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		96.69 46	96.69 46	96.72 100	98.58 100	91.00 156	99.14 131	99.45 1	93.86 74	95.15 148	98.73 111	88.48 83	99.76 109	97.23 89	99.56 56	99.40 105

thres100view900		93.34 189	92.15 212	96.90 88	97.62 132	94.84 43	99.06 145	99.36 2	87.96 277	90.47 260	96.78 257	83.29 191	98.75 191	84.11 334	90.69 303	97.12 283

tfpn200view9		93.43 183	92.27 204	96.90 88	97.68 129	94.84 43	99.18 119	99.36 2	88.45 255	90.79 250	96.90 246	83.31 189	98.75 191	84.11 334	90.69 303	97.12 283

thres600view7		93.18 195	92.00 215	96.75 96	97.62 132	94.92 38	99.07 142	99.36 2	87.96 277	90.47 260	96.78 257	83.29 191	98.71 196	82.93 353	90.47 307	96.61 302

thres400		93.39 185	92.27 204	96.73 98	97.68 129	94.84 43	99.18 119	99.36 2	88.45 255	90.79 250	96.90 246	83.31 189	98.75 191	84.11 334	90.69 303	96.61 302

thres200		93.69 169	92.59 195	96.97 83	97.76 125	94.74 49	99.35 101	99.36 2	89.23 221	91.21 246	96.97 238	83.42 188	98.77 187	85.08 317	90.96 301	97.39 274

MVS_111021_LR		95.78 89	95.94 75	95.28 199	98.19 111	87.69 275	98.80 173	99.26 7	93.39 88	95.04 150	98.69 118	84.09 178	99.76 109	96.96 95	99.06 86	98.38 222

sss		94.85 124	93.94 141	97.58 49	96.43 198	94.09 67	98.93 158	99.16 8	89.50 214	95.27 145	97.85 160	81.50 232	99.65 121	92.79 215	94.02 231	98.99 148

MM		97.76 12	97.39 22	98.86 6	98.30 105	96.83 8	99.81 20	99.13 9	97.66 2	98.29 60	98.96 88	85.84 146	99.90 62	99.72 3	98.80 105	99.85 35

MG-MVS		97.24 24	96.83 39	98.47 16	99.79 6	95.71 21	99.07 142	99.06 10	94.45 57	96.42 116	98.70 117	88.81 79	99.74 111	95.35 142	99.86 12	99.97 8

test2506		94.80 125	94.21 126	96.58 110	96.41 201	92.18 122	98.01 302	98.96 11	90.82 154	93.46 189	97.28 207	85.92 143	98.45 209	89.82 253	97.19 160	99.12 133

PVSNet	87.13 12	93.69 169	92.83 187	96.28 131	97.99 118	90.22 180	99.38 95	98.93 12	91.42 138	93.66 184	97.68 176	71.29 359	99.64 123	87.94 279	97.20 159	98.98 149

PGM-MVS		95.85 85	95.65 91	96.45 117	99.50 48	89.77 202	98.22 274	98.90 13	89.19 223	96.74 109	98.95 91	85.91 145	99.92 50	93.94 179	99.46 61	99.66 71

EPNet		96.82 40	96.68 47	97.25 68	98.65 98	93.10 94	99.48 76	98.76 14	96.54 22	97.84 76	98.22 149	87.49 102	99.66 117	95.35 142	97.78 144	99.00 146
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		95.97 77	95.11 107	98.54 14	97.62 132	96.65 10	99.44 85	98.74 15	92.25 118	95.21 146	98.46 141	86.56 130	99.46 141	95.00 154	92.69 255	99.50 95

HY-MVS	88.56 7	95.29 107	94.23 125	98.48 15	97.72 127	96.41 14	94.03 437	98.74 15	92.42 111	95.65 139	94.76 314	86.52 132	99.49 135	95.29 145	92.97 251	99.53 89

VNet		95.08 115	94.26 124	97.55 52	98.07 115	93.88 69	98.68 193	98.73 17	90.33 175	97.16 93	97.43 195	79.19 262	99.53 132	96.91 97	91.85 281	99.24 121

test_yl		95.27 108	94.60 117	97.28 66	98.53 101	92.98 99	99.05 146	98.70 18	86.76 316	94.65 160	97.74 171	87.78 96	99.44 142	95.57 136	92.61 256	99.44 102

DCV-MVSNet		95.27 108	94.60 117	97.28 66	98.53 101	92.98 99	99.05 146	98.70 18	86.76 316	94.65 160	97.74 171	87.78 96	99.44 142	95.57 136	92.61 256	99.44 102

PVSNet_0	83.28 16	87.31 342	85.16 358	93.74 283	94.78 304	84.59 368	98.91 162	98.69 20	89.81 198	78.59 419	93.23 346	61.95 429	99.34 157	94.75 160	55.72 496	97.30 278

ACMMP		94.67 132	94.30 123	95.79 164	99.25 65	88.13 264	98.41 246	98.67 21	90.38 174	91.43 239	98.72 113	82.22 222	99.95 38	93.83 184	95.76 192	99.29 117
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
lecture		96.67 47	96.77 43	96.39 122	99.27 63	89.71 204	99.65 52	98.62 22	92.28 117	98.62 45	99.07 70	86.74 122	99.79 104	97.83 79	98.82 102	99.66 71

SymmetryMVS		95.49 100	95.27 100	96.17 140	97.13 168	90.37 173	99.14 131	98.59 23	94.92 45	96.30 119	97.98 156	85.33 158	99.23 161	94.35 170	93.67 241	98.92 159

D2MVS		87.96 330	87.39 324	89.70 390	91.84 395	83.40 384	98.31 264	98.49 24	88.04 274	78.23 424	90.26 420	73.57 332	96.79 342	84.21 331	83.53 351	88.90 454

test_fmvsm_n_1920		97.08 32	97.55 15	95.67 170	97.94 120	89.61 208	99.93 1	98.48 25	97.08 12	99.08 25	99.13 60	88.17 88	99.93 47	99.11 37	99.06 86	97.47 271

fmvsm_s_conf0.5_n		96.19 68	96.49 52	95.30 198	97.37 149	89.16 222	99.86 9	98.47 26	95.68 34	98.87 34	99.15 55	82.44 219	99.92 50	99.14 35	97.43 155	96.83 294

HyFIR lowres test		93.68 171	93.29 169	94.87 222	97.57 138	88.04 266	98.18 278	98.47 26	87.57 294	91.24 244	95.05 310	85.49 151	97.46 313	93.22 205	92.82 252	99.10 136

testing3-2		95.17 111	94.78 114	96.33 128	97.35 150	92.35 117	99.85 12	98.43 28	90.60 163	92.84 205	97.00 236	90.89 45	98.89 181	95.95 125	90.12 309	97.76 257

fmvsm_s_conf0.5_n_a		95.97 77	96.19 63	95.31 195	96.51 195	89.01 231	99.81 20	98.39 29	95.46 39	99.19 24	99.16 51	81.44 236	99.91 57	98.83 45	96.97 165	97.01 290

UniMVSNet (Re)		89.50 301	88.32 309	93.03 296	92.21 385	90.96 157	98.90 164	98.39 29	89.13 229	83.22 339	92.03 366	81.69 229	96.34 369	86.79 293	72.53 431	91.81 369

CHOSEN 280x420		96.80 41	96.85 36	96.66 105	97.85 123	94.42 59	94.76 424	98.36 31	92.50 108	95.62 140	97.52 189	97.92 1	97.38 318	98.31 67	98.80 105	98.20 239

VPA-MVSNet		89.10 306	87.66 319	93.45 289	92.56 377	91.02 155	97.97 305	98.32 32	86.92 311	86.03 314	92.01 368	68.84 376	97.10 329	90.92 239	75.34 400	92.23 354

CHOSEN 1792x2688		94.35 142	93.82 149	95.95 157	97.40 146	88.74 247	98.41 246	98.27 33	92.18 120	91.43 239	96.40 273	78.88 267	99.81 98	93.59 189	97.81 141	99.30 116

patch_mono-2		97.10 31	97.97 9	94.49 244	99.21 69	83.73 380	99.62 60	98.25 34	95.28 41	99.38 14	98.91 96	92.28 33	99.94 41	99.61 11	99.22 78	99.78 46

FIs		90.70 268	89.87 265	93.18 294	92.29 382	91.12 149	98.17 280	98.25 34	89.11 230	83.44 336	94.82 313	82.26 221	96.17 381	87.76 280	82.76 357	92.25 352

UGNet		91.91 238	90.85 247	95.10 210	97.06 173	88.69 248	98.01 302	98.24 36	92.41 112	92.39 218	93.61 337	60.52 435	99.68 115	88.14 276	97.25 158	96.92 292
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
FC-MVSNet-test		90.22 284	89.40 278	92.67 312	91.78 396	89.86 197	97.89 307	98.22 37	88.81 240	82.96 346	94.66 315	81.90 228	95.96 391	85.89 311	82.52 360	92.20 357

WR-MVS_H		86.53 356	85.49 354	89.66 392	91.04 408	83.31 386	97.53 335	98.20 38	84.95 353	79.64 400	90.90 398	78.01 286	95.33 425	76.29 410	72.81 428	90.35 426

MGCNet		97.81 10	97.51 16	98.74 10	98.97 81	96.57 12	99.91 3	98.17 39	97.45 5	98.76 39	98.97 83	86.69 125	99.96 34	99.72 3	98.92 96	99.69 65

MVS		93.92 158	92.28 203	98.83 8	95.69 237	96.82 9	96.22 393	98.17 39	84.89 354	84.34 330	98.61 125	79.32 260	99.83 92	93.88 182	99.43 65	99.86 34

PAPM		96.35 61	95.94 75	97.58 49	94.10 334	95.25 28	98.93 158	98.17 39	94.26 59	93.94 176	98.72 113	89.68 68	97.88 272	96.36 111	99.29 73	99.62 81

baseline2		94.04 152	93.80 150	94.74 230	93.07 371	90.25 177	98.12 285	98.16 42	89.86 194	86.53 312	96.95 239	95.56 6	98.05 256	91.44 234	94.53 221	95.93 321

UniMVSNet_NR-MVSNet		89.60 298	88.55 305	92.75 306	92.17 386	90.07 187	98.74 182	98.15 43	88.37 261	83.21 340	93.98 326	82.86 201	95.93 393	86.95 289	72.47 432	92.25 352

CSCG		94.87 123	94.71 115	95.36 187	99.54 42	86.49 314	99.34 102	98.15 43	82.71 397	90.15 267	99.25 32	89.48 70	99.86 82	94.97 156	98.82 102	99.72 59

test_fmvsmconf_n		96.78 43	96.84 37	96.61 107	95.99 226	90.25 177	99.90 4	98.13 45	96.68 20	98.42 54	98.92 95	85.34 157	99.88 72	99.12 36	99.08 83	99.70 62

MSLP-MVS++		97.50 19	97.45 20	97.63 47	99.65 22	93.21 90	99.70 41	98.13 45	94.61 51	97.78 79	99.46 15	89.85 65	99.81 98	97.97 73	99.91 6	99.88 29

aaatest				97.84 37	99.75 8	93.67 74	99.65 52	98.11 47	92.89 101	98.58 49	99.53 8		100.00 1	99.53 20	99.64 44	99.87 32

MED-MVS		98.04 8	98.10 4	97.86 36	99.75 8	93.67 74	99.65 52	98.11 47	94.03 65	98.58 49	99.49 12	93.98 18	100.00 1	99.53 20	99.75 29	99.90 23

h-mvs33		92.47 222	91.95 218	94.05 270	97.13 168	85.01 362	98.36 259	98.08 49	93.85 75	96.27 121	96.73 260	83.19 195	99.43 145	95.81 128	68.09 453	97.70 263

aaEdge-Enhanced		97.59 16	97.51 16	97.84 37	99.73 12	93.67 74	99.52 72	98.07 50	92.38 115	98.32 59	99.53 8	90.83 48	99.97 26	99.53 20	99.64 44	99.87 32

fmvsm_s_conf0.5_n_4		96.17 69	96.49 52	95.21 204	97.06 173	89.26 217	99.76 32	98.07 50	95.99 28	99.35 15	99.22 37	82.19 223	99.89 70	99.06 38	97.68 146	96.49 309

TestfortrainingZip				99.33 5	99.87 2	97.98 5	99.65 52	98.06 52	92.29 116	99.91 1	99.64 2	95.49 8	100.00 1		98.29 133	100.00 1

IB-MVS	89.43 6	92.12 231	90.83 250	95.98 156	95.40 253	90.78 161	99.81 20	98.06 52	91.23 145	85.63 319	93.66 336	90.63 52	98.78 186	91.22 235	71.85 438	98.36 228
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
fmvsm_l_conf0.5_n		97.65 15	97.72 13	97.41 57	97.51 142	92.78 106	99.85 12	98.05 54	96.78 17	99.60 7	99.23 35	90.42 57	99.92 50	99.55 16	98.50 124	99.55 87

PHI-MVS		96.65 51	96.46 55	97.21 69	99.34 56	91.77 131	99.70 41	98.05 54	86.48 324	98.05 69	99.20 41	89.33 71	99.96 34	98.38 62	99.62 50	99.90 23

fmvsm_l_conf0.5_n_a		97.70 14	97.80 12	97.42 56	97.59 136	92.91 103	99.86 9	98.04 56	96.70 19	99.58 8	99.26 30	90.90 44	99.94 41	99.57 13	98.66 115	99.40 105

PVSNet_BlendedMVS		93.36 188	93.20 171	93.84 278	98.77 95	91.61 138	99.47 78	98.04 56	91.44 136	94.21 168	92.63 360	83.50 184	99.87 76	97.41 84	83.37 353	90.05 434

PVSNet_Blended		95.94 80	95.66 89	96.75 96	98.77 95	91.61 138	99.88 5	98.04 56	93.64 83	94.21 168	97.76 167	83.50 184	99.87 76	97.41 84	97.75 145	98.79 174

EPMVS		92.59 219	91.59 227	95.59 178	97.22 158	90.03 191	91.78 462	98.04 56	90.42 173	91.66 233	90.65 407	86.49 134	97.46 313	81.78 371	96.31 179	99.28 118

CNVR-MVS		98.46 1	98.38 1	98.72 11	99.80 5	96.19 16	99.80 26	97.99 60	97.05 13	99.41 11	99.59 3	92.89 28	100.00 1	98.99 42	99.90 7	99.96 11

MCST-MVS		98.18 2	97.95 10	98.86 6	99.85 4	96.60 11	99.70 41	97.98 61	97.18 11	95.96 125	99.33 27	92.62 29	100.00 1	98.99 42	99.93 1	99.98 7

fmvsm_s_conf0.5_n_10		96.95 35	96.82 40	97.33 62	97.76 125	93.00 98	99.87 6	97.95 62	97.32 9	99.71 4	99.20 41	81.48 233	99.90 62	99.32 24	98.78 109	99.09 137

testing3		87.75 334	88.22 311	86.36 434	94.66 310	77.41 451	99.52 72	97.95 62	86.05 331	81.12 382	96.69 263	86.18 140	89.31 491	61.65 483	90.12 309	92.35 351

fmvsm_s_conf0.5_n_7		95.87 83	96.25 61	94.72 232	96.19 214	87.74 274	99.66 50	97.94 64	95.78 31	98.44 53	99.23 35	81.26 239	99.90 62	99.17 34	98.57 121	96.52 308

reproduce_monomvs		92.11 233	91.82 222	92.98 298	98.25 106	90.55 169	98.38 257	97.93 65	94.81 47	80.46 390	92.37 362	96.46 3	97.17 324	94.06 177	73.61 419	91.23 402

testing222		94.48 140	94.00 135	95.95 157	97.30 153	92.27 119	98.82 169	97.92 66	89.20 222	94.82 153	97.26 209	87.13 112	97.32 321	91.95 227	91.56 287	98.25 233

1314		93.44 181	91.98 216	97.84 37	95.24 260	94.38 60	96.22 393	97.92 66	90.18 183	82.28 360	97.71 175	77.63 288	99.80 100	91.94 228	98.67 114	99.34 113

NCCC		98.12 5	98.11 3	98.13 27	99.76 7	94.46 56	99.81 20	97.88 68	96.54 22	98.84 36	99.46 15	92.55 30	99.98 14	98.25 69	99.93 1	99.94 19

tfpnnormal		83.65 399	81.35 405	90.56 366	91.37 404	88.06 265	97.29 344	97.87 69	78.51 438	76.20 431	90.91 397	64.78 414	96.47 357	61.71 482	73.50 422	87.13 471

TestfortrainingZip a		97.38 21	97.10 26	98.24 22	99.75 8	94.82 46	99.65 52	97.86 70	94.03 65	99.04 28	99.49 12	90.76 51	99.99 9	95.87 127	97.45 154	99.90 23

