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.

DVP-MVS++		99.08 5	98.89 7	99.64 4	99.17 113	99.23 7	99.69 1	98.88 78	97.32 66	99.53 39	99.47 38	97.81 3	99.94 15	98.47 65	99.72 68	99.74 51

FOURS1					99.82 1	98.66 31	99.69 1	98.95 61	97.46 58	99.39 47

CS-MVS		98.44 58	98.49 37	98.31 139	99.08 128	96.73 140	99.67 3	98.47 208	97.17 81	98.94 80	99.10 128	95.73 53	99.13 271	98.71 46	99.49 119	99.09 219

SPE-MVS-test		98.49 52	98.50 35	98.46 125	99.20 111	97.05 126	99.64 4	98.50 201	97.45 59	98.88 87	99.14 116	95.25 74	99.15 266	98.83 42	99.56 108	99.20 193

EC-MVSNet		98.21 80	98.11 77	98.49 121	98.34 220	97.26 113	99.61 5	98.43 229	96.78 103	98.87 88	98.84 182	93.72 110	99.01 302	98.91 39	99.50 117	99.19 197

HPM-MVS		98.36 67	98.10 78	99.13 60	99.74 12	97.82 82	99.53 6	98.80 116	94.63 252	98.61 116	98.97 157	95.13 81	99.77 131	97.65 126	99.83 14	99.79 30
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MVSFormer		97.57 120	97.49 107	97.84 204	98.07 273	95.76 215	99.47 7	98.40 238	94.98 229	98.79 95	98.83 186	92.34 132	98.41 377	96.91 181	99.59 96	99.34 152

test_djsdf		96.00 230	95.69 235	96.93 281	95.72 440	95.49 229	99.47 7	98.40 238	94.98 229	94.58 315	97.86 296	89.16 255	98.41 377	96.91 181	94.12 338	96.88 364

HPM-MVS_fast		98.38 64	98.13 75	99.12 62	99.75 6	97.86 77	99.44 9	98.82 103	94.46 265	98.94 80	99.20 96	95.16 79	99.74 136	97.58 135	99.85 7	99.77 41

lecture		98.95 10	98.78 15	99.45 20	99.75 6	98.63 33	99.43 10	99.38 8	97.60 47	99.58 35	99.47 38	95.36 66	99.93 35	98.87 40	99.57 100	99.78 34

nrg030		96.28 221	95.72 229	97.96 196	96.90 380	98.15 66	99.39 11	98.31 273	95.47 189	94.42 325	98.35 247	92.09 146	98.69 342	97.50 149	89.05 422	97.04 346

APDe-MVS		99.02 9	98.84 11	99.55 11	99.57 40	98.96 19	99.39 11	98.93 65	97.38 63	99.41 45	99.54 21	96.66 21	99.84 90	98.86 41	99.85 7	99.87 13
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
3Dnovator+	94.38 6	97.43 141	96.78 176	99.38 25	97.83 305	98.52 36	99.37 13	98.71 139	97.09 88	92.99 394	99.13 119	89.36 249	99.89 70	96.97 177	99.57 100	99.71 64

FIs		96.51 208	96.12 211	97.67 225	97.13 366	97.54 90	99.36 14	99.22 32	95.89 155	94.03 348	98.35 247	91.98 149	98.44 368	96.40 210	92.76 368	97.01 347

FC-MVSNet-test		96.42 211	96.05 213	97.53 237	96.95 375	97.27 108	99.36 14	99.23 27	95.83 160	93.93 351	98.37 245	92.00 148	98.32 389	96.02 223	92.72 369	97.00 348

3Dnovator	94.51 5	97.46 136	96.93 163	99.07 66	97.78 309	97.64 84	99.35 16	99.06 47	97.02 90	93.75 364	99.16 111	89.25 252	99.92 44	97.22 169	99.75 55	99.64 88

sasdasda		97.67 107	97.23 135	98.98 74	98.70 169	98.38 43	99.34 17	98.39 244	96.76 105	97.67 197	97.40 341	92.26 136	99.49 193	98.28 81	96.28 307	99.08 223

GeoE		96.58 205	96.07 212	98.10 172	98.35 215	95.89 202	99.34 17	98.12 317	93.12 343	96.09 280	98.87 178	89.71 236	98.97 305	92.95 341	98.08 235	99.43 132

canonicalmvs		97.67 107	97.23 135	98.98 74	98.70 169	98.38 43	99.34 17	98.39 244	96.76 105	97.67 197	97.40 341	92.26 136	99.49 193	98.28 81	96.28 307	99.08 223

CP-MVS		98.57 42	98.36 47	99.19 52	99.66 31	97.86 77	99.34 17	98.87 85	95.96 152	98.60 117	99.13 119	96.05 42	99.94 15	97.77 115	99.86 2	99.77 41

EPP-MVSNet		97.46 136	97.28 128	97.99 188	98.64 180	95.38 240	99.33 21	98.31 273	93.61 319	97.19 224	99.07 143	94.05 105	99.23 248	96.89 185	98.43 203	99.37 145

aaatest				99.52 15	99.77 2	98.86 24	99.32 22	99.24 20	96.41 126	99.30 53	99.35 63		99.92 44	98.30 77	99.80 26	99.79 30

MED-MVS		99.12 2	98.97 5	99.56 9	99.77 2	98.86 24	99.32 22	99.24 20	97.87 32	99.30 53	99.54 21	97.61 6	99.92 44	98.30 77	99.80 26	99.90 6

TestfortrainingZip a		99.05 7	98.85 10	99.65 2	99.77 2	99.13 12	99.32 22	99.01 52	97.87 32	99.74 22	99.54 21	96.71 19	99.92 44	98.35 74	99.33 141	99.90 6

TestfortrainingZip				99.43 22	99.13 121	99.06 16	99.32 22	98.57 180	96.88 98	99.42 44	99.05 146	96.54 25	99.73 138		98.59 183	99.51 106

MGCFI-Net		97.62 113	97.19 139	98.92 80	98.66 176	98.20 61	99.32 22	98.38 251	96.69 111	97.58 211	97.42 340	92.10 145	99.50 192	98.28 81	96.25 310	99.08 223

balanced_ft_v1		97.54 127	97.38 119	98.02 184	98.34 220	95.58 222	99.32 22	98.40 238	95.88 156	98.43 131	98.65 215	88.95 267	99.59 169	98.94 37	99.48 122	98.90 246

XVS		98.70 25	98.49 37	99.34 33	99.70 27	98.35 52	99.29 28	98.88 78	97.40 60	98.46 123	99.20 96	95.90 50	99.89 70	97.85 109	99.74 59	99.78 34

X-MVStestdata		94.06 371	92.30 397	99.34 33	99.70 27	98.35 52	99.29 28	98.88 78	97.40 60	98.46 123	43.50 555	95.90 50	99.89 70	97.85 109	99.74 59	99.78 34

tttt0517		96.07 227	95.51 241	97.78 210	98.41 205	94.84 273	99.28 30	94.33 496	94.26 273	97.64 204	98.64 216	84.05 379	99.47 202	95.34 250	97.60 256	99.03 231

mPP-MVS		98.51 50	98.26 63	99.25 46	99.75 6	98.04 71	99.28 30	98.81 109	96.24 135	98.35 136	99.23 88	95.46 60	99.94 15	97.42 158	99.81 17	99.77 41

test_vis1_n		95.47 260	95.13 261	96.49 329	97.77 310	90.41 424	99.27 32	98.11 320	96.58 116	99.66 30	99.18 106	67.00 491	99.62 166	99.21 29	99.40 133	99.44 128

test_fmvs1_n		95.90 238	95.99 219	95.63 385	98.67 175	88.32 467	99.26 33	98.22 295	96.40 127	99.67 29	99.26 81	73.91 476	99.70 145	99.02 35	99.50 117	98.87 248

MSP-MVS		98.74 23	98.55 30	99.29 40	99.75 6	98.23 59	99.26 33	98.88 78	97.52 51	99.41 45	98.78 195	96.00 44	99.79 123	97.79 114	99.59 96	99.85 17
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
v7n		94.19 358	93.43 371	96.47 332	95.90 434	94.38 297	99.26 33	98.34 262	91.99 386	92.76 399	97.13 361	88.31 283	98.52 359	89.48 427	87.70 436	96.52 419

MVSMamba_PlusPlus		98.31 74	98.19 74	98.67 97	98.96 143	97.36 99	99.24 36	98.57 180	94.81 240	98.99 78	98.90 174	95.22 77	99.59 169	99.15 30	99.84 12	99.07 227

WR-MVS_H		95.05 293	94.46 298	96.81 291	96.86 382	95.82 210	99.24 36	99.24 20	93.87 294	92.53 408	96.84 399	90.37 218	98.24 399	93.24 330	87.93 434	96.38 433

testing915		97.30 158	96.90 165	98.48 122	98.88 149	96.42 160	99.23 38	97.92 345	95.80 161	98.11 144	98.30 256	88.59 274	99.33 217	97.52 144	97.75 250	99.71 64

HFP-MVS		98.63 30	98.40 43	99.32 39	99.72 17	98.29 55	99.23 38	98.96 60	96.10 145	98.94 80	99.17 108	96.06 41	99.92 44	97.62 128	99.78 41	99.75 49

region2R		98.61 32	98.38 45	99.29 40	99.74 12	98.16 65	99.23 38	98.93 65	96.15 139	98.94 80	99.17 108	95.91 48	99.94 15	97.55 140	99.79 36	99.78 34

ACMMPR		98.59 35	98.36 47	99.29 40	99.74 12	98.15 66	99.23 38	98.95 61	96.10 145	98.93 84	99.19 103	95.70 54	99.94 15	97.62 128	99.79 36	99.78 34

QAPM		96.29 219	95.40 243	98.96 77	97.85 304	97.60 87	99.23 38	98.93 65	89.76 439	93.11 391	99.02 149	89.11 257	99.93 35	91.99 376	99.62 91	99.34 152

MP-MVS		98.33 73	98.01 83	99.28 43	99.75 6	98.18 63	99.22 43	98.79 121	96.13 140	97.92 172	99.23 88	94.54 92	99.94 15	96.74 200	99.78 41	99.73 56
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
Vis-MVSNet		97.42 142	97.11 149	98.34 137	98.66 176	96.23 170	99.22 43	99.00 53	96.63 115	98.04 155	99.21 94	88.05 294	99.35 214	96.01 224	99.21 147	99.45 125
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CSCG		97.85 95	97.74 92	98.20 151	99.67 30	95.16 253	99.22 43	99.32 12	93.04 346	97.02 234	98.92 172	95.36 66	99.91 58	97.43 156	99.64 87	99.52 103

mmtdpeth		93.12 393	92.61 389	94.63 426	97.60 325	89.68 440	99.21 46	97.32 405	94.02 281	97.72 192	94.42 468	77.01 453	99.44 205	99.05 32	77.18 494	94.78 477

SDMVSNet		96.85 188	96.42 196	98.14 161	99.30 85	96.38 162	99.21 46	99.23 27	95.92 153	95.96 286	98.76 203	85.88 339	99.44 205	97.93 100	95.59 322	98.60 285

OpenMVS	93.04 13	95.83 242	95.00 269	98.32 138	97.18 363	97.32 101	99.21 46	98.97 57	89.96 435	91.14 437	99.05 146	86.64 322	99.92 44	93.38 325	99.47 123	97.73 326

DTE-MVSNet		93.98 373	93.26 376	96.14 353	96.06 424	94.39 296	99.20 49	98.86 91	93.06 345	91.78 429	97.81 304	85.87 340	97.58 457	90.53 407	86.17 453	96.46 430

Vis-MVSNet (Re-imp)		96.87 187	96.55 190	97.83 205	98.73 164	95.46 231	99.20 49	98.30 280	94.96 231	96.60 258	98.87 178	90.05 226	98.59 354	93.67 319	98.60 182	99.46 123

test_fmvs2		93.43 381	93.58 363	92.95 460	96.97 374	83.91 491	99.19 51	97.24 415	95.74 165	95.20 300	98.27 260	69.65 483	98.72 341	96.26 214	93.73 347	96.24 439

BridgeMVS		98.45 57	98.35 49	98.74 91	98.65 179	97.55 88	99.19 51	98.60 166	96.72 110	99.35 49	98.77 198	95.06 84	99.55 183	98.95 36	99.87 1	99.12 210

ZNCC-MVS		98.49 52	98.20 72	99.35 32	99.73 16	98.39 42	99.19 51	98.86 91	95.77 164	98.31 140	99.10 128	95.46 60	99.93 35	97.57 139	99.81 17	99.74 51

