15 292	99.97 63	99.76 40	99.50 119	98.39 277

IB-MVS	92.85 6	94.99 232	93.94 253	98.16 154	97.72 241	95.69 195	99.99 5	98.81 67	94.28 161	92.70 293	96.90 319	95.08 61	99.17 203	96.07 215	73.88 437	99.60 148
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
3Dnovator	91.47 12	96.28 187	95.34 206	99.08 81	96.82 315	97.47 113	99.45 263	98.81 67	95.52 114	89.39 340	99.00 194	81.97 309	99.95 84	97.27 180	99.83 81	99.84 103

ME-MVS		99.07 12	98.89 17	99.59 26	99.93 27	98.79 41	99.95 72	98.80 71	95.89 101	99.28 96	99.93 11	96.28 37	99.98 50	99.98 9	99.96 46	99.99 24

PHI-MVS		98.41 53	98.21 53	99.03 84	99.86 57	97.10 131	99.98 21	98.80 71	90.78 315	99.62 60	99.78 66	95.30 56	100.00 1	99.80 32	99.93 65	99.99 24

fmvsm_s_conf0.5_n_10		98.24 69	97.90 80	99.26 54	99.24 115	97.88 91	99.99 5	98.76 73	98.20 9	99.92 4	99.74 87	85.97 260	99.94 93	99.72 46	99.53 113	99.96 74

fmvsm_s_conf0.5_n_4		97.75 102	97.86 84	97.42 218	99.01 130	94.69 239	99.97 39	98.76 73	97.91 25	99.87 13	99.76 72	86.70 248	99.93 103	99.67 52	99.12 148	97.64 299

MAR-MVS		97.43 117	97.19 120	98.15 157	99.47 102	94.79 236	99.05 315	98.76 73	92.65 239	98.66 135	99.82 53	88.52 220	99.98 50	98.12 145	99.63 99	99.67 129
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
DU-MVS		92.46 310	91.45 319	95.49 284	94.05 387	95.28 218	99.81 161	98.74 76	92.25 263	89.21 347	96.64 330	81.66 314	96.73 380	93.20 280	77.52 420	94.46 330

tt0805		91.28 333	90.18 341	94.60 318	96.26 333	87.55 398	98.39 380	98.72 77	89.00 347	89.22 346	98.47 264	62.98 438	98.96 218	90.57 325	88.00 338	97.28 309

无先验							99.49 254	98.71 78	93.46 196				100.00 1	94.36 252		99.99 24

fmvsm_l_conf0.5_n_9		98.55 40	98.23 51	99.49 36	99.10 124	98.50 64	99.99 5	98.70 79	98.14 16	99.94 1	99.68 111	89.02 213	99.98 50	99.89 21	99.61 104	99.99 24

NR-MVSNet		91.56 329	90.22 339	95.60 282	94.05 387	95.76 189	98.25 385	98.70 79	91.16 298	80.78 429	96.64 330	83.23 300	96.57 386	91.41 308	77.73 419	94.46 330

FE-MVS		95.70 211	95.01 221	97.79 182	98.21 205	94.57 241	95.03 445	98.69 81	88.90 353	97.50 186	96.19 343	92.60 146	99.49 184	89.99 336	97.94 191	99.31 211

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 21	98.69 81	98.20 9	99.93 2	99.98 2	96.82 26	100.00 1	99.75 41	100.00 1	99.99 24

WR-MVS		92.31 313	91.25 321	95.48 287	94.45 380	95.29 217	99.60 231	98.68 83	90.10 330	88.07 369	96.89 320	80.68 328	96.80 378	93.14 283	79.67 408	94.36 338

ab-mvs		94.69 243	93.42 270	98.51 132	98.07 216	96.26 167	96.49 429	98.68 83	90.31 327	94.54 264	97.00 317	76.30 372	99.71 159	95.98 217	93.38 300	99.56 158

QAPM		95.40 219	94.17 244	99.10 78	96.92 307	97.71 99	99.40 266	98.68 83	89.31 341	88.94 353	98.89 212	82.48 305	99.96 75	93.12 285	99.83 81	99.62 142

Anonymous20240529		92.10 317	90.65 329	96.47 254	98.82 155	90.61 352	98.72 356	98.67 86	75.54 451	93.90 279	98.58 252	66.23 425	99.90 112	94.70 246	90.67 310	98.90 256

fmvsm_s_conf0.5_n_7		97.70 108	97.74 89	97.59 204	98.44 187	95.16 226	99.97 39	98.65 87	97.95 24	99.62 60	99.78 66	86.09 257	99.94 93	99.69 50	99.50 119	97.66 297

test_prior				99.43 40	99.94 16	98.49 65		98.65 87					99.80 142			99.99 24

TranMVSNet+NR-MVSNet		91.68 328	90.61 331	94.87 307	93.69 394	93.98 265	99.69 210	98.65 87	91.03 303	88.44 362	96.83 326	80.05 337	96.18 404	90.26 333	76.89 428	94.45 335

fmvsm_s_conf0.5_n_6		98.27 63	97.96 75	99.23 57	97.66 249	98.11 77	99.98 21	98.64 90	97.85 27	99.87 13	99.72 94	88.86 216	99.93 103	99.64 54	99.36 135	99.63 141

fmvsm_l_conf0.5_n_3		98.41 53	98.08 64	99.39 45	99.12 123	98.29 69	99.98 21	98.64 90	98.14 16	99.86 15	99.76 72	87.99 225	99.97 63	99.72 46	99.54 111	99.91 94

fmvsm_s_conf0.1_n		97.30 125	97.21 119	97.60 201	97.38 273	94.40 251	99.90 114	98.64 90	96.47 80	99.51 76	99.65 117	84.99 278	99.93 103	99.22 75	99.09 149	98.46 273

旧先验1					99.76 72	97.52 108		98.64 90			99.85 37	95.63 48			99.94 59	99.99 24

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 39	98.64 90	98.47 3	99.13 104	99.92 17	96.38 36	100.00 1	99.74 43	100.00 1	100.00 1

PVSNet_Blended_VisFu		97.27 127	96.81 138	98.66 112	98.81 156	96.67 149	99.92 100	98.64 90	94.51 143	96.38 228	98.49 260	89.05 212	99.88 123	97.10 188	98.34 173	99.43 189

新几何1				99.42 42	99.75 75	98.27 70		98.63 96	92.69 236	99.55 69	99.82 53	94.40 84	100.00 1	91.21 310	99.94 59	99.99 24

NCCC		99.37 2	99.25 2	99.71 16	99.96 8	99.15 23	99.97 39	98.62 97	98.02 22	99.90 6	99.95 3	97.33 19	100.00 1	99.54 58	100.00 1	100.00 1

testing222		97.08 141	96.75 141	98.06 163	98.56 173	96.82 141	99.85 144	98.61 98	92.53 247	98.84 121	98.84 226	93.36 118	98.30 289	95.84 220	94.30 287	99.05 243

HFP-MVS		98.56 39	98.37 43	99.14 72	99.96 8	97.43 114	99.95 72	98.61 98	94.77 133	99.31 92	99.85 37	94.22 95	100.00 1	98.70 109	99.98 32	99.98 56

UWE-MVS		96.79 153	96.72 143	97.00 236	98.51 181	93.70 272	99.71 200	98.60 100	92.96 219	97.09 199	98.34 271	96.67 33	98.85 226	92.11 299	96.50 235	98.44 275

ACMMPR		98.50 44	98.32 47	99.05 82	99.96 8	97.18 124	99.95 72	98.60 100	94.77 133	99.31 92	99.84 48	93.73 111	100.00 1	98.70 109	99.98 32	99.98 56

fmvsm_s_conf0.5_n_2		97.59 112	97.28 115	98.53 129	99.01 130	98.15 71	99.98 21	98.59 102	98.17 13	99.75 40	99.63 121	81.83 312	99.94 93	99.78 35	98.79 161	97.51 307

VPNet		91.81 321	90.46 332	95.85 276	94.74 374	95.54 201	98.98 323	98.59 102	92.14 264	90.77 315	97.44 301	68.73 414	97.54 330	94.89 240	77.89 417	94.46 330

test0.0.03 1		93.86 270	93.61 260	94.64 316	95.02 371	92.18 312	99.93 97	98.58 104	94.07 169	87.96 370	98.50 259	93.90 106	94.96 429	81.33 414	93.17 301	96.78 312

DELS-MVS		98.54 41	98.22 52	99.50 34	99.15 122	98.65 57	100.00 1	98.58 104	97.70 32	98.21 162	99.24 168	92.58 147	99.94 93	98.63 116	99.94 59	99.92 92
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
fmvsm_s_conf0.5_n_9		98.15 73	98.02 68	98.55 123	99.28 112	95.84 185	99.99 5	98.57 106	98.17 13	99.93 2	99.74 87	87.04 241	99.97 63	99.86 27	99.59 108	99.83 104

fmvsm_s_conf0.5_n_5		98.08 77	97.71 92	99.17 65	98.67 165	97.69 103	99.99 5	98.57 106	97.40 40	99.89 10	99.69 104	85.99 259	99.96 75	99.80 32	99.40 132	99.85 102

UWE-MVS-28		95.95 197	96.49 152	94.34 334	98.51 181	89.99 366	99.39 270	98.57 106	93.14 211	97.33 192	98.31 274	93.44 116	94.68 434	93.69 275	95.98 248	98.34 280

ETVMVS		97.03 142	96.64 146	98.20 152	98.67 165	97.12 128	99.89 124	98.57 106	91.10 301	98.17 163	98.59 249	93.86 108	98.19 299	95.64 224	95.24 275	99.28 218

CP-MVSNet		91.23 335	90.22 339	94.26 336	93.96 389	92.39 308	99.09 304	98.57 106	88.95 351	86.42 393	96.57 333	79.19 344	96.37 395	90.29 332	78.95 410	94.02 372

OpenMVS	90.15 15	94.77 240	93.59 263	98.33 145	96.07 337	97.48 112	99.56 241	98.57 106	90.46 322	86.51 390	98.95 206	78.57 351	99.94 93	93.86 264	99.74 90	97.57 304

hse-mvs2		94.38 257	94.08 248	95.31 295	98.27 201	90.02 365	99.29 287	98.56 112	95.90 99	98.77 127	98.00 285	90.89 184	98.26 296	97.80 164	69.20 450	97.64 299

AUN-MVS		93.28 288	92.60 293	95.34 293	98.29 198	90.09 364	99.31 282	98.56 112	91.80 278	96.35 229	98.00 285	89.38 205	98.28 292	92.46 290	69.22 449	97.64 299

HPM-MVS++		99.07 12	98.88 18	99.63 18	99.90 46	99.02 26	99.95 72	98.56 112	97.56 37	99.44 80	99.85 37	95.38 55	100.00 1	99.31 71	99.99 21	99.87 99

testdata				98.42 141	99.47 102	95.33 213		98.56 112	93.78 185	99.79 35	99.85 37	93.64 114	99.94 93	94.97 235	99.94 59	100.00 1

EPP-MVSNet		96.69 162	96.60 148	96.96 238	97.74 236	93.05 289	99.37 274	98.56 112	88.75 357	95.83 244	99.01 192	96.01 39	98.56 261	96.92 197	97.20 212	99.25 222

DeepPCF-MVS	95.94 2	97.71 107	98.98 13	93.92 349	99.63 89	81.76 441	99.96 53	98.56 112	99.47 1	99.19 101	99.99 1	94.16 99	100.00 1	99.92 16	99.93 65	100.00 1

myMVS_eth3d28		97.86 88	97.59 100	98.68 109	98.50 183	97.26 120	99.92 100	98.55 118	93.79 184	98.26 159	98.75 231	95.20 57	99.48 185	98.93 92	96.40 238	99.29 216

region2R		98.54 41	98.37 43	99.05 82	99.96 8	97.18 124	99.96 53	98.55 118	94.87 130	99.45 79	99.85 37	94.07 101	100.00 1	98.67 111	100.00 1	99.98 56

test222					99.55 96	97.41 116	99.34 278	98.55 118	91.86 274	99.27 97	99.83 50	93.84 109			99.95 54	99.99 24

tpmvs		94.28 262	93.57 264	96.40 259	98.55 176	91.50 336	95.70 444	98.55 118	87.47 376	92.15 298	94.26 417	91.42 169	98.95 219	88.15 357	95.85 254	98.76 262

thisisatest0530		97.10 136	96.72 143	98.22 151	97.60 255	96.70 145	99.92 100	98.54 122	91.11 300	97.07 201	98.97 199	97.47 12	99.03 211	93.73 273	96.09 245	98.92 253

tttt0517		96.85 150	96.49 152	97.92 172	97.48 266	95.89 184	99.85 144	98.54 122	90.72 317	96.63 215	98.93 211	97.47 12	99.02 212	93.03 286	95.76 257	98.85 257

thisisatest0515		97.41 122	97.02 128	98.59 120	97.71 243	97.52 108	99.97 39	98.54 122	91.83 275	97.45 187	99.04 189	97.50 9	99.10 208	94.75 244	96.37 240	99.16 229

kuosan		93.17 291	92.60 293	94.86 310	98.40 189	89.54 374	98.44 375	98.53 125	84.46 414	88.49 360	97.92 290	90.57 188	97.05 357	83.10 403	93.49 297	97.99 288