ETVMVS		94.50 139	93.90 145	96.31 129	97.48 144	92.98 99	99.07 142	97.86 70	88.09 272	94.40 164	96.90 246	88.35 85	97.28 322	90.72 245	92.25 274	98.66 201

fmvsm_l_conf0.5_n_9		97.33 22	97.32 24	97.37 60	97.64 131	92.45 116	99.93 1	97.85 72	97.39 6	99.84 2	99.09 69	85.42 155	99.92 50	99.52 23	99.20 82	99.73 58

3Dnovator	87.35 11	93.17 197	91.77 224	97.37 60	95.41 252	93.07 95	98.82 169	97.85 72	91.53 133	82.56 353	97.58 185	71.97 351	99.82 95	91.01 238	99.23 77	99.22 124

UWE-MVS		93.18 195	93.40 164	92.50 314	96.56 191	83.55 382	98.09 291	97.84 74	89.50 214	91.72 231	96.23 279	91.08 40	96.70 344	86.28 304	93.33 247	97.26 280

FE-MVS		91.38 249	90.16 262	95.05 216	96.46 197	87.53 289	89.69 480	97.84 74	82.97 390	92.18 221	92.00 370	84.07 179	98.93 180	80.71 378	95.52 198	98.68 195

WR-MVS		88.54 324	87.22 329	92.52 313	91.93 393	89.50 209	98.56 222	97.84 74	86.99 306	81.87 374	93.81 331	74.25 328	95.92 395	85.29 315	74.43 410	92.12 360

DELS-MVS		97.12 29	96.60 49	98.68 12	98.03 117	96.57 12	99.84 14	97.84 74	96.36 27	95.20 147	98.24 148	88.17 88	99.83 92	96.11 120	99.60 54	99.64 76
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_8		97.06 33	96.94 30	97.44 53	97.78 124	92.77 107	99.83 15	97.83 78	97.58 3	99.25 19	99.20 41	82.71 209	99.92 50	99.64 8	98.61 117	99.64 76

fmvsm_s_conf0.5_n_3		96.58 54	96.55 50	96.66 105	97.23 157	92.59 113	99.81 20	97.82 79	97.35 7	99.42 10	99.16 51	80.27 246	99.93 47	99.26 27	98.60 119	97.45 272

EI-MVSNet-Vis-set		95.76 91	95.63 93	96.17 140	99.14 72	90.33 175	98.49 232	97.82 79	91.92 124	94.75 156	98.88 102	87.06 115	99.48 139	95.40 141	97.17 162	98.70 192

无先验							98.52 226	97.82 79	87.20 303				99.90 62	87.64 282		99.85 35

EPNet_dtu		92.28 227	92.15 212	92.70 310	97.29 154	84.84 365	98.64 200	97.82 79	92.91 100	93.02 197	97.02 235	85.48 153	95.70 411	72.25 443	94.89 213	97.55 270
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SDMVSNet		91.09 257	89.91 264	94.65 234	96.80 184	90.54 170	97.78 315	97.81 83	88.34 263	85.73 316	95.26 307	66.44 403	98.26 218	94.25 174	86.75 322	95.14 326

HFP-MVS		96.42 60	96.26 60	96.90 88	99.69 14	90.96 157	99.47 78	97.81 83	90.54 168	96.88 98	99.05 75	87.57 100	99.96 34	95.65 130	99.72 34	99.78 46

EI-MVSNet-UG-set		95.43 102	95.29 99	95.86 161	99.07 78	89.87 196	98.43 240	97.80 85	91.78 126	94.11 171	98.77 107	86.25 139	99.48 139	94.95 157	96.45 175	98.22 237

ACMMPR		96.28 65	96.14 72	96.73 98	99.68 15	90.47 172	99.47 78	97.80 85	90.54 168	96.83 103	99.03 77	86.51 133	99.95 38	95.65 130	99.72 34	99.75 54

UWE-MVS-28		90.99 262	91.93 219	88.15 414	95.12 272	77.87 449	97.18 353	97.79 87	88.72 246	88.69 290	96.52 267	86.54 131	90.75 481	84.64 325	92.16 278	95.83 323

UBG		95.73 95	95.41 95	96.69 102	96.97 177	93.23 89	99.13 136	97.79 87	91.28 142	94.38 166	96.78 257	92.37 32	98.56 202	96.17 116	93.84 234	98.26 232

MAR-MVS		94.43 141	94.09 132	95.45 181	99.10 76	87.47 291	98.39 255	97.79 87	88.37 261	94.02 174	99.17 50	78.64 277	99.91 57	92.48 218	98.85 101	98.96 151
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
FBQ-MVS		94.65 134	94.17 130	96.09 146	97.22 158	90.65 168	98.93 158	97.78 90	90.19 182	95.02 151	96.47 271	87.80 95	98.41 211	91.72 232	92.45 265	99.21 125

DPM-MVS		97.86 9	97.25 25	99.68 1	98.25 106	99.10 1	99.76 32	97.78 90	96.61 21	98.15 63	99.53 8	93.62 19	100.00 1	91.79 230	99.80 26	99.94 19

API-MVS		94.78 126	94.18 129	96.59 109	99.21 69	90.06 190	98.80 173	97.78 90	83.59 379	93.85 179	99.21 40	83.79 181	99.97 26	92.37 221	99.00 90	99.74 55

新几何1				97.40 58	98.92 89	92.51 115		97.77 93	85.52 341	96.69 111	99.06 73	88.08 92	99.89 70	84.88 321	99.62 50	99.79 43

HPM-MVS++		97.72 13	97.59 14	98.14 26	99.53 46	94.76 48	99.19 116	97.75 94	95.66 35	98.21 62	99.29 29	91.10 39	99.99 9	97.68 80	99.87 9	99.68 67

GG-mvs-BLEND				96.98 82	96.53 193	94.81 47	87.20 483	97.74 95		93.91 177	96.40 273	96.56 2	96.94 335	95.08 150	98.95 95	99.20 126

gg-mvs-nofinetune		90.00 291	87.71 318	96.89 92	96.15 216	94.69 52	85.15 490	97.74 95	68.32 486	92.97 201	60.16 519	96.10 4	96.84 338	93.89 180	98.87 100	99.14 130

旧先验1					98.97 81	92.90 104		97.74 95			99.15 55	91.05 41			99.33 69	99.60 82

IU-MVS					99.63 24	95.38 26		97.73 98	95.54 37	99.54 9				99.69 7	99.81 23	99.99 2

SED-MVS		98.18 2	98.10 4	98.41 19	99.63 24	95.24 29	99.77 29	97.72 99	94.17 60	99.30 17	99.54 4	93.32 22	99.98 14	99.70 5	99.81 23	99.99 2

test_241102_TWO								97.72 99	94.17 60	99.23 20	99.54 4	93.14 27	99.98 14	99.70 5	99.82 19	99.99 2

test_241102_ONE					99.63 24	95.24 29		97.72 99	94.16 62	99.30 17	99.49 12	93.32 22	99.98 14

DPE-MVS		98.11 6	98.00 7	98.44 17	99.50 48	95.39 25	99.29 105	97.72 99	94.50 53	98.64 44	99.54 4	93.32 22	99.97 26	99.58 12	99.90 7	99.95 16
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DeepPCF-MVS	93.56 1	96.55 57	97.84 11	92.68 311	98.71 97	78.11 446	99.70 41	97.71 103	98.18 1	97.36 86	99.76 1	90.37 59	99.94 41	99.27 26	99.54 58	99.99 2

myMVS_eth3d28		95.74 94	95.34 97	96.92 87	97.41 145	93.58 80	99.28 108	97.70 104	90.97 149	93.91 177	97.25 211	90.59 53	98.75 191	96.85 99	94.14 228	98.44 216

fmvsm_l_conf0.5_n_3		97.12 29	96.89 34	97.79 44	97.39 147	93.84 71	99.87 6	97.70 104	97.34 8	99.39 13	99.20 41	82.86 201	99.94 41	99.21 32	99.07 85	99.58 86

test0726					99.66 18	95.20 34	99.77 29	97.70 104	93.95 67	99.35 15	99.54 4	93.18 25

MSP-MVS		97.77 11	98.18 2	96.53 114	99.54 42	90.14 183	99.41 92	97.70 104	95.46 39	98.60 46	99.19 45	95.71 5	99.49 135	98.15 71	99.85 13	99.95 16
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
MSC_two_6792asdad				99.51 2	99.61 30	98.60 2		97.69 108					99.98 14	99.55 16	99.83 15	99.96 11

No_MVS				99.51 2	99.61 30	98.60 2		97.69 108					99.98 14	99.55 16	99.83 15	99.96 11

fmvsm_s_conf0.5_n_6		96.78 43	96.64 48	97.20 70	96.03 225	93.20 91	99.82 19	97.68 110	95.20 42	99.61 6	99.11 67	84.52 171	99.90 62	99.04 39	98.77 110	98.50 213

testing11		95.33 106	94.98 112	96.37 124	97.20 160	92.31 118	99.29 105	97.68 110	90.59 164	94.43 162	97.20 215	90.79 50	98.60 200	95.25 146	92.38 268	98.18 241

DVP-MVS++		98.18 2	98.09 6	98.44 17	99.61 30	95.38 26	99.55 66	97.68 110	93.01 94	99.23 20	99.45 19	95.12 9	99.98 14	99.25 29	99.92 3	99.97 8

test_0728_SECOND				98.77 9	99.66 18	96.37 15	99.72 38	97.68 110					99.98 14	99.64 8	99.82 19	99.96 11

test11								97.68 110

fmvsm_s_conf0.1_n		95.56 99	95.68 88	95.20 206	94.35 321	89.10 224	99.50 74	97.67 115	94.76 50	98.68 43	99.03 77	81.13 240	99.86 82	98.63 50	97.36 157	96.63 301

testing91		94.88 121	94.44 120	96.21 135	97.19 162	91.90 128	99.23 113	97.66 116	89.91 193	93.66 184	97.05 234	90.21 62	98.50 203	93.52 191	91.53 292	98.25 233

testing99		94.88 121	94.45 119	96.17 140	97.20 160	91.91 127	99.20 115	97.66 116	89.95 192	93.68 183	97.06 232	90.28 61	98.50 203	93.52 191	91.54 289	98.12 248

TEST9					99.57 39	93.17 92	99.38 95	97.66 116	89.57 210	98.39 55	99.18 48	90.88 46	99.66 117

train_agg		97.20 27	97.08 27	97.57 51	99.57 39	93.17 92	99.38 95	97.66 116	90.18 183	98.39 55	99.18 48	90.94 42	99.66 117	98.58 54	99.85 13	99.88 29

region2R		96.30 64	96.17 68	96.70 101	99.70 13	90.31 176	99.46 82	97.66 116	90.55 167	97.07 94	99.07 70	86.85 119	99.97 26	95.43 140	99.74 31	99.81 40

SteuartSystems-ACMMP		97.25 23	97.34 23	97.01 77	97.38 148	91.46 141	99.75 35	97.66 116	94.14 64	98.13 64	99.26 30	92.16 34	99.66 117	97.91 75	99.64 44	99.90 23
Skip Steuart: Steuart Systems R&D Blog.
EPP-MVSNet		93.75 168	93.67 154	94.01 272	95.86 230	85.70 348	98.67 196	97.66 116	84.46 364	91.36 242	97.18 218	91.16 37	97.79 281	92.93 211	93.75 239	98.53 211

fmvsm_s_conf0.5_n_2		95.85 85	95.83 79	95.91 159	97.19 162	91.79 129	99.78 28	97.65 123	97.23 10	99.22 22	99.06 73	75.93 307	99.90 62	99.30 25	97.09 164	96.02 320

SMA-MVS		97.24 24	96.99 28	98.00 33	99.30 60	94.20 64	99.16 123	97.65 123	89.55 212	99.22 22	99.52 11	90.34 60	99.99 9	98.32 66	99.83 15	99.82 37
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
test_one_0601					99.59 34	94.89 39		97.64 125	93.14 93	98.93 33	99.45 19	93.45 20

test_8					99.55 41	93.07 95	99.37 98	97.64 125	90.18 183	98.36 57	99.19 45	90.94 42	99.64 123

agg_prior					99.54 42	92.66 108		97.64 125		97.98 73			99.61 125

DeepC-MVS_fast	93.52 2	97.16 28	96.84 37	98.13 27	99.61 30	94.45 57	98.85 166	97.64 125	96.51 25	95.88 128	99.39 23	87.35 109	99.99 9	96.61 105	99.69 40	99.96 11
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
save fliter					99.34 56	93.85 70	99.65 52	97.63 129	95.69 33

原ACMM1				96.18 138	99.03 79	90.08 186		97.63 129	88.98 233	97.00 96	98.97 83	88.14 91	99.71 113	88.23 275	99.62 50	98.76 181

test-260524					99.74 11	96.14 17		97.62 131		97.79 78		91.57 36	100.00 1	99.55 16	99.75 29

DU-MVS		88.83 314	87.51 322	92.79 304	91.46 402	90.07 187	98.71 186	97.62 131	88.87 239	83.21 340	93.68 334	74.63 318	95.93 393	86.95 289	72.47 432	92.36 348

ZD-MVS					99.67 16	93.28 88		97.61 133	87.78 286	97.41 84	99.16 51	90.15 63	99.56 128	98.35 64	99.70 39

CP-MVS		96.22 67	96.15 71	96.42 119	99.67 16	89.62 207	99.70 41	97.61 133	90.07 190	96.00 124	99.16 51	87.43 103	99.92 50	96.03 123	99.72 34	99.70 62

thisisatest0530		94.00 153	93.52 157	95.43 184	95.76 235	90.02 192	98.99 153	97.60 135	86.58 319	91.74 230	97.36 200	94.78 12	98.34 213	86.37 302	92.48 264	97.94 254

tttt0517		93.30 190	93.01 179	94.17 263	95.57 242	86.47 315	98.51 229	97.60 135	85.99 332	90.55 257	97.19 217	94.80 11	98.31 214	85.06 318	91.86 280	97.74 258

thisisatest0515		94.75 127	94.19 127	96.43 118	96.13 221	92.64 111	99.47 78	97.60 135	87.55 295	93.17 193	97.59 184	94.71 13	98.42 210	88.28 274	93.20 248	98.24 236

testdata				95.26 201	98.20 109	87.28 298		97.60 135	85.21 345	98.48 52	99.15 55	88.15 90	98.72 195	90.29 248	99.45 63	99.78 46

ACMMP_NAP		96.59 52	96.18 65	97.81 41	98.82 93	93.55 82	98.88 165	97.59 139	90.66 159	97.98 73	99.14 58	86.59 128	100.00 1	96.47 109	99.46 61	99.89 28

CVMVSNet		90.30 282	90.91 245	88.46 413	94.32 326	73.58 470	97.61 332	97.59 139	90.16 186	88.43 294	97.10 224	76.83 296	92.86 460	82.64 357	93.54 242	98.93 157

XVS		96.47 58	96.37 57	96.77 94	99.62 28	90.66 166	99.43 89	97.58 141	92.41 112	96.86 99	98.96 88	87.37 105	99.87 76	95.65 130	99.43 65	99.78 46

X-MVStestdata		90.69 269	88.66 300	96.77 94	99.62 28	90.66 166	99.43 89	97.58 141	92.41 112	96.86 99	29.59 543	87.37 105	99.87 76	95.65 130	99.43 65	99.78 46

test222					98.32 104	91.21 145	98.08 294	97.58 141	83.74 375	95.87 129	99.02 79	86.74 122			99.64 44	99.81 40

test_prior				97.01 77	99.58 36	91.77 131		97.57 144					99.49 135			99.79 43

CP-MVSNet		86.54 355	85.45 355	89.79 387	91.02 409	82.78 395	97.38 341	97.56 145	85.37 343	79.53 403	93.03 352	71.86 353	95.25 427	79.92 383	73.43 426	91.34 396

fmvsm_s_conf0.5_n_9		96.76 45	96.92 31	96.29 130	97.95 119	89.21 219	99.81 20	97.55 146	97.04 14	99.68 5	99.22 37	82.84 203	99.94 41	99.56 15	98.61 117	99.71 60

test12				97.83 40	99.33 59	94.45 57		97.55 146		97.56 80		88.60 82	99.50 134		99.71 38	99.55 87

PAPR		96.35 61	95.82 81	97.94 35	99.63 24	94.19 65	99.42 91	97.55 146	92.43 109	93.82 182	99.12 63	87.30 110	99.91 57	94.02 178	99.06 86	99.74 55

AdaColmap		93.82 166	93.06 176	96.10 145	99.88 1	89.07 226	98.33 261	97.55 146	86.81 314	90.39 262	98.65 120	75.09 317	99.98 14	93.32 198	97.53 151	99.26 120