IS-MVSNet		97.22 164	96.88 166	98.25 145	98.85 157	96.36 164	99.19 51	97.97 340	95.39 195	97.23 222	98.99 156	91.11 191	98.93 315	94.60 284	98.59 183	99.47 118

mvsmamba		97.25 162	96.99 159	98.02 184	98.34 220	95.54 227	99.18 55	97.47 390	95.04 222	98.15 141	98.57 226	89.46 244	99.31 223	97.68 125	99.01 157	99.22 190

PEN-MVS		94.42 343	93.73 356	96.49 329	96.28 413	94.84 273	99.17 56	99.00 53	93.51 322	92.23 420	97.83 302	86.10 335	97.90 436	92.55 362	86.92 448	96.74 379

PS-MVSNAJss		96.43 210	96.26 205	96.92 284	95.84 437	95.08 259	99.16 57	98.50 201	95.87 158	93.84 359	98.34 251	94.51 93	98.61 350	96.88 187	93.45 355	97.06 345

BP-MVS1		97.82 97	97.51 106	98.76 90	98.25 240	97.39 98	99.15 58	97.68 363	96.69 111	98.47 122	99.10 128	90.29 221	99.51 189	98.60 52	99.35 138	99.37 145

dcpmvs_2		98.08 83	98.59 26	96.56 320	99.57 40	90.34 427	99.15 58	98.38 251	96.82 102	99.29 55	99.49 35	95.78 52	99.57 173	98.94 37	99.86 2	99.77 41

APD-MVS_3200maxsize		98.53 47	98.33 59	99.15 58	99.50 49	97.92 76	99.15 58	98.81 109	96.24 135	99.20 61	99.37 57	95.30 70	99.80 111	97.73 117	99.67 76	99.72 60

TSAR-MVS + MP.		98.78 21	98.62 23	99.24 47	99.69 29	98.28 56	99.14 61	98.66 155	96.84 100	99.56 36	99.31 72	96.34 34	99.70 145	98.32 76	99.73 63	99.73 56
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
anonymousdsp		95.42 266	94.91 274	96.94 280	95.10 458	95.90 197	99.14 61	98.41 235	93.75 300	93.16 387	97.46 334	87.50 308	98.41 377	95.63 242	94.03 340	96.50 425

jajsoiax		95.45 263	95.03 268	96.73 296	95.42 454	94.63 283	99.14 61	98.52 193	95.74 165	93.22 384	98.36 246	83.87 384	98.65 347	96.95 179	94.04 339	96.91 360

PS-CasMVS		94.67 322	93.99 335	96.71 299	96.68 394	95.26 247	99.13 64	99.03 50	93.68 311	92.33 418	97.95 287	85.35 349	98.10 411	93.59 321	88.16 433	96.79 374

RRT-MVS		97.03 177	96.78 176	97.77 213	97.90 301	94.34 299	99.12 65	98.35 258	95.87 158	98.06 151	98.70 209	86.45 327	99.63 162	98.04 95	98.54 189	99.35 150

CPTT-MVS		97.72 103	97.32 125	98.92 80	99.64 33	97.10 124	99.12 65	98.81 109	92.34 374	98.09 147	99.08 139	93.01 119	99.92 44	96.06 221	99.77 43	99.75 49

SR-MVS-dyc-post		98.54 46	98.35 49	99.13 60	99.49 53	97.86 77	99.11 67	98.80 116	96.49 121	99.17 64	99.35 63	95.34 68	99.82 99	97.72 118	99.65 82	99.71 64

RE-MVS-def			98.34 55		99.49 53	97.86 77	99.11 67	98.80 116	96.49 121	99.17 64	99.35 63	95.29 71		97.72 118	99.65 82	99.71 64

CP-MVSNet		94.94 307	94.30 308	96.83 289	96.72 392	95.56 224	99.11 67	98.95 61	93.89 291	92.42 414	97.90 292	87.19 313	98.12 410	94.32 295	88.21 431	96.82 373

SteuartSystems-ACMMP		98.90 16	98.75 18	99.36 31	99.22 108	98.43 41	99.10 70	98.87 85	97.38 63	99.35 49	99.40 50	97.78 5	99.87 81	97.77 115	99.85 7	99.78 34
Skip Steuart: Steuart Systems R&D Blog.
SR-MVS		98.57 42	98.35 49	99.24 47	99.53 43	98.18 63	99.09 71	98.82 103	96.58 116	99.10 71	99.32 70	95.39 63	99.82 99	97.70 123	99.63 89	99.72 60

GST-MVS		98.43 60	98.12 76	99.34 33	99.72 17	98.38 43	99.09 71	98.82 103	95.71 168	98.73 101	99.06 144	95.27 72	99.93 35	97.07 173	99.63 89	99.72 60

Casviewmamba		97.62 113	97.43 115	98.19 155	98.48 195	95.83 207	99.07 73	98.42 233	96.27 134	98.09 147	99.26 81	91.00 196	99.30 224	97.81 113	98.48 196	99.44 128

K. test v3		92.55 401	91.91 404	94.48 432	95.64 442	89.24 448	99.07 73	94.88 490	94.04 279	86.78 478	97.59 325	77.64 446	97.64 453	92.08 371	89.43 417	96.57 409

test2506		94.44 342	93.91 340	96.04 357	99.02 133	88.99 454	99.06 75	79.47 530	96.96 94	98.36 134	99.26 81	77.21 448	99.52 188	96.78 198	99.04 154	99.59 96

test0726					99.72 17	99.25 2	99.06 75	98.88 78	97.62 44	99.56 36	99.50 32	97.42 10

GDP-MVS		97.64 110	97.28 128	98.71 94	98.30 229	97.33 100	99.05 77	98.52 193	96.34 131	98.80 94	99.05 146	89.74 235	99.51 189	96.86 193	98.86 168	99.28 176

test_vis1_n_1920		96.71 196	96.84 169	96.31 347	99.11 125	89.74 436	99.05 77	98.58 178	98.08 25	99.87 5	99.37 57	78.48 433	99.93 35	99.29 28	99.69 73	99.27 177

test_fmvs3		87.17 456	87.06 459	87.50 482	91.21 504	75.66 509	99.05 77	96.61 461	92.79 357	88.85 464	92.78 491	43.72 513	93.49 507	93.95 309	84.56 462	93.34 498

v8		94.47 340	93.77 352	96.57 319	96.36 410	94.83 275	99.05 77	98.19 301	91.92 388	93.16 387	96.97 385	88.82 272	98.48 361	91.69 385	87.79 435	96.39 432

test1111		95.94 235	95.78 226	96.41 339	98.99 140	90.12 429	99.04 81	92.45 512	96.99 93	98.03 156	99.27 80	81.40 403	99.48 198	96.87 190	99.04 154	99.63 90

SF-MVS		98.59 35	98.32 60	99.41 24	99.54 42	98.71 28	99.04 81	98.81 109	95.12 216	99.32 52	99.39 51	96.22 35	99.84 90	97.72 118	99.73 63	99.67 81

PHI-MVS		98.34 71	98.06 79	99.18 54	99.15 120	98.12 69	99.04 81	99.09 44	93.32 332	98.83 93	99.10 128	96.54 25	99.83 92	97.70 123	99.76 49	99.59 96

ECVR-MVS		95.95 232	95.71 232	96.65 305	99.02 133	90.86 410	99.03 84	91.80 513	96.96 94	98.10 146	99.26 81	81.31 404	99.51 189	96.90 184	99.04 154	99.59 96

TranMVSNet+NR-MVSNet		95.14 286	94.48 296	97.11 266	96.45 407	96.36 164	99.03 84	99.03 50	95.04 222	93.58 368	97.93 289	88.27 286	98.03 425	94.13 303	86.90 449	96.95 352

ACMMP		98.23 77	97.95 85	99.09 64	99.74 12	97.62 86	99.03 84	99.41 6	95.98 150	97.60 209	99.36 61	94.45 97	99.93 35	97.14 170	98.85 170	99.70 69
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
hybridcas		97.52 130	97.29 127	98.20 151	98.44 200	96.00 181	99.02 87	98.39 244	96.12 143	97.69 195	99.23 88	90.77 206	99.17 260	97.55 140	98.42 209	99.44 128

SED-MVS		99.09 3	98.91 6	99.63 5	99.71 24	99.24 5	99.02 87	98.87 85	97.65 42	99.73 24	99.48 36	97.53 8	99.94 15	98.43 69	99.81 17	99.70 69

OPU-MVS				99.37 29	99.24 105	99.05 17	99.02 87				99.16 111	97.81 3	99.37 213	97.24 167	99.73 63	99.70 69

EIA-MVS		97.75 101	97.58 98	98.27 141	98.38 210	96.44 157	99.01 90	98.60 166	95.88 156	97.26 220	97.53 331	94.97 86	99.33 217	97.38 163	99.20 148	99.05 228

Anonymous20231211		94.10 367	93.26 376	96.61 313	99.11 125	94.28 302	99.01 90	98.88 78	86.43 473	92.81 397	97.57 327	81.66 402	98.68 345	94.83 268	89.02 424	96.88 364

test_cas_vis1_n_1920		97.38 146	97.36 121	97.45 241	98.95 144	93.25 353	99.00 92	98.53 190	97.70 40	99.77 19	99.35 63	84.71 364	99.85 86	98.57 54	99.66 79	99.26 184

mvs_tets		95.41 268	95.00 269	96.65 305	95.58 445	94.42 294	99.00 92	98.55 186	95.73 167	93.21 385	98.38 244	83.45 390	98.63 348	97.09 172	94.00 341	96.91 360

baseline		97.64 110	97.44 113	98.25 145	98.35 215	96.20 171	99.00 92	98.32 268	96.33 133	98.03 156	99.17 108	91.35 175	99.16 262	98.10 89	98.29 223	99.39 140

KinetiMVS		97.48 132	97.05 154	98.78 88	98.37 213	97.30 104	98.99 95	98.70 142	97.18 80	99.02 73	99.01 153	87.50 308	99.67 152	95.33 251	99.33 141	99.37 145

v10		94.29 351	93.55 365	96.51 327	96.39 409	94.80 277	98.99 95	98.19 301	91.35 406	93.02 393	96.99 383	88.09 291	98.41 377	90.50 408	88.41 430	96.33 436

PGM-MVS		98.49 52	98.23 68	99.27 45	99.72 17	98.08 70	98.99 95	99.49 5	95.43 191	99.03 72	99.32 70	95.56 57	99.94 15	96.80 197	99.77 43	99.78 34

LPG-MVS_test		95.62 254	95.34 249	96.47 332	97.46 339	93.54 331	98.99 95	98.54 188	94.67 250	94.36 328	98.77 198	85.39 347	99.11 276	95.71 237	94.15 336	96.76 377

fmvsm_s_conf0.5_n_11		98.58 37	98.57 27	98.62 101	99.42 65	97.16 120	98.97 99	98.86 91	98.91 5	99.87 5	99.66 4	91.82 155	99.95 10	99.82 7	99.82 15	98.75 266

test_fmvsmvis_n_1920		98.44 58	98.51 33	98.23 148	98.33 224	96.15 174	98.97 99	99.15 41	98.55 17	98.45 126	99.55 19	94.26 102	99.97 1	99.65 19	99.66 79	98.57 291

DVP-MVS		99.03 8	98.83 12	99.63 5	99.72 17	99.25 2	98.97 99	98.58 178	97.62 44	99.45 41	99.46 43	97.42 10	99.94 15	98.47 65	99.81 17	99.69 72
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
test_0728_SECOND				99.71 1	99.72 17	99.35 1	98.97 99	98.88 78					99.94 15	98.47 65	99.81 17	99.84 19

tfpnnormal		93.66 376	92.70 387	96.55 324	96.94 376	95.94 191	98.97 99	99.19 35	91.04 417	91.38 435	97.34 345	84.94 357	98.61 350	85.45 467	89.02 424	95.11 468

V42		94.78 314	94.14 321	96.70 301	96.33 412	95.22 250	98.97 99	98.09 327	92.32 376	94.31 331	97.06 373	88.39 282	98.55 356	92.90 343	88.87 426	96.34 434

test_fmvsm_n_1920		98.87 19	99.01 4	98.45 126	99.42 65	96.43 158	98.96 105	99.36 10	98.63 14	99.86 9	99.51 29	95.91 48	99.97 1	99.72 15	99.75 55	98.94 242

test_fmvsmconf0.01_n		97.86 93	97.54 104	98.83 85	95.48 450	96.83 135	98.95 106	98.60 166	98.58 15	98.93 84	99.55 19	88.57 276	99.91 58	99.54 25	99.61 92	99.77 41

