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 47	96.69 47	96.72 101	98.58 100	91.00 157	99.14 132	99.45 1	93.86 75	95.15 149	98.73 112	88.48 84	99.76 110	97.23 90	99.56 56	99.40 106

thres100view900		93.34 190	92.15 213	96.90 89	97.62 132	94.84 44	99.06 146	99.36 2	87.96 278	90.47 261	96.78 258	83.29 192	98.75 192	84.11 335	90.69 304	97.12 284

tfpn200view9		93.43 184	92.27 205	96.90 89	97.68 129	94.84 44	99.18 120	99.36 2	88.45 256	90.79 251	96.90 247	83.31 190	98.75 192	84.11 335	90.69 304	97.12 284

thres600view7		93.18 196	92.00 216	96.75 97	97.62 132	94.92 39	99.07 143	99.36 2	87.96 278	90.47 261	96.78 258	83.29 192	98.71 197	82.93 354	90.47 308	96.61 303

thres400		93.39 186	92.27 205	96.73 99	97.68 129	94.84 44	99.18 120	99.36 2	88.45 256	90.79 251	96.90 247	83.31 190	98.75 192	84.11 335	90.69 304	96.61 303

thres200		93.69 170	92.59 196	96.97 84	97.76 125	94.74 50	99.35 102	99.36 2	89.23 222	91.21 247	96.97 239	83.42 189	98.77 188	85.08 318	90.96 302	97.39 275

MVS_111021_LR		95.78 90	95.94 76	95.28 200	98.19 111	87.69 276	98.80 174	99.26 7	93.39 89	95.04 151	98.69 119	84.09 179	99.76 110	96.96 96	99.06 87	98.38 223

sss		94.85 125	93.94 142	97.58 50	96.43 199	94.09 68	98.93 159	99.16 8	89.50 215	95.27 146	97.85 161	81.50 233	99.65 122	92.79 216	94.02 232	98.99 149

MM		97.76 13	97.39 23	98.86 6	98.30 105	96.83 8	99.81 21	99.13 9	97.66 3	98.29 61	98.96 89	85.84 147	99.90 63	99.72 3	98.80 106	99.85 35

MG-MVS		97.24 25	96.83 40	98.47 17	99.79 6	95.71 22	99.07 143	99.06 10	94.45 58	96.42 117	98.70 118	88.81 80	99.74 112	95.35 143	99.86 12	99.97 8

test2506		94.80 126	94.21 127	96.58 111	96.41 202	92.18 123	98.01 303	98.96 11	90.82 155	93.46 190	97.28 208	85.92 144	98.45 210	89.82 254	97.19 161	99.12 134

PVSNet	87.13 12	93.69 170	92.83 188	96.28 132	97.99 118	90.22 181	99.38 96	98.93 12	91.42 139	93.66 185	97.68 177	71.29 360	99.64 124	87.94 280	97.20 160	98.98 150

PGM-MVS		95.85 86	95.65 92	96.45 118	99.50 48	89.77 203	98.22 275	98.90 13	89.19 224	96.74 110	98.95 92	85.91 146	99.92 50	93.94 180	99.46 61	99.66 71

EPNet		96.82 41	96.68 48	97.25 69	98.65 98	93.10 95	99.48 77	98.76 14	96.54 23	97.84 77	98.22 150	87.49 103	99.66 118	95.35 143	97.78 145	99.00 147
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		95.97 78	95.11 108	98.54 15	97.62 132	96.65 11	99.44 86	98.74 15	92.25 119	95.21 147	98.46 142	86.56 131	99.46 142	95.00 155	92.69 256	99.50 96

HY-MVS	88.56 7	95.29 108	94.23 126	98.48 16	97.72 127	96.41 15	94.03 438	98.74 15	92.42 112	95.65 140	94.76 315	86.52 133	99.49 136	95.29 146	92.97 252	99.53 90

VNet		95.08 116	94.26 125	97.55 53	98.07 115	93.88 70	98.68 194	98.73 17	90.33 176	97.16 94	97.43 196	79.19 263	99.53 133	96.91 98	91.85 282	99.24 122

test_yl		95.27 109	94.60 118	97.28 67	98.53 101	92.98 100	99.05 147	98.70 18	86.76 317	94.65 161	97.74 172	87.78 97	99.44 143	95.57 137	92.61 257	99.44 103

DCV-MVSNet		95.27 109	94.60 118	97.28 67	98.53 101	92.98 100	99.05 147	98.70 18	86.76 317	94.65 161	97.74 172	87.78 97	99.44 143	95.57 137	92.61 257	99.44 103

PVSNet_0	83.28 16	87.31 343	85.16 359	93.74 284	94.78 305	84.59 369	98.91 163	98.69 20	89.81 199	78.59 420	93.23 347	61.95 430	99.34 158	94.75 161	55.72 497	97.30 279

ACMMP		94.67 133	94.30 124	95.79 165	99.25 65	88.13 265	98.41 247	98.67 21	90.38 175	91.43 240	98.72 114	82.22 223	99.95 38	93.83 185	95.76 193	99.29 118
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 48	96.77 44	96.39 123	99.27 63	89.71 205	99.65 53	98.62 22	92.28 118	98.62 46	99.07 71	86.74 123	99.79 105	97.83 80	98.82 103	99.66 71

SymmetryMVS		95.49 101	95.27 101	96.17 141	97.13 169	90.37 174	99.14 132	98.59 23	94.92 46	96.30 120	97.98 157	85.33 159	99.23 162	94.35 171	93.67 242	98.92 160

D2MVS		87.96 331	87.39 325	89.70 391	91.84 396	83.40 385	98.31 265	98.49 24	88.04 275	78.23 425	90.26 421	73.57 333	96.79 343	84.21 332	83.53 352	88.90 455

test_fmvsm_n_1920		97.08 33	97.55 16	95.67 171	97.94 120	89.61 209	99.93 1	98.48 25	97.08 13	99.08 26	99.13 61	88.17 89	99.93 47	99.11 38	99.06 87	97.47 272

fmvsm_s_conf0.5_n		96.19 69	96.49 53	95.30 199	97.37 149	89.16 223	99.86 10	98.47 26	95.68 35	98.87 35	99.15 56	82.44 220	99.92 50	99.14 36	97.43 156	96.83 295

HyFIR lowres test		93.68 172	93.29 170	94.87 223	97.57 138	88.04 267	98.18 279	98.47 26	87.57 295	91.24 245	95.05 311	85.49 152	97.46 314	93.22 206	92.82 253	99.10 137

testing3-2		95.17 112	94.78 115	96.33 129	97.35 150	92.35 118	99.85 13	98.43 28	90.60 164	92.84 206	97.00 237	90.89 46	98.89 182	95.95 126	90.12 310	97.76 258

fmvsm_s_conf0.5_n_a		95.97 78	96.19 64	95.31 196	96.51 196	89.01 232	99.81 21	98.39 29	95.46 40	99.19 25	99.16 52	81.44 237	99.91 58	98.83 46	96.97 166	97.01 291

UniMVSNet (Re)		89.50 302	88.32 310	93.03 297	92.21 386	90.96 158	98.90 165	98.39 29	89.13 230	83.22 340	92.03 367	81.69 230	96.34 370	86.79 294	72.53 432	91.81 370

CHOSEN 280x420		96.80 42	96.85 37	96.66 106	97.85 123	94.42 60	94.76 425	98.36 31	92.50 109	95.62 141	97.52 190	97.92 1	97.38 319	98.31 68	98.80 106	98.20 240

VPA-MVSNet		89.10 307	87.66 320	93.45 290	92.56 378	91.02 156	97.97 306	98.32 32	86.92 312	86.03 315	92.01 369	68.84 377	97.10 330	90.92 240	75.34 401	92.23 355

CHOSEN 1792x2688		94.35 143	93.82 150	95.95 158	97.40 146	88.74 248	98.41 247	98.27 33	92.18 121	91.43 240	96.40 274	78.88 268	99.81 99	93.59 190	97.81 142	99.30 117

patch_mono-2		97.10 32	97.97 10	94.49 245	99.21 69	83.73 381	99.62 61	98.25 34	95.28 42	99.38 15	98.91 97	92.28 34	99.94 41	99.61 11	99.22 79	99.78 46

FIs		90.70 269	89.87 266	93.18 295	92.29 383	91.12 150	98.17 281	98.25 34	89.11 231	83.44 337	94.82 314	82.26 222	96.17 382	87.76 281	82.76 358	92.25 353

UGNet		91.91 239	90.85 248	95.10 211	97.06 174	88.69 249	98.01 303	98.24 36	92.41 113	92.39 219	93.61 338	60.52 436	99.68 116	88.14 277	97.25 159	96.92 293
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		90.22 285	89.40 279	92.67 313	91.78 397	89.86 198	97.89 308	98.22 37	88.81 241	82.96 347	94.66 316	81.90 229	95.96 392	85.89 312	82.52 361	92.20 358

WR-MVS_H		86.53 357	85.49 355	89.66 393	91.04 409	83.31 387	97.53 336	98.20 38	84.95 354	79.64 401	90.90 399	78.01 287	95.33 426	76.29 411	72.81 429	90.35 427

MGCNet		97.81 11	97.51 17	98.74 11	98.97 81	96.57 13	99.91 3	98.17 39	97.45 6	98.76 40	98.97 84	86.69 126	99.96 34	99.72 3	98.92 97	99.69 65

MVS		93.92 159	92.28 204	98.83 8	95.69 238	96.82 9	96.22 394	98.17 39	84.89 355	84.34 331	98.61 126	79.32 261	99.83 93	93.88 183	99.43 66	99.86 34

PAPM		96.35 62	95.94 76	97.58 50	94.10 335	95.25 29	98.93 159	98.17 39	94.26 60	93.94 177	98.72 114	89.68 69	97.88 273	96.36 112	99.29 74	99.62 82

baseline2		94.04 153	93.80 151	94.74 231	93.07 372	90.25 178	98.12 286	98.16 42	89.86 195	86.53 313	96.95 240	95.56 6	98.05 257	91.44 235	94.53 222	95.93 322

UniMVSNet_NR-MVSNet		89.60 299	88.55 306	92.75 307	92.17 387	90.07 188	98.74 183	98.15 43	88.37 262	83.21 341	93.98 327	82.86 202	95.93 394	86.95 290	72.47 433	92.25 353

CSCG		94.87 124	94.71 116	95.36 188	99.54 42	86.49 315	99.34 103	98.15 43	82.71 398	90.15 268	99.25 33	89.48 71	99.86 83	94.97 157	98.82 103	99.72 59

test_fmvsmconf_n		96.78 44	96.84 38	96.61 108	95.99 227	90.25 178	99.90 4	98.13 45	96.68 21	98.42 55	98.92 96	85.34 158	99.88 73	99.12 37	99.08 84	99.70 62

MSLP-MVS++		97.50 20	97.45 21	97.63 48	99.65 22	93.21 91	99.70 42	98.13 45	94.61 52	97.78 80	99.46 15	89.85 66	99.81 99	97.97 74	99.91 6	99.88 29

aaatest				97.84 38	99.75 8	93.67 75	99.65 53	98.11 47	92.89 102	98.58 50	99.53 8		100.00 1	99.53 20	99.64 44	99.87 32

MED-MVS		98.04 9	98.10 4	97.86 37	99.75 8	93.67 75	99.65 53	98.11 47	94.03 66	98.58 50	99.49 12	93.98 18	100.00 1	99.53 20	99.75 29	99.90 23

h-mvs33		92.47 223	91.95 219	94.05 271	97.13 169	85.01 363	98.36 260	98.08 49	93.85 76	96.27 122	96.73 261	83.19 196	99.43 146	95.81 129	68.09 454	97.70 264

aaEdge-Enhanced		97.59 17	97.51 17	97.84 38	99.73 12	93.67 75	99.52 73	98.07 50	92.38 116	98.32 60	99.53 8	90.83 49	99.97 26	99.53 20	99.64 44	99.87 32

fmvsm_s_conf0.5_n_4		96.17 70	96.49 53	95.21 205	97.06 174	89.26 218	99.76 33	98.07 50	95.99 29	99.35 16	99.22 38	82.19 224	99.89 71	99.06 39	97.68 147	96.49 310

TestfortrainingZip				99.33 5	99.87 2	97.98 5	99.65 53	98.06 52	92.29 117	99.91 1	99.64 2	95.49 8	100.00 1		98.29 134	100.00 1

IB-MVS	89.43 6	92.12 232	90.83 251	95.98 157	95.40 254	90.78 162	99.81 21	98.06 52	91.23 146	85.63 320	93.66 337	90.63 53	98.78 187	91.22 236	71.85 439	98.36 229
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 16	97.72 14	97.41 58	97.51 142	92.78 107	99.85 13	98.05 54	96.78 18	99.60 8	99.23 36	90.42 58	99.92 50	99.55 16	98.50 125	99.55 88

PHI-MVS		96.65 52	96.46 56	97.21 70	99.34 56	91.77 132	99.70 42	98.05 54	86.48 325	98.05 70	99.20 42	89.33 72	99.96 34	98.38 63	99.62 50	99.90 23

fmvsm_l_conf0.5_n_a		97.70 15	97.80 13	97.42 57	97.59 136	92.91 104	99.86 10	98.04 56	96.70 20	99.58 9	99.26 31	90.90 45	99.94 41	99.57 13	98.66 116	99.40 106

PVSNet_BlendedMVS		93.36 189	93.20 172	93.84 279	98.77 95	91.61 139	99.47 79	98.04 56	91.44 137	94.21 169	92.63 361	83.50 185	99.87 77	97.41 85	83.37 354	90.05 435

PVSNet_Blended		95.94 81	95.66 90	96.75 97	98.77 95	91.61 139	99.88 6	98.04 56	93.64 84	94.21 169	97.76 168	83.50 185	99.87 77	97.41 85	97.75 146	98.79 175

EPMVS		92.59 220	91.59 228	95.59 179	97.22 159	90.03 192	91.78 463	98.04 56	90.42 174	91.66 234	90.65 408	86.49 135	97.46 314	81.78 372	96.31 180	99.28 119

CNVR-MVS		98.46 1	98.38 1	98.72 12	99.80 5	96.19 17	99.80 27	97.99 60	97.05 14	99.41 12	99.59 3	92.89 29	100.00 1	98.99 43	99.90 7	99.96 11

MCST-MVS		98.18 3	97.95 11	98.86 6	99.85 4	96.60 12	99.70 42	97.98 61	97.18 12	95.96 126	99.33 27	92.62 30	100.00 1	98.99 43	99.93 1	99.98 7

fmvsm_s_conf0.5_n_10		96.95 36	96.82 41	97.33 63	97.76 125	93.00 99	99.87 7	97.95 62	97.32 10	99.71 4	99.20 42	81.48 234	99.90 63	99.32 25	98.78 110	99.09 138

testing3		87.75 335	88.22 312	86.36 435	94.66 311	77.41 452	99.52 73	97.95 62	86.05 332	81.12 383	96.69 264	86.18 141	89.31 492	61.65 484	90.12 310	92.35 352

fmvsm_s_conf0.5_n_7		95.87 84	96.25 62	94.72 233	96.19 215	87.74 275	99.66 51	97.94 64	95.78 32	98.44 54	99.23 36	81.26 240	99.90 63	99.17 35	98.57 122	96.52 309

reproduce_monomvs		92.11 234	91.82 223	92.98 299	98.25 106	90.55 170	98.38 258	97.93 65	94.81 48	80.46 391	92.37 363	96.46 3	97.17 325	94.06 178	73.61 420	91.23 403

testing222		94.48 141	94.00 136	95.95 158	97.30 154	92.27 120	98.82 170	97.92 66	89.20 223	94.82 154	97.26 210	87.13 113	97.32 322	91.95 228	91.56 288	98.25 234

1314		93.44 182	91.98 217	97.84 38	95.24 261	94.38 61	96.22 394	97.92 66	90.18 184	82.28 361	97.71 176	77.63 289	99.80 101	91.94 229	98.67 115	99.34 114

NCCC		98.12 6	98.11 3	98.13 28	99.76 7	94.46 57	99.81 21	97.88 68	96.54 23	98.84 37	99.46 15	92.55 31	99.98 14	98.25 70	99.93 1	99.94 19

tfpnnormal		83.65 400	81.35 406	90.56 367	91.37 405	88.06 266	97.29 345	97.87 69	78.51 439	76.20 432	90.91 398	64.78 415	96.47 358	61.71 483	73.50 423	87.13 472

TestfortrainingZip a		97.38 22	97.10 27	98.24 23	99.75 8	94.82 47	99.65 53	97.86 70	94.03 66	99.04 29	99.49 12	90.76 52	99.99 9	95.87 128	97.45 155	99.90 23