TESTMET0.1,1		93.82 166	93.26 170	95.49 180	95.21 264	90.25 177	99.15 128	97.54 150	89.18 224	91.79 229	94.87 312	89.13 72	97.63 301	86.21 305	96.29 182	98.60 206

fmvsm_s_conf0.1_n_a		95.16 112	95.15 104	95.18 207	92.06 388	88.94 237	99.29 105	97.53 151	94.46 55	98.98 30	98.99 81	79.99 249	99.85 86	98.24 70	96.86 169	96.73 298

hse-mvs2		91.67 243	91.51 229	92.15 321	96.22 210	82.61 400	97.74 321	97.53 151	93.85 75	96.27 121	96.15 281	83.19 195	97.44 315	95.81 128	66.86 461	96.40 313

AUN-MVS		90.17 287	89.50 274	92.19 319	96.21 211	82.67 396	97.76 320	97.53 151	88.05 273	91.67 232	96.15 281	83.10 197	97.47 312	88.11 277	66.91 460	96.43 312

ZNCC-MVS		96.09 71	95.81 83	96.95 85	99.42 53	91.19 146	99.55 66	97.53 151	89.72 201	95.86 130	98.94 94	86.59 128	99.97 26	95.13 149	99.56 56	99.68 67

CANet		97.00 34	96.49 52	98.55 13	98.86 92	96.10 18	99.83 15	97.52 155	95.90 29	97.21 90	98.90 98	82.66 211	99.93 47	98.71 46	98.80 105	99.63 79

APDe-MVS		97.53 17	97.47 18	97.70 45	99.58 36	93.63 77	99.56 65	97.52 155	93.59 84	98.01 72	99.12 63	90.80 49	99.55 129	99.26 27	99.79 27	99.93 21
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MDTV_nov1_ep13			90.47 259		96.14 218	88.55 252	91.34 470	97.51 157	89.58 209	92.24 219	90.50 417	86.99 118	97.61 303	77.64 399	92.34 270

QAPM		91.41 248	89.49 275	97.17 72	95.66 239	93.42 86	98.60 213	97.51 157	80.92 424	81.39 381	97.41 196	72.89 343	99.87 76	82.33 363	98.68 113	98.21 238

PAPM_NR		95.43 102	95.05 109	96.57 112	99.42 53	90.14 183	98.58 219	97.51 157	90.65 161	92.44 216	98.90 98	87.77 98	99.90 62	90.88 240	99.32 70	99.68 67

TSAR-MVS + MP.		97.44 20	97.46 19	97.39 59	99.12 73	93.49 85	98.52 226	97.50 160	94.46 55	98.99 29	98.64 121	91.58 35	99.08 173	98.49 58	99.83 15	99.60 82
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
alignmvs		95.77 90	95.00 111	98.06 31	97.35 150	95.68 22	99.71 40	97.50 160	91.50 134	96.16 123	98.61 125	86.28 137	99.00 176	96.19 114	91.74 283	99.51 93

9.14			96.87 35		99.34 56		99.50 74	97.49 162	89.41 218	98.59 47	99.43 21	89.78 66	99.69 114	98.69 47	99.62 50

GST-MVS		95.97 77	95.66 89	96.90 88	99.49 51	91.22 144	99.45 84	97.48 163	89.69 203	95.89 127	98.72 113	86.37 136	99.95 38	94.62 166	99.22 78	99.52 90

DP-MVS Recon		95.85 85	95.15 104	97.95 34	99.87 2	94.38 60	99.60 61	97.48 163	86.58 319	94.42 163	99.13 60	87.36 108	99.98 14	93.64 188	98.33 130	99.48 97

FOURS1					99.50 48	88.94 237	99.55 66	97.47 165	91.32 141	98.12 66

DVP-MVS		98.07 7	98.00 7	98.29 20	99.66 18	95.20 34	99.72 38	97.47 165	93.95 67	99.07 26	99.46 15	93.18 25	99.97 26	99.64 8	99.82 19	99.69 65
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
CPTT-MVS		94.60 135	94.43 121	95.09 211	99.66 18	86.85 307	99.44 85	97.47 165	83.22 384	94.34 167	98.96 88	82.50 213	99.55 129	94.81 159	99.50 59	98.88 162

BP-MVS1		96.59 52	96.36 58	97.29 64	95.05 284	94.72 50	99.44 85	97.45 168	92.71 104	96.41 117	98.50 131	94.11 17	98.50 203	95.61 135	97.97 138	98.66 201

SF-MVS		97.22 26	96.92 31	98.12 29	99.11 74	94.88 40	99.44 85	97.45 168	89.60 208	98.70 41	99.42 22	90.42 57	99.72 112	98.47 59	99.65 42	99.77 51

MTGPA								97.45 168

MTAPA		96.09 71	95.80 84	96.96 84	99.29 61	91.19 146	97.23 349	97.45 168	92.58 106	94.39 165	99.24 34	86.43 135	99.99 9	96.22 113	99.40 68	99.71 60

CDPH-MVS		96.56 56	96.18 65	97.70 45	99.59 34	93.92 68	99.13 136	97.44 172	89.02 232	97.90 75	99.22 37	88.90 78	99.49 135	94.63 165	99.79 27	99.68 67

APD-MVS		96.95 35	96.72 45	97.63 47	99.51 47	93.58 80	99.16 123	97.44 172	90.08 189	98.59 47	99.07 70	89.06 73	99.42 146	97.92 74	99.66 41	99.88 29
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PVSNet_Blended_VisFu		94.67 132	94.11 131	96.34 126	97.14 167	91.10 151	99.32 104	97.43 174	92.10 123	91.53 238	96.38 276	83.29 191	99.68 115	93.42 197	96.37 177	98.25 233

NR-MVSNet		87.74 337	86.00 346	92.96 300	91.46 402	90.68 165	96.65 375	97.42 175	88.02 275	73.42 450	93.68 334	77.31 290	95.83 401	84.26 330	71.82 439	92.36 348

MP-MVS		96.00 74	95.82 81	96.54 113	99.47 52	90.13 185	99.36 99	97.41 176	90.64 162	95.49 142	98.95 91	85.51 150	99.98 14	96.00 124	99.59 55	99.52 90
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
mPP-MVS		95.90 82	95.75 86	96.38 123	99.58 36	89.41 213	99.26 111	97.41 176	90.66 159	94.82 153	98.95 91	86.15 141	99.98 14	95.24 147	99.64 44	99.74 55

OpenMVS	85.28 14	90.75 267	88.84 295	96.48 115	93.58 356	93.51 84	98.80 173	97.41 176	82.59 398	78.62 414	97.49 191	68.00 384	99.82 95	84.52 328	98.55 123	96.11 317

fmvsm_s_conf0.5_n_5		96.46 59	96.23 62	97.15 73	96.42 199	92.80 105	99.83 15	97.39 179	94.50 53	98.71 40	99.13 60	82.52 212	99.90 62	99.24 31	98.38 128	98.74 183

reproduce-ours		96.66 48	96.80 41	96.22 133	98.95 85	89.03 229	98.62 206	97.38 180	93.42 86	96.80 107	99.36 24	88.92 76	99.80 100	98.51 56	99.26 75	99.82 37

our_new_method		96.66 48	96.80 41	96.22 133	98.95 85	89.03 229	98.62 206	97.38 180	93.42 86	96.80 107	99.36 24	88.92 76	99.80 100	98.51 56	99.26 75	99.82 37

tt0805		86.50 357	84.79 366	91.63 341	91.97 389	81.49 409	96.49 380	97.38 180	82.24 406	82.44 355	95.82 294	51.22 470	98.25 219	84.55 327	80.96 368	95.13 328

SD-MVS		97.51 18	97.40 21	97.81 41	99.01 80	93.79 73	99.33 103	97.38 180	93.73 79	98.83 37	99.02 79	90.87 47	99.88 72	98.69 47	99.74 31	99.77 51
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
tpmvs		89.16 303	87.76 316	93.35 291	97.19 162	84.75 367	90.58 478	97.36 184	81.99 409	84.56 326	89.31 438	83.98 180	98.17 228	74.85 420	90.00 311	97.12 283

PS-CasMVS		85.81 369	84.58 371	89.49 397	90.77 411	82.11 403	97.20 351	97.36 184	84.83 355	79.12 410	92.84 356	67.42 390	95.16 429	78.39 396	73.25 427	91.21 403

0.3-1-1-0.015		91.27 251	89.64 270	96.15 144	92.69 376	91.62 136	99.74 36	97.35 186	84.68 360	92.71 208	93.18 347	85.31 160	97.75 290	92.11 224	68.98 449	99.09 137

0.4-1-1-0.1		91.07 258	89.43 277	96.01 152	92.48 379	91.23 143	99.69 48	97.34 187	84.50 363	92.49 214	92.98 355	84.53 170	97.72 295	91.87 229	68.97 451	99.08 141

0.4-1-1-0.2		91.19 256	89.53 273	96.20 136	92.78 375	91.76 133	99.76 32	97.34 187	84.77 356	92.54 212	93.05 351	84.51 172	97.74 293	92.01 225	68.98 449	99.09 137

reproduce_model		96.57 55	96.75 44	96.02 150	98.93 88	88.46 255	98.56 222	97.34 187	93.18 92	96.96 97	99.35 26	88.69 81	99.80 100	98.53 55	99.21 81	99.79 43

SR-MVS		96.13 70	96.16 70	96.07 147	99.42 53	89.04 227	98.59 216	97.33 190	90.44 171	96.84 101	99.12 63	86.75 121	99.41 149	97.47 83	99.44 64	99.76 53

WB-MVSnew		88.69 320	88.34 308	89.77 388	94.30 332	85.99 340	98.14 282	97.31 191	87.15 304	87.85 297	96.07 285	69.91 364	95.52 417	72.83 439	91.47 293	87.80 462

PatchmatchNet		92.05 235	91.04 240	95.06 214	96.17 215	89.04 227	91.26 471	97.26 192	89.56 211	90.64 254	90.56 413	88.35 85	97.11 327	79.53 384	96.07 189	99.03 145
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
FA-MVS(test-final)		92.22 230	91.08 239	95.64 172	96.05 224	88.98 234	91.60 465	97.25 193	86.99 306	91.84 228	92.12 364	83.03 198	99.00 176	86.91 291	93.91 232	98.93 157

test-LLR		93.11 201	92.68 190	94.40 248	94.94 295	87.27 299	99.15 128	97.25 193	90.21 180	91.57 234	94.04 320	84.89 165	97.58 307	85.94 309	96.13 185	98.36 228

test-mter		93.27 193	92.89 185	94.40 248	94.94 295	87.27 299	99.15 128	97.25 193	88.95 235	91.57 234	94.04 320	88.03 93	97.58 307	85.94 309	96.13 185	98.36 228

PEN-MVS		85.21 378	83.93 381	89.07 406	89.89 421	81.31 415	97.09 356	97.24 196	84.45 365	78.66 413	92.68 359	68.44 379	94.87 434	75.98 412	70.92 443	91.04 407

nomal-1		93.28 192	92.96 182	94.27 255	96.12 222	87.08 304	98.16 281	97.23 197	88.41 259	88.79 288	94.03 322	87.66 99	97.86 275	93.72 187	92.50 263	97.86 256

ab-mvs		91.05 261	89.17 283	96.69 102	95.96 227	91.72 134	92.62 454	97.23 197	85.61 340	89.74 277	93.89 330	68.55 377	99.42 146	91.09 236	87.84 317	98.92 159

APD-MVS_3200maxsize		95.64 98	95.65 91	95.62 176	99.24 66	87.80 273	98.42 243	97.22 199	88.93 237	96.64 114	98.98 82	85.49 151	99.36 153	96.68 102	99.27 74	99.70 62

SR-MVS-dyc-post		95.75 92	95.86 78	95.41 186	99.22 67	87.26 301	98.40 250	97.21 200	89.63 205	96.67 112	98.97 83	86.73 124	99.36 153	96.62 103	99.31 71	99.60 82

RE-MVS-def			95.70 87		99.22 67	87.26 301	98.40 250	97.21 200	89.63 205	96.67 112	98.97 83	85.24 161		96.62 103	99.31 71	99.60 82

SCA		90.64 272	89.25 282	94.83 226	94.95 294	88.83 242	96.26 390	97.21 200	90.06 191	90.03 270	90.62 409	66.61 400	96.81 340	83.16 349	94.36 224	98.84 166

RPMNet		85.07 380	81.88 399	94.64 236	93.47 359	86.24 323	84.97 492	97.21 200	64.85 494	90.76 252	78.80 499	80.95 242	99.27 160	53.76 497	92.17 276	98.41 218

VPNet		88.30 326	86.57 337	93.49 287	91.95 391	91.35 142	98.18 278	97.20 204	88.61 249	84.52 328	94.89 311	62.21 428	96.76 343	89.34 261	72.26 435	92.36 348

KinetiMVS		93.07 203	91.98 216	96.34 126	94.84 301	91.78 130	98.73 185	97.18 205	91.25 143	94.01 175	97.09 228	71.02 360	98.86 182	86.77 295	96.89 168	98.37 225

TranMVSNet+NR-MVSNet		87.75 334	86.31 341	92.07 323	90.81 410	88.56 251	98.33 261	97.18 205	87.76 287	81.87 374	93.90 329	72.45 345	95.43 421	83.13 351	71.30 442	92.23 354

cdsmvs_eth3d_5k		22.52 504	30.03 501	0.00 541	0.00 565	0.00 568	0.00 553	97.17 207	0.00 560	0.00 561	98.77 107	74.35 325	0.00 562	0.00 560	0.00 560	0.00 557

tpm2		91.77 241	91.09 238	93.82 279	94.83 302	85.56 351	92.51 455	97.16 208	84.00 370	93.83 181	90.66 406	87.54 101	97.17 324	87.73 281	91.55 288	98.72 189

MP-MVS-pluss		95.80 88	95.30 98	97.29 64	98.95 85	92.66 108	98.59 216	97.14 209	88.95 235	93.12 194	99.25 32	85.62 147	99.94 41	96.56 107	99.48 60	99.28 118
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
PatchMatch-RL		91.47 246	90.54 256	94.26 257	98.20 109	86.36 320	96.94 361	97.14 209	87.75 288	88.98 286	95.75 295	71.80 354	99.40 150	80.92 376	97.39 156	97.02 289

Anonymous20240529		87.66 338	85.58 352	93.92 275	97.59 136	85.01 362	98.13 283	97.13 211	66.69 491	88.47 293	96.01 287	55.09 456	99.51 133	87.00 288	84.12 344	97.23 282

JIA-IIPM		85.97 365	84.85 364	89.33 400	93.23 366	73.68 469	85.05 491	97.13 211	69.62 482	91.56 236	68.03 515	88.03 93	96.96 333	77.89 398	93.12 249	97.34 275

PS-MVSNAJ		96.87 38	96.40 56	98.29 20	97.35 150	97.29 6	99.03 148	97.11 213	95.83 30	98.97 31	99.14 58	82.48 215	99.60 126	98.60 51	99.08 83	98.00 251

HPM-MVS_fast		94.89 119	94.62 116	95.70 168	99.11 74	88.44 256	99.14 131	97.11 213	85.82 336	95.69 137	98.47 139	83.46 186	99.32 158	93.16 206	99.63 49	99.35 111

DeepC-MVS	91.02 4	94.56 138	93.92 142	96.46 116	97.16 166	90.76 162	98.39 255	97.11 213	93.92 69	88.66 291	98.33 144	78.14 283	99.85 86	95.02 152	98.57 121	98.78 177
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
tpmrst		92.78 211	92.16 211	94.65 234	96.27 208	87.45 292	91.83 461	97.10 216	89.10 231	94.68 159	90.69 404	88.22 87	97.73 294	89.78 254	91.80 282	98.77 179

HPM-MVS		95.41 104	95.22 102	95.99 154	99.29 61	89.14 223	99.17 122	97.09 217	87.28 301	95.40 143	98.48 138	84.93 164	99.38 151	95.64 134	99.65 42	99.47 99
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
tpm cat1		88.89 310	87.27 327	93.76 282	95.79 233	85.32 356	90.76 476	97.09 217	76.14 451	85.72 318	88.59 441	82.92 200	98.04 258	76.96 403	91.43 294	97.90 255

dp		90.16 288	88.83 296	94.14 264	96.38 204	86.42 316	91.57 466	97.06 219	84.76 357	88.81 287	90.19 426	84.29 176	97.43 316	75.05 417	91.35 298	98.56 209

xiu_mvs_v2_base		96.66 48	96.17 68	98.11 30	97.11 171	96.96 7	99.01 151	97.04 220	95.51 38	98.86 35	99.11 67	82.19 223	99.36 153	98.59 53	98.14 135	98.00 251

3Dnovator+	87.72 8	93.43 183	91.84 221	98.17 25	95.73 236	95.08 37	98.92 161	97.04 220	91.42 138	81.48 380	97.60 183	74.60 320	99.79 104	90.84 241	98.97 92	99.64 76

sd_testset		89.23 302	88.05 315	92.74 307	96.80 184	85.33 355	95.85 408	97.03 222	88.34 263	85.73 316	95.26 307	61.12 433	97.76 289	85.61 313	86.75 322	95.14 326

