High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

MVS_111021_HR		96.69 46	96.69 46	96.72 99	98.58 100	91.00 155	99.14 130	99.45 1	93.86 73	95.15 147	98.73 111	88.48 83	99.76 109	97.23 89	99.56 56	99.40 105

thres100view900		93.34 187	92.15 210	96.90 87	97.62 132	94.84 43	99.06 144	99.36 2	87.96 275	90.47 259	96.78 256	83.29 188	98.75 191	84.11 332	90.69 301	97.12 281

tfpn200view9		93.43 181	92.27 202	96.90 87	97.68 129	94.84 43	99.18 118	99.36 2	88.45 254	90.79 249	96.90 245	83.31 186	98.75 191	84.11 332	90.69 301	97.12 281

thres600view7		93.18 192	92.00 213	96.75 95	97.62 132	94.92 38	99.07 141	99.36 2	87.96 275	90.47 259	96.78 256	83.29 188	98.71 196	82.93 351	90.47 305	96.61 300

thres400		93.39 183	92.27 202	96.73 97	97.68 129	94.84 43	99.18 118	99.36 2	88.45 254	90.79 249	96.90 245	83.31 186	98.75 191	84.11 332	90.69 301	96.61 300

thres200		93.69 167	92.59 193	96.97 83	97.76 125	94.74 49	99.35 101	99.36 2	89.23 220	91.21 245	96.97 237	83.42 185	98.77 187	85.08 315	90.96 299	97.39 272

MVS_111021_LR		95.78 88	95.94 74	95.28 197	98.19 111	87.69 273	98.80 171	99.26 7	93.39 87	95.04 149	98.69 118	84.09 176	99.76 109	96.96 95	99.06 86	98.38 221

sss		94.85 123	93.94 139	97.58 49	96.43 197	94.09 67	98.93 157	99.16 8	89.50 213	95.27 144	97.85 159	81.50 229	99.65 121	92.79 214	94.02 231	98.99 147

MM		97.76 12	97.39 22	98.86 6	98.30 105	96.83 8	99.81 20	99.13 9	97.66 2	98.29 60	98.96 88	85.84 144	99.90 62	99.72 3	98.80 106	99.85 35

MG-MVS		97.24 24	96.83 39	98.47 16	99.79 6	95.71 21	99.07 141	99.06 10	94.45 56	96.42 115	98.70 117	88.81 79	99.74 111	95.35 142	99.86 12	99.97 8

test2506		94.80 124	94.21 125	96.58 109	96.41 200	92.18 121	98.01 300	98.96 11	90.82 154	93.46 187	97.28 206	85.92 141	98.45 210	89.82 251	97.19 160	99.12 132

PVSNet	87.13 12	93.69 167	92.83 185	96.28 130	97.99 118	90.22 178	99.38 95	98.93 12	91.42 138	93.66 182	97.68 175	71.29 357	99.64 123	87.94 277	97.20 159	98.98 148

PGM-MVS		95.85 84	95.65 90	96.45 116	99.50 48	89.77 200	98.22 272	98.90 13	89.19 222	96.74 108	98.95 91	85.91 143	99.92 50	93.94 179	99.46 61	99.66 71

EPNet		96.82 40	96.68 47	97.25 68	98.65 98	93.10 93	99.48 76	98.76 14	96.54 22	97.84 75	98.22 148	87.49 100	99.66 117	95.35 142	97.78 144	99.00 145
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		95.97 76	95.11 106	98.54 14	97.62 132	96.65 10	99.44 85	98.74 15	92.25 118	95.21 145	98.46 140	86.56 128	99.46 141	95.00 154	92.69 255	99.50 95

HY-MVS	88.56 7	95.29 106	94.23 124	98.48 15	97.72 127	96.41 14	94.03 435	98.74 15	92.42 111	95.65 138	94.76 313	86.52 130	99.49 135	95.29 145	92.97 251	99.53 89

VNet		95.08 114	94.26 123	97.55 52	98.07 115	93.88 69	98.68 191	98.73 17	90.33 175	97.16 92	97.43 194	79.19 259	99.53 132	96.91 97	91.85 279	99.24 121

test_yl		95.27 107	94.60 116	97.28 66	98.53 101	92.98 98	99.05 145	98.70 18	86.76 314	94.65 158	97.74 170	87.78 95	99.44 142	95.57 136	92.61 256	99.44 102

DCV-MVSNet		95.27 107	94.60 116	97.28 66	98.53 101	92.98 98	99.05 145	98.70 18	86.76 314	94.65 158	97.74 170	87.78 95	99.44 142	95.57 136	92.61 256	99.44 102

PVSNet_0	83.28 16	87.31 340	85.16 356	93.74 280	94.78 302	84.59 365	98.91 160	98.69 20	89.81 197	78.59 417	93.23 344	61.95 427	99.34 157	94.75 160	55.72 494	97.30 276

ACMMP		94.67 131	94.30 122	95.79 162	99.25 65	88.13 262	98.41 244	98.67 21	90.38 174	91.43 238	98.72 113	82.22 219	99.95 38	93.83 184	95.76 192	99.29 117
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
lecture		96.67 47	96.77 43	96.39 121	99.27 63	89.71 202	99.65 52	98.62 22	92.28 117	98.62 45	99.07 70	86.74 120	99.79 104	97.83 79	98.82 103	99.66 71

SymmetryMVS		95.49 99	95.27 99	96.17 139	97.13 168	90.37 171	99.14 130	98.59 23	94.92 45	96.30 118	97.98 155	85.33 156	99.23 161	94.35 170	93.67 241	98.92 158

D2MVS		87.96 328	87.39 322	89.70 388	91.84 393	83.40 381	98.31 262	98.49 24	88.04 272	78.23 422	90.26 418	73.57 330	96.79 340	84.21 329	83.53 349	88.90 452

test_fmvsm_n_1920		97.08 32	97.55 15	95.67 168	97.94 120	89.61 206	99.93 1	98.48 25	97.08 12	99.08 25	99.13 60	88.17 88	99.93 47	99.11 37	99.06 86	97.47 269

fmvsm_s_conf0.5_n		96.19 67	96.49 52	95.30 196	97.37 150	89.16 220	99.86 9	98.47 26	95.68 34	98.87 34	99.15 55	82.44 216	99.92 50	99.14 35	97.43 155	96.83 292

HyFIR lowres test		93.68 169	93.29 168	94.87 220	97.57 138	88.04 264	98.18 276	98.47 26	87.57 292	91.24 243	95.05 309	85.49 149	97.46 311	93.22 204	92.82 252	99.10 135

testing3-2		95.17 110	94.78 113	96.33 127	97.35 151	92.35 116	99.85 12	98.43 28	90.60 163	92.84 203	97.00 235	90.89 45	98.89 181	95.95 125	90.12 307	97.76 255

fmvsm_s_conf0.5_n_a		95.97 76	96.19 63	95.31 193	96.51 194	89.01 229	99.81 20	98.39 29	95.46 39	99.19 24	99.16 51	81.44 233	99.91 57	98.83 45	96.97 165	97.01 288

UniMVSNet (Re)		89.50 299	88.32 307	93.03 293	92.21 383	90.96 156	98.90 162	98.39 29	89.13 228	83.22 337	92.03 364	81.69 226	96.34 367	86.79 291	72.53 429	91.81 367

CHOSEN 280x420		96.80 41	96.85 36	96.66 104	97.85 123	94.42 59	94.76 422	98.36 31	92.50 108	95.62 139	97.52 188	97.92 1	97.38 316	98.31 67	98.80 106	98.20 238

VPA-MVSNet		89.10 304	87.66 317	93.45 286	92.56 375	91.02 154	97.97 303	98.32 32	86.92 309	86.03 312	92.01 366	68.84 374	97.10 327	90.92 237	75.34 398	92.23 352

CHOSEN 1792x2688		94.35 140	93.82 148	95.95 155	97.40 146	88.74 245	98.41 244	98.27 33	92.18 120	91.43 238	96.40 271	78.88 264	99.81 98	93.59 188	97.81 141	99.30 116

patch_mono-2		97.10 31	97.97 9	94.49 242	99.21 69	83.73 377	99.62 60	98.25 34	95.28 41	99.38 14	98.91 96	92.28 33	99.94 41	99.61 11	99.22 78	99.78 46

FIs		90.70 266	89.87 263	93.18 291	92.29 380	91.12 148	98.17 278	98.25 34	89.11 229	83.44 334	94.82 312	82.26 218	96.17 379	87.76 278	82.76 355	92.25 350

UGNet		91.91 236	90.85 245	95.10 208	97.06 173	88.69 246	98.01 300	98.24 36	92.41 112	92.39 217	93.61 335	60.52 433	99.68 115	88.14 274	97.25 158	96.92 290
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		90.22 282	89.40 276	92.67 309	91.78 394	89.86 195	97.89 305	98.22 37	88.81 239	82.96 344	94.66 314	81.90 225	95.96 389	85.89 309	82.52 358	92.20 355

WR-MVS_H		86.53 354	85.49 352	89.66 390	91.04 406	83.31 383	97.53 333	98.20 38	84.95 351	79.64 398	90.90 396	78.01 283	95.33 423	76.29 408	72.81 426	90.35 424

MGCNet		97.81 10	97.51 16	98.74 10	98.97 81	96.57 12	99.91 3	98.17 39	97.45 5	98.76 39	98.97 83	86.69 123	99.96 34	99.72 3	98.92 97	99.69 65

MVS		93.92 156	92.28 201	98.83 8	95.69 235	96.82 9	96.22 391	98.17 39	84.89 352	84.34 328	98.61 125	79.32 257	99.83 92	93.88 182	99.43 65	99.86 34

PAPM		96.35 61	95.94 74	97.58 49	94.10 332	95.25 28	98.93 157	98.17 39	94.26 58	93.94 174	98.72 113	89.68 68	97.88 272	96.36 111	99.29 73	99.62 81

baseline2		94.04 150	93.80 149	94.74 228	93.07 369	90.25 175	98.12 283	98.16 42	89.86 193	86.53 310	96.95 238	95.56 6	98.05 256	91.44 232	94.53 221	95.93 319

UniMVSNet_NR-MVSNet		89.60 296	88.55 303	92.75 303	92.17 384	90.07 185	98.74 180	98.15 43	88.37 259	83.21 338	93.98 324	82.86 198	95.93 391	86.95 287	72.47 430	92.25 350

CSCG		94.87 122	94.71 114	95.36 185	99.54 42	86.49 311	99.34 102	98.15 43	82.71 395	90.15 266	99.25 32	89.48 70	99.86 82	94.97 156	98.82 103	99.72 59

test_fmvsmconf_n		96.78 43	96.84 37	96.61 106	95.99 224	90.25 175	99.90 4	98.13 45	96.68 20	98.42 54	98.92 95	85.34 155	99.88 72	99.12 36	99.08 83	99.70 62

MSLP-MVS++		97.50 19	97.45 20	97.63 47	99.65 22	93.21 89	99.70 41	98.13 45	94.61 50	97.78 78	99.46 15	89.85 65	99.81 98	97.97 73	99.91 6	99.88 29

aaatest				97.84 37	99.75 8	93.67 73	99.65 52	98.11 47	92.89 100	98.58 49	99.53 8		100.00 1	99.53 20	99.64 44	99.87 32

MED-MVS		98.04 8	98.10 4	97.86 36	99.75 8	93.67 73	99.65 52	98.11 47	94.03 64	98.58 49	99.49 12	93.98 18	100.00 1	99.53 20	99.75 29	99.90 23

h-mvs33		92.47 220	91.95 216	94.05 267	97.13 168	85.01 359	98.36 257	98.08 49	93.85 74	96.27 120	96.73 259	83.19 192	99.43 145	95.81 128	68.09 451	97.70 261

aaEdge-Enhanced		97.59 16	97.51 16	97.84 37	99.73 12	93.67 73	99.52 72	98.07 50	92.38 115	98.32 59	99.53 8	90.83 48	99.97 26	99.53 20	99.64 44	99.87 32

fmvsm_s_conf0.5_n_4		96.17 68	96.49 52	95.21 202	97.06 173	89.26 215	99.76 32	98.07 50	95.99 28	99.35 15	99.22 37	82.19 220	99.89 70	99.06 38	97.68 146	96.49 307

TestfortrainingZip				99.33 5	99.87 2	97.98 5	99.65 52	98.06 52	92.29 116	99.91 1	99.64 2	95.49 8	100.00 1		98.29 134	100.00 1

IB-MVS	89.43 6	92.12 229	90.83 248	95.98 154	95.40 251	90.78 160	99.81 20	98.06 52	91.23 145	85.63 317	93.66 334	90.63 52	98.78 186	91.22 233	71.85 436	98.36 227
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
fmvsm_l_conf0.5_n		97.65 15	97.72 13	97.41 57	97.51 142	92.78 105	99.85 12	98.05 54	96.78 17	99.60 7	99.23 35	90.42 57	99.92 50	99.55 16	98.50 125	99.55 87

PHI-MVS		96.65 51	96.46 55	97.21 69	99.34 56	91.77 130	99.70 41	98.05 54	86.48 322	98.05 68	99.20 41	89.33 71	99.96 34	98.38 62	99.62 50	99.90 23

fmvsm_l_conf0.5_n_a		97.70 14	97.80 12	97.42 56	97.59 136	92.91 102	99.86 9	98.04 56	96.70 19	99.58 8	99.26 30	90.90 44	99.94 41	99.57 13	98.66 116	99.40 105

PVSNet_BlendedMVS		93.36 186	93.20 170	93.84 275	98.77 95	91.61 137	99.47 78	98.04 56	91.44 136	94.21 166	92.63 358	83.50 182	99.87 76	97.41 84	83.37 351	90.05 432

PVSNet_Blended		95.94 79	95.66 88	96.75 95	98.77 95	91.61 137	99.88 5	98.04 56	93.64 82	94.21 166	97.76 166	83.50 182	99.87 76	97.41 84	97.75 145	98.79 173

EPMVS		92.59 217	91.59 225	95.59 176	97.22 159	90.03 189	91.78 460	98.04 56	90.42 173	91.66 232	90.65 405	86.49 132	97.46 311	81.78 369	96.31 179	99.28 118

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

MCST-MVS		98.18 2	97.95 10	98.86 6	99.85 4	96.60 11	99.70 41	97.98 61	97.18 11	95.96 124	99.33 27	92.62 29	100.00 1	98.99 42	99.93 1	99.98 7

fmvsm_s_conf0.5_n_10		96.95 35	96.82 40	97.33 62	97.76 125	93.00 97	99.87 6	97.95 62	97.32 9	99.71 4	99.20 41	81.48 230	99.90 62	99.32 24	98.78 110	99.09 136

testing3		87.75 332	88.22 309	86.36 432	94.66 308	77.41 448	99.52 72	97.95 62	86.05 329	81.12 380	96.69 262	86.18 138	89.31 489	61.65 481	90.12 307	92.35 349

fmvsm_s_conf0.5_n_7		95.87 82	96.25 61	94.72 230	96.19 213	87.74 272	99.66 50	97.94 64	95.78 31	98.44 53	99.23 35	81.26 236	99.90 62	99.17 34	98.57 122	96.52 306

reproduce_monomvs		92.11 231	91.82 220	92.98 295	98.25 106	90.55 167	98.38 255	97.93 65	94.81 47	80.46 388	92.37 360	96.46 3	97.17 322	94.06 177	73.61 417	91.23 400

testing222		94.48 138	94.00 133	95.95 155	97.30 154	92.27 118	98.82 167	97.92 66	89.20 221	94.82 151	97.26 208	87.13 110	97.32 319	91.95 226	91.56 285	98.25 232

1314		93.44 179	91.98 214	97.84 37	95.24 258	94.38 60	96.22 391	97.92 66	90.18 182	82.28 358	97.71 174	77.63 285	99.80 100	91.94 227	98.67 115	99.34 113

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

tfpnnormal		83.65 397	81.35 403	90.56 364	91.37 402	88.06 263	97.29 342	97.87 69	78.51 436	76.20 429	90.91 395	64.78 412	96.47 355	61.71 480	73.50 420	87.13 469

TestfortrainingZip a		97.38 21	97.10 26	98.24 22	99.75 8	94.82 46	99.65 52	97.86 70	94.03 64	99.04 28	99.49 12	90.76 51	99.99 9	95.87 127	97.45 154	99.90 23

ETVMVS		94.50 137	93.90 143	96.31 128	97.48 144	92.98 98	99.07 141	97.86 70	88.09 270	94.40 162	96.90 245	88.35 85	97.28 320	90.72 243	92.25 272	98.66 200

fmvsm_l_conf0.5_n_9		97.33 22	97.32 24	97.37 60	97.64 131	92.45 115	99.93 1	97.85 72	97.39 6	99.84 2	99.09 69	85.42 153	99.92 50	99.52 23	99.20 82	99.73 58