ETVMVS		94.50 140	93.90 146	96.31 130	97.48 144	92.98 100	99.07 143	97.86 70	88.09 273	94.40 165	96.90 247	88.35 86	97.28 323	90.72 246	92.25 275	98.66 202

fmvsm_l_conf0.5_n_9		97.33 23	97.32 25	97.37 61	97.64 131	92.45 117	99.93 1	97.85 72	97.39 7	99.84 2	99.09 70	85.42 156	99.92 50	99.52 23	99.20 83	99.73 58

3Dnovator	87.35 11	93.17 198	91.77 225	97.37 61	95.41 253	93.07 96	98.82 170	97.85 72	91.53 134	82.56 354	97.58 186	71.97 352	99.82 96	91.01 239	99.23 78	99.22 125

UWE-MVS		93.18 196	93.40 165	92.50 315	96.56 192	83.55 383	98.09 292	97.84 74	89.50 215	91.72 232	96.23 280	91.08 41	96.70 345	86.28 305	93.33 248	97.26 281

FE-MVS		91.38 250	90.16 263	95.05 217	96.46 198	87.53 290	89.69 481	97.84 74	82.97 391	92.18 222	92.00 371	84.07 180	98.93 181	80.71 379	95.52 199	98.68 196

WR-MVS		88.54 325	87.22 330	92.52 314	91.93 394	89.50 210	98.56 223	97.84 74	86.99 307	81.87 375	93.81 332	74.25 329	95.92 396	85.29 316	74.43 411	92.12 361

DELS-MVS		97.12 30	96.60 50	98.68 13	98.03 117	96.57 13	99.84 15	97.84 74	96.36 28	95.20 148	98.24 149	88.17 89	99.83 93	96.11 121	99.60 54	99.64 77
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 34	96.94 31	97.44 54	97.78 124	92.77 108	99.83 16	97.83 78	97.58 4	99.25 20	99.20 42	82.71 210	99.92 50	99.64 8	98.61 118	99.64 77

fmvsm_s_conf0.5_n_3		96.58 55	96.55 51	96.66 106	97.23 158	92.59 114	99.81 21	97.82 79	97.35 8	99.42 11	99.16 52	80.27 247	99.93 47	99.26 28	98.60 120	97.45 273

EI-MVSNet-Vis-set		95.76 92	95.63 94	96.17 141	99.14 72	90.33 176	98.49 233	97.82 79	91.92 125	94.75 157	98.88 103	87.06 116	99.48 140	95.40 142	97.17 163	98.70 193

无先验							98.52 227	97.82 79	87.20 304				99.90 63	87.64 283		99.85 35

EPNet_dtu		92.28 228	92.15 213	92.70 311	97.29 155	84.84 366	98.64 201	97.82 79	92.91 101	93.02 198	97.02 236	85.48 154	95.70 412	72.25 444	94.89 214	97.55 271
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SDMVSNet		91.09 258	89.91 265	94.65 235	96.80 185	90.54 171	97.78 316	97.81 83	88.34 264	85.73 317	95.26 308	66.44 404	98.26 219	94.25 175	86.75 323	95.14 327

HFP-MVS		96.42 61	96.26 61	96.90 89	99.69 14	90.96 158	99.47 79	97.81 83	90.54 169	96.88 99	99.05 76	87.57 101	99.96 34	95.65 131	99.72 34	99.78 46

EI-MVSNet-UG-set		95.43 103	95.29 100	95.86 162	99.07 78	89.87 197	98.43 241	97.80 85	91.78 127	94.11 172	98.77 108	86.25 140	99.48 140	94.95 158	96.45 176	98.22 238

ACMMPR		96.28 66	96.14 73	96.73 99	99.68 15	90.47 173	99.47 79	97.80 85	90.54 169	96.83 104	99.03 78	86.51 134	99.95 38	95.65 131	99.72 34	99.75 54

UWE-MVS-28		90.99 263	91.93 220	88.15 415	95.12 273	77.87 450	97.18 354	97.79 87	88.72 247	88.69 291	96.52 268	86.54 132	90.75 482	84.64 326	92.16 279	95.83 324

UBG		95.73 96	95.41 96	96.69 103	96.97 178	93.23 90	99.13 137	97.79 87	91.28 143	94.38 167	96.78 258	92.37 33	98.56 203	96.17 117	93.84 235	98.26 233

MAR-MVS		94.43 142	94.09 133	95.45 182	99.10 76	87.47 292	98.39 256	97.79 87	88.37 262	94.02 175	99.17 51	78.64 278	99.91 58	92.48 219	98.85 102	98.96 152
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		94.65 135	94.17 131	96.09 147	97.22 159	90.65 169	98.93 159	97.78 90	90.19 183	95.02 152	96.47 272	87.80 96	98.41 212	91.72 233	92.45 266	99.21 126

DPM-MVS		97.86 10	97.25 26	99.68 1	98.25 106	99.10 1	99.76 33	97.78 90	96.61 22	98.15 64	99.53 8	93.62 19	100.00 1	91.79 231	99.80 26	99.94 19

API-MVS		94.78 127	94.18 130	96.59 110	99.21 69	90.06 191	98.80 174	97.78 90	83.59 380	93.85 180	99.21 41	83.79 182	99.97 26	92.37 222	99.00 91	99.74 55

新几何1				97.40 59	98.92 89	92.51 116		97.77 93	85.52 342	96.69 112	99.06 74	88.08 93	99.89 71	84.88 322	99.62 50	99.79 43

HPM-MVS++		97.72 14	97.59 15	98.14 27	99.53 46	94.76 49	99.19 117	97.75 94	95.66 36	98.21 63	99.29 30	91.10 40	99.99 9	97.68 81	99.87 9	99.68 67

GG-mvs-BLEND				96.98 83	96.53 194	94.81 48	87.20 484	97.74 95		93.91 178	96.40 274	96.56 2	96.94 336	95.08 151	98.95 96	99.20 127

gg-mvs-nofinetune		90.00 292	87.71 319	96.89 93	96.15 217	94.69 53	85.15 491	97.74 95	68.32 487	92.97 202	60.16 520	96.10 4	96.84 339	93.89 181	98.87 101	99.14 131

旧先验1					98.97 81	92.90 105		97.74 95			99.15 56	91.05 42			99.33 70	99.60 83

IU-MVS					99.63 24	95.38 27		97.73 98	95.54 38	99.54 10				99.69 7	99.81 23	99.99 2

SED-MVS		98.18 3	98.10 4	98.41 20	99.63 24	95.24 30	99.77 30	97.72 99	94.17 61	99.30 18	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 61	99.23 21	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 30		97.72 99	94.16 63	99.30 18	99.49 12	93.32 22	99.98 14

DPE-MVS		98.11 7	98.00 8	98.44 18	99.50 48	95.39 26	99.29 106	97.72 99	94.50 54	98.64 45	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 58	97.84 12	92.68 312	98.71 97	78.11 447	99.70 42	97.71 103	98.18 1	97.36 87	99.76 1	90.37 60	99.94 41	99.27 27	99.54 58	99.99 2

myMVS_eth3d28		95.74 95	95.34 98	96.92 88	97.41 145	93.58 81	99.28 109	97.70 104	90.97 150	93.91 178	97.25 212	90.59 54	98.75 192	96.85 100	94.14 229	98.44 217

fmvsm_l_conf0.5_n_3		97.12 30	96.89 35	97.79 45	97.39 147	93.84 72	99.87 7	97.70 104	97.34 9	99.39 14	99.20 42	82.86 202	99.94 41	99.21 33	99.07 86	99.58 87

test0726					99.66 18	95.20 35	99.77 30	97.70 104	93.95 68	99.35 16	99.54 4	93.18 25

MSP-MVS		97.77 12	98.18 2	96.53 115	99.54 42	90.14 184	99.41 93	97.70 104	95.46 40	98.60 47	99.19 46	95.71 5	99.49 136	98.15 72	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 44	96.64 49	97.20 71	96.03 226	93.20 92	99.82 20	97.68 110	95.20 43	99.61 7	99.11 68	84.52 172	99.90 63	99.04 40	98.77 111	98.50 214

testing11		95.33 107	94.98 113	96.37 125	97.20 161	92.31 119	99.29 106	97.68 110	90.59 165	94.43 163	97.20 216	90.79 51	98.60 201	95.25 147	92.38 269	98.18 242

DVP-MVS++		98.18 3	98.09 6	98.44 18	99.61 30	95.38 27	99.55 67	97.68 110	93.01 95	99.23 21	99.45 19	95.12 9	99.98 14	99.25 30	99.92 3	99.97 8

test_0728_SECOND				98.77 9	99.66 18	96.37 16	99.72 39	97.68 110					99.98 14	99.64 8	99.82 19	99.96 11

test11								97.68 110

fmvsm_s_conf0.1_n		95.56 100	95.68 89	95.20 207	94.35 322	89.10 225	99.50 75	97.67 115	94.76 51	98.68 44	99.03 78	81.13 241	99.86 83	98.63 51	97.36 158	96.63 302

testing91		94.88 122	94.44 121	96.21 136	97.19 163	91.90 129	99.23 114	97.66 116	89.91 194	93.66 185	97.05 235	90.21 63	98.50 204	93.52 192	91.53 293	98.25 234

testing99		94.88 122	94.45 120	96.17 141	97.20 161	91.91 128	99.20 116	97.66 116	89.95 193	93.68 184	97.06 233	90.28 62	98.50 204	93.52 192	91.54 290	98.12 249

TEST9					99.57 39	93.17 93	99.38 96	97.66 116	89.57 211	98.39 56	99.18 49	90.88 47	99.66 118

train_agg		97.20 28	97.08 28	97.57 52	99.57 39	93.17 93	99.38 96	97.66 116	90.18 184	98.39 56	99.18 49	90.94 43	99.66 118	98.58 55	99.85 13	99.88 29

region2R		96.30 65	96.17 69	96.70 102	99.70 13	90.31 177	99.46 83	97.66 116	90.55 168	97.07 95	99.07 71	86.85 120	99.97 26	95.43 141	99.74 31	99.81 40

SteuartSystems-ACMMP		97.25 24	97.34 24	97.01 78	97.38 148	91.46 142	99.75 36	97.66 116	94.14 65	98.13 65	99.26 31	92.16 35	99.66 118	97.91 76	99.64 44	99.90 23
Skip Steuart: Steuart Systems R&D Blog.
EPP-MVSNet		93.75 169	93.67 155	94.01 273	95.86 231	85.70 349	98.67 197	97.66 116	84.46 365	91.36 243	97.18 219	91.16 38	97.79 282	92.93 212	93.75 240	98.53 212

fmvsm_s_conf0.5_n_2		95.85 86	95.83 80	95.91 160	97.19 163	91.79 130	99.78 29	97.65 123	97.23 11	99.22 23	99.06 74	75.93 308	99.90 63	99.30 26	97.09 165	96.02 321

SMA-MVS		97.24 25	96.99 29	98.00 34	99.30 60	94.20 65	99.16 124	97.65 123	89.55 213	99.22 23	99.52 11	90.34 61	99.99 9	98.32 67	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 40		97.64 125	93.14 94	98.93 34	99.45 19	93.45 20

test_8					99.55 41	93.07 96	99.37 99	97.64 125	90.18 184	98.36 58	99.19 46	90.94 43	99.64 124

agg_prior					99.54 42	92.66 109		97.64 125		97.98 74			99.61 126

DeepC-MVS_fast	93.52 2	97.16 29	96.84 38	98.13 28	99.61 30	94.45 58	98.85 167	97.64 125	96.51 26	95.88 129	99.39 23	87.35 110	99.99 9	96.61 106	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 71	99.65 53	97.63 129	95.69 34

原ACMM1				96.18 139	99.03 79	90.08 187		97.63 129	88.98 234	97.00 97	98.97 84	88.14 92	99.71 114	88.23 276	99.62 50	98.76 182

test-260524					99.74 11	96.14 18		97.62 131		97.79 79		91.57 37	100.00 1	99.55 16	99.75 29

DU-MVS		88.83 315	87.51 323	92.79 305	91.46 403	90.07 188	98.71 187	97.62 131	88.87 240	83.21 341	93.68 335	74.63 319	95.93 394	86.95 290	72.47 433	92.36 349

ZD-MVS					99.67 16	93.28 89		97.61 133	87.78 287	97.41 85	99.16 52	90.15 64	99.56 129	98.35 65	99.70 39

CP-MVS		96.22 68	96.15 72	96.42 120	99.67 16	89.62 208	99.70 42	97.61 133	90.07 191	96.00 125	99.16 52	87.43 104	99.92 50	96.03 124	99.72 34	99.70 62

thisisatest0530		94.00 154	93.52 158	95.43 185	95.76 236	90.02 193	98.99 154	97.60 135	86.58 320	91.74 231	97.36 201	94.78 12	98.34 214	86.37 303	92.48 265	97.94 255

tttt0517		93.30 191	93.01 180	94.17 264	95.57 243	86.47 316	98.51 230	97.60 135	85.99 333	90.55 258	97.19 218	94.80 11	98.31 215	85.06 319	91.86 281	97.74 259

thisisatest0515		94.75 128	94.19 128	96.43 119	96.13 222	92.64 112	99.47 79	97.60 135	87.55 296	93.17 194	97.59 185	94.71 13	98.42 211	88.28 275	93.20 249	98.24 237

testdata				95.26 202	98.20 109	87.28 299		97.60 135	85.21 346	98.48 53	99.15 56	88.15 91	98.72 196	90.29 249	99.45 64	99.78 46

ACMMP_NAP		96.59 53	96.18 66	97.81 42	98.82 93	93.55 83	98.88 166	97.59 139	90.66 160	97.98 74	99.14 59	86.59 129	100.00 1	96.47 110	99.46 61	99.89 28

CVMVSNet		90.30 283	90.91 246	88.46 414	94.32 327	73.58 471	97.61 333	97.59 139	90.16 187	88.43 295	97.10 225	76.83 297	92.86 461	82.64 358	93.54 243	98.93 158

XVS		96.47 59	96.37 58	96.77 95	99.62 28	90.66 167	99.43 90	97.58 141	92.41 113	96.86 100	98.96 89	87.37 106	99.87 77	95.65 131	99.43 66	99.78 46

X-MVStestdata		90.69 270	88.66 301	96.77 95	99.62 28	90.66 167	99.43 90	97.58 141	92.41 113	96.86 100	29.59 544	87.37 106	99.87 77	95.65 131	99.43 66	99.78 46

test222					98.32 104	91.21 146	98.08 295	97.58 141	83.74 376	95.87 130	99.02 80	86.74 123			99.64 44	99.81 40

test_prior				97.01 78	99.58 36	91.77 132		97.57 144					99.49 136			99.79 43

CP-MVSNet		86.54 356	85.45 356	89.79 388	91.02 410	82.78 396	97.38 342	97.56 145	85.37 344	79.53 404	93.03 353	71.86 354	95.25 428	79.92 384	73.43 427	91.34 397

fmvsm_s_conf0.5_n_9		96.76 46	96.92 32	96.29 131	97.95 119	89.21 220	99.81 21	97.55 146	97.04 15	99.68 6	99.22 38	82.84 204	99.94 41	99.56 15	98.61 118	99.71 60

test12				97.83 41	99.33 59	94.45 58		97.55 146		97.56 81		88.60 83	99.50 135		99.71 38	99.55 88

PAPR		96.35 62	95.82 82	97.94 36	99.63 24	94.19 66	99.42 92	97.55 146	92.43 110	93.82 183	99.12 64	87.30 111	99.91 58	94.02 179	99.06 87	99.74 55

AdaColmap		93.82 167	93.06 177	96.10 146	99.88 1	89.07 227	98.33 262	97.55 146	86.81 315	90.39 263	98.65 121	75.09 318	99.98 14	93.32 199	97.53 152	99.26 121

TESTMET0.1,1		93.82 167	93.26 171	95.49 181	95.21 265	90.25 178	99.15 129	97.54 150	89.18 225	91.79 230	94.87 313	89.13 73	97.63 302	86.21 306	96.29 183	98.60 207

fmvsm_s_conf0.1_n_a		95.16 113	95.15 105	95.18 208	92.06 389	88.94 238	99.29 106	97.53 151	94.46 56	98.98 31	98.99 82	79.99 250	99.85 87	98.24 71	96.86 170	96.73 299

hse-mvs2		91.67 244	91.51 230	92.15 322	96.22 211	82.61 401	97.74 322	97.53 151	93.85 76	96.27 122	96.15 282	83.19 196	97.44 316	95.81 129	66.86 462	96.40 314

AUN-MVS		90.17 288	89.50 275	92.19 320	96.21 212	82.67 397	97.76 321	97.53 151	88.05 274	91.67 233	96.15 282	83.10 198	97.47 313	88.11 278	66.91 461	96.43 313

ZNCC-MVS		96.09 72	95.81 84	96.95 86	99.42 53	91.19 147	99.55 67	97.53 151	89.72 202	95.86 131	98.94 95	86.59 129	99.97 26	95.13 150	99.56 56	99.68 67