CDS-MVSNet		93.47 179	93.04 178	94.76 228	94.75 306	89.45 211	98.82 169	97.03 222	87.91 279	90.97 247	96.48 270	89.06 73	96.36 363	89.50 257	92.81 254	98.49 214
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test0.0.03 1		88.96 308	88.61 301	90.03 382	91.09 407	84.43 370	98.97 156	97.02 224	90.21 180	80.29 392	96.31 278	84.89 165	91.93 475	72.98 436	85.70 333	93.73 334

114514_t		94.06 151	93.05 177	97.06 75	99.08 77	92.26 120	98.97 156	97.01 225	82.58 399	92.57 211	98.22 149	80.68 244	99.30 159	89.34 261	99.02 89	99.63 79

CostFormer		92.89 206	92.48 198	94.12 265	94.99 289	85.89 343	92.89 450	97.00 226	86.98 309	95.00 152	90.78 400	90.05 64	97.51 311	92.92 213	91.73 284	98.96 151

test_fmvsmvis_n_1920		95.47 101	95.40 96	95.70 168	94.33 325	90.22 180	99.70 41	96.98 227	96.80 16	92.75 206	98.89 100	82.46 218	99.92 50	98.36 63	98.33 130	96.97 291

ET-MVSNet_ETH3D		92.56 220	91.45 230	95.88 160	96.39 203	94.13 66	99.46 82	96.97 228	92.18 120	66.94 482	98.29 147	94.65 15	94.28 444	94.34 172	83.82 348	99.24 121

UA-Net		93.30 190	92.62 194	95.34 191	96.27 208	88.53 254	95.88 405	96.97 228	90.90 150	95.37 144	97.07 231	82.38 220	99.10 172	83.91 340	94.86 215	98.38 222

TAMVS		92.62 217	92.09 214	94.20 262	94.10 334	87.68 276	98.41 246	96.97 228	87.53 296	89.74 277	96.04 286	84.77 169	96.49 356	88.97 269	92.31 271	98.42 217

kuosan		84.40 391	83.34 385	87.60 420	95.87 229	79.21 433	92.39 456	96.87 231	76.12 452	73.79 447	93.98 326	81.51 231	90.63 482	64.13 475	75.42 399	92.95 339

guyue		94.21 147	93.72 153	95.66 171	95.22 262	90.17 182	98.74 182	96.85 232	93.67 80	93.01 199	96.72 261	78.83 271	98.06 252	96.04 122	94.44 222	98.77 179

test_fmvsmconf0.1_n		95.94 80	95.79 85	96.40 121	92.42 381	89.92 194	99.79 27	96.85 232	96.53 24	97.22 89	98.67 119	82.71 209	99.84 88	98.92 44	98.98 91	99.43 104

dongtai		81.36 417	80.61 409	83.62 456	94.25 333	73.32 471	95.15 420	96.81 234	73.56 469	69.79 467	92.81 357	81.00 241	86.80 501	52.08 502	70.06 445	90.75 417

Vis-MVSNet		92.64 216	91.85 220	95.03 217	95.12 272	88.23 261	98.48 234	96.81 234	91.61 129	92.16 222	97.22 214	71.58 357	98.00 264	85.85 312	97.81 141	98.88 162
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PMMVS		93.62 175	93.90 145	92.79 304	96.79 186	81.40 412	98.85 166	96.81 234	91.25 143	96.82 105	98.15 153	77.02 295	98.13 233	93.15 208	96.30 180	98.83 169

ADS-MVSNet		88.99 307	87.30 326	94.07 267	96.21 211	87.56 288	87.15 484	96.78 237	83.01 388	89.91 273	87.27 453	78.87 269	97.01 332	74.20 425	92.27 272	97.64 264

BridgeMVS		96.83 39	96.51 51	97.81 41	97.60 135	95.15 36	98.40 250	96.77 238	93.00 96	98.69 42	96.19 280	89.75 67	98.76 190	98.45 60	99.72 34	99.51 93

MVSMamba_PlusPlus		95.73 95	95.15 104	97.44 53	97.28 156	94.35 62	98.26 270	96.75 239	83.09 387	97.84 76	95.97 288	89.59 69	98.48 208	97.86 76	99.73 33	99.49 96

WBMVS		91.35 250	90.49 257	93.94 274	96.97 177	93.40 87	99.27 110	96.71 240	87.40 299	83.10 345	91.76 376	92.38 31	96.23 377	88.95 270	77.89 384	92.17 358

Vis-MVSNet (Re-imp)		93.26 194	93.00 181	94.06 269	96.14 218	86.71 310	98.68 193	96.70 241	88.30 265	89.71 279	97.64 181	85.43 154	96.39 361	88.06 278	96.32 178	99.08 141

Anonymous20231211		84.72 383	82.65 395	90.91 354	97.71 128	84.55 369	97.28 345	96.67 242	66.88 490	79.18 409	90.87 399	58.47 441	96.60 347	82.61 358	74.20 414	91.59 380

Syy-MVS		84.10 396	84.53 372	82.83 460	95.14 270	65.71 492	97.68 325	96.66 243	86.52 322	82.63 350	96.84 254	68.15 381	89.89 486	45.62 510	91.54 289	92.87 340

myMVS_eth3d		88.68 322	89.07 288	87.50 422	95.14 270	79.74 429	97.68 325	96.66 243	86.52 322	82.63 350	96.84 254	85.22 162	89.89 486	69.43 455	91.54 289	92.87 340

SSC-MVS3.2		85.22 377	83.90 382	89.17 403	91.87 394	79.84 428	97.66 328	96.63 245	86.81 314	81.99 369	91.35 387	55.80 449	96.00 388	76.52 409	76.53 395	91.67 371

EIA-MVS		95.11 113	95.27 100	94.64 236	96.34 205	86.51 313	99.59 62	96.62 246	92.51 107	94.08 172	98.64 121	86.05 142	98.24 220	95.07 151	98.50 124	99.18 127

ETV-MVS		96.00 74	96.00 73	96.00 153	96.56 191	91.05 154	99.63 59	96.61 247	93.26 91	97.39 85	98.30 146	86.62 127	98.13 233	98.07 72	97.57 148	98.82 170

usedtu_dtu_shiyan1		89.12 304	87.56 320	93.78 280	89.74 424	93.60 78	98.70 189	96.60 248	87.85 281	83.43 337	91.56 381	76.34 303	95.92 395	82.75 354	81.08 365	91.82 367

FE-MVSNET3		89.12 304	87.56 320	93.78 280	89.74 424	93.60 78	98.70 189	96.60 248	87.85 281	83.43 337	91.56 381	76.34 303	95.92 395	82.75 354	81.08 365	91.82 367

LS3D		90.19 285	88.72 298	94.59 242	98.97 81	86.33 321	96.90 363	96.60 248	74.96 463	84.06 333	98.74 110	75.78 311	99.83 92	74.93 418	97.57 148	97.62 268

EI-MVSNet		89.87 293	89.38 279	91.36 346	94.32 326	85.87 344	97.61 332	96.59 251	85.10 347	85.51 320	97.10 224	81.30 238	96.56 350	83.85 342	83.03 355	91.64 373

MVSTER		92.71 213	92.32 201	93.86 277	97.29 154	92.95 102	99.01 151	96.59 251	90.09 188	85.51 320	94.00 325	94.61 16	96.56 350	90.77 244	83.03 355	92.08 362

cascas		90.93 264	89.33 280	95.76 165	95.69 237	93.03 97	98.99 153	96.59 251	80.49 426	86.79 311	94.45 317	65.23 413	98.60 200	93.52 191	92.18 275	95.66 325

TAPA-MVS	87.50 9	90.35 279	89.05 289	94.25 258	98.48 103	85.17 359	98.42 243	96.58 254	82.44 404	87.24 304	98.53 127	82.77 205	98.84 184	59.09 489	97.88 140	98.72 189
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
OMC-MVS		93.90 160	93.62 155	94.73 231	98.63 99	87.00 305	98.04 300	96.56 255	92.19 119	92.46 215	98.73 111	79.49 259	99.14 170	92.16 223	94.34 226	98.03 250

PLC	91.07 3	94.23 146	94.01 134	94.87 222	99.17 71	87.49 290	99.25 112	96.55 256	88.43 258	91.26 243	98.21 151	85.92 143	99.86 82	89.77 255	97.57 148	97.24 281
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TSAR-MVS + GP.		96.95 35	96.91 33	97.07 74	98.88 91	91.62 136	99.58 63	96.54 257	95.09 44	96.84 101	98.63 123	91.16 37	99.77 108	99.04 39	96.42 176	99.81 40

PRO-TEST		96.23 66	95.99 74	96.95 85	96.86 180	93.81 72	99.19 116	96.51 258	94.78 49	98.27 61	98.49 134	83.43 187	97.60 304	98.43 61	97.99 137	99.46 100

cl22		89.57 299	88.79 297	91.91 325	97.94 120	87.62 285	97.98 304	96.51 258	85.03 350	82.37 359	91.79 373	83.65 182	96.50 354	85.96 308	77.89 384	91.61 378

xiu_mvs_v1_base_debu		94.73 128	93.98 136	96.99 79	95.19 265	95.24 29	98.62 206	96.50 260	92.99 97	97.52 81	98.83 104	72.37 346	99.15 166	97.03 91	96.74 170	96.58 304

xiu_mvs_v1_base		94.73 128	93.98 136	96.99 79	95.19 265	95.24 29	98.62 206	96.50 260	92.99 97	97.52 81	98.83 104	72.37 346	99.15 166	97.03 91	96.74 170	96.58 304

xiu_mvs_v1_base_debi		94.73 128	93.98 136	96.99 79	95.19 265	95.24 29	98.62 206	96.50 260	92.99 97	97.52 81	98.83 104	72.37 346	99.15 166	97.03 91	96.74 170	96.58 304

lupinMVS		96.32 63	95.94 75	97.44 53	95.05 284	94.87 41	99.86 9	96.50 260	93.82 77	98.04 70	98.77 107	85.52 148	98.09 242	96.98 94	98.97 92	99.37 108

fmvsm_s_conf0.5_n_11		96.80 41	96.97 29	96.28 131	98.09 114	92.26 120	99.87 6	96.49 264	97.55 4	99.75 3	99.32 28	83.20 194	99.91 57	99.57 13	98.88 99	96.67 300

mvs_anonymous		92.50 221	91.65 226	95.06 214	96.60 190	89.64 206	97.06 357	96.44 265	86.64 318	84.14 331	93.93 328	82.49 214	96.17 381	91.47 233	96.08 188	99.35 111

GDP-MVS		96.05 73	95.63 93	97.31 63	95.37 256	94.65 53	99.36 99	96.42 266	92.14 122	97.07 94	98.53 127	93.33 21	98.50 203	91.76 231	96.66 173	98.78 177

VDDNet		90.08 290	88.54 306	94.69 233	94.41 319	87.68 276	98.21 276	96.40 267	76.21 450	93.33 192	97.75 168	54.93 458	98.77 187	94.71 163	90.96 301	97.61 269

NormalMVS		95.87 83	95.83 79	95.99 154	99.27 63	90.37 173	99.14 131	96.39 268	94.92 45	96.30 119	97.98 156	85.33 158	99.23 161	94.35 170	98.82 102	98.37 225

Elysia		90.62 273	88.95 291	95.64 172	93.08 369	91.94 125	97.65 329	96.39 268	84.72 358	90.59 255	95.95 289	62.22 426	98.23 221	83.69 343	96.23 183	96.74 296

StellarMVS		90.62 273	88.95 291	95.64 172	93.08 369	91.94 125	97.65 329	96.39 268	84.72 358	90.59 255	95.95 289	62.22 426	98.23 221	83.69 343	96.23 183	96.74 296

mvsmamba		94.27 145	93.91 144	95.35 190	96.42 199	88.61 249	97.77 317	96.38 271	91.17 146	94.05 173	95.27 306	78.41 280	97.96 266	97.36 86	98.40 127	99.48 97

HQP3-MVS								96.37 272							86.29 325

PatchT		85.44 375	83.19 386	92.22 317	93.13 368	83.00 388	83.80 498	96.37 272	70.62 475	90.55 257	79.63 495	84.81 167	94.87 434	58.18 491	91.59 286	98.79 174

HQP-MVS		91.50 245	91.23 235	92.29 316	93.95 339	86.39 318	99.16 123	96.37 272	93.92 69	87.57 299	96.67 264	73.34 334	97.77 283	93.82 185	86.29 325	92.72 342

UnsupCasMVSNet_eth		78.90 431	76.67 436	85.58 443	82.81 485	74.94 464	91.98 460	96.31 275	84.64 361	65.84 488	87.71 446	51.33 469	92.23 470	72.89 438	56.50 495	89.56 443

HQP_MVS		91.26 252	90.95 244	92.16 320	93.84 347	86.07 337	99.02 149	96.30 276	93.38 89	86.99 306	96.52 267	72.92 341	97.75 290	93.46 195	86.17 328	92.67 344

plane_prior5								96.30 276					97.75 290	93.46 195	86.17 328	92.67 344

jason		95.40 105	94.86 113	97.03 76	92.91 372	94.23 63	99.70 41	96.30 276	93.56 85	96.73 110	98.52 129	81.46 235	97.91 268	96.08 121	98.47 126	98.96 151
jason: jason.
CLD-MVS		91.06 260	90.71 252	92.10 322	94.05 338	86.10 334	99.55 66	96.29 279	94.16 62	84.70 325	97.17 219	69.62 369	97.82 277	94.74 161	86.08 330	92.39 347
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GA-MVS		90.10 289	88.69 299	94.33 252	92.44 380	87.97 269	99.08 141	96.26 280	89.65 204	86.92 308	93.11 350	68.09 382	96.96 333	82.54 359	90.15 308	98.05 249

DTE-MVSNet		84.14 394	82.80 390	88.14 415	88.95 437	79.87 427	96.81 366	96.24 281	83.50 380	77.60 427	92.52 361	67.89 386	94.24 445	72.64 440	69.05 448	90.32 427

LFMVS		92.23 229	90.84 248	96.42 119	98.24 108	91.08 153	98.24 273	96.22 282	83.39 382	94.74 157	98.31 145	61.12 433	98.85 183	94.45 168	92.82 252	99.32 114

LuminaMVS		93.16 198	92.30 202	95.76 165	92.26 383	92.64 111	97.60 334	96.21 283	90.30 177	93.06 196	95.59 297	76.00 306	97.89 270	94.93 158	94.70 216	96.76 295

balanced_ft_v1		94.96 118	94.35 122	96.78 93	97.54 139	92.05 123	98.03 301	96.20 284	90.90 150	96.83 103	95.51 299	76.75 297	98.77 187	98.68 49	98.70 112	99.52 90

baseline1		92.61 218	91.28 234	96.58 110	97.05 175	94.63 54	97.72 322	96.20 284	89.82 197	88.56 292	96.85 251	86.85 119	97.82 277	88.42 272	80.10 374	97.30 278

FMVSNet3		88.81 316	87.08 330	93.99 273	96.52 194	94.59 55	98.08 294	96.20 284	85.85 335	82.12 363	91.60 379	74.05 329	95.40 423	79.04 388	80.24 371	91.99 365

sasdasda		95.02 116	93.96 139	98.20 23	97.53 140	95.92 19	98.71 186	96.19 287	91.78 126	95.86 130	98.49 134	79.53 257	99.03 174	96.12 118	91.42 295	99.66 71

canonicalmvs		95.02 116	93.96 139	98.20 23	97.53 140	95.92 19	98.71 186	96.19 287	91.78 126	95.86 130	98.49 134	79.53 257	99.03 174	96.12 118	91.42 295	99.66 71

fmvsm_s_conf0.1_n_2		95.24 110	95.04 110	95.83 162	95.60 240	91.71 135	99.65 52	96.18 289	96.99 15	98.79 38	98.91 96	73.91 331	99.87 76	99.00 41	96.30 180	95.91 322

dmvs_re		88.69 320	88.06 314	90.59 363	93.83 349	78.68 439	95.75 411	96.18 289	87.99 276	84.48 329	96.32 277	67.52 388	96.94 335	84.98 320	85.49 334	96.14 316

MVSFormer		94.71 131	94.08 133	96.61 107	95.05 284	94.87 41	97.77 317	96.17 291	86.84 312	98.04 70	98.52 129	85.52 148	95.99 389	89.83 251	98.97 92	98.96 151

test_djsdf		88.26 328	87.73 317	89.84 385	88.05 448	82.21 402	97.77 317	96.17 291	86.84 312	82.41 358	91.95 372	72.07 350	95.99 389	89.83 251	84.50 340	91.32 397

MS-PatchMatch		86.75 350	85.92 347	89.22 401	91.97 389	82.47 401	96.91 362	96.14 293	83.74 375	77.73 426	93.53 340	58.19 442	97.37 320	76.75 406	98.35 129	87.84 460

CS-MVS		95.75 92	96.19 63	94.40 248	97.88 122	86.22 325	99.66 50	96.12 294	92.69 105	98.07 68	98.89 100	87.09 113	97.59 305	96.71 100	98.62 116	99.39 107

