High-res multi-view results

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

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

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

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

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

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

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

MVS_111021_HR		96.69 47	96.69 47	96.72 102	98.58 100	91.00 158	99.14 132	99.45 1	93.86 75	95.15 150	98.73 112	88.48 85	99.76 110	97.23 91	99.56 56	99.40 107

thres100view900		93.34 191	92.15 214	96.90 90	97.62 132	94.84 44	99.06 147	99.36 2	87.96 279	90.47 262	96.78 259	83.29 193	98.75 192	84.11 336	90.69 305	97.12 285

tfpn200view9		93.43 185	92.27 206	96.90 90	97.68 129	94.84 44	99.18 120	99.36 2	88.45 257	90.79 252	96.90 248	83.31 191	98.75 192	84.11 336	90.69 305	97.12 285

thres600view7		93.18 197	92.00 217	96.75 98	97.62 132	94.92 39	99.07 144	99.36 2	87.96 279	90.47 262	96.78 259	83.29 193	98.71 197	82.93 355	90.47 309	96.61 304

thres400		93.39 187	92.27 206	96.73 100	97.68 129	94.84 44	99.18 120	99.36 2	88.45 257	90.79 252	96.90 248	83.31 191	98.75 192	84.11 336	90.69 305	96.61 304

thres200		93.69 171	92.59 197	96.97 85	97.76 125	94.74 50	99.35 102	99.36 2	89.23 223	91.21 248	96.97 240	83.42 190	98.77 188	85.08 319	90.96 303	97.39 276

MVS_111021_LR		95.78 91	95.94 76	95.28 201	98.19 111	87.69 277	98.80 175	99.26 7	93.39 89	95.04 152	98.69 119	84.09 180	99.76 110	96.96 97	99.06 87	98.38 224

sss		94.85 126	93.94 143	97.58 50	96.43 200	94.09 69	98.93 160	99.16 8	89.50 216	95.27 147	97.85 161	81.50 234	99.65 122	92.79 217	94.02 232	98.99 150

MM		97.76 13	97.39 23	98.86 6	98.30 105	96.83 8	99.81 21	99.13 9	97.66 3	98.29 61	98.96 89	85.84 148	99.90 63	99.72 3	98.80 106	99.85 35

MG-MVS		97.24 25	96.83 40	98.47 17	99.79 6	95.71 22	99.07 144	99.06 10	94.45 58	96.42 117	98.70 118	88.81 81	99.74 112	95.35 144	99.86 12	99.97 8

test2506		94.80 127	94.21 128	96.58 112	96.41 203	92.18 124	98.01 304	98.96 11	90.82 155	93.46 191	97.28 208	85.92 145	98.45 210	89.82 255	97.19 161	99.12 135

PVSNet	87.13 12	93.69 171	92.83 189	96.28 133	97.99 118	90.22 182	99.38 96	98.93 12	91.42 139	93.66 186	97.68 177	71.29 361	99.64 124	87.94 281	97.20 160	98.98 151

PGM-MVS		95.85 87	95.65 92	96.45 119	99.50 48	89.77 204	98.22 276	98.90 13	89.19 225	96.74 110	98.95 92	85.91 147	99.92 50	93.94 181	99.46 61	99.66 72

EPNet		96.82 41	96.68 48	97.25 70	98.65 98	93.10 96	99.48 77	98.76 14	96.54 23	97.84 77	98.22 150	87.49 104	99.66 118	95.35 144	97.78 145	99.00 148
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		95.97 78	95.11 109	98.54 15	97.62 132	96.65 11	99.44 86	98.74 15	92.25 119	95.21 148	98.46 142	86.56 132	99.46 142	95.00 156	92.69 257	99.50 97

HY-MVS	88.56 7	95.29 109	94.23 127	98.48 16	97.72 127	96.41 15	94.03 439	98.74 15	92.42 112	95.65 141	94.76 316	86.52 134	99.49 136	95.29 147	92.97 253	99.53 91

VNet		95.08 117	94.26 126	97.55 53	98.07 115	93.88 71	98.68 195	98.73 17	90.33 177	97.16 94	97.43 196	79.19 264	99.53 133	96.91 99	91.85 283	99.24 123

test_yl		95.27 110	94.60 119	97.28 68	98.53 101	92.98 101	99.05 148	98.70 18	86.76 318	94.65 162	97.74 172	87.78 98	99.44 143	95.57 138	92.61 258	99.44 104

DCV-MVSNet		95.27 110	94.60 119	97.28 68	98.53 101	92.98 101	99.05 148	98.70 18	86.76 318	94.65 162	97.74 172	87.78 98	99.44 143	95.57 138	92.61 258	99.44 104

PVSNet_0	83.28 16	87.31 344	85.16 360	93.74 285	94.78 306	84.59 370	98.91 164	98.69 20	89.81 200	78.59 421	93.23 348	61.95 431	99.34 158	94.75 162	55.72 498	97.30 280

ACMMP		94.67 134	94.30 125	95.79 166	99.25 65	88.13 266	98.41 248	98.67 21	90.38 176	91.43 241	98.72 114	82.22 224	99.95 38	93.83 186	95.76 193	99.29 119
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
lecture		96.67 48	96.77 44	96.39 124	99.27 63	89.71 206	99.65 53	98.62 22	92.28 118	98.62 46	99.07 71	86.74 124	99.79 105	97.83 80	98.82 103	99.66 72

SymmetryMVS		95.49 102	95.27 102	96.17 142	97.13 169	90.37 175	99.14 132	98.59 23	94.92 46	96.30 120	97.98 157	85.33 160	99.23 162	94.35 172	93.67 243	98.92 161

D2MVS		87.96 332	87.39 326	89.70 392	91.84 397	83.40 386	98.31 266	98.49 24	88.04 276	78.23 426	90.26 422	73.57 334	96.79 344	84.21 333	83.53 353	88.90 456

test_fmvsm_n_1920		97.08 33	97.55 16	95.67 172	97.94 120	89.61 210	99.93 1	98.48 25	97.08 13	99.08 26	99.13 61	88.17 90	99.93 47	99.11 38	99.06 87	97.47 273

fmvsm_s_conf0.5_n		96.19 69	96.49 53	95.30 200	97.37 149	89.16 224	99.86 10	98.47 26	95.68 35	98.87 35	99.15 56	82.44 221	99.92 50	99.14 36	97.43 156	96.83 296

HyFIR lowres test		93.68 173	93.29 171	94.87 224	97.57 138	88.04 268	98.18 280	98.47 26	87.57 296	91.24 246	95.05 312	85.49 153	97.46 315	93.22 207	92.82 254	99.10 138

testing3-2		95.17 113	94.78 116	96.33 130	97.35 150	92.35 119	99.85 13	98.43 28	90.60 164	92.84 207	97.00 238	90.89 46	98.89 182	95.95 127	90.12 311	97.76 259

fmvsm_s_conf0.5_n_a		95.97 78	96.19 64	95.31 197	96.51 197	89.01 233	99.81 21	98.39 29	95.46 40	99.19 25	99.16 52	81.44 238	99.91 58	98.83 46	96.97 166	97.01 292

UniMVSNet (Re)		89.50 303	88.32 311	93.03 298	92.21 387	90.96 159	98.90 166	98.39 29	89.13 231	83.22 341	92.03 368	81.69 231	96.34 371	86.79 295	72.53 433	91.81 371

CHOSEN 280x420		96.80 42	96.85 37	96.66 107	97.85 123	94.42 60	94.76 426	98.36 31	92.50 109	95.62 142	97.52 190	97.92 1	97.38 320	98.31 68	98.80 106	98.20 241

VPA-MVSNet		89.10 308	87.66 321	93.45 291	92.56 379	91.02 157	97.97 307	98.32 32	86.92 313	86.03 316	92.01 370	68.84 378	97.10 331	90.92 241	75.34 402	92.23 356

CHOSEN 1792x2688		94.35 144	93.82 151	95.95 159	97.40 146	88.74 249	98.41 248	98.27 33	92.18 121	91.43 241	96.40 275	78.88 269	99.81 99	93.59 191	97.81 142	99.30 118

patch_mono-2		97.10 32	97.97 10	94.49 246	99.21 69	83.73 382	99.62 61	98.25 34	95.28 42	99.38 15	98.91 97	92.28 34	99.94 41	99.61 11	99.22 79	99.78 47

FIs		90.70 270	89.87 267	93.18 296	92.29 384	91.12 151	98.17 282	98.25 34	89.11 232	83.44 338	94.82 315	82.26 223	96.17 383	87.76 282	82.76 359	92.25 354

UGNet		91.91 240	90.85 249	95.10 212	97.06 174	88.69 250	98.01 304	98.24 36	92.41 113	92.39 220	93.61 339	60.52 437	99.68 116	88.14 278	97.25 159	96.92 294
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		90.22 286	89.40 280	92.67 314	91.78 398	89.86 199	97.89 309	98.22 37	88.81 242	82.96 348	94.66 317	81.90 230	95.96 393	85.89 313	82.52 362	92.20 359

WR-MVS_H		86.53 358	85.49 356	89.66 394	91.04 410	83.31 388	97.53 337	98.20 38	84.95 355	79.64 402	90.90 400	78.01 288	95.33 427	76.29 412	72.81 430	90.35 428

MGCNet		97.81 11	97.51 17	98.74 11	98.97 81	96.57 13	99.91 3	98.17 39	97.45 6	98.76 40	98.97 84	86.69 127	99.96 34	99.72 3	98.92 97	99.69 66

MVS		93.92 160	92.28 205	98.83 8	95.69 239	96.82 9	96.22 395	98.17 39	84.89 356	84.34 332	98.61 126	79.32 262	99.83 93	93.88 184	99.43 66	99.86 34

PAPM		96.35 62	95.94 76	97.58 50	94.10 336	95.25 29	98.93 160	98.17 39	94.26 60	93.94 178	98.72 114	89.68 70	97.88 274	96.36 113	99.29 74	99.62 83

baseline2		94.04 154	93.80 152	94.74 232	93.07 373	90.25 179	98.12 287	98.16 42	89.86 196	86.53 314	96.95 241	95.56 6	98.05 258	91.44 236	94.53 222	95.93 323

UniMVSNet_NR-MVSNet		89.60 300	88.55 307	92.75 308	92.17 388	90.07 189	98.74 184	98.15 43	88.37 263	83.21 342	93.98 328	82.86 203	95.93 395	86.95 291	72.47 434	92.25 354

CSCG		94.87 125	94.71 117	95.36 189	99.54 42	86.49 316	99.34 103	98.15 43	82.71 399	90.15 269	99.25 33	89.48 72	99.86 83	94.97 158	98.82 103	99.72 60

test_fmvsmconf_n		96.78 44	96.84 38	96.61 109	95.99 228	90.25 179	99.90 4	98.13 45	96.68 21	98.42 55	98.92 96	85.34 159	99.88 73	99.12 37	99.08 84	99.70 63

MSLP-MVS++		97.50 20	97.45 21	97.63 48	99.65 22	93.21 92	99.70 42	98.13 45	94.61 52	97.78 80	99.46 15	89.85 67	99.81 99	97.97 74	99.91 6	99.88 29

aaatest				97.84 38	99.75 8	93.67 76	99.65 53	98.11 47	92.89 102	98.58 50	99.53 8		100.00 1	99.53 20	99.64 44	99.87 32

MED-MVS		98.04 9	98.10 4	97.86 37	99.75 8	93.67 76	99.65 53	98.11 47	94.03 66	98.58 50	99.49 12	93.98 18	100.00 1	99.53 20	99.75 29	99.90 23

h-mvs33		92.47 224	91.95 220	94.05 272	97.13 169	85.01 364	98.36 261	98.08 49	93.85 76	96.27 122	96.73 262	83.19 197	99.43 146	95.81 130	68.09 455	97.70 265

aaEdge-Enhanced		97.59 17	97.51 17	97.84 38	99.73 12	93.67 76	99.52 73	98.07 50	92.38 116	98.32 60	99.53 8	90.83 49	99.97 26	99.53 20	99.64 44	99.87 32

fmvsm_s_conf0.5_n_4		96.17 70	96.49 53	95.21 206	97.06 174	89.26 219	99.76 33	98.07 50	95.99 29	99.35 16	99.22 38	82.19 225	99.89 71	99.06 39	97.68 147	96.49 311

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

IB-MVS	89.43 6	92.12 233	90.83 252	95.98 158	95.40 255	90.78 163	99.81 21	98.06 52	91.23 146	85.63 321	93.66 338	90.63 53	98.78 187	91.22 237	71.85 440	98.36 230
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
fmvsm_l_conf0.5_n		97.65 16	97.72 14	97.41 59	97.51 142	92.78 108	99.85 13	98.05 54	96.78 18	99.60 8	99.23 36	90.42 58	99.92 50	99.55 16	98.50 125	99.55 89

PHI-MVS		96.65 52	96.46 56	97.21 71	99.34 56	91.77 133	99.70 42	98.05 54	86.48 326	98.05 70	99.20 42	89.33 73	99.96 34	98.38 63	99.62 50	99.90 23

fmvsm_l_conf0.5_n_a		97.70 15	97.80 13	97.42 58	97.59 136	92.91 105	99.86 10	98.04 56	96.70 20	99.58 9	99.26 31	90.90 45	99.94 41	99.57 13	98.66 116	99.40 107

PVSNet_BlendedMVS		93.36 190	93.20 173	93.84 280	98.77 95	91.61 140	99.47 79	98.04 56	91.44 137	94.21 170	92.63 362	83.50 186	99.87 77	97.41 86	83.37 355	90.05 436

PVSNet_Blended		95.94 82	95.66 90	96.75 98	98.77 95	91.61 140	99.88 6	98.04 56	93.64 84	94.21 170	97.76 168	83.50 186	99.87 77	97.41 86	97.75 146	98.79 176

EPMVS		92.59 221	91.59 229	95.59 180	97.22 159	90.03 193	91.78 464	98.04 56	90.42 174	91.66 235	90.65 409	86.49 136	97.46 315	81.78 373	96.31 180	99.28 120

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

MCST-MVS		98.18 3	97.95 11	98.86 6	99.85 4	96.60 12	99.70 42	97.98 61	97.18 12	95.96 127	99.33 27	92.62 30	100.00 1	98.99 43	99.93 1	99.98 7

fmvsm_s_conf0.5_n_10		96.95 36	96.82 41	97.33 64	97.76 125	93.00 100	99.87 7	97.95 62	97.32 10	99.71 4	99.20 42	81.48 235	99.90 63	99.32 25	98.78 110	99.09 139

testing3		87.75 336	88.22 313	86.36 436	94.66 312	77.41 453	99.52 73	97.95 62	86.05 333	81.12 384	96.69 265	86.18 142	89.31 493	61.65 485	90.12 311	92.35 353

testing915		95.97 78	95.46 96	97.50 54	97.05 176	94.32 64	99.08 142	97.94 64	90.40 175	96.01 125	97.09 229	90.37 60	98.39 213	97.45 85	93.74 241	99.80 43

fmvsm_s_conf0.5_n_7		95.87 85	96.25 62	94.72 234	96.19 216	87.74 276	99.66 51	97.94 64	95.78 32	98.44 54	99.23 36	81.26 241	99.90 63	99.17 35	98.57 122	96.52 310

reproduce_monomvs		92.11 235	91.82 224	92.98 300	98.25 106	90.55 171	98.38 259	97.93 66	94.81 48	80.46 392	92.37 364	96.46 3	97.17 326	94.06 179	73.61 421	91.23 404

testing222		94.48 142	94.00 137	95.95 159	97.30 154	92.27 121	98.82 171	97.92 67	89.20 224	94.82 155	97.26 210	87.13 114	97.32 323	91.95 229	91.56 289	98.25 235

1314		93.44 183	91.98 218	97.84 38	95.24 262	94.38 61	96.22 395	97.92 67	90.18 185	82.28 362	97.71 176	77.63 290	99.80 101	91.94 230	98.67 115	99.34 115

NCCC		98.12 6	98.11 3	98.13 28	99.76 7	94.46 57	99.81 21	97.88 69	96.54 23	98.84 37	99.46 15	92.55 31	99.98 14	98.25 70	99.93 1	99.94 19

tfpnnormal		83.65 401	81.35 407	90.56 368	91.37 406	88.06 267	97.29 346	97.87 70	78.51 440	76.20 433	90.91 399	64.78 416	96.47 359	61.71 484	73.50 424	87.13 473

TestfortrainingZip a		97.38 22	97.10 27	98.24 23	99.75 8	94.82 47	99.65 53	97.86 71	94.03 66	99.04 29	99.49 12	90.76 52	99.99 9	95.87 129	97.45 155	99.90 23