UBG		97.84 91	97.69 93	98.29 148	98.38 190	96.59 155	99.90 114	98.53 125	93.91 180	98.52 142	98.42 267	96.77 27	99.17 203	98.54 119	96.20 242	99.11 236

ZD-MVS					99.92 35	98.57 60		98.52 127	92.34 256	99.31 92	99.83 50	95.06 62	99.80 142	99.70 49	99.97 42

GG-mvs-BLEND				98.54 127	98.21 205	98.01 83	93.87 450	98.52 127		97.92 170	97.92 290	99.02 3	97.94 316	98.17 142	99.58 109	99.67 129

PS-CasMVS		90.63 348	89.51 355	93.99 347	93.83 391	91.70 327	98.98 323	98.52 127	88.48 363	86.15 397	96.53 335	75.46 379	96.31 399	88.83 347	78.86 412	93.95 380

dongtai		91.55 330	91.13 323	92.82 379	98.16 210	86.35 407	99.47 258	98.51 130	83.24 422	85.07 406	97.56 298	90.33 193	94.94 430	76.09 441	91.73 305	97.18 310

dmvs_re		93.20 290	93.15 282	93.34 365	96.54 327	83.81 423	98.71 357	98.51 130	91.39 293	92.37 297	98.56 254	78.66 350	97.83 319	93.89 263	89.74 311	98.38 278

CANet		98.27 63	97.82 87	99.63 18	99.72 81	99.10 24	99.98 21	98.51 130	97.00 59	98.52 142	99.71 97	87.80 226	99.95 84	99.75 41	99.38 133	99.83 104

gg-mvs-nofinetune		93.51 284	91.86 311	98.47 134	97.72 241	97.96 88	92.62 456	98.51 130	74.70 454	97.33 192	69.59 471	98.91 4	97.79 320	97.77 169	99.56 110	99.67 129

EI-MVSNet-Vis-set		98.27 63	98.11 62	98.75 105	99.83 63	96.59 155	99.40 266	98.51 130	95.29 119	98.51 144	99.76 72	93.60 115	99.71 159	98.53 121	99.52 114	99.95 82

原ACMM1				98.96 93	99.73 79	96.99 135		98.51 130	94.06 171	99.62 60	99.85 37	94.97 68	99.96 75	95.11 231	99.95 54	99.92 92

fmvsm_s_conf0.1_n_a		97.09 138	96.90 131	97.63 198	95.65 359	94.21 258	99.83 156	98.50 136	96.27 91	99.65 53	99.64 118	84.72 284	99.93 103	99.04 84	98.84 158	98.74 264

EI-MVSNet-UG-set		98.14 74	97.99 70	98.60 117	99.80 67	96.27 166	99.36 276	98.50 136	95.21 121	98.30 156	99.75 80	93.29 123	99.73 158	98.37 130	99.30 138	99.81 108

LS3D		95.84 203	95.11 216	98.02 166	99.85 60	95.10 227	98.74 354	98.50 136	87.22 381	93.66 280	99.86 33	87.45 234	99.95 84	90.94 318	99.81 87	99.02 245

PEN-MVS		90.19 360	89.06 363	93.57 361	93.06 406	90.90 345	99.06 311	98.47 139	88.11 368	85.91 399	96.30 340	76.67 366	95.94 414	87.07 371	76.91 427	93.89 385

DeepC-MVS_fast	96.59 1	98.81 26	98.54 32	99.62 21	99.90 46	98.85 36	99.24 292	98.47 139	98.14 16	99.08 107	99.91 18	93.09 130	100.00 1	99.04 84	99.99 21	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PLC	95.54 3	97.93 83	97.89 82	98.05 164	99.82 64	94.77 237	99.92 100	98.46 141	93.93 178	97.20 196	99.27 161	95.44 54	99.97 63	97.41 176	99.51 117	99.41 192
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
testing11		97.48 116	97.27 116	98.10 160	98.36 193	96.02 180	99.92 100	98.45 142	93.45 198	98.15 164	98.70 236	95.48 53	99.22 196	97.85 162	95.05 277	99.07 240

test_fmvsmvis_n_1920		97.67 109	97.59 100	97.91 174	97.02 298	95.34 212	99.95 72	98.45 142	97.87 26	97.02 202	99.59 124	89.64 201	99.98 50	99.41 68	99.34 137	98.42 276

test1111		95.57 215	94.98 222	97.37 222	98.56 173	93.37 284	98.86 343	98.45 142	94.95 124	96.63 215	98.95 206	75.21 384	99.11 206	95.02 233	98.14 184	99.64 135

ECVR-MVS		95.66 212	95.05 219	97.51 211	98.66 167	93.71 271	98.85 345	98.45 142	94.93 125	96.86 209	98.96 201	75.22 383	99.20 200	95.34 226	98.15 182	99.64 135

UA-Net		96.54 170	95.96 178	98.27 149	98.23 203	95.71 192	98.00 398	98.45 142	93.72 189	98.41 150	99.27 161	88.71 219	99.66 170	91.19 311	97.69 194	99.44 188

ZNCC-MVS		98.31 60	98.03 67	99.17 65	99.88 53	97.59 105	99.94 90	98.44 147	94.31 158	98.50 145	99.82 53	93.06 131	99.99 39	98.30 135	99.99 21	99.93 87

DPM-MVS		98.83 24	98.46 36	99.97 1	99.33 109	99.92 1	99.96 53	98.44 147	97.96 23	99.55 69	99.94 4	97.18 23	100.00 1	93.81 268	99.94 59	99.98 56

DPE-MVS		99.26 6	99.10 8	99.74 12	99.89 49	99.24 20	99.87 130	98.44 147	97.48 39	99.64 56	99.94 4	96.68 31	99.99 39	99.99 5	100.00 1	99.99 24
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
alignmvs		97.81 96	97.33 113	99.25 55	98.77 159	98.66 55	99.99 5	98.44 147	94.40 154	98.41 150	99.47 137	93.65 113	99.42 189	98.57 117	94.26 288	99.67 129

test11								98.44 147

SteuartSystems-ACMMP		99.02 16	98.97 14	99.18 62	98.72 162	97.71 99	99.98 21	98.44 147	96.85 62	99.80 26	99.91 18	97.57 8	99.85 129	99.44 66	99.99 21	99.99 24
Skip Steuart: Steuart Systems R&D Blog.
MDTV_nov1_ep13			95.69 193		97.90 225	94.15 259	95.98 440	98.44 147	93.12 213	97.98 168	95.74 356	95.10 60	98.58 259	90.02 335	96.92 228

DP-MVS Recon		98.41 53	98.02 68	99.56 29	99.97 3	98.70 52	99.92 100	98.44 147	92.06 268	98.40 152	99.84 48	95.68 47	100.00 1	98.19 141	99.71 92	99.97 66

testing99		97.17 132	96.91 130	97.95 168	98.35 195	95.70 193	99.91 108	98.43 155	92.94 220	97.36 190	98.72 234	94.83 70	99.21 197	97.00 191	94.64 279	98.95 249

DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 43	99.31 10	99.95 72	98.43 155	96.48 78	99.80 26	99.93 11	97.44 14	100.00 1	99.92 16	99.98 32	100.00 1

SED-MVS		99.28 5	99.11 7	99.77 8	99.93 27	99.30 12	99.96 53	98.43 155	97.27 47	99.80 26	99.94 4	96.71 29	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_TWO								98.43 155	97.27 47	99.80 26	99.94 4	97.18 23	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 27	99.30 12		98.43 155	97.26 49	99.80 26	99.88 28	96.71 29	100.00 1

test_0728_SECOND				99.82 7	99.94 16	99.47 7	99.95 72	98.43 155					100.00 1	99.99 5	100.00 1	100.00 1

TEST9					99.92 35	98.92 30	99.96 53	98.43 155	93.90 181	99.71 47	99.86 33	95.88 44	99.85 129

train_agg		98.88 23	98.65 27	99.59 26	99.92 35	98.92 30	99.96 53	98.43 155	94.35 155	99.71 47	99.86 33	95.94 41	99.85 129	99.69 50	99.98 32	99.99 24

test_8					99.92 35	98.88 33	99.96 53	98.43 155	94.35 155	99.69 49	99.85 37	95.94 41	99.85 129

agg_prior					99.93 27	98.77 46		98.43 155		99.63 57			99.85 129

PAPM_NR		98.12 75	97.93 78	98.70 108	99.94 16	96.13 177	99.82 159	98.43 155	94.56 141	97.52 184	99.70 100	94.40 84	99.98 50	97.00 191	99.98 32	99.99 24

PAPR		98.52 43	98.16 58	99.58 28	99.97 3	98.77 46	99.95 72	98.43 155	95.35 117	98.03 167	99.75 80	94.03 102	99.98 50	98.11 146	99.83 81	99.99 24

testing91		97.16 133	96.90 131	97.97 167	98.35 195	95.67 196	99.91 108	98.42 167	92.91 222	97.33 192	98.72 234	94.81 71	99.21 197	96.98 193	94.63 280	99.03 244

test0726					99.93 27	99.29 15	99.96 53	98.42 167	97.28 45	99.86 15	99.94 4	97.22 21

MSP-MVS		99.09 10	99.12 5	98.98 91	99.93 27	97.24 121	99.95 72	98.42 167	97.50 38	99.52 74	99.88 28	97.43 16	99.71 159	99.50 61	99.98 32	100.00 1
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
XVS		98.70 32	98.55 31	99.15 70	99.94 16	97.50 110	99.94 90	98.42 167	96.22 92	99.41 84	99.78 66	94.34 89	99.96 75	98.92 94	99.95 54	99.99 24

X-MVStestdata		93.83 271	92.06 306	99.15 70	99.94 16	97.50 110	99.94 90	98.42 167	96.22 92	99.41 84	41.37 480	94.34 89	99.96 75	98.92 94	99.95 54	99.99 24

MSC_two_6792asdad				99.93 2	99.91 43	99.80 2		98.41 172					100.00 1	99.96 12	100.00 1	100.00 1

No_MVS				99.93 2	99.91 43	99.80 2		98.41 172					100.00 1	99.96 12	100.00 1	100.00 1

test_one_0601					99.94 16	99.30 12		98.41 172	96.63 73	99.75 40	99.93 11	97.49 10

IU-MVS					99.93 27	99.31 10		98.41 172	97.71 31	99.84 21				100.00 1	100.00 1	100.00 1

save fliter					99.82 64	98.79 41	99.96 53	98.40 176	97.66 33

test12				99.43 40	99.74 76	98.56 61		98.40 176		99.65 53		94.76 72	99.75 153		99.98 32	99.99 24

PatchmatchNet		95.94 198	95.45 200	97.39 221	97.83 230	94.41 249	96.05 438	98.40 176	92.86 224	97.09 199	95.28 386	94.21 97	98.07 307	89.26 344	98.11 185	99.70 124
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
GST-MVS		98.27 63	97.97 72	99.17 65	99.92 35	97.57 106	99.93 97	98.39 179	94.04 173	98.80 124	99.74 87	92.98 133	100.00 1	98.16 143	99.76 89	99.93 87

APDe-MVS		99.06 14	98.91 15	99.51 33	99.94 16	98.76 49	99.91 108	98.39 179	97.20 51	99.46 78	99.85 37	95.53 51	99.79 144	99.86 27	100.00 1	99.99 24
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MP-MVS		98.23 71	97.97 72	99.03 84	99.94 16	97.17 127	99.95 72	98.39 179	94.70 137	98.26 159	99.81 57	91.84 167	100.00 1	98.85 100	99.97 42	99.93 87
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CP-MVS		98.45 48	98.32 47	98.87 97	99.96 8	96.62 151	99.97 39	98.39 179	94.43 150	98.90 119	99.87 31	94.30 92	100.00 1	99.04 84	99.99 21	99.99 24