E3new		94.19 148	93.78 151	95.43 184	95.81 232	89.44 212	98.80 173	96.11 295	90.24 179	93.85 179	97.75 168	80.94 243	98.14 230	95.00 154	95.48 201	98.72 189

viewcassd2359sk11		93.95 157	93.48 160	95.36 187	95.48 248	89.25 218	98.74 182	96.10 296	90.10 187	93.48 188	97.55 187	80.05 248	98.14 230	94.66 164	95.16 206	98.69 193

MGCFI-Net		94.89 119	93.84 148	98.06 31	97.49 143	95.55 23	98.64 200	96.10 296	91.60 132	95.75 135	98.46 141	79.31 261	98.98 178	95.95 125	91.24 300	99.65 75

SPE-MVS-test		95.98 76	96.34 59	94.90 221	98.06 116	87.66 279	99.69 48	96.10 296	93.66 81	98.35 58	99.05 75	86.28 137	97.66 298	96.96 95	98.90 98	99.37 108

VDD-MVS		91.24 255	90.18 261	94.45 247	97.08 172	85.84 346	98.40 250	96.10 296	86.99 306	93.36 191	98.16 152	54.27 460	99.20 163	96.59 106	90.63 306	98.31 231

PCF-MVS	89.78 5	91.26 252	89.63 271	96.16 143	95.44 250	91.58 140	95.29 418	96.10 296	85.07 349	82.75 347	97.45 194	78.28 282	99.78 107	80.60 380	95.65 196	97.12 283
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
E2		93.62 175	93.07 174	95.26 201	95.00 288	88.99 233	98.63 202	96.09 301	89.84 195	93.02 197	97.36 200	78.88 267	98.11 237	94.23 175	94.60 218	98.67 196

E3		93.62 175	93.07 174	95.26 201	94.98 290	89.00 232	98.63 202	96.09 301	89.83 196	93.01 199	97.35 202	78.90 266	98.11 237	94.23 175	94.60 218	98.67 196

test_cas_vis1_n_1920		93.86 165	93.74 152	94.22 261	95.39 254	86.08 335	99.73 37	96.07 303	96.38 26	97.19 92	97.78 165	65.46 411	99.86 82	96.71 100	98.92 96	96.73 298

test_vis1_n_1920		93.08 202	93.42 162	92.04 324	96.31 206	79.36 431	99.83 15	96.06 304	96.72 18	98.53 51	98.10 154	58.57 440	99.91 57	97.86 76	98.79 108	96.85 293

MVS_Test		93.67 172	92.67 191	96.69 102	96.72 188	92.66 108	97.22 350	96.03 305	87.69 292	95.12 149	94.03 322	81.55 230	98.28 217	89.17 267	96.46 174	99.14 130

viewmanbaseed2359cas		93.90 160	93.34 166	95.56 179	95.39 254	89.72 203	98.58 219	96.00 306	90.32 176	93.58 186	97.78 165	78.71 275	98.07 249	94.43 169	95.29 203	98.88 162

E4		93.15 200	92.50 197	95.09 211	94.41 319	88.61 249	98.48 234	95.99 307	89.40 219	92.22 220	97.13 221	77.43 289	98.10 240	93.58 190	93.90 233	98.56 209

casdiffmvs_mvg		94.00 153	93.33 167	96.03 149	95.22 262	90.90 160	99.09 140	95.99 307	90.58 165	91.55 237	97.37 199	79.91 250	98.06 252	95.01 153	95.22 205	99.13 132
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
jajsoiax		87.35 341	86.51 339	89.87 383	87.75 455	81.74 407	97.03 358	95.98 309	88.47 252	80.15 394	93.80 332	61.47 430	96.36 363	89.44 259	84.47 341	91.50 382

E5new		92.80 207	92.19 206	94.62 238	94.34 322	87.64 280	98.08 294	95.97 310	89.15 225	92.01 224	97.08 229	76.37 301	98.08 244	93.25 201	93.46 243	98.15 243

E6new		92.80 207	92.19 206	94.62 238	94.31 330	87.64 280	98.08 294	95.97 310	89.15 225	92.01 224	97.10 224	76.38 299	98.08 244	93.25 201	93.45 245	98.15 243

E6		92.80 207	92.19 206	94.62 238	94.31 330	87.64 280	98.08 294	95.97 310	89.15 225	92.01 224	97.10 224	76.38 299	98.08 244	93.25 201	93.45 245	98.15 243

E5		92.80 207	92.19 206	94.62 238	94.34 322	87.64 280	98.08 294	95.97 310	89.15 225	92.01 224	97.08 229	76.37 301	98.08 244	93.25 201	93.46 243	98.15 243

PS-MVSNAJss		89.54 300	89.05 289	91.00 352	88.77 438	84.36 371	97.39 339	95.97 310	88.47 252	81.88 372	93.80 332	82.48 215	96.50 354	89.34 261	83.34 354	92.15 359

F-COLMAP		92.07 234	91.75 225	93.02 297	98.16 112	82.89 392	98.79 178	95.97 310	86.54 321	87.92 296	97.80 163	78.69 276	99.65 121	85.97 307	95.93 191	96.53 307

miper_enhance_ethall		90.33 280	89.70 267	92.22 317	97.12 170	88.93 239	98.35 260	95.96 316	88.60 250	83.14 344	92.33 363	87.38 104	96.18 379	86.49 301	77.89 384	91.55 381

TR-MVS		90.77 266	89.44 276	94.76 228	96.31 206	88.02 267	97.92 306	95.96 316	85.52 341	88.22 295	97.23 213	66.80 397	98.09 242	84.58 326	92.38 268	98.17 242

CMPMVS	58.40 21	80.48 421	80.11 419	81.59 467	85.10 471	59.56 500	94.14 435	95.95 318	68.54 485	60.71 494	93.31 343	55.35 455	97.87 273	83.06 352	84.85 338	87.33 467
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
VortexMVS		90.18 286	89.28 281	92.89 302	95.58 241	90.94 159	97.82 312	95.94 319	90.90 150	82.11 367	91.48 384	78.75 274	96.08 385	91.99 226	78.97 378	91.65 372

test_fmvsmconf0.01_n		94.14 149	93.51 159	96.04 148	86.79 461	89.19 220	99.28 108	95.94 319	95.70 32	95.50 141	98.49 134	73.27 337	99.79 104	98.28 68	98.32 132	99.15 129

LPG-MVS_test		88.86 311	88.47 307	90.06 378	93.35 364	80.95 421	98.22 274	95.94 319	87.73 290	83.17 342	96.11 283	66.28 404	97.77 283	90.19 249	85.19 335	91.46 385

LGP-MVS_train				90.06 378	93.35 364	80.95 421		95.94 319	87.73 290	83.17 342	96.11 283	66.28 404	97.77 283	90.19 249	85.19 335	91.46 385

OPM-MVS		89.76 296	89.15 287	91.57 342	90.53 413	85.58 350	98.11 287	95.93 323	92.88 102	86.05 313	96.47 271	67.06 393	97.87 273	89.29 264	86.08 330	91.26 400
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Casviewmamba		93.63 174	93.20 171	94.94 219	95.12 272	87.64 280	98.76 180	95.92 324	90.44 171	92.12 223	97.90 159	79.15 263	98.16 229	93.89 180	95.52 198	99.00 146

viewdifsd2359ckpt13		93.45 180	92.86 186	95.21 204	95.45 249	88.91 241	98.59 216	95.92 324	89.39 220	92.67 210	97.33 204	78.02 285	98.03 259	93.27 200	95.12 208	98.69 193

XVG-OURS-SEG-HR		90.95 263	90.66 255	91.83 327	95.18 268	81.14 419	95.92 402	95.92 324	88.40 260	90.33 263	97.85 160	70.66 363	99.38 151	92.83 214	88.83 314	94.98 329

XVG-OURS		90.83 265	90.49 257	91.86 326	95.23 261	81.25 416	95.79 410	95.92 324	88.96 234	90.02 271	98.03 155	71.60 356	99.35 156	91.06 237	87.78 318	94.98 329

tpm		89.67 297	88.95 291	91.82 329	92.54 378	81.43 411	92.95 449	95.92 324	87.81 285	90.50 259	89.44 435	84.99 163	95.65 413	83.67 345	82.71 358	98.38 222

EC-MVSNet		95.09 114	95.17 103	94.84 225	95.42 251	88.17 262	99.48 76	95.92 324	91.47 135	97.34 87	98.36 143	82.77 205	97.41 317	97.24 88	98.58 120	98.94 156

ACMM	86.95 13	88.77 317	88.22 311	90.43 369	93.61 355	81.34 414	98.50 230	95.92 324	87.88 280	83.85 334	95.20 309	67.20 391	97.89 270	86.90 292	84.90 337	92.06 363
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline		93.91 159	93.30 168	95.72 167	95.10 281	90.07 187	97.48 336	95.91 331	91.03 147	93.54 187	97.68 176	79.58 254	98.02 261	94.27 173	95.14 207	99.08 141

mvs_tets		87.09 344	86.22 342	89.71 389	87.87 451	81.39 413	96.73 372	95.90 332	88.19 269	79.99 396	93.61 337	59.96 437	96.31 371	89.40 260	84.34 342	91.43 387

XXY-MVS		87.75 334	86.02 345	92.95 301	90.46 415	89.70 205	97.71 324	95.90 332	84.02 369	80.95 383	94.05 319	67.51 389	97.10 329	85.16 316	78.41 381	92.04 364

nrg030		90.23 283	88.87 294	94.32 253	91.53 401	93.54 83	98.79 178	95.89 334	88.12 271	84.55 327	94.61 316	78.80 272	96.88 337	92.35 222	75.21 401	92.53 346

CNLPA		93.64 173	92.74 189	96.36 125	98.96 84	90.01 193	99.19 116	95.89 334	86.22 327	89.40 283	98.85 103	80.66 245	99.84 88	88.57 271	96.92 167	99.24 121

KD-MVS_2432*1600		82.98 407	80.52 411	90.38 371	94.32 326	88.98 234	92.87 451	95.87 336	80.46 427	73.79 447	87.49 450	82.76 207	93.29 457	70.56 450	46.53 509	88.87 455

miper_refine_blended		82.98 407	80.52 411	90.38 371	94.32 326	88.98 234	92.87 451	95.87 336	80.46 427	73.79 447	87.49 450	82.76 207	93.29 457	70.56 450	46.53 509	88.87 455

AstraMVS		93.38 187	93.01 179	94.50 243	93.94 342	86.55 311	98.91 162	95.86 338	93.88 73	92.88 202	97.49 191	75.61 315	98.21 223	96.15 117	92.39 267	98.73 188

FMVSNet2		86.90 346	84.79 366	93.24 293	95.11 278	92.54 114	97.67 327	95.86 338	82.94 391	80.55 387	91.17 392	62.89 423	95.29 426	77.23 400	79.71 377	91.90 366

hybridcas		93.44 181	92.82 188	95.31 195	94.91 298	89.08 225	98.82 169	95.84 340	90.28 178	91.22 245	97.65 180	78.39 281	98.06 252	92.71 216	95.55 197	98.79 174

viewmacassd2359aftdt		93.16 198	92.44 199	95.31 195	94.34 322	89.19 220	98.40 250	95.84 340	89.62 207	92.87 204	97.31 205	76.07 305	98.00 264	92.93 211	94.58 220	98.75 182

casdiffmvs		93.98 155	93.43 161	95.61 177	95.07 283	89.86 197	98.80 173	95.84 340	90.98 148	92.74 207	97.66 178	79.71 252	98.10 240	94.72 162	95.37 202	98.87 165
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
onestephybrid01		94.12 150	93.87 147	94.86 224	95.26 259	87.86 271	98.60 213	95.82 343	90.70 157	95.67 138	97.72 174	79.72 251	98.13 233	96.37 110	94.99 211	98.60 206

viewdifsd2359ckpt07		92.71 213	92.19 206	94.28 254	94.96 293	86.26 322	98.29 268	95.80 344	88.71 247	90.81 249	97.34 203	76.57 298	98.19 225	93.16 206	94.05 230	98.39 221

UniMVSNet_ETH3D		85.65 374	83.79 383	91.21 347	90.41 416	80.75 424	95.36 416	95.78 345	78.76 436	81.83 377	94.33 318	49.86 476	96.66 345	84.30 329	83.52 352	96.22 315

Effi-MVS+		93.87 164	93.15 173	96.02 150	95.79 233	90.76 162	96.70 373	95.78 345	86.98 309	95.71 136	97.17 219	79.58 254	98.01 262	94.57 167	96.09 187	99.31 115

gbinet_0.2-2-1-0.02		83.16 406	80.42 415	91.39 345	83.70 477	87.60 286	98.62 206	95.77 347	75.83 453	79.33 406	87.92 444	64.07 417	95.34 424	81.87 370	56.67 493	91.25 401

RRT-MVS		93.39 185	92.64 192	95.64 172	96.11 223	88.75 246	97.40 338	95.77 347	89.46 216	92.70 209	95.42 303	72.98 340	98.81 185	96.91 97	96.97 165	99.37 108

EU-MVSNet		84.19 393	84.42 375	83.52 458	88.64 441	67.37 491	96.04 400	95.76 349	85.29 344	78.44 421	93.18 347	70.67 362	91.48 478	75.79 414	75.98 396	91.70 370

BH-w/o		92.32 225	91.79 223	93.91 276	96.85 181	86.18 331	99.11 139	95.74 350	88.13 270	84.81 324	97.00 236	77.26 291	97.91 268	89.16 268	98.03 136	97.64 264

icg_test_0407_2		91.56 244	90.90 246	93.54 286	94.61 312	86.22 325	95.72 412	95.72 351	88.78 241	89.76 275	96.93 242	77.24 292	95.65 413	86.73 296	92.59 258	98.74 183

IMVS_0407		91.79 240	90.98 242	94.24 260	94.61 312	86.22 325	96.45 381	95.72 351	88.78 241	89.76 275	96.93 242	77.24 292	97.77 283	86.73 296	92.59 258	98.74 183

IMVS_0404		89.79 295	88.57 304	93.47 288	94.61 312	86.22 325	94.45 426	95.72 351	88.78 241	81.88 372	96.93 242	65.39 412	95.47 419	86.73 296	92.59 258	98.74 183

IMVS_0403		91.93 237	91.13 237	94.34 251	94.61 312	86.22 325	96.70 373	95.72 351	88.78 241	90.00 272	96.93 242	78.07 284	98.07 249	86.73 296	92.59 258	98.74 183

anonymousdsp		86.69 351	85.75 350	89.53 394	86.46 464	82.94 389	96.39 383	95.71 355	83.97 371	79.63 401	90.70 403	68.85 375	95.94 392	86.01 306	84.02 345	89.72 440

hybrid		93.89 162	93.41 163	95.33 193	94.98 290	89.30 216	98.58 219	95.70 356	89.70 202	94.76 155	97.54 188	78.98 265	98.07 249	95.52 139	94.92 212	98.61 204

Fast-Effi-MVS+		91.72 242	90.79 251	94.49 244	95.89 228	87.40 294	99.54 71	95.70 356	85.01 352	89.28 285	95.68 296	77.75 287	97.57 310	83.22 348	95.06 210	98.51 212

IS-MVSNet		93.00 205	92.51 196	94.49 244	96.14 218	87.36 295	98.31 264	95.70 356	88.58 251	90.17 266	97.50 190	83.02 199	97.22 323	87.06 286	96.07 189	98.90 161

viewmambaseed2359dif		93.05 204	92.64 192	94.25 258	94.94 295	86.53 312	98.38 257	95.69 359	87.03 305	93.38 190	97.74 171	78.79 273	98.08 244	93.49 194	94.35 225	98.15 243

diffmvs_AUTHOR		94.30 144	93.92 142	95.45 181	94.77 305	89.92 194	98.55 225	95.68 360	91.33 140	95.83 133	97.64 181	79.58 254	98.05 256	96.19 114	95.66 195	98.37 225

diffmvs		94.59 136	94.19 127	95.81 163	95.54 245	90.69 164	98.70 189	95.68 360	91.61 129	95.96 125	97.81 162	80.11 247	98.06 252	96.52 108	95.76 192	98.67 196
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
casdiffseed414692147		91.84 239	90.69 253	95.28 199	94.50 317	89.32 215	98.31 264	95.67 362	87.82 284	90.22 265	96.63 266	74.27 326	97.94 267	86.37 302	92.43 266	98.59 208

v7n		84.42 390	82.75 393	89.43 399	88.15 446	81.86 406	96.75 370	95.67 362	80.53 425	78.38 422	89.43 436	69.89 365	96.35 368	73.83 430	72.13 436	90.07 432