ETVMVS		94.50 141	93.90 147	96.31 131	97.48 144	92.98 101	99.07 144	97.86 71	88.09 274	94.40 166	96.90 248	88.35 87	97.28 324	90.72 247	92.25 276	98.66 203

fmvsm_l_conf0.5_n_9		97.33 23	97.32 25	97.37 62	97.64 131	92.45 118	99.93 1	97.85 73	97.39 7	99.84 2	99.09 70	85.42 157	99.92 50	99.52 23	99.20 83	99.73 59

3Dnovator	87.35 11	93.17 199	91.77 226	97.37 62	95.41 254	93.07 97	98.82 171	97.85 73	91.53 134	82.56 355	97.58 186	71.97 353	99.82 96	91.01 240	99.23 78	99.22 126

UWE-MVS		93.18 197	93.40 166	92.50 316	96.56 193	83.55 384	98.09 293	97.84 75	89.50 216	91.72 233	96.23 281	91.08 41	96.70 346	86.28 306	93.33 249	97.26 282

FE-MVS		91.38 251	90.16 264	95.05 218	96.46 199	87.53 291	89.69 482	97.84 75	82.97 392	92.18 223	92.00 372	84.07 181	98.93 181	80.71 380	95.52 199	98.68 197

WR-MVS		88.54 326	87.22 331	92.52 315	91.93 395	89.50 211	98.56 224	97.84 75	86.99 308	81.87 376	93.81 333	74.25 330	95.92 397	85.29 317	74.43 412	92.12 362

DELS-MVS		97.12 30	96.60 50	98.68 13	98.03 117	96.57 13	99.84 15	97.84 75	96.36 28	95.20 149	98.24 149	88.17 90	99.83 93	96.11 122	99.60 54	99.64 78
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
fmvsm_s_conf0.5_n_8		97.06 34	96.94 31	97.44 55	97.78 124	92.77 109	99.83 16	97.83 79	97.58 4	99.25 20	99.20 42	82.71 211	99.92 50	99.64 8	98.61 118	99.64 78

fmvsm_s_conf0.5_n_3		96.58 55	96.55 51	96.66 107	97.23 158	92.59 115	99.81 21	97.82 80	97.35 8	99.42 11	99.16 52	80.27 248	99.93 47	99.26 28	98.60 120	97.45 274

EI-MVSNet-Vis-set		95.76 93	95.63 94	96.17 142	99.14 72	90.33 177	98.49 234	97.82 80	91.92 125	94.75 158	98.88 103	87.06 117	99.48 140	95.40 143	97.17 163	98.70 194

无先验							98.52 228	97.82 80	87.20 305				99.90 63	87.64 284		99.85 35

EPNet_dtu		92.28 229	92.15 214	92.70 312	97.29 155	84.84 367	98.64 202	97.82 80	92.91 101	93.02 199	97.02 237	85.48 155	95.70 413	72.25 445	94.89 214	97.55 272
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SDMVSNet		91.09 259	89.91 266	94.65 236	96.80 186	90.54 172	97.78 317	97.81 84	88.34 265	85.73 318	95.26 309	66.44 405	98.26 220	94.25 176	86.75 324	95.14 328

HFP-MVS		96.42 61	96.26 61	96.90 90	99.69 14	90.96 159	99.47 79	97.81 84	90.54 169	96.88 99	99.05 76	87.57 102	99.96 34	95.65 132	99.72 34	99.78 47

EI-MVSNet-UG-set		95.43 104	95.29 101	95.86 163	99.07 78	89.87 198	98.43 242	97.80 86	91.78 127	94.11 173	98.77 108	86.25 141	99.48 140	94.95 159	96.45 176	98.22 239

ACMMPR		96.28 66	96.14 73	96.73 100	99.68 15	90.47 174	99.47 79	97.80 86	90.54 169	96.83 104	99.03 78	86.51 135	99.95 38	95.65 132	99.72 34	99.75 55

UWE-MVS-28		90.99 264	91.93 221	88.15 416	95.12 274	77.87 451	97.18 355	97.79 88	88.72 248	88.69 292	96.52 269	86.54 133	90.75 483	84.64 327	92.16 280	95.83 325

UBG		95.73 97	95.41 97	96.69 104	96.97 179	93.23 91	99.13 137	97.79 88	91.28 143	94.38 168	96.78 259	92.37 33	98.56 203	96.17 118	93.84 235	98.26 234

MAR-MVS		94.43 143	94.09 134	95.45 183	99.10 76	87.47 293	98.39 257	97.79 88	88.37 263	94.02 176	99.17 51	78.64 279	99.91 58	92.48 220	98.85 102	98.96 153
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
FBQ-MVS		94.65 136	94.17 132	96.09 148	97.22 159	90.65 170	98.93 160	97.78 91	90.19 184	95.02 153	96.47 273	87.80 97	98.41 212	91.72 234	92.45 267	99.21 127

DPM-MVS		97.86 10	97.25 26	99.68 1	98.25 106	99.10 1	99.76 33	97.78 91	96.61 22	98.15 64	99.53 8	93.62 19	100.00 1	91.79 232	99.80 26	99.94 19

API-MVS		94.78 128	94.18 131	96.59 111	99.21 69	90.06 192	98.80 175	97.78 91	83.59 381	93.85 181	99.21 41	83.79 183	99.97 26	92.37 223	99.00 91	99.74 56

新几何1				97.40 60	98.92 89	92.51 117		97.77 94	85.52 343	96.69 112	99.06 74	88.08 94	99.89 71	84.88 323	99.62 50	99.79 44

HPM-MVS++		97.72 14	97.59 15	98.14 27	99.53 46	94.76 49	99.19 117	97.75 95	95.66 36	98.21 63	99.29 30	91.10 40	99.99 9	97.68 81	99.87 9	99.68 68

GG-mvs-BLEND				96.98 84	96.53 195	94.81 48	87.20 485	97.74 96		93.91 179	96.40 275	96.56 2	96.94 337	95.08 152	98.95 96	99.20 128

gg-mvs-nofinetune		90.00 293	87.71 320	96.89 94	96.15 218	94.69 53	85.15 492	97.74 96	68.32 488	92.97 203	60.16 521	96.10 4	96.84 340	93.89 182	98.87 101	99.14 132

旧先验1					98.97 81	92.90 106		97.74 96			99.15 56	91.05 42			99.33 70	99.60 84

IU-MVS					99.63 24	95.38 27		97.73 99	95.54 38	99.54 10				99.69 7	99.81 23	99.99 2

SED-MVS		98.18 3	98.10 4	98.41 20	99.63 24	95.24 30	99.77 30	97.72 100	94.17 61	99.30 18	99.54 4	93.32 22	99.98 14	99.70 5	99.81 23	99.99 2

test_241102_TWO								97.72 100	94.17 61	99.23 21	99.54 4	93.14 27	99.98 14	99.70 5	99.82 19	99.99 2

test_241102_ONE					99.63 24	95.24 30		97.72 100	94.16 63	99.30 18	99.49 12	93.32 22	99.98 14

DPE-MVS		98.11 7	98.00 8	98.44 18	99.50 48	95.39 26	99.29 106	97.72 100	94.50 54	98.64 45	99.54 4	93.32 22	99.97 26	99.58 12	99.90 7	99.95 16
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DeepPCF-MVS	93.56 1	96.55 58	97.84 12	92.68 313	98.71 97	78.11 448	99.70 42	97.71 104	98.18 1	97.36 87	99.76 1	90.37 60	99.94 41	99.27 27	99.54 58	99.99 2

myMVS_eth3d28		95.74 96	95.34 99	96.92 89	97.41 145	93.58 82	99.28 109	97.70 105	90.97 150	93.91 179	97.25 212	90.59 54	98.75 192	96.85 101	94.14 229	98.44 218

fmvsm_l_conf0.5_n_3		97.12 30	96.89 35	97.79 45	97.39 147	93.84 73	99.87 7	97.70 105	97.34 9	99.39 14	99.20 42	82.86 203	99.94 41	99.21 33	99.07 86	99.58 88

test0726					99.66 18	95.20 35	99.77 30	97.70 105	93.95 68	99.35 16	99.54 4	93.18 25

MSP-MVS		97.77 12	98.18 2	96.53 116	99.54 42	90.14 185	99.41 93	97.70 105	95.46 40	98.60 47	99.19 46	95.71 5	99.49 136	98.15 72	99.85 13	99.95 16
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
MSC_two_6792asdad				99.51 2	99.61 30	98.60 2		97.69 109					99.98 14	99.55 16	99.83 15	99.96 11

No_MVS				99.51 2	99.61 30	98.60 2		97.69 109					99.98 14	99.55 16	99.83 15	99.96 11

fmvsm_s_conf0.5_n_6		96.78 44	96.64 49	97.20 72	96.03 227	93.20 93	99.82 20	97.68 111	95.20 43	99.61 7	99.11 68	84.52 173	99.90 63	99.04 40	98.77 111	98.50 215

testing11		95.33 108	94.98 114	96.37 126	97.20 161	92.31 120	99.29 106	97.68 111	90.59 165	94.43 164	97.20 216	90.79 51	98.60 201	95.25 148	92.38 270	98.18 243

DVP-MVS++		98.18 3	98.09 6	98.44 18	99.61 30	95.38 27	99.55 67	97.68 111	93.01 95	99.23 21	99.45 19	95.12 9	99.98 14	99.25 30	99.92 3	99.97 8

test_0728_SECOND				98.77 9	99.66 18	96.37 16	99.72 39	97.68 111					99.98 14	99.64 8	99.82 19	99.96 11

test11								97.68 111

fmvsm_s_conf0.1_n		95.56 101	95.68 89	95.20 208	94.35 323	89.10 226	99.50 75	97.67 116	94.76 51	98.68 44	99.03 78	81.13 242	99.86 83	98.63 51	97.36 158	96.63 303

testing91		94.88 123	94.44 122	96.21 137	97.19 163	91.90 130	99.23 114	97.66 117	89.91 195	93.66 186	97.05 236	90.21 64	98.50 204	93.52 193	91.53 294	98.25 235

testing99		94.88 123	94.45 121	96.17 142	97.20 161	91.91 129	99.20 116	97.66 117	89.95 194	93.68 185	97.06 234	90.28 63	98.50 204	93.52 193	91.54 291	98.12 250

TEST9					99.57 39	93.17 94	99.38 96	97.66 117	89.57 212	98.39 56	99.18 49	90.88 47	99.66 118

train_agg		97.20 28	97.08 28	97.57 52	99.57 39	93.17 94	99.38 96	97.66 117	90.18 185	98.39 56	99.18 49	90.94 43	99.66 118	98.58 55	99.85 13	99.88 29

region2R		96.30 65	96.17 69	96.70 103	99.70 13	90.31 178	99.46 83	97.66 117	90.55 168	97.07 95	99.07 71	86.85 121	99.97 26	95.43 142	99.74 31	99.81 40

SteuartSystems-ACMMP		97.25 24	97.34 24	97.01 79	97.38 148	91.46 143	99.75 36	97.66 117	94.14 65	98.13 65	99.26 31	92.16 35	99.66 118	97.91 76	99.64 44	99.90 23
Skip Steuart: Steuart Systems R&D Blog.
EPP-MVSNet		93.75 170	93.67 156	94.01 274	95.86 232	85.70 350	98.67 198	97.66 117	84.46 366	91.36 244	97.18 219	91.16 38	97.79 283	92.93 213	93.75 240	98.53 213

fmvsm_s_conf0.5_n_2		95.85 87	95.83 80	95.91 161	97.19 163	91.79 131	99.78 29	97.65 124	97.23 11	99.22 23	99.06 74	75.93 309	99.90 63	99.30 26	97.09 165	96.02 322

SMA-MVS		97.24 25	96.99 29	98.00 34	99.30 60	94.20 66	99.16 124	97.65 124	89.55 214	99.22 23	99.52 11	90.34 62	99.99 9	98.32 67	99.83 15	99.82 37
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
test_one_0601					99.59 34	94.89 40		97.64 126	93.14 94	98.93 34	99.45 19	93.45 20

test_8					99.55 41	93.07 97	99.37 99	97.64 126	90.18 185	98.36 58	99.19 46	90.94 43	99.64 124

agg_prior					99.54 42	92.66 110		97.64 126		97.98 74			99.61 126

DeepC-MVS_fast	93.52 2	97.16 29	96.84 38	98.13 28	99.61 30	94.45 58	98.85 168	97.64 126	96.51 26	95.88 130	99.39 23	87.35 111	99.99 9	96.61 107	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 72	99.65 53	97.63 130	95.69 34

原ACMM1				96.18 140	99.03 79	90.08 188		97.63 130	88.98 235	97.00 97	98.97 84	88.14 93	99.71 114	88.23 277	99.62 50	98.76 183

test-260524					99.74 11	96.14 18		97.62 132		97.79 79		91.57 37	100.00 1	99.55 16	99.75 29

DU-MVS		88.83 316	87.51 324	92.79 306	91.46 404	90.07 189	98.71 188	97.62 132	88.87 241	83.21 342	93.68 336	74.63 320	95.93 395	86.95 291	72.47 434	92.36 350

ZD-MVS					99.67 16	93.28 90		97.61 134	87.78 288	97.41 85	99.16 52	90.15 65	99.56 129	98.35 65	99.70 39

CP-MVS		96.22 68	96.15 72	96.42 121	99.67 16	89.62 209	99.70 42	97.61 134	90.07 192	96.00 126	99.16 52	87.43 105	99.92 50	96.03 125	99.72 34	99.70 63

thisisatest0530		94.00 155	93.52 159	95.43 186	95.76 237	90.02 194	98.99 155	97.60 136	86.58 321	91.74 232	97.36 201	94.78 12	98.34 215	86.37 304	92.48 266	97.94 256

tttt0517		93.30 192	93.01 181	94.17 265	95.57 244	86.47 317	98.51 231	97.60 136	85.99 334	90.55 259	97.19 218	94.80 11	98.31 216	85.06 320	91.86 282	97.74 260

thisisatest0515		94.75 129	94.19 129	96.43 120	96.13 223	92.64 113	99.47 79	97.60 136	87.55 297	93.17 195	97.59 185	94.71 13	98.42 211	88.28 276	93.20 250	98.24 238

testdata				95.26 203	98.20 109	87.28 300		97.60 136	85.21 347	98.48 53	99.15 56	88.15 92	98.72 196	90.29 250	99.45 64	99.78 47

ACMMP_NAP		96.59 53	96.18 66	97.81 42	98.82 93	93.55 84	98.88 167	97.59 140	90.66 160	97.98 74	99.14 59	86.59 130	100.00 1	96.47 111	99.46 61	99.89 28

CVMVSNet		90.30 284	90.91 247	88.46 415	94.32 328	73.58 472	97.61 334	97.59 140	90.16 188	88.43 296	97.10 225	76.83 298	92.86 462	82.64 359	93.54 244	98.93 159

XVS		96.47 59	96.37 58	96.77 96	99.62 28	90.66 168	99.43 90	97.58 142	92.41 113	96.86 100	98.96 89	87.37 107	99.87 77	95.65 132	99.43 66	99.78 47

X-MVStestdata		90.69 271	88.66 302	96.77 96	99.62 28	90.66 168	99.43 90	97.58 142	92.41 113	96.86 100	29.59 545	87.37 107	99.87 77	95.65 132	99.43 66	99.78 47

test222					98.32 104	91.21 147	98.08 296	97.58 142	83.74 377	95.87 131	99.02 80	86.74 124			99.64 44	99.81 40

test_prior				97.01 79	99.58 36	91.77 133		97.57 145					99.49 136			99.79 44

CP-MVSNet		86.54 357	85.45 357	89.79 389	91.02 411	82.78 397	97.38 343	97.56 146	85.37 345	79.53 405	93.03 354	71.86 355	95.25 429	79.92 385	73.43 428	91.34 398

fmvsm_s_conf0.5_n_9		96.76 46	96.92 32	96.29 132	97.95 119	89.21 221	99.81 21	97.55 147	97.04 15	99.68 6	99.22 38	82.84 205	99.94 41	99.56 15	98.61 118	99.71 61

test12				97.83 41	99.33 59	94.45 58		97.55 147		97.56 81		88.60 84	99.50 135		99.71 38	99.55 89

PAPR		96.35 62	95.82 82	97.94 36	99.63 24	94.19 67	99.42 92	97.55 147	92.43 110	93.82 184	99.12 64	87.30 112	99.91 58	94.02 180	99.06 87	99.74 56

AdaColmap		93.82 168	93.06 178	96.10 147	99.88 1	89.07 228	98.33 263	97.55 147	86.81 316	90.39 264	98.65 121	75.09 319	99.98 14	93.32 200	97.53 152	99.26 122

TESTMET0.1,1		93.82 168	93.26 172	95.49 182	95.21 266	90.25 179	99.15 129	97.54 151	89.18 226	91.79 231	94.87 314	89.13 74	97.63 303	86.21 307	96.29 183	98.60 208

fmvsm_s_conf0.1_n_a		95.16 114	95.15 106	95.18 209	92.06 390	88.94 239	99.29 106	97.53 152	94.46 56	98.98 31	98.99 82	79.99 251	99.85 87	98.24 71	96.86 170	96.73 300

hse-mvs2		91.67 245	91.51 231	92.15 323	96.22 212	82.61 402	97.74 323	97.53 152	93.85 76	96.27 122	96.15 283	83.19 197	97.44 317	95.81 130	66.86 463	96.40 315