3Dnovator	87.35 11	93.17 194	91.77 222	97.37 60	95.41 250	93.07 94	98.82 167	97.85 72	91.53 133	82.56 351	97.58 184	71.97 349	99.82 95	91.01 236	99.23 77	99.22 124

UWE-MVS		93.18 192	93.40 163	92.50 311	96.56 190	83.55 379	98.09 289	97.84 74	89.50 213	91.72 230	96.23 277	91.08 40	96.70 342	86.28 302	93.33 247	97.26 278

FE-MVS		91.38 247	90.16 260	95.05 214	96.46 196	87.53 287	89.69 478	97.84 74	82.97 388	92.18 220	92.00 368	84.07 177	98.93 180	80.71 376	95.52 198	98.68 194

WR-MVS		88.54 322	87.22 327	92.52 310	91.93 391	89.50 207	98.56 220	97.84 74	86.99 304	81.87 372	93.81 329	74.25 326	95.92 393	85.29 313	74.43 408	92.12 358

DELS-MVS		97.12 29	96.60 49	98.68 12	98.03 117	96.57 12	99.84 14	97.84 74	96.36 27	95.20 146	98.24 147	88.17 88	99.83 92	96.11 120	99.60 54	99.64 76
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
fmvsm_s_conf0.5_n_8		97.06 33	96.94 30	97.44 53	97.78 124	92.77 106	99.83 15	97.83 78	97.58 3	99.25 19	99.20 41	82.71 206	99.92 50	99.64 8	98.61 118	99.64 76

fmvsm_s_conf0.5_n_3		96.58 54	96.55 50	96.66 104	97.23 158	92.59 112	99.81 20	97.82 79	97.35 7	99.42 10	99.16 51	80.27 243	99.93 47	99.26 27	98.60 120	97.45 270

EI-MVSNet-Vis-set		95.76 90	95.63 92	96.17 139	99.14 72	90.33 173	98.49 230	97.82 79	91.92 124	94.75 154	98.88 102	87.06 113	99.48 139	95.40 141	97.17 162	98.70 191

无先验							98.52 224	97.82 79	87.20 301				99.90 62	87.64 280		99.85 35

EPNet_dtu		92.28 225	92.15 210	92.70 307	97.29 155	84.84 362	98.64 198	97.82 79	92.91 99	93.02 195	97.02 234	85.48 151	95.70 409	72.25 441	94.89 213	97.55 268
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SDMVSNet		91.09 255	89.91 262	94.65 232	96.80 183	90.54 168	97.78 313	97.81 83	88.34 261	85.73 314	95.26 306	66.44 401	98.26 218	94.25 174	86.75 320	95.14 324

HFP-MVS		96.42 60	96.26 60	96.90 87	99.69 14	90.96 156	99.47 78	97.81 83	90.54 168	96.88 97	99.05 75	87.57 98	99.96 34	95.65 130	99.72 34	99.78 46

EI-MVSNet-UG-set		95.43 101	95.29 98	95.86 159	99.07 78	89.87 194	98.43 238	97.80 85	91.78 126	94.11 169	98.77 107	86.25 137	99.48 139	94.95 157	96.45 175	98.22 236

ACMMPR		96.28 65	96.14 72	96.73 97	99.68 15	90.47 170	99.47 78	97.80 85	90.54 168	96.83 102	99.03 77	86.51 131	99.95 38	95.65 130	99.72 34	99.75 54

UWE-MVS-28		90.99 260	91.93 217	88.15 412	95.12 270	77.87 446	97.18 351	97.79 87	88.72 245	88.69 288	96.52 266	86.54 129	90.75 479	84.64 323	92.16 276	95.83 321

UBG		95.73 94	95.41 94	96.69 101	96.97 177	93.23 88	99.13 135	97.79 87	91.28 142	94.38 164	96.78 256	92.37 32	98.56 203	96.17 116	93.84 234	98.26 231

MAR-MVS		94.43 139	94.09 130	95.45 179	99.10 76	87.47 289	98.39 253	97.79 87	88.37 259	94.02 172	99.17 50	78.64 274	99.91 57	92.48 217	98.85 102	98.96 150
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
DPM-MVS		97.86 9	97.25 25	99.68 1	98.25 106	99.10 1	99.76 32	97.78 90	96.61 21	98.15 62	99.53 8	93.62 19	100.00 1	91.79 229	99.80 26	99.94 19

API-MVS		94.78 125	94.18 128	96.59 108	99.21 69	90.06 188	98.80 171	97.78 90	83.59 377	93.85 177	99.21 40	83.79 179	99.97 26	92.37 220	99.00 90	99.74 55

新几何1				97.40 58	98.92 89	92.51 114		97.77 92	85.52 339	96.69 110	99.06 73	88.08 92	99.89 70	84.88 319	99.62 50	99.79 43

HPM-MVS++		97.72 13	97.59 14	98.14 26	99.53 46	94.76 48	99.19 116	97.75 93	95.66 35	98.21 61	99.29 29	91.10 39	99.99 9	97.68 80	99.87 9	99.68 67

GG-mvs-BLEND				96.98 82	96.53 192	94.81 47	87.20 481	97.74 94		93.91 175	96.40 271	96.56 2	96.94 333	95.08 150	98.95 95	99.20 125

gg-mvs-nofinetune		90.00 289	87.71 316	96.89 91	96.15 215	94.69 52	85.15 488	97.74 94	68.32 484	92.97 199	60.16 515	96.10 4	96.84 336	93.89 180	98.87 101	99.14 129

旧先验1					98.97 81	92.90 103		97.74 94			99.15 55	91.05 41			99.33 69	99.60 82

IU-MVS					99.63 24	95.38 26		97.73 97	95.54 37	99.54 9				99.69 7	99.81 23	99.99 2

SED-MVS		98.18 2	98.10 4	98.41 19	99.63 24	95.24 29	99.77 29	97.72 98	94.17 59	99.30 17	99.54 4	93.32 22	99.98 14	99.70 5	99.81 23	99.99 2

test_241102_TWO								97.72 98	94.17 59	99.23 20	99.54 4	93.14 27	99.98 14	99.70 5	99.82 19	99.99 2

test_241102_ONE					99.63 24	95.24 29		97.72 98	94.16 61	99.30 17	99.49 12	93.32 22	99.98 14

DPE-MVS		98.11 6	98.00 7	98.44 17	99.50 48	95.39 25	99.29 105	97.72 98	94.50 52	98.64 44	99.54 4	93.32 22	99.97 26	99.58 12	99.90 7	99.95 16
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DeepPCF-MVS	93.56 1	96.55 57	97.84 11	92.68 308	98.71 97	78.11 443	99.70 41	97.71 102	98.18 1	97.36 85	99.76 1	90.37 59	99.94 41	99.27 26	99.54 58	99.99 2

myMVS_eth3d28		95.74 93	95.34 96	96.92 86	97.41 145	93.58 79	99.28 108	97.70 103	90.97 149	93.91 175	97.25 210	90.59 53	98.75 191	96.85 99	94.14 228	98.44 215

fmvsm_l_conf0.5_n_3		97.12 29	96.89 34	97.79 44	97.39 147	93.84 71	99.87 6	97.70 103	97.34 8	99.39 13	99.20 41	82.86 198	99.94 41	99.21 32	99.07 85	99.58 86

test0726					99.66 18	95.20 34	99.77 29	97.70 103	93.95 66	99.35 15	99.54 4	93.18 25

MSP-MVS		97.77 11	98.18 2	96.53 113	99.54 42	90.14 181	99.41 92	97.70 103	95.46 39	98.60 46	99.19 45	95.71 5	99.49 135	98.15 71	99.85 13	99.95 16
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
MSC_two_6792asdad				99.51 2	99.61 30	98.60 2		97.69 107					99.98 14	99.55 16	99.83 15	99.96 11

No_MVS				99.51 2	99.61 30	98.60 2		97.69 107					99.98 14	99.55 16	99.83 15	99.96 11

fmvsm_s_conf0.5_n_6		96.78 43	96.64 48	97.20 70	96.03 223	93.20 90	99.82 19	97.68 109	95.20 42	99.61 6	99.11 67	84.52 169	99.90 62	99.04 39	98.77 111	98.50 212

testing11		95.33 105	94.98 111	96.37 123	97.20 160	92.31 117	99.29 105	97.68 109	90.59 164	94.43 160	97.20 214	90.79 50	98.60 200	95.25 146	92.38 266	98.18 240

DVP-MVS++		98.18 2	98.09 6	98.44 17	99.61 30	95.38 26	99.55 66	97.68 109	93.01 93	99.23 20	99.45 19	95.12 9	99.98 14	99.25 29	99.92 3	99.97 8

test_0728_SECOND				98.77 9	99.66 18	96.37 15	99.72 38	97.68 109					99.98 14	99.64 8	99.82 19	99.96 11

test11								97.68 109

fmvsm_s_conf0.1_n		95.56 98	95.68 87	95.20 204	94.35 319	89.10 222	99.50 74	97.67 114	94.76 49	98.68 43	99.03 77	81.13 237	99.86 82	98.63 50	97.36 157	96.63 299

testing91		94.88 120	94.44 119	96.21 134	97.19 162	91.90 127	99.23 113	97.66 115	89.91 192	93.66 182	97.05 233	90.21 62	98.50 204	93.52 190	91.53 290	98.25 232

testing99		94.88 120	94.45 118	96.17 139	97.20 160	91.91 126	99.20 115	97.66 115	89.95 191	93.68 181	97.06 231	90.28 61	98.50 204	93.52 190	91.54 287	98.12 247

TEST9					99.57 39	93.17 91	99.38 95	97.66 115	89.57 209	98.39 55	99.18 48	90.88 46	99.66 117

train_agg		97.20 27	97.08 27	97.57 51	99.57 39	93.17 91	99.38 95	97.66 115	90.18 182	98.39 55	99.18 48	90.94 42	99.66 117	98.58 55	99.85 13	99.88 29

region2R		96.30 64	96.17 68	96.70 100	99.70 13	90.31 174	99.46 82	97.66 115	90.55 167	97.07 93	99.07 70	86.85 117	99.97 26	95.43 140	99.74 31	99.81 40

SteuartSystems-ACMMP		97.25 23	97.34 23	97.01 77	97.38 149	91.46 140	99.75 35	97.66 115	94.14 63	98.13 63	99.26 30	92.16 34	99.66 117	97.91 75	99.64 44	99.90 23
Skip Steuart: Steuart Systems R&D Blog.
EPP-MVSNet		93.75 166	93.67 153	94.01 269	95.86 228	85.70 345	98.67 194	97.66 115	84.46 362	91.36 241	97.18 217	91.16 37	97.79 280	92.93 210	93.75 239	98.53 210

fmvsm_s_conf0.5_n_2		95.85 84	95.83 78	95.91 157	97.19 162	91.79 128	99.78 28	97.65 122	97.23 10	99.22 22	99.06 73	75.93 304	99.90 62	99.30 25	97.09 164	96.02 318

SMA-MVS		97.24 24	96.99 28	98.00 33	99.30 60	94.20 64	99.16 122	97.65 122	89.55 211	99.22 22	99.52 11	90.34 60	99.99 9	98.32 66	99.83 15	99.82 37
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
test_one_0601					99.59 34	94.89 39		97.64 124	93.14 92	98.93 33	99.45 19	93.45 20

test_8					99.55 41	93.07 94	99.37 98	97.64 124	90.18 182	98.36 57	99.19 45	90.94 42	99.64 123

agg_prior					99.54 42	92.66 107		97.64 124		97.98 72			99.61 125

DeepC-MVS_fast	93.52 2	97.16 28	96.84 37	98.13 27	99.61 30	94.45 57	98.85 164	97.64 124	96.51 25	95.88 127	99.39 23	87.35 107	99.99 9	96.61 105	99.69 40	99.96 11
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
save fliter					99.34 56	93.85 70	99.65 52	97.63 128	95.69 33

原ACMM1				96.18 137	99.03 79	90.08 184		97.63 128	88.98 232	97.00 95	98.97 83	88.14 91	99.71 113	88.23 273	99.62 50	98.76 180

test-260524					99.74 11	96.14 17		97.62 130		97.79 77		91.57 36	100.00 1	99.55 16	99.75 29

DU-MVS		88.83 312	87.51 320	92.79 301	91.46 400	90.07 185	98.71 184	97.62 130	88.87 238	83.21 338	93.68 332	74.63 316	95.93 391	86.95 287	72.47 430	92.36 346

ZD-MVS					99.67 16	93.28 87		97.61 132	87.78 284	97.41 83	99.16 51	90.15 63	99.56 128	98.35 64	99.70 39

CP-MVS		96.22 66	96.15 71	96.42 118	99.67 16	89.62 205	99.70 41	97.61 132	90.07 189	96.00 123	99.16 51	87.43 101	99.92 50	96.03 123	99.72 34	99.70 62

thisisatest0530		94.00 151	93.52 156	95.43 182	95.76 233	90.02 190	98.99 152	97.60 134	86.58 317	91.74 229	97.36 199	94.78 12	98.34 213	86.37 300	92.48 263	97.94 253

tttt0517		93.30 188	93.01 178	94.17 260	95.57 240	86.47 312	98.51 227	97.60 134	85.99 330	90.55 256	97.19 216	94.80 11	98.31 214	85.06 316	91.86 278	97.74 256

thisisatest0515		94.75 126	94.19 126	96.43 117	96.13 220	92.64 110	99.47 78	97.60 134	87.55 293	93.17 191	97.59 183	94.71 13	98.42 211	88.28 272	93.20 248	98.24 235

testdata				95.26 199	98.20 109	87.28 296		97.60 134	85.21 343	98.48 52	99.15 55	88.15 90	98.72 195	90.29 246	99.45 63	99.78 46

ACMMP_NAP		96.59 52	96.18 65	97.81 41	98.82 93	93.55 81	98.88 163	97.59 138	90.66 159	97.98 72	99.14 58	86.59 126	100.00 1	96.47 109	99.46 61	99.89 28

CVMVSNet		90.30 280	90.91 243	88.46 411	94.32 324	73.58 468	97.61 330	97.59 138	90.16 185	88.43 292	97.10 223	76.83 293	92.86 458	82.64 355	93.54 242	98.93 156

XVS		96.47 58	96.37 57	96.77 93	99.62 28	90.66 165	99.43 89	97.58 140	92.41 112	96.86 98	98.96 88	87.37 103	99.87 76	95.65 130	99.43 65	99.78 46

X-MVStestdata		90.69 267	88.66 298	96.77 93	99.62 28	90.66 165	99.43 89	97.58 140	92.41 112	96.86 98	29.59 538	87.37 103	99.87 76	95.65 130	99.43 65	99.78 46

test222					98.32 104	91.21 144	98.08 292	97.58 140	83.74 373	95.87 128	99.02 79	86.74 120			99.64 44	99.81 40

test_prior				97.01 77	99.58 36	91.77 130		97.57 143					99.49 135			99.79 43

CP-MVSNet		86.54 353	85.45 353	89.79 385	91.02 407	82.78 392	97.38 339	97.56 144	85.37 341	79.53 401	93.03 350	71.86 351	95.25 425	79.92 381	73.43 424	91.34 394

fmvsm_s_conf0.5_n_9		96.76 45	96.92 31	96.29 129	97.95 119	89.21 217	99.81 20	97.55 145	97.04 14	99.68 5	99.22 37	82.84 200	99.94 41	99.56 15	98.61 118	99.71 60

test12				97.83 40	99.33 59	94.45 57		97.55 145		97.56 79		88.60 82	99.50 134		99.71 38	99.55 87

PAPR		96.35 61	95.82 80	97.94 35	99.63 24	94.19 65	99.42 91	97.55 145	92.43 109	93.82 180	99.12 63	87.30 108	99.91 57	94.02 178	99.06 86	99.74 55

AdaColmap		93.82 164	93.06 175	96.10 144	99.88 1	89.07 224	98.33 259	97.55 145	86.81 312	90.39 261	98.65 120	75.09 315	99.98 14	93.32 197	97.53 151	99.26 120

TESTMET0.1,1		93.82 164	93.26 169	95.49 178	95.21 262	90.25 175	99.15 127	97.54 149	89.18 223	91.79 228	94.87 311	89.13 72	97.63 300	86.21 303	96.29 182	98.60 205

fmvsm_s_conf0.1_n_a		95.16 111	95.15 103	95.18 205	92.06 386	88.94 235	99.29 105	97.53 150	94.46 54	98.98 30	98.99 81	79.99 246	99.85 86	98.24 70	96.86 169	96.73 296

hse-mvs2		91.67 241	91.51 227	92.15 318	96.22 209	82.61 397	97.74 319	97.53 150	93.85 74	96.27 120	96.15 279	83.19 192	97.44 313	95.81 128	66.86 459	96.40 311