SMA-MVS		98.76 29	98.48 35	99.62 21	99.87 55	98.87 34	99.86 141	98.38 183	93.19 207	99.77 38	99.94 4	95.54 49	100.00 1	99.74 43	99.99 21	100.00 1
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
TSAR-MVS + MP.		98.93 20	98.77 22	99.41 43	99.74 76	98.67 53	99.77 173	98.38 183	96.73 69	99.88 12	99.74 87	94.89 69	99.59 173	99.80 32	99.98 32	99.97 66
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
mPP-MVS		98.39 56	98.20 54	98.97 92	99.97 3	96.92 138	99.95 72	98.38 183	95.04 123	98.61 138	99.80 58	93.39 117	100.00 1	98.64 114	100.00 1	99.98 56

ACMMP_NAP		98.49 45	98.14 59	99.54 31	99.66 88	98.62 59	99.85 144	98.37 186	94.68 138	99.53 72	99.83 50	92.87 136	100.00 1	98.66 113	99.84 80	99.99 24

FOURS1					99.92 35	97.66 104	99.95 72	98.36 187	95.58 111	99.52 74

APD-MVS		98.62 36	98.35 46	99.41 43	99.90 46	98.51 63	99.87 130	98.36 187	94.08 168	99.74 43	99.73 91	94.08 100	99.74 155	99.42 67	99.99 21	99.99 24
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
Syy-MVS		90.00 364	90.63 330	88.11 429	97.68 246	74.66 457	99.71 200	98.35 189	90.79 313	92.10 299	98.67 238	79.10 346	93.09 449	63.35 464	95.95 251	96.59 315

myMVS_eth3d		94.46 255	94.76 231	93.55 362	97.68 246	90.97 341	99.71 200	98.35 189	90.79 313	92.10 299	98.67 238	92.46 153	93.09 449	87.13 370	95.95 251	96.59 315

SR-MVS		98.46 47	98.30 50	98.93 95	99.88 53	97.04 133	99.84 149	98.35 189	94.92 127	99.32 91	99.80 58	93.35 119	99.78 146	99.30 72	99.95 54	99.96 74

CPTT-MVS		97.64 110	97.32 114	98.58 121	99.97 3	95.77 188	99.96 53	98.35 189	89.90 335	98.36 153	99.79 62	91.18 176	99.99 39	98.37 130	99.99 21	99.99 24

SD-MVS		98.92 21	98.70 23	99.56 29	99.70 84	98.73 50	99.94 90	98.34 193	96.38 84	99.81 24	99.76 72	94.59 77	99.98 50	99.84 29	99.96 46	99.97 66
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
9.14			98.38 41		99.87 55		99.91 108	98.33 194	93.22 205	99.78 37	99.89 26	94.57 80	99.85 129	99.84 29	99.97 42

CDPH-MVS		98.65 35	98.36 45	99.49 36	99.94 16	98.73 50	99.87 130	98.33 194	93.97 175	99.76 39	99.87 31	94.99 67	99.75 153	98.55 118	100.00 1	99.98 56

DVP-MVS		99.30 4	99.16 3	99.73 13	99.93 27	99.29 15	99.95 72	98.32 196	97.28 45	99.83 22	99.91 18	97.22 21	100.00 1	99.99 5	100.00 1	99.89 96
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
SCA		94.69 243	93.81 257	97.33 227	97.10 292	94.44 246	98.86 343	98.32 196	93.30 203	96.17 235	95.59 364	76.48 370	97.95 314	91.06 314	97.43 200	99.59 149

SR-MVS-dyc-post		98.31 60	98.17 57	98.71 107	99.79 68	96.37 164	99.76 179	98.31 198	94.43 150	99.40 86	99.75 80	93.28 124	99.78 146	98.90 97	99.92 68	99.97 66

RE-MVS-def			98.13 60		99.79 68	96.37 164	99.76 179	98.31 198	94.43 150	99.40 86	99.75 80	92.95 134		98.90 97	99.92 68	99.97 66

RPMNet		89.76 368	87.28 385	97.19 230	96.29 331	92.66 300	92.01 459	98.31 198	70.19 461	96.94 206	85.87 463	87.25 238	99.78 146	62.69 465	95.96 249	99.13 233

APD-MVS_3200maxsize		98.25 68	98.08 64	98.78 102	99.81 66	96.60 153	99.82 159	98.30 201	93.95 177	99.37 89	99.77 70	92.84 137	99.76 152	98.95 90	99.92 68	99.97 66

TESTMET0.1,1		96.74 159	96.26 161	98.16 154	97.36 277	96.48 157	99.96 53	98.29 202	91.93 271	95.77 245	98.07 283	95.54 49	98.29 290	90.55 326	98.89 155	99.70 124

MTGPA								98.28 203

MTAPA		98.29 62	97.96 75	99.30 51	99.85 60	97.93 89	99.39 270	98.28 203	95.76 105	97.18 198	99.88 28	92.74 140	100.00 1	98.67 111	99.88 77	99.99 24

114514_t		97.41 122	96.83 136	99.14 72	99.51 100	97.83 93	99.89 124	98.27 205	88.48 363	99.06 112	99.66 115	90.30 194	99.64 172	96.32 212	99.97 42	99.96 74

Anonymous20231211		89.86 366	88.44 374	94.13 340	98.93 142	90.68 350	98.54 370	98.26 206	76.28 447	86.73 386	95.54 366	70.60 408	97.56 329	90.82 321	80.27 405	94.15 361

reproduce-ours		98.78 27	98.67 24	99.09 79	99.70 84	97.30 118	99.74 186	98.25 207	97.10 53	99.10 105	99.90 22	94.59 77	99.99 39	99.77 37	99.91 71	99.99 24

our_new_method		98.78 27	98.67 24	99.09 79	99.70 84	97.30 118	99.74 186	98.25 207	97.10 53	99.10 105	99.90 22	94.59 77	99.99 39	99.77 37	99.91 71	99.99 24

Vis-MVSNet		95.72 207	95.15 215	97.45 214	97.62 253	94.28 255	99.28 288	98.24 209	94.27 163	96.84 210	98.94 208	79.39 341	98.76 238	93.25 279	98.49 170	99.30 214
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
3Dnovator+	91.53 11	96.31 184	95.24 210	99.52 32	96.88 312	98.64 58	99.72 197	98.24 209	95.27 120	88.42 366	98.98 197	82.76 303	99.94 93	97.10 188	99.83 81	99.96 74

reproduce_model		98.75 30	98.66 26	99.03 84	99.71 82	97.10 131	99.73 193	98.23 211	97.02 58	99.18 102	99.90 22	94.54 81	99.99 39	99.77 37	99.90 73	99.99 24

DTE-MVSNet		89.40 374	88.24 377	92.88 378	92.66 417	89.95 368	99.10 303	98.22 212	87.29 379	85.12 405	96.22 342	76.27 373	95.30 426	83.56 401	75.74 432	93.41 402

SF-MVS		98.67 33	98.40 39	99.50 34	99.77 71	98.67 53	99.90 114	98.21 213	93.53 193	99.81 24	99.89 26	94.70 76	99.86 128	99.84 29	99.93 65	99.96 74

VDDNet		93.12 293	91.91 309	96.76 246	96.67 326	92.65 302	98.69 360	98.21 213	82.81 427	97.75 181	99.28 158	61.57 443	99.48 185	98.09 148	94.09 290	98.15 283

test-LLR		96.47 172	96.04 170	97.78 184	97.02 298	95.44 204	99.96 53	98.21 213	94.07 169	95.55 251	96.38 336	93.90 106	98.27 294	90.42 329	98.83 159	99.64 135

test-mter		96.39 178	95.93 183	97.78 184	97.02 298	95.44 204	99.96 53	98.21 213	91.81 277	95.55 251	96.38 336	95.17 58	98.27 294	90.42 329	98.83 159	99.64 135

MP-MVS-pluss		98.07 78	97.64 96	99.38 48	99.74 76	98.41 68	99.74 186	98.18 217	93.35 200	96.45 224	99.85 37	92.64 144	99.97 63	98.91 96	99.89 74	99.77 115
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
BP-MVS1		98.33 59	98.18 56	98.81 100	97.44 267	97.98 85	99.96 53	98.17 218	94.88 129	98.77 127	99.59 124	97.59 7	99.08 209	98.24 139	98.93 154	99.36 198

FA-MVS(test-final)		95.86 201	95.09 217	98.15 157	97.74 236	95.62 198	96.31 433	98.17 218	91.42 291	96.26 230	96.13 347	90.56 189	99.47 187	92.18 294	97.07 220	99.35 202

PS-MVSNAJ		98.44 49	98.20 54	99.16 68	98.80 157	98.92 30	99.54 246	98.17 218	97.34 42	99.85 18	99.85 37	91.20 173	99.89 117	99.41 68	99.67 95	98.69 267

HPM-MVS		97.96 80	97.72 90	98.68 109	99.84 62	96.39 163	99.90 114	98.17 218	92.61 241	98.62 137	99.57 130	91.87 166	99.67 167	98.87 99	99.99 21	99.99 24
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
tpmrst		96.27 188	95.98 174	97.13 231	97.96 222	93.15 286	96.34 432	98.17 218	92.07 266	98.71 133	95.12 391	93.91 105	98.73 242	94.91 239	96.62 232	99.50 175

WB-MVSnew		92.90 298	92.77 290	93.26 369	96.95 306	93.63 274	99.71 200	98.16 223	91.49 284	94.28 273	98.14 280	81.33 319	96.48 390	79.47 424	95.46 268	89.68 450

ADS-MVSNet		94.79 238	94.02 250	97.11 233	97.87 227	93.79 268	94.24 446	98.16 223	90.07 331	96.43 225	94.48 412	90.29 195	98.19 299	87.44 364	97.23 210	99.36 198

HPM-MVS_fast		97.80 97	97.50 103	98.68 109	99.79 68	96.42 159	99.88 127	98.16 223	91.75 279	98.94 117	99.54 133	91.82 168	99.65 171	97.62 174	99.99 21	99.99 24

Vis-MVSNet (Re-imp)		96.32 183	95.98 174	97.35 226	97.93 224	94.82 234	99.47 258	98.15 226	91.83 275	95.09 260	99.11 181	91.37 171	97.47 332	93.47 277	97.43 200	99.74 118

CNLPA		97.76 101	97.38 110	98.92 96	99.53 97	96.84 140	99.87 130	98.14 227	93.78 185	96.55 221	99.69 104	92.28 157	99.98 50	97.13 186	99.44 128	99.93 87

JIA-IIPM		91.76 327	90.70 328	94.94 305	96.11 336	87.51 399	93.16 455	98.13 228	75.79 450	97.58 183	77.68 468	92.84 137	97.97 311	88.47 354	96.54 233	99.33 205

KinetiMVS		96.10 192	95.29 209	98.53 129	97.08 294	97.12 128	99.56 241	98.12 229	94.78 132	98.44 147	98.94 208	80.30 335	99.39 190	91.56 307	98.79 161	99.06 241

cl22		93.77 276	93.25 280	95.33 294	99.49 101	94.43 247	99.61 228	98.09 230	90.38 323	89.16 350	95.61 362	90.56 189	97.34 336	91.93 301	84.45 367	94.21 353

cdsmvs_eth3d_5k		23.43 446	31.24 449	0.00 464	0.00 487	0.00 489	0.00 476	98.09 230	0.00 482	0.00 483	99.67 113	83.37 298	0.00 483	0.00 482	0.00 481	0.00 479

xiu_mvs_v2_base		98.23 71	97.97 72	99.02 87	98.69 163	98.66 55	99.52 248	98.08 232	97.05 56	99.86 15	99.86 33	90.65 186	99.71 159	99.39 70	98.63 165	98.69 267

tpm cat1		93.51 284	92.52 299	96.47 254	97.77 234	91.47 337	96.13 436	98.06 233	80.98 436	92.91 290	93.78 421	89.66 200	98.87 224	87.03 373	96.39 239	99.09 237

DeepC-MVS	94.51 4	96.92 149	96.40 158	98.45 137	99.16 121	95.90 183	99.66 216	98.06 233	96.37 87	94.37 271	99.49 136	83.29 299	99.90 112	97.63 173	99.61 104	99.55 159
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_fmvsmconf0.1_n		97.74 103	97.44 107	98.64 114	95.76 349	96.20 173	99.94 90	98.05 235	98.17 13	98.89 120	99.42 141	87.65 228	99.90 112	99.50 61	99.60 107	99.82 106

fmvsm_s_conf0.5_n_11		98.03 79	97.89 82	98.46 136	99.35 108	97.76 97	99.99 5	98.04 236	98.20 9	99.90 6	99.78 66	86.21 256	99.95 84	99.89 21	99.68 94	97.65 298