AUN-MVS		90.17 289	89.50 276	92.19 321	96.21 213	82.67 398	97.76 322	97.53 152	88.05 275	91.67 234	96.15 283	83.10 199	97.47 314	88.11 279	66.91 462	96.43 314

ZNCC-MVS		96.09 72	95.81 84	96.95 87	99.42 53	91.19 148	99.55 67	97.53 152	89.72 203	95.86 132	98.94 95	86.59 130	99.97 26	95.13 151	99.56 56	99.68 68

CANet		97.00 35	96.49 53	98.55 14	98.86 92	96.10 19	99.83 16	97.52 156	95.90 30	97.21 91	98.90 99	82.66 213	99.93 47	98.71 47	98.80 106	99.63 81

APDe-MVS		97.53 18	97.47 19	97.70 46	99.58 36	93.63 79	99.56 66	97.52 156	93.59 85	98.01 73	99.12 64	90.80 50	99.55 130	99.26 28	99.79 27	99.93 21
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MDTV_nov1_ep13			90.47 261		96.14 220	88.55 254	91.34 472	97.51 158	89.58 211	92.24 221	90.50 419	86.99 120	97.61 305	77.64 401	92.34 272

QAPM		91.41 250	89.49 277	97.17 74	95.66 241	93.42 88	98.60 215	97.51 158	80.92 426	81.39 383	97.41 197	72.89 345	99.87 77	82.33 365	98.68 114	98.21 240

PAPM_NR		95.43 104	95.05 111	96.57 114	99.42 53	90.14 185	98.58 221	97.51 158	90.65 162	92.44 218	98.90 99	87.77 100	99.90 63	90.88 242	99.32 71	99.68 68

TSAR-MVS + MP.		97.44 21	97.46 20	97.39 61	99.12 73	93.49 87	98.52 228	97.50 161	94.46 56	98.99 30	98.64 122	91.58 36	99.08 174	98.49 59	99.83 15	99.60 84
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 92	95.00 113	98.06 32	97.35 150	95.68 23	99.71 41	97.50 161	91.50 135	96.16 124	98.61 126	86.28 139	99.00 177	96.19 116	91.74 285	99.51 95

9.14			96.87 36		99.34 56		99.50 75	97.49 163	89.41 220	98.59 48	99.43 21	89.78 68	99.69 115	98.69 48	99.62 50

GST-MVS		95.97 78	95.66 90	96.90 90	99.49 51	91.22 146	99.45 85	97.48 164	89.69 205	95.89 129	98.72 114	86.37 138	99.95 38	94.62 168	99.22 79	99.52 92

DP-MVS Recon		95.85 87	95.15 106	97.95 35	99.87 2	94.38 61	99.60 62	97.48 164	86.58 321	94.42 165	99.13 61	87.36 110	99.98 14	93.64 190	98.33 131	99.48 99

FOURS1					99.50 48	88.94 239	99.55 67	97.47 166	91.32 142	98.12 67

DVP-MVS		98.07 8	98.00 8	98.29 21	99.66 18	95.20 35	99.72 39	97.47 166	93.95 68	99.07 27	99.46 15	93.18 25	99.97 26	99.64 8	99.82 19	99.69 66
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		94.60 137	94.43 123	95.09 213	99.66 18	86.85 309	99.44 86	97.47 166	83.22 386	94.34 169	98.96 89	82.50 215	99.55 130	94.81 161	99.50 59	98.88 164

BP-MVS1		96.59 53	96.36 59	97.29 66	95.05 286	94.72 51	99.44 86	97.45 169	92.71 105	96.41 118	98.50 132	94.11 17	98.50 204	95.61 137	97.97 139	98.66 203

SF-MVS		97.22 27	96.92 32	98.12 30	99.11 74	94.88 41	99.44 86	97.45 169	89.60 210	98.70 42	99.42 22	90.42 58	99.72 113	98.47 60	99.65 42	99.77 52

MTGPA								97.45 169

MTAPA		96.09 72	95.80 85	96.96 86	99.29 61	91.19 148	97.23 351	97.45 169	92.58 107	94.39 167	99.24 35	86.43 137	99.99 9	96.22 115	99.40 69	99.71 61

CDPH-MVS		96.56 57	96.18 66	97.70 46	99.59 34	93.92 70	99.13 137	97.44 173	89.02 234	97.90 76	99.22 38	88.90 80	99.49 136	94.63 167	99.79 27	99.68 68

APD-MVS		96.95 36	96.72 46	97.63 48	99.51 47	93.58 82	99.16 124	97.44 173	90.08 191	98.59 48	99.07 71	89.06 75	99.42 147	97.92 75	99.66 41	99.88 29
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PVSNet_Blended_VisFu		94.67 134	94.11 133	96.34 128	97.14 168	91.10 153	99.32 105	97.43 175	92.10 124	91.53 240	96.38 278	83.29 193	99.68 116	93.42 199	96.37 178	98.25 235

NR-MVSNet		87.74 339	86.00 348	92.96 302	91.46 404	90.68 167	96.65 377	97.42 176	88.02 277	73.42 452	93.68 336	77.31 292	95.83 403	84.26 332	71.82 441	92.36 350

MP-MVS		96.00 75	95.82 82	96.54 115	99.47 52	90.13 187	99.36 100	97.41 177	90.64 163	95.49 144	98.95 92	85.51 152	99.98 14	96.00 126	99.59 55	99.52 92
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
mPP-MVS		95.90 84	95.75 87	96.38 125	99.58 36	89.41 215	99.26 112	97.41 177	90.66 160	94.82 155	98.95 92	86.15 143	99.98 14	95.24 149	99.64 44	99.74 56

OpenMVS	85.28 14	90.75 269	88.84 297	96.48 117	93.58 358	93.51 86	98.80 175	97.41 177	82.59 400	78.62 416	97.49 192	68.00 386	99.82 96	84.52 330	98.55 124	96.11 319

fmvsm_s_conf0.5_n_5		96.46 60	96.23 63	97.15 75	96.42 201	92.80 107	99.83 16	97.39 180	94.50 54	98.71 41	99.13 61	82.52 214	99.90 63	99.24 32	98.38 129	98.74 185

reproduce-ours		96.66 49	96.80 42	96.22 135	98.95 85	89.03 231	98.62 208	97.38 181	93.42 87	96.80 108	99.36 24	88.92 78	99.80 101	98.51 57	99.26 76	99.82 37

our_new_method		96.66 49	96.80 42	96.22 135	98.95 85	89.03 231	98.62 208	97.38 181	93.42 87	96.80 108	99.36 24	88.92 78	99.80 101	98.51 57	99.26 76	99.82 37

tt0805		86.50 359	84.79 368	91.63 343	91.97 391	81.49 411	96.49 382	97.38 181	82.24 408	82.44 357	95.82 296	51.22 472	98.25 221	84.55 329	80.96 370	95.13 330

SD-MVS		97.51 19	97.40 22	97.81 42	99.01 80	93.79 75	99.33 104	97.38 181	93.73 80	98.83 38	99.02 80	90.87 48	99.88 73	98.69 48	99.74 31	99.77 52
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		89.16 305	87.76 318	93.35 293	97.19 163	84.75 369	90.58 480	97.36 185	81.99 411	84.56 328	89.31 440	83.98 182	98.17 230	74.85 422	90.00 313	97.12 285

PS-CasMVS		85.81 371	84.58 373	89.49 399	90.77 413	82.11 405	97.20 353	97.36 185	84.83 357	79.12 412	92.84 358	67.42 392	95.16 431	78.39 398	73.25 429	91.21 405

0.3-1-1-0.015		91.27 253	89.64 272	96.15 146	92.69 378	91.62 138	99.74 37	97.35 187	84.68 362	92.71 210	93.18 349	85.31 162	97.75 292	92.11 226	68.98 451	99.09 139

0.4-1-1-0.1		91.07 260	89.43 279	96.01 154	92.48 381	91.23 145	99.69 49	97.34 188	84.50 365	92.49 216	92.98 357	84.53 172	97.72 297	91.87 231	68.97 453	99.08 143

0.4-1-1-0.2		91.19 258	89.53 275	96.20 138	92.78 377	91.76 135	99.76 33	97.34 188	84.77 358	92.54 214	93.05 353	84.51 174	97.74 295	92.01 227	68.98 451	99.09 139

reproduce_model		96.57 56	96.75 45	96.02 152	98.93 88	88.46 257	98.56 224	97.34 188	93.18 93	96.96 98	99.35 26	88.69 83	99.80 101	98.53 56	99.21 82	99.79 44

SR-MVS		96.13 71	96.16 71	96.07 149	99.42 53	89.04 229	98.59 218	97.33 191	90.44 172	96.84 102	99.12 64	86.75 123	99.41 150	97.47 84	99.44 65	99.76 54

WB-MVSnew		88.69 322	88.34 310	89.77 390	94.30 334	85.99 342	98.14 284	97.31 192	87.15 306	87.85 299	96.07 287	69.91 366	95.52 419	72.83 441	91.47 295	87.80 464

PatchmatchNet		92.05 237	91.04 242	95.06 216	96.17 217	89.04 229	91.26 473	97.26 193	89.56 213	90.64 256	90.56 415	88.35 87	97.11 329	79.53 386	96.07 190	99.03 147
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
FA-MVS(test-final)		92.22 232	91.08 241	95.64 174	96.05 226	88.98 236	91.60 467	97.25 194	86.99 308	91.84 230	92.12 366	83.03 200	99.00 177	86.91 293	93.91 233	98.93 159

test-LLR		93.11 203	92.68 192	94.40 250	94.94 297	87.27 301	99.15 129	97.25 194	90.21 182	91.57 236	94.04 322	84.89 167	97.58 309	85.94 311	96.13 186	98.36 230

test-mter		93.27 195	92.89 187	94.40 250	94.94 297	87.27 301	99.15 129	97.25 194	88.95 237	91.57 236	94.04 322	88.03 95	97.58 309	85.94 311	96.13 186	98.36 230

PEN-MVS		85.21 380	83.93 383	89.07 408	89.89 423	81.31 417	97.09 358	97.24 197	84.45 367	78.66 415	92.68 361	68.44 381	94.87 436	75.98 414	70.92 445	91.04 409

nomal-1		93.28 194	92.96 184	94.27 257	96.12 224	87.08 306	98.16 283	97.23 198	88.41 261	88.79 290	94.03 324	87.66 101	97.86 277	93.72 189	92.50 265	97.86 258

ab-mvs		91.05 263	89.17 285	96.69 104	95.96 229	91.72 136	92.62 456	97.23 198	85.61 342	89.74 279	93.89 332	68.55 379	99.42 147	91.09 238	87.84 319	98.92 161

APD-MVS_3200maxsize		95.64 100	95.65 92	95.62 178	99.24 66	87.80 275	98.42 245	97.22 200	88.93 239	96.64 115	98.98 83	85.49 153	99.36 154	96.68 104	99.27 75	99.70 63

SR-MVS-dyc-post		95.75 94	95.86 79	95.41 188	99.22 67	87.26 303	98.40 252	97.21 201	89.63 207	96.67 113	98.97 84	86.73 126	99.36 154	96.62 105	99.31 72	99.60 84

RE-MVS-def			95.70 88		99.22 67	87.26 303	98.40 252	97.21 201	89.63 207	96.67 113	98.97 84	85.24 163		96.62 105	99.31 72	99.60 84

SCA		90.64 274	89.25 284	94.83 228	94.95 296	88.83 244	96.26 392	97.21 201	90.06 193	90.03 272	90.62 411	66.61 402	96.81 342	83.16 351	94.36 225	98.84 168

RPMNet		85.07 382	81.88 401	94.64 238	93.47 361	86.24 325	84.97 494	97.21 201	64.85 496	90.76 254	78.80 501	80.95 244	99.27 161	53.76 499	92.17 278	98.41 220

VPNet		88.30 328	86.57 339	93.49 289	91.95 393	91.35 144	98.18 280	97.20 205	88.61 251	84.52 330	94.89 313	62.21 430	96.76 345	89.34 263	72.26 437	92.36 350

KinetiMVS		93.07 205	91.98 218	96.34 128	94.84 303	91.78 132	98.73 187	97.18 206	91.25 144	94.01 177	97.09 229	71.02 362	98.86 183	86.77 297	96.89 169	98.37 227

TranMVSNet+NR-MVSNet		87.75 336	86.31 343	92.07 325	90.81 412	88.56 253	98.33 263	97.18 206	87.76 289	81.87 376	93.90 331	72.45 347	95.43 423	83.13 353	71.30 444	92.23 356

cdsmvs_eth3d_5k		22.52 506	30.03 503	0.00 543	0.00 567	0.00 570	0.00 555	97.17 208	0.00 562	0.00 563	98.77 108	74.35 327	0.00 564	0.00 562	0.00 562	0.00 559

tpm2		91.77 243	91.09 240	93.82 281	94.83 304	85.56 353	92.51 457	97.16 209	84.00 372	93.83 183	90.66 408	87.54 103	97.17 326	87.73 283	91.55 290	98.72 191

MP-MVS-pluss		95.80 90	95.30 100	97.29 66	98.95 85	92.66 110	98.59 218	97.14 210	88.95 237	93.12 196	99.25 33	85.62 149	99.94 41	96.56 109	99.48 60	99.28 120
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
PatchMatch-RL		91.47 248	90.54 258	94.26 259	98.20 109	86.36 322	96.94 363	97.14 210	87.75 290	88.98 288	95.75 297	71.80 356	99.40 151	80.92 378	97.39 157	97.02 291

Anonymous20240529		87.66 340	85.58 354	93.92 277	97.59 136	85.01 364	98.13 285	97.13 212	66.69 493	88.47 295	96.01 289	55.09 458	99.51 134	87.00 290	84.12 346	97.23 284

JIA-IIPM		85.97 367	84.85 366	89.33 402	93.23 368	73.68 471	85.05 493	97.13 212	69.62 484	91.56 238	68.03 517	88.03 95	96.96 335	77.89 400	93.12 251	97.34 277

PS-MVSNAJ		96.87 39	96.40 57	98.29 21	97.35 150	97.29 6	99.03 150	97.11 214	95.83 31	98.97 32	99.14 59	82.48 217	99.60 127	98.60 52	99.08 84	98.00 253

HPM-MVS_fast		94.89 121	94.62 118	95.70 170	99.11 74	88.44 258	99.14 132	97.11 214	85.82 338	95.69 139	98.47 140	83.46 188	99.32 159	93.16 208	99.63 49	99.35 113

DeepC-MVS	91.02 4	94.56 140	93.92 144	96.46 118	97.16 167	90.76 164	98.39 257	97.11 214	93.92 70	88.66 293	98.33 145	78.14 285	99.85 87	95.02 154	98.57 122	98.78 179
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
tpmrst		92.78 213	92.16 213	94.65 236	96.27 210	87.45 294	91.83 463	97.10 217	89.10 233	94.68 161	90.69 406	88.22 89	97.73 296	89.78 256	91.80 284	98.77 181

HPM-MVS		95.41 106	95.22 104	95.99 156	99.29 61	89.14 225	99.17 123	97.09 218	87.28 303	95.40 145	98.48 139	84.93 166	99.38 152	95.64 136	99.65 42	99.47 101
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
tpm cat1		88.89 312	87.27 329	93.76 284	95.79 235	85.32 358	90.76 478	97.09 218	76.14 453	85.72 320	88.59 443	82.92 202	98.04 260	76.96 405	91.43 296	97.90 257

dp		90.16 290	88.83 298	94.14 266	96.38 206	86.42 318	91.57 468	97.06 220	84.76 359	88.81 289	90.19 428	84.29 178	97.43 318	75.05 419	91.35 300	98.56 211

xiu_mvs_v2_base		96.66 49	96.17 69	98.11 31	97.11 172	96.96 7	99.01 153	97.04 221	95.51 39	98.86 36	99.11 68	82.19 225	99.36 154	98.59 54	98.14 136	98.00 253

3Dnovator+	87.72 8	93.43 185	91.84 223	98.17 26	95.73 238	95.08 38	98.92 163	97.04 221	91.42 139	81.48 382	97.60 184	74.60 322	99.79 105	90.84 243	98.97 93	99.64 78

sd_testset		89.23 304	88.05 317	92.74 309	96.80 186	85.33 357	95.85 410	97.03 223	88.34 265	85.73 318	95.26 309	61.12 435	97.76 291	85.61 315	86.75 324	95.14 328