AUN-MVS		90.17 285	89.50 272	92.19 316	96.21 210	82.67 393	97.76 318	97.53 150	88.05 271	91.67 231	96.15 279	83.10 194	97.47 310	88.11 275	66.91 458	96.43 310

ZNCC-MVS		96.09 70	95.81 82	96.95 85	99.42 53	91.19 145	99.55 66	97.53 150	89.72 200	95.86 129	98.94 94	86.59 126	99.97 26	95.13 149	99.56 56	99.68 67

CANet		97.00 34	96.49 52	98.55 13	98.86 92	96.10 18	99.83 15	97.52 154	95.90 29	97.21 89	98.90 98	82.66 208	99.93 47	98.71 46	98.80 106	99.63 79

APDe-MVS		97.53 17	97.47 18	97.70 45	99.58 36	93.63 76	99.56 65	97.52 154	93.59 83	98.01 71	99.12 63	90.80 49	99.55 129	99.26 27	99.79 27	99.93 21
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MDTV_nov1_ep13			90.47 257		96.14 217	88.55 250	91.34 468	97.51 156	89.58 208	92.24 218	90.50 415	86.99 116	97.61 302	77.64 397	92.34 268

QAPM		91.41 246	89.49 273	97.17 72	95.66 237	93.42 85	98.60 211	97.51 156	80.92 422	81.39 379	97.41 195	72.89 341	99.87 76	82.33 361	98.68 114	98.21 237

PAPM_NR		95.43 101	95.05 108	96.57 111	99.42 53	90.14 181	98.58 217	97.51 156	90.65 161	92.44 215	98.90 98	87.77 97	99.90 62	90.88 238	99.32 70	99.68 67

TSAR-MVS + MP.		97.44 20	97.46 19	97.39 59	99.12 73	93.49 84	98.52 224	97.50 159	94.46 54	98.99 29	98.64 121	91.58 35	99.08 173	98.49 59	99.83 15	99.60 82
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
alignmvs		95.77 89	95.00 110	98.06 31	97.35 151	95.68 22	99.71 40	97.50 159	91.50 134	96.16 122	98.61 125	86.28 135	99.00 176	96.19 114	91.74 281	99.51 93

9.14			96.87 35		99.34 56		99.50 74	97.49 161	89.41 217	98.59 47	99.43 21	89.78 66	99.69 114	98.69 47	99.62 50

GST-MVS		95.97 76	95.66 88	96.90 87	99.49 51	91.22 143	99.45 84	97.48 162	89.69 202	95.89 126	98.72 113	86.37 134	99.95 38	94.62 166	99.22 78	99.52 90

DP-MVS Recon		95.85 84	95.15 103	97.95 34	99.87 2	94.38 60	99.60 61	97.48 162	86.58 317	94.42 161	99.13 60	87.36 106	99.98 14	93.64 187	98.33 131	99.48 98

FOURS1					99.50 48	88.94 235	99.55 66	97.47 164	91.32 141	98.12 65

DVP-MVS		98.07 7	98.00 7	98.29 20	99.66 18	95.20 34	99.72 38	97.47 164	93.95 66	99.07 26	99.46 15	93.18 25	99.97 26	99.64 8	99.82 19	99.69 65
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
CPTT-MVS		94.60 133	94.43 120	95.09 209	99.66 18	86.85 304	99.44 85	97.47 164	83.22 382	94.34 165	98.96 88	82.50 210	99.55 129	94.81 159	99.50 59	98.88 161

BP-MVS1		96.59 52	96.36 58	97.29 64	95.05 282	94.72 50	99.44 85	97.45 167	92.71 104	96.41 116	98.50 131	94.11 17	98.50 204	95.61 135	97.97 138	98.66 200

SF-MVS		97.22 26	96.92 31	98.12 29	99.11 74	94.88 40	99.44 85	97.45 167	89.60 207	98.70 41	99.42 22	90.42 57	99.72 112	98.47 60	99.65 42	99.77 51

MTGPA								97.45 167

MTAPA		96.09 70	95.80 83	96.96 84	99.29 61	91.19 145	97.23 347	97.45 167	92.58 106	94.39 163	99.24 34	86.43 133	99.99 9	96.22 113	99.40 68	99.71 60

CDPH-MVS		96.56 56	96.18 65	97.70 45	99.59 34	93.92 68	99.13 135	97.44 171	89.02 231	97.90 74	99.22 37	88.90 78	99.49 135	94.63 165	99.79 27	99.68 67

APD-MVS		96.95 35	96.72 45	97.63 47	99.51 47	93.58 79	99.16 122	97.44 171	90.08 188	98.59 47	99.07 70	89.06 73	99.42 146	97.92 74	99.66 41	99.88 29
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PVSNet_Blended_VisFu		94.67 131	94.11 129	96.34 125	97.14 167	91.10 150	99.32 104	97.43 173	92.10 123	91.53 237	96.38 274	83.29 188	99.68 115	93.42 196	96.37 177	98.25 232

NR-MVSNet		87.74 335	86.00 344	92.96 297	91.46 400	90.68 164	96.65 373	97.42 174	88.02 273	73.42 448	93.68 332	77.31 287	95.83 399	84.26 328	71.82 437	92.36 346

MP-MVS		96.00 73	95.82 80	96.54 112	99.47 52	90.13 183	99.36 99	97.41 175	90.64 162	95.49 141	98.95 91	85.51 148	99.98 14	96.00 124	99.59 55	99.52 90
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
mPP-MVS		95.90 81	95.75 85	96.38 122	99.58 36	89.41 211	99.26 111	97.41 175	90.66 159	94.82 151	98.95 91	86.15 139	99.98 14	95.24 147	99.64 44	99.74 55

OpenMVS	85.28 14	90.75 265	88.84 293	96.48 114	93.58 354	93.51 83	98.80 171	97.41 175	82.59 396	78.62 412	97.49 190	68.00 382	99.82 95	84.52 326	98.55 124	96.11 315

fmvsm_s_conf0.5_n_5		96.46 59	96.23 62	97.15 73	96.42 198	92.80 104	99.83 15	97.39 178	94.50 52	98.71 40	99.13 60	82.52 209	99.90 62	99.24 31	98.38 129	98.74 182

reproduce-ours		96.66 48	96.80 41	96.22 132	98.95 85	89.03 227	98.62 204	97.38 179	93.42 85	96.80 106	99.36 24	88.92 76	99.80 100	98.51 57	99.26 75	99.82 37

our_new_method		96.66 48	96.80 41	96.22 132	98.95 85	89.03 227	98.62 204	97.38 179	93.42 85	96.80 106	99.36 24	88.92 76	99.80 100	98.51 57	99.26 75	99.82 37

tt0805		86.50 355	84.79 364	91.63 338	91.97 387	81.49 406	96.49 378	97.38 179	82.24 404	82.44 353	95.82 292	51.22 468	98.25 219	84.55 325	80.96 366	95.13 326

SD-MVS		97.51 18	97.40 21	97.81 41	99.01 80	93.79 72	99.33 103	97.38 179	93.73 78	98.83 37	99.02 79	90.87 47	99.88 72	98.69 47	99.74 31	99.77 51
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
tpmvs		89.16 301	87.76 314	93.35 288	97.19 162	84.75 364	90.58 476	97.36 183	81.99 407	84.56 324	89.31 436	83.98 178	98.17 228	74.85 418	90.00 309	97.12 281

PS-CasMVS		85.81 367	84.58 369	89.49 395	90.77 409	82.11 400	97.20 349	97.36 183	84.83 353	79.12 408	92.84 354	67.42 388	95.16 427	78.39 394	73.25 425	91.21 401

0.3-1-1-0.015		91.27 249	89.64 268	96.15 143	92.69 374	91.62 135	99.74 36	97.35 185	84.68 358	92.71 206	93.18 345	85.31 158	97.75 289	92.11 223	68.98 447	99.09 136

0.4-1-1-0.1		91.07 256	89.43 275	96.01 150	92.48 377	91.23 142	99.69 48	97.34 186	84.50 361	92.49 213	92.98 353	84.53 168	97.72 294	91.87 228	68.97 449	99.08 140

0.4-1-1-0.2		91.19 254	89.53 271	96.20 135	92.78 373	91.76 132	99.76 32	97.34 186	84.77 354	92.54 210	93.05 349	84.51 170	97.74 292	92.01 224	68.98 447	99.09 136

reproduce_model		96.57 55	96.75 44	96.02 148	98.93 88	88.46 253	98.56 220	97.34 186	93.18 91	96.96 96	99.35 26	88.69 81	99.80 100	98.53 56	99.21 81	99.79 43

SR-MVS		96.13 69	96.16 70	96.07 145	99.42 53	89.04 225	98.59 214	97.33 189	90.44 171	96.84 100	99.12 63	86.75 119	99.41 149	97.47 83	99.44 64	99.76 53

WB-MVSnew		88.69 318	88.34 306	89.77 386	94.30 330	85.99 337	98.14 280	97.31 190	87.15 302	87.85 295	96.07 283	69.91 362	95.52 415	72.83 437	91.47 291	87.80 460

PatchmatchNet		92.05 233	91.04 238	95.06 212	96.17 214	89.04 225	91.26 469	97.26 191	89.56 210	90.64 253	90.56 411	88.35 85	97.11 325	79.53 382	96.07 189	99.03 144
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
FA-MVS(test-final)		92.22 228	91.08 237	95.64 170	96.05 222	88.98 232	91.60 463	97.25 192	86.99 304	91.84 227	92.12 362	83.03 195	99.00 176	86.91 289	93.91 232	98.93 156

test-LLR		93.11 198	92.68 188	94.40 246	94.94 293	87.27 297	99.15 127	97.25 192	90.21 180	91.57 233	94.04 319	84.89 163	97.58 305	85.94 307	96.13 185	98.36 227

test-mter		93.27 190	92.89 183	94.40 246	94.94 293	87.27 297	99.15 127	97.25 192	88.95 234	91.57 233	94.04 319	88.03 93	97.58 305	85.94 307	96.13 185	98.36 227

PEN-MVS		85.21 376	83.93 379	89.07 404	89.89 419	81.31 412	97.09 354	97.24 195	84.45 363	78.66 411	92.68 357	68.44 377	94.87 432	75.98 410	70.92 441	91.04 405

ab-mvs		91.05 259	89.17 281	96.69 101	95.96 225	91.72 133	92.62 452	97.23 196	85.61 338	89.74 276	93.89 328	68.55 375	99.42 146	91.09 234	87.84 315	98.92 158

APD-MVS_3200maxsize		95.64 97	95.65 90	95.62 174	99.24 66	87.80 271	98.42 241	97.22 197	88.93 236	96.64 113	98.98 82	85.49 149	99.36 153	96.68 102	99.27 74	99.70 62

SR-MVS-dyc-post		95.75 91	95.86 77	95.41 184	99.22 67	87.26 299	98.40 248	97.21 198	89.63 204	96.67 111	98.97 83	86.73 122	99.36 153	96.62 103	99.31 71	99.60 82

RE-MVS-def			95.70 86		99.22 67	87.26 299	98.40 248	97.21 198	89.63 204	96.67 111	98.97 83	85.24 159		96.62 103	99.31 71	99.60 82

SCA		90.64 270	89.25 280	94.83 224	94.95 292	88.83 240	96.26 388	97.21 198	90.06 190	90.03 269	90.62 407	66.61 398	96.81 338	83.16 347	94.36 224	98.84 165

RPMNet		85.07 378	81.88 397	94.64 234	93.47 357	86.24 320	84.97 490	97.21 198	64.85 492	90.76 251	78.80 496	80.95 239	99.27 160	53.76 495	92.17 274	98.41 217

VPNet		88.30 324	86.57 335	93.49 284	91.95 389	91.35 141	98.18 276	97.20 202	88.61 248	84.52 326	94.89 310	62.21 426	96.76 341	89.34 259	72.26 433	92.36 346

KinetiMVS		93.07 200	91.98 214	96.34 125	94.84 299	91.78 129	98.73 183	97.18 203	91.25 143	94.01 173	97.09 227	71.02 358	98.86 182	86.77 293	96.89 168	98.37 224

TranMVSNet+NR-MVSNet		87.75 332	86.31 339	92.07 320	90.81 408	88.56 249	98.33 259	97.18 203	87.76 285	81.87 372	93.90 327	72.45 343	95.43 419	83.13 349	71.30 440	92.23 352

cdsmvs_eth3d_5k		22.52 500	30.03 497	0.00 536	0.00 560	0.00 563	0.00 548	97.17 205	0.00 555	0.00 556	98.77 107	74.35 323	0.00 557	0.00 555	0.00 555	0.00 552

tpm2		91.77 239	91.09 236	93.82 276	94.83 300	85.56 348	92.51 453	97.16 206	84.00 368	93.83 179	90.66 404	87.54 99	97.17 322	87.73 279	91.55 286	98.72 188

MP-MVS-pluss		95.80 87	95.30 97	97.29 64	98.95 85	92.66 107	98.59 214	97.14 207	88.95 234	93.12 192	99.25 32	85.62 145	99.94 41	96.56 107	99.48 60	99.28 118
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
PatchMatch-RL		91.47 244	90.54 254	94.26 254	98.20 109	86.36 317	96.94 359	97.14 207	87.75 286	88.98 285	95.75 293	71.80 352	99.40 150	80.92 374	97.39 156	97.02 287

Anonymous20240529		87.66 336	85.58 350	93.92 272	97.59 136	85.01 359	98.13 281	97.13 209	66.69 489	88.47 291	96.01 285	55.09 454	99.51 133	87.00 286	84.12 342	97.23 280

JIA-IIPM		85.97 363	84.85 362	89.33 398	93.23 364	73.68 467	85.05 489	97.13 209	69.62 480	91.56 235	68.03 511	88.03 93	96.96 331	77.89 396	93.12 249	97.34 273

PS-MVSNAJ		96.87 38	96.40 56	98.29 20	97.35 151	97.29 6	99.03 147	97.11 211	95.83 30	98.97 31	99.14 58	82.48 212	99.60 126	98.60 51	99.08 83	98.00 250

HPM-MVS_fast		94.89 118	94.62 115	95.70 166	99.11 74	88.44 254	99.14 130	97.11 211	85.82 334	95.69 136	98.47 138	83.46 184	99.32 158	93.16 205	99.63 49	99.35 111

DeepC-MVS	91.02 4	94.56 136	93.92 140	96.46 115	97.16 166	90.76 161	98.39 253	97.11 211	93.92 68	88.66 289	98.33 143	78.14 280	99.85 86	95.02 152	98.57 122	98.78 176
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
tpmrst		92.78 209	92.16 209	94.65 232	96.27 207	87.45 290	91.83 459	97.10 214	89.10 230	94.68 157	90.69 402	88.22 87	97.73 293	89.78 252	91.80 280	98.77 178

HPM-MVS		95.41 103	95.22 101	95.99 152	99.29 61	89.14 221	99.17 121	97.09 215	87.28 299	95.40 142	98.48 137	84.93 162	99.38 151	95.64 134	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		88.89 308	87.27 325	93.76 279	95.79 231	85.32 353	90.76 474	97.09 215	76.14 449	85.72 316	88.59 439	82.92 197	98.04 258	76.96 401	91.43 292	97.90 254

dp		90.16 286	88.83 294	94.14 261	96.38 203	86.42 313	91.57 464	97.06 217	84.76 355	88.81 286	90.19 424	84.29 174	97.43 314	75.05 415	91.35 296	98.56 208

xiu_mvs_v2_base		96.66 48	96.17 68	98.11 30	97.11 171	96.96 7	99.01 150	97.04 218	95.51 38	98.86 35	99.11 67	82.19 220	99.36 153	98.59 54	98.14 136	98.00 250

3Dnovator+	87.72 8	93.43 181	91.84 219	98.17 25	95.73 234	95.08 37	98.92 159	97.04 218	91.42 138	81.48 378	97.60 182	74.60 318	99.79 104	90.84 239	98.97 92	99.64 76

sd_testset		89.23 300	88.05 313	92.74 304	96.80 183	85.33 352	95.85 406	97.03 220	88.34 261	85.73 314	95.26 306	61.12 431	97.76 288	85.61 311	86.75 320	95.14 324

CDS-MVSNet		93.47 177	93.04 177	94.76 226	94.75 304	89.45 209	98.82 167	97.03 220	87.91 277	90.97 246	96.48 269	89.06 73	96.36 361	89.50 255	92.81 254	98.49 213
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test0.0.03 1		88.96 306	88.61 299	90.03 380	91.09 405	84.43 367	98.97 155	97.02 222	90.21 180	80.29 390	96.31 276	84.89 163	91.93 473	72.98 434	85.70 331	93.73 332