EU-MVSNet		90.14 362	90.34 336	89.54 417	92.55 418	81.06 445	98.69 360	98.04 236	91.41 292	86.59 389	96.84 325	80.83 326	93.31 448	86.20 380	81.91 386	94.26 346

SD_0403		92.63 307	93.38 274	90.40 410	97.32 281	77.91 453	97.75 405	98.03 238	91.89 272	90.83 313	98.29 276	82.00 308	93.79 443	88.51 353	95.75 258	99.52 169

TAPA-MVS	92.12 8	94.42 256	93.60 262	96.90 241	99.33 109	91.78 322	99.78 168	98.00 239	89.89 336	94.52 265	99.47 137	91.97 164	99.18 202	69.90 452	99.52 114	99.73 119
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
baseline1		95.78 205	94.86 225	98.54 127	98.47 186	98.07 79	99.06 311	97.99 240	92.68 237	94.13 276	98.62 246	93.28 124	98.69 249	93.79 270	85.76 354	98.84 258

UnsupCasMVSNet_eth		85.52 396	83.99 398	90.10 413	89.36 449	83.51 428	96.65 427	97.99 240	89.14 342	75.89 450	93.83 420	63.25 437	93.92 440	81.92 412	67.90 455	92.88 416

LFMVS		94.75 242	93.56 265	98.30 147	99.03 129	95.70 193	98.74 354	97.98 242	87.81 374	98.47 146	99.39 148	67.43 421	99.53 174	98.01 152	95.20 276	99.67 129

dp		95.05 229	94.43 236	96.91 239	97.99 220	92.73 298	96.29 434	97.98 242	89.70 338	95.93 240	94.67 407	93.83 110	98.45 269	86.91 377	96.53 234	99.54 163

PMMVS		96.76 156	96.76 140	96.76 246	98.28 200	92.10 313	99.91 108	97.98 242	94.12 166	99.53 72	99.39 148	86.93 244	98.73 242	96.95 196	97.73 193	99.45 185

F-COLMAP		96.93 148	96.95 129	96.87 242	99.71 82	91.74 323	99.85 144	97.95 245	93.11 214	95.72 248	99.16 179	92.35 155	99.94 93	95.32 227	99.35 136	98.92 253

OMC-MVS		97.28 126	97.23 118	97.41 219	99.76 72	93.36 285	99.65 217	97.95 245	96.03 97	97.41 189	99.70 100	89.61 202	99.51 177	96.73 203	98.25 179	99.38 194

mvsany_test1		97.82 95	97.90 80	97.55 206	98.77 159	93.04 290	99.80 165	97.93 247	96.95 61	99.61 67	99.68 111	90.92 181	99.83 139	99.18 76	98.29 178	99.80 110

Anonymous202405211		93.10 294	91.99 307	96.40 259	99.10 124	89.65 372	98.88 339	97.93 247	83.71 419	94.00 277	98.75 231	68.79 412	99.88 123	95.08 232	91.71 306	99.68 127

tpm2		95.47 217	95.18 213	96.35 262	96.91 308	91.70 327	96.96 421	97.93 247	88.04 370	98.44 147	95.40 375	93.32 121	97.97 311	94.00 259	95.61 266	99.38 194

TSAR-MVS + GP.		98.60 37	98.51 34	98.86 98	99.73 79	96.63 150	99.97 39	97.92 250	98.07 19	98.76 130	99.55 131	95.00 66	99.94 93	99.91 19	97.68 196	99.99 24

CDS-MVSNet		96.34 182	96.07 168	97.13 231	97.37 275	94.96 229	99.53 247	97.91 251	91.55 283	95.37 256	98.32 272	95.05 63	97.13 351	93.80 269	95.75 258	99.30 214
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HQP3-MVS								97.89 252							89.60 312

HQP-MVS		94.61 247	94.50 235	94.92 306	95.78 345	91.85 319	99.87 130	97.89 252	96.82 64	93.37 282	98.65 241	80.65 329	98.39 277	97.92 158	89.60 312	94.53 325

HQP_MVS		94.49 254	94.36 238	94.87 307	95.71 355	91.74 323	99.84 149	97.87 254	96.38 84	93.01 287	98.59 249	80.47 333	98.37 283	97.79 167	89.55 315	94.52 327

plane_prior5								97.87 254					98.37 283	97.79 167	89.55 315	94.52 327

xiu_mvs_v1_base_debu		97.43 117	97.06 123	98.55 123	97.74 236	98.14 73	99.31 282	97.86 256	96.43 81	99.62 60	99.69 104	85.56 268	99.68 164	99.05 81	98.31 175	97.83 292

xiu_mvs_v1_base		97.43 117	97.06 123	98.55 123	97.74 236	98.14 73	99.31 282	97.86 256	96.43 81	99.62 60	99.69 104	85.56 268	99.68 164	99.05 81	98.31 175	97.83 292

xiu_mvs_v1_base_debi		97.43 117	97.06 123	98.55 123	97.74 236	98.14 73	99.31 282	97.86 256	96.43 81	99.62 60	99.69 104	85.56 268	99.68 164	99.05 81	98.31 175	97.83 292

guyue		97.15 134	96.82 137	98.15 157	97.56 258	96.25 171	99.71 200	97.84 259	95.75 106	98.13 165	98.65 241	87.58 230	98.82 228	98.29 136	97.91 192	99.36 198

CostFormer		96.10 192	95.88 186	96.78 245	97.03 297	92.55 304	97.08 418	97.83 260	90.04 333	98.72 132	94.89 401	95.01 65	98.29 290	96.54 208	95.77 256	99.50 175

TAMVS		95.85 202	95.58 197	96.65 251	97.07 295	93.50 278	99.17 298	97.82 261	91.39 293	95.02 261	98.01 284	92.20 158	97.30 341	93.75 272	95.83 255	99.14 232

balanced_conf03		98.27 63	97.99 70	99.11 77	98.64 170	98.43 67	99.47 258	97.79 262	94.56 141	99.74 43	98.35 269	94.33 91	99.25 194	99.12 78	99.96 46	99.64 135

VDD-MVS		93.77 276	92.94 285	96.27 264	98.55 176	90.22 361	98.77 353	97.79 262	90.85 307	96.82 211	99.42 141	61.18 445	99.77 149	98.95 90	94.13 289	98.82 259

NormalMVS		97.90 85	97.85 85	98.04 165	99.86 57	95.39 209	99.61 228	97.78 264	96.52 76	98.61 138	99.31 156	92.73 141	99.67 167	96.77 201	99.48 121	99.06 241

Elysia		94.50 252	93.38 274	97.85 178	96.49 328	96.70 145	98.98 323	97.78 264	90.81 309	96.19 233	98.55 256	73.63 394	98.98 214	89.41 340	98.56 167	97.88 290

StellarMVS		94.50 252	93.38 274	97.85 178	96.49 328	96.70 145	98.98 323	97.78 264	90.81 309	96.19 233	98.55 256	73.63 394	98.98 214	89.41 340	98.56 167	97.88 290

cascas		94.64 246	93.61 260	97.74 190	97.82 231	96.26 167	99.96 53	97.78 264	85.76 399	94.00 277	97.54 299	76.95 363	99.21 197	97.23 184	95.43 270	97.76 296

fmvsm_s_conf0.1_n_2		97.25 128	96.85 135	98.43 139	98.08 215	98.08 78	99.92 100	97.76 268	98.05 20	99.65 53	99.58 127	80.88 325	99.93 103	99.59 56	98.17 180	97.29 308

MVSMamba_PlusPlus		97.83 92	97.45 106	98.99 89	98.60 172	98.15 71	99.58 235	97.74 269	90.34 326	99.26 98	98.32 272	94.29 93	99.23 195	99.03 87	99.89 74	99.58 155

CLD-MVS		94.06 268	93.90 254	94.55 322	96.02 339	90.69 349	99.98 21	97.72 270	96.62 75	91.05 310	98.85 225	77.21 356	98.47 265	98.11 146	89.51 317	94.48 329
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MS-PatchMatch		90.65 346	90.30 337	91.71 395	94.22 385	85.50 414	98.24 386	97.70 271	88.67 359	86.42 393	96.37 338	67.82 419	98.03 309	83.62 400	99.62 100	91.60 431

mvsmamba		96.94 146	96.73 142	97.55 206	97.99 220	94.37 253	99.62 224	97.70 271	93.13 212	98.42 149	97.92 290	88.02 224	98.75 240	98.78 104	99.01 152	99.52 169

XXY-MVS		91.82 320	90.46 332	95.88 274	93.91 390	95.40 208	98.87 342	97.69 273	88.63 361	87.87 371	97.08 312	74.38 390	97.89 317	91.66 305	84.07 371	94.35 341

LuminaMVS		96.63 165	96.21 165	97.87 177	95.58 363	96.82 141	99.12 300	97.67 274	94.47 144	97.88 174	98.31 274	87.50 232	98.71 245	98.07 150	97.29 209	98.10 286

EI-MVSNet		93.73 278	93.40 273	94.74 312	96.80 316	92.69 299	99.06 311	97.67 274	88.96 350	91.39 305	99.02 190	88.75 218	97.30 341	91.07 313	87.85 339	94.22 351

MVSTER		95.53 216	95.22 211	96.45 257	98.56 173	97.72 98	99.91 108	97.67 274	92.38 255	91.39 305	97.14 309	97.24 20	97.30 341	94.80 242	87.85 339	94.34 343

SSC-MVS3.2		89.59 371	88.66 371	92.38 384	94.29 384	86.12 409	99.49 254	97.66 277	90.28 329	88.63 359	95.18 389	64.46 432	96.88 372	85.30 388	82.66 379	94.14 364

mamv4		95.24 224	96.90 131	90.25 411	98.65 169	72.11 459	98.28 384	97.64 278	89.99 334	95.93 240	98.25 277	94.74 73	99.11 206	99.01 89	99.64 97	99.53 167

WBMVS		94.52 251	94.03 249	95.98 270	98.38 190	96.68 148	99.92 100	97.63 279	90.75 316	89.64 334	95.25 387	96.77 27	96.90 369	94.35 254	83.57 374	94.35 341

ETV-MVS		97.92 84	97.80 88	98.25 150	98.14 212	96.48 157	99.98 21	97.63 279	95.61 110	99.29 95	99.46 139	92.55 148	98.82 228	99.02 88	98.54 169	99.46 180

CANet_DTU		96.76 156	96.15 167	98.60 117	98.78 158	97.53 107	99.84 149	97.63 279	97.25 50	99.20 99	99.64 118	81.36 318	99.98 50	92.77 289	98.89 155	98.28 281

LPG-MVS_test		92.96 296	92.71 291	93.71 356	95.43 364	88.67 386	99.75 183	97.62 282	92.81 227	90.05 319	98.49 260	75.24 381	98.40 275	95.84 220	89.12 319	94.07 369

LGP-MVS_train				93.71 356	95.43 364	88.67 386		97.62 282	92.81 227	90.05 319	98.49 260	75.24 381	98.40 275	95.84 220	89.12 319	94.07 369

FMVSNet3		92.69 304	91.58 314	95.99 269	98.29 198	97.42 115	99.26 291	97.62 282	89.80 337	89.68 330	95.32 381	81.62 316	96.27 400	87.01 374	85.65 355	94.29 345

ET-MVSNet_ETH3D		94.37 258	93.28 279	97.64 195	98.30 197	97.99 84	99.99 5	97.61 285	94.35 155	71.57 457	99.45 140	96.23 38	95.34 424	96.91 198	85.14 361	99.59 149

EIA-MVS		97.53 114	97.46 104	97.76 188	98.04 218	94.84 233	99.98 21	97.61 285	94.41 153	97.90 171	99.59 124	92.40 154	98.87 224	98.04 151	99.13 146	99.59 149

OPM-MVS		93.21 289	92.80 288	94.44 329	93.12 404	90.85 347	99.77 173	97.61 285	96.19 94	91.56 304	98.65 241	75.16 385	98.47 265	93.78 271	89.39 318	93.99 377
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
IS-MVSNet		96.29 186	95.90 185	97.45 214	98.13 213	94.80 235	99.08 306	97.61 285	92.02 270	95.54 253	98.96 201	90.64 187	98.08 305	93.73 273	97.41 203	99.47 178