CDS-MVSNet		93.47 181	93.04 180	94.76 230	94.75 308	89.45 213	98.82 171	97.03 223	87.91 281	90.97 249	96.48 272	89.06 75	96.36 365	89.50 259	92.81 256	98.49 216
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test0.0.03 1		88.96 310	88.61 303	90.03 384	91.09 409	84.43 372	98.97 158	97.02 225	90.21 182	80.29 394	96.31 280	84.89 167	91.93 477	72.98 438	85.70 335	93.73 336

114514_t		94.06 153	93.05 179	97.06 77	99.08 77	92.26 122	98.97 158	97.01 226	82.58 401	92.57 213	98.22 150	80.68 246	99.30 160	89.34 263	99.02 90	99.63 81

CostFormer		92.89 208	92.48 200	94.12 267	94.99 291	85.89 345	92.89 452	97.00 227	86.98 311	95.00 154	90.78 402	90.05 66	97.51 313	92.92 215	91.73 286	98.96 153

test_fmvsmvis_n_1920		95.47 103	95.40 98	95.70 170	94.33 327	90.22 182	99.70 42	96.98 228	96.80 17	92.75 208	98.89 101	82.46 220	99.92 50	98.36 64	98.33 131	96.97 293

fmvsm_l_mol_unc0.5_1		98.26 2	98.09 6	98.75 10	97.31 153	96.69 10	99.89 5	96.97 229	97.78 2	99.69 5	99.31 29	92.95 28	99.92 50	99.50 24	99.46 61	99.65 76

ET-MVSNet_ETH3D		92.56 222	91.45 232	95.88 162	96.39 205	94.13 68	99.46 83	96.97 229	92.18 121	66.94 484	98.29 148	94.65 15	94.28 446	94.34 174	83.82 350	99.24 123

UA-Net		93.30 192	92.62 196	95.34 193	96.27 210	88.53 256	95.88 407	96.97 229	90.90 151	95.37 146	97.07 233	82.38 222	99.10 173	83.91 342	94.86 216	98.38 224

TAMVS		92.62 219	92.09 216	94.20 264	94.10 336	87.68 278	98.41 248	96.97 229	87.53 298	89.74 279	96.04 288	84.77 171	96.49 358	88.97 271	92.31 273	98.42 219

kuosan		84.40 393	83.34 387	87.60 422	95.87 231	79.21 435	92.39 458	96.87 233	76.12 454	73.79 449	93.98 328	81.51 233	90.63 484	64.13 477	75.42 401	92.95 341

guyue		94.21 149	93.72 155	95.66 173	95.22 264	90.17 184	98.74 184	96.85 234	93.67 81	93.01 201	96.72 263	78.83 273	98.06 254	96.04 124	94.44 223	98.77 181

test_fmvsmconf0.1_n		95.94 82	95.79 86	96.40 123	92.42 383	89.92 196	99.79 28	96.85 234	96.53 25	97.22 90	98.67 120	82.71 211	99.84 89	98.92 45	98.98 92	99.43 106

dongtai		81.36 419	80.61 411	83.62 458	94.25 335	73.32 473	95.15 422	96.81 236	73.56 471	69.79 469	92.81 359	81.00 243	86.80 503	52.08 504	70.06 447	90.75 419

Vis-MVSNet		92.64 218	91.85 222	95.03 219	95.12 274	88.23 263	98.48 236	96.81 236	91.61 130	92.16 224	97.22 215	71.58 359	98.00 266	85.85 314	97.81 142	98.88 164
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PMMVS		93.62 177	93.90 147	92.79 306	96.79 188	81.40 414	98.85 168	96.81 236	91.25 144	96.82 106	98.15 154	77.02 297	98.13 235	93.15 210	96.30 181	98.83 171

ADS-MVSNet		88.99 309	87.30 328	94.07 269	96.21 213	87.56 290	87.15 486	96.78 239	83.01 390	89.91 275	87.27 455	78.87 271	97.01 334	74.20 427	92.27 274	97.64 266

BridgeMVS		96.83 40	96.51 52	97.81 42	97.60 135	95.15 37	98.40 252	96.77 240	93.00 97	98.69 43	96.19 282	89.75 69	98.76 191	98.45 61	99.72 34	99.51 95

MVSMamba_PlusPlus		95.73 97	95.15 106	97.44 55	97.28 157	94.35 63	98.26 272	96.75 241	83.09 389	97.84 77	95.97 290	89.59 71	98.48 209	97.86 77	99.73 33	99.49 98

WBMVS		91.35 252	90.49 259	93.94 276	96.97 179	93.40 89	99.27 111	96.71 242	87.40 301	83.10 347	91.76 378	92.38 32	96.23 379	88.95 272	77.89 386	92.17 360

Vis-MVSNet (Re-imp)		93.26 196	93.00 183	94.06 271	96.14 220	86.71 312	98.68 195	96.70 243	88.30 267	89.71 281	97.64 182	85.43 156	96.39 363	88.06 280	96.32 179	99.08 143

Anonymous20231211		84.72 385	82.65 397	90.91 356	97.71 128	84.55 371	97.28 347	96.67 244	66.88 492	79.18 411	90.87 401	58.47 443	96.60 349	82.61 360	74.20 416	91.59 382

Syy-MVS		84.10 398	84.53 374	82.83 462	95.14 272	65.71 494	97.68 327	96.66 245	86.52 324	82.63 352	96.84 256	68.15 383	89.89 488	45.62 512	91.54 291	92.87 342

myMVS_eth3d		88.68 324	89.07 290	87.50 424	95.14 272	79.74 431	97.68 327	96.66 245	86.52 324	82.63 352	96.84 256	85.22 164	89.89 488	69.43 457	91.54 291	92.87 342

SSC-MVS3.2		85.22 379	83.90 384	89.17 405	91.87 396	79.84 430	97.66 330	96.63 247	86.81 316	81.99 371	91.35 389	55.80 451	96.00 390	76.52 411	76.53 397	91.67 373

EIA-MVS		95.11 115	95.27 102	94.64 238	96.34 207	86.51 315	99.59 63	96.62 248	92.51 108	94.08 174	98.64 122	86.05 144	98.24 222	95.07 153	98.50 125	99.18 129

ETV-MVS		96.00 75	96.00 74	96.00 155	96.56 193	91.05 156	99.63 60	96.61 249	93.26 92	97.39 86	98.30 147	86.62 129	98.13 235	98.07 73	97.57 149	98.82 172

usedtu_dtu_shiyan1		89.12 306	87.56 322	93.78 282	89.74 426	93.60 80	98.70 191	96.60 250	87.85 283	83.43 339	91.56 383	76.34 305	95.92 397	82.75 356	81.08 367	91.82 369

FE-MVSNET3		89.12 306	87.56 322	93.78 282	89.74 426	93.60 80	98.70 191	96.60 250	87.85 283	83.43 339	91.56 383	76.34 305	95.92 397	82.75 356	81.08 367	91.82 369

LS3D		90.19 287	88.72 300	94.59 244	98.97 81	86.33 323	96.90 365	96.60 250	74.96 465	84.06 335	98.74 111	75.78 313	99.83 93	74.93 420	97.57 149	97.62 270

EI-MVSNet		89.87 295	89.38 281	91.36 348	94.32 328	85.87 346	97.61 334	96.59 253	85.10 349	85.51 322	97.10 225	81.30 240	96.56 352	83.85 344	83.03 357	91.64 375

MVSTER		92.71 215	92.32 203	93.86 279	97.29 155	92.95 104	99.01 153	96.59 253	90.09 190	85.51 322	94.00 327	94.61 16	96.56 352	90.77 246	83.03 357	92.08 364

cascas		90.93 266	89.33 282	95.76 167	95.69 239	93.03 99	98.99 155	96.59 253	80.49 428	86.79 313	94.45 319	65.23 415	98.60 201	93.52 193	92.18 277	95.66 327

TAPA-MVS	87.50 9	90.35 281	89.05 291	94.25 260	98.48 103	85.17 361	98.42 245	96.58 256	82.44 406	87.24 306	98.53 128	82.77 207	98.84 185	59.09 491	97.88 141	98.72 191
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
OMC-MVS		93.90 162	93.62 157	94.73 233	98.63 99	87.00 307	98.04 302	96.56 257	92.19 120	92.46 217	98.73 112	79.49 261	99.14 171	92.16 225	94.34 227	98.03 252

PLC	91.07 3	94.23 148	94.01 136	94.87 224	99.17 71	87.49 292	99.25 113	96.55 258	88.43 260	91.26 245	98.21 152	85.92 145	99.86 83	89.77 257	97.57 149	97.24 283
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TSAR-MVS + GP.		96.95 36	96.91 34	97.07 76	98.88 91	91.62 138	99.58 64	96.54 259	95.09 45	96.84 102	98.63 124	91.16 38	99.77 109	99.04 40	96.42 177	99.81 40

PRO-TEST		96.23 67	95.99 75	96.95 87	96.86 182	93.81 74	99.19 117	96.51 260	94.78 50	98.27 62	98.49 135	83.43 189	97.60 306	98.43 62	97.99 138	99.46 102

cl22		89.57 301	88.79 299	91.91 327	97.94 120	87.62 287	97.98 306	96.51 260	85.03 352	82.37 361	91.79 375	83.65 184	96.50 356	85.96 310	77.89 386	91.61 380

xiu_mvs_v1_base_debu		94.73 130	93.98 138	96.99 81	95.19 267	95.24 30	98.62 208	96.50 262	92.99 98	97.52 82	98.83 105	72.37 348	99.15 167	97.03 93	96.74 171	96.58 306

xiu_mvs_v1_base		94.73 130	93.98 138	96.99 81	95.19 267	95.24 30	98.62 208	96.50 262	92.99 98	97.52 82	98.83 105	72.37 348	99.15 167	97.03 93	96.74 171	96.58 306

xiu_mvs_v1_base_debi		94.73 130	93.98 138	96.99 81	95.19 267	95.24 30	98.62 208	96.50 262	92.99 98	97.52 82	98.83 105	72.37 348	99.15 167	97.03 93	96.74 171	96.58 306

lupinMVS		96.32 64	95.94 76	97.44 55	95.05 286	94.87 42	99.86 10	96.50 262	93.82 78	98.04 71	98.77 108	85.52 150	98.09 244	96.98 96	98.97 93	99.37 110

fmvsm_s_conf0.5_n_11		96.80 42	96.97 30	96.28 133	98.09 114	92.26 122	99.87 7	96.49 266	97.55 5	99.75 3	99.32 28	83.20 196	99.91 58	99.57 13	98.88 100	96.67 302

mvs_anonymous		92.50 223	91.65 228	95.06 216	96.60 192	89.64 208	97.06 359	96.44 267	86.64 320	84.14 333	93.93 330	82.49 216	96.17 383	91.47 235	96.08 189	99.35 113

GDP-MVS		96.05 74	95.63 94	97.31 65	95.37 258	94.65 54	99.36 100	96.42 268	92.14 123	97.07 95	98.53 128	93.33 21	98.50 204	91.76 233	96.66 174	98.78 179

VDDNet		90.08 292	88.54 308	94.69 235	94.41 321	87.68 278	98.21 278	96.40 269	76.21 452	93.33 194	97.75 169	54.93 460	98.77 188	94.71 165	90.96 303	97.61 271

NormalMVS		95.87 85	95.83 80	95.99 156	99.27 63	90.37 175	99.14 132	96.39 270	94.92 46	96.30 120	97.98 157	85.33 160	99.23 162	94.35 172	98.82 103	98.37 227

Elysia		90.62 275	88.95 293	95.64 174	93.08 371	91.94 127	97.65 331	96.39 270	84.72 360	90.59 257	95.95 291	62.22 428	98.23 223	83.69 345	96.23 184	96.74 298

StellarMVS		90.62 275	88.95 293	95.64 174	93.08 371	91.94 127	97.65 331	96.39 270	84.72 360	90.59 257	95.95 291	62.22 428	98.23 223	83.69 345	96.23 184	96.74 298

mvsmamba		94.27 147	93.91 146	95.35 192	96.42 201	88.61 251	97.77 319	96.38 273	91.17 147	94.05 175	95.27 308	78.41 282	97.96 268	97.36 88	98.40 128	99.48 99

HQP3-MVS								96.37 274							86.29 327

PatchT		85.44 377	83.19 388	92.22 319	93.13 370	83.00 390	83.80 500	96.37 274	70.62 477	90.55 259	79.63 497	84.81 169	94.87 436	58.18 493	91.59 288	98.79 176

HQP-MVS		91.50 247	91.23 237	92.29 318	93.95 341	86.39 320	99.16 124	96.37 274	93.92 70	87.57 301	96.67 266	73.34 336	97.77 285	93.82 187	86.29 327	92.72 344

UnsupCasMVSNet_eth		78.90 433	76.67 438	85.58 445	82.81 487	74.94 466	91.98 462	96.31 277	84.64 363	65.84 490	87.71 448	51.33 471	92.23 472	72.89 440	56.50 497	89.56 445

HQP_MVS		91.26 254	90.95 246	92.16 322	93.84 349	86.07 339	99.02 151	96.30 278	93.38 90	86.99 308	96.52 269	72.92 343	97.75 292	93.46 197	86.17 330	92.67 346

plane_prior5								96.30 278					97.75 292	93.46 197	86.17 330	92.67 346

jason		95.40 107	94.86 115	97.03 78	92.91 374	94.23 65	99.70 42	96.30 278	93.56 86	96.73 111	98.52 130	81.46 237	97.91 270	96.08 123	98.47 127	98.96 153
jason: jason.
CLD-MVS		91.06 262	90.71 254	92.10 324	94.05 340	86.10 336	99.55 67	96.29 281	94.16 63	84.70 327	97.17 220	69.62 371	97.82 279	94.74 163	86.08 332	92.39 349
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GA-MVS		90.10 291	88.69 301	94.33 254	92.44 382	87.97 271	99.08 142	96.26 282	89.65 206	86.92 310	93.11 352	68.09 384	96.96 335	82.54 361	90.15 310	98.05 251

DTE-MVSNet		84.14 396	82.80 392	88.14 417	88.95 439	79.87 429	96.81 368	96.24 283	83.50 382	77.60 429	92.52 363	67.89 388	94.24 447	72.64 442	69.05 450	90.32 429

LFMVS		92.23 231	90.84 250	96.42 121	98.24 108	91.08 155	98.24 275	96.22 284	83.39 384	94.74 159	98.31 146	61.12 435	98.85 184	94.45 170	92.82 254	99.32 116

LuminaMVS		93.16 200	92.30 204	95.76 167	92.26 385	92.64 113	97.60 336	96.21 285	90.30 179	93.06 198	95.59 299	76.00 308	97.89 272	94.93 160	94.70 217	96.76 297

balanced_ft_v1		94.96 120	94.35 124	96.78 95	97.54 139	92.05 125	98.03 303	96.20 286	90.90 151	96.83 104	95.51 301	76.75 299	98.77 188	98.68 50	98.70 113	99.52 92

baseline1		92.61 220	91.28 236	96.58 112	97.05 176	94.63 55	97.72 324	96.20 286	89.82 199	88.56 294	96.85 253	86.85 121	97.82 279	88.42 274	80.10 376	97.30 280

FMVSNet3		88.81 318	87.08 332	93.99 275	96.52 196	94.59 56	98.08 296	96.20 286	85.85 337	82.12 365	91.60 381	74.05 331	95.40 425	79.04 390	80.24 373	91.99 367

sasdasda		95.02 118	93.96 141	98.20 24	97.53 140	95.92 20	98.71 188	96.19 289	91.78 127	95.86 132	98.49 135	79.53 259	99.03 175	96.12 120	91.42 297	99.66 72

canonicalmvs		95.02 118	93.96 141	98.20 24	97.53 140	95.92 20	98.71 188	96.19 289	91.78 127	95.86 132	98.49 135	79.53 259	99.03 175	96.12 120	91.42 297	99.66 72

fmvsm_s_conf0.1_n_2		95.24 112	95.04 112	95.83 164	95.60 242	91.71 137	99.65 53	96.18 291	96.99 16	98.79 39	98.91 97	73.91 333	99.87 77	99.00 42	96.30 181	95.91 324

dmvs_re		88.69 322	88.06 316	90.59 365	93.83 351	78.68 441	95.75 413	96.18 291	87.99 278	84.48 331	96.32 279	67.52 390	96.94 337	84.98 322	85.49 336	96.14 318

MVSFormer		94.71 133	94.08 135	96.61 109	95.05 286	94.87 42	97.77 319	96.17 293	86.84 314	98.04 71	98.52 130	85.52 150	95.99 391	89.83 253	98.97 93	98.96 153

test_djsdf		88.26 330	87.73 319	89.84 387	88.05 450	82.21 404	97.77 319	96.17 293	86.84 314	82.41 360	91.95 374	72.07 352	95.99 391	89.83 253	84.50 342	91.32 399

MS-PatchMatch		86.75 352	85.92 349	89.22 403	91.97 391	82.47 403	96.91 364	96.14 295	83.74 377	77.73 428	93.53 342	58.19 444	97.37 322	76.75 408	98.35 130	87.84 462