114514_t		94.06 149	93.05 176	97.06 75	99.08 77	92.26 119	98.97 155	97.01 223	82.58 397	92.57 209	98.22 148	80.68 241	99.30 159	89.34 259	99.02 89	99.63 79

CostFormer		92.89 204	92.48 196	94.12 262	94.99 287	85.89 340	92.89 448	97.00 224	86.98 307	95.00 150	90.78 398	90.05 64	97.51 309	92.92 212	91.73 282	98.96 150

test_fmvsmvis_n_1920		95.47 100	95.40 95	95.70 166	94.33 323	90.22 178	99.70 41	96.98 225	96.80 16	92.75 204	98.89 100	82.46 215	99.92 50	98.36 63	98.33 131	96.97 289

ET-MVSNet_ETH3D		92.56 218	91.45 228	95.88 158	96.39 202	94.13 66	99.46 82	96.97 226	92.18 120	66.94 480	98.29 146	94.65 15	94.28 442	94.34 172	83.82 346	99.24 121

UA-Net		93.30 188	92.62 192	95.34 189	96.27 207	88.53 252	95.88 403	96.97 226	90.90 150	95.37 143	97.07 230	82.38 217	99.10 172	83.91 338	94.86 215	98.38 221

TAMVS		92.62 215	92.09 212	94.20 259	94.10 332	87.68 274	98.41 244	96.97 226	87.53 294	89.74 276	96.04 284	84.77 167	96.49 354	88.97 267	92.31 269	98.42 216

kuosan		84.40 389	83.34 383	87.60 418	95.87 227	79.21 430	92.39 454	96.87 229	76.12 450	73.79 445	93.98 324	81.51 228	90.63 480	64.13 473	75.42 397	92.95 337

guyue		94.21 145	93.72 152	95.66 169	95.22 260	90.17 180	98.74 180	96.85 230	93.67 79	93.01 197	96.72 260	78.83 268	98.06 252	96.04 122	94.44 222	98.77 178

test_fmvsmconf0.1_n		95.94 79	95.79 84	96.40 120	92.42 379	89.92 192	99.79 27	96.85 230	96.53 24	97.22 88	98.67 119	82.71 206	99.84 88	98.92 44	98.98 91	99.43 104

dongtai		81.36 415	80.61 407	83.62 454	94.25 331	73.32 469	95.15 418	96.81 232	73.56 467	69.79 465	92.81 355	81.00 238	86.80 499	52.08 500	70.06 443	90.75 415

Vis-MVSNet		92.64 214	91.85 218	95.03 215	95.12 270	88.23 259	98.48 232	96.81 232	91.61 129	92.16 221	97.22 213	71.58 355	98.00 264	85.85 310	97.81 141	98.88 161
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PMMVS		93.62 173	93.90 143	92.79 301	96.79 185	81.40 409	98.85 164	96.81 232	91.25 143	96.82 104	98.15 152	77.02 292	98.13 233	93.15 207	96.30 180	98.83 168

ADS-MVSNet		88.99 305	87.30 324	94.07 264	96.21 210	87.56 286	87.15 482	96.78 235	83.01 386	89.91 272	87.27 451	78.87 266	97.01 330	74.20 423	92.27 270	97.64 262

BridgeMVS		96.83 39	96.51 51	97.81 41	97.60 135	95.15 36	98.40 248	96.77 236	93.00 95	98.69 42	96.19 278	89.75 67	98.76 190	98.45 61	99.72 34	99.51 93

MVSMamba_PlusPlus		95.73 94	95.15 103	97.44 53	97.28 157	94.35 62	98.26 268	96.75 237	83.09 385	97.84 75	95.97 286	89.59 69	98.48 209	97.86 76	99.73 33	99.49 97

WBMVS		91.35 248	90.49 255	93.94 271	96.97 177	93.40 86	99.27 110	96.71 238	87.40 297	83.10 343	91.76 374	92.38 31	96.23 375	88.95 268	77.89 382	92.17 356

Vis-MVSNet (Re-imp)		93.26 191	93.00 180	94.06 266	96.14 217	86.71 307	98.68 191	96.70 239	88.30 263	89.71 278	97.64 180	85.43 152	96.39 359	88.06 276	96.32 178	99.08 140

Anonymous20231211		84.72 381	82.65 393	90.91 351	97.71 128	84.55 366	97.28 343	96.67 240	66.88 488	79.18 407	90.87 397	58.47 439	96.60 345	82.61 356	74.20 412	91.59 378

Syy-MVS		84.10 394	84.53 370	82.83 458	95.14 268	65.71 490	97.68 323	96.66 241	86.52 320	82.63 348	96.84 253	68.15 379	89.89 484	45.62 507	91.54 287	92.87 338

myMVS_eth3d		88.68 320	89.07 286	87.50 420	95.14 268	79.74 426	97.68 323	96.66 241	86.52 320	82.63 348	96.84 253	85.22 160	89.89 484	69.43 453	91.54 287	92.87 338

SSC-MVS3.2		85.22 375	83.90 380	89.17 401	91.87 392	79.84 425	97.66 326	96.63 243	86.81 312	81.99 367	91.35 385	55.80 447	96.00 386	76.52 407	76.53 393	91.67 369

EIA-MVS		95.11 112	95.27 99	94.64 234	96.34 204	86.51 310	99.59 62	96.62 244	92.51 107	94.08 170	98.64 121	86.05 140	98.24 220	95.07 151	98.50 125	99.18 126

ETV-MVS		96.00 73	96.00 73	96.00 151	96.56 190	91.05 153	99.63 59	96.61 245	93.26 90	97.39 84	98.30 145	86.62 125	98.13 233	98.07 72	97.57 148	98.82 169

usedtu_dtu_shiyan1		89.12 302	87.56 318	93.78 277	89.74 422	93.60 77	98.70 187	96.60 246	87.85 279	83.43 335	91.56 379	76.34 300	95.92 393	82.75 352	81.08 363	91.82 365

FE-MVSNET3		89.12 302	87.56 318	93.78 277	89.74 422	93.60 77	98.70 187	96.60 246	87.85 279	83.43 335	91.56 379	76.34 300	95.92 393	82.75 352	81.08 363	91.82 365

LS3D		90.19 283	88.72 296	94.59 240	98.97 81	86.33 318	96.90 361	96.60 246	74.96 461	84.06 331	98.74 110	75.78 308	99.83 92	74.93 416	97.57 148	97.62 266

EI-MVSNet		89.87 291	89.38 277	91.36 343	94.32 324	85.87 341	97.61 330	96.59 249	85.10 345	85.51 318	97.10 223	81.30 235	96.56 348	83.85 340	83.03 353	91.64 371

MVSTER		92.71 211	92.32 199	93.86 274	97.29 155	92.95 101	99.01 150	96.59 249	90.09 187	85.51 318	94.00 323	94.61 16	96.56 348	90.77 242	83.03 353	92.08 360

cascas		90.93 262	89.33 278	95.76 163	95.69 235	93.03 96	98.99 152	96.59 249	80.49 424	86.79 309	94.45 316	65.23 411	98.60 200	93.52 190	92.18 273	95.66 323

TAPA-MVS	87.50 9	90.35 277	89.05 287	94.25 255	98.48 103	85.17 356	98.42 241	96.58 252	82.44 402	87.24 302	98.53 127	82.77 202	98.84 184	59.09 487	97.88 140	98.72 188
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
OMC-MVS		93.90 158	93.62 154	94.73 229	98.63 99	87.00 302	98.04 298	96.56 253	92.19 119	92.46 214	98.73 111	79.49 256	99.14 170	92.16 222	94.34 226	98.03 249

PLC	91.07 3	94.23 144	94.01 132	94.87 220	99.17 71	87.49 288	99.25 112	96.55 254	88.43 257	91.26 242	98.21 150	85.92 141	99.86 82	89.77 253	97.57 148	97.24 279
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TSAR-MVS + GP.		96.95 35	96.91 33	97.07 74	98.88 91	91.62 135	99.58 63	96.54 255	95.09 44	96.84 100	98.63 123	91.16 37	99.77 108	99.04 39	96.42 176	99.81 40

cl22		89.57 297	88.79 295	91.91 322	97.94 120	87.62 283	97.98 302	96.51 256	85.03 348	82.37 357	91.79 371	83.65 180	96.50 352	85.96 306	77.89 382	91.61 376

xiu_mvs_v1_base_debu		94.73 127	93.98 134	96.99 79	95.19 263	95.24 29	98.62 204	96.50 257	92.99 96	97.52 80	98.83 104	72.37 344	99.15 166	97.03 91	96.74 170	96.58 302

xiu_mvs_v1_base		94.73 127	93.98 134	96.99 79	95.19 263	95.24 29	98.62 204	96.50 257	92.99 96	97.52 80	98.83 104	72.37 344	99.15 166	97.03 91	96.74 170	96.58 302

xiu_mvs_v1_base_debi		94.73 127	93.98 134	96.99 79	95.19 263	95.24 29	98.62 204	96.50 257	92.99 96	97.52 80	98.83 104	72.37 344	99.15 166	97.03 91	96.74 170	96.58 302

lupinMVS		96.32 63	95.94 74	97.44 53	95.05 282	94.87 41	99.86 9	96.50 257	93.82 76	98.04 69	98.77 107	85.52 146	98.09 242	96.98 94	98.97 92	99.37 108

fmvsm_s_conf0.5_n_11		96.80 41	96.97 29	96.28 130	98.09 114	92.26 119	99.87 6	96.49 261	97.55 4	99.75 3	99.32 28	83.20 191	99.91 57	99.57 13	98.88 100	96.67 298

mvs_anonymous		92.50 219	91.65 224	95.06 212	96.60 189	89.64 204	97.06 355	96.44 262	86.64 316	84.14 329	93.93 326	82.49 211	96.17 379	91.47 231	96.08 188	99.35 111

GDP-MVS		96.05 72	95.63 92	97.31 63	95.37 254	94.65 53	99.36 99	96.42 263	92.14 122	97.07 93	98.53 127	93.33 21	98.50 204	91.76 230	96.66 173	98.78 176

VDDNet		90.08 288	88.54 304	94.69 231	94.41 317	87.68 274	98.21 274	96.40 264	76.21 448	93.33 190	97.75 167	54.93 456	98.77 187	94.71 163	90.96 299	97.61 267

NormalMVS		95.87 82	95.83 78	95.99 152	99.27 63	90.37 171	99.14 130	96.39 265	94.92 45	96.30 118	97.98 155	85.33 156	99.23 161	94.35 170	98.82 103	98.37 224

Elysia		90.62 271	88.95 289	95.64 170	93.08 367	91.94 124	97.65 327	96.39 265	84.72 356	90.59 254	95.95 287	62.22 424	98.23 221	83.69 341	96.23 183	96.74 294

StellarMVS		90.62 271	88.95 289	95.64 170	93.08 367	91.94 124	97.65 327	96.39 265	84.72 356	90.59 254	95.95 287	62.22 424	98.23 221	83.69 341	96.23 183	96.74 294

mvsmamba		94.27 143	93.91 142	95.35 188	96.42 198	88.61 247	97.77 315	96.38 268	91.17 146	94.05 171	95.27 305	78.41 277	97.96 266	97.36 86	98.40 128	99.48 98

HQP3-MVS								96.37 269							86.29 323

PatchT		85.44 373	83.19 384	92.22 314	93.13 366	83.00 385	83.80 496	96.37 269	70.62 473	90.55 256	79.63 493	84.81 165	94.87 432	58.18 489	91.59 284	98.79 173

HQP-MVS		91.50 243	91.23 233	92.29 313	93.95 337	86.39 315	99.16 122	96.37 269	93.92 68	87.57 297	96.67 263	73.34 332	97.77 282	93.82 185	86.29 323	92.72 340

UnsupCasMVSNet_eth		78.90 429	76.67 434	85.58 441	82.81 483	74.94 461	91.98 458	96.31 272	84.64 359	65.84 486	87.71 444	51.33 467	92.23 468	72.89 436	56.50 493	89.56 441

HQP_MVS		91.26 250	90.95 242	92.16 317	93.84 345	86.07 334	99.02 148	96.30 273	93.38 88	86.99 304	96.52 266	72.92 339	97.75 289	93.46 194	86.17 326	92.67 342

plane_prior5								96.30 273					97.75 289	93.46 194	86.17 326	92.67 342

jason		95.40 104	94.86 112	97.03 76	92.91 370	94.23 63	99.70 41	96.30 273	93.56 84	96.73 109	98.52 129	81.46 232	97.91 268	96.08 121	98.47 127	98.96 150
jason: jason.
CLD-MVS		91.06 258	90.71 250	92.10 319	94.05 336	86.10 331	99.55 66	96.29 276	94.16 61	84.70 323	97.17 218	69.62 367	97.82 276	94.74 161	86.08 328	92.39 345
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GA-MVS		90.10 287	88.69 297	94.33 250	92.44 378	87.97 267	99.08 140	96.26 277	89.65 203	86.92 306	93.11 348	68.09 380	96.96 331	82.54 357	90.15 306	98.05 248

DTE-MVSNet		84.14 392	82.80 388	88.14 413	88.95 435	79.87 424	96.81 364	96.24 278	83.50 378	77.60 425	92.52 359	67.89 384	94.24 443	72.64 438	69.05 446	90.32 425

LFMVS		92.23 227	90.84 246	96.42 118	98.24 108	91.08 152	98.24 271	96.22 279	83.39 380	94.74 155	98.31 144	61.12 431	98.85 183	94.45 168	92.82 252	99.32 114

LuminaMVS		93.16 195	92.30 200	95.76 163	92.26 381	92.64 110	97.60 332	96.21 280	90.30 177	93.06 194	95.59 296	76.00 303	97.89 270	94.93 158	94.70 216	96.76 293

balanced_ft_v1		94.96 117	94.35 121	96.78 92	97.54 139	92.05 122	98.03 299	96.20 281	90.90 150	96.83 102	95.51 298	76.75 294	98.77 187	98.68 49	98.70 113	99.52 90

baseline1		92.61 216	91.28 232	96.58 109	97.05 175	94.63 54	97.72 320	96.20 281	89.82 196	88.56 290	96.85 250	86.85 117	97.82 276	88.42 270	80.10 372	97.30 276

FMVSNet3		88.81 314	87.08 328	93.99 270	96.52 193	94.59 55	98.08 292	96.20 281	85.85 333	82.12 361	91.60 377	74.05 327	95.40 421	79.04 386	80.24 369	91.99 363

sasdasda		95.02 115	93.96 137	98.20 23	97.53 140	95.92 19	98.71 184	96.19 284	91.78 126	95.86 129	98.49 134	79.53 254	99.03 174	96.12 118	91.42 293	99.66 71

canonicalmvs		95.02 115	93.96 137	98.20 23	97.53 140	95.92 19	98.71 184	96.19 284	91.78 126	95.86 129	98.49 134	79.53 254	99.03 174	96.12 118	91.42 293	99.66 71

fmvsm_s_conf0.1_n_2		95.24 109	95.04 109	95.83 160	95.60 238	91.71 134	99.65 52	96.18 286	96.99 15	98.79 38	98.91 96	73.91 329	99.87 76	99.00 41	96.30 180	95.91 320

dmvs_re		88.69 318	88.06 312	90.59 361	93.83 347	78.68 436	95.75 409	96.18 286	87.99 274	84.48 327	96.32 275	67.52 386	96.94 333	84.98 318	85.49 332	96.14 314

MVSFormer		94.71 130	94.08 131	96.61 106	95.05 282	94.87 41	97.77 315	96.17 288	86.84 310	98.04 69	98.52 129	85.52 146	95.99 387	89.83 249	98.97 92	98.96 150

test_djsdf		88.26 326	87.73 315	89.84 383	88.05 446	82.21 399	97.77 315	96.17 288	86.84 310	82.41 356	91.95 370	72.07 348	95.99 387	89.83 249	84.50 338	91.32 395

MS-PatchMatch		86.75 348	85.92 345	89.22 399	91.97 387	82.47 398	96.91 360	96.14 290	83.74 373	77.73 424	93.53 338	58.19 440	97.37 318	76.75 404	98.35 130	87.84 458

CS-MVS		95.75 91	96.19 63	94.40 246	97.88 122	86.22 322	99.66 50	96.12 291	92.69 105	98.07 67	98.89 100	87.09 111	97.59 303	96.71 100	98.62 117	99.39 107