SMA-MVS		98.58 37	98.25 64	99.56 9	99.51 47	99.04 18	98.95 106	98.80 116	93.67 313	99.37 48	99.52 26	96.52 27	99.89 70	98.06 92	99.81 17	99.76 48
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
pm-mvs1		93.94 374	93.06 379	96.59 316	96.49 404	95.16 253	98.95 106	98.03 337	92.32 376	91.08 438	97.84 299	84.54 369	98.41 377	92.16 369	86.13 456	96.19 442

PRO-TEST		97.77 100	97.67 95	98.06 178	98.15 265	96.06 180	98.94 109	98.46 209	96.88 98	98.72 103	98.59 222	92.46 128	99.03 295	97.89 105	98.97 160	99.10 215

NormalMVS		98.07 85	97.90 88	98.59 105	99.75 6	96.60 146	98.94 109	98.60 166	97.86 34	98.71 105	99.08 139	91.22 183	99.80 111	97.40 160	99.57 100	99.37 145

SymmetryMVS		97.84 96	97.58 98	98.62 101	99.01 135	96.60 146	98.94 109	98.44 218	97.86 34	98.71 105	99.08 139	91.22 183	99.80 111	97.40 160	97.53 264	99.47 118

AstraMVS		97.34 154	97.24 134	97.65 229	98.13 267	94.15 310	98.94 109	96.25 469	97.47 57	98.60 117	99.28 77	89.67 237	99.41 208	98.73 45	98.07 236	99.38 144

reproduce_model		98.94 11	98.81 13	99.34 33	99.52 46	98.26 57	98.94 109	98.84 97	98.06 26	99.35 49	99.61 6	96.39 33	99.94 15	98.77 44	99.82 15	99.83 20

Anonymous20240521		91.18 417	90.44 415	93.42 448	93.70 477	88.47 464	98.94 109	97.56 377	88.46 457	89.56 457	95.08 463	77.15 451	96.97 469	83.92 477	89.55 413	94.82 474

VPA-MVSNet		95.75 246	95.11 264	97.69 221	97.24 355	97.27 108	98.94 109	99.23 27	95.13 215	95.51 293	97.32 348	85.73 341	98.91 318	97.33 165	89.55 413	96.89 363

casdiffseed414692147		96.97 182	96.55 190	98.25 145	98.26 238	96.28 169	98.93 116	98.33 264	94.99 227	96.87 242	99.09 136	88.97 265	99.07 285	95.70 239	97.77 248	99.39 140

MM		98.51 50	98.24 66	99.33 37	99.12 123	98.14 68	98.93 116	97.02 436	98.96 2	99.17 64	99.47 38	91.97 151	99.94 15	99.85 5	99.69 73	99.91 5

LS3D		97.16 171	96.66 185	98.68 96	98.53 189	97.19 118	98.93 116	98.90 73	92.83 356	95.99 284	99.37 57	92.12 144	99.87 81	93.67 319	99.57 100	98.97 237

MonoMVSNet		95.51 258	95.45 242	95.68 382	95.54 446	90.87 409	98.92 119	97.37 402	95.79 163	95.53 292	97.38 343	89.58 239	97.68 451	96.40 210	92.59 370	98.49 295

casdiffmvs_mvg		97.72 103	97.48 109	98.44 128	98.42 203	96.59 150	98.92 119	98.44 218	96.20 137	97.76 186	99.20 96	91.66 161	99.23 248	98.27 84	98.41 211	99.49 114
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMM	93.85 9	95.69 251	95.38 247	96.61 313	97.61 324	93.84 319	98.91 121	98.44 218	95.25 206	94.28 334	98.47 235	86.04 338	99.12 274	95.50 247	93.95 343	96.87 367
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MTAPA		98.58 37	98.29 62	99.46 19	99.76 5	98.64 32	98.90 122	98.74 131	97.27 74	98.02 158	99.39 51	94.81 89	99.96 5	97.91 103	99.79 36	99.77 41

SD-MVS		98.64 29	98.68 20	98.53 114	99.33 76	98.36 51	98.90 122	98.85 96	97.28 70	99.72 27	99.39 51	96.63 23	97.60 455	98.17 86	99.85 7	99.64 88
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
TransMVSNet (Re)		92.67 399	91.51 406	96.15 352	96.58 398	94.65 281	98.90 122	96.73 453	90.86 420	89.46 458	97.86 296	85.62 344	98.09 415	86.45 459	81.12 479	95.71 455

EPNet		97.28 159	96.87 167	98.51 116	94.98 459	96.14 175	98.90 122	97.02 436	98.28 22	95.99 284	99.11 126	91.36 174	99.89 70	96.98 176	99.19 149	99.50 109
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
guyue		97.57 120	97.37 120	98.20 151	98.50 190	95.86 204	98.89 126	97.03 433	97.29 68	98.73 101	98.90 174	89.41 247	99.32 219	98.68 47	98.86 168	99.42 135

fmvsm_l_conf0.5_n_3		98.90 16	98.74 19	99.37 29	99.36 70	98.25 58	98.89 126	99.24 20	98.77 11	99.89 4	99.59 14	93.39 114	99.96 5	99.78 11	99.76 49	99.89 9

fmvsm_l_conf0.5_n		99.07 6	99.05 3	99.14 59	99.41 67	97.54 90	98.89 126	99.31 13	98.49 18	99.86 9	99.42 47	96.45 30	99.96 5	99.86 1	99.74 59	99.90 6

fmvsm_s_conf0.1_n_a		98.08 83	98.04 81	98.21 149	97.66 321	95.39 239	98.89 126	99.17 37	97.24 75	99.76 21	99.67 2	91.13 188	99.88 79	99.39 27	99.41 130	99.35 150

MTMP							98.89 126	94.14 501

UA-Net		97.96 88	97.62 96	98.98 74	98.86 154	97.47 94	98.89 126	99.08 45	96.67 113	98.72 103	99.54 21	93.15 118	99.81 104	94.87 266	98.83 171	99.65 85

OurMVSNet-221017-0		94.21 356	94.00 333	94.85 416	95.60 444	89.22 449	98.89 126	97.43 397	95.29 203	92.18 423	98.52 231	82.86 391	98.59 354	93.46 324	91.76 381	96.74 379

fmvsm_l_conf0.5_n_a		99.09 3	99.08 2	99.11 63	99.43 64	97.48 92	98.88 133	99.30 14	98.47 19	99.85 12	99.43 46	96.71 19	99.96 5	99.86 1	99.80 26	99.89 9

thisisatest0530		96.01 229	95.36 248	97.97 194	98.38 210	95.52 228	98.88 133	94.19 500	94.04 279	97.64 204	98.31 254	83.82 386	99.46 203	95.29 255	97.70 253	98.93 243

UGNet		96.78 192	96.30 203	98.19 155	98.24 243	95.89 202	98.88 133	98.93 65	97.39 62	96.81 246	97.84 299	82.60 393	99.90 66	96.53 205	99.49 119	98.79 257
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
E5new		97.37 148	97.16 142	97.98 190	98.30 229	95.41 234	98.87 136	98.45 214	95.56 177	97.84 178	99.19 103	90.39 216	99.25 236	97.61 131	98.22 227	99.29 169

E6new		97.37 148	97.16 142	97.98 190	98.28 235	95.40 237	98.87 136	98.45 214	95.55 182	97.84 178	99.20 96	90.44 214	99.25 236	97.61 131	98.22 227	99.29 169

E6		97.37 148	97.16 142	97.98 190	98.28 235	95.40 237	98.87 136	98.45 214	95.55 182	97.84 178	99.20 96	90.44 214	99.25 236	97.61 131	98.22 227	99.29 169

E5		97.37 148	97.16 142	97.98 190	98.30 229	95.41 234	98.87 136	98.45 214	95.56 177	97.84 178	99.19 103	90.39 216	99.25 236	97.61 131	98.22 227	99.29 169

testing3-2		95.45 263	95.34 249	95.77 380	98.69 172	88.75 458	98.87 136	97.21 418	96.13 140	97.22 223	97.68 316	77.95 441	99.65 156	97.58 135	96.77 285	98.91 245

fmvsm_s_conf0.1_n		98.18 81	98.21 70	98.11 171	98.54 188	95.24 249	98.87 136	99.24 20	97.50 53	99.70 28	99.67 2	91.33 176	99.89 70	99.47 26	99.54 111	99.21 192

Anonymous20240529		95.10 289	94.22 314	97.75 215	99.01 135	94.26 304	98.87 136	98.83 99	85.79 479	96.64 254	98.97 157	78.73 430	99.85 86	96.27 213	94.89 327	99.12 210

thres100view900		95.38 269	94.70 284	97.41 245	98.98 141	94.92 270	98.87 136	96.90 444	95.38 196	96.61 257	96.88 395	84.29 371	99.56 176	88.11 443	96.29 304	97.76 323

fmvsm_s_conf0.5_n_10		98.66 26	98.54 32	99.02 70	99.36 70	97.21 117	98.86 144	99.23 27	98.90 6	99.83 13	99.59 14	91.57 164	99.94 15	99.79 10	99.74 59	99.89 9

reproduce-ours		98.93 12	98.78 15	99.38 25	99.49 53	98.38 43	98.86 144	98.83 99	98.06 26	99.29 55	99.58 17	96.40 31	99.94 15	98.68 47	99.81 17	99.81 26

our_new_method		98.93 12	98.78 15	99.38 25	99.49 53	98.38 43	98.86 144	98.83 99	98.06 26	99.29 55	99.58 17	96.40 31	99.94 15	98.68 47	99.81 17	99.81 26

fmvsm_s_conf0.5_n_a		98.38 64	98.42 42	98.27 141	99.09 127	95.41 234	98.86 144	99.37 9	97.69 41	99.78 18	99.61 6	92.38 130	99.91 58	99.58 24	99.43 128	99.49 114

XXY-MVS		95.20 283	94.45 301	97.46 240	96.75 390	96.56 152	98.86 144	98.65 159	93.30 334	93.27 383	98.27 260	84.85 359	98.87 325	94.82 269	91.26 389	96.96 350

fmvsm_s_conf0.5_n		98.42 61	98.51 33	98.13 166	99.30 85	95.25 248	98.85 149	99.39 7	97.94 30	99.74 22	99.62 5	92.59 125	99.91 58	99.65 19	99.52 114	99.25 186

VDDNet		95.36 272	94.53 293	97.86 203	98.10 270	95.13 256	98.85 149	97.75 361	90.46 426	98.36 134	99.39 51	73.27 478	99.64 159	97.98 97	96.58 291	98.81 255

thres600view7		95.49 259	94.77 279	97.67 225	98.98 141	95.02 261	98.85 149	96.90 444	95.38 196	96.63 255	96.90 394	84.29 371	99.59 169	88.65 439	96.33 300	98.40 299

114514_t		96.93 184	96.27 204	98.92 80	99.50 49	97.63 85	98.85 149	98.90 73	84.80 485	97.77 185	99.11 126	92.84 121	99.66 155	94.85 267	99.77 43	99.47 118

test_fmvsmconf0.1_n		98.58 37	98.44 41	98.99 72	97.73 315	97.15 121	98.84 153	98.97 57	98.75 12	99.43 43	99.54 21	93.29 116	99.93 35	99.64 21	99.79 36	99.89 9

LFMVS		95.86 240	94.98 271	98.47 124	98.87 153	96.32 166	98.84 153	96.02 470	93.40 329	98.62 115	99.20 96	74.99 468	99.63 162	97.72 118	97.20 269	99.46 123

alignmvs		97.56 122	97.07 152	99.01 71	98.66 176	98.37 50	98.83 155	98.06 335	96.74 107	98.00 162	97.65 318	90.80 201	99.48 198	98.37 73	96.56 292	99.19 197

DeepC-MVS	95.98 3	97.88 92	97.58 98	98.77 89	99.25 98	96.93 130	98.83 155	98.75 129	96.96 94	96.89 241	99.50 32	90.46 213	99.87 81	97.84 111	99.76 49	99.52 103
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_fmvsmconf_n		98.92 14	98.87 8	99.04 69	98.88 149	97.25 114	98.82 157	99.34 11	98.75 12	99.80 15	99.61 6	95.16 79	99.95 10	99.70 18	99.80 26	99.93 2

sd_testset		96.17 224	95.76 227	97.42 244	99.30 85	94.34 299	98.82 157	99.08 45	95.92 153	95.96 286	98.76 203	82.83 392	99.32 219	95.56 244	95.59 322	98.60 285