CS-MVS		95.75 94	96.19 64	94.40 250	97.88 122	86.22 327	99.66 51	96.12 296	92.69 106	98.07 69	98.89 101	87.09 115	97.59 307	96.71 102	98.62 117	99.39 109

E3new		94.19 150	93.78 153	95.43 186	95.81 234	89.44 214	98.80 175	96.11 297	90.24 181	93.85 181	97.75 169	80.94 245	98.14 232	95.00 156	95.48 202	98.72 191

viewcassd2359sk11		93.95 159	93.48 162	95.36 189	95.48 250	89.25 220	98.74 184	96.10 298	90.10 189	93.48 190	97.55 188	80.05 250	98.14 232	94.66 166	95.16 207	98.69 195

MGCFI-Net		94.89 121	93.84 150	98.06 32	97.49 143	95.55 24	98.64 202	96.10 298	91.60 133	95.75 137	98.46 142	79.31 263	98.98 179	95.95 127	91.24 302	99.65 76

SPE-MVS-test		95.98 77	96.34 60	94.90 223	98.06 116	87.66 281	99.69 49	96.10 298	93.66 82	98.35 59	99.05 76	86.28 139	97.66 300	96.96 97	98.90 99	99.37 110

VDD-MVS		91.24 257	90.18 263	94.45 249	97.08 173	85.84 348	98.40 252	96.10 298	86.99 308	93.36 193	98.16 153	54.27 462	99.20 164	96.59 108	90.63 308	98.31 233

PCF-MVS	89.78 5	91.26 254	89.63 273	96.16 145	95.44 252	91.58 142	95.29 420	96.10 298	85.07 351	82.75 349	97.45 195	78.28 284	99.78 108	80.60 382	95.65 197	97.12 285
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
E2		93.62 177	93.07 176	95.26 203	95.00 290	88.99 235	98.63 204	96.09 303	89.84 197	93.02 199	97.36 201	78.88 269	98.11 239	94.23 177	94.60 219	98.67 198

E3		93.62 177	93.07 176	95.26 203	94.98 292	89.00 234	98.63 204	96.09 303	89.83 198	93.01 201	97.35 203	78.90 268	98.11 239	94.23 177	94.60 219	98.67 198

test_cas_vis1_n_1920		93.86 167	93.74 154	94.22 263	95.39 256	86.08 337	99.73 38	96.07 305	96.38 27	97.19 93	97.78 166	65.46 413	99.86 83	96.71 102	98.92 97	96.73 300

test_vis1_n_1920		93.08 204	93.42 164	92.04 326	96.31 208	79.36 433	99.83 16	96.06 306	96.72 19	98.53 52	98.10 155	58.57 442	99.91 58	97.86 77	98.79 109	96.85 295

MVS_Test		93.67 174	92.67 193	96.69 104	96.72 190	92.66 110	97.22 352	96.03 307	87.69 294	95.12 151	94.03 324	81.55 232	98.28 219	89.17 269	96.46 175	99.14 132

viewmanbaseed2359cas		93.90 162	93.34 168	95.56 181	95.39 256	89.72 205	98.58 221	96.00 308	90.32 178	93.58 188	97.78 166	78.71 277	98.07 251	94.43 171	95.29 204	98.88 164

E4		93.15 202	92.50 199	95.09 213	94.41 321	88.61 251	98.48 236	95.99 309	89.40 221	92.22 222	97.13 222	77.43 291	98.10 242	93.58 192	93.90 234	98.56 211

casdiffmvs_mvg		94.00 155	93.33 169	96.03 151	95.22 264	90.90 162	99.09 141	95.99 309	90.58 166	91.55 239	97.37 200	79.91 252	98.06 254	95.01 155	95.22 206	99.13 134
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		87.35 343	86.51 341	89.87 385	87.75 457	81.74 409	97.03 360	95.98 311	88.47 254	80.15 396	93.80 334	61.47 432	96.36 365	89.44 261	84.47 343	91.50 384

E5new		92.80 209	92.19 208	94.62 240	94.34 324	87.64 282	98.08 296	95.97 312	89.15 227	92.01 226	97.08 231	76.37 303	98.08 246	93.25 203	93.46 245	98.15 245

E6new		92.80 209	92.19 208	94.62 240	94.31 332	87.64 282	98.08 296	95.97 312	89.15 227	92.01 226	97.10 225	76.38 301	98.08 246	93.25 203	93.45 247	98.15 245

E6		92.80 209	92.19 208	94.62 240	94.31 332	87.64 282	98.08 296	95.97 312	89.15 227	92.01 226	97.10 225	76.38 301	98.08 246	93.25 203	93.45 247	98.15 245

E5		92.80 209	92.19 208	94.62 240	94.34 324	87.64 282	98.08 296	95.97 312	89.15 227	92.01 226	97.08 231	76.37 303	98.08 246	93.25 203	93.46 245	98.15 245

PS-MVSNAJss		89.54 302	89.05 291	91.00 354	88.77 440	84.36 373	97.39 341	95.97 312	88.47 254	81.88 374	93.80 334	82.48 217	96.50 356	89.34 263	83.34 356	92.15 361

F-COLMAP		92.07 236	91.75 227	93.02 299	98.16 112	82.89 394	98.79 180	95.97 312	86.54 323	87.92 298	97.80 164	78.69 278	99.65 122	85.97 309	95.93 192	96.53 309

miper_enhance_ethall		90.33 282	89.70 269	92.22 319	97.12 171	88.93 241	98.35 262	95.96 318	88.60 252	83.14 346	92.33 365	87.38 106	96.18 381	86.49 303	77.89 386	91.55 383

TR-MVS		90.77 268	89.44 278	94.76 230	96.31 208	88.02 269	97.92 308	95.96 318	85.52 343	88.22 297	97.23 214	66.80 399	98.09 244	84.58 328	92.38 270	98.17 244

CMPMVS	58.40 21	80.48 423	80.11 421	81.59 469	85.10 473	59.56 502	94.14 437	95.95 320	68.54 487	60.71 496	93.31 345	55.35 457	97.87 275	83.06 354	84.85 340	87.33 469
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
VortexMVS		90.18 288	89.28 283	92.89 304	95.58 243	90.94 161	97.82 314	95.94 321	90.90 151	82.11 369	91.48 386	78.75 276	96.08 387	91.99 228	78.97 380	91.65 374

test_fmvsmconf0.01_n		94.14 151	93.51 161	96.04 150	86.79 463	89.19 222	99.28 109	95.94 321	95.70 33	95.50 143	98.49 135	73.27 339	99.79 105	98.28 69	98.32 133	99.15 131

LPG-MVS_test		88.86 313	88.47 309	90.06 380	93.35 366	80.95 423	98.22 276	95.94 321	87.73 292	83.17 344	96.11 285	66.28 406	97.77 285	90.19 251	85.19 337	91.46 387

LGP-MVS_train				90.06 380	93.35 366	80.95 423		95.94 321	87.73 292	83.17 344	96.11 285	66.28 406	97.77 285	90.19 251	85.19 337	91.46 387

OPM-MVS		89.76 298	89.15 289	91.57 344	90.53 415	85.58 352	98.11 289	95.93 325	92.88 103	86.05 315	96.47 273	67.06 395	97.87 275	89.29 266	86.08 332	91.26 402
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Casviewmamba		93.63 176	93.20 173	94.94 221	95.12 274	87.64 282	98.76 182	95.92 326	90.44 172	92.12 225	97.90 160	79.15 265	98.16 231	93.89 182	95.52 199	99.00 148

viewdifsd2359ckpt13		93.45 182	92.86 188	95.21 206	95.45 251	88.91 243	98.59 218	95.92 326	89.39 222	92.67 212	97.33 205	78.02 287	98.03 261	93.27 202	95.12 209	98.69 195

XVG-OURS-SEG-HR		90.95 265	90.66 257	91.83 329	95.18 270	81.14 421	95.92 404	95.92 326	88.40 262	90.33 265	97.85 161	70.66 365	99.38 152	92.83 216	88.83 316	94.98 331

XVG-OURS		90.83 267	90.49 259	91.86 328	95.23 263	81.25 418	95.79 412	95.92 326	88.96 236	90.02 273	98.03 156	71.60 358	99.35 157	91.06 239	87.78 320	94.98 331

tpm		89.67 299	88.95 293	91.82 331	92.54 380	81.43 413	92.95 451	95.92 326	87.81 287	90.50 261	89.44 437	84.99 165	95.65 415	83.67 347	82.71 360	98.38 224

EC-MVSNet		95.09 116	95.17 105	94.84 227	95.42 253	88.17 264	99.48 77	95.92 326	91.47 136	97.34 88	98.36 144	82.77 207	97.41 319	97.24 90	98.58 121	98.94 158

ACMM	86.95 13	88.77 319	88.22 313	90.43 371	93.61 357	81.34 416	98.50 232	95.92 326	87.88 282	83.85 336	95.20 311	67.20 393	97.89 272	86.90 294	84.90 339	92.06 365
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline		93.91 161	93.30 170	95.72 169	95.10 283	90.07 189	97.48 338	95.91 333	91.03 148	93.54 189	97.68 177	79.58 256	98.02 263	94.27 175	95.14 208	99.08 143

mvs_tets		87.09 346	86.22 344	89.71 391	87.87 453	81.39 415	96.73 374	95.90 334	88.19 271	79.99 398	93.61 339	59.96 439	96.31 373	89.40 262	84.34 344	91.43 389

XXY-MVS		87.75 336	86.02 347	92.95 303	90.46 417	89.70 207	97.71 326	95.90 334	84.02 371	80.95 385	94.05 321	67.51 391	97.10 331	85.16 318	78.41 383	92.04 366

nrg030		90.23 285	88.87 296	94.32 255	91.53 403	93.54 85	98.79 180	95.89 336	88.12 273	84.55 329	94.61 318	78.80 274	96.88 339	92.35 224	75.21 403	92.53 348

CNLPA		93.64 175	92.74 191	96.36 127	98.96 84	90.01 195	99.19 117	95.89 336	86.22 329	89.40 285	98.85 104	80.66 247	99.84 89	88.57 273	96.92 168	99.24 123

KD-MVS_2432*1600		82.98 409	80.52 413	90.38 373	94.32 328	88.98 236	92.87 453	95.87 338	80.46 429	73.79 449	87.49 452	82.76 209	93.29 459	70.56 452	46.53 511	88.87 457

miper_refine_blended		82.98 409	80.52 413	90.38 373	94.32 328	88.98 236	92.87 453	95.87 338	80.46 429	73.79 449	87.49 452	82.76 209	93.29 459	70.56 452	46.53 511	88.87 457

AstraMVS		93.38 189	93.01 181	94.50 245	93.94 344	86.55 313	98.91 164	95.86 340	93.88 74	92.88 204	97.49 192	75.61 317	98.21 225	96.15 119	92.39 269	98.73 190

FMVSNet2		86.90 348	84.79 368	93.24 295	95.11 280	92.54 116	97.67 329	95.86 340	82.94 393	80.55 389	91.17 394	62.89 425	95.29 428	77.23 402	79.71 379	91.90 368

hybridcas		93.44 183	92.82 190	95.31 197	94.91 300	89.08 227	98.82 171	95.84 342	90.28 180	91.22 247	97.65 181	78.39 283	98.06 254	92.71 218	95.55 198	98.79 176

viewmacassd2359aftdt		93.16 200	92.44 201	95.31 197	94.34 324	89.19 222	98.40 252	95.84 342	89.62 209	92.87 206	97.31 206	76.07 307	98.00 266	92.93 213	94.58 221	98.75 184

casdiffmvs		93.98 157	93.43 163	95.61 179	95.07 285	89.86 199	98.80 175	95.84 342	90.98 149	92.74 209	97.66 179	79.71 254	98.10 242	94.72 164	95.37 203	98.87 167
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		94.12 152	93.87 149	94.86 226	95.26 261	87.86 273	98.60 215	95.82 345	90.70 158	95.67 140	97.72 175	79.72 253	98.13 235	96.37 112	94.99 212	98.60 208

viewdifsd2359ckpt07		92.71 215	92.19 208	94.28 256	94.96 295	86.26 324	98.29 270	95.80 346	88.71 249	90.81 251	97.34 204	76.57 300	98.19 227	93.16 208	94.05 231	98.39 223

UniMVSNet_ETH3D		85.65 376	83.79 385	91.21 349	90.41 418	80.75 426	95.36 418	95.78 347	78.76 438	81.83 379	94.33 320	49.86 478	96.66 347	84.30 331	83.52 354	96.22 317

Effi-MVS+		93.87 166	93.15 175	96.02 152	95.79 235	90.76 164	96.70 375	95.78 347	86.98 311	95.71 138	97.17 220	79.58 256	98.01 264	94.57 169	96.09 188	99.31 117

gbinet_0.2-2-1-0.02		83.16 408	80.42 417	91.39 347	83.70 479	87.60 288	98.62 208	95.77 349	75.83 455	79.33 408	87.92 446	64.07 419	95.34 426	81.87 372	56.67 495	91.25 403

RRT-MVS		93.39 187	92.64 194	95.64 174	96.11 225	88.75 248	97.40 340	95.77 349	89.46 218	92.70 211	95.42 305	72.98 342	98.81 186	96.91 99	96.97 166	99.37 110

EU-MVSNet		84.19 395	84.42 377	83.52 460	88.64 443	67.37 493	96.04 402	95.76 351	85.29 346	78.44 423	93.18 349	70.67 364	91.48 480	75.79 416	75.98 398	91.70 372

BH-w/o		92.32 227	91.79 225	93.91 278	96.85 183	86.18 333	99.11 140	95.74 352	88.13 272	84.81 326	97.00 238	77.26 293	97.91 270	89.16 270	98.03 137	97.64 266

icg_test_0407_2		91.56 246	90.90 248	93.54 288	94.61 314	86.22 327	95.72 414	95.72 353	88.78 243	89.76 277	96.93 244	77.24 294	95.65 415	86.73 298	92.59 260	98.74 185

IMVS_0407		91.79 242	90.98 244	94.24 262	94.61 314	86.22 327	96.45 383	95.72 353	88.78 243	89.76 277	96.93 244	77.24 294	97.77 285	86.73 298	92.59 260	98.74 185

IMVS_0404		89.79 297	88.57 306	93.47 290	94.61 314	86.22 327	94.45 428	95.72 353	88.78 243	81.88 374	96.93 244	65.39 414	95.47 421	86.73 298	92.59 260	98.74 185

IMVS_0403		91.93 239	91.13 239	94.34 253	94.61 314	86.22 327	96.70 375	95.72 353	88.78 243	90.00 274	96.93 244	78.07 286	98.07 251	86.73 298	92.59 260	98.74 185

anonymousdsp		86.69 353	85.75 352	89.53 396	86.46 466	82.94 391	96.39 385	95.71 357	83.97 373	79.63 403	90.70 405	68.85 377	95.94 394	86.01 308	84.02 347	89.72 442

hybrid		93.89 164	93.41 165	95.33 195	94.98 292	89.30 218	98.58 221	95.70 358	89.70 204	94.76 157	97.54 189	78.98 267	98.07 251	95.52 141	94.92 213	98.61 206

Fast-Effi-MVS+		91.72 244	90.79 253	94.49 246	95.89 230	87.40 296	99.54 72	95.70 358	85.01 354	89.28 287	95.68 298	77.75 289	97.57 312	83.22 350	95.06 211	98.51 214

IS-MVSNet		93.00 207	92.51 198	94.49 246	96.14 220	87.36 297	98.31 266	95.70 358	88.58 253	90.17 268	97.50 191	83.02 201	97.22 325	87.06 288	96.07 190	98.90 163

viewmambaseed2359dif		93.05 206	92.64 194	94.25 260	94.94 297	86.53 314	98.38 259	95.69 361	87.03 307	93.38 192	97.74 172	78.79 275	98.08 246	93.49 196	94.35 226	98.15 245

diffmvs_AUTHOR		94.30 146	93.92 144	95.45 183	94.77 307	89.92 196	98.55 227	95.68 362	91.33 141	95.83 135	97.64 182	79.58 256	98.05 258	96.19 116	95.66 196	98.37 227

diffmvs		94.59 138	94.19 129	95.81 165	95.54 247	90.69 166	98.70 191	95.68 362	91.61 130	95.96 127	97.81 163	80.11 249	98.06 254	96.52 110	95.76 193	98.67 198
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		91.84 241	90.69 255	95.28 201	94.50 319	89.32 217	98.31 266	95.67 364	87.82 286	90.22 267	96.63 268	74.27 328	97.94 269	86.37 304	92.43 268	98.59 210

v7n		84.42 392	82.75 395	89.43 401	88.15 448	81.86 408	96.75 372	95.67 364	80.53 427	78.38 424	89.43 438	69.89 367	96.35 370	73.83 432	72.13 438	90.07 434