E3new		94.19 146	93.78 150	95.43 182	95.81 230	89.44 210	98.80 171	96.11 292	90.24 179	93.85 177	97.75 167	80.94 240	98.14 230	95.00 154	95.48 201	98.72 188

viewcassd2359sk11		93.95 155	93.48 159	95.36 185	95.48 246	89.25 216	98.74 180	96.10 293	90.10 186	93.48 186	97.55 186	80.05 245	98.14 230	94.66 164	95.16 206	98.69 192

MGCFI-Net		94.89 118	93.84 147	98.06 31	97.49 143	95.55 23	98.64 198	96.10 293	91.60 132	95.75 134	98.46 140	79.31 258	98.98 178	95.95 125	91.24 298	99.65 75

SPE-MVS-test		95.98 75	96.34 59	94.90 219	98.06 116	87.66 277	99.69 48	96.10 293	93.66 80	98.35 58	99.05 75	86.28 135	97.66 297	96.96 95	98.90 99	99.37 108

VDD-MVS		91.24 253	90.18 259	94.45 245	97.08 172	85.84 343	98.40 248	96.10 293	86.99 304	93.36 189	98.16 151	54.27 458	99.20 163	96.59 106	90.63 304	98.31 230

PCF-MVS	89.78 5	91.26 250	89.63 269	96.16 142	95.44 248	91.58 139	95.29 416	96.10 293	85.07 347	82.75 345	97.45 193	78.28 279	99.78 107	80.60 378	95.65 196	97.12 281
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
E2		93.62 173	93.07 173	95.26 199	95.00 286	88.99 231	98.63 200	96.09 298	89.84 194	93.02 195	97.36 199	78.88 264	98.11 237	94.23 175	94.60 218	98.67 195

E3		93.62 173	93.07 173	95.26 199	94.98 288	89.00 230	98.63 200	96.09 298	89.83 195	93.01 197	97.35 201	78.90 263	98.11 237	94.23 175	94.60 218	98.67 195

test_cas_vis1_n_1920		93.86 163	93.74 151	94.22 258	95.39 252	86.08 332	99.73 37	96.07 300	96.38 26	97.19 91	97.78 164	65.46 409	99.86 82	96.71 100	98.92 97	96.73 296

test_vis1_n_1920		93.08 199	93.42 161	92.04 321	96.31 205	79.36 428	99.83 15	96.06 301	96.72 18	98.53 51	98.10 153	58.57 438	99.91 57	97.86 76	98.79 109	96.85 291

MVS_Test		93.67 170	92.67 189	96.69 101	96.72 187	92.66 107	97.22 348	96.03 302	87.69 290	95.12 148	94.03 321	81.55 227	98.28 217	89.17 265	96.46 174	99.14 129

viewmanbaseed2359cas		93.90 158	93.34 165	95.56 177	95.39 252	89.72 201	98.58 217	96.00 303	90.32 176	93.58 184	97.78 164	78.71 272	98.07 249	94.43 169	95.29 203	98.88 161

E4		93.15 197	92.50 195	95.09 209	94.41 317	88.61 247	98.48 232	95.99 304	89.40 218	92.22 219	97.13 220	77.43 286	98.10 240	93.58 189	93.90 233	98.56 208

casdiffmvs_mvg		94.00 151	93.33 166	96.03 147	95.22 260	90.90 159	99.09 139	95.99 304	90.58 165	91.55 236	97.37 198	79.91 247	98.06 252	95.01 153	95.22 205	99.13 131
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		87.35 339	86.51 337	89.87 381	87.75 453	81.74 404	97.03 356	95.98 306	88.47 251	80.15 392	93.80 330	61.47 428	96.36 361	89.44 257	84.47 339	91.50 380

E5new		92.80 205	92.19 204	94.62 236	94.34 320	87.64 278	98.08 292	95.97 307	89.15 224	92.01 223	97.08 228	76.37 298	98.08 244	93.25 200	93.46 243	98.15 242

E6new		92.80 205	92.19 204	94.62 236	94.31 328	87.64 278	98.08 292	95.97 307	89.15 224	92.01 223	97.10 223	76.38 296	98.08 244	93.25 200	93.45 245	98.15 242

E6		92.80 205	92.19 204	94.62 236	94.31 328	87.64 278	98.08 292	95.97 307	89.15 224	92.01 223	97.10 223	76.38 296	98.08 244	93.25 200	93.45 245	98.15 242

E5		92.80 205	92.19 204	94.62 236	94.34 320	87.64 278	98.08 292	95.97 307	89.15 224	92.01 223	97.08 228	76.37 298	98.08 244	93.25 200	93.46 243	98.15 242

PS-MVSNAJss		89.54 298	89.05 287	91.00 349	88.77 436	84.36 368	97.39 337	95.97 307	88.47 251	81.88 370	93.80 330	82.48 212	96.50 352	89.34 259	83.34 352	92.15 357

F-COLMAP		92.07 232	91.75 223	93.02 294	98.16 112	82.89 389	98.79 176	95.97 307	86.54 319	87.92 294	97.80 162	78.69 273	99.65 121	85.97 305	95.93 191	96.53 305

miper_enhance_ethall		90.33 278	89.70 265	92.22 314	97.12 170	88.93 237	98.35 258	95.96 313	88.60 249	83.14 342	92.33 361	87.38 102	96.18 377	86.49 299	77.89 382	91.55 379

TR-MVS		90.77 264	89.44 274	94.76 226	96.31 205	88.02 265	97.92 304	95.96 313	85.52 339	88.22 293	97.23 212	66.80 395	98.09 242	84.58 324	92.38 266	98.17 241

CMPMVS	58.40 21	80.48 419	80.11 417	81.59 465	85.10 469	59.56 498	94.14 433	95.95 315	68.54 483	60.71 492	93.31 341	55.35 453	97.87 273	83.06 350	84.85 336	87.33 465
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
VortexMVS		90.18 284	89.28 279	92.89 299	95.58 239	90.94 158	97.82 310	95.94 316	90.90 150	82.11 365	91.48 382	78.75 271	96.08 383	91.99 225	78.97 376	91.65 370

test_fmvsmconf0.01_n		94.14 147	93.51 158	96.04 146	86.79 459	89.19 218	99.28 108	95.94 316	95.70 32	95.50 140	98.49 134	73.27 335	99.79 104	98.28 68	98.32 133	99.15 128

LPG-MVS_test		88.86 309	88.47 305	90.06 376	93.35 362	80.95 418	98.22 272	95.94 316	87.73 288	83.17 340	96.11 281	66.28 402	97.77 282	90.19 247	85.19 333	91.46 383

LGP-MVS_train				90.06 376	93.35 362	80.95 418		95.94 316	87.73 288	83.17 340	96.11 281	66.28 402	97.77 282	90.19 247	85.19 333	91.46 383

OPM-MVS		89.76 294	89.15 285	91.57 339	90.53 411	85.58 347	98.11 285	95.93 320	92.88 101	86.05 311	96.47 270	67.06 391	97.87 273	89.29 262	86.08 328	91.26 398
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Casviewmamba		93.63 172	93.20 170	94.94 217	95.12 270	87.64 278	98.76 178	95.92 321	90.44 171	92.12 222	97.90 158	79.15 260	98.16 229	93.89 180	95.52 198	99.00 145

viewdifsd2359ckpt13		93.45 178	92.86 184	95.21 202	95.45 247	88.91 239	98.59 214	95.92 321	89.39 219	92.67 208	97.33 203	78.02 282	98.03 259	93.27 199	95.12 208	98.69 192

XVG-OURS-SEG-HR		90.95 261	90.66 253	91.83 324	95.18 266	81.14 416	95.92 400	95.92 321	88.40 258	90.33 262	97.85 159	70.66 361	99.38 151	92.83 213	88.83 312	94.98 327

XVG-OURS		90.83 263	90.49 255	91.86 323	95.23 259	81.25 413	95.79 408	95.92 321	88.96 233	90.02 270	98.03 154	71.60 354	99.35 156	91.06 235	87.78 316	94.98 327

tpm		89.67 295	88.95 289	91.82 326	92.54 376	81.43 408	92.95 447	95.92 321	87.81 283	90.50 258	89.44 433	84.99 161	95.65 411	83.67 343	82.71 356	98.38 221

EC-MVSNet		95.09 113	95.17 102	94.84 223	95.42 249	88.17 260	99.48 76	95.92 321	91.47 135	97.34 86	98.36 142	82.77 202	97.41 315	97.24 88	98.58 121	98.94 155

ACMM	86.95 13	88.77 315	88.22 309	90.43 367	93.61 353	81.34 411	98.50 228	95.92 321	87.88 278	83.85 332	95.20 308	67.20 389	97.89 270	86.90 290	84.90 335	92.06 361
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline		93.91 157	93.30 167	95.72 165	95.10 279	90.07 185	97.48 334	95.91 328	91.03 147	93.54 185	97.68 175	79.58 251	98.02 261	94.27 173	95.14 207	99.08 140

mvs_tets		87.09 342	86.22 340	89.71 387	87.87 449	81.39 410	96.73 370	95.90 329	88.19 267	79.99 394	93.61 335	59.96 435	96.31 369	89.40 258	84.34 340	91.43 385

XXY-MVS		87.75 332	86.02 343	92.95 298	90.46 413	89.70 203	97.71 322	95.90 329	84.02 367	80.95 381	94.05 318	67.51 387	97.10 327	85.16 314	78.41 379	92.04 362

nrg030		90.23 281	88.87 292	94.32 251	91.53 399	93.54 82	98.79 176	95.89 331	88.12 269	84.55 325	94.61 315	78.80 269	96.88 335	92.35 221	75.21 399	92.53 344

CNLPA		93.64 171	92.74 187	96.36 124	98.96 84	90.01 191	99.19 116	95.89 331	86.22 325	89.40 282	98.85 103	80.66 242	99.84 88	88.57 269	96.92 167	99.24 121

KD-MVS_2432*1600		82.98 405	80.52 409	90.38 369	94.32 324	88.98 232	92.87 449	95.87 333	80.46 425	73.79 445	87.49 448	82.76 204	93.29 455	70.56 448	46.53 507	88.87 453

miper_refine_blended		82.98 405	80.52 409	90.38 369	94.32 324	88.98 232	92.87 449	95.87 333	80.46 425	73.79 445	87.49 448	82.76 204	93.29 455	70.56 448	46.53 507	88.87 453

AstraMVS		93.38 185	93.01 178	94.50 241	93.94 340	86.55 308	98.91 160	95.86 335	93.88 72	92.88 200	97.49 190	75.61 312	98.21 223	96.15 117	92.39 265	98.73 187

FMVSNet2		86.90 344	84.79 364	93.24 290	95.11 276	92.54 113	97.67 325	95.86 335	82.94 389	80.55 385	91.17 390	62.89 421	95.29 424	77.23 398	79.71 375	91.90 364

hybridcas		93.44 179	92.82 186	95.31 193	94.91 296	89.08 223	98.82 167	95.84 337	90.28 178	91.22 244	97.65 179	78.39 278	98.06 252	92.71 215	95.55 197	98.79 173

viewmacassd2359aftdt		93.16 195	92.44 197	95.31 193	94.34 320	89.19 218	98.40 248	95.84 337	89.62 206	92.87 202	97.31 204	76.07 302	98.00 264	92.93 210	94.58 220	98.75 181

casdiffmvs		93.98 153	93.43 160	95.61 175	95.07 281	89.86 195	98.80 171	95.84 337	90.98 148	92.74 205	97.66 177	79.71 249	98.10 240	94.72 162	95.37 202	98.87 164
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		94.12 148	93.87 145	94.86 222	95.26 257	87.86 269	98.60 211	95.82 340	90.70 157	95.67 137	97.72 173	79.72 248	98.13 233	96.37 110	94.99 211	98.60 205

viewdifsd2359ckpt07		92.71 211	92.19 204	94.28 252	94.96 291	86.26 319	98.29 266	95.80 341	88.71 246	90.81 248	97.34 202	76.57 295	98.19 225	93.16 205	94.05 230	98.39 220

UniMVSNet_ETH3D		85.65 372	83.79 381	91.21 344	90.41 414	80.75 421	95.36 414	95.78 342	78.76 434	81.83 375	94.33 317	49.86 474	96.66 343	84.30 327	83.52 350	96.22 313

Effi-MVS+		93.87 162	93.15 172	96.02 148	95.79 231	90.76 161	96.70 371	95.78 342	86.98 307	95.71 135	97.17 218	79.58 251	98.01 262	94.57 167	96.09 187	99.31 115

gbinet_0.2-2-1-0.02		83.16 404	80.42 413	91.39 342	83.70 475	87.60 284	98.62 204	95.77 344	75.83 451	79.33 404	87.92 442	64.07 415	95.34 422	81.87 368	56.67 491	91.25 399

RRT-MVS		93.39 183	92.64 190	95.64 170	96.11 221	88.75 244	97.40 336	95.77 344	89.46 215	92.70 207	95.42 302	72.98 338	98.81 185	96.91 97	96.97 165	99.37 108

EU-MVSNet		84.19 391	84.42 373	83.52 456	88.64 439	67.37 489	96.04 398	95.76 346	85.29 342	78.44 419	93.18 345	70.67 360	91.48 476	75.79 412	75.98 394	91.70 368

BH-w/o		92.32 223	91.79 221	93.91 273	96.85 180	86.18 328	99.11 138	95.74 347	88.13 268	84.81 322	97.00 235	77.26 288	97.91 268	89.16 266	98.03 137	97.64 262

icg_test_0407_2		91.56 242	90.90 244	93.54 283	94.61 310	86.22 322	95.72 410	95.72 348	88.78 240	89.76 274	96.93 241	77.24 289	95.65 411	86.73 294	92.59 258	98.74 182

IMVS_0407		91.79 238	90.98 240	94.24 257	94.61 310	86.22 322	96.45 379	95.72 348	88.78 240	89.76 274	96.93 241	77.24 289	97.77 282	86.73 294	92.59 258	98.74 182

IMVS_0404		89.79 293	88.57 302	93.47 285	94.61 310	86.22 322	94.45 424	95.72 348	88.78 240	81.88 370	96.93 241	65.39 410	95.47 417	86.73 294	92.59 258	98.74 182

IMVS_0403		91.93 235	91.13 235	94.34 249	94.61 310	86.22 322	96.70 371	95.72 348	88.78 240	90.00 271	96.93 241	78.07 281	98.07 249	86.73 294	92.59 258	98.74 182

anonymousdsp		86.69 349	85.75 348	89.53 392	86.46 462	82.94 386	96.39 381	95.71 352	83.97 369	79.63 399	90.70 401	68.85 373	95.94 390	86.01 304	84.02 343	89.72 438

hybrid		93.89 160	93.41 162	95.33 191	94.98 288	89.30 214	98.58 217	95.70 353	89.70 201	94.76 153	97.54 187	78.98 262	98.07 249	95.52 139	94.92 212	98.61 203

Fast-Effi-MVS+		91.72 240	90.79 249	94.49 242	95.89 226	87.40 292	99.54 71	95.70 353	85.01 350	89.28 284	95.68 295	77.75 284	97.57 308	83.22 346	95.06 210	98.51 211

IS-MVSNet		93.00 203	92.51 194	94.49 242	96.14 217	87.36 293	98.31 262	95.70 353	88.58 250	90.17 265	97.50 189	83.02 196	97.22 321	87.06 284	96.07 189	98.90 160

viewmambaseed2359dif		93.05 202	92.64 190	94.25 255	94.94 293	86.53 309	98.38 255	95.69 356	87.03 303	93.38 188	97.74 170	78.79 270	98.08 244	93.49 193	94.35 225	98.15 242

diffmvs_AUTHOR		94.30 142	93.92 140	95.45 179	94.77 303	89.92 192	98.55 223	95.68 357	91.33 140	95.83 132	97.64 180	79.58 251	98.05 256	96.19 114	95.66 195	98.37 224

diffmvs		94.59 134	94.19 126	95.81 161	95.54 243	90.69 163	98.70 187	95.68 357	91.61 129	95.96 124	97.81 161	80.11 244	98.06 252	96.52 108	95.76 192	98.67 195
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		91.84 237	90.69 251	95.28 197	94.50 315	89.32 213	98.31 262	95.67 359	87.82 282	90.22 264	96.63 265	74.27 324	97.94 267	86.37 300	92.43 264	98.59 207

v7n		84.42 388	82.75 391	89.43 397	88.15 444	81.86 403	96.75 368	95.67 359	80.53 423	78.38 420	89.43 434	69.89 363	96.35 366	73.83 428	72.13 434	90.07 430