ACMMP_NAP		98.61 32	98.30 61	99.55 11	99.62 36	98.95 20	98.82 157	98.81 109	95.80 161	99.16 68	99.47 38	95.37 65	99.92 44	97.89 105	99.75 55	99.79 30

casdiffmvs		97.63 112	97.41 116	98.28 140	98.33 224	96.14 175	98.82 157	98.32 268	96.38 129	97.95 167	99.21 94	91.23 182	99.23 248	98.12 88	98.37 214	99.48 116
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GBi-Net		94.49 337	93.80 349	96.56 320	98.21 249	95.00 262	98.82 157	98.18 304	92.46 367	94.09 344	97.07 369	81.16 406	97.95 432	92.08 371	92.14 375	96.72 382

test1		94.49 337	93.80 349	96.56 320	98.21 249	95.00 262	98.82 157	98.18 304	92.46 367	94.09 344	97.07 369	81.16 406	97.95 432	92.08 371	92.14 375	96.72 382

FMVSNet1		93.19 390	92.07 399	96.56 320	97.54 332	95.00 262	98.82 157	98.18 304	90.38 429	92.27 419	97.07 369	73.68 477	97.95 432	89.36 429	91.30 387	96.72 382

API-MVS		97.41 143	97.25 130	97.91 197	98.70 169	96.80 136	98.82 157	98.69 144	94.53 257	98.11 144	98.28 257	94.50 96	99.57 173	94.12 304	99.49 119	97.37 339

ACMH	92.88 16	94.55 330	93.95 337	96.34 345	97.63 323	93.26 351	98.81 165	98.49 206	93.43 327	89.74 453	98.53 228	81.91 397	99.08 284	93.69 316	93.30 361	96.70 386
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.5_n_8		98.73 24	98.62 23	99.05 68	99.35 72	97.27 108	98.80 166	99.23 27	98.93 4	99.79 16	99.59 14	92.34 132	99.95 10	99.82 7	99.71 70	99.92 3

fmvsm_s_conf0.5_n_3		98.53 47	98.45 40	98.79 87	99.23 106	97.32 101	98.80 166	99.26 16	98.82 8	99.87 5	99.60 11	90.95 199	99.93 35	99.76 12	99.73 63	99.12 210

reproduce_monomvs		94.77 315	94.67 286	95.08 405	98.40 207	89.48 444	98.80 166	98.64 160	97.57 49	93.21 385	97.65 318	80.57 416	98.83 331	97.72 118	89.47 416	96.93 354

test_fmvs1		96.42 211	96.67 184	95.66 384	98.82 159	88.53 463	98.80 166	98.20 298	96.39 128	99.64 32	99.20 96	80.35 418	99.67 152	99.04 33	99.57 100	98.78 261

Effi-MVS+-dtu		96.29 219	96.56 189	95.51 389	97.89 303	90.22 428	98.80 166	98.10 323	96.57 118	96.45 268	96.66 408	90.81 200	98.91 318	95.72 236	97.99 238	97.40 336

HQP_MVS		96.14 226	95.90 222	96.85 288	97.42 344	94.60 288	98.80 166	98.56 184	97.28 70	95.34 295	98.28 257	87.09 314	99.03 295	96.07 218	94.27 330	96.92 355

plane_prior2							98.80 166		97.28 70

APD-MVS		98.35 69	98.00 84	99.42 23	99.51 47	98.72 27	98.80 166	98.82 103	94.52 259	99.23 60	99.25 87	95.54 59	99.80 111	96.52 206	99.77 43	99.74 51
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
fmvsm_s_conf0.5_n_9		98.63 30	98.66 22	98.54 111	99.40 68	95.83 207	98.79 174	99.17 37	98.94 3	99.92 1	99.61 6	92.49 126	99.93 35	99.86 1	99.76 49	99.86 14

fmvsm_s_conf0.5_n_6		98.65 27	98.55 30	98.95 79	98.50 190	97.30 104	98.79 174	99.16 39	98.14 24	99.86 9	99.41 49	93.71 111	99.91 58	99.71 16	99.64 87	99.65 85

UniMVSNet (Re)		95.78 245	95.19 259	97.58 234	96.99 373	97.47 94	98.79 174	99.18 36	95.60 173	93.92 352	97.04 377	91.68 159	98.48 361	95.80 233	87.66 438	96.79 374

FMVSNet2		94.47 340	93.61 362	97.04 271	98.21 249	96.43 158	98.79 174	98.27 283	92.46 367	93.50 374	97.09 366	81.16 406	98.00 429	91.09 396	91.93 378	96.70 386

tt0805		94.54 331	93.85 346	96.63 310	97.98 294	93.06 362	98.77 178	97.84 350	93.67 313	93.80 361	98.04 278	76.88 455	98.96 309	94.79 271	92.86 366	97.86 322

fmvsm_s_conf0.5_n_4		98.35 69	98.50 35	97.90 198	99.16 117	95.08 259	98.75 179	99.24 20	98.39 20	99.81 14	99.52 26	92.35 131	99.90 66	99.74 14	99.51 116	98.71 272

testgi		93.06 394	92.45 395	94.88 414	96.43 408	89.90 432	98.75 179	97.54 383	95.60 173	91.63 433	97.91 291	74.46 473	97.02 468	86.10 461	93.67 348	97.72 327

LCM-MVSNet-Re		95.22 281	95.32 253	94.91 411	98.18 259	87.85 474	98.75 179	95.66 477	95.11 217	88.96 461	96.85 398	90.26 223	97.65 452	95.65 241	98.44 200	99.22 190

SixPastTwentyTwo		93.34 384	92.86 383	94.75 421	95.67 441	89.41 447	98.75 179	96.67 458	93.89 291	90.15 450	98.25 263	80.87 412	98.27 398	90.90 403	90.64 396	96.57 409

Elysia		96.64 199	96.02 216	98.51 116	98.04 281	97.30 104	98.74 183	98.60 166	95.04 222	97.91 173	98.84 182	83.59 388	99.48 198	94.20 300	99.25 145	98.75 266

StellarMVS		96.64 199	96.02 216	98.51 116	98.04 281	97.30 104	98.74 183	98.60 166	95.04 222	97.91 173	98.84 182	83.59 388	99.48 198	94.20 300	99.25 145	98.75 266

UniMVSNet_ETH3D		94.24 355	93.33 373	96.97 278	97.19 362	93.38 342	98.74 183	98.57 180	91.21 415	93.81 360	98.58 223	72.85 480	98.77 338	95.05 263	93.93 344	98.77 264

MVS_Test		97.28 159	97.00 157	98.13 166	98.33 224	95.97 188	98.74 183	98.07 330	94.27 272	98.44 129	98.07 275	92.48 127	99.26 232	96.43 209	98.19 231	99.16 203

UniMVSNet_NR-MVSNet		95.71 248	95.15 260	97.40 247	96.84 383	96.97 128	98.74 183	99.24 20	95.16 210	93.88 354	97.72 310	91.68 159	98.31 391	95.81 231	87.25 444	96.92 355

NR-MVSNet		94.98 299	94.16 319	97.44 242	96.53 400	97.22 116	98.74 183	98.95 61	94.96 231	89.25 459	97.69 313	89.32 250	98.18 403	94.59 286	87.40 441	96.92 355

ETV-MVS		97.96 88	97.81 89	98.40 134	98.42 203	97.27 108	98.73 189	98.55 186	96.84 100	98.38 132	97.44 337	95.39 63	99.35 214	97.62 128	98.89 164	98.58 290

baseline1		95.84 241	95.12 263	98.01 186	98.49 194	95.98 183	98.73 189	97.03 433	95.37 198	96.22 275	98.19 267	89.96 229	99.16 262	94.60 284	87.48 439	98.90 246

MVSTER		96.06 228	95.72 229	97.08 268	98.23 246	95.93 194	98.73 189	98.27 283	94.86 237	95.07 301	98.09 274	88.21 287	98.54 357	96.59 201	93.46 353	96.79 374

ACMP	93.49 10	95.34 274	94.98 271	96.43 337	97.67 319	93.48 335	98.73 189	98.44 218	94.94 235	92.53 408	98.53 228	84.50 370	99.14 269	95.48 248	94.00 341	96.66 392
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HPM-MVS++		98.58 37	98.25 64	99.55 11	99.50 49	99.08 13	98.72 193	98.66 155	97.51 52	98.15 141	98.83 186	95.70 54	99.92 44	97.53 143	99.67 76	99.66 84

9.14			98.06 79		99.47 57		98.71 194	98.82 103	94.36 269	99.16 68	99.29 76	96.05 42	99.81 104	97.00 175	99.71 70

VPNet		94.99 297	94.19 316	97.40 247	97.16 364	96.57 151	98.71 194	98.97 57	95.67 170	94.84 306	98.24 264	80.36 417	98.67 346	96.46 207	87.32 443	96.96 350

MSLP-MVS++		98.56 44	98.57 27	98.55 109	99.26 97	96.80 136	98.71 194	99.05 49	97.28 70	98.84 90	99.28 77	96.47 29	99.40 209	98.52 63	99.70 72	99.47 118

ACMH+	92.99 14	94.30 349	93.77 352	95.88 372	97.81 307	92.04 389	98.71 194	98.37 253	93.99 286	90.60 444	98.47 235	80.86 413	99.05 289	92.75 350	92.40 372	96.55 413

fmvsm_l_conf0.5_n_9		98.90 16	98.79 14	99.24 47	99.34 73	97.83 81	98.70 198	99.26 16	98.85 7	99.92 1	99.51 29	93.91 108	99.95 10	99.86 1	99.79 36	99.92 3

Anonymous202405211		95.28 278	94.49 295	97.67 225	99.00 137	93.75 323	98.70 198	97.04 432	90.66 422	96.49 265	98.80 189	78.13 437	99.83 92	96.21 217	95.36 326	99.44 128

DP-MVS		96.59 203	95.93 221	98.57 106	99.34 73	96.19 173	98.70 198	98.39 244	89.45 445	94.52 317	99.35 63	91.85 153	99.85 86	92.89 345	98.88 165	99.68 77

aaEdge-Enhanced		98.83 20	98.60 25	99.52 15	99.58 38	98.86 24	98.69 201	98.93 65	97.00 92	99.17 64	99.35 63	96.62 24	99.90 66	98.30 77	99.80 26	99.79 30

fmvsm_s_conf0.1_n_2		98.14 82	98.02 82	98.53 114	98.88 149	97.07 125	98.69 201	98.82 103	98.78 10	99.77 19	99.61 6	88.83 270	99.91 58	99.71 16	99.07 152	98.61 284

Fast-Effi-MVS+-dtu		95.87 239	95.85 223	95.91 369	97.74 314	91.74 394	98.69 201	98.15 313	95.56 177	94.92 304	97.68 316	88.98 264	98.79 336	93.19 332	97.78 247	97.20 343

VortexMVS		95.95 232	95.79 225	96.42 338	98.29 233	93.96 315	98.68 204	98.31 273	96.02 147	94.29 333	97.57 327	89.47 242	98.37 384	97.51 148	91.93 378	96.94 353

fmvsm_s_conf0.5_n_5		98.53 47	98.35 49	99.08 65	99.07 129	97.46 96	98.68 204	99.20 33	97.50 53	99.87 5	99.50 32	91.96 152	99.96 5	99.76 12	99.65 82	99.82 24

tfpn200view9		95.32 276	94.62 288	97.43 243	98.94 145	94.98 266	98.68 204	96.93 442	95.33 200	96.55 261	96.53 414	84.23 375	99.56 176	88.11 443	96.29 304	97.76 323

VDD-MVS		95.82 243	95.23 257	97.61 233	98.84 158	93.98 314	98.68 204	97.40 399	95.02 226	97.95 167	99.34 69	74.37 474	99.78 126	98.64 50	96.80 282	99.08 223

thres400		95.38 269	94.62 288	97.65 229	98.94 145	94.98 266	98.68 204	96.93 442	95.33 200	96.55 261	96.53 414	84.23 375	99.56 176	88.11 443	96.29 304	98.40 299

pmmvs6		91.77 407	90.63 413	95.17 401	94.69 466	91.24 403	98.67 209	97.92 345	86.14 475	89.62 455	97.56 330	75.79 462	98.34 386	90.75 405	84.56 462	95.94 449

v2v482		94.69 317	94.03 329	96.65 305	96.17 418	94.79 278	98.67 209	98.08 328	92.72 358	94.00 349	97.16 359	87.69 305	98.45 366	92.91 342	88.87 426	96.72 382

fmvsm_s_conf0.5_n_2		98.30 76	98.21 70	98.57 106	99.25 98	97.11 123	98.66 211	99.20 33	98.82 8	99.79 16	99.60 11	89.38 248	99.92 44	99.80 9	99.38 135	98.69 274