ACMP	87.39 10	88.71 321	88.24 312	90.12 379	93.91 347	81.06 422	98.50 232	95.67 364	89.43 219	80.37 393	95.55 300	65.67 408	97.83 278	90.55 248	84.51 341	91.47 386
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
viewdifsd2359ckpt09		93.54 180	92.91 186	95.44 185	95.57 244	89.48 212	98.68 195	95.66 367	89.52 215	92.50 215	97.75 169	78.46 281	98.03 261	93.32 200	94.69 218	98.81 173

hybridnocas07		93.98 157	93.52 159	95.36 189	95.01 289	89.37 216	98.63 204	95.64 368	90.79 157	94.69 160	97.31 206	79.01 266	98.11 239	95.54 140	95.07 210	98.61 206

CL-MVSNet_self_test		79.89 427	78.34 429	84.54 453	81.56 491	75.01 465	96.88 366	95.62 369	81.10 421	75.86 438	85.81 472	68.49 380	90.26 486	63.21 480	56.51 496	88.35 459

V42		87.00 347	85.68 353	90.98 355	89.91 421	86.08 337	98.32 265	95.61 370	83.67 380	82.72 350	90.67 407	74.00 332	96.53 354	81.94 371	74.28 415	90.32 429

viewmamba		93.88 165	93.59 158	94.78 229	94.82 305	87.68 278	98.41 248	95.60 371	91.61 130	94.17 172	97.93 159	79.65 255	98.01 264	95.20 150	94.87 215	98.66 203

XVG-ACMP-BASELINE		85.86 369	84.95 364	88.57 413	89.90 422	77.12 455	94.30 433	95.60 371	87.40 301	82.12 365	92.99 356	53.42 466	97.66 300	85.02 321	83.83 348	90.92 412

dtuplus		92.78 213	92.35 202	94.07 269	94.70 309	85.91 343	98.47 239	95.59 373	87.50 299	92.88 204	97.66 179	77.24 294	98.12 238	93.01 211	94.15 228	98.20 241

Anonymous202405211		88.84 314	87.03 334	94.27 257	98.14 113	84.18 376	98.44 241	95.58 374	76.79 450	89.34 286	96.88 251	53.42 466	99.54 132	87.53 285	87.12 323	99.09 139

miper_ehance_all_eth		88.94 311	88.12 315	91.40 345	95.32 260	86.93 308	97.85 313	95.55 375	84.19 369	81.97 372	91.50 385	84.16 179	95.91 400	84.69 325	77.89 386	91.36 396

CANet_DTU		94.31 145	93.35 167	97.20 72	97.03 178	94.71 52	98.62 208	95.54 376	95.61 37	97.21 91	98.47 140	71.88 354	99.84 89	88.38 275	97.46 154	97.04 290

v2v482		87.27 345	85.76 351	91.78 337	89.59 429	87.58 289	98.56 224	95.54 376	84.53 364	82.51 356	91.78 376	73.11 340	96.47 359	82.07 368	74.14 418	91.30 400

wanda-best-256-512		83.28 404	80.44 415	91.78 337	82.91 483	88.24 259	98.43 242	95.51 378	75.76 456	78.60 418	86.54 465	66.95 396	95.71 411	82.44 363	56.84 491	91.38 392

FE-blended-shiyan7		83.27 405	80.44 415	91.78 337	82.91 483	88.24 259	98.43 242	95.51 378	75.76 456	78.60 418	86.54 465	66.93 397	95.71 411	82.44 363	56.84 491	91.38 392

blended_shiyan6		83.17 407	80.34 419	91.67 342	82.80 488	87.93 272	98.29 270	95.51 378	75.63 460	78.46 422	86.48 468	66.74 401	95.70 413	82.33 365	56.84 491	91.37 395

blend_shiyan4		86.02 365	84.08 380	91.83 329	83.24 481	88.24 259	98.42 245	95.51 378	75.55 462	79.43 406	86.84 462	84.51 174	95.77 405	83.97 340	69.26 448	91.48 385

BH-untuned		91.46 249	90.84 250	93.33 294	96.51 197	84.83 368	98.84 170	95.50 382	86.44 328	83.50 337	96.70 264	75.49 318	97.77 285	86.78 296	97.81 142	97.40 275

blended_shiyan8		83.22 406	80.40 418	91.71 340	82.77 489	88.01 270	98.25 274	95.49 383	75.64 459	78.68 414	86.55 463	66.76 400	95.75 407	82.50 362	56.93 490	91.36 396

SSM_0407		92.04 238	91.03 243	95.07 215	95.12 274	89.81 201	97.18 355	95.49 383	86.17 330	89.50 282	97.13 222	75.65 314	97.68 298	89.26 267	93.79 237	97.73 261

SSM_0404		92.33 226	91.33 234	95.33 195	95.35 259	90.54 172	97.45 339	95.49 383	86.17 330	90.26 266	97.13 222	75.65 314	97.82 279	89.26 267	95.26 205	97.63 269

v148		86.38 361	85.06 361	90.37 375	89.47 434	84.10 377	98.52 228	95.48 386	83.80 376	80.93 386	90.22 426	74.60 322	96.31 373	80.92 378	71.55 442	90.69 422

IterMVS-LS		88.34 327	87.44 325	91.04 353	94.10 336	85.85 347	98.10 290	95.48 386	85.12 348	82.03 370	91.21 393	81.35 239	95.63 417	83.86 343	75.73 400	91.63 376
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dcpmvs_2		95.67 99	96.18 66	94.12 267	98.82 93	84.22 375	97.37 344	95.45 388	90.70 158	95.77 136	98.63 124	90.47 56	98.68 198	99.20 34	99.22 79	99.45 103

v1144		86.83 350	85.31 359	91.40 345	89.75 425	87.21 305	98.31 266	95.45 388	83.22 386	82.70 351	90.78 402	73.36 335	96.36 365	79.49 387	74.69 409	90.63 424

v1192		86.32 362	84.71 370	91.17 350	89.53 432	86.40 319	98.13 285	95.44 390	82.52 403	82.42 359	90.62 411	71.58 359	96.33 372	77.23 402	74.88 406	90.79 416

v144192		86.40 360	84.89 365	90.91 356	89.48 433	85.59 351	98.21 278	95.43 391	82.45 405	82.62 354	90.58 414	72.79 346	96.36 365	78.45 397	74.04 419	90.79 416

Effi-MVS+-dtu		89.97 294	90.68 256	87.81 420	95.15 271	71.98 480	97.87 312	95.40 392	91.92 125	87.57 301	91.44 387	74.27 328	96.84 340	89.45 260	93.10 252	94.60 334

c3_l		88.19 331	87.23 330	91.06 352	94.97 294	86.17 334	97.72 324	95.38 393	83.43 383	81.68 380	91.37 388	82.81 206	95.72 410	84.04 339	73.70 420	91.29 401

eth_miper_zixun_eth		87.76 335	87.00 335	90.06 380	94.67 311	82.65 401	97.02 362	95.37 394	84.19 369	81.86 378	91.58 382	81.47 236	95.90 401	83.24 349	73.61 421	91.61 380

v8		86.11 364	84.45 375	91.10 351	89.99 420	86.85 309	97.24 350	95.36 395	81.99 411	79.89 400	89.86 432	74.53 324	96.39 363	78.83 394	72.32 436	90.05 436

v1921920		86.02 365	84.44 376	90.77 362	89.32 435	85.20 359	98.10 290	95.35 396	82.19 409	82.25 363	90.71 404	70.73 363	96.30 376	76.85 407	74.49 411	90.80 415

pmmvs4		87.58 342	86.17 346	91.80 332	89.58 430	88.92 242	97.25 349	95.28 397	82.54 402	80.49 390	93.17 351	75.62 316	96.05 389	82.75 356	78.90 381	90.42 427

viewdifsd2359ckpt11		90.42 279	89.65 270	92.73 311	93.71 356	82.67 398	98.09 293	95.27 398	89.80 201	90.10 271	97.40 198	69.43 373	98.18 229	92.46 221	80.61 372	97.34 277

viewmsd2359difaftdt		90.43 278	89.65 270	92.74 309	93.72 355	82.67 398	98.09 293	95.27 398	89.80 201	90.12 270	97.40 198	69.43 373	98.20 226	92.45 222	80.62 371	97.34 277

GBi-Net		86.67 354	84.96 362	91.80 332	95.11 280	88.81 245	96.77 369	95.25 400	82.94 393	82.12 365	90.25 423	62.89 425	94.97 433	79.04 390	80.24 373	91.62 377

test1		86.67 354	84.96 362	91.80 332	95.11 280	88.81 245	96.77 369	95.25 400	82.94 393	82.12 365	90.25 423	62.89 425	94.97 433	79.04 390	80.24 373	91.62 377

FMVSNet1		83.94 399	81.32 408	91.80 332	91.94 394	88.81 245	96.77 369	95.25 400	77.98 441	78.25 425	90.25 423	50.37 477	94.97 433	73.27 436	77.81 391	91.62 377

mvsany_test1		94.57 139	95.09 110	92.98 300	95.84 233	82.07 406	98.76 182	95.24 403	92.87 104	96.45 116	98.71 117	84.81 169	99.15 167	97.68 81	95.49 201	97.73 261

cl____		87.82 333	86.79 338	90.89 358	94.88 301	85.43 354	97.81 315	95.24 403	82.91 397	80.71 388	91.22 392	81.97 229	95.84 402	81.34 375	75.06 404	91.40 391

miper_lstm_enhance		86.90 348	86.20 345	89.00 409	94.53 318	81.19 419	96.74 373	95.24 403	82.33 407	80.15 396	90.51 418	81.99 227	94.68 442	80.71 380	73.58 423	91.12 407

UnsupCasMVSNet_bld		73.85 458	70.14 462	84.99 449	79.44 497	75.73 462	88.53 483	95.24 403	70.12 482	61.94 494	74.81 509	41.41 492	93.62 455	68.65 462	51.13 506	85.62 483

v1240		85.77 373	84.11 379	90.73 363	89.26 436	85.15 362	97.88 311	95.23 407	81.89 414	82.16 364	90.55 416	69.60 372	96.31 373	75.59 417	74.87 407	90.72 421

DIV-MVS_self_test		87.82 333	86.81 337	90.87 359	94.87 302	85.39 356	97.81 315	95.22 408	82.92 396	80.76 387	91.31 391	81.99 227	95.81 404	81.36 374	75.04 405	91.42 390

v10		85.73 374	84.01 382	90.87 359	90.03 419	86.73 311	97.20 353	95.22 408	81.25 419	79.85 401	89.75 433	73.30 338	96.28 377	76.87 406	72.64 432	89.61 444

mamba_0408		90.65 273	89.16 286	95.12 211	95.12 274	89.81 201	83.02 502	95.17 410	85.95 335	89.50 282	96.85 253	75.85 310	97.82 279	87.19 286	93.79 237	97.73 261

SSM_04072		90.31 283	89.16 286	93.74 285	95.12 274	89.81 201	83.02 502	95.17 410	85.95 335	89.50 282	96.85 253	75.85 310	93.69 453	87.19 286	93.79 237	97.73 261

SD_0403		86.82 351	87.08 332	86.04 440	93.55 359	69.09 489	94.11 438	95.02 412	87.84 285	80.48 391	95.86 295	73.05 341	91.04 482	72.53 443	91.26 301	97.99 255

test_fmvs1		92.35 225	92.94 185	90.57 366	97.19 163	75.43 464	99.55 67	94.97 413	95.20 43	96.82 106	97.57 187	59.59 440	99.84 89	97.30 89	98.29 134	96.46 313

BH-RMVSNet		91.25 256	89.99 265	95.03 219	96.75 189	88.55 254	98.65 200	94.95 414	87.74 291	87.74 300	97.80 164	68.27 382	98.14 232	80.53 383	97.49 153	98.41 220

GeoE		90.60 277	89.56 274	93.72 287	95.10 283	85.43 354	99.41 93	94.94 415	83.96 374	87.21 307	96.83 258	74.37 326	97.05 333	80.50 384	93.73 242	98.67 198

ACMH	83.09 17	84.60 387	82.61 398	90.57 366	93.18 369	82.94 391	96.27 390	94.92 416	81.01 424	72.61 461	93.61 339	56.54 449	97.79 283	74.31 425	81.07 369	90.99 410
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs1_n		91.07 260	91.41 233	90.06 380	94.10 336	74.31 468	99.18 120	94.84 417	94.81 48	96.37 119	97.46 194	50.86 475	99.82 96	97.14 92	97.90 140	96.04 320

test1111		92.12 233	91.19 238	94.94 221	96.15 218	87.36 297	98.12 287	94.84 417	90.85 154	90.97 249	97.26 210	65.60 411	98.37 214	89.74 258	97.14 164	99.07 146

ECVR-MVS		92.29 228	91.33 234	95.15 210	96.41 203	87.84 274	98.10 290	94.84 417	90.82 155	91.42 243	97.28 208	65.61 410	98.49 208	90.33 249	97.19 161	99.12 135

IterMVS		85.81 371	84.67 371	89.22 403	93.51 360	83.67 383	96.32 389	94.80 420	85.09 350	78.69 413	90.17 429	66.57 404	93.17 461	79.48 388	77.42 393	90.81 414
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
LTVRE_ROB	81.71 19	84.59 388	82.72 396	90.18 377	92.89 375	83.18 389	93.15 448	94.74 421	78.99 435	75.14 443	92.69 360	65.64 409	97.63 303	69.46 456	81.82 365	89.74 441
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		84.68 386	82.78 394	90.40 372	89.58 430	85.18 360	97.31 345	94.73 422	81.93 413	76.05 435	92.01 370	65.48 412	96.11 386	78.75 395	69.14 449	89.91 439

IterMVS-SCA-FT		85.73 374	84.64 372	89.00 409	93.46 363	82.90 393	96.27 390	94.70 423	85.02 353	78.62 416	90.35 420	66.61 402	93.33 457	79.38 389	77.36 394	90.76 418

1112_ss		92.71 215	91.55 230	96.20 138	95.56 246	91.12 151	98.48 236	94.69 424	88.29 268	86.89 311	98.50 132	87.02 118	98.66 199	84.75 324	89.77 314	98.81 173

Test_1112_low_res		92.27 230	90.97 245	96.18 140	95.53 248	91.10 153	98.47 239	94.66 425	88.28 269	86.83 312	93.50 343	87.00 119	98.65 200	84.69 325	89.74 315	98.80 175

Fast-Effi-MVS+-dtu		88.84 314	88.59 305	89.58 395	93.44 364	78.18 445	98.65 200	94.62 426	88.46 256	84.12 334	95.37 307	68.91 376	96.52 355	82.06 369	91.70 287	94.06 335

our_test_3		84.47 391	82.80 392	89.50 397	89.01 437	83.90 380	97.03 360	94.56 427	81.33 418	75.36 442	90.52 417	71.69 357	94.54 444	68.81 461	76.84 395	90.07 434

ppachtmachnet_test		83.63 402	81.57 405	89.80 388	89.01 437	85.09 363	97.13 357	94.50 428	78.84 436	76.14 434	91.00 396	69.78 368	94.61 443	63.40 479	74.36 413	89.71 443

test_vis1_n		90.40 280	90.27 262	90.79 361	91.55 402	76.48 458	99.12 139	94.44 429	94.31 59	97.34 88	96.95 241	43.60 488	99.42 147	97.57 83	97.60 148	96.47 312

MonoMVSNet		90.69 271	89.78 268	93.45 291	91.78 398	84.97 366	96.51 381	94.44 429	90.56 167	85.96 317	90.97 398	78.61 280	96.27 378	95.35 144	83.79 351	99.11 137

YYNet1		79.64 430	77.04 436	87.43 426	87.80 455	79.98 428	96.23 394	94.44 429	73.83 470	51.83 503	87.53 450	67.96 387	92.07 476	66.00 472	67.75 459	90.23 431

MDA-MVSNet_test_wron		79.65 429	77.05 435	87.45 425	87.79 456	80.13 427	96.25 393	94.44 429	73.87 469	51.80 504	87.47 454	68.04 385	92.12 475	66.02 471	67.79 458	90.09 432

MIMVSNet		84.48 390	81.83 402	92.42 317	91.73 400	87.36 297	85.52 489	94.42 433	81.40 417	81.91 373	87.58 449	51.92 469	92.81 464	73.84 431	88.15 318	97.08 289

MVP-Stereo		86.61 356	85.83 350	88.93 411	88.70 442	83.85 381	96.07 401	94.41 434	82.15 410	75.64 440	91.96 373	67.65 389	96.45 361	77.20 404	98.72 112	86.51 476
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MSDG		88.29 329	86.37 342	94.04 273	96.90 181	86.15 335	96.52 380	94.36 435	77.89 445	79.22 410	96.95 241	69.72 369	99.59 128	73.20 437	92.58 264	96.37 316