ACMP	87.39 10	88.71 317	88.24 308	90.12 375	93.91 343	81.06 417	98.50 228	95.67 359	89.43 216	80.37 389	95.55 297	65.67 404	97.83 275	90.55 244	84.51 337	91.47 382
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
viewdifsd2359ckpt09		93.54 176	92.91 182	95.44 181	95.57 240	89.48 208	98.68 191	95.66 362	89.52 212	92.50 211	97.75 167	78.46 276	98.03 259	93.32 197	94.69 217	98.81 170

hybridnocas07		93.98 153	93.52 156	95.36 185	95.01 285	89.37 212	98.63 200	95.64 363	90.79 156	94.69 156	97.31 204	79.01 261	98.11 237	95.54 138	95.07 209	98.61 203

CL-MVSNet_self_test		79.89 423	78.34 425	84.54 449	81.56 487	75.01 460	96.88 362	95.62 364	81.10 417	75.86 434	85.81 468	68.49 376	90.26 482	63.21 476	56.51 492	88.35 455

V42		87.00 343	85.68 349	90.98 350	89.91 417	86.08 332	98.32 261	95.61 365	83.67 376	82.72 346	90.67 403	74.00 328	96.53 350	81.94 367	74.28 411	90.32 425

PRO-TEST		93.06 201	93.87 145	90.64 360	97.39 147	73.83 466	98.15 279	95.60 366	92.80 103	92.50 211	95.70 294	75.11 314	98.58 202	98.60 51	98.93 96	99.50 95

viewmamba		93.88 161	93.59 155	94.78 225	94.82 301	87.68 274	98.41 244	95.60 366	91.61 129	94.17 168	97.93 157	79.65 250	98.01 262	95.20 148	94.87 214	98.66 200

XVG-ACMP-BASELINE		85.86 365	84.95 360	88.57 409	89.90 418	77.12 450	94.30 429	95.60 366	87.40 297	82.12 361	92.99 352	53.42 462	97.66 297	85.02 317	83.83 344	90.92 408

dtuplus		92.78 209	92.35 198	94.07 264	94.70 305	85.91 338	98.47 235	95.59 369	87.50 295	92.88 200	97.66 177	77.24 289	98.12 236	93.01 208	94.15 227	98.20 238

Anonymous202405211		88.84 310	87.03 330	94.27 253	98.14 113	84.18 371	98.44 237	95.58 370	76.79 446	89.34 283	96.88 248	53.42 462	99.54 131	87.53 281	87.12 319	99.09 136

miper_ehance_all_eth		88.94 307	88.12 311	91.40 340	95.32 256	86.93 303	97.85 309	95.55 371	84.19 365	81.97 368	91.50 381	84.16 175	95.91 396	84.69 321	77.89 382	91.36 392

CANet_DTU		94.31 141	93.35 164	97.20 70	97.03 176	94.71 51	98.62 204	95.54 372	95.61 36	97.21 89	98.47 138	71.88 350	99.84 88	88.38 271	97.46 153	97.04 286

v2v482		87.27 341	85.76 347	91.78 332	89.59 425	87.58 285	98.56 220	95.54 372	84.53 360	82.51 352	91.78 372	73.11 336	96.47 355	82.07 364	74.14 414	91.30 396

wanda-best-256-512		83.28 400	80.44 411	91.78 332	82.91 479	88.24 255	98.43 238	95.51 374	75.76 452	78.60 414	86.54 461	66.95 392	95.71 407	82.44 359	56.84 487	91.38 388

FE-blended-shiyan7		83.27 401	80.44 411	91.78 332	82.91 479	88.24 255	98.43 238	95.51 374	75.76 452	78.60 414	86.54 461	66.93 393	95.71 407	82.44 359	56.84 487	91.38 388

blended_shiyan6		83.17 403	80.34 415	91.67 337	82.80 484	87.93 268	98.29 266	95.51 374	75.63 456	78.46 418	86.48 464	66.74 397	95.70 409	82.33 361	56.84 487	91.37 391

blend_shiyan4		86.02 361	84.08 376	91.83 324	83.24 477	88.24 255	98.42 241	95.51 374	75.55 458	79.43 402	86.84 458	84.51 170	95.77 401	83.97 336	69.26 444	91.48 381

BH-untuned		91.46 245	90.84 246	93.33 289	96.51 194	84.83 363	98.84 166	95.50 378	86.44 324	83.50 333	96.70 261	75.49 313	97.77 282	86.78 292	97.81 141	97.40 271

blended_shiyan8		83.22 402	80.40 414	91.71 335	82.77 485	88.01 266	98.25 270	95.49 379	75.64 455	78.68 410	86.55 459	66.76 396	95.75 403	82.50 358	56.93 486	91.36 392

SSM_0407		92.04 234	91.03 239	95.07 211	95.12 270	89.81 197	97.18 351	95.49 379	86.17 326	89.50 279	97.13 220	75.65 309	97.68 295	89.26 263	93.79 236	97.73 257

SSM_0404		92.33 222	91.33 230	95.33 191	95.35 255	90.54 168	97.45 335	95.49 379	86.17 326	90.26 263	97.13 220	75.65 309	97.82 276	89.26 263	95.26 204	97.63 265

v148		86.38 357	85.06 357	90.37 371	89.47 430	84.10 372	98.52 224	95.48 382	83.80 372	80.93 382	90.22 422	74.60 318	96.31 369	80.92 374	71.55 438	90.69 418

IterMVS-LS		88.34 323	87.44 321	91.04 348	94.10 332	85.85 342	98.10 286	95.48 382	85.12 344	82.03 366	91.21 389	81.35 234	95.63 413	83.86 339	75.73 396	91.63 372
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dcpmvs_2		95.67 96	96.18 65	94.12 262	98.82 93	84.22 370	97.37 340	95.45 384	90.70 157	95.77 133	98.63 123	90.47 55	98.68 197	99.20 33	99.22 78	99.45 101

v1144		86.83 346	85.31 355	91.40 340	89.75 421	87.21 301	98.31 262	95.45 384	83.22 382	82.70 347	90.78 398	73.36 331	96.36 361	79.49 383	74.69 405	90.63 420

v1192		86.32 358	84.71 366	91.17 345	89.53 428	86.40 314	98.13 281	95.44 386	82.52 399	82.42 355	90.62 407	71.58 355	96.33 368	77.23 398	74.88 402	90.79 412

v144192		86.40 356	84.89 361	90.91 351	89.48 429	85.59 346	98.21 274	95.43 387	82.45 401	82.62 350	90.58 410	72.79 342	96.36 361	78.45 393	74.04 415	90.79 412

Effi-MVS+-dtu		89.97 290	90.68 252	87.81 416	95.15 267	71.98 476	97.87 308	95.40 388	91.92 124	87.57 297	91.44 383	74.27 324	96.84 336	89.45 256	93.10 250	94.60 330

c3_l		88.19 327	87.23 326	91.06 347	94.97 290	86.17 329	97.72 320	95.38 389	83.43 379	81.68 376	91.37 384	82.81 201	95.72 406	84.04 335	73.70 416	91.29 397

eth_miper_zixun_eth		87.76 331	87.00 331	90.06 376	94.67 307	82.65 396	97.02 358	95.37 390	84.19 365	81.86 374	91.58 378	81.47 231	95.90 397	83.24 345	73.61 417	91.61 376

v8		86.11 360	84.45 371	91.10 346	89.99 416	86.85 304	97.24 346	95.36 391	81.99 407	79.89 396	89.86 428	74.53 320	96.39 359	78.83 390	72.32 432	90.05 432

v1921920		86.02 361	84.44 372	90.77 357	89.32 431	85.20 354	98.10 286	95.35 392	82.19 405	82.25 359	90.71 400	70.73 359	96.30 372	76.85 403	74.49 407	90.80 411

pmmvs4		87.58 338	86.17 342	91.80 327	89.58 426	88.92 238	97.25 345	95.28 393	82.54 398	80.49 386	93.17 347	75.62 311	96.05 385	82.75 352	78.90 377	90.42 423

viewdifsd2359ckpt11		90.42 275	89.65 266	92.73 306	93.71 352	82.67 393	98.09 289	95.27 394	89.80 198	90.10 268	97.40 196	69.43 369	98.18 227	92.46 218	80.61 368	97.34 273

viewmsd2359difaftdt		90.43 274	89.65 266	92.74 304	93.72 351	82.67 393	98.09 289	95.27 394	89.80 198	90.12 267	97.40 196	69.43 369	98.20 224	92.45 219	80.62 367	97.34 273

GBi-Net		86.67 350	84.96 358	91.80 327	95.11 276	88.81 241	96.77 365	95.25 396	82.94 389	82.12 361	90.25 419	62.89 421	94.97 429	79.04 386	80.24 369	91.62 373

test1		86.67 350	84.96 358	91.80 327	95.11 276	88.81 241	96.77 365	95.25 396	82.94 389	82.12 361	90.25 419	62.89 421	94.97 429	79.04 386	80.24 369	91.62 373

FMVSNet1		83.94 395	81.32 404	91.80 327	91.94 390	88.81 241	96.77 365	95.25 396	77.98 437	78.25 421	90.25 419	50.37 473	94.97 429	73.27 432	77.81 387	91.62 373

mvsany_test1		94.57 135	95.09 107	92.98 295	95.84 229	82.07 401	98.76 178	95.24 399	92.87 102	96.45 114	98.71 116	84.81 165	99.15 166	97.68 80	95.49 200	97.73 257

cl____		87.82 329	86.79 334	90.89 353	94.88 297	85.43 349	97.81 311	95.24 399	82.91 393	80.71 384	91.22 388	81.97 224	95.84 398	81.34 371	75.06 400	91.40 387

miper_lstm_enhance		86.90 344	86.20 341	89.00 405	94.53 314	81.19 414	96.74 369	95.24 399	82.33 403	80.15 392	90.51 414	81.99 222	94.68 438	80.71 376	73.58 419	91.12 403

UnsupCasMVSNet_bld		73.85 454	70.14 458	84.99 445	79.44 493	75.73 457	88.53 479	95.24 399	70.12 478	61.94 490	74.81 504	41.41 488	93.62 451	68.65 458	51.13 502	85.62 479

v1240		85.77 369	84.11 375	90.73 358	89.26 432	85.15 357	97.88 307	95.23 403	81.89 410	82.16 360	90.55 412	69.60 368	96.31 369	75.59 413	74.87 403	90.72 417

DIV-MVS_self_test		87.82 329	86.81 333	90.87 354	94.87 298	85.39 351	97.81 311	95.22 404	82.92 392	80.76 383	91.31 387	81.99 222	95.81 400	81.36 370	75.04 401	91.42 386

v10		85.73 370	84.01 378	90.87 354	90.03 415	86.73 306	97.20 349	95.22 404	81.25 415	79.85 397	89.75 429	73.30 334	96.28 373	76.87 402	72.64 428	89.61 440

mamba_0408		90.65 269	89.16 282	95.12 207	95.12 270	89.81 197	83.02 498	95.17 406	85.95 331	89.50 279	96.85 250	75.85 305	97.82 276	87.19 282	93.79 236	97.73 257

SSM_04072		90.31 279	89.16 282	93.74 280	95.12 270	89.81 197	83.02 498	95.17 406	85.95 331	89.50 279	96.85 250	75.85 305	93.69 449	87.19 282	93.79 236	97.73 257

SD_0403		86.82 347	87.08 328	86.04 436	93.55 355	69.09 485	94.11 434	95.02 408	87.84 281	80.48 387	95.86 291	73.05 337	91.04 478	72.53 439	91.26 297	97.99 252

test_fmvs1		92.35 221	92.94 181	90.57 362	97.19 162	75.43 459	99.55 66	94.97 409	95.20 42	96.82 104	97.57 185	59.59 436	99.84 88	97.30 87	98.29 134	96.46 309

BH-RMVSNet		91.25 252	89.99 261	95.03 215	96.75 186	88.55 250	98.65 196	94.95 410	87.74 287	87.74 296	97.80 162	68.27 378	98.14 230	80.53 379	97.49 152	98.41 217

GeoE		90.60 273	89.56 270	93.72 282	95.10 279	85.43 349	99.41 92	94.94 411	83.96 370	87.21 303	96.83 255	74.37 322	97.05 329	80.50 380	93.73 240	98.67 195

ACMH	83.09 17	84.60 383	82.61 394	90.57 362	93.18 365	82.94 386	96.27 386	94.92 412	81.01 420	72.61 457	93.61 335	56.54 445	97.79 280	74.31 421	81.07 365	90.99 406
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs1_n		91.07 256	91.41 229	90.06 376	94.10 332	74.31 463	99.18 118	94.84 413	94.81 47	96.37 117	97.46 192	50.86 471	99.82 95	97.14 90	97.90 139	96.04 316

test1111		92.12 229	91.19 234	94.94 217	96.15 215	87.36 293	98.12 283	94.84 413	90.85 153	90.97 246	97.26 208	65.60 407	98.37 212	89.74 254	97.14 163	99.07 143

ECVR-MVS		92.29 224	91.33 230	95.15 206	96.41 200	87.84 270	98.10 286	94.84 413	90.82 154	91.42 240	97.28 206	65.61 406	98.49 208	90.33 245	97.19 160	99.12 132

IterMVS		85.81 367	84.67 367	89.22 399	93.51 356	83.67 378	96.32 385	94.80 416	85.09 346	78.69 409	90.17 425	66.57 400	93.17 457	79.48 384	77.42 389	90.81 410
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
LTVRE_ROB	81.71 19	84.59 384	82.72 392	90.18 373	92.89 371	83.18 384	93.15 444	94.74 417	78.99 431	75.14 439	92.69 356	65.64 405	97.63 300	69.46 452	81.82 361	89.74 437
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		84.68 382	82.78 390	90.40 368	89.58 426	85.18 355	97.31 341	94.73 418	81.93 409	76.05 431	92.01 366	65.48 408	96.11 382	78.75 391	69.14 445	89.91 435

IterMVS-SCA-FT		85.73 370	84.64 368	89.00 405	93.46 359	82.90 388	96.27 386	94.70 419	85.02 349	78.62 412	90.35 416	66.61 398	93.33 453	79.38 385	77.36 390	90.76 414

1112_ss		92.71 211	91.55 226	96.20 135	95.56 242	91.12 148	98.48 232	94.69 420	88.29 264	86.89 307	98.50 131	87.02 114	98.66 198	84.75 320	89.77 310	98.81 170

Test_1112_low_res		92.27 226	90.97 241	96.18 137	95.53 244	91.10 150	98.47 235	94.66 421	88.28 265	86.83 308	93.50 339	87.00 115	98.65 199	84.69 321	89.74 311	98.80 172

Fast-Effi-MVS+-dtu		88.84 310	88.59 301	89.58 391	93.44 360	78.18 440	98.65 196	94.62 422	88.46 253	84.12 330	95.37 304	68.91 372	96.52 351	82.06 365	91.70 283	94.06 331

our_test_3		84.47 387	82.80 388	89.50 393	89.01 433	83.90 375	97.03 356	94.56 423	81.33 414	75.36 438	90.52 413	71.69 353	94.54 440	68.81 457	76.84 391	90.07 430

ppachtmachnet_test		83.63 398	81.57 401	89.80 384	89.01 433	85.09 358	97.13 353	94.50 424	78.84 432	76.14 430	91.00 392	69.78 364	94.61 439	63.40 475	74.36 409	89.71 439

test_vis1_n		90.40 276	90.27 258	90.79 356	91.55 398	76.48 453	99.12 137	94.44 425	94.31 57	97.34 86	96.95 238	43.60 484	99.42 146	97.57 82	97.60 147	96.47 308

MonoMVSNet		90.69 267	89.78 264	93.45 286	91.78 394	84.97 361	96.51 377	94.44 425	90.56 166	85.96 313	90.97 394	78.61 275	96.27 374	95.35 142	83.79 347	99.11 134

YYNet1		79.64 426	77.04 432	87.43 422	87.80 451	79.98 423	96.23 390	94.44 425	73.83 466	51.83 499	87.53 446	67.96 383	92.07 472	66.00 468	67.75 455	90.23 427

MDA-MVSNet_test_wron		79.65 425	77.05 431	87.45 421	87.79 452	80.13 422	96.25 389	94.44 425	73.87 465	51.80 500	87.47 450	68.04 381	92.12 471	66.02 467	67.79 454	90.09 428

MIMVSNet		84.48 386	81.83 398	92.42 312	91.73 396	87.36 293	85.52 485	94.42 429	81.40 413	81.91 369	87.58 445	51.92 465	92.81 460	73.84 427	88.15 314	97.08 285

MVP-Stereo		86.61 352	85.83 346	88.93 407	88.70 438	83.85 376	96.07 397	94.41 430	82.15 406	75.64 436	91.96 369	67.65 385	96.45 357	77.20 400	98.72 112	86.51 472
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MSDG		88.29 325	86.37 338	94.04 268	96.90 179	86.15 330	96.52 376	94.36 431	77.89 441	79.22 406	96.95 238	69.72 365	99.59 127	73.20 433	92.58 262	96.37 312