DU-MVS		95.42 266	94.76 280	97.40 247	96.53 400	96.97 128	98.66 211	98.99 56	95.43 191	93.88 354	97.69 313	88.57 276	98.31 391	95.81 231	87.25 444	96.92 355

MAR-MVS		96.91 185	96.40 198	98.45 126	98.69 172	96.90 132	98.66 211	98.68 147	92.40 373	97.07 231	97.96 286	91.54 168	99.75 134	93.68 317	98.92 162	98.69 274
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
testing3		93.19 390	92.48 394	95.30 398	98.07 273	92.27 377	98.64 214	97.17 423	93.94 290	93.98 350	97.04 377	67.97 488	96.01 489	88.40 441	97.14 271	97.63 330

patch_mono-2		98.36 67	98.87 8	96.82 290	99.53 43	90.68 415	98.64 214	99.29 15	97.88 31	99.19 63	99.52 26	96.80 17	99.97 1	99.11 31	99.86 2	99.82 24

h-mvs33		96.17 224	95.62 238	97.81 208	99.03 132	94.45 292	98.64 214	98.75 129	97.48 55	98.67 108	98.72 208	89.76 233	99.86 85	97.95 98	81.59 476	99.11 213

VNet		97.79 99	97.40 117	98.96 77	98.88 149	97.55 88	98.63 217	98.93 65	96.74 107	99.02 73	98.84 182	90.33 220	99.83 92	98.53 57	96.66 288	99.50 109

PVSNet_Blended_VisFu		97.70 105	97.46 110	98.44 128	99.27 95	95.91 196	98.63 217	99.16 39	94.48 264	97.67 197	98.88 177	92.80 122	99.91 58	97.11 171	99.12 151	99.50 109

PAPM_NR		97.46 136	97.11 149	98.50 119	99.50 49	96.41 161	98.63 217	98.60 166	95.18 209	97.06 232	98.06 276	94.26 102	99.57 173	93.80 315	98.87 167	99.52 103

viewmacassd2359aftdt		97.32 156	97.07 152	98.08 174	98.30 229	95.69 218	98.62 220	98.44 218	95.56 177	97.86 177	99.22 91	89.91 230	99.14 269	97.29 166	98.43 203	99.42 135

SSM_0404		97.26 161	97.00 157	98.03 182	98.46 197	95.99 182	98.62 220	98.44 218	94.77 243	97.24 221	98.93 167	91.22 183	99.28 229	96.54 203	98.74 175	98.84 252

Baseline_NR-MVSNet		94.35 346	93.81 348	95.96 367	96.20 415	94.05 313	98.61 222	96.67 458	91.44 402	93.85 358	97.60 324	88.57 276	98.14 407	94.39 291	86.93 447	95.68 456

E4		97.37 148	97.13 147	98.12 169	98.27 237	95.70 217	98.59 223	98.44 218	95.56 177	97.80 183	99.18 106	90.57 210	99.26 232	97.45 155	98.28 225	99.40 139

viewdifsd2359ckpt13		97.24 163	96.97 162	98.06 178	98.43 201	95.77 214	98.59 223	98.34 262	94.81 240	97.60 209	98.94 165	90.78 205	99.09 281	96.93 180	98.33 219	99.32 160

v1144		94.59 327	93.92 338	96.60 315	96.21 414	94.78 279	98.59 223	98.14 315	91.86 391	94.21 339	97.02 380	87.97 295	98.41 377	91.72 384	89.57 411	96.61 398

AllTest		95.24 280	94.65 287	96.99 273	99.25 98	93.21 355	98.59 223	98.18 304	91.36 404	93.52 371	98.77 198	84.67 365	99.72 139	89.70 422	97.87 243	98.02 317

E2		97.48 132	97.25 130	98.16 157	98.40 207	95.79 212	98.58 227	98.44 218	95.58 175	98.00 162	99.14 116	91.21 187	99.24 244	97.50 149	98.43 203	99.45 125

E3		97.48 132	97.25 130	98.16 157	98.38 210	95.79 212	98.58 227	98.44 218	95.58 175	98.00 162	99.14 116	91.25 181	99.24 244	97.50 149	98.44 200	99.45 125

fmvsm_s_conf0.5_n_7		98.23 77	98.35 49	97.89 200	98.86 154	94.99 265	98.58 227	99.00 53	98.29 21	99.73 24	99.60 11	91.70 158	99.92 44	99.63 22	99.73 63	98.76 265

MGCNet		98.23 77	97.91 87	99.21 51	98.06 277	97.96 75	98.58 227	95.51 479	98.58 15	98.87 88	99.26 81	92.99 120	99.95 10	99.62 23	99.67 76	99.73 56

Fast-Effi-MVS+		96.28 221	95.70 234	98.03 182	98.29 233	95.97 188	98.58 227	98.25 292	91.74 392	95.29 299	97.23 355	91.03 194	99.15 266	92.90 343	97.96 240	98.97 237

Anonymous20231206		91.66 408	91.10 409	93.33 451	94.02 476	87.35 476	98.58 227	97.26 413	90.48 425	90.16 449	96.31 423	83.83 385	96.53 481	79.36 495	89.90 407	96.12 444

v144192		94.39 345	93.70 358	96.48 331	96.06 424	94.35 298	98.58 227	98.16 312	91.45 401	94.33 330	97.02 380	87.50 308	98.45 366	91.08 398	89.11 421	96.63 394

v148		94.29 351	93.76 354	95.91 369	96.10 422	92.93 365	98.58 227	97.97 340	92.59 365	93.47 376	96.95 389	88.53 280	98.32 389	92.56 361	87.06 446	96.49 426

COLMAP_ROB	93.27 12	95.33 275	94.87 277	96.71 299	99.29 90	93.24 354	98.58 227	98.11 320	89.92 436	93.57 369	99.10 128	86.37 329	99.79 123	90.78 404	98.10 234	97.09 344
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
viewcassd2359sk11		97.53 129	97.32 125	98.16 157	98.45 199	95.83 207	98.57 236	98.42 233	95.52 186	98.07 149	99.12 123	91.81 156	99.25 236	97.46 154	98.48 196	99.41 138

viewmanbaseed2359cas		97.47 135	97.25 130	98.14 161	98.41 205	95.84 206	98.57 236	98.43 229	95.55 182	97.97 165	99.12 123	91.26 180	99.15 266	97.42 158	98.53 190	99.43 132

test_vis1_rt		91.29 413	90.65 412	93.19 455	97.45 342	86.25 483	98.57 236	90.90 518	93.30 334	86.94 477	93.59 480	62.07 501	99.11 276	97.48 152	95.58 324	94.22 484

FMVSNet3		94.97 301	94.26 312	97.11 266	98.18 259	96.62 143	98.56 239	98.26 291	93.67 313	94.09 344	97.10 362	84.25 373	98.01 427	92.08 371	92.14 375	96.70 386

E3new		97.55 123	97.35 123	98.16 157	98.48 195	95.85 205	98.55 240	98.41 235	95.42 193	98.06 151	99.12 123	92.23 139	99.24 244	97.43 156	98.45 199	99.39 140

F-COLMAP		97.09 176	96.80 172	97.97 194	99.45 62	94.95 269	98.55 240	98.62 165	93.02 347	96.17 279	98.58 223	94.01 106	99.81 104	93.95 309	98.90 163	99.14 207

dmvs_re		94.48 339	94.18 318	95.37 395	97.68 318	90.11 430	98.54 242	97.08 427	94.56 255	94.42 325	97.24 354	84.25 373	97.76 448	91.02 402	92.83 367	98.24 306

viewdifsd2359ckpt09		97.13 173	96.79 174	98.14 161	98.43 201	95.90 197	98.52 243	98.37 253	94.32 270	97.33 216	98.86 180	90.23 224	99.16 262	96.81 194	98.25 226	99.36 149

SSM_0407		97.17 170	96.87 167	98.08 174	98.19 253	95.90 197	98.52 243	98.44 218	94.77 243	96.75 249	98.93 167	91.22 183	99.22 252	96.54 203	98.43 203	99.10 215

ttmdpeth		92.61 400	91.96 403	94.55 428	94.10 472	90.60 420	98.52 243	97.29 409	92.67 360	90.18 448	97.92 290	79.75 422	97.79 444	91.09 396	86.15 455	95.26 463

v1921920		94.20 357	93.47 369	96.40 341	95.98 428	94.08 312	98.52 243	98.15 313	91.33 407	94.25 336	97.20 358	86.41 328	98.42 370	90.04 416	89.39 418	96.69 391

EU-MVSNet		93.66 376	94.14 321	92.25 467	95.96 430	83.38 494	98.52 243	98.12 317	94.69 248	92.61 404	98.13 272	87.36 312	96.39 485	91.82 381	90.00 406	96.98 349

TAMVS		97.02 178	96.79 174	97.70 220	98.06 277	95.31 246	98.52 243	98.31 273	93.95 288	97.05 233	98.61 217	93.49 113	98.52 359	95.33 251	97.81 245	99.29 169

LTVRE_ROB	92.95 15	94.60 325	93.90 341	96.68 303	97.41 347	94.42 294	98.52 243	98.59 173	91.69 395	91.21 436	98.35 247	84.87 358	99.04 292	91.06 399	93.44 356	96.60 400
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
TDRefinement		91.06 421	89.68 426	95.21 399	85.35 529	91.49 399	98.51 250	97.07 429	91.47 400	88.83 465	97.84 299	77.31 447	99.09 281	92.79 349	77.98 492	95.04 471

v1192		94.32 348	93.58 363	96.53 325	96.10 422	94.45 292	98.50 251	98.17 310	91.54 399	94.19 340	97.06 373	86.95 318	98.43 369	90.14 411	89.57 411	96.70 386

test_0402		91.32 412	90.27 417	94.48 432	96.60 397	91.12 404	98.50 251	97.22 416	86.10 476	88.30 470	96.98 384	77.65 445	97.99 430	78.13 500	92.94 365	94.34 480

DeepC-MVS_fast	96.70 1	98.55 45	98.34 55	99.18 54	99.25 98	98.04 71	98.50 251	98.78 123	97.72 37	98.92 86	99.28 77	95.27 72	99.82 99	97.55 140	99.77 43	99.69 72
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
viewdifsd2359ckpt11		96.30 217	96.13 209	96.81 291	98.10 270	92.10 384	98.49 254	98.40 238	96.02 147	97.61 206	99.31 72	86.37 329	99.29 227	97.52 144	93.36 359	99.04 229

viewmsd2359difaftdt		96.30 217	96.13 209	96.81 291	98.10 270	92.10 384	98.49 254	98.40 238	96.02 147	97.61 206	99.31 72	86.37 329	99.30 224	97.52 144	93.37 358	99.04 229

FBQ-MVS		94.89 309	94.10 324	97.26 252	98.07 273	93.75 323	98.48 256	97.26 413	94.51 260	96.28 273	95.64 454	76.88 455	99.07 285	93.29 329	96.47 297	98.96 240

IMVS_0403		96.74 193	96.61 187	97.12 264	97.99 288	92.82 367	98.47 257	98.27 283	95.16 210	97.13 226	98.79 191	91.44 172	99.26 232	94.74 272	97.54 260	99.27 177

CNVR-MVS		98.78 21	98.56 29	99.45 20	99.32 79	98.87 22	98.47 257	98.81 109	97.72 37	98.76 98	99.16 111	97.05 15	99.78 126	98.06 92	99.66 79	99.69 72

FE-MVSNET2		90.29 436	88.94 441	94.36 437	90.48 512	92.27 377	98.45 259	97.82 354	91.59 398	84.90 490	93.10 487	73.92 475	96.42 484	87.92 450	82.26 471	94.39 479

IMVS_0407		96.74 193	96.64 186	97.05 270	97.99 288	92.82 367	98.45 259	98.27 283	95.16 210	97.30 217	98.79 191	91.53 169	99.06 288	94.74 272	97.54 260	99.27 177