ACMP	87.39 10	88.71 319	88.24 310	90.12 377	93.91 345	81.06 420	98.50 230	95.67 362	89.43 217	80.37 391	95.55 298	65.67 406	97.83 276	90.55 246	84.51 339	91.47 384
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
viewdifsd2359ckpt09		93.54 178	92.91 184	95.44 183	95.57 242	89.48 210	98.68 193	95.66 365	89.52 213	92.50 213	97.75 168	78.46 279	98.03 259	93.32 198	94.69 217	98.81 171

hybridnocas07		93.98 155	93.52 157	95.36 187	95.01 287	89.37 214	98.63 202	95.64 366	90.79 156	94.69 158	97.31 205	79.01 264	98.11 237	95.54 138	95.07 209	98.61 204

CL-MVSNet_self_test		79.89 425	78.34 427	84.54 451	81.56 489	75.01 463	96.88 364	95.62 367	81.10 419	75.86 436	85.81 470	68.49 378	90.26 484	63.21 478	56.51 494	88.35 457

V42		87.00 345	85.68 351	90.98 353	89.91 419	86.08 335	98.32 263	95.61 368	83.67 378	82.72 348	90.67 405	74.00 330	96.53 352	81.94 369	74.28 413	90.32 427

viewmamba		93.88 163	93.59 156	94.78 227	94.82 303	87.68 276	98.41 246	95.60 369	91.61 129	94.17 170	97.93 158	79.65 253	98.01 262	95.20 148	94.87 214	98.66 201

XVG-ACMP-BASELINE		85.86 367	84.95 362	88.57 411	89.90 420	77.12 453	94.30 431	95.60 369	87.40 299	82.12 363	92.99 354	53.42 464	97.66 298	85.02 319	83.83 346	90.92 410

dtuplus		92.78 211	92.35 200	94.07 267	94.70 307	85.91 341	98.47 237	95.59 371	87.50 297	92.88 202	97.66 178	77.24 292	98.12 236	93.01 209	94.15 227	98.20 239

Anonymous202405211		88.84 312	87.03 332	94.27 255	98.14 113	84.18 374	98.44 239	95.58 372	76.79 448	89.34 284	96.88 249	53.42 464	99.54 131	87.53 283	87.12 321	99.09 137

miper_ehance_all_eth		88.94 309	88.12 313	91.40 343	95.32 258	86.93 306	97.85 311	95.55 373	84.19 367	81.97 370	91.50 383	84.16 177	95.91 398	84.69 323	77.89 384	91.36 394

CANet_DTU		94.31 143	93.35 165	97.20 70	97.03 176	94.71 51	98.62 206	95.54 374	95.61 36	97.21 90	98.47 139	71.88 352	99.84 88	88.38 273	97.46 153	97.04 288

v2v482		87.27 343	85.76 349	91.78 335	89.59 427	87.58 287	98.56 222	95.54 374	84.53 362	82.51 354	91.78 374	73.11 338	96.47 357	82.07 366	74.14 416	91.30 398

wanda-best-256-512		83.28 402	80.44 413	91.78 335	82.91 481	88.24 257	98.43 240	95.51 376	75.76 454	78.60 416	86.54 463	66.95 394	95.71 409	82.44 361	56.84 489	91.38 390

FE-blended-shiyan7		83.27 403	80.44 413	91.78 335	82.91 481	88.24 257	98.43 240	95.51 376	75.76 454	78.60 416	86.54 463	66.93 395	95.71 409	82.44 361	56.84 489	91.38 390

blended_shiyan6		83.17 405	80.34 417	91.67 340	82.80 486	87.93 270	98.29 268	95.51 376	75.63 458	78.46 420	86.48 466	66.74 399	95.70 411	82.33 363	56.84 489	91.37 393

blend_shiyan4		86.02 363	84.08 378	91.83 327	83.24 479	88.24 257	98.42 243	95.51 376	75.55 460	79.43 404	86.84 460	84.51 172	95.77 403	83.97 338	69.26 446	91.48 383

BH-untuned		91.46 247	90.84 248	93.33 292	96.51 195	84.83 366	98.84 168	95.50 380	86.44 326	83.50 335	96.70 262	75.49 316	97.77 283	86.78 294	97.81 141	97.40 273

blended_shiyan8		83.22 404	80.40 416	91.71 338	82.77 487	88.01 268	98.25 272	95.49 381	75.64 457	78.68 412	86.55 461	66.76 398	95.75 405	82.50 360	56.93 488	91.36 394

SSM_0407		92.04 236	91.03 241	95.07 213	95.12 272	89.81 199	97.18 353	95.49 381	86.17 328	89.50 280	97.13 221	75.65 312	97.68 296	89.26 265	93.79 236	97.73 259

SSM_0404		92.33 224	91.33 232	95.33 193	95.35 257	90.54 170	97.45 337	95.49 381	86.17 328	90.26 264	97.13 221	75.65 312	97.82 277	89.26 265	95.26 204	97.63 267

v148		86.38 359	85.06 359	90.37 373	89.47 432	84.10 375	98.52 226	95.48 384	83.80 374	80.93 384	90.22 424	74.60 320	96.31 371	80.92 376	71.55 440	90.69 420

IterMVS-LS		88.34 325	87.44 323	91.04 351	94.10 334	85.85 345	98.10 288	95.48 384	85.12 346	82.03 368	91.21 391	81.35 237	95.63 415	83.86 341	75.73 398	91.63 374
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dcpmvs_2		95.67 97	96.18 65	94.12 265	98.82 93	84.22 373	97.37 342	95.45 386	90.70 157	95.77 134	98.63 123	90.47 55	98.68 197	99.20 33	99.22 78	99.45 101

v1144		86.83 348	85.31 357	91.40 343	89.75 423	87.21 303	98.31 264	95.45 386	83.22 384	82.70 349	90.78 400	73.36 333	96.36 363	79.49 385	74.69 407	90.63 422

v1192		86.32 360	84.71 368	91.17 348	89.53 430	86.40 317	98.13 283	95.44 388	82.52 401	82.42 357	90.62 409	71.58 357	96.33 370	77.23 400	74.88 404	90.79 414

v144192		86.40 358	84.89 363	90.91 354	89.48 431	85.59 349	98.21 276	95.43 389	82.45 403	82.62 352	90.58 412	72.79 344	96.36 363	78.45 395	74.04 417	90.79 414

Effi-MVS+-dtu		89.97 292	90.68 254	87.81 418	95.15 269	71.98 478	97.87 310	95.40 390	91.92 124	87.57 299	91.44 385	74.27 326	96.84 338	89.45 258	93.10 250	94.60 332

c3_l		88.19 329	87.23 328	91.06 350	94.97 292	86.17 332	97.72 322	95.38 391	83.43 381	81.68 378	91.37 386	82.81 204	95.72 408	84.04 337	73.70 418	91.29 399

eth_miper_zixun_eth		87.76 333	87.00 333	90.06 378	94.67 309	82.65 399	97.02 360	95.37 392	84.19 367	81.86 376	91.58 380	81.47 234	95.90 399	83.24 347	73.61 419	91.61 378

v8		86.11 362	84.45 373	91.10 349	89.99 418	86.85 307	97.24 348	95.36 393	81.99 409	79.89 398	89.86 430	74.53 322	96.39 361	78.83 392	72.32 434	90.05 434

v1921920		86.02 363	84.44 374	90.77 360	89.32 433	85.20 357	98.10 288	95.35 394	82.19 407	82.25 361	90.71 402	70.73 361	96.30 374	76.85 405	74.49 409	90.80 413

pmmvs4		87.58 340	86.17 344	91.80 330	89.58 428	88.92 240	97.25 347	95.28 395	82.54 400	80.49 388	93.17 349	75.62 314	96.05 387	82.75 354	78.90 379	90.42 425

viewdifsd2359ckpt11		90.42 277	89.65 268	92.73 309	93.71 354	82.67 396	98.09 291	95.27 396	89.80 199	90.10 269	97.40 197	69.43 371	98.18 227	92.46 219	80.61 370	97.34 275

viewmsd2359difaftdt		90.43 276	89.65 268	92.74 307	93.72 353	82.67 396	98.09 291	95.27 396	89.80 199	90.12 268	97.40 197	69.43 371	98.20 224	92.45 220	80.62 369	97.34 275

GBi-Net		86.67 352	84.96 360	91.80 330	95.11 278	88.81 243	96.77 367	95.25 398	82.94 391	82.12 363	90.25 421	62.89 423	94.97 431	79.04 388	80.24 371	91.62 375

test1		86.67 352	84.96 360	91.80 330	95.11 278	88.81 243	96.77 367	95.25 398	82.94 391	82.12 363	90.25 421	62.89 423	94.97 431	79.04 388	80.24 371	91.62 375

FMVSNet1		83.94 397	81.32 406	91.80 330	91.94 392	88.81 243	96.77 367	95.25 398	77.98 439	78.25 423	90.25 421	50.37 475	94.97 431	73.27 434	77.81 389	91.62 375

mvsany_test1		94.57 137	95.09 108	92.98 298	95.84 231	82.07 404	98.76 180	95.24 401	92.87 103	96.45 115	98.71 116	84.81 167	99.15 166	97.68 80	95.49 200	97.73 259

cl____		87.82 331	86.79 336	90.89 356	94.88 299	85.43 352	97.81 313	95.24 401	82.91 395	80.71 386	91.22 390	81.97 227	95.84 400	81.34 373	75.06 402	91.40 389

miper_lstm_enhance		86.90 346	86.20 343	89.00 407	94.53 316	81.19 417	96.74 371	95.24 401	82.33 405	80.15 394	90.51 416	81.99 225	94.68 440	80.71 378	73.58 421	91.12 405

UnsupCasMVSNet_bld		73.85 456	70.14 460	84.99 447	79.44 495	75.73 460	88.53 481	95.24 401	70.12 480	61.94 492	74.81 507	41.41 490	93.62 453	68.65 460	51.13 504	85.62 481

v1240		85.77 371	84.11 377	90.73 361	89.26 434	85.15 360	97.88 309	95.23 405	81.89 412	82.16 362	90.55 414	69.60 370	96.31 371	75.59 415	74.87 405	90.72 419

DIV-MVS_self_test		87.82 331	86.81 335	90.87 357	94.87 300	85.39 354	97.81 313	95.22 406	82.92 394	80.76 385	91.31 389	81.99 225	95.81 402	81.36 372	75.04 403	91.42 388

v10		85.73 372	84.01 380	90.87 357	90.03 417	86.73 309	97.20 351	95.22 406	81.25 417	79.85 399	89.75 431	73.30 336	96.28 375	76.87 404	72.64 430	89.61 442

mamba_0408		90.65 271	89.16 284	95.12 209	95.12 272	89.81 199	83.02 500	95.17 408	85.95 333	89.50 280	96.85 251	75.85 308	97.82 277	87.19 284	93.79 236	97.73 259

SSM_04072		90.31 281	89.16 284	93.74 283	95.12 272	89.81 199	83.02 500	95.17 408	85.95 333	89.50 280	96.85 251	75.85 308	93.69 451	87.19 284	93.79 236	97.73 259

SD_0403		86.82 349	87.08 330	86.04 438	93.55 357	69.09 487	94.11 436	95.02 410	87.84 283	80.48 389	95.86 293	73.05 339	91.04 480	72.53 441	91.26 299	97.99 253

test_fmvs1		92.35 223	92.94 183	90.57 364	97.19 162	75.43 462	99.55 66	94.97 411	95.20 42	96.82 105	97.57 186	59.59 438	99.84 88	97.30 87	98.29 133	96.46 311

BH-RMVSNet		91.25 254	89.99 263	95.03 217	96.75 187	88.55 252	98.65 198	94.95 412	87.74 289	87.74 298	97.80 163	68.27 380	98.14 230	80.53 381	97.49 152	98.41 218

GeoE		90.60 275	89.56 272	93.72 285	95.10 281	85.43 352	99.41 92	94.94 413	83.96 372	87.21 305	96.83 256	74.37 324	97.05 331	80.50 382	93.73 240	98.67 196

ACMH	83.09 17	84.60 385	82.61 396	90.57 364	93.18 367	82.94 389	96.27 388	94.92 414	81.01 422	72.61 459	93.61 337	56.54 447	97.79 281	74.31 423	81.07 367	90.99 408
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs1_n		91.07 258	91.41 231	90.06 378	94.10 334	74.31 466	99.18 119	94.84 415	94.81 47	96.37 118	97.46 193	50.86 473	99.82 95	97.14 90	97.90 139	96.04 318

test1111		92.12 231	91.19 236	94.94 219	96.15 216	87.36 295	98.12 285	94.84 415	90.85 153	90.97 247	97.26 209	65.60 409	98.37 212	89.74 256	97.14 163	99.07 144

ECVR-MVS		92.29 226	91.33 232	95.15 208	96.41 201	87.84 272	98.10 288	94.84 415	90.82 154	91.42 241	97.28 207	65.61 408	98.49 207	90.33 247	97.19 160	99.12 133

IterMVS		85.81 369	84.67 369	89.22 401	93.51 358	83.67 381	96.32 387	94.80 418	85.09 348	78.69 411	90.17 427	66.57 402	93.17 459	79.48 386	77.42 391	90.81 412
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
LTVRE_ROB	81.71 19	84.59 386	82.72 394	90.18 375	92.89 373	83.18 387	93.15 446	94.74 419	78.99 433	75.14 441	92.69 358	65.64 407	97.63 301	69.46 454	81.82 363	89.74 439
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
pm-mvs1		84.68 384	82.78 392	90.40 370	89.58 428	85.18 358	97.31 343	94.73 420	81.93 411	76.05 433	92.01 368	65.48 410	96.11 384	78.75 393	69.14 447	89.91 437

IterMVS-SCA-FT		85.73 372	84.64 370	89.00 407	93.46 361	82.90 391	96.27 388	94.70 421	85.02 351	78.62 414	90.35 418	66.61 400	93.33 455	79.38 387	77.36 392	90.76 416

1112_ss		92.71 213	91.55 228	96.20 136	95.56 244	91.12 149	98.48 234	94.69 422	88.29 266	86.89 309	98.50 131	87.02 116	98.66 198	84.75 322	89.77 312	98.81 171

Test_1112_low_res		92.27 228	90.97 243	96.18 138	95.53 246	91.10 151	98.47 237	94.66 423	88.28 267	86.83 310	93.50 341	87.00 117	98.65 199	84.69 323	89.74 313	98.80 173

Fast-Effi-MVS+-dtu		88.84 312	88.59 303	89.58 393	93.44 362	78.18 443	98.65 198	94.62 424	88.46 254	84.12 332	95.37 305	68.91 374	96.52 353	82.06 367	91.70 285	94.06 333

our_test_3		84.47 389	82.80 390	89.50 395	89.01 435	83.90 378	97.03 358	94.56 425	81.33 416	75.36 440	90.52 415	71.69 355	94.54 442	68.81 459	76.84 393	90.07 432

ppachtmachnet_test		83.63 400	81.57 403	89.80 386	89.01 435	85.09 361	97.13 355	94.50 426	78.84 434	76.14 432	91.00 394	69.78 366	94.61 441	63.40 477	74.36 411	89.71 441

test_vis1_n		90.40 278	90.27 260	90.79 359	91.55 400	76.48 456	99.12 138	94.44 427	94.31 58	97.34 87	96.95 239	43.60 486	99.42 146	97.57 82	97.60 147	96.47 310

MonoMVSNet		90.69 269	89.78 266	93.45 289	91.78 396	84.97 364	96.51 379	94.44 427	90.56 166	85.96 315	90.97 396	78.61 278	96.27 376	95.35 142	83.79 349	99.11 135

YYNet1		79.64 428	77.04 434	87.43 424	87.80 453	79.98 426	96.23 392	94.44 427	73.83 468	51.83 501	87.53 448	67.96 385	92.07 474	66.00 470	67.75 457	90.23 429

MDA-MVSNet_test_wron		79.65 427	77.05 433	87.45 423	87.79 454	80.13 425	96.25 391	94.44 427	73.87 467	51.80 502	87.47 452	68.04 383	92.12 473	66.02 469	67.79 456	90.09 430

MIMVSNet		84.48 388	81.83 400	92.42 315	91.73 398	87.36 295	85.52 487	94.42 431	81.40 415	81.91 371	87.58 447	51.92 467	92.81 462	73.84 429	88.15 316	97.08 287

MVP-Stereo		86.61 354	85.83 348	88.93 409	88.70 440	83.85 379	96.07 399	94.41 432	82.15 408	75.64 438	91.96 371	67.65 387	96.45 359	77.20 402	98.72 111	86.51 474
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MSDG		88.29 327	86.37 340	94.04 271	96.90 179	86.15 333	96.52 378	94.36 433	77.89 443	79.22 408	96.95 239	69.72 367	99.59 127	73.20 435	92.58 262	96.37 314

ACMH+	83.78 15	84.21 392	82.56 398	89.15 404	93.73 352	79.16 434	96.43 382	94.28 434	81.09 420	74.00 446	94.03 322	54.58 459	97.67 297	76.10 411	78.81 380	90.63 422