CANet		97.00 35	96.49 53	98.55 14	98.86 92	96.10 19	99.83 16	97.52 155	95.90 30	97.21 91	98.90 99	82.66 212	99.93 47	98.71 47	98.80 106	99.63 80

APDe-MVS		97.53 18	97.47 19	97.70 46	99.58 36	93.63 78	99.56 66	97.52 155	93.59 85	98.01 73	99.12 64	90.80 50	99.55 130	99.26 28	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			90.47 260		96.14 219	88.55 253	91.34 471	97.51 157	89.58 210	92.24 220	90.50 418	86.99 119	97.61 304	77.64 400	92.34 271

QAPM		91.41 249	89.49 276	97.17 73	95.66 240	93.42 87	98.60 214	97.51 157	80.92 425	81.39 382	97.41 197	72.89 344	99.87 77	82.33 364	98.68 114	98.21 239

PAPM_NR		95.43 103	95.05 110	96.57 113	99.42 53	90.14 184	98.58 220	97.51 157	90.65 162	92.44 217	98.90 99	87.77 99	99.90 63	90.88 241	99.32 71	99.68 67

TSAR-MVS + MP.		97.44 21	97.46 20	97.39 60	99.12 73	93.49 86	98.52 227	97.50 160	94.46 56	98.99 30	98.64 122	91.58 36	99.08 174	98.49 59	99.83 15	99.60 83
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 91	95.00 112	98.06 32	97.35 150	95.68 23	99.71 41	97.50 160	91.50 135	96.16 124	98.61 126	86.28 138	99.00 177	96.19 115	91.74 284	99.51 94

9.14			96.87 36		99.34 56		99.50 75	97.49 162	89.41 219	98.59 48	99.43 21	89.78 67	99.69 115	98.69 48	99.62 50

GST-MVS		95.97 78	95.66 90	96.90 89	99.49 51	91.22 145	99.45 85	97.48 163	89.69 204	95.89 128	98.72 114	86.37 137	99.95 38	94.62 167	99.22 79	99.52 91

DP-MVS Recon		95.85 86	95.15 105	97.95 35	99.87 2	94.38 61	99.60 62	97.48 163	86.58 320	94.42 164	99.13 61	87.36 109	99.98 14	93.64 189	98.33 131	99.48 98

FOURS1					99.50 48	88.94 238	99.55 67	97.47 165	91.32 142	98.12 67

DVP-MVS		98.07 8	98.00 8	98.29 21	99.66 18	95.20 35	99.72 39	97.47 165	93.95 68	99.07 27	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		94.60 136	94.43 122	95.09 212	99.66 18	86.85 308	99.44 86	97.47 165	83.22 385	94.34 168	98.96 89	82.50 214	99.55 130	94.81 160	99.50 59	98.88 163

BP-MVS1		96.59 53	96.36 59	97.29 65	95.05 285	94.72 51	99.44 86	97.45 168	92.71 105	96.41 118	98.50 132	94.11 17	98.50 204	95.61 136	97.97 139	98.66 202

SF-MVS		97.22 27	96.92 32	98.12 30	99.11 74	94.88 41	99.44 86	97.45 168	89.60 209	98.70 42	99.42 22	90.42 58	99.72 113	98.47 60	99.65 42	99.77 51

MTGPA								97.45 168

MTAPA		96.09 72	95.80 85	96.96 85	99.29 61	91.19 147	97.23 350	97.45 168	92.58 107	94.39 166	99.24 35	86.43 136	99.99 9	96.22 114	99.40 69	99.71 60

CDPH-MVS		96.56 57	96.18 66	97.70 46	99.59 34	93.92 69	99.13 137	97.44 172	89.02 233	97.90 76	99.22 38	88.90 79	99.49 136	94.63 166	99.79 27	99.68 67

APD-MVS		96.95 36	96.72 46	97.63 48	99.51 47	93.58 81	99.16 124	97.44 172	90.08 190	98.59 48	99.07 71	89.06 74	99.42 147	97.92 75	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		94.67 133	94.11 132	96.34 127	97.14 168	91.10 152	99.32 105	97.43 174	92.10 124	91.53 239	96.38 277	83.29 192	99.68 116	93.42 198	96.37 178	98.25 234

NR-MVSNet		87.74 338	86.00 347	92.96 301	91.46 403	90.68 166	96.65 376	97.42 175	88.02 276	73.42 451	93.68 335	77.31 291	95.83 402	84.26 331	71.82 440	92.36 349

MP-MVS		96.00 75	95.82 82	96.54 114	99.47 52	90.13 186	99.36 100	97.41 176	90.64 163	95.49 143	98.95 92	85.51 151	99.98 14	96.00 125	99.59 55	99.52 91
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
mPP-MVS		95.90 83	95.75 87	96.38 124	99.58 36	89.41 214	99.26 112	97.41 176	90.66 160	94.82 154	98.95 92	86.15 142	99.98 14	95.24 148	99.64 44	99.74 55

OpenMVS	85.28 14	90.75 268	88.84 296	96.48 116	93.58 357	93.51 85	98.80 174	97.41 176	82.59 399	78.62 415	97.49 192	68.00 385	99.82 96	84.52 329	98.55 124	96.11 318

fmvsm_s_conf0.5_n_5		96.46 60	96.23 63	97.15 74	96.42 200	92.80 106	99.83 16	97.39 179	94.50 54	98.71 41	99.13 61	82.52 213	99.90 63	99.24 32	98.38 129	98.74 184

reproduce-ours		96.66 49	96.80 42	96.22 134	98.95 85	89.03 230	98.62 207	97.38 180	93.42 87	96.80 108	99.36 24	88.92 77	99.80 101	98.51 57	99.26 76	99.82 37

our_new_method		96.66 49	96.80 42	96.22 134	98.95 85	89.03 230	98.62 207	97.38 180	93.42 87	96.80 108	99.36 24	88.92 77	99.80 101	98.51 57	99.26 76	99.82 37

tt0805		86.50 358	84.79 367	91.63 342	91.97 390	81.49 410	96.49 381	97.38 180	82.24 407	82.44 356	95.82 295	51.22 471	98.25 220	84.55 328	80.96 369	95.13 329

SD-MVS		97.51 19	97.40 22	97.81 42	99.01 80	93.79 74	99.33 104	97.38 180	93.73 80	98.83 38	99.02 80	90.87 48	99.88 73	98.69 48	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		89.16 304	87.76 317	93.35 292	97.19 163	84.75 368	90.58 479	97.36 184	81.99 410	84.56 327	89.31 439	83.98 181	98.17 229	74.85 421	90.00 312	97.12 284

PS-CasMVS		85.81 370	84.58 372	89.49 398	90.77 412	82.11 404	97.20 352	97.36 184	84.83 356	79.12 411	92.84 357	67.42 391	95.16 430	78.39 397	73.25 428	91.21 404

0.3-1-1-0.015		91.27 252	89.64 271	96.15 145	92.69 377	91.62 137	99.74 37	97.35 186	84.68 361	92.71 209	93.18 348	85.31 161	97.75 291	92.11 225	68.98 450	99.09 138

0.4-1-1-0.1		91.07 259	89.43 278	96.01 153	92.48 380	91.23 144	99.69 49	97.34 187	84.50 364	92.49 215	92.98 356	84.53 171	97.72 296	91.87 230	68.97 452	99.08 142

0.4-1-1-0.2		91.19 257	89.53 274	96.20 137	92.78 376	91.76 134	99.76 33	97.34 187	84.77 357	92.54 213	93.05 352	84.51 173	97.74 294	92.01 226	68.98 450	99.09 138

reproduce_model		96.57 56	96.75 45	96.02 151	98.93 88	88.46 256	98.56 223	97.34 187	93.18 93	96.96 98	99.35 26	88.69 82	99.80 101	98.53 56	99.21 82	99.79 43

SR-MVS		96.13 71	96.16 71	96.07 148	99.42 53	89.04 228	98.59 217	97.33 190	90.44 172	96.84 102	99.12 64	86.75 122	99.41 150	97.47 84	99.44 65	99.76 53

WB-MVSnew		88.69 321	88.34 309	89.77 389	94.30 333	85.99 341	98.14 283	97.31 191	87.15 305	87.85 298	96.07 286	69.91 365	95.52 418	72.83 440	91.47 294	87.80 463

PatchmatchNet		92.05 236	91.04 241	95.06 215	96.17 216	89.04 228	91.26 472	97.26 192	89.56 212	90.64 255	90.56 414	88.35 86	97.11 328	79.53 385	96.07 190	99.03 146
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
FA-MVS(test-final)		92.22 231	91.08 240	95.64 173	96.05 225	88.98 235	91.60 466	97.25 193	86.99 307	91.84 229	92.12 365	83.03 199	99.00 177	86.91 292	93.91 233	98.93 158

test-LLR		93.11 202	92.68 191	94.40 249	94.94 296	87.27 300	99.15 129	97.25 193	90.21 181	91.57 235	94.04 321	84.89 166	97.58 308	85.94 310	96.13 186	98.36 229

test-mter		93.27 194	92.89 186	94.40 249	94.94 296	87.27 300	99.15 129	97.25 193	88.95 236	91.57 235	94.04 321	88.03 94	97.58 308	85.94 310	96.13 186	98.36 229

PEN-MVS		85.21 379	83.93 382	89.07 407	89.89 422	81.31 416	97.09 357	97.24 196	84.45 366	78.66 414	92.68 360	68.44 380	94.87 435	75.98 413	70.92 444	91.04 408

nomal-1		93.28 193	92.96 183	94.27 256	96.12 223	87.08 305	98.16 282	97.23 197	88.41 260	88.79 289	94.03 323	87.66 100	97.86 276	93.72 188	92.50 264	97.86 257

ab-mvs		91.05 262	89.17 284	96.69 103	95.96 228	91.72 135	92.62 455	97.23 197	85.61 341	89.74 278	93.89 331	68.55 378	99.42 147	91.09 237	87.84 318	98.92 160

APD-MVS_3200maxsize		95.64 99	95.65 92	95.62 177	99.24 66	87.80 274	98.42 244	97.22 199	88.93 238	96.64 115	98.98 83	85.49 152	99.36 154	96.68 103	99.27 75	99.70 62

SR-MVS-dyc-post		95.75 93	95.86 79	95.41 187	99.22 67	87.26 302	98.40 251	97.21 200	89.63 206	96.67 113	98.97 84	86.73 125	99.36 154	96.62 104	99.31 72	99.60 83

RE-MVS-def			95.70 88		99.22 67	87.26 302	98.40 251	97.21 200	89.63 206	96.67 113	98.97 84	85.24 162		96.62 104	99.31 72	99.60 83

SCA		90.64 273	89.25 283	94.83 227	94.95 295	88.83 243	96.26 391	97.21 200	90.06 192	90.03 271	90.62 410	66.61 401	96.81 341	83.16 350	94.36 225	98.84 167

RPMNet		85.07 381	81.88 400	94.64 237	93.47 360	86.24 324	84.97 493	97.21 200	64.85 495	90.76 253	78.80 500	80.95 243	99.27 161	53.76 498	92.17 277	98.41 219

VPNet		88.30 327	86.57 338	93.49 288	91.95 392	91.35 143	98.18 279	97.20 204	88.61 250	84.52 329	94.89 312	62.21 429	96.76 344	89.34 262	72.26 436	92.36 349

KinetiMVS		93.07 204	91.98 217	96.34 127	94.84 302	91.78 131	98.73 186	97.18 205	91.25 144	94.01 176	97.09 229	71.02 361	98.86 183	86.77 296	96.89 169	98.37 226

TranMVSNet+NR-MVSNet		87.75 335	86.31 342	92.07 324	90.81 411	88.56 252	98.33 262	97.18 205	87.76 288	81.87 375	93.90 330	72.45 346	95.43 422	83.13 352	71.30 443	92.23 355

cdsmvs_eth3d_5k		22.52 505	30.03 502	0.00 542	0.00 566	0.00 569	0.00 554	97.17 207	0.00 561	0.00 562	98.77 108	74.35 326	0.00 563	0.00 561	0.00 561	0.00 558

tpm2		91.77 242	91.09 239	93.82 280	94.83 303	85.56 352	92.51 456	97.16 208	84.00 371	93.83 182	90.66 407	87.54 102	97.17 325	87.73 282	91.55 289	98.72 190

MP-MVS-pluss		95.80 89	95.30 99	97.29 65	98.95 85	92.66 109	98.59 217	97.14 209	88.95 236	93.12 195	99.25 33	85.62 148	99.94 41	96.56 108	99.48 60	99.28 119
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
PatchMatch-RL		91.47 247	90.54 257	94.26 258	98.20 109	86.36 321	96.94 362	97.14 209	87.75 289	88.98 287	95.75 296	71.80 355	99.40 151	80.92 377	97.39 157	97.02 290

Anonymous20240529		87.66 339	85.58 353	93.92 276	97.59 136	85.01 363	98.13 284	97.13 211	66.69 492	88.47 294	96.01 288	55.09 457	99.51 134	87.00 289	84.12 345	97.23 283

JIA-IIPM		85.97 366	84.85 365	89.33 401	93.23 367	73.68 470	85.05 492	97.13 211	69.62 483	91.56 237	68.03 516	88.03 94	96.96 334	77.89 399	93.12 250	97.34 276

PS-MVSNAJ		96.87 39	96.40 57	98.29 21	97.35 150	97.29 6	99.03 149	97.11 213	95.83 31	98.97 32	99.14 59	82.48 216	99.60 127	98.60 52	99.08 84	98.00 252

HPM-MVS_fast		94.89 120	94.62 117	95.70 169	99.11 74	88.44 257	99.14 132	97.11 213	85.82 337	95.69 138	98.47 140	83.46 187	99.32 159	93.16 207	99.63 49	99.35 112

DeepC-MVS	91.02 4	94.56 139	93.92 143	96.46 117	97.16 167	90.76 163	98.39 256	97.11 213	93.92 70	88.66 292	98.33 145	78.14 284	99.85 87	95.02 153	98.57 122	98.78 178
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
tpmrst		92.78 212	92.16 212	94.65 235	96.27 209	87.45 293	91.83 462	97.10 216	89.10 232	94.68 160	90.69 405	88.22 88	97.73 295	89.78 255	91.80 283	98.77 180

HPM-MVS		95.41 105	95.22 103	95.99 155	99.29 61	89.14 224	99.17 123	97.09 217	87.28 302	95.40 144	98.48 139	84.93 165	99.38 152	95.64 135	99.65 42	99.47 100
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
tpm cat1		88.89 311	87.27 328	93.76 283	95.79 234	85.32 357	90.76 477	97.09 217	76.14 452	85.72 319	88.59 442	82.92 201	98.04 259	76.96 404	91.43 295	97.90 256

dp		90.16 289	88.83 297	94.14 265	96.38 205	86.42 317	91.57 467	97.06 219	84.76 358	88.81 288	90.19 427	84.29 177	97.43 317	75.05 418	91.35 299	98.56 210

xiu_mvs_v2_base		96.66 49	96.17 69	98.11 31	97.11 172	96.96 7	99.01 152	97.04 220	95.51 39	98.86 36	99.11 68	82.19 224	99.36 154	98.59 54	98.14 136	98.00 252

3Dnovator+	87.72 8	93.43 184	91.84 222	98.17 26	95.73 237	95.08 38	98.92 162	97.04 220	91.42 139	81.48 381	97.60 184	74.60 321	99.79 105	90.84 242	98.97 93	99.64 77

sd_testset		89.23 303	88.05 316	92.74 308	96.80 185	85.33 356	95.85 409	97.03 222	88.34 264	85.73 317	95.26 308	61.12 434	97.76 290	85.61 314	86.75 323	95.14 327

CDS-MVSNet		93.47 180	93.04 179	94.76 229	94.75 307	89.45 212	98.82 170	97.03 222	87.91 280	90.97 248	96.48 271	89.06 74	96.36 364	89.50 258	92.81 255	98.49 215
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test0.0.03 1		88.96 309	88.61 302	90.03 383	91.09 408	84.43 371	98.97 157	97.02 224	90.21 181	80.29 393	96.31 279	84.89 166	91.93 476	72.98 437	85.70 334	93.73 335

114514_t		94.06 152	93.05 178	97.06 76	99.08 77	92.26 121	98.97 157	97.01 225	82.58 400	92.57 212	98.22 150	80.68 245	99.30 160	89.34 262	99.02 90	99.63 80