LuminaMVS		97.49 131	97.18 140	98.42 132	97.50 336	97.15 121	98.45 259	97.68 363	96.56 120	98.68 107	98.78 195	89.84 232	99.32 219	98.60 52	98.57 186	98.79 257

test_yl		97.22 164	96.78 176	98.54 111	98.73 164	96.60 146	98.45 259	98.31 273	94.70 246	98.02 158	98.42 239	90.80 201	99.70 145	96.81 194	96.79 283	99.34 152

DCV-MVSNet		97.22 164	96.78 176	98.54 111	98.73 164	96.60 146	98.45 259	98.31 273	94.70 246	98.02 158	98.42 239	90.80 201	99.70 145	96.81 194	96.79 283	99.34 152

NCCC		98.61 32	98.35 49	99.38 25	99.28 94	98.61 34	98.45 259	98.76 127	97.82 36	98.45 126	98.93 167	96.65 22	99.83 92	97.38 163	99.41 130	99.71 64

v1240		94.06 371	93.29 375	96.34 345	96.03 426	93.90 317	98.44 265	98.17 310	91.18 416	94.13 343	97.01 382	86.05 336	98.42 370	89.13 433	89.50 415	96.70 386

plane_prior						94.60 288	98.44 265		96.74 107						94.22 332

sc_t1		91.01 423	89.39 430	95.85 375	95.99 427	90.39 425	98.43 267	97.64 369	78.79 501	92.20 422	97.94 288	66.00 494	98.60 353	91.59 388	85.94 457	98.57 291

MP-MVS-pluss		98.31 74	97.92 86	99.49 17	99.72 17	98.88 21	98.43 267	98.78 123	94.10 277	97.69 195	99.42 47	95.25 74	99.92 44	98.09 90	99.80 26	99.67 81
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
OPM-MVS		95.69 251	95.33 252	96.76 295	96.16 420	94.63 283	98.43 267	98.39 244	96.64 114	95.02 303	98.78 195	85.15 354	99.05 289	95.21 260	94.20 333	96.60 400
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DPE-MVS		98.92 14	98.67 21	99.65 2	99.58 38	99.20 9	98.42 270	98.91 72	97.58 48	99.54 38	99.46 43	97.10 14	99.94 15	97.64 127	99.84 12	99.83 20
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_l_mol_unc0.5_1		99.24 1	99.14 1	99.53 14	99.37 69	98.68 30	98.41 271	98.86 91	99.00 1	99.90 3	99.79 1	97.24 13	99.97 1	99.85 5	99.86 2	99.94 1

MCST-MVS		98.65 27	98.37 46	99.48 18	99.60 37	98.87 22	98.41 271	98.68 147	97.04 89	98.52 121	98.80 189	96.78 18	99.83 92	97.93 100	99.61 92	99.74 51

viewdifsd2359ckpt07		97.20 167	97.05 154	97.65 229	98.40 207	94.33 301	98.39 273	98.43 229	95.67 170	97.66 201	99.08 139	90.04 227	99.32 219	97.47 153	98.29 223	99.31 161

hse-mvs2		95.71 248	95.30 255	96.93 281	98.50 190	93.53 333	98.36 274	98.10 323	97.48 55	98.67 108	97.99 283	89.76 233	99.02 300	97.95 98	80.91 482	98.22 308

viewmamba		97.55 123	97.45 112	97.87 202	98.22 247	95.13 256	98.35 275	98.35 258	96.57 118	98.45 126	99.15 115	91.60 162	99.18 257	97.99 96	98.36 216	99.29 169

CANet		98.05 86	97.76 91	98.90 83	98.73 164	97.27 108	98.35 275	98.78 123	97.37 65	97.72 192	98.96 162	91.53 169	99.92 44	98.79 43	99.65 82	99.51 106

AUN-MVS		94.53 333	93.73 356	96.92 284	98.50 190	93.52 334	98.34 277	98.10 323	93.83 297	95.94 288	97.98 285	85.59 345	99.03 295	94.35 293	80.94 481	98.22 308

test20.03		90.89 426	90.38 416	92.43 462	93.48 480	88.14 470	98.33 278	97.56 377	93.40 329	87.96 471	96.71 406	80.69 415	94.13 505	79.15 496	86.17 453	95.01 473

DP-MVS Recon		97.86 93	97.46 110	99.06 67	99.53 43	98.35 52	98.33 278	98.89 75	92.62 363	98.05 153	98.94 165	95.34 68	99.65 156	96.04 222	99.42 129	99.19 197

RPSCF		94.87 310	95.40 243	93.26 453	98.89 148	82.06 499	98.33 278	98.06 335	90.30 431	96.56 259	99.26 81	87.09 314	99.49 193	93.82 314	96.32 301	98.24 306

TAPA-MVS	93.98 7	95.35 273	94.56 292	97.74 216	99.13 121	94.83 275	98.33 278	98.64 160	86.62 471	96.29 272	98.61 217	94.00 107	99.29 227	80.00 492	99.41 130	99.09 219
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
IterMVS-LS		95.46 261	95.21 258	96.22 351	98.12 268	93.72 327	98.32 282	98.13 316	93.71 306	94.26 335	97.31 349	92.24 138	98.10 411	94.63 280	90.12 404	96.84 370
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SD_0403		94.28 353	94.46 298	93.73 444	98.02 284	85.32 487	98.31 283	98.40 238	94.75 245	93.59 366	98.16 269	89.01 260	96.54 480	82.32 483	97.58 258	99.34 152

mvs_anonymous		96.70 198	96.53 193	97.18 258	98.19 253	93.78 320	98.31 283	98.19 301	94.01 284	94.47 319	98.27 260	92.08 147	98.46 365	97.39 162	97.91 241	99.31 161

WTY-MVS		97.37 148	96.92 164	98.72 93	98.86 154	96.89 134	98.31 283	98.71 139	95.26 205	97.67 197	98.56 227	92.21 141	99.78 126	95.89 226	96.85 281	99.48 116

D2MVS		95.18 284	95.08 266	95.48 390	97.10 368	92.07 387	98.30 286	99.13 43	94.02 281	92.90 395	96.73 404	89.48 241	98.73 340	94.48 289	93.60 352	95.65 457

EI-MVSNet-Vis-set		98.47 55	98.39 44	98.69 95	99.46 59	96.49 155	98.30 286	98.69 144	97.21 77	98.84 90	99.36 61	95.41 62	99.78 126	98.62 51	99.65 82	99.80 29

DSMNet-mixed		92.52 403	92.58 391	92.33 464	94.15 470	82.65 497	98.30 286	94.26 498	89.08 451	92.65 403	95.73 447	85.01 356	95.76 491	86.24 460	97.76 249	98.59 288

EI-MVSNet-UG-set		98.41 62	98.34 55	98.61 103	99.45 62	96.32 166	98.28 289	98.68 147	97.17 81	98.74 99	99.37 57	95.25 74	99.79 123	98.57 54	99.54 111	99.73 56

OMC-MVS		97.55 123	97.34 124	98.20 151	99.33 76	95.92 195	98.28 289	98.59 173	95.52 186	97.97 165	99.10 128	93.28 117	99.49 193	95.09 261	98.88 165	99.19 197

baseline2		95.11 288	94.52 294	96.87 286	96.65 396	93.56 330	98.27 291	94.10 502	93.45 326	92.02 428	97.43 338	87.45 311	99.19 255	93.88 312	97.41 267	97.87 321

onestephybrid01		97.54 127	97.36 121	98.06 178	98.25 240	95.63 220	98.26 292	98.33 264	96.13 140	98.65 113	99.13 119	91.02 195	99.25 236	98.07 91	98.42 209	99.31 161

PVSNet_BlendedMVS		96.73 195	96.60 188	97.12 264	99.25 98	95.35 243	98.26 292	99.26 16	94.28 271	97.94 169	97.46 334	92.74 123	99.81 104	96.88 187	93.32 360	96.20 441

MVStest1		89.53 447	87.99 452	94.14 442	94.39 467	90.42 423	98.25 294	96.84 451	82.81 489	81.18 499	97.33 347	77.09 452	96.94 470	85.27 469	78.79 487	95.06 470

BH-untuned		95.95 232	95.72 229	96.65 305	98.55 187	92.26 379	98.23 295	97.79 359	93.73 303	94.62 314	98.01 281	88.97 265	99.00 303	93.04 338	98.51 192	98.68 276

sss		97.39 145	96.98 161	98.61 103	98.60 184	96.61 145	98.22 296	98.93 65	93.97 287	98.01 161	98.48 234	91.98 149	99.85 86	96.45 208	98.15 232	99.39 140

hybridnocas07		97.41 143	97.21 138	97.99 188	98.24 243	95.42 233	98.21 297	98.32 268	95.97 151	98.38 132	98.93 167	90.48 212	99.21 253	97.92 102	98.46 198	99.34 152

dtuplus		97.00 180	96.83 171	97.51 238	98.18 259	94.21 307	98.21 297	98.20 298	94.42 268	97.66 201	99.22 91	90.18 225	99.17 260	97.01 174	98.36 216	99.13 209

save fliter					99.46 59	98.38 43	98.21 297	98.71 139	97.95 29

WR-MVS		95.15 285	94.46 298	97.22 254	96.67 395	96.45 156	98.21 297	98.81 109	94.15 275	93.16 387	97.69 313	87.51 306	98.30 393	95.29 255	88.62 428	96.90 362

pmmvs5		93.65 378	92.97 382	95.68 382	95.49 449	92.37 376	98.20 301	97.28 411	89.66 441	92.58 405	97.26 351	82.14 396	98.09 415	93.18 333	90.95 394	96.58 407

thres200		95.25 279	94.57 291	97.28 251	98.81 160	94.92 270	98.20 301	97.11 425	95.24 208	96.54 263	96.22 429	84.58 368	99.53 185	87.93 449	96.50 295	97.39 337

CDS-MVSNet		96.99 181	96.69 182	97.90 198	98.05 279	95.98 183	98.20 301	98.33 264	93.67 313	96.95 235	98.49 233	93.54 112	98.42 370	95.24 258	97.74 251	99.31 161
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
nomal-1		94.97 301	94.34 307	96.86 287	97.79 308	92.62 373	98.19 304	96.71 456	93.89 291	94.74 313	96.05 435	79.44 425	99.09 281	95.58 243	96.68 287	98.86 249

ETVMVS		94.50 336	93.44 370	97.68 223	98.18 259	95.35 243	98.19 304	97.11 425	93.73 303	96.40 269	95.39 457	74.53 471	98.84 328	91.10 395	96.31 302	98.84 252

WB-MVS		84.86 462	85.33 463	83.46 494	89.48 518	69.56 521	98.19 304	96.42 466	89.55 443	81.79 496	94.67 466	84.80 360	90.12 518	52.44 527	80.64 483	90.69 510

1314		96.25 223	95.73 228	97.79 209	97.13 366	95.55 226	98.19 304	98.59 173	93.47 325	92.03 427	97.82 303	91.33 176	99.49 193	94.62 282	98.44 200	98.32 305

MVS		94.67 322	93.54 366	98.08 174	96.88 381	96.56 152	98.19 304	98.50 201	78.05 504	92.69 402	98.02 279	91.07 193	99.63 162	90.09 412	98.36 216	98.04 316

BH-RMVSNet		95.92 237	95.32 253	97.69 221	98.32 227	94.64 282	98.19 304	97.45 395	94.56 255	96.03 282	98.61 217	85.02 355	99.12 274	90.68 406	99.06 153	99.30 166

hybrid		97.34 154	97.16 142	97.88 201	98.25 240	95.18 252	98.18 310	98.33 264	95.36 199	98.35 136	99.06 144	90.61 208	99.18 257	97.88 107	98.40 212	99.27 177

1112_ss		96.63 201	96.00 218	98.50 119	98.56 185	96.37 163	98.18 310	98.10 323	92.92 351	94.84 306	98.43 237	92.14 143	99.58 172	94.35 293	96.51 294	99.56 102

tt0320		90.26 438	88.73 443	94.86 415	96.12 421	90.62 418	98.17 312	97.63 370	77.46 505	89.68 454	96.04 437	69.19 485	97.79 444	88.98 434	85.29 460	96.16 443

viewmambaseed2359dif		97.01 179	96.84 169	97.51 238	98.19 253	94.21 307	98.16 313	98.23 294	93.61 319	97.78 184	99.13 119	90.79 204	99.18 257	97.24 167	98.40 212	99.15 204

tt0320-xc		89.79 442	88.11 449	94.84 418	96.19 416	90.61 419	98.16 313	97.22 416	77.35 506	88.75 467	96.70 407	65.94 495	97.63 454	89.31 430	83.39 467	96.28 438