CMPMVS	61.59 21	84.75 405	85.14 397	83.57 438	90.32 443	62.54 466	96.98 420	97.59 289	74.33 455	69.95 459	96.66 328	64.17 433	98.32 287	87.88 361	88.41 333	89.84 449
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
UniMVSNet_ETH3D		90.06 363	88.58 372	94.49 326	94.67 376	88.09 395	97.81 403	97.57 290	83.91 418	88.44 362	97.41 302	57.44 450	97.62 327	91.41 308	88.59 330	97.77 295

lupinMVS		97.85 90	97.60 98	98.62 115	97.28 285	97.70 101	99.99 5	97.55 291	95.50 115	99.43 82	99.67 113	90.92 181	98.71 245	98.40 127	99.62 100	99.45 185

XVG-OURS		94.82 235	94.74 232	95.06 301	98.00 219	89.19 376	99.08 306	97.55 291	94.10 167	94.71 263	99.62 122	80.51 331	99.74 155	96.04 216	93.06 304	96.25 317

XVG-OURS-SEG-HR		94.79 238	94.70 233	95.08 300	98.05 217	89.19 376	99.08 306	97.54 293	93.66 190	94.87 262	99.58 127	78.78 348	99.79 144	97.31 179	93.40 299	96.25 317

PatchT		90.38 353	88.75 369	95.25 297	95.99 340	90.16 362	91.22 463	97.54 293	76.80 446	97.26 195	86.01 462	91.88 165	96.07 410	66.16 460	95.91 253	99.51 173

BH-RMVSNet		95.18 226	94.31 241	97.80 180	98.17 209	95.23 221	99.76 179	97.53 295	92.52 248	94.27 274	99.25 167	76.84 364	98.80 232	90.89 320	99.54 111	99.35 202

ACMP	92.05 9	92.74 302	92.42 301	93.73 354	95.91 343	88.72 385	99.81 161	97.53 295	94.13 165	87.00 384	98.23 278	74.07 391	98.47 265	96.22 214	88.86 324	93.99 377
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	91.95 10	92.88 299	92.52 299	93.98 348	95.75 351	89.08 380	99.77 173	97.52 297	93.00 218	89.95 323	97.99 287	76.17 374	98.46 268	93.63 276	88.87 323	94.39 337
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TR-MVS		94.54 248	93.56 265	97.49 213	97.96 222	94.34 254	98.71 357	97.51 298	90.30 328	94.51 266	98.69 237	75.56 378	98.77 236	92.82 288	95.99 247	99.35 202

BH-w/o		95.71 209	95.38 205	96.68 249	98.49 185	92.28 309	99.84 149	97.50 299	92.12 265	92.06 301	98.79 229	84.69 285	98.67 252	95.29 228	99.66 96	99.09 237

mvs_anonymous		95.65 213	95.03 220	97.53 208	98.19 207	95.74 190	99.33 279	97.49 300	90.87 306	90.47 317	97.10 311	88.23 222	97.16 348	95.92 218	97.66 197	99.68 127

DP-MVS		94.54 248	93.42 270	97.91 174	99.46 104	94.04 262	98.93 333	97.48 301	81.15 435	90.04 321	99.55 131	87.02 242	99.95 84	88.97 346	98.11 185	99.73 119

ACMH	89.72 17	90.64 347	89.63 350	93.66 360	95.64 360	88.64 388	98.55 368	97.45 302	89.03 345	81.62 423	97.61 297	69.75 410	98.41 273	89.37 342	87.62 345	93.92 383
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XVG-ACMP-BASELINE		91.22 336	90.75 327	92.63 383	93.73 393	85.61 412	98.52 372	97.44 303	92.77 231	89.90 325	96.85 323	66.64 424	98.39 277	92.29 292	88.61 328	93.89 385

mvs_tets		91.81 321	91.08 324	94.00 346	91.63 432	90.58 353	98.67 362	97.43 304	92.43 251	87.37 381	97.05 315	71.76 400	97.32 339	94.75 244	88.68 327	94.11 367

LTVRE_ROB	88.28 18	90.29 357	89.05 364	94.02 344	95.08 369	90.15 363	97.19 414	97.43 304	84.91 411	83.99 412	97.06 314	74.00 392	98.28 292	84.08 395	87.71 341	93.62 399
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
jajsoiax		91.92 319	91.18 322	94.15 338	91.35 435	90.95 344	99.00 321	97.42 306	92.61 241	87.38 380	97.08 312	72.46 398	97.36 334	94.53 250	88.77 325	94.13 366

K. test v3		88.05 385	87.24 386	90.47 408	91.82 430	82.23 437	98.96 329	97.42 306	89.05 344	76.93 446	95.60 363	68.49 415	95.42 422	85.87 385	81.01 398	93.75 393

FMVSNet2		91.02 338	89.56 352	95.41 291	97.53 261	95.74 190	98.98 323	97.41 308	87.05 382	88.43 364	95.00 397	71.34 403	96.24 402	85.12 389	85.21 360	94.25 348

jason		97.24 129	96.86 134	98.38 144	95.73 352	97.32 117	99.97 39	97.40 309	95.34 118	98.60 141	99.54 133	87.70 227	98.56 261	97.94 157	99.47 124	99.25 222
jason: jason.
AstraMVS		96.57 169	96.46 155	96.91 239	96.79 319	92.50 305	99.90 114	97.38 310	96.02 98	97.79 179	99.32 153	86.36 253	98.99 213	98.26 138	96.33 241	99.23 225

PS-MVSNAJss		93.64 281	93.31 278	94.61 317	92.11 425	92.19 311	99.12 300	97.38 310	92.51 249	88.45 361	96.99 318	91.20 173	97.29 344	94.36 252	87.71 341	94.36 338

MSDG		94.37 258	93.36 277	97.40 220	98.88 152	93.95 266	99.37 274	97.38 310	85.75 401	90.80 314	99.17 176	84.11 294	99.88 123	86.35 378	98.43 172	98.36 279

GDP-MVS		97.88 86	97.59 100	98.75 105	97.59 256	97.81 95	99.95 72	97.37 313	94.44 149	99.08 107	99.58 127	97.13 25	99.08 209	94.99 234	98.17 180	99.37 196

sasdasda		97.09 138	96.32 159	99.39 45	98.93 142	98.95 28	99.72 197	97.35 314	94.45 146	97.88 174	99.42 141	86.71 246	99.52 175	98.48 123	93.97 292	99.72 121

CL-MVSNet_self_test		84.50 407	83.15 407	88.53 426	86.00 456	81.79 440	98.82 347	97.35 314	85.12 407	83.62 415	90.91 443	76.66 367	91.40 457	69.53 453	60.36 467	92.40 424

canonicalmvs		97.09 138	96.32 159	99.39 45	98.93 142	98.95 28	99.72 197	97.35 314	94.45 146	97.88 174	99.42 141	86.71 246	99.52 175	98.48 123	93.97 292	99.72 121

UnsupCasMVSNet_bld		79.97 426	77.03 431	88.78 423	85.62 457	81.98 438	93.66 451	97.35 314	75.51 452	70.79 458	83.05 465	48.70 462	94.91 431	78.31 432	60.29 468	89.46 454

E2		96.36 180	95.95 180	97.60 201	97.41 269	94.52 243	99.71 200	97.33 318	93.20 206	97.02 202	99.07 185	85.37 273	98.82 228	97.27 180	97.14 216	99.46 180

E3		96.36 180	95.95 180	97.60 201	97.37 275	94.52 243	99.71 200	97.33 318	93.18 208	97.02 202	99.07 185	85.45 271	98.82 228	97.27 180	97.14 216	99.46 180

viewcassd2359sk11		96.59 167	96.23 162	97.66 193	97.63 252	94.70 238	99.77 173	97.33 318	93.41 199	97.34 191	99.17 176	86.72 245	98.83 227	97.40 177	97.32 207	99.46 180

viewmanbaseed2359cas		96.45 174	96.07 168	97.59 204	97.55 259	94.59 240	99.70 207	97.33 318	93.62 192	97.00 205	99.32 153	85.57 267	98.71 245	97.26 183	97.33 206	99.47 178

MVS-HIRNet		86.22 393	83.19 406	95.31 295	96.71 323	90.29 359	92.12 458	97.33 318	62.85 465	86.82 385	70.37 470	69.37 411	97.49 331	75.12 443	97.99 190	98.15 283

BH-untuned		95.18 226	94.83 226	96.22 265	98.36 193	91.22 339	99.80 165	97.32 323	90.91 305	91.08 308	98.67 238	83.51 296	98.54 263	94.23 257	99.61 104	98.92 253

PCF-MVS	94.20 5	95.18 226	94.10 245	98.43 139	98.55 176	95.99 181	97.91 400	97.31 324	90.35 325	89.48 339	99.22 169	85.19 275	99.89 117	90.40 331	98.47 171	99.41 192
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MGCFI-Net		97.00 143	96.22 164	99.34 50	98.86 153	98.80 40	99.67 215	97.30 325	94.31 158	97.77 180	99.41 145	86.36 253	99.50 179	98.38 128	93.90 294	99.72 121

test_fmvsmconf0.01_n		96.39 178	95.74 191	98.32 146	91.47 434	95.56 200	99.84 149	97.30 325	97.74 30	97.89 173	99.35 152	79.62 339	99.85 129	99.25 74	99.24 141	99.55 159

test_vis1_n_1920		95.44 218	95.31 207	95.82 278	98.50 183	88.74 384	99.98 21	97.30 325	97.84 28	99.85 18	99.19 174	66.82 423	99.97 63	98.82 101	99.46 126	98.76 262

miper_enhance_ethall		94.36 260	93.98 251	95.49 284	98.68 164	95.24 220	99.73 193	97.29 328	93.28 204	89.86 326	95.97 352	94.37 88	97.05 357	92.20 293	84.45 367	94.19 354

casdiffmvs_mvg		96.43 175	95.94 182	97.89 176	97.44 267	95.47 202	99.86 141	97.29 328	93.35 200	96.03 237	99.19 174	85.39 272	98.72 244	97.89 161	97.04 222	99.49 177
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVSFormer		96.94 146	96.60 148	97.95 168	97.28 285	97.70 101	99.55 244	97.27 330	91.17 296	99.43 82	99.54 133	90.92 181	96.89 370	94.67 247	99.62 100	99.25 222

test_djsdf		92.83 300	92.29 302	94.47 327	91.90 428	92.46 306	99.55 244	97.27 330	91.17 296	89.96 322	96.07 350	81.10 321	96.89 370	94.67 247	88.91 321	94.05 371

viewmacassd2359aftdt		95.93 199	95.45 200	97.36 224	97.09 293	94.12 261	99.57 238	97.26 332	93.05 217	96.50 222	99.17 176	82.76 303	98.68 250	96.61 205	97.04 222	99.28 218

SSM_0407		95.62 214	94.95 223	97.61 200	97.14 289	95.31 214	99.00 321	97.25 333	90.81 309	94.40 268	98.83 227	84.74 282	98.58 259	95.24 229	97.18 213	98.93 250

SSM_0404		95.75 206	95.16 214	97.50 212	97.53 261	95.39 209	99.11 302	97.25 333	90.81 309	95.27 258	98.83 227	84.74 282	98.67 252	95.24 229	97.69 194	98.45 274

test_cas_vis1_n_1920		96.59 167	96.23 162	97.65 194	98.22 204	94.23 257	99.99 5	97.25 333	97.77 29	99.58 68	99.08 183	77.10 357	99.97 63	97.64 172	99.45 127	98.74 264

viewdifsd2359ckpt07		95.83 204	95.42 202	97.07 234	97.40 271	93.04 290	99.60 231	97.24 336	92.39 254	96.09 236	99.14 180	83.07 302	98.93 220	97.02 190	96.87 229	99.23 225

GA-MVS		93.83 271	92.84 286	96.80 244	95.73 352	93.57 275	99.88 127	97.24 336	92.57 245	92.92 289	96.66 328	78.73 349	97.67 325	87.75 362	94.06 291	99.17 228

viewdifsd2359ckpt09		96.21 190	95.77 189	97.53 208	97.69 245	94.50 245	99.78 168	97.23 338	92.88 223	96.58 218	99.26 165	84.85 280	98.66 255	96.61 205	97.02 225	99.43 189

viewdifsd2359ckpt13		96.19 191	95.77 189	97.45 214	97.62 253	94.40 251	99.70 207	97.23 338	92.76 232	96.63 215	99.05 188	84.96 279	98.64 256	96.65 204	97.35 205	99.31 211

Effi-MVS+		96.30 185	95.69 193	98.16 154	97.85 229	96.26 167	97.41 409	97.21 340	90.37 324	98.65 136	98.58 252	86.61 250	98.70 248	97.11 187	97.37 204	99.52 169