CostFormer		92.89 207	92.48 199	94.12 266	94.99 290	85.89 344	92.89 451	97.00 226	86.98 310	95.00 153	90.78 401	90.05 65	97.51 312	92.92 214	91.73 285	98.96 152

test_fmvsmvis_n_1920		95.47 102	95.40 97	95.70 169	94.33 326	90.22 181	99.70 42	96.98 227	96.80 17	92.75 207	98.89 101	82.46 219	99.92 50	98.36 64	98.33 131	96.97 292

fmvsm_l_mol_unc0.5_1		98.26 2	98.09 6	98.75 10	97.31 153	96.69 10	99.89 5	96.97 228	97.78 2	99.69 5	99.31 29	92.95 28	99.92 50	99.50 24	99.46 61	99.65 75

ET-MVSNet_ETH3D		92.56 221	91.45 231	95.88 161	96.39 204	94.13 67	99.46 83	96.97 228	92.18 121	66.94 483	98.29 148	94.65 15	94.28 445	94.34 173	83.82 349	99.24 122

UA-Net		93.30 191	92.62 195	95.34 192	96.27 209	88.53 255	95.88 406	96.97 228	90.90 151	95.37 145	97.07 232	82.38 221	99.10 173	83.91 341	94.86 216	98.38 223

TAMVS		92.62 218	92.09 215	94.20 263	94.10 335	87.68 277	98.41 247	96.97 228	87.53 297	89.74 278	96.04 287	84.77 170	96.49 357	88.97 270	92.31 272	98.42 218

kuosan		84.40 392	83.34 386	87.60 421	95.87 230	79.21 434	92.39 457	96.87 232	76.12 453	73.79 448	93.98 327	81.51 232	90.63 483	64.13 476	75.42 400	92.95 340

guyue		94.21 148	93.72 154	95.66 172	95.22 263	90.17 183	98.74 183	96.85 233	93.67 81	93.01 200	96.72 262	78.83 272	98.06 253	96.04 123	94.44 223	98.77 180

test_fmvsmconf0.1_n		95.94 81	95.79 86	96.40 122	92.42 382	89.92 195	99.79 28	96.85 233	96.53 25	97.22 90	98.67 120	82.71 210	99.84 89	98.92 45	98.98 92	99.43 105

dongtai		81.36 418	80.61 410	83.62 457	94.25 334	73.32 472	95.15 421	96.81 235	73.56 470	69.79 468	92.81 358	81.00 242	86.80 502	52.08 503	70.06 446	90.75 418

Vis-MVSNet		92.64 217	91.85 221	95.03 218	95.12 273	88.23 262	98.48 235	96.81 235	91.61 130	92.16 223	97.22 215	71.58 358	98.00 265	85.85 313	97.81 142	98.88 163
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PMMVS		93.62 176	93.90 146	92.79 305	96.79 187	81.40 413	98.85 167	96.81 235	91.25 144	96.82 106	98.15 154	77.02 296	98.13 234	93.15 209	96.30 181	98.83 170

ADS-MVSNet		88.99 308	87.30 327	94.07 268	96.21 212	87.56 289	87.15 485	96.78 238	83.01 389	89.91 274	87.27 454	78.87 270	97.01 333	74.20 426	92.27 273	97.64 265

BridgeMVS		96.83 40	96.51 52	97.81 42	97.60 135	95.15 37	98.40 251	96.77 239	93.00 97	98.69 43	96.19 281	89.75 68	98.76 191	98.45 61	99.72 34	99.51 94

MVSMamba_PlusPlus		95.73 96	95.15 105	97.44 54	97.28 157	94.35 63	98.26 271	96.75 240	83.09 388	97.84 77	95.97 289	89.59 70	98.48 209	97.86 77	99.73 33	99.49 97

WBMVS		91.35 251	90.49 258	93.94 275	96.97 178	93.40 88	99.27 111	96.71 241	87.40 300	83.10 346	91.76 377	92.38 32	96.23 378	88.95 271	77.89 385	92.17 359

Vis-MVSNet (Re-imp)		93.26 195	93.00 182	94.06 270	96.14 219	86.71 311	98.68 194	96.70 242	88.30 266	89.71 280	97.64 182	85.43 155	96.39 362	88.06 279	96.32 179	99.08 142

Anonymous20231211		84.72 384	82.65 396	90.91 355	97.71 128	84.55 370	97.28 346	96.67 243	66.88 491	79.18 410	90.87 400	58.47 442	96.60 348	82.61 359	74.20 415	91.59 381

Syy-MVS		84.10 397	84.53 373	82.83 461	95.14 271	65.71 493	97.68 326	96.66 244	86.52 323	82.63 351	96.84 255	68.15 382	89.89 487	45.62 511	91.54 290	92.87 341

myMVS_eth3d		88.68 323	89.07 289	87.50 423	95.14 271	79.74 430	97.68 326	96.66 244	86.52 323	82.63 351	96.84 255	85.22 163	89.89 487	69.43 456	91.54 290	92.87 341

SSC-MVS3.2		85.22 378	83.90 383	89.17 404	91.87 395	79.84 429	97.66 329	96.63 246	86.81 315	81.99 370	91.35 388	55.80 450	96.00 389	76.52 410	76.53 396	91.67 372

EIA-MVS		95.11 114	95.27 101	94.64 237	96.34 206	86.51 314	99.59 63	96.62 247	92.51 108	94.08 173	98.64 122	86.05 143	98.24 221	95.07 152	98.50 125	99.18 128

ETV-MVS		96.00 75	96.00 74	96.00 154	96.56 192	91.05 155	99.63 60	96.61 248	93.26 92	97.39 86	98.30 147	86.62 128	98.13 234	98.07 73	97.57 149	98.82 171

usedtu_dtu_shiyan1		89.12 305	87.56 321	93.78 281	89.74 425	93.60 79	98.70 190	96.60 249	87.85 282	83.43 338	91.56 382	76.34 304	95.92 396	82.75 355	81.08 366	91.82 368

FE-MVSNET3		89.12 305	87.56 321	93.78 281	89.74 425	93.60 79	98.70 190	96.60 249	87.85 282	83.43 338	91.56 382	76.34 304	95.92 396	82.75 355	81.08 366	91.82 368

LS3D		90.19 286	88.72 299	94.59 243	98.97 81	86.33 322	96.90 364	96.60 249	74.96 464	84.06 334	98.74 111	75.78 312	99.83 93	74.93 419	97.57 149	97.62 269

EI-MVSNet		89.87 294	89.38 280	91.36 347	94.32 327	85.87 345	97.61 333	96.59 252	85.10 348	85.51 321	97.10 225	81.30 239	96.56 351	83.85 343	83.03 356	91.64 374

MVSTER		92.71 214	92.32 202	93.86 278	97.29 155	92.95 103	99.01 152	96.59 252	90.09 189	85.51 321	94.00 326	94.61 16	96.56 351	90.77 245	83.03 356	92.08 363

cascas		90.93 265	89.33 281	95.76 166	95.69 238	93.03 98	98.99 154	96.59 252	80.49 427	86.79 312	94.45 318	65.23 414	98.60 201	93.52 192	92.18 276	95.66 326

TAPA-MVS	87.50 9	90.35 280	89.05 290	94.25 259	98.48 103	85.17 360	98.42 244	96.58 255	82.44 405	87.24 305	98.53 128	82.77 206	98.84 185	59.09 490	97.88 141	98.72 190
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
OMC-MVS		93.90 161	93.62 156	94.73 232	98.63 99	87.00 306	98.04 301	96.56 256	92.19 120	92.46 216	98.73 112	79.49 260	99.14 171	92.16 224	94.34 227	98.03 251

PLC	91.07 3	94.23 147	94.01 135	94.87 223	99.17 71	87.49 291	99.25 113	96.55 257	88.43 259	91.26 244	98.21 152	85.92 144	99.86 83	89.77 256	97.57 149	97.24 282
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TSAR-MVS + GP.		96.95 36	96.91 34	97.07 75	98.88 91	91.62 137	99.58 64	96.54 258	95.09 45	96.84 102	98.63 124	91.16 38	99.77 109	99.04 40	96.42 177	99.81 40

PRO-TEST		96.23 67	95.99 75	96.95 86	96.86 181	93.81 73	99.19 117	96.51 259	94.78 50	98.27 62	98.49 135	83.43 188	97.60 305	98.43 62	97.99 138	99.46 101

cl22		89.57 300	88.79 298	91.91 326	97.94 120	87.62 286	97.98 305	96.51 259	85.03 351	82.37 360	91.79 374	83.65 183	96.50 355	85.96 309	77.89 385	91.61 379

xiu_mvs_v1_base_debu		94.73 129	93.98 137	96.99 80	95.19 266	95.24 30	98.62 207	96.50 261	92.99 98	97.52 82	98.83 105	72.37 347	99.15 167	97.03 92	96.74 171	96.58 305

xiu_mvs_v1_base		94.73 129	93.98 137	96.99 80	95.19 266	95.24 30	98.62 207	96.50 261	92.99 98	97.52 82	98.83 105	72.37 347	99.15 167	97.03 92	96.74 171	96.58 305

xiu_mvs_v1_base_debi		94.73 129	93.98 137	96.99 80	95.19 266	95.24 30	98.62 207	96.50 261	92.99 98	97.52 82	98.83 105	72.37 347	99.15 167	97.03 92	96.74 171	96.58 305

lupinMVS		96.32 64	95.94 76	97.44 54	95.05 285	94.87 42	99.86 10	96.50 261	93.82 78	98.04 71	98.77 108	85.52 149	98.09 243	96.98 95	98.97 93	99.37 109

fmvsm_s_conf0.5_n_11		96.80 42	96.97 30	96.28 132	98.09 114	92.26 121	99.87 7	96.49 265	97.55 5	99.75 3	99.32 28	83.20 195	99.91 58	99.57 13	98.88 100	96.67 301

mvs_anonymous		92.50 222	91.65 227	95.06 215	96.60 191	89.64 207	97.06 358	96.44 266	86.64 319	84.14 332	93.93 329	82.49 215	96.17 382	91.47 234	96.08 189	99.35 112

GDP-MVS		96.05 74	95.63 94	97.31 64	95.37 257	94.65 54	99.36 100	96.42 267	92.14 123	97.07 95	98.53 128	93.33 21	98.50 204	91.76 232	96.66 174	98.78 178

VDDNet		90.08 291	88.54 307	94.69 234	94.41 320	87.68 277	98.21 277	96.40 268	76.21 451	93.33 193	97.75 169	54.93 459	98.77 188	94.71 164	90.96 302	97.61 270

NormalMVS		95.87 84	95.83 80	95.99 155	99.27 63	90.37 174	99.14 132	96.39 269	94.92 46	96.30 120	97.98 157	85.33 159	99.23 162	94.35 171	98.82 103	98.37 226

Elysia		90.62 274	88.95 292	95.64 173	93.08 370	91.94 126	97.65 330	96.39 269	84.72 359	90.59 256	95.95 290	62.22 427	98.23 222	83.69 344	96.23 184	96.74 297

StellarMVS		90.62 274	88.95 292	95.64 173	93.08 370	91.94 126	97.65 330	96.39 269	84.72 359	90.59 256	95.95 290	62.22 427	98.23 222	83.69 344	96.23 184	96.74 297

mvsmamba		94.27 146	93.91 145	95.35 191	96.42 200	88.61 250	97.77 318	96.38 272	91.17 147	94.05 174	95.27 307	78.41 281	97.96 267	97.36 87	98.40 128	99.48 98

HQP3-MVS								96.37 273							86.29 326

PatchT		85.44 376	83.19 387	92.22 318	93.13 369	83.00 389	83.80 499	96.37 273	70.62 476	90.55 258	79.63 496	84.81 168	94.87 435	58.18 492	91.59 287	98.79 175

HQP-MVS		91.50 246	91.23 236	92.29 317	93.95 340	86.39 319	99.16 124	96.37 273	93.92 70	87.57 300	96.67 265	73.34 335	97.77 284	93.82 186	86.29 326	92.72 343

UnsupCasMVSNet_eth		78.90 432	76.67 437	85.58 444	82.81 486	74.94 465	91.98 461	96.31 276	84.64 362	65.84 489	87.71 447	51.33 470	92.23 471	72.89 439	56.50 496	89.56 444

HQP_MVS		91.26 253	90.95 245	92.16 321	93.84 348	86.07 338	99.02 150	96.30 277	93.38 90	86.99 307	96.52 268	72.92 342	97.75 291	93.46 196	86.17 329	92.67 345

plane_prior5								96.30 277					97.75 291	93.46 196	86.17 329	92.67 345

jason		95.40 106	94.86 114	97.03 77	92.91 373	94.23 64	99.70 42	96.30 277	93.56 86	96.73 111	98.52 130	81.46 236	97.91 269	96.08 122	98.47 127	98.96 152
jason: jason.
CLD-MVS		91.06 261	90.71 253	92.10 323	94.05 339	86.10 335	99.55 67	96.29 280	94.16 63	84.70 326	97.17 220	69.62 370	97.82 278	94.74 162	86.08 331	92.39 348
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GA-MVS		90.10 290	88.69 300	94.33 253	92.44 381	87.97 270	99.08 142	96.26 281	89.65 205	86.92 309	93.11 351	68.09 383	96.96 334	82.54 360	90.15 309	98.05 250

DTE-MVSNet		84.14 395	82.80 391	88.14 416	88.95 438	79.87 428	96.81 367	96.24 282	83.50 381	77.60 428	92.52 362	67.89 387	94.24 446	72.64 441	69.05 449	90.32 428

LFMVS		92.23 230	90.84 249	96.42 120	98.24 108	91.08 154	98.24 274	96.22 283	83.39 383	94.74 158	98.31 146	61.12 434	98.85 184	94.45 169	92.82 253	99.32 115

LuminaMVS		93.16 199	92.30 203	95.76 166	92.26 384	92.64 112	97.60 335	96.21 284	90.30 178	93.06 197	95.59 298	76.00 307	97.89 271	94.93 159	94.70 217	96.76 296

balanced_ft_v1		94.96 119	94.35 123	96.78 94	97.54 139	92.05 124	98.03 302	96.20 285	90.90 151	96.83 104	95.51 300	76.75 298	98.77 188	98.68 50	98.70 113	99.52 91

baseline1		92.61 219	91.28 235	96.58 111	97.05 176	94.63 55	97.72 323	96.20 285	89.82 198	88.56 293	96.85 252	86.85 120	97.82 278	88.42 273	80.10 375	97.30 279

FMVSNet3		88.81 317	87.08 331	93.99 274	96.52 195	94.59 56	98.08 295	96.20 285	85.85 336	82.12 364	91.60 380	74.05 330	95.40 424	79.04 389	80.24 372	91.99 366

sasdasda		95.02 117	93.96 140	98.20 24	97.53 140	95.92 20	98.71 187	96.19 288	91.78 127	95.86 131	98.49 135	79.53 258	99.03 175	96.12 119	91.42 296	99.66 71

canonicalmvs		95.02 117	93.96 140	98.20 24	97.53 140	95.92 20	98.71 187	96.19 288	91.78 127	95.86 131	98.49 135	79.53 258	99.03 175	96.12 119	91.42 296	99.66 71

fmvsm_s_conf0.1_n_2		95.24 111	95.04 111	95.83 163	95.60 241	91.71 136	99.65 53	96.18 290	96.99 16	98.79 39	98.91 97	73.91 332	99.87 77	99.00 42	96.30 181	95.91 323

dmvs_re		88.69 321	88.06 315	90.59 364	93.83 350	78.68 440	95.75 412	96.18 290	87.99 277	84.48 330	96.32 278	67.52 389	96.94 336	84.98 321	85.49 335	96.14 317

MVSFormer		94.71 132	94.08 134	96.61 108	95.05 285	94.87 42	97.77 318	96.17 292	86.84 313	98.04 71	98.52 130	85.52 149	95.99 390	89.83 252	98.97 93	98.96 152

test_djsdf		88.26 329	87.73 318	89.84 386	88.05 449	82.21 403	97.77 318	96.17 292	86.84 313	82.41 359	91.95 373	72.07 351	95.99 390	89.83 252	84.50 341	91.32 398

MS-PatchMatch		86.75 351	85.92 348	89.22 402	91.97 390	82.47 402	96.91 363	96.14 294	83.74 376	77.73 427	93.53 341	58.19 443	97.37 321	76.75 407	98.35 130	87.84 461

CS-MVS		95.75 93	96.19 64	94.40 249	97.88 122	86.22 326	99.66 51	96.12 295	92.69 106	98.07 69	98.89 101	87.09 114	97.59 306	96.71 101	98.62 117	99.39 108

E3new		94.19 149	93.78 152	95.43 185	95.81 233	89.44 213	98.80 174	96.11 296	90.24 180	93.85 180	97.75 169	80.94 244	98.14 231	95.00 155	95.48 202	98.72 190

viewcassd2359sk11		93.95 158	93.48 161	95.36 188	95.48 249	89.25 219	98.74 183	96.10 297	90.10 188	93.48 189	97.55 188	80.05 249	98.14 231	94.66 165	95.16 207	98.69 194