Patchmatch-test		86.25 361	84.06 379	92.82 303	94.42 318	82.88 393	82.88 502	94.23 435	71.58 472	79.39 405	90.62 409	89.00 75	96.42 360	63.03 479	91.37 297	99.16 128

CR-MVSNet		88.83 314	87.38 325	93.16 295	93.47 359	86.24 323	84.97 492	94.20 436	88.92 238	90.76 252	86.88 458	84.43 174	94.82 436	70.64 449	92.17 276	98.41 218

Patchmtry		83.61 401	81.64 401	89.50 395	93.36 363	82.84 394	84.10 495	94.20 436	69.47 483	79.57 402	86.88 458	84.43 174	94.78 437	68.48 461	74.30 412	90.88 411

EG-PatchMatch MVS		79.92 423	77.59 430	86.90 429	87.06 460	77.90 448	96.20 395	94.06 438	74.61 464	66.53 484	88.76 440	40.40 492	96.20 378	67.02 466	83.66 350	86.61 472

KD-MVS_self_test		77.47 442	75.88 439	82.24 461	81.59 488	68.93 488	92.83 453	94.02 439	77.03 445	73.14 453	83.39 477	55.44 454	90.42 483	67.95 462	57.53 486	87.38 465

K. test v3		81.04 419	79.77 421	84.83 448	87.41 456	70.23 484	95.60 414	93.93 440	83.70 377	67.51 480	89.35 437	55.76 450	93.58 454	76.67 407	68.03 454	90.67 421

FE-MVSNET2		78.42 437	75.71 440	86.55 432	78.55 498	81.99 405	95.40 415	93.86 441	81.11 418	66.27 485	81.89 484	49.29 479	91.80 476	72.03 444	63.02 469	85.86 478

RPSCF		85.33 376	85.55 353	84.67 450	94.63 311	62.28 497	93.73 439	93.76 442	74.38 466	85.23 323	97.06 232	64.09 416	98.31 214	80.98 374	86.08 330	93.41 338

MVS-HIRNet		79.01 430	75.13 444	90.66 362	93.82 350	81.69 408	85.16 489	93.75 443	54.54 502	74.17 445	59.15 521	57.46 444	96.58 349	63.74 476	94.38 223	93.72 335

pmmvs5		85.87 366	84.40 376	90.30 374	88.53 442	84.23 372	98.60 213	93.71 444	81.53 414	80.29 392	92.02 367	64.51 415	95.52 417	82.04 368	78.34 382	91.15 404

pmmvs6		79.90 424	77.31 432	87.67 419	84.17 474	78.13 445	95.86 407	93.68 445	67.94 487	72.67 458	89.62 433	50.98 472	95.75 405	74.80 421	66.04 462	89.14 448

OurMVSNet-221017-0		84.13 395	83.59 384	85.77 442	87.81 452	70.24 483	94.89 422	93.65 446	86.08 330	76.53 429	93.28 345	61.41 431	96.14 383	80.95 375	77.69 390	90.93 409

PatchmatchNet2					0.00 565	79.25 432	96.11 397	93.62 447	70.56 476
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
Anonymous20240521		78.63 434	76.90 435	83.82 454	82.82 484	72.86 474	95.72 412	93.57 448	73.55 470	72.17 460	84.79 474	49.69 477	92.51 467	65.29 473	74.50 408	86.09 477

DP-MVS		88.75 318	86.56 338	95.34 191	98.92 89	87.45 292	97.64 331	93.52 449	70.55 477	81.49 379	97.25 211	74.43 323	99.88 72	71.14 448	94.09 229	98.67 196

ITE_SJBPF				87.93 416	92.26 383	76.44 457		93.47 450	87.67 293	79.95 397	95.49 302	56.50 448	97.38 318	75.24 416	82.33 361	89.98 436

USDC		84.74 382	82.93 388	90.16 376	91.73 398	83.54 383	95.00 421	93.30 451	88.77 245	73.19 452	93.30 344	53.62 463	97.65 300	75.88 413	81.54 364	89.30 445

dtuonly		89.80 294	89.16 284	91.70 339	90.49 414	81.48 410	96.58 376	93.12 452	87.21 302	88.72 289	96.87 250	72.09 349	97.59 305	83.52 346	93.84 234	96.03 319

ADS-MVSNet2		87.62 339	86.88 334	89.86 384	96.21 211	79.14 435	87.15 484	92.99 453	83.01 388	89.91 273	87.27 453	78.87 269	92.80 463	74.20 425	92.27 272	97.64 264

Anonymous20231206		80.76 420	79.42 423	84.79 449	84.78 472	72.98 472	96.53 377	92.97 454	79.56 431	74.33 443	88.83 439	61.27 432	92.15 471	60.59 485	75.92 397	89.24 447

MDA-MVSNet-bldmvs		77.82 441	74.75 447	87.03 426	88.33 444	78.52 441	96.34 385	92.85 455	75.57 459	48.87 504	87.89 445	57.32 445	92.49 468	60.79 484	64.80 466	90.08 431

test20.03		78.51 436	77.48 431	81.62 466	83.07 480	71.03 480	96.11 397	92.83 456	81.66 413	69.31 471	89.68 432	57.53 443	87.29 500	58.65 490	68.47 452	86.53 473

COLMAP_ROB	82.69 18	84.54 387	82.82 389	89.70 390	96.72 188	78.85 436	95.89 403	92.83 456	71.55 473	77.54 428	95.89 292	59.40 439	99.14 170	67.26 465	88.26 315	91.11 406
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvs2		85.10 379	85.45 355	84.02 453	89.85 422	65.63 493	98.49 232	92.59 458	90.45 170	85.43 322	93.32 342	43.94 484	96.59 348	90.81 242	84.19 343	89.85 438

SixPastTwentyTwo		82.63 409	81.58 402	85.79 441	88.12 447	71.01 481	95.17 419	92.54 459	84.33 366	72.93 457	92.08 365	60.41 436	95.61 416	74.47 422	74.15 415	90.75 417

FMVSNet5		82.29 410	80.54 410	87.52 421	93.79 351	84.01 376	93.73 439	92.47 460	76.92 446	74.27 444	86.15 468	63.69 421	89.24 492	69.07 457	74.79 406	89.29 446

usedtu_blend_shiyan5		82.04 412	78.78 425	91.80 330	82.91 481	88.24 257	94.33 429	92.37 461	66.55 492	78.60 416	86.54 463	66.93 395	95.77 403	83.97 338	56.84 489	91.38 390

new-patchmatchnet		74.80 455	72.40 456	81.99 465	78.36 499	72.20 477	94.44 427	92.36 462	77.06 444	63.47 490	79.98 494	51.04 471	88.85 493	60.53 486	54.35 497	84.92 488

new_pmnet		76.02 446	73.71 451	82.95 459	83.88 475	72.85 475	91.26 471	92.26 463	70.44 478	62.60 491	81.37 488	47.64 481	92.32 469	61.85 481	72.10 437	83.68 493

AllTest		84.97 381	83.12 387	90.52 367	96.82 182	78.84 437	95.89 403	92.17 464	77.96 441	75.94 434	95.50 300	55.48 452	99.18 164	71.15 446	87.14 319	93.55 336

TestCases				90.52 367	96.82 182	78.84 437		92.17 464	77.96 441	75.94 434	95.50 300	55.48 452	99.18 164	71.15 446	87.14 319	93.55 336

pmmvs-eth3d		78.71 433	76.16 438	86.38 433	80.25 494	81.19 417	94.17 434	92.13 466	77.97 440	66.90 483	82.31 482	55.76 450	92.56 466	73.63 432	62.31 474	85.38 483

MIMVSNet1		75.92 447	73.30 453	83.81 455	81.29 490	75.57 461	92.26 457	92.05 467	73.09 471	67.48 481	86.18 467	40.87 491	87.64 499	55.78 494	70.68 444	88.21 458

ambc				79.60 472	72.76 510	56.61 502	76.20 512	92.01 468		68.25 476	80.23 493	23.34 505	94.73 438	73.78 431	60.81 478	87.48 464

LF4IMVS		81.94 414	81.17 407	84.25 452	87.23 459	68.87 489	93.35 445	91.93 469	83.35 383	75.40 439	93.00 353	49.25 480	96.65 346	78.88 391	78.11 383	87.22 469

TransMVSNet (Re)		81.97 413	79.61 422	89.08 405	89.70 426	84.01 376	97.26 346	91.85 470	78.84 434	73.07 456	91.62 378	67.17 392	95.21 428	67.50 464	59.46 482	88.02 459

MVStest1		76.56 445	73.43 452	85.96 440	86.30 466	80.88 423	94.26 432	91.74 471	61.98 496	58.53 496	89.96 428	69.30 373	91.47 479	59.26 488	49.56 507	85.52 482

Baseline_NR-MVSNet		85.83 368	84.82 365	88.87 410	88.73 439	83.34 385	98.63 202	91.66 472	80.41 429	82.44 355	91.35 387	74.63 318	95.42 422	84.13 333	71.39 441	87.84 460

mmtdpeth		83.69 398	82.59 397	86.99 428	92.82 374	76.98 454	96.16 396	91.63 473	82.89 396	92.41 217	82.90 478	54.95 457	98.19 225	96.27 112	53.27 499	85.81 479

testgi		82.29 410	81.00 408	86.17 436	87.24 458	74.84 465	97.39 339	91.62 474	88.63 248	75.85 437	95.42 303	46.07 483	91.55 477	66.87 468	79.94 375	92.12 360

TDRefinement		78.01 439	75.31 442	86.10 437	70.06 513	73.84 468	93.59 442	91.58 475	74.51 465	73.08 455	91.04 393	49.63 478	97.12 326	74.88 419	59.47 481	87.33 467

OpenMVS_ROB	73.86 20	77.99 440	75.06 445	86.77 431	83.81 476	77.94 447	96.38 384	91.53 476	67.54 488	68.38 475	87.13 457	43.94 484	96.08 385	55.03 496	81.83 362	86.29 476

ttmdpeth		79.80 426	77.91 429	85.47 444	83.34 478	75.75 459	95.32 417	91.45 477	76.84 447	74.81 442	91.71 377	53.98 462	94.13 446	72.42 442	61.29 475	86.51 474

test_0402		78.81 432	76.33 437	86.26 435	91.18 406	78.44 442	95.88 405	91.34 478	68.55 484	70.51 466	89.91 429	52.65 466	94.99 430	47.14 509	79.78 376	85.34 485

MTMP							99.21 114	91.09 479

DeepMVS_CX				76.08 475	90.74 412	51.65 511		90.84 480	86.47 325	57.89 498	87.98 443	35.88 497	92.60 464	65.77 471	65.06 465	83.97 491

dtuonlycased		79.10 429	78.53 426	80.81 469	86.63 462	72.95 473	96.33 386	90.81 481	81.09 420	68.85 472	87.27 453	56.94 446	87.84 497	71.57 445	67.30 459	81.65 497

test_fmvs3		75.09 452	75.19 443	74.81 478	77.45 501	54.08 506	95.93 401	90.64 482	82.51 402	73.29 451	81.19 489	22.29 506	86.29 503	85.50 314	67.89 455	84.06 490

usedtu_dtu_shiyan2		69.89 461	65.80 466	82.15 463	69.90 514	68.09 490	93.09 447	90.63 483	58.33 497	61.56 493	79.31 497	28.96 503	89.43 490	57.76 492	52.68 502	88.92 453

tt0320		76.58 444	73.16 454	86.86 430	88.03 449	77.60 450	93.55 444	90.63 483	55.37 500	70.93 462	84.98 472	41.57 488	94.01 447	69.02 458	64.32 468	88.97 451

sc_t1		78.53 435	74.87 446	89.48 398	87.92 450	77.36 452	94.80 423	90.61 485	57.65 498	76.28 430	89.59 434	38.25 493	96.18 379	74.04 427	64.72 467	94.91 331

lessismore_v0				85.08 446	85.59 470	69.28 486		90.56 486		67.68 479	90.21 425	54.21 461	95.46 420	73.88 428	62.64 472	90.50 424

Gipuma		54.77 478	52.22 480	62.40 498	86.50 463	59.37 501	50.20 531	90.35 487	36.52 519	41.20 517	49.49 527	18.33 510	81.29 506	32.10 524	65.34 464	46.54 531
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
TinyColmap		80.42 422	77.94 428	87.85 417	92.09 387	78.58 440	93.74 438	89.94 488	74.99 462	69.77 468	91.78 374	46.09 482	97.58 307	65.17 474	77.89 384	87.38 465

test_method		70.10 460	68.66 463	74.41 480	86.30 466	55.84 504	94.47 425	89.82 489	35.18 520	66.15 486	84.75 475	30.54 499	77.96 515	70.40 452	60.33 479	89.44 444

FPMVS		61.57 466	60.32 468	65.34 492	60.14 529	42.44 523	91.02 474	89.72 490	44.15 510	42.63 513	80.93 490	19.02 508	80.59 511	42.50 515	72.76 429	73.00 510

test_f		71.94 458	70.82 459	75.30 477	72.77 509	53.28 507	91.62 464	89.66 491	75.44 461	64.47 489	78.31 500	20.48 507	89.56 489	78.63 394	66.02 463	83.05 496

LCM-MVSNet		60.07 471	56.37 473	71.18 484	54.81 533	48.67 514	82.17 505	89.48 492	37.95 517	49.13 503	69.12 513	13.75 517	81.76 505	59.28 487	51.63 503	83.10 495

mvs5depth		78.17 438	75.56 441	85.97 439	80.43 493	76.44 457	85.46 488	89.24 493	76.39 449	78.17 425	88.26 442	51.73 468	95.73 407	69.31 456	61.09 476	85.73 480

tt0320-xc		75.92 447	72.23 458	87.01 427	88.40 443	78.15 444	93.57 443	89.15 494	55.46 499	69.66 469	85.79 471	38.20 494	93.85 448	69.72 453	60.08 480	89.03 449

pmmvs3		72.86 457	69.76 462	82.17 462	73.86 506	74.19 467	94.20 433	89.01 495	64.23 495	67.72 478	80.91 492	41.48 489	88.65 495	62.40 480	54.02 498	83.68 493

LCM-MVSNet-Re		88.59 323	88.61 301	88.51 412	95.53 246	72.68 476	96.85 365	88.43 496	88.45 255	73.14 453	90.63 408	75.82 310	94.38 443	92.95 210	95.71 194	98.48 215

Patchmatch-RL test		81.90 415	80.13 418	87.23 425	80.71 491	70.12 485	84.07 496	88.19 497	83.16 386	70.57 464	82.18 483	87.18 111	92.59 465	82.28 365	62.78 471	98.98 149

FE-MVSNET		75.08 453	72.25 457	83.56 457	77.93 500	76.96 455	94.36 428	87.96 498	75.72 456	66.01 487	81.60 487	50.48 474	88.85 493	55.38 495	60.82 477	84.86 489

mvsany_test3		75.85 449	74.52 448	79.83 470	73.53 507	60.64 499	91.73 463	87.87 499	83.91 373	70.55 465	82.52 480	31.12 498	93.66 452	86.66 300	62.83 470	85.19 487

DSMNet-mixed		81.60 416	81.43 404	82.10 464	84.36 473	60.79 498	93.63 441	86.74 500	79.00 432	79.32 407	87.15 456	63.87 419	89.78 488	66.89 467	91.92 279	95.73 324

ArgMatch-Sym		75.37 450	74.07 449	79.27 473	86.10 468	64.15 495	92.14 458	85.97 501	78.66 437	71.15 461	91.00 394	29.88 501	86.45 502	73.44 433	58.34 484	87.22 469

PM-MVS		74.88 454	72.85 455	80.98 468	78.98 496	64.75 494	90.81 475	85.77 502	80.95 423	68.23 477	82.81 479	29.08 502	92.84 461	76.54 408	62.46 473	85.36 484

door								85.30 503

ArgMatch-SfM		75.24 451	73.75 450	79.70 471	85.92 469	63.67 496	91.51 467	85.16 504	79.74 430	70.70 463	90.27 419	30.46 500	87.73 498	72.95 437	57.08 487	87.70 463

APD_test1		68.93 462	66.98 464	74.77 479	80.62 492	53.15 508	87.97 482	85.01 505	53.76 503	59.26 495	87.52 449	25.19 504	89.95 485	56.20 493	67.33 458	81.19 498

door-mid								84.90 506

EGC-MVSNET		60.70 470	55.37 474	76.72 474	86.35 465	71.08 479	89.96 479	84.44 507	0.38 558	1.50 560	84.09 476	37.30 495	88.10 496	40.85 519	73.44 424	70.97 513

WB-MVS		66.44 463	66.29 465	66.89 490	74.84 503	44.93 519	93.00 448	84.09 508	71.15 474	55.82 499	81.63 486	63.79 420	80.31 512	21.85 528	50.47 505	75.43 506