Patchmatch-test		92.65 306	91.50 317	96.10 268	96.85 313	90.49 355	91.50 461	97.19 341	82.76 428	90.23 318	95.59 364	95.02 64	98.00 310	77.41 435	96.98 227	99.82 106

diffmvs		97.00 143	96.64 146	98.09 161	97.64 251	96.17 176	99.81 161	97.19 341	94.67 139	98.95 116	99.28 158	86.43 251	98.76 238	98.37 130	97.42 202	99.33 205
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
VortexMVS		94.11 264	93.50 267	95.94 272	97.70 244	96.61 152	99.35 277	97.18 343	93.52 195	89.57 337	95.74 356	87.55 231	96.97 365	95.76 223	85.13 362	94.23 350

ACMH+	89.98 16	90.35 354	89.54 353	92.78 381	95.99 340	86.12 409	98.81 348	97.18 343	89.38 340	83.14 416	97.76 296	68.42 416	98.43 270	89.11 345	86.05 353	93.78 392

anonymousdsp		91.79 326	90.92 326	94.41 332	90.76 440	92.93 293	98.93 333	97.17 345	89.08 343	87.46 379	95.30 382	78.43 354	96.92 368	92.38 291	88.73 326	93.39 404

baseline		96.43 175	95.98 174	97.76 188	97.34 278	95.17 225	99.51 250	97.17 345	93.92 179	96.90 208	99.28 158	85.37 273	98.64 256	97.50 175	96.86 231	99.46 180

nrg030		93.51 284	92.53 298	96.45 257	94.36 381	97.20 123	99.81 161	97.16 347	91.60 281	89.86 326	97.46 300	86.37 252	97.68 324	95.88 219	80.31 404	94.46 330

diffmvs_AUTHOR		96.75 158	96.41 157	97.79 182	97.20 288	95.46 203	99.69 210	97.15 348	94.46 145	98.78 125	99.21 172	85.64 265	98.77 236	98.27 137	97.31 208	99.13 233

SPE-MVS-test		97.88 86	97.94 77	97.70 191	99.28 112	95.20 223	99.98 21	97.15 348	95.53 113	99.62 60	99.79 62	92.08 162	98.38 281	98.75 107	99.28 139	99.52 169

MVS_Test		96.46 173	95.74 191	98.61 116	98.18 208	97.23 122	99.31 282	97.15 348	91.07 302	98.84 121	97.05 315	88.17 223	98.97 216	94.39 251	97.50 199	99.61 146

MIMVSNet		90.30 356	88.67 370	95.17 299	96.45 330	91.64 329	92.39 457	97.15 348	85.99 396	90.50 316	93.19 429	66.95 422	94.86 432	82.01 411	93.43 298	99.01 246

viewmsd2359difaftdt		94.09 266	93.64 258	95.46 288	96.68 324	88.92 381	99.62 224	97.13 352	93.07 215	95.73 246	99.22 169	77.05 358	98.89 222	96.52 209	87.70 343	98.58 271

viewdifsd2359ckpt11		94.09 266	93.63 259	95.46 288	96.68 324	88.92 381	99.62 224	97.12 353	93.07 215	95.73 246	99.22 169	77.05 358	98.88 223	96.52 209	87.69 344	98.58 271

icg_test_0407_2		95.04 230	94.78 230	95.84 277	96.97 301	91.64 329	98.63 365	97.12 353	92.33 257	95.60 249	98.88 213	85.65 263	96.56 387	92.12 295	95.70 261	99.32 207

IMVS_0407		95.21 225	94.80 229	96.46 256	96.97 301	91.64 329	98.81 348	97.12 353	92.33 257	95.60 249	98.88 213	85.65 263	98.42 271	92.12 295	95.70 261	99.32 207

IMVS_0404		93.83 271	93.17 281	95.80 279	96.97 301	91.64 329	97.78 404	97.12 353	92.33 257	90.87 312	98.88 213	76.78 365	96.43 393	92.12 295	95.70 261	99.32 207

IMVS_0403		95.25 223	94.81 228	96.58 253	96.97 301	91.64 329	98.97 328	97.12 353	92.33 257	95.43 254	98.88 213	85.78 262	98.79 233	92.12 295	95.70 261	99.32 207

KD-MVS_2432*1600		88.00 386	86.10 390	93.70 358	96.91 308	94.04 262	97.17 415	97.12 353	84.93 409	81.96 420	92.41 434	92.48 151	94.51 436	79.23 425	52.68 470	92.56 420

miper_refine_blended		88.00 386	86.10 390	93.70 358	96.91 308	94.04 262	97.17 415	97.12 353	84.93 409	81.96 420	92.41 434	92.48 151	94.51 436	79.23 425	52.68 470	92.56 420

CS-MVS		97.79 99	97.91 79	97.43 217	99.10 124	94.42 248	99.99 5	97.10 360	95.07 122	99.68 50	99.75 80	92.95 134	98.34 285	98.38 128	99.14 145	99.54 163

v7n		89.65 370	88.29 376	93.72 355	92.22 423	90.56 354	99.07 310	97.10 360	85.42 406	86.73 386	94.72 403	80.06 336	97.13 351	81.14 415	78.12 416	93.49 401

RRT-MVS		96.24 189	95.68 195	97.94 171	97.65 250	94.92 231	99.27 290	97.10 360	92.79 230	97.43 188	97.99 287	81.85 311	99.37 191	98.46 125	98.57 166	99.53 167

casdiffmvs		96.42 177	95.97 177	97.77 186	97.30 283	94.98 228	99.84 149	97.09 363	93.75 188	96.58 218	99.26 165	85.07 276	98.78 235	97.77 169	97.04 222	99.54 163
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
mamba_0408		94.98 233	94.09 246	97.64 195	97.14 289	95.31 214	93.48 453	97.08 364	90.48 320	94.40 268	98.62 246	84.49 287	98.67 252	93.99 260	97.18 213	98.93 250

SSM_04072		94.77 240	94.09 246	96.82 243	97.14 289	95.31 214	93.48 453	97.08 364	90.48 320	94.40 268	98.62 246	84.49 287	96.21 403	93.99 260	97.18 213	98.93 250

Fast-Effi-MVS+		95.02 231	94.19 243	97.52 210	97.88 226	94.55 242	99.97 39	97.08 364	88.85 355	94.47 267	97.96 289	84.59 286	98.41 273	89.84 338	97.10 219	99.59 149

miper_ehance_all_eth		93.16 292	92.60 293	94.82 311	97.57 257	93.56 276	99.50 252	97.07 367	88.75 357	88.85 354	95.52 368	90.97 180	96.74 379	90.77 322	84.45 367	94.17 355

MonoMVSNet		94.82 235	94.43 236	95.98 270	94.54 378	90.73 348	99.03 318	97.06 368	93.16 210	93.15 286	95.47 372	88.29 221	97.57 328	97.85 162	91.33 309	99.62 142

Effi-MVS+-dtu		94.53 250	95.30 208	92.22 387	97.77 234	82.54 434	99.59 233	97.06 368	94.92 127	95.29 257	95.37 379	85.81 261	97.89 317	94.80 242	97.07 220	96.23 319

EC-MVSNet		97.38 124	97.24 117	97.80 180	97.41 269	95.64 197	99.99 5	97.06 368	94.59 140	99.63 57	99.32 153	89.20 211	98.14 301	98.76 106	99.23 142	99.62 142

IterMVS		90.91 340	90.17 342	93.12 372	96.78 320	90.42 358	98.89 337	97.05 371	89.03 345	86.49 391	95.42 374	76.59 368	95.02 427	87.22 369	84.09 370	93.93 382
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1192		90.62 349	89.25 359	94.72 314	93.13 402	93.07 287	99.50 252	97.02 372	86.33 393	89.56 338	95.01 395	79.22 343	97.09 356	82.34 409	81.16 392	94.01 374

v2v482		91.30 331	90.07 345	95.01 302	93.13 402	93.79 268	99.77 173	97.02 372	88.05 369	89.25 344	95.37 379	80.73 327	97.15 349	87.28 368	80.04 407	94.09 368

V42		91.28 333	90.12 344	94.74 312	93.42 399	93.46 279	99.68 213	97.02 372	87.36 378	89.85 328	95.05 393	81.31 320	97.34 336	87.34 367	80.07 406	93.40 403

IterMVS-SCA-FT		90.85 343	90.16 343	92.93 377	96.72 322	89.96 367	98.89 337	96.99 375	88.95 351	86.63 388	95.67 360	76.48 370	95.00 428	87.04 372	84.04 373	93.84 389

v144192		90.79 344	89.52 354	94.59 319	93.11 405	92.77 294	99.56 241	96.99 375	86.38 392	89.82 329	94.95 400	80.50 332	97.10 354	83.98 397	80.41 402	93.90 384

v1921920		90.46 351	89.12 361	94.50 325	92.96 409	92.46 306	99.49 254	96.98 377	86.10 395	89.61 336	95.30 382	78.55 352	97.03 362	82.17 410	80.89 400	94.01 374

v1144		91.09 337	89.83 346	94.87 307	93.25 401	93.69 273	99.62 224	96.98 377	86.83 388	89.64 334	94.99 398	80.94 323	97.05 357	85.08 390	81.16 392	93.87 387

viewmambaseed2359dif		95.92 200	95.55 199	97.04 235	97.38 273	93.41 281	99.78 168	96.97 379	91.14 299	96.58 218	99.27 161	84.85 280	98.75 240	96.87 199	97.12 218	98.97 248

eth_miper_zixun_eth		92.41 311	91.93 308	93.84 353	97.28 285	90.68 350	98.83 346	96.97 379	88.57 362	89.19 349	95.73 359	89.24 210	96.69 382	89.97 337	81.55 388	94.15 361

dcpmvs_2		97.42 121	98.09 63	95.42 290	99.58 95	87.24 402	99.23 293	96.95 381	94.28 161	98.93 118	99.73 91	94.39 87	99.16 205	99.89 21	99.82 85	99.86 101

GBi-Net		90.88 341	89.82 347	94.08 341	97.53 261	91.97 314	98.43 376	96.95 381	87.05 382	89.68 330	94.72 403	71.34 403	96.11 406	87.01 374	85.65 355	94.17 355

test1		90.88 341	89.82 347	94.08 341	97.53 261	91.97 314	98.43 376	96.95 381	87.05 382	89.68 330	94.72 403	71.34 403	96.11 406	87.01 374	85.65 355	94.17 355

FMVSNet1		88.50 381	86.64 388	94.08 341	95.62 362	91.97 314	98.43 376	96.95 381	83.00 425	86.08 398	94.72 403	59.09 448	96.11 406	81.82 413	84.07 371	94.17 355

v8		90.54 350	89.17 360	94.66 315	93.43 398	93.40 283	99.20 295	96.94 385	85.76 399	87.56 376	94.51 410	81.96 310	97.19 347	84.94 391	78.25 414	93.38 405

c3_l		92.53 308	91.87 310	94.52 323	97.40 271	92.99 292	99.40 266	96.93 386	87.86 372	88.69 357	95.44 373	89.95 198	96.44 392	90.45 328	80.69 401	94.14 364

v1240		90.20 359	88.79 368	94.44 329	93.05 407	92.27 310	99.38 272	96.92 387	85.89 397	89.36 341	94.87 402	77.89 355	97.03 362	80.66 418	81.08 395	94.01 374

tpm		93.70 280	93.41 272	94.58 320	95.36 366	87.41 400	97.01 419	96.90 388	90.85 307	96.72 214	94.14 418	90.40 192	96.84 374	90.75 323	88.54 331	99.51 173

v148		90.70 345	89.63 350	93.92 349	92.97 408	90.97 341	99.75 183	96.89 389	87.51 375	88.27 367	95.01 395	81.67 313	97.04 360	87.40 366	77.17 425	93.75 393

IterMVS-LS		92.69 304	92.11 304	94.43 331	96.80 316	92.74 296	99.45 263	96.89 389	88.98 348	89.65 333	95.38 378	88.77 217	96.34 397	90.98 317	82.04 385	94.22 351
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v10		90.25 358	88.82 367	94.57 321	93.53 396	93.43 280	99.08 306	96.87 391	85.00 408	87.34 382	94.51 410	80.93 324	97.02 364	82.85 405	79.23 409	93.26 407

ADS-MVSNet2		93.80 275	93.88 255	93.55 362	97.87 227	85.94 411	94.24 446	96.84 392	90.07 331	96.43 225	94.48 412	90.29 195	95.37 423	87.44 364	97.23 210	99.36 198