MGCFI-Net		94.89 120	93.84 149	98.06 32	97.49 143	95.55 24	98.64 201	96.10 297	91.60 133	95.75 136	98.46 142	79.31 262	98.98 179	95.95 126	91.24 301	99.65 75

SPE-MVS-test		95.98 77	96.34 60	94.90 222	98.06 116	87.66 280	99.69 49	96.10 297	93.66 82	98.35 59	99.05 76	86.28 138	97.66 299	96.96 96	98.90 99	99.37 109

VDD-MVS		91.24 256	90.18 262	94.45 248	97.08 173	85.84 347	98.40 251	96.10 297	86.99 307	93.36 192	98.16 153	54.27 461	99.20 164	96.59 107	90.63 307	98.31 232

PCF-MVS	89.78 5	91.26 253	89.63 272	96.16 144	95.44 251	91.58 141	95.29 419	96.10 297	85.07 350	82.75 348	97.45 195	78.28 283	99.78 108	80.60 381	95.65 197	97.12 284
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
E2		93.62 176	93.07 175	95.26 202	95.00 289	88.99 234	98.63 203	96.09 302	89.84 196	93.02 198	97.36 201	78.88 268	98.11 238	94.23 176	94.60 219	98.67 197

E3		93.62 176	93.07 175	95.26 202	94.98 291	89.00 233	98.63 203	96.09 302	89.83 197	93.01 200	97.35 203	78.90 267	98.11 238	94.23 176	94.60 219	98.67 197

test_cas_vis1_n_1920		93.86 166	93.74 153	94.22 262	95.39 255	86.08 336	99.73 38	96.07 304	96.38 27	97.19 93	97.78 166	65.46 412	99.86 83	96.71 101	98.92 97	96.73 299

test_vis1_n_1920		93.08 203	93.42 163	92.04 325	96.31 207	79.36 432	99.83 16	96.06 305	96.72 19	98.53 52	98.10 155	58.57 441	99.91 58	97.86 77	98.79 109	96.85 294

MVS_Test		93.67 173	92.67 192	96.69 103	96.72 189	92.66 109	97.22 351	96.03 306	87.69 293	95.12 150	94.03 323	81.55 231	98.28 218	89.17 268	96.46 175	99.14 131

viewmanbaseed2359cas		93.90 161	93.34 167	95.56 180	95.39 255	89.72 204	98.58 220	96.00 307	90.32 177	93.58 187	97.78 166	78.71 276	98.07 250	94.43 170	95.29 204	98.88 163

E4		93.15 201	92.50 198	95.09 212	94.41 320	88.61 250	98.48 235	95.99 308	89.40 220	92.22 221	97.13 222	77.43 290	98.10 241	93.58 191	93.90 234	98.56 210

casdiffmvs_mvg		94.00 154	93.33 168	96.03 150	95.22 263	90.90 161	99.09 141	95.99 308	90.58 166	91.55 238	97.37 200	79.91 251	98.06 253	95.01 154	95.22 206	99.13 133
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		87.35 342	86.51 340	89.87 384	87.75 456	81.74 408	97.03 359	95.98 310	88.47 253	80.15 395	93.80 333	61.47 431	96.36 364	89.44 260	84.47 342	91.50 383

E5new		92.80 208	92.19 207	94.62 239	94.34 323	87.64 281	98.08 295	95.97 311	89.15 226	92.01 225	97.08 230	76.37 302	98.08 245	93.25 202	93.46 244	98.15 244

E6new		92.80 208	92.19 207	94.62 239	94.31 331	87.64 281	98.08 295	95.97 311	89.15 226	92.01 225	97.10 225	76.38 300	98.08 245	93.25 202	93.45 246	98.15 244

E6		92.80 208	92.19 207	94.62 239	94.31 331	87.64 281	98.08 295	95.97 311	89.15 226	92.01 225	97.10 225	76.38 300	98.08 245	93.25 202	93.45 246	98.15 244

E5		92.80 208	92.19 207	94.62 239	94.34 323	87.64 281	98.08 295	95.97 311	89.15 226	92.01 225	97.08 230	76.37 302	98.08 245	93.25 202	93.46 244	98.15 244

PS-MVSNAJss		89.54 301	89.05 290	91.00 353	88.77 439	84.36 372	97.39 340	95.97 311	88.47 253	81.88 373	93.80 333	82.48 216	96.50 355	89.34 262	83.34 355	92.15 360

F-COLMAP		92.07 235	91.75 226	93.02 298	98.16 112	82.89 393	98.79 179	95.97 311	86.54 322	87.92 297	97.80 164	78.69 277	99.65 122	85.97 308	95.93 192	96.53 308

miper_enhance_ethall		90.33 281	89.70 268	92.22 318	97.12 171	88.93 240	98.35 261	95.96 317	88.60 251	83.14 345	92.33 364	87.38 105	96.18 380	86.49 302	77.89 385	91.55 382

TR-MVS		90.77 267	89.44 277	94.76 229	96.31 207	88.02 268	97.92 307	95.96 317	85.52 342	88.22 296	97.23 214	66.80 398	98.09 243	84.58 327	92.38 269	98.17 243

CMPMVS	58.40 21	80.48 422	80.11 420	81.59 468	85.10 472	59.56 501	94.14 436	95.95 319	68.54 486	60.71 495	93.31 344	55.35 456	97.87 274	83.06 353	84.85 339	87.33 468
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
VortexMVS		90.18 287	89.28 282	92.89 303	95.58 242	90.94 160	97.82 313	95.94 320	90.90 151	82.11 368	91.48 385	78.75 275	96.08 386	91.99 227	78.97 379	91.65 373

test_fmvsmconf0.01_n		94.14 150	93.51 160	96.04 149	86.79 462	89.19 221	99.28 109	95.94 320	95.70 33	95.50 142	98.49 135	73.27 338	99.79 105	98.28 69	98.32 133	99.15 130

LPG-MVS_test		88.86 312	88.47 308	90.06 379	93.35 365	80.95 422	98.22 275	95.94 320	87.73 291	83.17 343	96.11 284	66.28 405	97.77 284	90.19 250	85.19 336	91.46 386

LGP-MVS_train				90.06 379	93.35 365	80.95 422		95.94 320	87.73 291	83.17 343	96.11 284	66.28 405	97.77 284	90.19 250	85.19 336	91.46 386

OPM-MVS		89.76 297	89.15 288	91.57 343	90.53 414	85.58 351	98.11 288	95.93 324	92.88 103	86.05 314	96.47 272	67.06 394	97.87 274	89.29 265	86.08 331	91.26 401
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Casviewmamba		93.63 175	93.20 172	94.94 220	95.12 273	87.64 281	98.76 181	95.92 325	90.44 172	92.12 224	97.90 160	79.15 264	98.16 230	93.89 181	95.52 199	99.00 147

viewdifsd2359ckpt13		93.45 181	92.86 187	95.21 205	95.45 250	88.91 242	98.59 217	95.92 325	89.39 221	92.67 211	97.33 205	78.02 286	98.03 260	93.27 201	95.12 209	98.69 194

XVG-OURS-SEG-HR		90.95 264	90.66 256	91.83 328	95.18 269	81.14 420	95.92 403	95.92 325	88.40 261	90.33 264	97.85 161	70.66 364	99.38 152	92.83 215	88.83 315	94.98 330

XVG-OURS		90.83 266	90.49 258	91.86 327	95.23 262	81.25 417	95.79 411	95.92 325	88.96 235	90.02 272	98.03 156	71.60 357	99.35 157	91.06 238	87.78 319	94.98 330

tpm		89.67 298	88.95 292	91.82 330	92.54 379	81.43 412	92.95 450	95.92 325	87.81 286	90.50 260	89.44 436	84.99 164	95.65 414	83.67 346	82.71 359	98.38 223

EC-MVSNet		95.09 115	95.17 104	94.84 226	95.42 252	88.17 263	99.48 77	95.92 325	91.47 136	97.34 88	98.36 144	82.77 206	97.41 318	97.24 89	98.58 121	98.94 157

ACMM	86.95 13	88.77 318	88.22 312	90.43 370	93.61 356	81.34 415	98.50 231	95.92 325	87.88 281	83.85 335	95.20 310	67.20 392	97.89 271	86.90 293	84.90 338	92.06 364
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline		93.91 160	93.30 169	95.72 168	95.10 282	90.07 188	97.48 337	95.91 332	91.03 148	93.54 188	97.68 177	79.58 255	98.02 262	94.27 174	95.14 208	99.08 142

mvs_tets		87.09 345	86.22 343	89.71 390	87.87 452	81.39 414	96.73 373	95.90 333	88.19 270	79.99 397	93.61 338	59.96 438	96.31 372	89.40 261	84.34 343	91.43 388

XXY-MVS		87.75 335	86.02 346	92.95 302	90.46 416	89.70 206	97.71 325	95.90 333	84.02 370	80.95 384	94.05 320	67.51 390	97.10 330	85.16 317	78.41 382	92.04 365

nrg030		90.23 284	88.87 295	94.32 254	91.53 402	93.54 84	98.79 179	95.89 335	88.12 272	84.55 328	94.61 317	78.80 273	96.88 338	92.35 223	75.21 402	92.53 347

CNLPA		93.64 174	92.74 190	96.36 126	98.96 84	90.01 194	99.19 117	95.89 335	86.22 328	89.40 284	98.85 104	80.66 246	99.84 89	88.57 272	96.92 168	99.24 122

KD-MVS_2432*1600		82.98 408	80.52 412	90.38 372	94.32 327	88.98 235	92.87 452	95.87 337	80.46 428	73.79 448	87.49 451	82.76 208	93.29 458	70.56 451	46.53 510	88.87 456

miper_refine_blended		82.98 408	80.52 412	90.38 372	94.32 327	88.98 235	92.87 452	95.87 337	80.46 428	73.79 448	87.49 451	82.76 208	93.29 458	70.56 451	46.53 510	88.87 456

AstraMVS		93.38 188	93.01 180	94.50 244	93.94 343	86.55 312	98.91 163	95.86 339	93.88 74	92.88 203	97.49 192	75.61 316	98.21 224	96.15 118	92.39 268	98.73 189

FMVSNet2		86.90 347	84.79 367	93.24 294	95.11 279	92.54 115	97.67 328	95.86 339	82.94 392	80.55 388	91.17 393	62.89 424	95.29 427	77.23 401	79.71 378	91.90 367

hybridcas		93.44 182	92.82 189	95.31 196	94.91 299	89.08 226	98.82 170	95.84 341	90.28 179	91.22 246	97.65 181	78.39 282	98.06 253	92.71 217	95.55 198	98.79 175

viewmacassd2359aftdt		93.16 199	92.44 200	95.31 196	94.34 323	89.19 221	98.40 251	95.84 341	89.62 208	92.87 205	97.31 206	76.07 306	98.00 265	92.93 212	94.58 221	98.75 183

casdiffmvs		93.98 156	93.43 162	95.61 178	95.07 284	89.86 198	98.80 174	95.84 341	90.98 149	92.74 208	97.66 179	79.71 253	98.10 241	94.72 163	95.37 203	98.87 166
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		94.12 151	93.87 148	94.86 225	95.26 260	87.86 272	98.60 214	95.82 344	90.70 158	95.67 139	97.72 175	79.72 252	98.13 234	96.37 111	94.99 212	98.60 207

viewdifsd2359ckpt07		92.71 214	92.19 207	94.28 255	94.96 294	86.26 323	98.29 269	95.80 345	88.71 248	90.81 250	97.34 204	76.57 299	98.19 226	93.16 207	94.05 231	98.39 222

UniMVSNet_ETH3D		85.65 375	83.79 384	91.21 348	90.41 417	80.75 425	95.36 417	95.78 346	78.76 437	81.83 378	94.33 319	49.86 477	96.66 346	84.30 330	83.52 353	96.22 316

Effi-MVS+		93.87 165	93.15 174	96.02 151	95.79 234	90.76 163	96.70 374	95.78 346	86.98 310	95.71 137	97.17 220	79.58 255	98.01 263	94.57 168	96.09 188	99.31 116

gbinet_0.2-2-1-0.02		83.16 407	80.42 416	91.39 346	83.70 478	87.60 287	98.62 207	95.77 348	75.83 454	79.33 407	87.92 445	64.07 418	95.34 425	81.87 371	56.67 494	91.25 402

RRT-MVS		93.39 186	92.64 193	95.64 173	96.11 224	88.75 247	97.40 339	95.77 348	89.46 217	92.70 210	95.42 304	72.98 341	98.81 186	96.91 98	96.97 166	99.37 109

EU-MVSNet		84.19 394	84.42 376	83.52 459	88.64 442	67.37 492	96.04 401	95.76 350	85.29 345	78.44 422	93.18 348	70.67 363	91.48 479	75.79 415	75.98 397	91.70 371

BH-w/o		92.32 226	91.79 224	93.91 277	96.85 182	86.18 332	99.11 140	95.74 351	88.13 271	84.81 325	97.00 237	77.26 292	97.91 269	89.16 269	98.03 137	97.64 265

icg_test_0407_2		91.56 245	90.90 247	93.54 287	94.61 313	86.22 326	95.72 413	95.72 352	88.78 242	89.76 276	96.93 243	77.24 293	95.65 414	86.73 297	92.59 259	98.74 184

IMVS_0407		91.79 241	90.98 243	94.24 261	94.61 313	86.22 326	96.45 382	95.72 352	88.78 242	89.76 276	96.93 243	77.24 293	97.77 284	86.73 297	92.59 259	98.74 184

IMVS_0404		89.79 296	88.57 305	93.47 289	94.61 313	86.22 326	94.45 427	95.72 352	88.78 242	81.88 373	96.93 243	65.39 413	95.47 420	86.73 297	92.59 259	98.74 184

IMVS_0403		91.93 238	91.13 238	94.34 252	94.61 313	86.22 326	96.70 374	95.72 352	88.78 242	90.00 273	96.93 243	78.07 285	98.07 250	86.73 297	92.59 259	98.74 184

anonymousdsp		86.69 352	85.75 351	89.53 395	86.46 465	82.94 390	96.39 384	95.71 356	83.97 372	79.63 402	90.70 404	68.85 376	95.94 393	86.01 307	84.02 346	89.72 441

hybrid		93.89 163	93.41 164	95.33 194	94.98 291	89.30 217	98.58 220	95.70 357	89.70 203	94.76 156	97.54 189	78.98 266	98.07 250	95.52 140	94.92 213	98.61 205

Fast-Effi-MVS+		91.72 243	90.79 252	94.49 245	95.89 229	87.40 295	99.54 72	95.70 357	85.01 353	89.28 286	95.68 297	77.75 288	97.57 311	83.22 349	95.06 211	98.51 213

IS-MVSNet		93.00 206	92.51 197	94.49 245	96.14 219	87.36 296	98.31 265	95.70 357	88.58 252	90.17 267	97.50 191	83.02 200	97.22 324	87.06 287	96.07 190	98.90 162

viewmambaseed2359dif		93.05 205	92.64 193	94.25 259	94.94 296	86.53 313	98.38 258	95.69 360	87.03 306	93.38 191	97.74 172	78.79 274	98.08 245	93.49 195	94.35 226	98.15 244

diffmvs_AUTHOR		94.30 145	93.92 143	95.45 182	94.77 306	89.92 195	98.55 226	95.68 361	91.33 141	95.83 134	97.64 182	79.58 255	98.05 257	96.19 115	95.66 196	98.37 226

diffmvs		94.59 137	94.19 128	95.81 164	95.54 246	90.69 165	98.70 190	95.68 361	91.61 130	95.96 126	97.81 163	80.11 248	98.06 253	96.52 109	95.76 193	98.67 197
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		91.84 240	90.69 254	95.28 200	94.50 318	89.32 216	98.31 265	95.67 363	87.82 285	90.22 266	96.63 267	74.27 327	97.94 268	86.37 303	92.43 267	98.59 209

v7n		84.42 391	82.75 394	89.43 400	88.15 447	81.86 407	96.75 371	95.67 363	80.53 426	78.38 423	89.43 437	69.89 366	96.35 369	73.83 431	72.13 437	90.07 433

ACMP	87.39 10	88.71 320	88.24 311	90.12 378	93.91 346	81.06 421	98.50 231	95.67 363	89.43 218	80.37 392	95.55 299	65.67 407	97.83 277	90.55 247	84.51 340	91.47 385
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
viewdifsd2359ckpt09		93.54 179	92.91 185	95.44 184	95.57 243	89.48 211	98.68 194	95.66 366	89.52 214	92.50 214	97.75 169	78.46 280	98.03 260	93.32 199	94.69 218	98.81 172

hybridnocas07		93.98 156	93.52 158	95.36 188	95.01 288	89.37 215	98.63 203	95.64 367	90.79 157	94.69 159	97.31 206	79.01 265	98.11 238	95.54 139	95.07 210	98.61 205