ACMH+	83.78 15	84.21 394	82.56 400	89.15 406	93.73 354	79.16 436	96.43 384	94.28 436	81.09 422	74.00 448	94.03 324	54.58 461	97.67 299	76.10 413	78.81 382	90.63 424

Patchmatch-test		86.25 363	84.06 381	92.82 305	94.42 320	82.88 395	82.88 504	94.23 437	71.58 474	79.39 407	90.62 411	89.00 77	96.42 362	63.03 481	91.37 299	99.16 130

CR-MVSNet		88.83 316	87.38 327	93.16 297	93.47 361	86.24 325	84.97 494	94.20 438	88.92 240	90.76 254	86.88 460	84.43 176	94.82 438	70.64 451	92.17 278	98.41 220

Patchmtry		83.61 403	81.64 403	89.50 397	93.36 365	82.84 396	84.10 497	94.20 438	69.47 485	79.57 404	86.88 460	84.43 176	94.78 439	68.48 463	74.30 414	90.88 413

EG-PatchMatch MVS		79.92 425	77.59 432	86.90 431	87.06 462	77.90 450	96.20 397	94.06 440	74.61 466	66.53 486	88.76 442	40.40 494	96.20 380	67.02 468	83.66 352	86.61 474

KD-MVS_self_test		77.47 444	75.88 441	82.24 463	81.59 490	68.93 490	92.83 455	94.02 441	77.03 447	73.14 455	83.39 479	55.44 456	90.42 485	67.95 464	57.53 488	87.38 467

K. test v3		81.04 421	79.77 423	84.83 450	87.41 458	70.23 486	95.60 416	93.93 442	83.70 379	67.51 482	89.35 439	55.76 452	93.58 456	76.67 409	68.03 456	90.67 423

FE-MVSNET2		78.42 439	75.71 442	86.55 434	78.55 500	81.99 407	95.40 417	93.86 443	81.11 420	66.27 487	81.89 486	49.29 481	91.80 478	72.03 446	63.02 471	85.86 480

RPSCF		85.33 378	85.55 355	84.67 452	94.63 313	62.28 499	93.73 441	93.76 444	74.38 468	85.23 325	97.06 234	64.09 418	98.31 216	80.98 376	86.08 332	93.41 340

MVS-HIRNet		79.01 432	75.13 446	90.66 364	93.82 352	81.69 410	85.16 491	93.75 445	54.54 504	74.17 447	59.15 523	57.46 446	96.58 351	63.74 478	94.38 224	93.72 337

pmmvs5		85.87 368	84.40 378	90.30 376	88.53 444	84.23 374	98.60 215	93.71 446	81.53 416	80.29 394	92.02 369	64.51 417	95.52 419	82.04 370	78.34 384	91.15 406

pmmvs6		79.90 426	77.31 434	87.67 421	84.17 476	78.13 447	95.86 409	93.68 447	67.94 489	72.67 460	89.62 435	50.98 474	95.75 407	74.80 423	66.04 464	89.14 450

OurMVSNet-221017-0		84.13 397	83.59 386	85.77 444	87.81 454	70.24 485	94.89 424	93.65 448	86.08 332	76.53 431	93.28 347	61.41 433	96.14 385	80.95 377	77.69 392	90.93 411

PatchmatchNet2					0.00 567	79.25 434	96.11 399	93.62 449	70.56 478
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
Anonymous20240521		78.63 436	76.90 437	83.82 456	82.82 486	72.86 476	95.72 414	93.57 450	73.55 472	72.17 462	84.79 476	49.69 479	92.51 469	65.29 475	74.50 410	86.09 479

DP-MVS		88.75 320	86.56 340	95.34 193	98.92 89	87.45 294	97.64 333	93.52 451	70.55 479	81.49 381	97.25 212	74.43 325	99.88 73	71.14 450	94.09 230	98.67 198

ITE_SJBPF				87.93 418	92.26 385	76.44 459		93.47 452	87.67 295	79.95 399	95.49 304	56.50 450	97.38 320	75.24 418	82.33 363	89.98 438

USDC		84.74 384	82.93 390	90.16 378	91.73 400	83.54 385	95.00 423	93.30 453	88.77 247	73.19 454	93.30 346	53.62 465	97.65 302	75.88 415	81.54 366	89.30 447

dtuonly		89.80 296	89.16 286	91.70 341	90.49 416	81.48 412	96.58 378	93.12 454	87.21 304	88.72 291	96.87 252	72.09 351	97.59 307	83.52 348	93.84 235	96.03 321

ADS-MVSNet2		87.62 341	86.88 336	89.86 386	96.21 213	79.14 437	87.15 486	92.99 455	83.01 390	89.91 275	87.27 455	78.87 271	92.80 465	74.20 427	92.27 274	97.64 266

Anonymous20231206		80.76 422	79.42 425	84.79 451	84.78 474	72.98 474	96.53 379	92.97 456	79.56 433	74.33 445	88.83 441	61.27 434	92.15 473	60.59 487	75.92 399	89.24 449

MDA-MVSNet-bldmvs		77.82 443	74.75 449	87.03 428	88.33 446	78.52 443	96.34 387	92.85 457	75.57 461	48.87 506	87.89 447	57.32 447	92.49 470	60.79 486	64.80 468	90.08 433

test20.03		78.51 438	77.48 433	81.62 468	83.07 482	71.03 482	96.11 399	92.83 458	81.66 415	69.31 473	89.68 434	57.53 445	87.29 502	58.65 492	68.47 454	86.53 475

COLMAP_ROB	82.69 18	84.54 389	82.82 391	89.70 392	96.72 190	78.85 438	95.89 405	92.83 458	71.55 475	77.54 430	95.89 294	59.40 441	99.14 171	67.26 467	88.26 317	91.11 408
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_fmvs2		85.10 381	85.45 357	84.02 455	89.85 424	65.63 495	98.49 234	92.59 460	90.45 171	85.43 324	93.32 344	43.94 486	96.59 350	90.81 244	84.19 345	89.85 440

SixPastTwentyTwo		82.63 411	81.58 404	85.79 443	88.12 449	71.01 483	95.17 421	92.54 461	84.33 368	72.93 459	92.08 367	60.41 438	95.61 418	74.47 424	74.15 417	90.75 419

FMVSNet5		82.29 412	80.54 412	87.52 423	93.79 353	84.01 378	93.73 441	92.47 462	76.92 448	74.27 446	86.15 470	63.69 423	89.24 494	69.07 459	74.79 408	89.29 448

usedtu_blend_shiyan5		82.04 414	78.78 427	91.80 332	82.91 483	88.24 259	94.33 431	92.37 463	66.55 494	78.60 418	86.54 465	66.93 397	95.77 405	83.97 340	56.84 491	91.38 392

new-patchmatchnet		74.80 457	72.40 458	81.99 467	78.36 501	72.20 479	94.44 429	92.36 464	77.06 446	63.47 492	79.98 496	51.04 473	88.85 495	60.53 488	54.35 499	84.92 490

new_pmnet		76.02 448	73.71 453	82.95 461	83.88 477	72.85 477	91.26 473	92.26 465	70.44 480	62.60 493	81.37 490	47.64 483	92.32 471	61.85 483	72.10 439	83.68 495

AllTest		84.97 383	83.12 389	90.52 369	96.82 184	78.84 439	95.89 405	92.17 466	77.96 443	75.94 436	95.50 302	55.48 454	99.18 165	71.15 448	87.14 321	93.55 338

TestCases				90.52 369	96.82 184	78.84 439		92.17 466	77.96 443	75.94 436	95.50 302	55.48 454	99.18 165	71.15 448	87.14 321	93.55 338

pmmvs-eth3d		78.71 435	76.16 440	86.38 435	80.25 496	81.19 419	94.17 436	92.13 468	77.97 442	66.90 485	82.31 484	55.76 452	92.56 468	73.63 434	62.31 476	85.38 485

MIMVSNet1		75.92 449	73.30 455	83.81 457	81.29 492	75.57 463	92.26 459	92.05 469	73.09 473	67.48 483	86.18 469	40.87 493	87.64 501	55.78 496	70.68 446	88.21 460

ambc				79.60 474	72.76 512	56.61 504	76.20 514	92.01 470		68.25 478	80.23 495	23.34 507	94.73 440	73.78 433	60.81 480	87.48 466

LF4IMVS		81.94 416	81.17 409	84.25 454	87.23 461	68.87 491	93.35 447	91.93 471	83.35 385	75.40 441	93.00 355	49.25 482	96.65 348	78.88 393	78.11 385	87.22 471

TransMVSNet (Re)		81.97 415	79.61 424	89.08 407	89.70 428	84.01 378	97.26 348	91.85 472	78.84 436	73.07 458	91.62 380	67.17 394	95.21 430	67.50 466	59.46 484	88.02 461

MVStest1		76.56 447	73.43 454	85.96 442	86.30 468	80.88 425	94.26 434	91.74 473	61.98 498	58.53 498	89.96 430	69.30 375	91.47 481	59.26 490	49.56 509	85.52 484

Baseline_NR-MVSNet		85.83 370	84.82 367	88.87 412	88.73 441	83.34 387	98.63 204	91.66 474	80.41 431	82.44 357	91.35 389	74.63 320	95.42 424	84.13 335	71.39 443	87.84 462

mmtdpeth		83.69 400	82.59 399	86.99 430	92.82 376	76.98 456	96.16 398	91.63 475	82.89 398	92.41 219	82.90 480	54.95 459	98.19 227	96.27 114	53.27 501	85.81 481

testgi		82.29 412	81.00 410	86.17 438	87.24 460	74.84 467	97.39 341	91.62 476	88.63 250	75.85 439	95.42 305	46.07 485	91.55 479	66.87 470	79.94 377	92.12 362

TDRefinement		78.01 441	75.31 444	86.10 439	70.06 515	73.84 470	93.59 444	91.58 477	74.51 467	73.08 457	91.04 395	49.63 480	97.12 328	74.88 421	59.47 483	87.33 469

OpenMVS_ROB	73.86 20	77.99 442	75.06 447	86.77 433	83.81 478	77.94 449	96.38 386	91.53 478	67.54 490	68.38 477	87.13 459	43.94 486	96.08 387	55.03 498	81.83 364	86.29 478

ttmdpeth		79.80 428	77.91 431	85.47 446	83.34 480	75.75 461	95.32 419	91.45 479	76.84 449	74.81 444	91.71 379	53.98 464	94.13 448	72.42 444	61.29 477	86.51 476

test_0402		78.81 434	76.33 439	86.26 437	91.18 408	78.44 444	95.88 407	91.34 480	68.55 486	70.51 468	89.91 431	52.65 468	94.99 432	47.14 511	79.78 378	85.34 487

MTMP							99.21 115	91.09 481

DeepMVS_CX				76.08 477	90.74 414	51.65 513		90.84 482	86.47 327	57.89 500	87.98 445	35.88 499	92.60 466	65.77 473	65.06 467	83.97 493

dtuonlycased		79.10 431	78.53 428	80.81 471	86.63 464	72.95 475	96.33 388	90.81 483	81.09 422	68.85 474	87.27 455	56.94 448	87.84 499	71.57 447	67.30 461	81.65 499

test_fmvs3		75.09 454	75.19 445	74.81 480	77.45 503	54.08 508	95.93 403	90.64 484	82.51 404	73.29 453	81.19 491	22.29 508	86.29 505	85.50 316	67.89 457	84.06 492

usedtu_dtu_shiyan2		69.89 463	65.80 468	82.15 465	69.90 516	68.09 492	93.09 449	90.63 485	58.33 499	61.56 495	79.31 499	28.96 505	89.43 492	57.76 494	52.68 504	88.92 455

tt0320		76.58 446	73.16 456	86.86 432	88.03 451	77.60 452	93.55 446	90.63 485	55.37 502	70.93 464	84.98 474	41.57 490	94.01 449	69.02 460	64.32 470	88.97 453

sc_t1		78.53 437	74.87 448	89.48 400	87.92 452	77.36 454	94.80 425	90.61 487	57.65 500	76.28 432	89.59 436	38.25 495	96.18 381	74.04 429	64.72 469	94.91 333

lessismore_v0				85.08 448	85.59 472	69.28 488		90.56 488		67.68 481	90.21 427	54.21 463	95.46 422	73.88 430	62.64 474	90.50 426

Gipuma		54.77 480	52.22 482	62.40 500	86.50 465	59.37 503	50.20 533	90.35 489	36.52 521	41.20 519	49.49 529	18.33 512	81.29 508	32.10 526	65.34 466	46.54 533
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
TinyColmap		80.42 424	77.94 430	87.85 419	92.09 389	78.58 442	93.74 440	89.94 490	74.99 464	69.77 470	91.78 376	46.09 484	97.58 309	65.17 476	77.89 386	87.38 467

test_method		70.10 462	68.66 465	74.41 482	86.30 468	55.84 506	94.47 427	89.82 491	35.18 522	66.15 488	84.75 477	30.54 501	77.96 517	70.40 454	60.33 481	89.44 446

FPMVS		61.57 468	60.32 470	65.34 494	60.14 531	42.44 525	91.02 476	89.72 492	44.15 512	42.63 515	80.93 492	19.02 510	80.59 513	42.50 517	72.76 431	73.00 512

test_f		71.94 460	70.82 461	75.30 479	72.77 511	53.28 509	91.62 466	89.66 493	75.44 463	64.47 491	78.31 502	20.48 509	89.56 491	78.63 396	66.02 465	83.05 498

LCM-MVSNet		60.07 473	56.37 475	71.18 486	54.81 535	48.67 516	82.17 507	89.48 494	37.95 519	49.13 505	69.12 515	13.75 519	81.76 507	59.28 489	51.63 505	83.10 497

mvs5depth		78.17 440	75.56 443	85.97 441	80.43 495	76.44 459	85.46 490	89.24 495	76.39 451	78.17 427	88.26 444	51.73 470	95.73 409	69.31 458	61.09 478	85.73 482

tt0320-xc		75.92 449	72.23 460	87.01 429	88.40 445	78.15 446	93.57 445	89.15 496	55.46 501	69.66 471	85.79 473	38.20 496	93.85 450	69.72 455	60.08 482	89.03 451

pmmvs3		72.86 459	69.76 464	82.17 464	73.86 508	74.19 469	94.20 435	89.01 497	64.23 497	67.72 480	80.91 494	41.48 491	88.65 497	62.40 482	54.02 500	83.68 495

LCM-MVSNet-Re		88.59 325	88.61 303	88.51 414	95.53 248	72.68 478	96.85 367	88.43 498	88.45 257	73.14 455	90.63 410	75.82 312	94.38 445	92.95 212	95.71 195	98.48 217

Patchmatch-RL test		81.90 417	80.13 420	87.23 427	80.71 493	70.12 487	84.07 498	88.19 499	83.16 388	70.57 466	82.18 485	87.18 113	92.59 467	82.28 367	62.78 473	98.98 151

FE-MVSNET		75.08 455	72.25 459	83.56 459	77.93 502	76.96 457	94.36 430	87.96 500	75.72 458	66.01 489	81.60 489	50.48 476	88.85 495	55.38 497	60.82 479	84.86 491

mvsany_test3		75.85 451	74.52 450	79.83 472	73.53 509	60.64 501	91.73 465	87.87 501	83.91 375	70.55 467	82.52 482	31.12 500	93.66 454	86.66 302	62.83 472	85.19 489

DSMNet-mixed		81.60 418	81.43 406	82.10 466	84.36 475	60.79 500	93.63 443	86.74 502	79.00 434	79.32 409	87.15 458	63.87 421	89.78 490	66.89 469	91.92 281	95.73 326

ArgMatch-Sym		75.37 452	74.07 451	79.27 475	86.10 470	64.15 497	92.14 460	85.97 503	78.66 439	71.15 463	91.00 396	29.88 503	86.45 504	73.44 435	58.34 486	87.22 471

PM-MVS		74.88 456	72.85 457	80.98 470	78.98 498	64.75 496	90.81 477	85.77 504	80.95 425	68.23 479	82.81 481	29.08 504	92.84 463	76.54 410	62.46 475	85.36 486

door								85.30 505

ArgMatch-SfM		75.24 453	73.75 452	79.70 473	85.92 471	63.67 498	91.51 469	85.16 506	79.74 432	70.70 465	90.27 421	30.46 502	87.73 500	72.95 439	57.08 489	87.70 465

APD_test1		68.93 464	66.98 466	74.77 481	80.62 494	53.15 510	87.97 484	85.01 507	53.76 505	59.26 497	87.52 451	25.19 506	89.95 487	56.20 495	67.33 460	81.19 500

door-mid								84.90 508

EGC-MVSNET		60.70 472	55.37 476	76.72 476	86.35 467	71.08 481	89.96 481	84.44 509	0.38 560	1.50 562	84.09 478	37.30 497	88.10 498	40.85 521	73.44 426	70.97 515