Fast-Effi-MVS+-dtu		93.72 279	93.86 256	93.29 367	97.06 296	86.16 408	99.80 165	96.83 393	92.66 238	92.58 294	97.83 295	81.39 317	97.67 325	89.75 339	96.87 229	96.05 322

pmmvs4		92.10 317	91.07 325	95.18 298	92.82 414	94.96 229	99.48 257	96.83 393	87.45 377	88.66 358	96.56 334	83.78 295	96.83 376	89.29 343	84.77 365	93.75 393

AllTest		92.48 309	91.64 312	95.00 303	99.01 130	88.43 390	98.94 331	96.82 395	86.50 390	88.71 355	98.47 264	74.73 387	99.88 123	85.39 386	96.18 243	96.71 313

TestCases				95.00 303	99.01 130	88.43 390		96.82 395	86.50 390	88.71 355	98.47 264	74.73 387	99.88 123	85.39 386	96.18 243	96.71 313

miper_lstm_enhance		91.81 321	91.39 320	93.06 375	97.34 278	89.18 378	99.38 272	96.79 397	86.70 389	87.47 378	95.22 388	90.00 197	95.86 415	88.26 355	81.37 390	94.15 361

cl____		92.31 313	91.58 314	94.52 323	97.33 280	92.77 294	99.57 238	96.78 398	86.97 386	87.56 376	95.51 369	89.43 204	96.62 384	88.60 349	82.44 382	94.16 360

DIV-MVS_self_test		92.32 312	91.60 313	94.47 327	97.31 282	92.74 296	99.58 235	96.75 399	86.99 385	87.64 374	95.54 366	89.55 203	96.50 389	88.58 350	82.44 382	94.17 355

ppachtmachnet_test		89.58 372	88.35 375	93.25 370	92.40 421	90.44 357	99.33 279	96.73 400	85.49 404	85.90 400	95.77 355	81.09 322	96.00 413	76.00 442	82.49 381	93.30 406

GeoE		94.36 260	93.48 268	96.99 237	97.29 284	93.54 277	99.96 53	96.72 401	88.35 366	93.43 281	98.94 208	82.05 307	98.05 308	88.12 359	96.48 237	99.37 196

COLMAP_ROB	90.47 14	92.18 316	91.49 318	94.25 337	99.00 134	88.04 396	98.42 379	96.70 402	82.30 430	88.43 364	99.01 192	76.97 362	99.85 129	86.11 382	96.50 235	94.86 324
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
1112_ss		96.01 196	95.20 212	98.42 141	97.80 232	96.41 160	99.65 217	96.66 403	92.71 234	92.88 291	99.40 146	92.16 159	99.30 192	91.92 302	93.66 295	99.55 159

test_fmvs1		95.35 221	95.68 195	94.36 333	98.99 135	84.98 417	99.96 53	96.65 404	97.60 34	99.73 45	98.96 201	71.58 402	99.93 103	98.31 134	99.37 134	98.17 282

Test_1112_low_res		95.72 207	94.83 226	98.42 141	97.79 233	96.41 160	99.65 217	96.65 404	92.70 235	92.86 292	96.13 347	92.15 160	99.30 192	91.88 303	93.64 296	99.55 159

RPSCF		91.80 324	92.79 289	88.83 422	98.15 211	69.87 461	98.11 394	96.60 406	83.93 417	94.33 272	99.27 161	79.60 340	99.46 188	91.99 300	93.16 302	97.18 310

test_fmvs1_n		94.25 263	94.36 238	93.92 349	97.68 246	83.70 424	99.90 114	96.57 407	97.40 40	99.67 51	98.88 213	61.82 442	99.92 109	98.23 140	99.13 146	98.14 285

YYNet1		85.50 398	83.33 404	92.00 389	90.89 439	88.38 393	99.22 294	96.55 408	79.60 442	57.26 469	92.72 430	79.09 347	93.78 444	77.25 436	77.37 423	93.84 389

MDA-MVSNet_test_wron		85.51 397	83.32 405	92.10 388	90.96 438	88.58 389	99.20 295	96.52 409	79.70 441	57.12 470	92.69 431	79.11 345	93.86 442	77.10 437	77.46 422	93.86 388

MTMP							99.87 130	96.49 410

pm-mvs1		89.36 375	87.81 381	94.01 345	93.40 400	91.93 317	98.62 366	96.48 411	86.25 394	83.86 413	96.14 346	73.68 393	97.04 360	86.16 381	75.73 433	93.04 413

KD-MVS_self_test		83.59 413	82.06 413	88.20 428	86.93 454	80.70 447	97.21 413	96.38 412	82.87 426	82.49 418	88.97 450	67.63 420	92.32 454	73.75 446	62.30 466	91.58 432

test_vis1_n		93.61 282	93.03 284	95.35 292	95.86 344	86.94 404	99.87 130	96.36 413	96.85 62	99.54 71	98.79 229	52.41 457	99.83 139	98.64 114	98.97 153	99.29 216

our_test_3		90.39 352	89.48 357	93.12 372	92.40 421	89.57 373	99.33 279	96.35 414	87.84 373	85.30 403	94.99 398	84.14 293	96.09 409	80.38 420	84.56 366	93.71 398

CR-MVSNet		93.45 287	92.62 292	95.94 272	96.29 331	92.66 300	92.01 459	96.23 415	92.62 240	96.94 206	93.31 427	91.04 178	96.03 411	79.23 425	95.96 249	99.13 233

Patchmtry		89.70 369	88.49 373	93.33 366	96.24 334	89.94 370	91.37 462	96.23 415	78.22 444	87.69 373	93.31 427	91.04 178	96.03 411	80.18 423	82.10 384	94.02 372

MVP-Stereo		90.93 339	90.45 334	92.37 386	91.25 437	88.76 383	98.05 397	96.17 417	87.27 380	84.04 410	95.30 382	78.46 353	97.27 346	83.78 399	99.70 93	91.09 434
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
pmmvs6		85.69 394	83.84 401	91.26 398	90.00 446	84.41 421	97.82 402	96.15 418	75.86 449	81.29 426	95.39 377	61.21 444	96.87 373	83.52 402	73.29 438	92.50 422

EG-PatchMatch MVS		85.35 399	83.81 402	89.99 415	90.39 442	81.89 439	98.21 391	96.09 419	81.78 432	74.73 452	93.72 423	51.56 459	97.12 353	79.16 428	88.61 328	90.96 437

DeepMVS_CX				82.92 440	95.98 342	58.66 471		96.01 420	92.72 233	78.34 440	95.51 369	58.29 449	98.08 305	82.57 406	85.29 358	92.03 428

test20.03		84.72 406	83.99 398	86.91 432	88.19 453	80.62 448	98.88 339	95.94 421	88.36 365	78.87 436	94.62 408	68.75 413	89.11 463	66.52 459	75.82 431	91.00 436

MDA-MVSNet-bldmvs		84.09 409	81.52 416	91.81 393	91.32 436	88.00 397	98.67 362	95.92 422	80.22 439	55.60 471	93.32 426	68.29 417	93.60 446	73.76 445	76.61 429	93.82 391

lessismore_v0				90.53 406	90.58 441	80.90 446		95.80 423		77.01 445	95.84 353	66.15 426	96.95 366	83.03 404	75.05 435	93.74 396

Anonymous20240521		85.15 400	83.81 402	89.16 420	88.32 451	82.69 432	98.80 351	95.74 424	79.72 440	81.53 424	90.99 441	65.38 429	94.16 438	72.69 447	81.11 394	90.63 441

ttmdpeth		88.23 384	87.06 387	91.75 394	89.91 447	87.35 401	98.92 336	95.73 425	87.92 371	84.02 411	96.31 339	68.23 418	96.84 374	86.33 379	76.12 430	91.06 435

sc_t1		85.01 402	82.46 412	92.67 382	92.44 420	83.09 430	97.39 410	95.72 426	65.06 462	85.64 402	96.16 344	49.50 460	97.34 336	84.86 392	75.39 434	97.57 304

ITE_SJBPF				92.38 384	95.69 358	85.14 415		95.71 427	92.81 227	89.33 343	98.11 281	70.23 409	98.42 271	85.91 384	88.16 336	93.59 400

FMVSNet5		88.32 382	87.47 384	90.88 399	96.90 311	88.39 392	97.28 412	95.68 428	82.60 429	84.67 408	92.40 436	79.83 338	91.16 458	76.39 440	81.51 389	93.09 411

testgi		89.01 378	88.04 379	91.90 391	93.49 397	84.89 418	99.73 193	95.66 429	93.89 183	85.14 404	98.17 279	59.68 447	94.66 435	77.73 434	88.88 322	96.16 321

new_pmnet		84.49 408	82.92 408	89.21 419	90.03 445	82.60 433	96.89 423	95.62 430	80.59 437	75.77 451	89.17 449	65.04 431	94.79 433	72.12 449	81.02 397	90.23 443

pmmvs5		90.17 361	89.09 362	93.40 364	92.10 426	89.77 371	99.74 186	95.58 431	85.88 398	87.24 383	95.74 356	73.41 396	96.48 390	88.54 351	83.56 375	93.95 380

USDC		90.00 364	88.96 365	93.10 374	94.81 373	88.16 394	98.71 357	95.54 432	93.66 190	83.75 414	97.20 308	65.58 427	98.31 288	83.96 398	87.49 347	92.85 417

tt0320		83.56 414	81.15 417	90.77 403	92.77 416	83.58 426	96.83 425	95.52 433	63.26 463	81.36 425	92.54 432	53.26 455	95.77 416	80.45 419	74.38 436	92.96 414

test_method		80.79 421	79.70 424	84.08 437	92.83 413	67.06 463	99.51 250	95.42 434	54.34 469	81.07 428	93.53 424	44.48 464	92.22 455	78.90 429	77.23 424	92.94 415

MIMVSNet1		82.58 416	80.51 421	88.78 423	86.68 455	84.20 422	96.65 427	95.41 435	78.75 443	78.59 439	92.44 433	51.88 458	89.76 462	65.26 462	78.95 410	92.38 425

OurMVSNet-221017-0		89.81 367	89.48 357	90.83 402	91.64 431	81.21 443	98.17 392	95.38 436	91.48 286	85.65 401	97.31 305	72.66 397	97.29 344	88.15 357	84.83 364	93.97 379

Anonymous20231206		86.32 392	85.42 395	89.02 421	89.11 450	80.53 449	99.05 315	95.28 437	85.43 405	82.82 417	93.92 419	74.40 389	93.44 447	66.99 457	81.83 387	93.08 412

new-patchmatchnet		81.19 418	79.34 425	86.76 433	82.86 463	80.36 450	97.92 399	95.27 438	82.09 431	72.02 456	86.87 459	62.81 439	90.74 460	71.10 450	63.08 463	89.19 456

OpenMVS_ROB	79.82 20	83.77 412	81.68 415	90.03 414	88.30 452	82.82 431	98.46 373	95.22 439	73.92 456	76.00 449	91.29 440	55.00 452	96.94 367	68.40 455	88.51 332	90.34 442

test_0402		85.58 395	83.94 400	90.50 407	93.81 392	85.04 416	98.55 368	95.20 440	76.01 448	79.72 435	95.13 390	64.15 434	96.26 401	66.04 461	86.88 349	90.21 444

SixPastTwentyTwo		88.73 379	88.01 380	90.88 399	91.85 429	82.24 436	98.22 390	95.18 441	88.97 349	82.26 419	96.89 320	71.75 401	96.67 383	84.00 396	82.98 376	93.72 397

Gipuma		66.95 437	65.00 437	72.79 450	91.52 433	67.96 462	66.16 474	95.15 442	47.89 471	58.54 468	67.99 473	29.74 469	87.54 467	50.20 472	77.83 418	62.87 473
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
mmtdpeth		88.52 380	87.75 382	90.85 401	95.71 355	83.47 429	98.94 331	94.85 443	88.78 356	97.19 197	89.58 447	63.29 436	98.97 216	98.54 119	62.86 464	90.10 446

MVStest1		85.03 401	82.76 410	91.83 392	92.95 410	89.16 379	98.57 367	94.82 444	71.68 459	68.54 462	95.11 392	83.17 301	95.66 418	74.69 444	65.32 459	90.65 440

LF4IMVS		89.25 377	88.85 366	90.45 409	92.81 415	81.19 444	98.12 393	94.79 445	91.44 288	86.29 395	97.11 310	65.30 430	98.11 303	88.53 352	85.25 359	92.07 426