CL-MVSNet_self_test		79.89 426	78.34 428	84.54 452	81.56 490	75.01 464	96.88 365	95.62 368	81.10 420	75.86 437	85.81 471	68.49 379	90.26 485	63.21 479	56.51 495	88.35 458

V42		87.00 346	85.68 352	90.98 354	89.91 420	86.08 336	98.32 264	95.61 369	83.67 379	82.72 349	90.67 406	74.00 331	96.53 353	81.94 370	74.28 414	90.32 428

viewmamba		93.88 164	93.59 157	94.78 228	94.82 304	87.68 277	98.41 247	95.60 370	91.61 130	94.17 171	97.93 159	79.65 254	98.01 263	95.20 149	94.87 215	98.66 202

XVG-ACMP-BASELINE		85.86 368	84.95 363	88.57 412	89.90 421	77.12 454	94.30 432	95.60 370	87.40 300	82.12 364	92.99 355	53.42 465	97.66 299	85.02 320	83.83 347	90.92 411

dtuplus		92.78 212	92.35 201	94.07 268	94.70 308	85.91 342	98.47 238	95.59 372	87.50 298	92.88 203	97.66 179	77.24 293	98.12 237	93.01 210	94.15 228	98.20 240

Anonymous202405211		88.84 313	87.03 333	94.27 256	98.14 113	84.18 375	98.44 240	95.58 373	76.79 449	89.34 285	96.88 250	53.42 465	99.54 132	87.53 284	87.12 322	99.09 138

miper_ehance_all_eth		88.94 310	88.12 314	91.40 344	95.32 259	86.93 307	97.85 312	95.55 374	84.19 368	81.97 371	91.50 384	84.16 178	95.91 399	84.69 324	77.89 385	91.36 395

CANet_DTU		94.31 144	93.35 166	97.20 71	97.03 177	94.71 52	98.62 207	95.54 375	95.61 37	97.21 91	98.47 140	71.88 353	99.84 89	88.38 274	97.46 154	97.04 289

v2v482		87.27 344	85.76 350	91.78 336	89.59 428	87.58 288	98.56 223	95.54 375	84.53 363	82.51 355	91.78 375	73.11 339	96.47 358	82.07 367	74.14 417	91.30 399

wanda-best-256-512		83.28 403	80.44 414	91.78 336	82.91 482	88.24 258	98.43 241	95.51 377	75.76 455	78.60 417	86.54 464	66.95 395	95.71 410	82.44 362	56.84 490	91.38 391

FE-blended-shiyan7		83.27 404	80.44 414	91.78 336	82.91 482	88.24 258	98.43 241	95.51 377	75.76 455	78.60 417	86.54 464	66.93 396	95.71 410	82.44 362	56.84 490	91.38 391

blended_shiyan6		83.17 406	80.34 418	91.67 341	82.80 487	87.93 271	98.29 269	95.51 377	75.63 459	78.46 421	86.48 467	66.74 400	95.70 412	82.33 364	56.84 490	91.37 394

blend_shiyan4		86.02 364	84.08 379	91.83 328	83.24 480	88.24 258	98.42 244	95.51 377	75.55 461	79.43 405	86.84 461	84.51 173	95.77 404	83.97 339	69.26 447	91.48 384

BH-untuned		91.46 248	90.84 249	93.33 293	96.51 196	84.83 367	98.84 169	95.50 381	86.44 327	83.50 336	96.70 263	75.49 317	97.77 284	86.78 295	97.81 142	97.40 274

blended_shiyan8		83.22 405	80.40 417	91.71 339	82.77 488	88.01 269	98.25 273	95.49 382	75.64 458	78.68 413	86.55 462	66.76 399	95.75 406	82.50 361	56.93 489	91.36 395

SSM_0407		92.04 237	91.03 242	95.07 214	95.12 273	89.81 200	97.18 354	95.49 382	86.17 329	89.50 281	97.13 222	75.65 313	97.68 297	89.26 266	93.79 237	97.73 260

SSM_0404		92.33 225	91.33 233	95.33 194	95.35 258	90.54 171	97.45 338	95.49 382	86.17 329	90.26 265	97.13 222	75.65 313	97.82 278	89.26 266	95.26 205	97.63 268

v148		86.38 360	85.06 360	90.37 374	89.47 433	84.10 376	98.52 227	95.48 385	83.80 375	80.93 385	90.22 425	74.60 321	96.31 372	80.92 377	71.55 441	90.69 421

IterMVS-LS		88.34 326	87.44 324	91.04 352	94.10 335	85.85 346	98.10 289	95.48 385	85.12 347	82.03 369	91.21 392	81.35 238	95.63 416	83.86 342	75.73 399	91.63 375
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dcpmvs_2		95.67 98	96.18 66	94.12 266	98.82 93	84.22 374	97.37 343	95.45 387	90.70 158	95.77 135	98.63 124	90.47 56	98.68 198	99.20 34	99.22 79	99.45 102

v1144		86.83 349	85.31 358	91.40 344	89.75 424	87.21 304	98.31 265	95.45 387	83.22 385	82.70 350	90.78 401	73.36 334	96.36 364	79.49 386	74.69 408	90.63 423

v1192		86.32 361	84.71 369	91.17 349	89.53 431	86.40 318	98.13 284	95.44 389	82.52 402	82.42 358	90.62 410	71.58 358	96.33 371	77.23 401	74.88 405	90.79 415

v144192		86.40 359	84.89 364	90.91 355	89.48 432	85.59 350	98.21 277	95.43 390	82.45 404	82.62 353	90.58 413	72.79 345	96.36 364	78.45 396	74.04 418	90.79 415

Effi-MVS+-dtu		89.97 293	90.68 255	87.81 419	95.15 270	71.98 479	97.87 311	95.40 391	91.92 125	87.57 300	91.44 386	74.27 327	96.84 339	89.45 259	93.10 251	94.60 333

c3_l		88.19 330	87.23 329	91.06 351	94.97 293	86.17 333	97.72 323	95.38 392	83.43 382	81.68 379	91.37 387	82.81 205	95.72 409	84.04 338	73.70 419	91.29 400

eth_miper_zixun_eth		87.76 334	87.00 334	90.06 379	94.67 310	82.65 400	97.02 361	95.37 393	84.19 368	81.86 377	91.58 381	81.47 235	95.90 400	83.24 348	73.61 420	91.61 379

v8		86.11 363	84.45 374	91.10 350	89.99 419	86.85 308	97.24 349	95.36 394	81.99 410	79.89 399	89.86 431	74.53 323	96.39 362	78.83 393	72.32 435	90.05 435

v1921920		86.02 364	84.44 375	90.77 361	89.32 434	85.20 358	98.10 289	95.35 395	82.19 408	82.25 362	90.71 403	70.73 362	96.30 375	76.85 406	74.49 410	90.80 414

pmmvs4		87.58 341	86.17 345	91.80 331	89.58 429	88.92 241	97.25 348	95.28 396	82.54 401	80.49 389	93.17 350	75.62 315	96.05 388	82.75 355	78.90 380	90.42 426

viewdifsd2359ckpt11		90.42 278	89.65 269	92.73 310	93.71 355	82.67 397	98.09 292	95.27 397	89.80 200	90.10 270	97.40 198	69.43 372	98.18 228	92.46 220	80.61 371	97.34 276

viewmsd2359difaftdt		90.43 277	89.65 269	92.74 308	93.72 354	82.67 397	98.09 292	95.27 397	89.80 200	90.12 269	97.40 198	69.43 372	98.20 225	92.45 221	80.62 370	97.34 276

GBi-Net		86.67 353	84.96 361	91.80 331	95.11 279	88.81 244	96.77 368	95.25 399	82.94 392	82.12 364	90.25 422	62.89 424	94.97 432	79.04 389	80.24 372	91.62 376

test1		86.67 353	84.96 361	91.80 331	95.11 279	88.81 244	96.77 368	95.25 399	82.94 392	82.12 364	90.25 422	62.89 424	94.97 432	79.04 389	80.24 372	91.62 376

FMVSNet1		83.94 398	81.32 407	91.80 331	91.94 393	88.81 244	96.77 368	95.25 399	77.98 440	78.25 424	90.25 422	50.37 476	94.97 432	73.27 435	77.81 390	91.62 376

mvsany_test1		94.57 138	95.09 109	92.98 299	95.84 232	82.07 405	98.76 181	95.24 402	92.87 104	96.45 116	98.71 117	84.81 168	99.15 167	97.68 81	95.49 201	97.73 260

cl____		87.82 332	86.79 337	90.89 357	94.88 300	85.43 353	97.81 314	95.24 402	82.91 396	80.71 387	91.22 391	81.97 228	95.84 401	81.34 374	75.06 403	91.40 390

miper_lstm_enhance		86.90 347	86.20 344	89.00 408	94.53 317	81.19 418	96.74 372	95.24 402	82.33 406	80.15 395	90.51 417	81.99 226	94.68 441	80.71 379	73.58 422	91.12 406

UnsupCasMVSNet_bld		73.85 457	70.14 461	84.99 448	79.44 496	75.73 461	88.53 482	95.24 402	70.12 481	61.94 493	74.81 508	41.41 491	93.62 454	68.65 461	51.13 505	85.62 482

v1240		85.77 372	84.11 378	90.73 362	89.26 435	85.15 361	97.88 310	95.23 406	81.89 413	82.16 363	90.55 415	69.60 371	96.31 372	75.59 416	74.87 406	90.72 420

DIV-MVS_self_test		87.82 332	86.81 336	90.87 358	94.87 301	85.39 355	97.81 314	95.22 407	82.92 395	80.76 386	91.31 390	81.99 226	95.81 403	81.36 373	75.04 404	91.42 389

v10		85.73 373	84.01 381	90.87 358	90.03 418	86.73 310	97.20 352	95.22 407	81.25 418	79.85 400	89.75 432	73.30 337	96.28 376	76.87 405	72.64 431	89.61 443

mamba_0408		90.65 272	89.16 285	95.12 210	95.12 273	89.81 200	83.02 501	95.17 409	85.95 334	89.50 281	96.85 252	75.85 309	97.82 278	87.19 285	93.79 237	97.73 260

SSM_04072		90.31 282	89.16 285	93.74 284	95.12 273	89.81 200	83.02 501	95.17 409	85.95 334	89.50 281	96.85 252	75.85 309	93.69 452	87.19 285	93.79 237	97.73 260

SD_0403		86.82 350	87.08 331	86.04 439	93.55 358	69.09 488	94.11 437	95.02 411	87.84 284	80.48 390	95.86 294	73.05 340	91.04 481	72.53 442	91.26 300	97.99 254

test_fmvs1		92.35 224	92.94 184	90.57 365	97.19 163	75.43 463	99.55 67	94.97 412	95.20 43	96.82 106	97.57 187	59.59 439	99.84 89	97.30 88	98.29 134	96.46 312

BH-RMVSNet		91.25 255	89.99 264	95.03 218	96.75 188	88.55 253	98.65 199	94.95 413	87.74 290	87.74 299	97.80 164	68.27 381	98.14 231	80.53 382	97.49 153	98.41 219

GeoE		90.60 276	89.56 273	93.72 286	95.10 282	85.43 353	99.41 93	94.94 414	83.96 373	87.21 306	96.83 257	74.37 325	97.05 332	80.50 383	93.73 241	98.67 197

ACMH	83.09 17	84.60 386	82.61 397	90.57 365	93.18 368	82.94 390	96.27 389	94.92 415	81.01 423	72.61 460	93.61 338	56.54 448	97.79 282	74.31 424	81.07 368	90.99 409
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs1_n		91.07 259	91.41 232	90.06 379	94.10 335	74.31 467	99.18 120	94.84 416	94.81 48	96.37 119	97.46 194	50.86 474	99.82 96	97.14 91	97.90 140	96.04 319

test1111		92.12 232	91.19 237	94.94 220	96.15 217	87.36 296	98.12 286	94.84 416	90.85 154	90.97 248	97.26 210	65.60 410	98.37 213	89.74 257	97.14 164	99.07 145

ECVR-MVS		92.29 227	91.33 233	95.15 209	96.41 202	87.84 273	98.10 289	94.84 416	90.82 155	91.42 242	97.28 208	65.61 409	98.49 208	90.33 248	97.19 161	99.12 134

IterMVS		85.81 370	84.67 370	89.22 402	93.51 359	83.67 382	96.32 388	94.80 419	85.09 349	78.69 412	90.17 428	66.57 403	93.17 460	79.48 387	77.42 392	90.81 413
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
LTVRE_ROB	81.71 19	84.59 387	82.72 395	90.18 376	92.89 374	83.18 388	93.15 447	94.74 420	78.99 434	75.14 442	92.69 359	65.64 408	97.63 302	69.46 455	81.82 364	89.74 440
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		84.68 385	82.78 393	90.40 371	89.58 429	85.18 359	97.31 344	94.73 421	81.93 412	76.05 434	92.01 369	65.48 411	96.11 385	78.75 394	69.14 448	89.91 438

IterMVS-SCA-FT		85.73 373	84.64 371	89.00 408	93.46 362	82.90 392	96.27 389	94.70 422	85.02 352	78.62 415	90.35 419	66.61 401	93.33 456	79.38 388	77.36 393	90.76 417

1112_ss		92.71 214	91.55 229	96.20 137	95.56 245	91.12 150	98.48 235	94.69 423	88.29 267	86.89 310	98.50 132	87.02 117	98.66 199	84.75 323	89.77 313	98.81 172

Test_1112_low_res		92.27 229	90.97 244	96.18 139	95.53 247	91.10 152	98.47 238	94.66 424	88.28 268	86.83 311	93.50 342	87.00 118	98.65 200	84.69 324	89.74 314	98.80 174

Fast-Effi-MVS+-dtu		88.84 313	88.59 304	89.58 394	93.44 363	78.18 444	98.65 199	94.62 425	88.46 255	84.12 333	95.37 306	68.91 375	96.52 354	82.06 368	91.70 286	94.06 334

our_test_3		84.47 390	82.80 391	89.50 396	89.01 436	83.90 379	97.03 359	94.56 426	81.33 417	75.36 441	90.52 416	71.69 356	94.54 443	68.81 460	76.84 394	90.07 433

ppachtmachnet_test		83.63 401	81.57 404	89.80 387	89.01 436	85.09 362	97.13 356	94.50 427	78.84 435	76.14 433	91.00 395	69.78 367	94.61 442	63.40 478	74.36 412	89.71 442

test_vis1_n		90.40 279	90.27 261	90.79 360	91.55 401	76.48 457	99.12 139	94.44 428	94.31 59	97.34 88	96.95 240	43.60 487	99.42 147	97.57 83	97.60 148	96.47 311

MonoMVSNet		90.69 270	89.78 267	93.45 290	91.78 397	84.97 365	96.51 380	94.44 428	90.56 167	85.96 316	90.97 397	78.61 279	96.27 377	95.35 143	83.79 350	99.11 136

YYNet1		79.64 429	77.04 435	87.43 425	87.80 454	79.98 427	96.23 393	94.44 428	73.83 469	51.83 502	87.53 449	67.96 386	92.07 475	66.00 471	67.75 458	90.23 430

MDA-MVSNet_test_wron		79.65 428	77.05 434	87.45 424	87.79 455	80.13 426	96.25 392	94.44 428	73.87 468	51.80 503	87.47 453	68.04 384	92.12 474	66.02 470	67.79 457	90.09 431

MIMVSNet		84.48 389	81.83 401	92.42 316	91.73 399	87.36 296	85.52 488	94.42 432	81.40 416	81.91 372	87.58 448	51.92 468	92.81 463	73.84 430	88.15 317	97.08 288

MVP-Stereo		86.61 355	85.83 349	88.93 410	88.70 441	83.85 380	96.07 400	94.41 433	82.15 409	75.64 439	91.96 372	67.65 388	96.45 360	77.20 403	98.72 112	86.51 475
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MSDG		88.29 328	86.37 341	94.04 272	96.90 180	86.15 334	96.52 379	94.36 434	77.89 444	79.22 409	96.95 240	69.72 368	99.59 128	73.20 436	92.58 263	96.37 315

ACMH+	83.78 15	84.21 393	82.56 399	89.15 405	93.73 353	79.16 435	96.43 383	94.28 435	81.09 421	74.00 447	94.03 323	54.58 460	97.67 298	76.10 412	78.81 381	90.63 423

Patchmatch-test		86.25 362	84.06 380	92.82 304	94.42 319	82.88 394	82.88 503	94.23 436	71.58 473	79.39 406	90.62 410	89.00 76	96.42 361	63.03 480	91.37 298	99.16 129

CR-MVSNet		88.83 315	87.38 326	93.16 296	93.47 360	86.24 324	84.97 493	94.20 437	88.92 239	90.76 253	86.88 459	84.43 175	94.82 437	70.64 450	92.17 277	98.41 219