WB-MVS		66.44 465	66.29 467	66.89 492	74.84 505	44.93 521	93.00 450	84.09 510	71.15 476	55.82 501	81.63 488	63.79 422	80.31 514	21.85 530	50.47 507	75.43 508

SSC-MVS		65.42 466	65.20 469	66.06 493	73.96 507	43.83 522	92.08 461	83.54 511	69.77 483	54.73 502	80.92 493	63.30 424	79.92 515	20.48 532	48.02 510	74.44 510

dmvs_testset		77.17 445	78.99 426	71.71 485	87.25 459	38.55 529	91.44 470	81.76 512	85.77 339	69.49 472	95.94 293	69.71 370	84.37 506	52.71 502	76.82 396	92.21 358

PMMVS2		58.97 474	55.07 477	70.69 488	62.72 525	55.37 507	85.97 488	80.52 513	49.48 510	45.94 510	68.31 516	15.73 514	80.78 511	49.79 506	37.12 519	75.91 506

LoFTR		61.59 467	56.89 474	75.68 478	76.61 504	50.06 515	82.20 506	79.57 514	52.13 507	39.02 522	75.71 506	14.90 516	93.30 458	45.35 513	46.48 513	83.69 494

ANet_high		50.71 484	46.17 488	64.33 495	44.27 543	52.30 512	76.13 515	78.73 515	64.95 495	27.37 529	55.23 526	14.61 518	67.74 525	36.01 524	18.23 538	72.95 513

PMVS	41.42 23	45.67 487	42.50 489	55.17 506	34.28 557	32.37 534	66.24 520	78.71 516	30.72 524	22.04 535	59.59 522	4.59 544	77.85 518	27.49 527	58.84 485	55.29 525
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis1_rt		81.31 420	80.05 422	85.11 447	91.29 407	70.66 484	98.98 157	77.39 517	85.76 340	68.80 475	82.40 483	36.56 498	99.44 143	92.67 219	86.55 326	85.24 488

MatchFormer		56.78 476	51.80 483	71.74 484	73.47 510	45.39 518	81.84 508	76.12 518	40.41 515	35.13 524	69.22 514	12.67 523	92.15 473	35.57 525	41.74 514	77.67 504

tmp_tt		53.66 481	52.86 481	56.05 504	32.75 559	41.97 527	73.42 518	76.12 518	21.91 529	39.68 520	96.39 277	42.59 489	65.10 528	78.00 399	14.92 546	61.08 522

testf1		56.38 477	53.73 479	64.31 496	64.84 522	45.11 519	80.50 509	75.94 520	38.87 517	42.74 513	75.07 507	11.26 526	81.19 509	41.11 519	53.27 501	66.63 517

APD_test2		56.38 477	53.73 479	64.31 496	64.84 522	45.11 519	80.50 509	75.94 520	38.87 517	42.74 513	75.07 507	11.26 526	81.19 509	41.11 519	53.27 501	66.63 517

MASt3R-SfM		60.79 471	59.91 471	63.44 499	62.41 526	35.46 530	75.76 517	71.46 522	54.67 503	58.30 499	86.10 471	14.86 517	74.25 521	65.44 474	50.18 508	80.59 501

DenseAffine		61.07 470	57.33 473	72.29 483	78.74 499	56.29 505	83.24 501	69.15 523	53.26 506	47.82 508	79.48 498	13.61 520	80.66 512	51.15 505	39.51 516	79.92 502

MVE	44.00 22	41.70 489	37.64 496	53.90 507	49.46 538	43.37 523	65.09 521	66.66 524	26.19 527	25.77 532	48.53 530	3.58 547	63.35 529	26.15 529	27.28 529	54.97 526
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		41.02 490	40.93 492	41.29 510	61.97 527	33.83 531	84.00 499	65.17 525	27.17 525	27.56 528	46.72 533	17.63 513	60.41 531	19.32 533	18.82 535	29.61 537

EMVS		39.96 492	39.88 493	40.18 511	59.57 533	32.12 536	84.79 496	64.57 526	26.27 526	26.14 531	44.18 537	18.73 511	59.29 532	17.03 534	17.67 540	29.12 538

ELoFTR		47.00 486	42.41 490	60.77 502	51.54 537	32.77 533	63.82 522	61.24 527	39.04 516	29.94 526	67.31 518	4.83 543	75.52 520	39.39 522	24.54 532	74.03 511

test_vis3_rt		61.29 469	58.75 472	68.92 489	67.41 519	52.84 511	91.18 475	59.23 528	66.96 491	41.96 518	58.44 524	11.37 525	94.72 441	74.25 426	57.97 487	59.20 523

VLMVS_CLIP		40.95 491	42.04 491	37.71 513	32.13 560	14.08 560	54.07 531	58.90 529	13.80 534	44.01 512	74.81 509	9.85 530	48.39 533	49.70 507	41.06 515	50.67 529

RoMa-SfM		58.43 475	54.99 478	68.74 490	74.29 506	50.87 514	82.37 505	58.12 530	50.53 508	48.40 507	81.78 487	12.70 522	78.25 516	47.71 510	39.01 517	77.09 505

DKM		55.59 479	51.49 484	67.89 491	72.36 513	48.29 517	80.45 511	52.05 531	47.86 511	42.54 516	77.08 505	9.06 535	77.32 519	48.87 508	33.13 521	78.05 503

GLUNet-SfM		37.11 495	32.05 500	52.28 509	44.07 545	25.94 541	52.38 532	46.25 532	24.11 528	21.50 536	55.60 525	6.32 542	66.20 527	27.48 528	10.71 552	64.70 519

RoMa-HiRes		51.04 482	47.47 485	61.73 501	65.35 521	42.38 526	76.31 513	41.57 533	42.69 513	42.32 517	77.75 503	9.33 532	73.10 522	42.68 516	29.24 524	69.72 516

DKM-HiRes		50.92 483	46.71 486	63.56 498	66.42 520	42.72 524	76.47 512	41.46 534	42.47 514	39.40 521	73.35 511	7.13 541	72.77 523	44.18 514	29.50 523	75.19 509

PDCNetPlus		48.73 485	46.34 487	55.88 505	64.17 524	41.40 528	76.11 516	34.96 535	50.17 509	35.24 523	71.04 512	15.41 515	67.33 526	52.41 503	17.59 541	58.93 524

VLMVS		38.17 494	38.75 495	36.45 516	35.35 555	13.53 562	50.05 534	33.90 536	9.30 542	47.14 509	77.14 504	12.39 524	32.34 537	47.77 509	35.68 520	63.48 520

PMatch-SfM		44.26 488	39.30 494	59.12 503	52.80 536	33.36 532	66.34 519	29.85 537	36.60 520	30.58 525	70.53 513	2.50 559	68.49 524	42.14 518	22.39 534	75.51 507

ALIKED-LG		33.96 497	32.42 499	38.57 512	70.35 514	32.25 535	57.19 526	29.49 538	19.94 530	22.96 534	46.96 532	10.85 528	47.42 534	8.53 546	25.49 530	36.04 534

N_pmnet		70.19 461	69.87 463	71.12 487	88.24 447	30.63 539	95.85 410	28.70 539	70.18 481	68.73 476	86.55 463	64.04 420	93.81 451	53.12 500	73.46 425	88.94 454

ALIKED-NN		33.05 498	31.67 501	37.18 515	69.89 517	31.76 537	55.83 530	28.14 540	16.92 531	23.23 533	47.45 531	9.65 531	45.41 536	8.80 544	25.13 531	34.38 536

ALIKED-MNN		32.26 499	30.45 502	37.68 514	69.07 518	31.55 538	56.28 529	27.56 541	16.30 532	21.15 537	44.78 535	8.12 538	46.74 535	8.19 547	22.59 533	34.76 535

SP-DiffGlue		29.92 502	29.42 506	31.40 520	32.10 561	20.02 543	47.81 535	27.27 542	14.91 533	26.24 530	54.34 527	10.53 529	24.46 544	21.49 531	30.15 522	49.71 532

SP-SuperGlue		30.18 501	29.74 505	31.50 519	60.57 529	18.71 546	57.45 524	26.07 543	13.70 535	20.25 538	39.95 541	9.22 534	25.03 543	11.85 539	28.64 527	50.78 528

SP-LightGlue		30.23 500	29.76 504	31.66 517	60.90 528	18.79 545	57.25 525	25.88 544	13.65 536	20.11 539	39.95 541	9.29 533	25.08 542	11.83 540	28.96 525	51.11 527

SP-MNN		29.29 504	28.62 508	31.29 521	59.13 534	18.03 550	56.77 528	25.19 545	11.83 538	18.01 543	39.35 544	8.35 537	25.39 540	10.99 543	27.91 528	50.47 530

XFeat-MNN		22.62 505	22.31 510	23.56 523	28.01 562	15.00 558	39.69 538	25.09 546	11.81 539	17.88 544	39.92 543	7.77 539	29.38 538	13.26 537	17.33 544	26.31 540

SP-NN		29.64 503	29.14 507	31.16 522	59.77 532	18.23 547	56.90 527	24.71 547	12.64 537	18.99 540	40.64 540	8.48 536	25.23 541	11.37 541	28.74 526	50.01 531

XFeat-NN		22.06 507	22.11 511	21.91 524	27.57 563	14.27 559	38.62 539	22.62 548	11.16 540	18.84 541	41.23 539	7.46 540	26.91 539	13.19 538	18.30 537	24.56 541

PMatch-Up-SfM		39.29 493	34.48 498	53.73 508	46.70 541	28.02 540	58.71 523	21.05 549	31.53 523	27.94 527	66.24 519	1.99 562	61.38 530	38.41 523	17.72 539	71.80 514

SIFT-NN		18.10 509	18.53 513	16.83 525	48.67 540	18.97 544	33.34 540	14.35 550	7.78 543	10.98 547	25.86 546	3.78 545	19.51 546	3.23 548	18.78 536	12.02 544

SIFT-MNN		17.20 510	17.47 514	16.41 527	45.38 542	18.16 548	31.28 542	14.20 551	7.60 544	9.54 548	25.18 547	3.39 548	19.18 547	3.18 549	17.44 542	11.88 545

SIFT-NN-NCMNet		16.94 511	17.19 515	16.19 528	43.53 546	18.04 549	31.30 541	14.18 552	7.55 546	9.51 549	24.88 548	3.32 549	18.84 548	3.08 550	17.35 543	11.70 547

SIFT-NN-UMatch		15.49 516	15.62 519	15.11 532	38.08 552	15.93 555	29.97 543	13.04 553	7.57 545	7.22 553	24.84 550	3.26 550	18.03 551	3.02 551	13.56 547	11.37 548

SIFT-NCM-Cal		16.07 514	16.20 517	15.69 529	44.16 544	17.32 551	29.83 544	12.88 554	7.33 549	6.22 556	23.59 554	3.00 553	18.75 549	2.74 556	16.09 545	10.99 550

SIFT-NN-CMatch		15.72 515	15.77 518	15.60 530	39.99 550	16.99 553	28.08 545	12.85 555	7.52 547	9.34 550	24.86 549	3.24 551	18.08 550	2.99 552	13.01 549	11.71 546

SIFT-ConvMatch		15.12 517	15.10 520	15.19 531	42.19 547	17.16 552	26.33 548	12.02 556	7.39 548	7.26 552	24.08 551	2.92 554	17.97 552	2.85 554	10.90 551	10.43 552

SIFT-NN-PointCN		14.43 519	14.70 522	13.64 535	36.13 553	12.94 563	27.63 547	11.82 557	7.03 553	8.24 551	23.49 555	3.21 552	16.75 555	2.85 554	11.89 550	11.22 549

SIFT-UMatch		14.73 518	14.79 521	14.57 533	40.58 549	15.36 557	27.70 546	11.21 558	7.28 550	6.62 555	24.07 552	2.81 557	17.91 553	2.87 553	9.94 553	10.45 551

SIFT-CM-Cal		14.12 520	14.09 523	14.22 534	40.92 548	15.56 556	23.80 550	10.18 559	7.20 551	6.72 554	23.20 556	2.86 556	16.98 554	2.67 558	9.24 556	10.13 553

SIFT-PointCN		12.37 522	12.72 525	11.33 537	35.33 556	10.01 564	23.72 551	9.79 560	6.45 555	5.30 560	20.10 558	2.22 561	14.67 559	2.33 560	9.26 555	9.30 555

SIFT-UM-Cal		13.73 521	13.86 524	13.34 536	39.95 551	13.63 561	25.68 549	9.21 561	7.19 552	5.57 557	23.60 553	2.66 558	16.67 556	2.70 557	8.18 557	9.73 554

MVS_clip		35.38 496	36.65 497	31.56 518	48.77 539	16.48 554	41.99 536	8.97 562	9.90 541	45.60 511	78.84 500	13.61 520	15.85 557	44.08 515	38.09 518	62.37 521

SIFT-PCN-Cal		12.09 523	12.36 526	11.26 538	35.43 554	9.79 565	22.24 552	8.83 563	6.37 556	5.43 559	20.44 557	2.34 560	14.88 558	2.35 559	7.87 558	9.13 556

SIFT-NCMNet		10.41 525	10.63 529	9.76 539	33.41 558	9.03 566	18.23 553	5.49 564	6.29 557	4.60 561	17.58 559	1.84 563	12.74 560	2.03 561	6.21 559	7.52 557

wuyk23d		16.71 512	16.73 516	16.65 526	60.15 530	25.22 542	41.24 537	5.17 565	6.56 554	5.48 558	3.61 560	3.64 546	22.72 545	15.20 535	9.52 554	1.99 558

testmvs		18.81 508	23.05 509	6.10 542	4.48 565	2.29 568	97.78 317	3.00 566	3.27 558	18.60 542	62.71 520	1.53 564	2.49 562	14.26 536	1.80 560	13.50 543

test123		16.58 513	19.47 512	7.91 541	3.59 566	5.37 567	94.32 432	1.39 567	2.49 559	13.98 546	44.60 536	2.91 555	2.65 561	11.35 542	0.57 561	15.70 542

MVS_baseline		11.50 524	12.32 527	9.06 540	13.94 564	0.55 569	4.75 554	1.33 568	0.26 561	16.85 545	50.28 528	1.45 565	0.03 563	8.71 545	13.26 548	26.61 539

mmdepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

monomultidepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

test_blank		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

uanet_test		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

DCPMVS		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

pcd_1.5k_mvsjas		6.87 527	9.16 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	82.48 217	0.00 564	0.00 562	0.00 562	0.00 559

sosnet-low-res		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

sosnet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

uncertanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

Regformer		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

n2								0.00 569

nn								0.00 569

ab-mvs-re		8.21 526	10.94 528	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	98.50 132	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

uanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

Meshroom													0.00 564
: In preparation.
AliceVision / Meshro													0.00 564
: In preparation.
AliceVision_Meshroom													0.00 564
: In preparation.
PatchmatchNet1														52.97 501	73.44 426	88.99 452
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													93.74 452
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						79.74 431								67.75 465

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

eth-test2					0.00 567

eth-test					0.00 567

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

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

GSMVS																98.84 168

test_part2					99.54 42	95.42 25				98.13 65

sam_mvs1												88.39 86				98.84 168

sam_mvs												87.08 116

test_post1							90.74 479				41.37 538	85.38 158	96.36 365	83.16 351

test_post											46.00 534	87.37 107	97.11 329

patchmatchnet-post											84.86 475	88.73 82	96.81 342

gm-plane-assit					94.69 310	88.14 265			88.22 270		97.20 216		98.29 218	90.79 245

test9_res														98.60 52	99.87 9	99.90 23

agg_prior2														97.84 79	99.87 9	99.91 22

test_prior4						92.00 126	99.41 93

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

旧先验2							98.67 198		85.75 341	98.96 33			98.97 180	93.84 185

新几何2							98.26 272

原ACMM2							98.69 194

testdata2													99.88 73	84.16 334

segment_acmp												90.56 55

testdata1							97.89 309		92.43 110

plane_prior7					93.84 349	85.73 349

plane_prior6					93.92 346	86.02 341						72.92 343

plane_prior4											96.52 269

plane_prior3						85.91 343			93.65 83	86.99 308

plane_prior2							99.02 151		93.38 90

plane_prior1					93.90 348

plane_prior						86.07 339	99.14 132		93.81 79						86.26 329

HQP5-MVS						86.39 320

HQP-NCC					93.95 341		99.16 124		93.92 70	87.57 301

ACMP_Plane					93.95 341		99.16 124		93.92 70	87.57 301

BP-MVS														93.82 187

HQP4-MVS										87.57 301			97.77 285			92.72 344

HQP2-MVS												73.34 336

NP-MVS					93.94 344	86.22 327					96.67 266

MDTV_nov1_ep13_2view						91.17 150	91.38 471		87.45 300	93.08 197		86.67 128		87.02 289		98.95 157

ACMMP++_ref															82.64 361

ACMMP++															83.83 348

Test By Simon												83.62 185

High-resolution multi-view benchmark