FPMVS		68.72 432	68.72 433	68.71 455	65.95 478	44.27 484	95.97 441	94.74 446	51.13 470	53.26 472	90.50 445	25.11 474	83.00 471	60.80 466	80.97 399	78.87 468

tt0320-xc		82.94 415	80.35 422	90.72 405	92.90 411	83.54 427	96.85 424	94.73 447	63.12 464	79.85 434	93.77 422	49.43 461	95.46 421	80.98 417	71.54 442	93.16 410

pmmvs-eth3d		84.03 410	81.97 414	90.20 412	84.15 460	87.09 403	98.10 395	94.73 447	83.05 424	74.10 455	87.77 456	65.56 428	94.01 439	81.08 416	69.24 448	89.49 453

test_fmvs2		89.47 373	89.70 349	88.77 425	94.54 378	75.74 454	99.83 156	94.70 449	94.71 136	91.08 308	96.82 327	54.46 453	97.78 322	92.87 287	88.27 334	92.80 418

TDRefinement		84.76 404	82.56 411	91.38 397	74.58 474	84.80 420	97.36 411	94.56 450	84.73 412	80.21 431	96.12 349	63.56 435	98.39 277	87.92 360	63.97 462	90.95 438

ambc				83.23 439	77.17 472	62.61 465	87.38 469	94.55 451		76.72 447	86.65 460	30.16 468	96.36 396	84.85 393	69.86 445	90.73 439

WB-MVS		76.28 428	77.28 430	73.29 449	81.18 466	54.68 474	97.87 401	94.19 452	81.30 433	69.43 460	90.70 444	77.02 361	82.06 472	35.71 477	68.11 454	83.13 463

TinyColmap		87.87 388	86.51 389	91.94 390	95.05 370	85.57 413	97.65 406	94.08 453	84.40 415	81.82 422	96.85 323	62.14 441	98.33 286	80.25 422	86.37 352	91.91 430

SSC-MVS		75.42 429	76.40 432	72.49 453	80.68 468	53.62 475	97.42 408	94.06 454	80.42 438	68.75 461	90.14 446	76.54 369	81.66 473	33.25 478	66.34 458	82.19 464

TransMVSNet (Re)		87.25 389	85.28 396	93.16 371	93.56 395	91.03 340	98.54 370	94.05 455	83.69 420	81.09 427	96.16 344	75.32 380	96.40 394	76.69 439	68.41 452	92.06 427

Baseline_NR-MVSNet		90.33 355	89.51 355	92.81 380	92.84 412	89.95 368	99.77 173	93.94 456	84.69 413	89.04 351	95.66 361	81.66 314	96.52 388	90.99 316	76.98 426	91.97 429

EGC-MVSNET		69.38 430	63.76 440	86.26 434	90.32 443	81.66 442	96.24 435	93.85 457	0.99 481	3.22 482	92.33 437	52.44 456	92.92 451	59.53 468	84.90 363	84.21 462

LCM-MVSNet		67.77 435	64.73 438	76.87 446	62.95 480	56.25 473	89.37 468	93.74 458	44.53 472	61.99 464	80.74 466	20.42 478	86.53 469	69.37 454	59.50 469	87.84 458

APD_test1		81.15 419	80.92 419	81.86 441	92.45 419	59.76 470	96.04 439	93.61 459	73.29 457	77.06 444	96.64 330	44.28 465	96.16 405	72.35 448	82.52 380	89.67 451

test_fmvs3		79.99 425	80.17 423	79.45 443	84.02 461	62.83 464	99.05 315	93.49 460	88.29 367	80.06 433	86.65 460	28.09 471	88.00 464	88.63 348	73.27 439	87.54 460

mvs5depth		84.87 403	82.90 409	90.77 403	85.59 458	84.84 419	91.10 464	93.29 461	83.14 423	85.07 406	94.33 416	62.17 440	97.32 339	78.83 430	72.59 441	90.14 445

test_f		78.40 427	77.59 429	80.81 442	80.82 467	62.48 467	96.96 421	93.08 462	83.44 421	74.57 453	84.57 464	27.95 472	92.63 452	84.15 394	72.79 440	87.32 461

Patchmatch-RL test		86.90 390	85.98 394	89.67 416	84.45 459	75.59 455	89.71 467	92.43 463	86.89 387	77.83 443	90.94 442	94.22 95	93.63 445	87.75 362	69.61 446	99.79 111

mvsany_test3		82.12 417	81.14 418	85.06 436	81.87 465	70.41 460	97.09 417	92.14 464	91.27 295	77.84 442	88.73 451	39.31 466	95.49 419	90.75 323	71.24 443	89.29 455

pmmvs3		80.27 423	77.77 428	87.76 431	80.32 469	82.43 435	98.23 388	91.97 465	72.74 458	78.75 437	87.97 455	57.30 451	90.99 459	70.31 451	62.37 465	89.87 448

LCM-MVSNet-Re		92.31 313	92.60 293	91.43 396	97.53 261	79.27 451	99.02 320	91.83 466	92.07 266	80.31 430	94.38 415	83.50 297	95.48 420	97.22 185	97.58 198	99.54 163

FE-MVSNET		81.05 420	78.81 427	87.79 430	81.98 464	83.70 424	98.23 388	91.78 467	81.27 434	74.29 454	87.44 457	60.92 446	90.67 461	64.92 463	68.43 451	89.01 457

PM-MVS		80.47 422	78.88 426	85.26 435	83.79 462	72.22 458	95.89 442	91.08 468	85.71 402	76.56 448	88.30 452	36.64 467	93.90 441	82.39 408	69.57 447	89.66 452

door								90.31 469

dmvs_testset		83.79 411	86.07 392	76.94 445	92.14 424	48.60 480	96.75 426	90.27 470	89.48 339	78.65 438	98.55 256	79.25 342	86.65 468	66.85 458	82.69 378	95.57 323

DSMNet-mixed		88.28 383	88.24 377	88.42 427	89.64 448	75.38 456	98.06 396	89.86 471	85.59 403	88.20 368	92.14 438	76.15 375	91.95 456	78.46 431	96.05 246	97.92 289

door-mid								89.69 472

PMVS	49.05 23	53.75 440	51.34 444	60.97 458	40.80 484	34.68 485	74.82 473	89.62 473	37.55 474	28.67 480	72.12 469	7.09 483	81.63 474	43.17 475	68.21 453	66.59 472
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		65.23 438	62.94 441	72.13 454	44.90 483	50.03 479	81.05 471	89.42 474	38.45 473	48.51 475	99.90 22	54.09 454	78.70 475	91.84 304	18.26 477	87.64 459

PMMVS2		67.15 436	64.15 439	76.14 447	70.56 477	62.07 468	93.89 449	87.52 475	58.09 466	60.02 465	78.32 467	22.38 475	84.54 470	59.56 467	47.03 472	81.80 465

testf1		68.38 433	66.92 434	72.78 451	78.80 470	50.36 477	90.95 465	87.35 476	55.47 467	58.95 466	88.14 453	20.64 476	87.60 465	57.28 469	64.69 460	80.39 466

APD_test2		68.38 433	66.92 434	72.78 451	78.80 470	50.36 477	90.95 465	87.35 476	55.47 467	58.95 466	88.14 453	20.64 476	87.60 465	57.28 469	64.69 460	80.39 466

test_vis1_rt		86.87 391	86.05 393	89.34 418	96.12 335	78.07 452	99.87 130	83.54 478	92.03 269	78.21 441	89.51 448	45.80 463	99.91 110	96.25 213	93.11 303	90.03 447

ANet_high		56.10 439	52.24 442	67.66 456	49.27 482	56.82 472	83.94 470	82.02 479	70.47 460	33.28 479	64.54 474	17.23 480	69.16 477	45.59 474	23.85 476	77.02 469

MVE	53.74 22	51.54 442	47.86 446	62.60 457	59.56 481	50.93 476	79.41 472	77.69 480	35.69 476	36.27 478	61.76 477	5.79 485	69.63 476	37.97 476	36.61 473	67.24 471
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		52.30 441	52.18 443	52.67 459	71.51 475	45.40 481	93.62 452	76.60 481	36.01 475	43.50 476	64.13 475	27.11 473	67.31 478	31.06 479	26.06 474	45.30 477

EMVS		51.44 443	51.22 445	52.11 460	70.71 476	44.97 483	94.04 448	75.66 482	35.34 477	42.40 477	61.56 478	28.93 470	65.87 479	27.64 480	24.73 475	45.49 476

test_vis3_rt		68.82 431	66.69 436	75.21 448	76.24 473	60.41 469	96.44 430	68.71 483	75.13 453	50.54 474	69.52 472	16.42 481	96.32 398	80.27 421	66.92 457	68.89 470

N_pmnet		80.06 424	80.78 420	77.89 444	91.94 427	45.28 482	98.80 351	56.82 484	78.10 445	80.08 432	93.33 425	77.03 360	95.76 417	68.14 456	82.81 377	92.64 419

testmvs		40.60 444	44.45 447	29.05 462	19.49 486	14.11 488	99.68 213	18.47 485	20.74 478	64.59 463	98.48 263	10.95 482	17.09 482	56.66 471	11.01 478	55.94 475

test123		37.68 445	39.14 448	33.31 461	19.94 485	24.83 487	98.36 381	9.75 486	15.53 479	51.31 473	87.14 458	19.62 479	17.74 481	47.10 473	3.47 480	57.36 474

wuyk23d		20.37 447	20.84 450	18.99 463	65.34 479	27.73 486	50.43 475	7.67 487	9.50 480	8.01 481	6.34 481	6.13 484	26.24 480	23.40 481	10.69 479	2.99 478

mmdepth		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 483	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

monomultidepth		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 483	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

test_blank		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.02 482	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

uanet_test		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 483	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

DCPMVS		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 483	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

pcd_1.5k_mvsjas		7.60 449	10.13 452	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 483	91.20 173	0.00 483	0.00 482	0.00 481	0.00 479

sosnet-low-res		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 483	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

sosnet		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 483	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

uncertanet		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 483	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

Regformer		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 483	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

n2								0.00 488

nn								0.00 488

ab-mvs-re		8.28 448	11.04 451	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	99.40 146	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

uanet		0.00 450	0.00 453	0.00 464	0.00 487	0.00 489	0.00 476	0.00 488	0.00 482	0.00 483	0.00 483	0.00 486	0.00 483	0.00 482	0.00 481	0.00 479

TestfortrainingZip							99.97 39

WAC-MVS						90.97 341								86.10 383

PC_three_1452									96.96 60	99.80 26	99.79 62	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

eth-test2					0.00 487

eth-test					0.00 487

OPU-MVS				99.93 2	99.89 49	99.80 2	99.96 53				99.80 58	97.44 14	100.00 1	100.00 1	99.98 32	100.00 1

test_0728_THIRD									96.48 78	99.83 22	99.91 18	97.87 5	100.00 1	99.92 16	100.00 1	100.00 1

GSMVS																99.59 149

test_part2					99.89 49	99.25 19				99.49 77

sam_mvs1												94.72 74				99.59 149

sam_mvs												94.25 94

test_post1							95.78 443				59.23 479	93.20 128	97.74 323	91.06 314

test_post											63.35 476	94.43 82	98.13 302

patchmatchnet-post											91.70 439	95.12 59	97.95 314

gm-plane-assit					96.97 301	93.76 270			91.47 287		98.96 201		98.79 233	94.92 237

test9_res														99.71 48	99.99 21	100.00 1

agg_prior2														99.48 63	100.00 1	100.00 1

test_prior4						98.05 81	99.94 90

test_prior2							99.95 72		95.78 104	99.73 45	99.76 72	96.00 40		99.78 35	100.00 1

旧先验2							99.46 262		94.21 164	99.85 18			99.95 84	96.96 195

新几何2							99.40 266

原ACMM2							99.90 114

testdata2													99.99 39	90.54 327

segment_acmp												96.68 31

testdata1							99.28 288		96.35 90

plane_prior7					95.71 355	91.59 335

plane_prior6					95.76 349	91.72 326						80.47 333

plane_prior4											98.59 249

plane_prior3						91.64 329			96.63 73	93.01 287

plane_prior2							99.84 149		96.38 84

plane_prior1					95.73 352

plane_prior						91.74 323	99.86 141		96.76 68						89.59 314

HQP5-MVS						91.85 319

HQP-NCC					95.78 345		99.87 130		96.82 64	93.37 282

ACMP_Plane					95.78 345		99.87 130		96.82 64	93.37 282

BP-MVS														97.92 158

HQP4-MVS										93.37 282			98.39 277			94.53 325

HQP2-MVS												80.65 329

NP-MVS					95.77 348	91.79 321					98.65 241

MDTV_nov1_ep13_2view						96.26 167	96.11 437		91.89 272	98.06 166		94.40 84		94.30 255		99.67 129

ACMMP++_ref															87.04 348

ACMMP++															88.23 335

Test By Simon												92.82 139

High-resolution multi-view benchmark