Patchmtry		83.61 402	81.64 402	89.50 396	93.36 364	82.84 395	84.10 496	94.20 437	69.47 484	79.57 403	86.88 459	84.43 175	94.78 438	68.48 462	74.30 413	90.88 412

EG-PatchMatch MVS		79.92 424	77.59 431	86.90 430	87.06 461	77.90 449	96.20 396	94.06 439	74.61 465	66.53 485	88.76 441	40.40 493	96.20 379	67.02 467	83.66 351	86.61 473

KD-MVS_self_test		77.47 443	75.88 440	82.24 462	81.59 489	68.93 489	92.83 454	94.02 440	77.03 446	73.14 454	83.39 478	55.44 455	90.42 484	67.95 463	57.53 487	87.38 466

K. test v3		81.04 420	79.77 422	84.83 449	87.41 457	70.23 485	95.60 415	93.93 441	83.70 378	67.51 481	89.35 438	55.76 451	93.58 455	76.67 408	68.03 455	90.67 422

FE-MVSNET2		78.42 438	75.71 441	86.55 433	78.55 499	81.99 406	95.40 416	93.86 442	81.11 419	66.27 486	81.89 485	49.29 480	91.80 477	72.03 445	63.02 470	85.86 479

RPSCF		85.33 377	85.55 354	84.67 451	94.63 312	62.28 498	93.73 440	93.76 443	74.38 467	85.23 324	97.06 233	64.09 417	98.31 215	80.98 375	86.08 331	93.41 339

MVS-HIRNet		79.01 431	75.13 445	90.66 363	93.82 351	81.69 409	85.16 490	93.75 444	54.54 503	74.17 446	59.15 522	57.46 445	96.58 350	63.74 477	94.38 224	93.72 336

pmmvs5		85.87 367	84.40 377	90.30 375	88.53 443	84.23 373	98.60 214	93.71 445	81.53 415	80.29 393	92.02 368	64.51 416	95.52 418	82.04 369	78.34 383	91.15 405

pmmvs6		79.90 425	77.31 433	87.67 420	84.17 475	78.13 446	95.86 408	93.68 446	67.94 488	72.67 459	89.62 434	50.98 473	95.75 406	74.80 422	66.04 463	89.14 449

OurMVSNet-221017-0		84.13 396	83.59 385	85.77 443	87.81 453	70.24 484	94.89 423	93.65 447	86.08 331	76.53 430	93.28 346	61.41 432	96.14 384	80.95 376	77.69 391	90.93 410

PatchmatchNet2					0.00 566	79.25 433	96.11 398	93.62 448	70.56 477
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
Anonymous20240521		78.63 435	76.90 436	83.82 455	82.82 485	72.86 475	95.72 413	93.57 449	73.55 471	72.17 461	84.79 475	49.69 478	92.51 468	65.29 474	74.50 409	86.09 478

DP-MVS		88.75 319	86.56 339	95.34 192	98.92 89	87.45 293	97.64 332	93.52 450	70.55 478	81.49 380	97.25 212	74.43 324	99.88 73	71.14 449	94.09 230	98.67 197

ITE_SJBPF				87.93 417	92.26 384	76.44 458		93.47 451	87.67 294	79.95 398	95.49 303	56.50 449	97.38 319	75.24 417	82.33 362	89.98 437

USDC		84.74 383	82.93 389	90.16 377	91.73 399	83.54 384	95.00 422	93.30 452	88.77 246	73.19 453	93.30 345	53.62 464	97.65 301	75.88 414	81.54 365	89.30 446

dtuonly		89.80 295	89.16 285	91.70 340	90.49 415	81.48 411	96.58 377	93.12 453	87.21 303	88.72 290	96.87 251	72.09 350	97.59 306	83.52 347	93.84 235	96.03 320

ADS-MVSNet2		87.62 340	86.88 335	89.86 385	96.21 212	79.14 436	87.15 485	92.99 454	83.01 389	89.91 274	87.27 454	78.87 270	92.80 464	74.20 426	92.27 273	97.64 265

Anonymous20231206		80.76 421	79.42 424	84.79 450	84.78 473	72.98 473	96.53 378	92.97 455	79.56 432	74.33 444	88.83 440	61.27 433	92.15 472	60.59 486	75.92 398	89.24 448

MDA-MVSNet-bldmvs		77.82 442	74.75 448	87.03 427	88.33 445	78.52 442	96.34 386	92.85 456	75.57 460	48.87 505	87.89 446	57.32 446	92.49 469	60.79 485	64.80 467	90.08 432

test20.03		78.51 437	77.48 432	81.62 467	83.07 481	71.03 481	96.11 398	92.83 457	81.66 414	69.31 472	89.68 433	57.53 444	87.29 501	58.65 491	68.47 453	86.53 474

COLMAP_ROB	82.69 18	84.54 388	82.82 390	89.70 391	96.72 189	78.85 437	95.89 404	92.83 457	71.55 474	77.54 429	95.89 293	59.40 440	99.14 171	67.26 466	88.26 316	91.11 407
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvs2		85.10 380	85.45 356	84.02 454	89.85 423	65.63 494	98.49 233	92.59 459	90.45 171	85.43 323	93.32 343	43.94 485	96.59 349	90.81 243	84.19 344	89.85 439

SixPastTwentyTwo		82.63 410	81.58 403	85.79 442	88.12 448	71.01 482	95.17 420	92.54 460	84.33 367	72.93 458	92.08 366	60.41 437	95.61 417	74.47 423	74.15 416	90.75 418

FMVSNet5		82.29 411	80.54 411	87.52 422	93.79 352	84.01 377	93.73 440	92.47 461	76.92 447	74.27 445	86.15 469	63.69 422	89.24 493	69.07 458	74.79 407	89.29 447

usedtu_blend_shiyan5		82.04 413	78.78 426	91.80 331	82.91 482	88.24 258	94.33 430	92.37 462	66.55 493	78.60 417	86.54 464	66.93 396	95.77 404	83.97 339	56.84 490	91.38 391

new-patchmatchnet		74.80 456	72.40 457	81.99 466	78.36 500	72.20 478	94.44 428	92.36 463	77.06 445	63.47 491	79.98 495	51.04 472	88.85 494	60.53 487	54.35 498	84.92 489

new_pmnet		76.02 447	73.71 452	82.95 460	83.88 476	72.85 476	91.26 472	92.26 464	70.44 479	62.60 492	81.37 489	47.64 482	92.32 470	61.85 482	72.10 438	83.68 494

AllTest		84.97 382	83.12 388	90.52 368	96.82 183	78.84 438	95.89 404	92.17 465	77.96 442	75.94 435	95.50 301	55.48 453	99.18 165	71.15 447	87.14 320	93.55 337

TestCases				90.52 368	96.82 183	78.84 438		92.17 465	77.96 442	75.94 435	95.50 301	55.48 453	99.18 165	71.15 447	87.14 320	93.55 337

pmmvs-eth3d		78.71 434	76.16 439	86.38 434	80.25 495	81.19 418	94.17 435	92.13 467	77.97 441	66.90 484	82.31 483	55.76 451	92.56 467	73.63 433	62.31 475	85.38 484

MIMVSNet1		75.92 448	73.30 454	83.81 456	81.29 491	75.57 462	92.26 458	92.05 468	73.09 472	67.48 482	86.18 468	40.87 492	87.64 500	55.78 495	70.68 445	88.21 459

ambc				79.60 473	72.76 511	56.61 503	76.20 513	92.01 469		68.25 477	80.23 494	23.34 506	94.73 439	73.78 432	60.81 479	87.48 465

LF4IMVS		81.94 415	81.17 408	84.25 453	87.23 460	68.87 490	93.35 446	91.93 470	83.35 384	75.40 440	93.00 354	49.25 481	96.65 347	78.88 392	78.11 384	87.22 470

TransMVSNet (Re)		81.97 414	79.61 423	89.08 406	89.70 427	84.01 377	97.26 347	91.85 471	78.84 435	73.07 457	91.62 379	67.17 393	95.21 429	67.50 465	59.46 483	88.02 460

MVStest1		76.56 446	73.43 453	85.96 441	86.30 467	80.88 424	94.26 433	91.74 472	61.98 497	58.53 497	89.96 429	69.30 374	91.47 480	59.26 489	49.56 508	85.52 483

Baseline_NR-MVSNet		85.83 369	84.82 366	88.87 411	88.73 440	83.34 386	98.63 203	91.66 473	80.41 430	82.44 356	91.35 388	74.63 319	95.42 423	84.13 334	71.39 442	87.84 461

mmtdpeth		83.69 399	82.59 398	86.99 429	92.82 375	76.98 455	96.16 397	91.63 474	82.89 397	92.41 218	82.90 479	54.95 458	98.19 226	96.27 113	53.27 500	85.81 480

testgi		82.29 411	81.00 409	86.17 437	87.24 459	74.84 466	97.39 340	91.62 475	88.63 249	75.85 438	95.42 304	46.07 484	91.55 478	66.87 469	79.94 376	92.12 361

TDRefinement		78.01 440	75.31 443	86.10 438	70.06 514	73.84 469	93.59 443	91.58 476	74.51 466	73.08 456	91.04 394	49.63 479	97.12 327	74.88 420	59.47 482	87.33 468

OpenMVS_ROB	73.86 20	77.99 441	75.06 446	86.77 432	83.81 477	77.94 448	96.38 385	91.53 477	67.54 489	68.38 476	87.13 458	43.94 485	96.08 386	55.03 497	81.83 363	86.29 477

ttmdpeth		79.80 427	77.91 430	85.47 445	83.34 479	75.75 460	95.32 418	91.45 478	76.84 448	74.81 443	91.71 378	53.98 463	94.13 447	72.42 443	61.29 476	86.51 475

test_0402		78.81 433	76.33 438	86.26 436	91.18 407	78.44 443	95.88 406	91.34 479	68.55 485	70.51 467	89.91 430	52.65 467	94.99 431	47.14 510	79.78 377	85.34 486

MTMP							99.21 115	91.09 480

DeepMVS_CX				76.08 476	90.74 413	51.65 512		90.84 481	86.47 326	57.89 499	87.98 444	35.88 498	92.60 465	65.77 472	65.06 466	83.97 492

dtuonlycased		79.10 430	78.53 427	80.81 470	86.63 463	72.95 474	96.33 387	90.81 482	81.09 421	68.85 473	87.27 454	56.94 447	87.84 498	71.57 446	67.30 460	81.65 498

test_fmvs3		75.09 453	75.19 444	74.81 479	77.45 502	54.08 507	95.93 402	90.64 483	82.51 403	73.29 452	81.19 490	22.29 507	86.29 504	85.50 315	67.89 456	84.06 491

usedtu_dtu_shiyan2		69.89 462	65.80 467	82.15 464	69.90 515	68.09 491	93.09 448	90.63 484	58.33 498	61.56 494	79.31 498	28.96 504	89.43 491	57.76 493	52.68 503	88.92 454

tt0320		76.58 445	73.16 455	86.86 431	88.03 450	77.60 451	93.55 445	90.63 484	55.37 501	70.93 463	84.98 473	41.57 489	94.01 448	69.02 459	64.32 469	88.97 452

sc_t1		78.53 436	74.87 447	89.48 399	87.92 451	77.36 453	94.80 424	90.61 486	57.65 499	76.28 431	89.59 435	38.25 494	96.18 380	74.04 428	64.72 468	94.91 332

lessismore_v0				85.08 447	85.59 471	69.28 487		90.56 487		67.68 480	90.21 426	54.21 462	95.46 421	73.88 429	62.64 473	90.50 425

Gipuma		54.77 479	52.22 481	62.40 499	86.50 464	59.37 502	50.20 532	90.35 488	36.52 520	41.20 518	49.49 528	18.33 511	81.29 507	32.10 525	65.34 465	46.54 532
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
TinyColmap		80.42 423	77.94 429	87.85 418	92.09 388	78.58 441	93.74 439	89.94 489	74.99 463	69.77 469	91.78 375	46.09 483	97.58 308	65.17 475	77.89 385	87.38 466

test_method		70.10 461	68.66 464	74.41 481	86.30 467	55.84 505	94.47 426	89.82 490	35.18 521	66.15 487	84.75 476	30.54 500	77.96 516	70.40 453	60.33 480	89.44 445

FPMVS		61.57 467	60.32 469	65.34 493	60.14 530	42.44 524	91.02 475	89.72 491	44.15 511	42.63 514	80.93 491	19.02 509	80.59 512	42.50 516	72.76 430	73.00 511

test_f		71.94 459	70.82 460	75.30 478	72.77 510	53.28 508	91.62 465	89.66 492	75.44 462	64.47 490	78.31 501	20.48 508	89.56 490	78.63 395	66.02 464	83.05 497

LCM-MVSNet		60.07 472	56.37 474	71.18 485	54.81 534	48.67 515	82.17 506	89.48 493	37.95 518	49.13 504	69.12 514	13.75 518	81.76 506	59.28 488	51.63 504	83.10 496

mvs5depth		78.17 439	75.56 442	85.97 440	80.43 494	76.44 458	85.46 489	89.24 494	76.39 450	78.17 426	88.26 443	51.73 469	95.73 408	69.31 457	61.09 477	85.73 481

tt0320-xc		75.92 448	72.23 459	87.01 428	88.40 444	78.15 445	93.57 444	89.15 495	55.46 500	69.66 470	85.79 472	38.20 495	93.85 449	69.72 454	60.08 481	89.03 450

pmmvs3		72.86 458	69.76 463	82.17 463	73.86 507	74.19 468	94.20 434	89.01 496	64.23 496	67.72 479	80.91 493	41.48 490	88.65 496	62.40 481	54.02 499	83.68 494

LCM-MVSNet-Re		88.59 324	88.61 302	88.51 413	95.53 247	72.68 477	96.85 366	88.43 497	88.45 256	73.14 454	90.63 409	75.82 311	94.38 444	92.95 211	95.71 195	98.48 216

Patchmatch-RL test		81.90 416	80.13 419	87.23 426	80.71 492	70.12 486	84.07 497	88.19 498	83.16 387	70.57 465	82.18 484	87.18 112	92.59 466	82.28 366	62.78 472	98.98 150

FE-MVSNET		75.08 454	72.25 458	83.56 458	77.93 501	76.96 456	94.36 429	87.96 499	75.72 457	66.01 488	81.60 488	50.48 475	88.85 494	55.38 496	60.82 478	84.86 490

mvsany_test3		75.85 450	74.52 449	79.83 471	73.53 508	60.64 500	91.73 464	87.87 500	83.91 374	70.55 466	82.52 481	31.12 499	93.66 453	86.66 301	62.83 471	85.19 488

DSMNet-mixed		81.60 417	81.43 405	82.10 465	84.36 474	60.79 499	93.63 442	86.74 501	79.00 433	79.32 408	87.15 457	63.87 420	89.78 489	66.89 468	91.92 280	95.73 325

ArgMatch-Sym		75.37 451	74.07 450	79.27 474	86.10 469	64.15 496	92.14 459	85.97 502	78.66 438	71.15 462	91.00 395	29.88 502	86.45 503	73.44 434	58.34 485	87.22 470

PM-MVS		74.88 455	72.85 456	80.98 469	78.98 497	64.75 495	90.81 476	85.77 503	80.95 424	68.23 478	82.81 480	29.08 503	92.84 462	76.54 409	62.46 474	85.36 485

door								85.30 504

ArgMatch-SfM		75.24 452	73.75 451	79.70 472	85.92 470	63.67 497	91.51 468	85.16 505	79.74 431	70.70 464	90.27 420	30.46 501	87.73 499	72.95 438	57.08 488	87.70 464

APD_test1		68.93 463	66.98 465	74.77 480	80.62 493	53.15 509	87.97 483	85.01 506	53.76 504	59.26 496	87.52 450	25.19 505	89.95 486	56.20 494	67.33 459	81.19 499

door-mid								84.90 507

EGC-MVSNET		60.70 471	55.37 475	76.72 475	86.35 466	71.08 480	89.96 480	84.44 508	0.38 559	1.50 561	84.09 477	37.30 496	88.10 497	40.85 520	73.44 425	70.97 514

WB-MVS		66.44 464	66.29 466	66.89 491	74.84 504	44.93 520	93.00 449	84.09 509	71.15 475	55.82 500	81.63 487	63.79 421	80.31 513	21.85 529	50.47 506	75.43 507

SSC-MVS		65.42 465	65.20 468	66.06 492	73.96 506	43.83 521	92.08 460	83.54 510	69.77 482	54.73 501	80.92 492	63.30 423	79.92 514	20.48 531	48.02 509	74.44 509

dmvs_testset		77.17 444	78.99 425	71.71 484	87.25 458	38.55 528	91.44 469	81.76 511	85.77 338	69.49 471	95.94 292	69.71 369	84.37 505	52.71 501	76.82 395	92.21 357