EPNet_dtu		95.21 282	94.95 273	95.99 362	96.17 418	90.45 422	98.16 313	97.27 412	96.77 104	93.14 390	98.33 252	90.34 219	98.42 370	85.57 465	98.81 173	99.09 219
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FE-MVSNET		88.56 451	87.09 458	92.99 459	89.93 516	89.99 431	98.15 316	95.59 478	88.42 458	84.87 491	92.90 489	74.82 469	94.99 500	77.88 501	81.21 478	93.99 490

HY-MVS	93.96 8	96.82 190	96.23 207	98.57 106	98.46 197	97.00 127	98.14 317	98.21 296	93.95 288	96.72 252	97.99 283	91.58 163	99.76 132	94.51 288	96.54 293	98.95 241

PLC	95.07 4	97.20 167	96.78 176	98.44 128	99.29 90	96.31 168	98.14 317	98.76 127	92.41 372	96.39 270	98.31 254	94.92 88	99.78 126	94.06 307	98.77 174	99.23 188
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EG-PatchMatch MVS		91.13 420	90.12 420	94.17 441	94.73 465	89.00 453	98.13 319	97.81 358	89.22 449	85.32 488	96.46 417	67.71 489	98.42 370	87.89 451	93.82 346	95.08 469

usedtu_blend_shiyan5		90.87 428	89.15 435	96.01 359	91.33 501	93.35 345	98.12 320	97.36 403	81.93 495	92.36 415	91.75 502	81.83 398	98.09 415	92.88 346	74.82 505	96.59 403

diffmvs_AUTHOR		97.59 118	97.44 113	98.01 186	98.26 238	95.47 230	98.12 320	98.36 257	96.38 129	98.84 90	99.10 128	91.13 188	99.26 232	98.24 85	98.56 187	99.30 166

EI-MVSNet		95.96 231	95.83 224	96.36 343	97.93 299	93.70 328	98.12 320	98.27 283	93.70 308	95.07 301	99.02 149	92.23 139	98.54 357	94.68 277	93.46 353	96.84 370

CVMVSNet		95.43 265	96.04 214	93.57 447	97.93 299	83.62 492	98.12 320	98.59 173	95.68 169	96.56 259	99.02 149	87.51 306	97.51 460	93.56 323	97.44 265	99.60 94

TSAR-MVS + GP.		98.38 64	98.24 66	98.81 86	99.22 108	97.25 114	98.11 324	98.29 282	97.19 79	98.99 78	99.02 149	96.22 35	99.67 152	98.52 63	98.56 187	99.51 106

XVG-ACMP-BASELINE		94.54 331	94.14 321	95.75 381	96.55 399	91.65 396	98.11 324	98.44 218	94.96 231	94.22 338	97.90 292	79.18 428	99.11 276	94.05 308	93.85 345	96.48 428

testing99		94.83 311	94.08 325	97.07 269	97.94 297	93.13 357	98.10 326	97.17 423	94.86 237	95.34 295	96.00 441	76.31 458	99.40 209	95.08 262	95.90 318	98.68 276

testing11		95.00 295	94.28 309	97.16 260	97.96 296	93.36 344	98.09 327	97.06 431	94.94 235	95.33 298	96.15 431	76.89 454	99.40 209	95.77 235	96.30 303	98.72 269

SSC-MVS		84.27 465	84.71 466	82.96 499	89.19 520	68.83 522	98.08 328	96.30 468	89.04 452	81.37 498	94.47 467	84.60 367	89.89 519	49.80 530	79.52 485	90.15 511

CNLPA		97.45 139	97.03 156	98.73 92	99.05 130	97.44 97	98.07 329	98.53 190	95.32 202	96.80 247	98.53 228	93.32 115	99.72 139	94.31 296	99.31 143	99.02 232

diffmvs		97.58 119	97.40 117	98.13 166	98.32 227	95.81 211	98.06 330	98.37 253	96.20 137	98.74 99	98.89 176	91.31 178	99.25 236	98.16 87	98.52 191	99.34 152
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CHOSEN 1792x2688		97.12 174	96.80 172	98.08 174	99.30 85	94.56 290	98.05 331	99.71 1	93.57 321	97.09 228	98.91 173	88.17 288	99.89 70	96.87 190	99.56 108	99.81 26

HQP-NCC					97.20 359		98.05 331		96.43 123	94.45 320

ACMP_Plane					97.20 359		98.05 331		96.43 123	94.45 320

HQP-MVS		95.72 247	95.40 243	96.69 302	97.20 359	94.25 305	98.05 331	98.46 209	96.43 123	94.45 320	97.73 308	86.75 320	98.96 309	95.30 253	94.18 334	96.86 369

myMVS_eth3d28		95.12 287	94.62 288	96.64 309	98.17 263	92.17 380	98.02 335	97.32 405	95.41 194	96.22 275	96.05 435	78.01 439	99.13 271	95.22 259	97.16 270	98.60 285

MIMVSNet1		89.67 444	88.28 447	93.82 443	92.81 488	91.08 405	98.01 336	97.45 395	87.95 460	87.90 472	95.87 443	67.63 490	94.56 503	78.73 499	88.18 432	95.83 453

AdaColmap		97.15 172	96.70 181	98.48 122	99.16 117	96.69 142	98.01 336	98.89 75	94.44 266	96.83 243	98.68 211	90.69 207	99.76 132	94.36 292	99.29 144	98.98 236

testing91		94.98 299	94.25 313	97.20 255	97.94 297	93.41 338	98.00 338	97.58 374	94.99 227	95.45 294	96.04 437	77.20 449	99.42 207	94.97 265	96.02 317	98.78 261

FMVSNet5		91.81 406	90.92 410	94.49 431	97.21 358	92.09 386	98.00 338	97.55 382	89.31 448	90.86 441	95.61 455	74.48 472	95.32 495	85.57 465	89.70 409	96.07 446

CANet_DTU		96.96 183	96.55 190	98.21 149	98.17 263	96.07 179	97.98 340	98.21 296	97.24 75	97.13 226	98.93 167	86.88 319	99.91 58	95.00 264	99.37 137	98.66 280

MVP-Stereo		94.28 353	93.92 338	95.35 396	94.95 460	92.60 374	97.97 341	97.65 367	91.61 397	90.68 443	97.09 366	86.32 332	98.42 370	89.70 422	99.34 139	95.02 472
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SSC-MVS3.2		93.59 380	93.13 378	94.97 409	96.81 386	89.71 437	97.95 342	98.49 206	94.59 254	93.50 374	96.91 393	77.74 442	98.37 384	91.69 385	90.47 399	96.83 372

KD-MVS_self_test		90.38 434	89.38 432	93.40 450	92.85 487	88.94 456	97.95 342	97.94 343	90.35 430	90.25 447	93.96 477	79.82 420	95.94 490	84.62 476	76.69 499	95.33 462

MVS_111021_LR		98.34 71	98.23 68	98.67 97	99.27 95	96.90 132	97.95 342	99.58 3	97.14 84	98.44 129	99.01 153	95.03 85	99.62 166	97.91 103	99.75 55	99.50 109

testing222		94.12 365	93.03 380	97.37 250	98.02 284	94.66 280	97.94 345	96.65 460	94.63 252	95.78 289	95.76 444	71.49 481	98.92 316	91.17 394	95.88 319	98.52 293

UWE-MVS-28		92.79 397	92.51 392	93.62 446	96.46 406	86.28 482	97.93 346	92.71 510	94.17 274	94.78 311	97.16 359	81.05 409	96.43 483	81.45 486	96.86 279	98.14 313

TEST9					99.31 81	98.50 37	97.92 347	98.73 134	92.63 362	97.74 189	98.68 211	96.20 37	99.80 111

train_agg		97.97 87	97.52 105	99.33 37	99.31 81	98.50 37	97.92 347	98.73 134	92.98 348	97.74 189	98.68 211	96.20 37	99.80 111	96.59 201	99.57 100	99.68 77

Syy-MVS		92.55 401	92.61 389	92.38 463	97.39 348	83.41 493	97.91 349	97.46 391	93.16 340	93.42 378	95.37 458	84.75 362	96.12 487	77.00 504	96.99 275	97.60 331

myMVS_eth3d		92.73 398	92.01 400	94.89 413	97.39 348	90.94 407	97.91 349	97.46 391	93.16 340	93.42 378	95.37 458	68.09 487	96.12 487	88.34 442	96.99 275	97.60 331

CDPH-MVS		97.94 90	97.49 107	99.28 43	99.47 57	98.44 39	97.91 349	98.67 152	92.57 366	98.77 97	98.85 181	95.93 47	99.72 139	95.56 244	99.69 73	99.68 77

MVS_111021_HR		98.47 55	98.34 55	98.88 84	99.22 108	97.32 101	97.91 349	99.58 3	97.20 78	98.33 138	99.00 155	95.99 45	99.64 159	98.05 94	99.76 49	99.69 72

PatchMatch-RL		96.59 203	96.03 215	98.27 141	99.31 81	96.51 154	97.91 349	99.06 47	93.72 305	96.92 239	98.06 276	88.50 281	99.65 156	91.77 383	99.00 159	98.66 280

OpenMVS_ROB	86.42 20	89.00 449	87.43 457	93.69 445	93.08 486	89.42 446	97.91 349	96.89 446	78.58 502	85.86 483	94.69 465	69.48 484	98.29 396	77.13 503	93.29 362	93.36 497

test_8					99.29 90	98.44 39	97.89 355	98.72 136	92.98 348	97.70 194	98.66 214	96.20 37	99.80 111

ab-mvs		96.42 211	95.71 232	98.55 109	98.63 181	96.75 139	97.88 356	98.74 131	93.84 295	96.54 263	98.18 268	85.34 350	99.75 134	95.93 225	96.35 299	99.15 204

UBG		95.32 276	94.72 283	97.13 262	98.05 279	93.26 351	97.87 357	97.20 421	94.96 231	96.18 278	95.66 453	80.97 410	99.35 214	94.47 290	97.08 272	98.78 261

jason		97.32 156	97.08 151	98.06 178	97.45 342	95.59 221	97.87 357	97.91 347	94.79 242	98.55 120	98.83 186	91.12 190	99.23 248	97.58 135	99.60 94	99.34 152
jason: jason.
WB-MVSnew		94.19 358	94.04 327	94.66 424	96.82 385	92.14 381	97.86 359	95.96 473	93.50 323	95.64 291	96.77 403	88.06 293	97.99 430	84.87 471	96.86 279	93.85 494

xiu_mvs_v1_base_debu		97.60 115	97.56 101	97.72 217	98.35 215	95.98 183	97.86 359	98.51 196	97.13 85	99.01 75	98.40 241	91.56 165	99.80 111	98.53 57	98.68 176	97.37 339

xiu_mvs_v1_base		97.60 115	97.56 101	97.72 217	98.35 215	95.98 183	97.86 359	98.51 196	97.13 85	99.01 75	98.40 241	91.56 165	99.80 111	98.53 57	98.68 176	97.37 339

xiu_mvs_v1_base_debi		97.60 115	97.56 101	97.72 217	98.35 215	95.98 183	97.86 359	98.51 196	97.13 85	99.01 75	98.40 241	91.56 165	99.80 111	98.53 57	98.68 176	97.37 339

test_prior4						98.01 73	97.86 359

mvsany_test3		88.80 450	88.04 450	91.09 472	89.78 517	81.57 500	97.83 364	95.49 480	93.81 298	87.53 473	93.95 478	56.14 504	97.43 461	94.68 277	83.13 468	94.26 481

WBMVS		94.56 329	94.04 327	96.10 356	98.03 283	93.08 361	97.82 365	98.18 304	94.02 281	93.77 363	96.82 400	81.28 405	98.34 386	95.47 249	91.00 393	96.88 364

FA-MVS(test-final)		96.41 214	95.94 220	97.82 207	98.21 249	95.20 251	97.80 366	97.58 374	93.21 337	97.36 215	97.70 311	89.47 242	99.56 176	94.12 304	97.99 238	98.71 272

test_prior2							97.80 366		96.12 143	97.89 176	98.69 210	95.96 46		96.89 185	99.60 94

XVG-OURS-SEG-HR		96.51 208	96.34 201	97.02 272	98.77 162	93.76 321	97.79 368	98.50 201	95.45 190	96.94 236	99.09 136	87.87 299	99.55 183	96.76 199	95.83 321	97.74 325

usedtu_dtu_shiyan2		84.80 463	82.31 468	92.27 466	86.38 526	85.55 486	97.77 369	96.56 462	78.34 503	83.90 493	93.50 481	54.16 505	95.32 495	77.55 502	72.62 513	95.92 450