SSC-MVS		65.42 464	65.20 467	66.06 491	73.96 505	43.83 520	92.08 459	83.54 509	69.77 481	54.73 500	80.92 491	63.30 422	79.92 513	20.48 530	48.02 508	74.44 508

dmvs_testset		77.17 443	78.99 424	71.71 483	87.25 457	38.55 527	91.44 468	81.76 510	85.77 337	69.49 470	95.94 291	69.71 368	84.37 504	52.71 500	76.82 394	92.21 356

PMMVS2		58.97 472	55.07 475	70.69 486	62.72 523	55.37 505	85.97 486	80.52 511	49.48 508	45.94 508	68.31 514	15.73 512	80.78 509	49.79 504	37.12 517	75.91 504

LoFTR		61.59 465	56.89 472	75.68 476	76.61 502	50.06 513	82.20 504	79.57 512	52.13 505	39.02 520	75.71 504	14.90 514	93.30 456	45.35 511	46.48 511	83.69 492

ANet_high		50.71 482	46.17 486	64.33 493	44.27 541	52.30 510	76.13 513	78.73 513	64.95 493	27.37 527	55.23 524	14.61 516	67.74 523	36.01 522	18.23 536	72.95 511

PMVS	41.42 23	45.67 485	42.50 487	55.17 504	34.28 555	32.37 532	66.24 518	78.71 514	30.72 522	22.04 533	59.59 520	4.59 542	77.85 516	27.49 525	58.84 483	55.29 523
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis1_rt		81.31 418	80.05 420	85.11 445	91.29 405	70.66 482	98.98 155	77.39 515	85.76 338	68.80 473	82.40 481	36.56 496	99.44 142	92.67 217	86.55 324	85.24 486

MatchFormer		56.78 474	51.80 481	71.74 482	73.47 508	45.39 516	81.84 506	76.12 516	40.41 513	35.13 522	69.22 512	12.67 521	92.15 471	35.57 523	41.74 512	77.67 502

tmp_tt		53.66 479	52.86 479	56.05 502	32.75 557	41.97 525	73.42 516	76.12 516	21.91 527	39.68 518	96.39 275	42.59 487	65.10 526	78.00 397	14.92 544	61.08 520

testf1		56.38 475	53.73 477	64.31 494	64.84 520	45.11 517	80.50 507	75.94 518	38.87 515	42.74 511	75.07 505	11.26 524	81.19 507	41.11 517	53.27 499	66.63 515

APD_test2		56.38 475	53.73 477	64.31 494	64.84 520	45.11 517	80.50 507	75.94 518	38.87 515	42.74 511	75.07 505	11.26 524	81.19 507	41.11 517	53.27 499	66.63 515

MASt3R-SfM		60.79 469	59.91 469	63.44 497	62.41 524	35.46 528	75.76 515	71.46 520	54.67 501	58.30 497	86.10 469	14.86 515	74.25 519	65.44 472	50.18 506	80.59 499

DenseAffine		61.07 468	57.33 471	72.29 481	78.74 497	56.29 503	83.24 499	69.15 521	53.26 504	47.82 506	79.48 496	13.61 518	80.66 510	51.15 503	39.51 514	79.92 500

MVE	44.00 22	41.70 487	37.64 494	53.90 505	49.46 536	43.37 521	65.09 519	66.66 522	26.19 525	25.77 530	48.53 528	3.58 545	63.35 527	26.15 527	27.28 527	54.97 524
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		41.02 488	40.93 490	41.29 508	61.97 525	33.83 529	84.00 497	65.17 523	27.17 523	27.56 526	46.72 531	17.63 511	60.41 529	19.32 531	18.82 533	29.61 535

EMVS		39.96 490	39.88 491	40.18 509	59.57 531	32.12 534	84.79 494	64.57 524	26.27 524	26.14 529	44.18 535	18.73 509	59.29 530	17.03 532	17.67 538	29.12 536

ELoFTR		47.00 484	42.41 488	60.77 500	51.54 535	32.77 531	63.82 520	61.24 525	39.04 514	29.94 524	67.31 516	4.83 541	75.52 518	39.39 520	24.54 530	74.03 509

test_vis3_rt		61.29 467	58.75 470	68.92 487	67.41 517	52.84 509	91.18 473	59.23 526	66.96 489	41.96 516	58.44 522	11.37 523	94.72 439	74.25 424	57.97 485	59.20 521

VLMVS_CLIP		40.95 489	42.04 489	37.71 511	32.13 558	14.08 558	54.07 529	58.90 527	13.80 532	44.01 510	74.81 507	9.85 528	48.39 531	49.70 505	41.06 513	50.67 527

RoMa-SfM		58.43 473	54.99 476	68.74 488	74.29 504	50.87 512	82.37 503	58.12 528	50.53 506	48.40 505	81.78 485	12.70 520	78.25 514	47.71 508	39.01 515	77.09 503

DKM		55.59 477	51.49 482	67.89 489	72.36 511	48.29 515	80.45 509	52.05 529	47.86 509	42.54 514	77.08 503	9.06 533	77.32 517	48.87 506	33.13 519	78.05 501

GLUNet-SfM		37.11 493	32.05 498	52.28 507	44.07 543	25.94 539	52.38 530	46.25 530	24.11 526	21.50 534	55.60 523	6.32 540	66.20 525	27.48 526	10.71 550	64.70 517

RoMa-HiRes		51.04 480	47.47 483	61.73 499	65.35 519	42.38 524	76.31 511	41.57 531	42.69 511	42.32 515	77.75 501	9.33 530	73.10 520	42.68 514	29.24 522	69.72 514

DKM-HiRes		50.92 481	46.71 484	63.56 496	66.42 518	42.72 522	76.47 510	41.46 532	42.47 512	39.40 519	73.35 509	7.13 539	72.77 521	44.18 512	29.50 521	75.19 507

PDCNetPlus		48.73 483	46.34 485	55.88 503	64.17 522	41.40 526	76.11 514	34.96 533	50.17 507	35.24 521	71.04 510	15.41 513	67.33 524	52.41 501	17.59 539	58.93 522

VLMVS		38.17 492	38.75 493	36.45 514	35.35 553	13.53 560	50.05 532	33.90 534	9.30 540	47.14 507	77.14 502	12.39 522	32.34 535	47.77 507	35.68 518	63.48 518

PMatch-SfM		44.26 486	39.30 492	59.12 501	52.80 534	33.36 530	66.34 517	29.85 535	36.60 518	30.58 523	70.53 511	2.50 557	68.49 522	42.14 516	22.39 532	75.51 505

ALIKED-LG		33.96 495	32.42 497	38.57 510	70.35 512	32.25 533	57.19 524	29.49 536	19.94 528	22.96 532	46.96 530	10.85 526	47.42 532	8.53 544	25.49 528	36.04 532

N_pmnet		70.19 459	69.87 461	71.12 485	88.24 445	30.63 537	95.85 408	28.70 537	70.18 479	68.73 474	86.55 461	64.04 418	93.81 449	53.12 498	73.46 423	88.94 452

ALIKED-NN		33.05 496	31.67 499	37.18 513	69.89 515	31.76 535	55.83 528	28.14 538	16.92 529	23.23 531	47.45 529	9.65 529	45.41 534	8.80 542	25.13 529	34.38 534

ALIKED-MNN		32.26 497	30.45 500	37.68 512	69.07 516	31.55 536	56.28 527	27.56 539	16.30 530	21.15 535	44.78 533	8.12 536	46.74 533	8.19 545	22.59 531	34.76 533

SP-DiffGlue		29.92 500	29.42 504	31.40 518	32.10 559	20.02 541	47.81 533	27.27 540	14.91 531	26.24 528	54.34 525	10.53 527	24.46 542	21.49 529	30.15 520	49.71 530

SP-SuperGlue		30.18 499	29.74 503	31.50 517	60.57 527	18.71 544	57.45 522	26.07 541	13.70 533	20.25 536	39.95 539	9.22 532	25.03 541	11.85 537	28.64 525	50.78 526

SP-LightGlue		30.23 498	29.76 502	31.66 515	60.90 526	18.79 543	57.25 523	25.88 542	13.65 534	20.11 537	39.95 539	9.29 531	25.08 540	11.83 538	28.96 523	51.11 525

SP-MNN		29.29 502	28.62 506	31.29 519	59.13 532	18.03 548	56.77 526	25.19 543	11.83 536	18.01 541	39.35 542	8.35 535	25.39 538	10.99 541	27.91 526	50.47 528

XFeat-MNN		22.62 503	22.31 508	23.56 521	28.01 560	15.00 556	39.69 536	25.09 544	11.81 537	17.88 542	39.92 541	7.77 537	29.38 536	13.26 535	17.33 542	26.31 538

SP-NN		29.64 501	29.14 505	31.16 520	59.77 530	18.23 545	56.90 525	24.71 545	12.64 535	18.99 538	40.64 538	8.48 534	25.23 539	11.37 539	28.74 524	50.01 529

XFeat-NN		22.06 505	22.11 509	21.91 522	27.57 561	14.27 557	38.62 537	22.62 546	11.16 538	18.84 539	41.23 537	7.46 538	26.91 537	13.19 536	18.30 535	24.56 539

PMatch-Up-SfM		39.29 491	34.48 496	53.73 506	46.70 539	28.02 538	58.71 521	21.05 547	31.53 521	27.94 525	66.24 517	1.99 560	61.38 528	38.41 521	17.72 537	71.80 512

SIFT-NN		18.10 507	18.53 511	16.83 523	48.67 538	18.97 542	33.34 538	14.35 548	7.78 541	10.98 545	25.86 544	3.78 543	19.51 544	3.23 546	18.78 534	12.02 542

SIFT-MNN		17.20 508	17.47 512	16.41 525	45.38 540	18.16 546	31.28 540	14.20 549	7.60 542	9.54 546	25.18 545	3.39 546	19.18 545	3.18 547	17.44 540	11.88 543

SIFT-NN-NCMNet		16.94 509	17.19 513	16.19 526	43.53 544	18.04 547	31.30 539	14.18 550	7.55 544	9.51 547	24.88 546	3.32 547	18.84 546	3.08 548	17.35 541	11.70 545

SIFT-NN-UMatch		15.49 514	15.62 517	15.11 530	38.08 550	15.93 553	29.97 541	13.04 551	7.57 543	7.22 551	24.84 548	3.26 548	18.03 549	3.02 549	13.56 545	11.37 546

SIFT-NCM-Cal		16.07 512	16.20 515	15.69 527	44.16 542	17.32 549	29.83 542	12.88 552	7.33 547	6.22 554	23.59 552	3.00 551	18.75 547	2.74 554	16.09 543	10.99 548

SIFT-NN-CMatch		15.72 513	15.77 516	15.60 528	39.99 548	16.99 551	28.08 543	12.85 553	7.52 545	9.34 548	24.86 547	3.24 549	18.08 548	2.99 550	13.01 547	11.71 544

SIFT-ConvMatch		15.12 515	15.10 518	15.19 529	42.19 545	17.16 550	26.33 546	12.02 554	7.39 546	7.26 550	24.08 549	2.92 552	17.97 550	2.85 552	10.90 549	10.43 550

SIFT-NN-PointCN		14.43 517	14.70 520	13.64 533	36.13 551	12.94 561	27.63 545	11.82 555	7.03 551	8.24 549	23.49 553	3.21 550	16.75 553	2.85 552	11.89 548	11.22 547

SIFT-UMatch		14.73 516	14.79 519	14.57 531	40.58 547	15.36 555	27.70 544	11.21 556	7.28 548	6.62 553	24.07 550	2.81 555	17.91 551	2.87 551	9.94 551	10.45 549

SIFT-CM-Cal		14.12 518	14.09 521	14.22 532	40.92 546	15.56 554	23.80 548	10.18 557	7.20 549	6.72 552	23.20 554	2.86 554	16.98 552	2.67 556	9.24 554	10.13 551

SIFT-PointCN		12.37 520	12.72 523	11.33 535	35.33 554	10.01 562	23.72 549	9.79 558	6.45 553	5.30 558	20.10 556	2.22 559	14.67 557	2.33 558	9.26 553	9.30 553

SIFT-UM-Cal		13.73 519	13.86 522	13.34 534	39.95 549	13.63 559	25.68 547	9.21 559	7.19 550	5.57 555	23.60 551	2.66 556	16.67 554	2.70 555	8.18 555	9.73 552

MVS_clip		35.38 494	36.65 495	31.56 516	48.77 537	16.48 552	41.99 534	8.97 560	9.90 539	45.60 509	78.84 498	13.61 518	15.85 555	44.08 513	38.09 516	62.37 519

SIFT-PCN-Cal		12.09 521	12.36 524	11.26 536	35.43 552	9.79 563	22.24 550	8.83 561	6.37 554	5.43 557	20.44 555	2.34 558	14.88 556	2.35 557	7.87 556	9.13 554

SIFT-NCMNet		10.41 523	10.63 527	9.76 537	33.41 556	9.03 564	18.23 551	5.49 562	6.29 555	4.60 559	17.58 557	1.84 561	12.74 558	2.03 559	6.21 557	7.52 555

wuyk23d		16.71 510	16.73 514	16.65 524	60.15 528	25.22 540	41.24 535	5.17 563	6.56 552	5.48 556	3.61 558	3.64 544	22.72 543	15.20 533	9.52 552	1.99 556

testmvs		18.81 506	23.05 507	6.10 540	4.48 563	2.29 566	97.78 315	3.00 564	3.27 556	18.60 540	62.71 518	1.53 562	2.49 560	14.26 534	1.80 558	13.50 541

test123		16.58 511	19.47 510	7.91 539	3.59 564	5.37 565	94.32 430	1.39 565	2.49 557	13.98 544	44.60 534	2.91 553	2.65 559	11.35 540	0.57 559	15.70 540

MVS_baseline		11.50 522	12.32 525	9.06 538	13.94 562	0.55 567	4.75 552	1.33 566	0.26 559	16.85 543	50.28 526	1.45 563	0.03 561	8.71 543	13.26 546	26.61 537

mmdepth		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

monomultidepth		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

test_blank		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

uanet_test		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

DCPMVS		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

pcd_1.5k_mvsjas		6.87 525	9.16 528	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	82.48 215	0.00 562	0.00 560	0.00 560	0.00 557

sosnet-low-res		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

sosnet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

uncertanet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

Regformer		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

n2								0.00 567

nn								0.00 567

ab-mvs-re		8.21 524	10.94 526	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	98.50 131	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

uanet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

PatchmatchNet1														52.97 499	73.44 424	88.99 450
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													93.74 450
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						79.74 429								67.75 463

PC_three_1452									94.60 52	99.41 11	99.12 63	95.50 7	99.96 34	99.84 2	99.92 3	99.97 8

eth-test2					0.00 565

eth-test					0.00 565

OPU-MVS				99.49 4	99.64 23	98.51 4	99.77 29				99.19 45	95.12 9	99.97 26	99.90 1	99.92 3	99.99 2

test_0728_THIRD									93.01 94	99.07 26	99.46 15	94.66 14	99.97 26	99.25 29	99.82 19	99.95 16

GSMVS																98.84 166

test_part2					99.54 42	95.42 24				98.13 64

sam_mvs1												88.39 84				98.84 166

sam_mvs												87.08 114

test_post1							90.74 477				41.37 536	85.38 156	96.36 363	83.16 349

test_post											46.00 532	87.37 105	97.11 327

patchmatchnet-post											84.86 473	88.73 80	96.81 340

gm-plane-assit					94.69 308	88.14 263			88.22 268		97.20 215		98.29 216	90.79 243

test9_res														98.60 51	99.87 9	99.90 23

agg_prior2														97.84 78	99.87 9	99.91 22

test_prior4						92.00 124	99.41 92

test_prior2							99.57 64		91.43 137	98.12 66	98.97 83	90.43 56		98.33 65	99.81 23

旧先验2							98.67 196		85.75 339	98.96 32			98.97 179	93.84 183

新几何2							98.26 270

原ACMM2							98.69 192

testdata2													99.88 72	84.16 332

segment_acmp												90.56 54

testdata1							97.89 307		92.43 109

plane_prior7					93.84 347	85.73 347

plane_prior6					93.92 344	86.02 339						72.92 341

plane_prior4											96.52 267

plane_prior3						85.91 341			93.65 82	86.99 306

plane_prior2							99.02 149		93.38 89

plane_prior1					93.90 346

plane_prior						86.07 337	99.14 131		93.81 78						86.26 327

HQP5-MVS						86.39 318

HQP-NCC					93.95 339		99.16 123		93.92 69	87.57 299

ACMP_Plane					93.95 339		99.16 123		93.92 69	87.57 299

BP-MVS														93.82 185

HQP4-MVS										87.57 299			97.77 283			92.72 342

HQP2-MVS												73.34 334

NP-MVS					93.94 342	86.22 325					96.67 264

MDTV_nov1_ep13_2view						91.17 148	91.38 469		87.45 298	93.08 195		86.67 126		87.02 287		98.95 155

ACMMP++_ref															82.64 359

ACMMP++															83.83 346

Test By Simon												83.62 183

High-resolution multi-view benchmark