PMMVS2		58.97 473	55.07 476	70.69 487	62.72 524	55.37 506	85.97 487	80.52 512	49.48 509	45.94 509	68.31 515	15.73 513	80.78 510	49.79 505	37.12 518	75.91 505

LoFTR		61.59 466	56.89 473	75.68 477	76.61 503	50.06 514	82.20 505	79.57 513	52.13 506	39.02 521	75.71 505	14.90 515	93.30 457	45.35 512	46.48 512	83.69 493

ANet_high		50.71 483	46.17 487	64.33 494	44.27 542	52.30 511	76.13 514	78.73 514	64.95 494	27.37 528	55.23 525	14.61 517	67.74 524	36.01 523	18.23 537	72.95 512

PMVS	41.42 23	45.67 486	42.50 488	55.17 505	34.28 556	32.37 533	66.24 519	78.71 515	30.72 523	22.04 534	59.59 521	4.59 543	77.85 517	27.49 526	58.84 484	55.29 524
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis1_rt		81.31 419	80.05 421	85.11 446	91.29 406	70.66 483	98.98 156	77.39 516	85.76 339	68.80 474	82.40 482	36.56 497	99.44 143	92.67 218	86.55 325	85.24 487

MatchFormer		56.78 475	51.80 482	71.74 483	73.47 509	45.39 517	81.84 507	76.12 517	40.41 514	35.13 523	69.22 513	12.67 522	92.15 472	35.57 524	41.74 513	77.67 503

tmp_tt		53.66 480	52.86 480	56.05 503	32.75 558	41.97 526	73.42 517	76.12 517	21.91 528	39.68 519	96.39 276	42.59 488	65.10 527	78.00 398	14.92 545	61.08 521

testf1		56.38 476	53.73 478	64.31 495	64.84 521	45.11 518	80.50 508	75.94 519	38.87 516	42.74 512	75.07 506	11.26 525	81.19 508	41.11 518	53.27 500	66.63 516

APD_test2		56.38 476	53.73 478	64.31 495	64.84 521	45.11 518	80.50 508	75.94 519	38.87 516	42.74 512	75.07 506	11.26 525	81.19 508	41.11 518	53.27 500	66.63 516

MASt3R-SfM		60.79 470	59.91 470	63.44 498	62.41 525	35.46 529	75.76 516	71.46 521	54.67 502	58.30 498	86.10 470	14.86 516	74.25 520	65.44 473	50.18 507	80.59 500

DenseAffine		61.07 469	57.33 472	72.29 482	78.74 498	56.29 504	83.24 500	69.15 522	53.26 505	47.82 507	79.48 497	13.61 519	80.66 511	51.15 504	39.51 515	79.92 501

MVE	44.00 22	41.70 488	37.64 495	53.90 506	49.46 537	43.37 522	65.09 520	66.66 523	26.19 526	25.77 531	48.53 529	3.58 546	63.35 528	26.15 528	27.28 528	54.97 525
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		41.02 489	40.93 491	41.29 509	61.97 526	33.83 530	84.00 498	65.17 524	27.17 524	27.56 527	46.72 532	17.63 512	60.41 530	19.32 532	18.82 534	29.61 536

EMVS		39.96 491	39.88 492	40.18 510	59.57 532	32.12 535	84.79 495	64.57 525	26.27 525	26.14 530	44.18 536	18.73 510	59.29 531	17.03 533	17.67 539	29.12 537

ELoFTR		47.00 485	42.41 489	60.77 501	51.54 536	32.77 532	63.82 521	61.24 526	39.04 515	29.94 525	67.31 517	4.83 542	75.52 519	39.39 521	24.54 531	74.03 510

test_vis3_rt		61.29 468	58.75 471	68.92 488	67.41 518	52.84 510	91.18 474	59.23 527	66.96 490	41.96 517	58.44 523	11.37 524	94.72 440	74.25 425	57.97 486	59.20 522

VLMVS_CLIP		40.95 490	42.04 490	37.71 512	32.13 559	14.08 559	54.07 530	58.90 528	13.80 533	44.01 511	74.81 508	9.85 529	48.39 532	49.70 506	41.06 514	50.67 528

RoMa-SfM		58.43 474	54.99 477	68.74 489	74.29 505	50.87 513	82.37 504	58.12 529	50.53 507	48.40 506	81.78 486	12.70 521	78.25 515	47.71 509	39.01 516	77.09 504

DKM		55.59 478	51.49 483	67.89 490	72.36 512	48.29 516	80.45 510	52.05 530	47.86 510	42.54 515	77.08 504	9.06 534	77.32 518	48.87 507	33.13 520	78.05 502

GLUNet-SfM		37.11 494	32.05 499	52.28 508	44.07 544	25.94 540	52.38 531	46.25 531	24.11 527	21.50 535	55.60 524	6.32 541	66.20 526	27.48 527	10.71 551	64.70 518

RoMa-HiRes		51.04 481	47.47 484	61.73 500	65.35 520	42.38 525	76.31 512	41.57 532	42.69 512	42.32 516	77.75 502	9.33 531	73.10 521	42.68 515	29.24 523	69.72 515

DKM-HiRes		50.92 482	46.71 485	63.56 497	66.42 519	42.72 523	76.47 511	41.46 533	42.47 513	39.40 520	73.35 510	7.13 540	72.77 522	44.18 513	29.50 522	75.19 508

PDCNetPlus		48.73 484	46.34 486	55.88 504	64.17 523	41.40 527	76.11 515	34.96 534	50.17 508	35.24 522	71.04 511	15.41 514	67.33 525	52.41 502	17.59 540	58.93 523

VLMVS		38.17 493	38.75 494	36.45 515	35.35 554	13.53 561	50.05 533	33.90 535	9.30 541	47.14 508	77.14 503	12.39 523	32.34 536	47.77 508	35.68 519	63.48 519

PMatch-SfM		44.26 487	39.30 493	59.12 502	52.80 535	33.36 531	66.34 518	29.85 536	36.60 519	30.58 524	70.53 512	2.50 558	68.49 523	42.14 517	22.39 533	75.51 506

ALIKED-LG		33.96 496	32.42 498	38.57 511	70.35 513	32.25 534	57.19 525	29.49 537	19.94 529	22.96 533	46.96 531	10.85 527	47.42 533	8.53 545	25.49 529	36.04 533

N_pmnet		70.19 460	69.87 462	71.12 486	88.24 446	30.63 538	95.85 409	28.70 538	70.18 480	68.73 475	86.55 462	64.04 419	93.81 450	53.12 499	73.46 424	88.94 453

ALIKED-NN		33.05 497	31.67 500	37.18 514	69.89 516	31.76 536	55.83 529	28.14 539	16.92 530	23.23 532	47.45 530	9.65 530	45.41 535	8.80 543	25.13 530	34.38 535

ALIKED-MNN		32.26 498	30.45 501	37.68 513	69.07 517	31.55 537	56.28 528	27.56 540	16.30 531	21.15 536	44.78 534	8.12 537	46.74 534	8.19 546	22.59 532	34.76 534

SP-DiffGlue		29.92 501	29.42 505	31.40 519	32.10 560	20.02 542	47.81 534	27.27 541	14.91 532	26.24 529	54.34 526	10.53 528	24.46 543	21.49 530	30.15 521	49.71 531

SP-SuperGlue		30.18 500	29.74 504	31.50 518	60.57 528	18.71 545	57.45 523	26.07 542	13.70 534	20.25 537	39.95 540	9.22 533	25.03 542	11.85 538	28.64 526	50.78 527

SP-LightGlue		30.23 499	29.76 503	31.66 516	60.90 527	18.79 544	57.25 524	25.88 543	13.65 535	20.11 538	39.95 540	9.29 532	25.08 541	11.83 539	28.96 524	51.11 526

SP-MNN		29.29 503	28.62 507	31.29 520	59.13 533	18.03 549	56.77 527	25.19 544	11.83 537	18.01 542	39.35 543	8.35 536	25.39 539	10.99 542	27.91 527	50.47 529

XFeat-MNN		22.62 504	22.31 509	23.56 522	28.01 561	15.00 557	39.69 537	25.09 545	11.81 538	17.88 543	39.92 542	7.77 538	29.38 537	13.26 536	17.33 543	26.31 539

SP-NN		29.64 502	29.14 506	31.16 521	59.77 531	18.23 546	56.90 526	24.71 546	12.64 536	18.99 539	40.64 539	8.48 535	25.23 540	11.37 540	28.74 525	50.01 530

XFeat-NN		22.06 506	22.11 510	21.91 523	27.57 562	14.27 558	38.62 538	22.62 547	11.16 539	18.84 540	41.23 538	7.46 539	26.91 538	13.19 537	18.30 536	24.56 540

PMatch-Up-SfM		39.29 492	34.48 497	53.73 507	46.70 540	28.02 539	58.71 522	21.05 548	31.53 522	27.94 526	66.24 518	1.99 561	61.38 529	38.41 522	17.72 538	71.80 513

SIFT-NN		18.10 508	18.53 512	16.83 524	48.67 539	18.97 543	33.34 539	14.35 549	7.78 542	10.98 546	25.86 545	3.78 544	19.51 545	3.23 547	18.78 535	12.02 543

SIFT-MNN		17.20 509	17.47 513	16.41 526	45.38 541	18.16 547	31.28 541	14.20 550	7.60 543	9.54 547	25.18 546	3.39 547	19.18 546	3.18 548	17.44 541	11.88 544

SIFT-NN-NCMNet		16.94 510	17.19 514	16.19 527	43.53 545	18.04 548	31.30 540	14.18 551	7.55 545	9.51 548	24.88 547	3.32 548	18.84 547	3.08 549	17.35 542	11.70 546

SIFT-NN-UMatch		15.49 515	15.62 518	15.11 531	38.08 551	15.93 554	29.97 542	13.04 552	7.57 544	7.22 552	24.84 549	3.26 549	18.03 550	3.02 550	13.56 546	11.37 547

SIFT-NCM-Cal		16.07 513	16.20 516	15.69 528	44.16 543	17.32 550	29.83 543	12.88 553	7.33 548	6.22 555	23.59 553	3.00 552	18.75 548	2.74 555	16.09 544	10.99 549

SIFT-NN-CMatch		15.72 514	15.77 517	15.60 529	39.99 549	16.99 552	28.08 544	12.85 554	7.52 546	9.34 549	24.86 548	3.24 550	18.08 549	2.99 551	13.01 548	11.71 545

SIFT-ConvMatch		15.12 516	15.10 519	15.19 530	42.19 546	17.16 551	26.33 547	12.02 555	7.39 547	7.26 551	24.08 550	2.92 553	17.97 551	2.85 553	10.90 550	10.43 551

SIFT-NN-PointCN		14.43 518	14.70 521	13.64 534	36.13 552	12.94 562	27.63 546	11.82 556	7.03 552	8.24 550	23.49 554	3.21 551	16.75 554	2.85 553	11.89 549	11.22 548

SIFT-UMatch		14.73 517	14.79 520	14.57 532	40.58 548	15.36 556	27.70 545	11.21 557	7.28 549	6.62 554	24.07 551	2.81 556	17.91 552	2.87 552	9.94 552	10.45 550

SIFT-CM-Cal		14.12 519	14.09 522	14.22 533	40.92 547	15.56 555	23.80 549	10.18 558	7.20 550	6.72 553	23.20 555	2.86 555	16.98 553	2.67 557	9.24 555	10.13 552

SIFT-PointCN		12.37 521	12.72 524	11.33 536	35.33 555	10.01 563	23.72 550	9.79 559	6.45 554	5.30 559	20.10 557	2.22 560	14.67 558	2.33 559	9.26 554	9.30 554

SIFT-UM-Cal		13.73 520	13.86 523	13.34 535	39.95 550	13.63 560	25.68 548	9.21 560	7.19 551	5.57 556	23.60 552	2.66 557	16.67 555	2.70 556	8.18 556	9.73 553

MVS_clip		35.38 495	36.65 496	31.56 517	48.77 538	16.48 553	41.99 535	8.97 561	9.90 540	45.60 510	78.84 499	13.61 519	15.85 556	44.08 514	38.09 517	62.37 520

SIFT-PCN-Cal		12.09 522	12.36 525	11.26 537	35.43 553	9.79 564	22.24 551	8.83 562	6.37 555	5.43 558	20.44 556	2.34 559	14.88 557	2.35 558	7.87 557	9.13 555

SIFT-NCMNet		10.41 524	10.63 528	9.76 538	33.41 557	9.03 565	18.23 552	5.49 563	6.29 556	4.60 560	17.58 558	1.84 562	12.74 559	2.03 560	6.21 558	7.52 556

wuyk23d		16.71 511	16.73 515	16.65 525	60.15 529	25.22 541	41.24 536	5.17 564	6.56 553	5.48 557	3.61 559	3.64 545	22.72 544	15.20 534	9.52 553	1.99 557

testmvs		18.81 507	23.05 508	6.10 541	4.48 564	2.29 567	97.78 316	3.00 565	3.27 557	18.60 541	62.71 519	1.53 563	2.49 561	14.26 535	1.80 559	13.50 542

test123		16.58 512	19.47 511	7.91 540	3.59 565	5.37 566	94.32 431	1.39 566	2.49 558	13.98 545	44.60 535	2.91 554	2.65 560	11.35 541	0.57 560	15.70 541

MVS_baseline		11.50 523	12.32 526	9.06 539	13.94 563	0.55 568	4.75 553	1.33 567	0.26 560	16.85 544	50.28 527	1.45 564	0.03 562	8.71 544	13.26 547	26.61 538

mmdepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

monomultidepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

test_blank		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

uanet_test		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

DCPMVS		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

pcd_1.5k_mvsjas		6.87 526	9.16 529	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	82.48 216	0.00 563	0.00 561	0.00 561	0.00 558

sosnet-low-res		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

sosnet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

uncertanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

Regformer		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

n2								0.00 568

nn								0.00 568

ab-mvs-re		8.21 525	10.94 527	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	98.50 132	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

uanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 563	0.00 561	0.00 561	0.00 558

Meshroom													0.00 563
: In preparation.
AliceVision / Meshro													0.00 563
: In preparation.
AliceVision_Meshroom													0.00 563
: In preparation.
PatchmatchNet1														52.97 500	73.44 425	88.99 451
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													93.74 451
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						79.74 430								67.75 464

PC_three_1452									94.60 53	99.41 12	99.12 64	95.50 7	99.96 34	99.84 2	99.92 3	99.97 8

eth-test2					0.00 566

eth-test					0.00 566

OPU-MVS				99.49 4	99.64 23	98.51 4	99.77 30				99.19 46	95.12 9	99.97 26	99.90 1	99.92 3	99.99 2

test_0728_THIRD									93.01 95	99.07 27	99.46 15	94.66 14	99.97 26	99.25 30	99.82 19	99.95 16

GSMVS																98.84 167

test_part2					99.54 42	95.42 25				98.13 65

sam_mvs1												88.39 85				98.84 167

sam_mvs												87.08 115

test_post1							90.74 478				41.37 537	85.38 157	96.36 364	83.16 350

test_post											46.00 533	87.37 106	97.11 328

patchmatchnet-post											84.86 474	88.73 81	96.81 341

gm-plane-assit					94.69 309	88.14 264			88.22 269		97.20 216		98.29 217	90.79 244

test9_res														98.60 52	99.87 9	99.90 23

agg_prior2														97.84 79	99.87 9	99.91 22

test_prior4						92.00 125	99.41 93

test_prior2							99.57 65		91.43 138	98.12 67	98.97 84	90.43 57		98.33 66	99.81 23

旧先验2							98.67 197		85.75 340	98.96 33			98.97 180	93.84 184

新几何2							98.26 271

原ACMM2							98.69 193

testdata2													99.88 73	84.16 333

segment_acmp												90.56 55

testdata1							97.89 308		92.43 110

plane_prior7					93.84 348	85.73 348

plane_prior6					93.92 345	86.02 340						72.92 342

plane_prior4											96.52 268

plane_prior3						85.91 342			93.65 83	86.99 307

plane_prior2							99.02 150		93.38 90

plane_prior1					93.90 347

plane_prior						86.07 338	99.14 132		93.81 79						86.26 328

HQP5-MVS						86.39 319

HQP-NCC					93.95 340		99.16 124		93.92 70	87.57 300

ACMP_Plane					93.95 340		99.16 124		93.92 70	87.57 300

BP-MVS														93.82 186

HQP4-MVS										87.57 300			97.77 284			92.72 343

HQP2-MVS												73.34 335

NP-MVS					93.94 343	86.22 326					96.67 265

MDTV_nov1_ep13_2view						91.17 149	91.38 470		87.45 299	93.08 196		86.67 127		87.02 288		98.95 156

ACMMP++_ref															82.64 360

ACMMP++															83.83 347

Test By Simon												83.62 184

High-resolution multi-view benchmark