ACMH+	83.78 15	84.21 390	82.56 396	89.15 402	93.73 350	79.16 431	96.43 380	94.28 432	81.09 418	74.00 444	94.03 321	54.58 457	97.67 296	76.10 409	78.81 378	90.63 420

Patchmatch-test		86.25 359	84.06 377	92.82 300	94.42 316	82.88 390	82.88 500	94.23 433	71.58 470	79.39 403	90.62 407	89.00 75	96.42 358	63.03 477	91.37 295	99.16 127

CR-MVSNet		88.83 312	87.38 323	93.16 292	93.47 357	86.24 320	84.97 490	94.20 434	88.92 237	90.76 251	86.88 456	84.43 172	94.82 434	70.64 447	92.17 274	98.41 217

Patchmtry		83.61 399	81.64 399	89.50 393	93.36 361	82.84 391	84.10 493	94.20 434	69.47 481	79.57 400	86.88 456	84.43 172	94.78 435	68.48 459	74.30 410	90.88 409

EG-PatchMatch MVS		79.92 421	77.59 428	86.90 427	87.06 458	77.90 445	96.20 393	94.06 436	74.61 462	66.53 482	88.76 438	40.40 490	96.20 376	67.02 464	83.66 348	86.61 470

KD-MVS_self_test		77.47 440	75.88 437	82.24 459	81.59 486	68.93 486	92.83 451	94.02 437	77.03 443	73.14 451	83.39 475	55.44 452	90.42 481	67.95 460	57.53 484	87.38 463

K. test v3		81.04 417	79.77 419	84.83 446	87.41 454	70.23 482	95.60 412	93.93 438	83.70 375	67.51 478	89.35 435	55.76 448	93.58 452	76.67 405	68.03 452	90.67 419

FE-MVSNET2		78.42 435	75.71 438	86.55 430	78.55 496	81.99 402	95.40 413	93.86 439	81.11 416	66.27 483	81.89 482	49.29 477	91.80 474	72.03 442	63.02 467	85.86 476

RPSCF		85.33 374	85.55 351	84.67 448	94.63 309	62.28 495	93.73 437	93.76 440	74.38 464	85.23 321	97.06 231	64.09 414	98.31 214	80.98 372	86.08 328	93.41 336

MVS-HIRNet		79.01 428	75.13 442	90.66 359	93.82 348	81.69 405	85.16 487	93.75 441	54.54 500	74.17 443	59.15 517	57.46 442	96.58 347	63.74 474	94.38 223	93.72 333

pmmvs5		85.87 364	84.40 374	90.30 372	88.53 440	84.23 369	98.60 211	93.71 442	81.53 412	80.29 390	92.02 365	64.51 413	95.52 415	82.04 366	78.34 380	91.15 402

pmmvs6		79.90 422	77.31 430	87.67 417	84.17 472	78.13 442	95.86 405	93.68 443	67.94 485	72.67 456	89.62 431	50.98 470	95.75 403	74.80 419	66.04 460	89.14 446

OurMVSNet-221017-0		84.13 393	83.59 382	85.77 440	87.81 450	70.24 481	94.89 420	93.65 444	86.08 328	76.53 427	93.28 343	61.41 429	96.14 381	80.95 373	77.69 388	90.93 407

PatchmatchNet2					0.00 560	79.25 429	96.11 395	93.62 445	70.56 474
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
Anonymous20240521		78.63 432	76.90 433	83.82 452	82.82 482	72.86 472	95.72 410	93.57 446	73.55 468	72.17 458	84.79 472	49.69 475	92.51 465	65.29 471	74.50 406	86.09 475

DP-MVS		88.75 316	86.56 336	95.34 189	98.92 89	87.45 290	97.64 329	93.52 447	70.55 475	81.49 377	97.25 210	74.43 321	99.88 72	71.14 446	94.09 229	98.67 195

ITE_SJBPF				87.93 414	92.26 381	76.44 454		93.47 448	87.67 291	79.95 395	95.49 301	56.50 446	97.38 316	75.24 414	82.33 359	89.98 434

USDC		84.74 380	82.93 386	90.16 374	91.73 396	83.54 380	95.00 419	93.30 449	88.77 244	73.19 450	93.30 342	53.62 461	97.65 299	75.88 411	81.54 362	89.30 443

dtuonly		89.80 292	89.16 282	91.70 336	90.49 412	81.48 407	96.58 374	93.12 450	87.21 300	88.72 287	96.87 249	72.09 347	97.59 303	83.52 344	93.84 234	96.03 317

ADS-MVSNet2		87.62 337	86.88 332	89.86 382	96.21 210	79.14 432	87.15 482	92.99 451	83.01 386	89.91 272	87.27 451	78.87 266	92.80 461	74.20 423	92.27 270	97.64 262

Anonymous20231206		80.76 418	79.42 421	84.79 447	84.78 470	72.98 470	96.53 375	92.97 452	79.56 429	74.33 441	88.83 437	61.27 430	92.15 469	60.59 483	75.92 395	89.24 445

MDA-MVSNet-bldmvs		77.82 439	74.75 445	87.03 424	88.33 442	78.52 438	96.34 383	92.85 453	75.57 457	48.87 502	87.89 443	57.32 443	92.49 466	60.79 482	64.80 464	90.08 429

test20.03		78.51 434	77.48 429	81.62 464	83.07 478	71.03 478	96.11 395	92.83 454	81.66 411	69.31 469	89.68 430	57.53 441	87.29 498	58.65 488	68.47 450	86.53 471

COLMAP_ROB	82.69 18	84.54 385	82.82 387	89.70 388	96.72 187	78.85 433	95.89 401	92.83 454	71.55 471	77.54 426	95.89 290	59.40 437	99.14 170	67.26 463	88.26 313	91.11 404
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvs2		85.10 377	85.45 353	84.02 451	89.85 420	65.63 491	98.49 230	92.59 456	90.45 170	85.43 320	93.32 340	43.94 482	96.59 346	90.81 240	84.19 341	89.85 436

SixPastTwentyTwo		82.63 407	81.58 400	85.79 439	88.12 445	71.01 479	95.17 417	92.54 457	84.33 364	72.93 455	92.08 363	60.41 434	95.61 414	74.47 420	74.15 413	90.75 415

FMVSNet5		82.29 408	80.54 408	87.52 419	93.79 349	84.01 373	93.73 437	92.47 458	76.92 444	74.27 442	86.15 466	63.69 419	89.24 490	69.07 455	74.79 404	89.29 444

usedtu_blend_shiyan5		82.04 410	78.78 423	91.80 327	82.91 479	88.24 255	94.33 427	92.37 459	66.55 490	78.60 414	86.54 461	66.93 393	95.77 401	83.97 336	56.84 487	91.38 388

new-patchmatchnet		74.80 453	72.40 454	81.99 463	78.36 497	72.20 475	94.44 425	92.36 460	77.06 442	63.47 488	79.98 492	51.04 469	88.85 491	60.53 484	54.35 495	84.92 486

new_pmnet		76.02 444	73.71 449	82.95 457	83.88 473	72.85 473	91.26 469	92.26 461	70.44 476	62.60 489	81.37 486	47.64 479	92.32 467	61.85 479	72.10 435	83.68 491

AllTest		84.97 379	83.12 385	90.52 365	96.82 181	78.84 434	95.89 401	92.17 462	77.96 439	75.94 432	95.50 299	55.48 450	99.18 164	71.15 444	87.14 317	93.55 334

TestCases				90.52 365	96.82 181	78.84 434		92.17 462	77.96 439	75.94 432	95.50 299	55.48 450	99.18 164	71.15 444	87.14 317	93.55 334

pmmvs-eth3d		78.71 431	76.16 436	86.38 431	80.25 492	81.19 414	94.17 432	92.13 464	77.97 438	66.90 481	82.31 480	55.76 448	92.56 464	73.63 430	62.31 472	85.38 481

MIMVSNet1		75.92 445	73.30 451	83.81 453	81.29 488	75.57 458	92.26 455	92.05 465	73.09 469	67.48 479	86.18 465	40.87 489	87.64 497	55.78 492	70.68 442	88.21 456

ambc				79.60 470	72.76 508	56.61 500	76.20 510	92.01 466		68.25 474	80.23 491	23.34 503	94.73 436	73.78 429	60.81 476	87.48 462

LF4IMVS		81.94 412	81.17 405	84.25 450	87.23 457	68.87 487	93.35 443	91.93 467	83.35 381	75.40 437	93.00 351	49.25 478	96.65 344	78.88 389	78.11 381	87.22 467

TransMVSNet (Re)		81.97 411	79.61 420	89.08 403	89.70 424	84.01 373	97.26 344	91.85 468	78.84 432	73.07 454	91.62 376	67.17 390	95.21 426	67.50 462	59.46 480	88.02 457

MVStest1		76.56 443	73.43 450	85.96 438	86.30 464	80.88 420	94.26 430	91.74 469	61.98 494	58.53 494	89.96 426	69.30 371	91.47 477	59.26 486	49.56 505	85.52 480

Baseline_NR-MVSNet		85.83 366	84.82 363	88.87 408	88.73 437	83.34 382	98.63 200	91.66 470	80.41 427	82.44 353	91.35 385	74.63 316	95.42 420	84.13 331	71.39 439	87.84 458

mmtdpeth		83.69 396	82.59 395	86.99 426	92.82 372	76.98 451	96.16 394	91.63 471	82.89 394	92.41 216	82.90 476	54.95 455	98.19 225	96.27 112	53.27 497	85.81 477

testgi		82.29 408	81.00 406	86.17 434	87.24 456	74.84 462	97.39 337	91.62 472	88.63 247	75.85 435	95.42 302	46.07 481	91.55 475	66.87 466	79.94 373	92.12 358

TDRefinement		78.01 437	75.31 440	86.10 435	70.06 511	73.84 465	93.59 440	91.58 473	74.51 463	73.08 453	91.04 391	49.63 476	97.12 324	74.88 417	59.47 479	87.33 465

OpenMVS_ROB	73.86 20	77.99 438	75.06 443	86.77 429	83.81 474	77.94 444	96.38 382	91.53 474	67.54 486	68.38 473	87.13 455	43.94 482	96.08 383	55.03 494	81.83 360	86.29 474

ttmdpeth		79.80 424	77.91 427	85.47 442	83.34 476	75.75 456	95.32 415	91.45 475	76.84 445	74.81 440	91.71 375	53.98 460	94.13 444	72.42 440	61.29 473	86.51 472

test_0402		78.81 430	76.33 435	86.26 433	91.18 404	78.44 439	95.88 403	91.34 476	68.55 482	70.51 464	89.91 427	52.65 464	94.99 428	47.14 506	79.78 374	85.34 483

MTMP							99.21 114	91.09 477

DeepMVS_CX				76.08 473	90.74 410	51.65 509		90.84 478	86.47 323	57.89 496	87.98 441	35.88 495	92.60 462	65.77 469	65.06 463	83.97 489

dtuonlycased		79.10 427	78.53 424	80.81 467	86.63 460	72.95 471	96.33 384	90.81 479	81.09 418	68.85 470	87.27 451	56.94 444	87.84 495	71.57 443	67.30 457	81.65 495

test_fmvs3		75.09 450	75.19 441	74.81 476	77.45 499	54.08 504	95.93 399	90.64 480	82.51 400	73.29 449	81.19 487	22.29 504	86.29 501	85.50 312	67.89 453	84.06 488

usedtu_dtu_shiyan2		69.89 459	65.80 464	82.15 461	69.90 512	68.09 488	93.09 445	90.63 481	58.33 495	61.56 491	79.31 495	28.96 501	89.43 488	57.76 490	52.68 500	88.92 451

tt0320		76.58 442	73.16 452	86.86 428	88.03 447	77.60 447	93.55 442	90.63 481	55.37 498	70.93 460	84.98 470	41.57 486	94.01 445	69.02 456	64.32 466	88.97 449

sc_t1		78.53 433	74.87 444	89.48 396	87.92 448	77.36 449	94.80 421	90.61 483	57.65 496	76.28 428	89.59 432	38.25 491	96.18 377	74.04 425	64.72 465	94.91 329

lessismore_v0				85.08 444	85.59 468	69.28 484		90.56 484		67.68 477	90.21 423	54.21 459	95.46 418	73.88 426	62.64 470	90.50 422

Gipuma		54.77 476	52.22 478	62.40 496	86.50 461	59.37 499	50.20 528	90.35 485	36.52 517	41.20 513	49.49 522	18.33 508	81.29 504	32.10 520	65.34 462	46.54 527
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
TinyColmap		80.42 420	77.94 426	87.85 415	92.09 385	78.58 437	93.74 436	89.94 486	74.99 460	69.77 466	91.78 372	46.09 480	97.58 305	65.17 472	77.89 382	87.38 463

test_method		70.10 458	68.66 461	74.41 478	86.30 464	55.84 502	94.47 423	89.82 487	35.18 518	66.15 484	84.75 473	30.54 497	77.96 513	70.40 450	60.33 477	89.44 442

FPMVS		61.57 464	60.32 466	65.34 490	60.14 527	42.44 521	91.02 472	89.72 488	44.15 508	42.63 509	80.93 488	19.02 506	80.59 509	42.50 511	72.76 427	73.00 508

test_f		71.94 456	70.82 457	75.30 475	72.77 507	53.28 505	91.62 462	89.66 489	75.44 459	64.47 487	78.31 497	20.48 505	89.56 487	78.63 392	66.02 461	83.05 494

LCM-MVSNet		60.07 469	56.37 471	71.18 482	54.81 531	48.67 512	82.17 503	89.48 490	37.95 515	49.13 501	69.12 509	13.75 515	81.76 503	59.28 485	51.63 501	83.10 493

mvs5depth		78.17 436	75.56 439	85.97 437	80.43 491	76.44 454	85.46 486	89.24 491	76.39 447	78.17 423	88.26 440	51.73 466	95.73 405	69.31 454	61.09 474	85.73 478

tt0320-xc		75.92 445	72.23 456	87.01 425	88.40 441	78.15 441	93.57 441	89.15 492	55.46 497	69.66 467	85.79 469	38.20 492	93.85 446	69.72 451	60.08 478	89.03 447

pmmvs3		72.86 455	69.76 460	82.17 460	73.86 504	74.19 464	94.20 431	89.01 493	64.23 493	67.72 476	80.91 490	41.48 487	88.65 493	62.40 478	54.02 496	83.68 491

LCM-MVSNet-Re		88.59 321	88.61 299	88.51 410	95.53 244	72.68 474	96.85 363	88.43 494	88.45 254	73.14 451	90.63 406	75.82 307	94.38 441	92.95 209	95.71 194	98.48 214

Patchmatch-RL test		81.90 413	80.13 416	87.23 423	80.71 489	70.12 483	84.07 494	88.19 495	83.16 384	70.57 462	82.18 481	87.18 109	92.59 463	82.28 363	62.78 469	98.98 148

FE-MVSNET		75.08 451	72.25 455	83.56 455	77.93 498	76.96 452	94.36 426	87.96 496	75.72 454	66.01 485	81.60 485	50.48 472	88.85 491	55.38 493	60.82 475	84.86 487

mvsany_test3		75.85 447	74.52 446	79.83 468	73.53 505	60.64 497	91.73 461	87.87 497	83.91 371	70.55 463	82.52 478	31.12 496	93.66 450	86.66 298	62.83 468	85.19 485

DSMNet-mixed		81.60 414	81.43 402	82.10 462	84.36 471	60.79 496	93.63 439	86.74 498	79.00 430	79.32 405	87.15 454	63.87 417	89.78 486	66.89 465	91.92 277	95.73 322

ArgMatch-Sym		75.37 448	74.07 447	79.27 471	86.10 466	64.15 493	92.14 456	85.97 499	78.66 435	71.15 459	91.00 392	29.88 499	86.45 500	73.44 431	58.34 482	87.22 467

PM-MVS		74.88 452	72.85 453	80.98 466	78.98 494	64.75 492	90.81 473	85.77 500	80.95 421	68.23 475	82.81 477	29.08 500	92.84 459	76.54 406	62.46 471	85.36 482

door								85.30 501

ArgMatch-SfM		75.24 449	73.75 448	79.70 469	85.92 467	63.67 494	91.51 465	85.16 502	79.74 428	70.70 461	90.27 417	30.46 498	87.73 496	72.95 435	57.08 485	87.70 461

APD_test1		68.93 460	66.98 462	74.77 477	80.62 490	53.15 506	87.97 480	85.01 503	53.76 501	59.26 493	87.52 447	25.19 502	89.95 483	56.20 491	67.33 456	81.19 496

door-mid								84.90 504

EGC-MVSNET		60.70 468	55.37 472	76.72 472	86.35 463	71.08 477	89.96 477	84.44 505	0.38 554	1.50 555	84.09 474	37.30 493	88.10 494	40.85 515	73.44 422	70.97 511

WB-MVS		66.44 461	66.29 463	66.89 488	74.84 501	44.93 517	93.00 446	84.09 506	71.15 472	55.82 497	81.63 484	63.79 418	80.31 510	21.85 524	50.47 503	75.43 504

SSC-MVS		65.42 462	65.20 465	66.06 489	73.96 503	43.83 518	92.08 457	83.54 507	69.77 479	54.73 498	80.92 489	63.30 420	79.92 511	20.48 526	48.02 506	74.44 506

dmvs_testset		77.17 441	78.99 422	71.71 481	87.25 455	38.55 525	91.44 466	81.76 508	85.77 335	69.49 468	95.94 289	69.71 366	84.37 502	52.71 498	76.82 392	92.21 354

PMMVS2		58.97 470	55.07 473	70.69 484	62.72 521	55.37 503	85.97 484	80.52 509	49.48 506	45.94 506	68.31 510	15.73 510	80.78 507	49.79 502	37.12 513	75.91 502

LoFTR		61.59 463	56.89 470	75.68 474	76.61 500	50.06 511	82.20 502	79.57 510	52.13 503	39.02 516	75.71 501	14.90 512	93.30 454	45.35 508	46.48 509	83.69 490

ANet_high		50.71 480	46.17 484	64.33 491	44.27 538	52.30 508	76.13 511	78.73 511	64.95 491	27.37 523	55.23 520	14.61 514	67.74 521	36.01 518	18.23 532	72.95 509

PMVS	41.42 23	45.67 483	42.50 485	55.17 502	34.28 552	32.37 530	66.24 516	78.71 512	30.72 520	22.04 529	59.59 516	4.59 538	77.85 514	27.49 521	58.84 481	55.29 520
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis1_rt		81.31 416	80.05 418	85.11 443	91.29 403	70.66 480	98.98 154	77.39 513	85.76 336	68.80 471	82.40 479	36.56 494	99.44 142	92.67 216	86.55 322	85.24 484

MatchFormer		56.78 472	51.80 479	71.74 480	73.47 506	45.39 514	81.84 504	76.12 514	40.41 511	35.13 518	69.22 508	12.67 518	92.15 469	35.57 519	41.74 510	77.67 500

tmp_tt		53.66 477	52.86 477	56.05 500	32.75 554	41.97 523	73.42 514	76.12 514	21.91 525	39.68 514	96.39 273	42.59 485	65.10 524	78.00 395	14.92 540	61.08 517

testf1		56.38 473	53.73 475	64.31 492	64.84 518	45.11 515	80.50 505	75.94 516	38.87 513	42.74 507	75.07 502	11.26 521	81.19 505	41.11 513	53.27 497	66.63 513

APD_test2		56.38 473	53.73 475	64.31 492	64.84 518	45.11 515	80.50 505	75.94 516	38.87 513	42.74 507	75.07 502	11.26 521	81.19 505	41.11 513	53.27 497	66.63 513

MASt3R-SfM		60.79 467	59.91 467	63.44 495	62.41 522	35.46 526	75.76 513	71.46 518	54.67 499	58.30 495	86.10 467	14.86 513	74.25 517	65.44 470	50.18 504	80.59 497

DenseAffine		61.07 466	57.33 469	72.29 479	78.74 495	56.29 501	83.24 497	69.15 519	53.26 502	47.82 504	79.48 494	13.61 516	80.66 508	51.15 501	39.51 511	79.92 498

MVE	44.00 22	41.70 485	37.64 491	53.90 503	49.46 534	43.37 519	65.09 517	66.66 520	26.19 523	25.77 526	48.53 523	3.58 541	63.35 525	26.15 523	27.28 523	54.97 521
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		41.02 486	40.93 487	41.29 506	61.97 523	33.83 527	84.00 495	65.17 521	27.17 521	27.56 522	46.72 526	17.63 509	60.41 527	19.32 527	18.82 529	29.61 531

EMVS		39.96 487	39.88 488	40.18 507	59.57 529	32.12 532	84.79 492	64.57 522	26.27 522	26.14 525	44.18 530	18.73 507	59.29 528	17.03 528	17.67 534	29.12 532

ELoFTR		47.00 482	42.41 486	60.77 498	51.54 533	32.77 529	63.82 518	61.24 523	39.04 512	29.94 520	67.31 512	4.83 537	75.52 516	39.39 516	24.54 526	74.03 507

test_vis3_rt		61.29 465	58.75 468	68.92 485	67.41 515	52.84 507	91.18 471	59.23 524	66.96 487	41.96 512	58.44 518	11.37 520	94.72 437	74.25 422	57.97 483	59.20 518

RoMa-SfM		58.43 471	54.99 474	68.74 486	74.29 502	50.87 510	82.37 501	58.12 525	50.53 504	48.40 503	81.78 483	12.70 517	78.25 512	47.71 505	39.01 512	77.09 501

DKM		55.59 475	51.49 480	67.89 487	72.36 509	48.29 513	80.45 507	52.05 526	47.86 507	42.54 510	77.08 500	9.06 529	77.32 515	48.87 503	33.13 515	78.05 499

GLUNet-SfM		37.11 490	32.05 494	52.28 505	44.07 540	25.94 537	52.38 527	46.25 527	24.11 524	21.50 530	55.60 519	6.32 536	66.20 523	27.48 522	10.71 545	64.70 515

RoMa-HiRes		51.04 478	47.47 481	61.73 497	65.35 517	42.38 522	76.31 509	41.57 528	42.69 509	42.32 511	77.75 498	9.33 526	73.10 518	42.68 510	29.24 518	69.72 512

DKM-HiRes		50.92 479	46.71 482	63.56 494	66.42 516	42.72 520	76.47 508	41.46 529	42.47 510	39.40 515	73.35 505	7.13 535	72.77 519	44.18 509	29.50 517	75.19 505

PDCNetPlus		48.73 481	46.34 483	55.88 501	64.17 520	41.40 524	76.11 512	34.96 530	50.17 505	35.24 517	71.04 506	15.41 511	67.33 522	52.41 499	17.59 535	58.93 519

VLMVS		38.17 489	38.75 490	36.45 511	35.35 550	13.53 556	50.05 529	33.90 531	9.30 536	47.14 505	77.14 499	12.39 519	32.34 532	47.77 504	35.68 514	63.48 516

PMatch-SfM		44.26 484	39.30 489	59.12 499	52.80 532	33.36 528	66.34 515	29.85 532	36.60 516	30.58 519	70.53 507	2.50 553	68.49 520	42.14 512	22.39 528	75.51 503

ALIKED-LG		33.96 491	32.42 493	38.57 508	70.35 510	32.25 531	57.19 522	29.49 533	19.94 526	22.96 528	46.96 525	10.85 523	47.42 529	8.53 539	25.49 524	36.04 528

N_pmnet		70.19 457	69.87 459	71.12 483	88.24 443	30.63 535	95.85 406	28.70 534	70.18 477	68.73 472	86.55 459	64.04 416	93.81 447	53.12 496	73.46 421	88.94 450

ALIKED-NN		33.05 492	31.67 495	37.18 510	69.89 513	31.76 533	55.83 526	28.14 535	16.92 527	23.23 527	47.45 524	9.65 525	45.41 531	8.80 538	25.13 525	34.38 530

ALIKED-MNN		32.26 493	30.45 496	37.68 509	69.07 514	31.55 534	56.28 525	27.56 536	16.30 528	21.15 531	44.78 528	8.12 532	46.74 530	8.19 540	22.59 527	34.76 529

SP-DiffGlue		29.92 496	29.42 500	31.40 514	32.10 555	20.02 539	47.81 530	27.27 537	14.91 529	26.24 524	54.34 521	10.53 524	24.46 539	21.49 525	30.15 516	49.71 526

SP-SuperGlue		30.18 495	29.74 499	31.50 513	60.57 525	18.71 542	57.45 520	26.07 538	13.70 530	20.25 532	39.95 534	9.22 528	25.03 538	11.85 533	28.64 521	50.78 523

SP-LightGlue		30.23 494	29.76 498	31.66 512	60.90 524	18.79 541	57.25 521	25.88 539	13.65 531	20.11 533	39.95 534	9.29 527	25.08 537	11.83 534	28.96 519	51.11 522

SP-MNN		29.29 498	28.62 502	31.29 515	59.13 530	18.03 546	56.77 524	25.19 540	11.83 533	18.01 537	39.35 537	8.35 531	25.39 535	10.99 537	27.91 522	50.47 524

XFeat-MNN		22.62 499	22.31 504	23.56 517	28.01 556	15.00 553	39.69 532	25.09 541	11.81 534	17.88 538	39.92 536	7.77 533	29.38 533	13.26 531	17.33 538	26.31 533

SP-NN		29.64 497	29.14 501	31.16 516	59.77 528	18.23 543	56.90 523	24.71 542	12.64 532	18.99 534	40.64 533	8.48 530	25.23 536	11.37 535	28.74 520	50.01 525

XFeat-NN		22.06 501	22.11 505	21.91 518	27.57 557	14.27 554	38.62 533	22.62 543	11.16 535	18.84 535	41.23 532	7.46 534	26.91 534	13.19 532	18.30 531	24.56 534

PMatch-Up-SfM		39.29 488	34.48 492	53.73 504	46.70 536	28.02 536	58.71 519	21.05 544	31.53 519	27.94 521	66.24 513	1.99 556	61.38 526	38.41 517	17.72 533	71.80 510

SIFT-NN		18.10 503	18.53 507	16.83 519	48.67 535	18.97 540	33.34 534	14.35 545	7.78 537	10.98 540	25.86 539	3.78 539	19.51 541	3.23 541	18.78 530	12.02 537

SIFT-MNN		17.20 504	17.47 508	16.41 521	45.38 537	18.16 544	31.28 536	14.20 546	7.60 538	9.54 541	25.18 540	3.39 542	19.18 542	3.18 542	17.44 536	11.88 538

SIFT-NN-NCMNet		16.94 505	17.19 509	16.19 522	43.53 541	18.04 545	31.30 535	14.18 547	7.55 540	9.51 542	24.88 541	3.32 543	18.84 543	3.08 543	17.35 537	11.70 540

SIFT-NN-UMatch		15.49 510	15.62 513	15.11 526	38.08 547	15.93 550	29.97 537	13.04 548	7.57 539	7.22 546	24.84 543	3.26 544	18.03 546	3.02 544	13.56 541	11.37 541

SIFT-NCM-Cal		16.07 508	16.20 511	15.69 523	44.16 539	17.32 547	29.83 538	12.88 549	7.33 543	6.22 549	23.59 547	3.00 547	18.75 544	2.74 549	16.09 539	10.99 543

SIFT-NN-CMatch		15.72 509	15.77 512	15.60 524	39.99 545	16.99 549	28.08 539	12.85 550	7.52 541	9.34 543	24.86 542	3.24 545	18.08 545	2.99 545	13.01 542	11.71 539

SIFT-ConvMatch		15.12 511	15.10 514	15.19 525	42.19 542	17.16 548	26.33 542	12.02 551	7.39 542	7.26 545	24.08 544	2.92 548	17.97 547	2.85 547	10.90 544	10.43 545

SIFT-NN-PointCN		14.43 513	14.70 516	13.64 529	36.13 548	12.94 557	27.63 541	11.82 552	7.03 547	8.24 544	23.49 548	3.21 546	16.75 550	2.85 547	11.89 543	11.22 542

SIFT-UMatch		14.73 512	14.79 515	14.57 527	40.58 544	15.36 552	27.70 540	11.21 553	7.28 544	6.62 548	24.07 545	2.81 551	17.91 548	2.87 546	9.94 546	10.45 544

SIFT-CM-Cal		14.12 514	14.09 517	14.22 528	40.92 543	15.56 551	23.80 544	10.18 554	7.20 545	6.72 547	23.20 549	2.86 550	16.98 549	2.67 551	9.24 549	10.13 546

SIFT-PointCN		12.37 516	12.72 519	11.33 531	35.33 551	10.01 558	23.72 545	9.79 555	6.45 549	5.30 553	20.10 551	2.22 555	14.67 553	2.33 553	9.26 548	9.30 548

SIFT-UM-Cal		13.73 515	13.86 518	13.34 530	39.95 546	13.63 555	25.68 543	9.21 556	7.19 546	5.57 550	23.60 546	2.66 552	16.67 551	2.70 550	8.18 550	9.73 547

SIFT-PCN-Cal		12.09 517	12.36 520	11.26 532	35.43 549	9.79 559	22.24 546	8.83 557	6.37 550	5.43 552	20.44 550	2.34 554	14.88 552	2.35 552	7.87 551	9.13 549

SIFT-NCMNet		10.41 518	10.63 522	9.76 533	33.41 553	9.03 560	18.23 547	5.49 558	6.29 551	4.60 554	17.58 552	1.84 557	12.74 554	2.03 554	6.21 552	7.52 550

wuyk23d		16.71 506	16.73 510	16.65 520	60.15 526	25.22 538	41.24 531	5.17 559	6.56 548	5.48 551	3.61 553	3.64 540	22.72 540	15.20 529	9.52 547	1.99 551

testmvs		18.81 502	23.05 503	6.10 535	4.48 558	2.29 562	97.78 313	3.00 560	3.27 552	18.60 536	62.71 514	1.53 558	2.49 556	14.26 530	1.80 553	13.50 536

test123		16.58 507	19.47 506	7.91 534	3.59 559	5.37 561	94.32 428	1.39 561	2.49 553	13.98 539	44.60 529	2.91 549	2.65 555	11.35 536	0.57 554	15.70 535

mmdepth		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

monomultidepth		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

test_blank		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

uanet_test		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

DCPMVS		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

pcd_1.5k_mvsjas		6.87 520	9.16 523	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	82.48 212	0.00 557	0.00 555	0.00 555	0.00 552

sosnet-low-res		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

sosnet		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

uncertanet		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

Regformer		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

n2								0.00 562

nn								0.00 562

ab-mvs-re		8.21 519	10.94 521	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	98.50 131	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

uanet		0.00 521	0.00 524	0.00 536	0.00 560	0.00 563	0.00 548	0.00 562	0.00 555	0.00 556	0.00 554	0.00 559	0.00 557	0.00 555	0.00 555	0.00 552

PatchmatchNet1														52.97 497	73.44 422	88.99 448
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													93.74 448
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						79.74 426								67.75 461

PC_three_1452									94.60 51	99.41 11	99.12 63	95.50 7	99.96 34	99.84 2	99.92 3	99.97 8

eth-test2					0.00 560

eth-test					0.00 560

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

test_0728_THIRD									93.01 93	99.07 26	99.46 15	94.66 14	99.97 26	99.25 29	99.82 19	99.95 16

GSMVS																98.84 165

test_part2					99.54 42	95.42 24				98.13 63

sam_mvs1												88.39 84				98.84 165

sam_mvs												87.08 112

test_post1							90.74 475				41.37 531	85.38 154	96.36 361	83.16 347

test_post											46.00 527	87.37 103	97.11 325

patchmatchnet-post											84.86 471	88.73 80	96.81 338

gm-plane-assit					94.69 306	88.14 261			88.22 266		97.20 214		98.29 216	90.79 241

test9_res														98.60 51	99.87 9	99.90 23

agg_prior2														97.84 78	99.87 9	99.91 22

test_prior4						92.00 123	99.41 92

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

旧先验2							98.67 194		85.75 337	98.96 32			98.97 179	93.84 183

新几何2							98.26 268

原ACMM2							98.69 190

testdata2													99.88 72	84.16 330

segment_acmp												90.56 54

testdata1							97.89 305		92.43 109

plane_prior7					93.84 345	85.73 344

plane_prior6					93.92 342	86.02 336						72.92 339

plane_prior4											96.52 266

plane_prior3						85.91 338			93.65 81	86.99 304

plane_prior2							99.02 148		93.38 88

plane_prior1					93.90 344

plane_prior						86.07 334	99.14 130		93.81 77						86.26 325

HQP5-MVS						86.39 315

HQP-NCC					93.95 337		99.16 122		93.92 68	87.57 297

ACMP_Plane					93.95 337		99.16 122		93.92 68	87.57 297

BP-MVS														93.82 185

HQP4-MVS										87.57 297			97.77 282			92.72 340

HQP2-MVS												73.34 332

NP-MVS					93.94 340	86.22 322					96.67 263

MDTV_nov1_ep13_2view						91.17 147	91.38 467		87.45 296	93.08 193		86.67 124		87.02 285		98.95 154

ACMMP++_ref															82.64 357

ACMMP++															83.83 344

Test By Simon												83.62 181

High-resolution multi-view benchmark