MS-PatchMatch		93.84 375	93.63 361	94.46 434	96.18 417	89.45 445	97.76 370	98.27 283	92.23 379	92.13 425	97.49 332	79.50 424	98.69 342	89.75 420	99.38 135	95.25 464

DELS-MVS		98.40 63	98.20 72	98.99 72	99.00 137	97.66 83	97.75 371	98.89 75	97.71 39	98.33 138	98.97 157	94.97 86	99.88 79	98.42 71	99.76 49	99.42 135
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
MG-MVS		97.81 98	97.60 97	98.44 128	99.12 123	95.97 188	97.75 371	98.78 123	96.89 97	98.46 123	99.22 91	93.90 109	99.68 151	94.81 270	99.52 114	99.67 81

test_f		86.07 460	85.39 462	88.10 480	89.28 519	75.57 510	97.73 373	96.33 467	89.41 447	85.35 487	91.56 505	43.31 515	95.53 492	91.32 392	84.23 464	93.21 499

Test_1112_low_res		96.34 216	95.66 237	98.36 136	98.56 185	95.94 191	97.71 374	98.07 330	92.10 384	94.79 310	97.29 350	91.75 157	99.56 176	94.17 302	96.50 295	99.58 100

BH-w/o		95.38 269	95.08 266	96.26 350	98.34 220	91.79 391	97.70 375	97.43 397	92.87 354	94.24 337	97.22 356	88.66 273	98.84 328	91.55 389	97.70 253	98.16 312

lupinMVS		97.44 140	97.22 137	98.12 169	98.07 273	95.76 215	97.68 376	97.76 360	94.50 263	98.79 95	98.61 217	92.34 132	99.30 224	97.58 135	99.59 96	99.31 161

原ACMM2							97.67 377

test_vis3_rt		79.22 473	77.40 478	84.67 489	86.44 525	74.85 514	97.66 378	81.43 528	84.98 484	67.12 519	81.91 525	28.09 539	97.60 455	88.96 435	80.04 484	81.55 527

LF4IMVS		93.14 392	92.79 385	94.20 439	95.88 435	88.67 460	97.66 378	97.07 429	93.81 298	91.71 430	97.65 318	77.96 440	98.81 334	91.47 390	91.92 380	95.12 467

EGC-MVSNET		75.22 483	69.54 487	92.28 465	94.81 463	89.58 442	97.64 380	96.50 463	1.82 560	5.57 562	95.74 445	68.21 486	96.26 486	73.80 512	91.71 382	90.99 508

新几何2							97.64 380

MDA-MVSNet-bldmvs		89.97 441	88.35 446	94.83 419	95.21 456	91.34 400	97.64 380	97.51 386	88.36 459	71.17 516	96.13 432	79.22 427	96.63 479	83.65 478	86.27 452	96.52 419

pmmvs-eth3d		90.36 435	89.05 437	94.32 438	91.10 506	92.12 382	97.63 383	96.95 441	88.86 453	84.91 489	93.13 486	78.32 434	96.74 474	88.70 437	81.81 475	94.09 487

TR-MVS		94.94 307	94.20 315	97.17 259	97.75 311	94.14 311	97.59 384	97.02 436	92.28 378	95.75 290	97.64 321	83.88 383	98.96 309	89.77 419	96.15 314	98.40 299

无先验							97.58 385	98.72 136	91.38 403				99.87 81	93.36 327		99.60 94

旧先验2							97.57 386		91.30 409	98.67 108			99.80 111	95.70 239

mvsany_test1		97.69 106	97.70 93	97.66 228	98.24 243	94.18 309	97.53 387	97.53 384	95.52 186	99.66 30	99.51 29	94.30 100	99.56 176	98.38 72	98.62 181	99.23 188

CostFormer		94.95 305	94.73 282	95.60 387	97.28 353	89.06 451	97.53 387	96.89 446	89.66 441	96.82 245	96.72 405	86.05 336	98.95 314	95.53 246	96.13 315	98.79 257

UWE-MVS		94.30 349	93.89 343	95.53 388	97.83 305	88.95 455	97.52 389	93.25 505	94.44 266	96.63 255	97.07 369	78.70 431	99.28 229	91.99 376	97.56 259	98.36 302

XVG-OURS		96.55 207	96.41 197	96.99 273	98.75 163	93.76 321	97.50 390	98.52 193	95.67 170	96.83 243	99.30 75	88.95 267	99.53 185	95.88 227	96.26 309	97.69 328

blended_shiyan8		91.42 410	89.89 423	96.01 359	91.50 497	93.30 348	97.48 391	97.83 351	86.93 466	92.57 407	92.37 495	82.46 394	98.13 408	92.86 348	74.99 502	96.61 398

blended_shiyan6		91.37 411	89.84 424	95.98 365	91.49 498	93.28 349	97.48 391	97.83 351	86.93 466	92.43 413	92.36 496	82.44 395	98.06 420	92.74 353	74.82 505	96.59 403

blend_shiyan4		90.76 429	89.01 438	95.99 362	91.69 496	93.35 345	97.44 393	97.83 351	86.93 466	92.23 420	91.98 499	75.19 466	98.09 415	92.88 346	74.96 503	96.52 419

xiu_mvs_v2_base		97.66 109	97.70 93	97.56 236	98.61 183	95.46 231	97.44 393	98.46 209	97.15 83	98.65 113	98.15 270	94.33 99	99.80 111	97.84 111	98.66 180	97.41 335

tpm		94.13 363	93.80 349	95.12 402	96.50 403	87.91 473	97.44 393	95.89 476	92.62 363	96.37 271	96.30 424	84.13 378	98.30 393	93.24 330	91.66 384	99.14 207

DeepPCF-MVS	96.37 2	97.93 91	98.48 39	96.30 348	99.00 137	89.54 443	97.43 396	98.87 85	98.16 23	99.26 59	99.38 56	96.12 40	99.64 159	98.30 77	99.77 43	99.72 60

test222					99.23 106	97.17 119	97.40 397	98.66 155	88.68 455	98.05 153	98.96 162	94.14 104			99.53 113	99.61 92

pmmvs4		94.69 317	93.99 335	96.81 291	95.74 439	95.94 191	97.40 397	97.67 366	90.42 428	93.37 380	97.59 325	89.08 258	98.20 402	92.97 340	91.67 383	96.30 437

test0.0.03 1		94.08 369	93.51 367	95.80 377	95.53 448	92.89 366	97.38 399	95.97 472	95.11 217	92.51 410	96.66 408	87.71 301	96.94 470	87.03 455	93.67 348	97.57 333

HyFIR lowres test		96.90 186	96.49 195	98.14 161	99.33 76	95.56 224	97.38 399	99.65 2	92.34 374	97.61 206	98.20 266	89.29 251	99.10 280	96.97 177	97.60 256	99.77 41

Effi-MVS+		97.12 174	96.69 182	98.39 135	98.19 253	96.72 141	97.37 401	98.43 229	93.71 306	97.65 203	98.02 279	92.20 142	99.25 236	96.87 190	97.79 246	99.19 197

N_pmnet		87.12 458	87.77 455	85.17 488	95.46 451	61.92 533	97.37 401	70.66 545	85.83 478	88.73 468	96.04 437	85.33 351	97.76 448	80.02 490	90.48 398	95.84 452

PAPR		96.84 189	96.24 206	98.65 99	98.72 168	96.92 131	97.36 403	98.57 180	93.33 331	96.67 253	97.57 327	94.30 100	99.56 176	91.05 401	98.59 183	99.47 118

PMMVS		96.60 202	96.33 202	97.41 245	97.90 301	93.93 316	97.35 404	98.41 235	92.84 355	97.76 186	97.45 336	91.10 192	99.20 254	96.26 214	97.91 241	99.11 213

PS-MVSNAJ		97.73 102	97.77 90	97.62 232	98.68 174	95.58 222	97.34 405	98.51 196	97.29 68	98.66 112	97.88 295	94.51 93	99.90 66	97.87 108	99.17 150	97.39 337

SCA		95.46 261	95.13 261	96.46 335	97.67 319	91.29 402	97.33 406	97.60 373	94.68 249	96.92 239	97.10 362	83.97 381	98.89 322	92.59 359	98.32 222	99.20 193

ArgMatch-Sym		90.92 425	90.22 418	93.02 457	95.81 438	86.50 481	97.32 407	97.01 439	92.67 360	91.02 439	97.35 344	66.90 492	97.17 466	88.53 440	85.40 459	95.39 461

testdata1							97.32 407		96.34 131

ET-MVSNet_ETH3D		94.13 363	92.98 381	97.58 234	98.22 247	96.20 171	97.31 409	95.37 481	94.53 257	79.56 504	97.63 323	86.51 323	97.53 459	96.91 181	90.74 395	99.02 232

tpm2		94.19 358	93.76 354	95.46 392	97.23 356	89.04 452	97.31 409	96.85 450	87.08 464	96.21 277	96.79 402	83.75 387	98.74 339	92.43 367	96.23 312	98.59 288

PVSNet_Blended		97.38 146	97.12 148	98.14 161	99.25 98	95.35 243	97.28 411	99.26 16	93.13 342	97.94 169	98.21 265	92.74 123	99.81 104	96.88 187	99.40 133	99.27 177

CLD-MVS		95.62 254	95.34 249	96.46 335	97.52 335	93.75 323	97.27 412	98.46 209	95.53 185	94.42 325	98.00 282	86.21 333	98.97 305	96.25 216	94.37 328	96.66 392
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
IMVS_0404		95.82 243	95.52 239	96.73 296	97.99 288	92.82 367	97.23 413	98.27 283	95.16 210	94.31 331	98.79 191	85.63 343	98.10 411	94.74 272	97.54 260	99.27 177

EPMVS		94.99 297	94.48 296	96.52 326	97.22 357	91.75 393	97.23 413	91.66 514	94.11 276	97.28 219	96.81 401	85.70 342	98.84 328	93.04 338	97.28 268	98.97 237

miper_lstm_enhance		94.33 347	94.07 326	95.11 403	97.75 311	90.97 406	97.22 415	98.03 337	91.67 396	92.76 399	96.97 385	90.03 228	97.78 446	92.51 364	89.64 410	96.56 411

APD_test1		88.22 453	88.01 451	88.86 479	95.98 428	74.66 516	97.21 416	96.44 465	83.96 488	86.66 480	97.90 292	60.95 502	97.84 443	82.73 480	90.23 403	94.09 487

ArgMatch-SfM		90.55 432	89.69 425	93.14 456	95.91 433	86.12 484	97.20 417	96.81 452	92.91 352	91.39 434	96.95 389	65.65 496	97.72 450	88.03 446	82.36 470	95.57 458

dmvs_testset		87.64 455	88.93 442	83.79 493	95.25 455	63.36 529	97.20 417	91.17 515	93.07 344	85.64 486	95.98 442	85.30 353	91.52 515	69.42 517	87.33 442	96.49 426

YYNet1		90.70 431	89.39 430	94.62 427	94.79 464	90.65 416	97.20 417	97.46 391	87.54 462	72.54 513	95.74 445	86.51 323	96.66 478	86.00 462	86.76 451	96.54 414

gbinet_0.2-2-1-0.02		91.03 422	89.37 434	96.01 359	91.39 499	93.41 338	97.19 420	97.82 354	87.00 465	92.18 423	91.87 501	78.97 429	98.04 424	93.13 334	74.75 509	96.60 400

MDA-MVSNet_test_wron		90.71 430	89.38 432	94.68 423	94.83 462	90.78 413	97.19 420	97.46 391	87.60 461	72.41 514	95.72 449	86.51 323	96.71 477	85.92 463	86.80 450	96.56 411

icg_test_0407_2		96.56 206	96.50 194	96.73 296	97.99 288	92.82 367	97.18 422	98.27 283	95.16 210	97.30 217	98.79 191	91.53 169	98.10 411	94.74 272	97.54 260	99.27 177

IterMVS-SCA-FT		94.11 366	93.87 344	94.85 416	97.98 294	90.56 421	97.18 422	98.11 320	93.75 300	92.58 405	97.48 333	83.97 381	97.41 462	92.48 366	91.30 387	96.58 407

IterMVS		94.09 368	93.85 346	94.80 420	97.99 288	90.35 426	97.18 422	98.12 317	93.68 311	92.46 412	97.34 345	84.05 379	97.41 462	92.51 364	91.33 386	96.62 397
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FE-MVS		95.62 254	94.90 275	97.78 210	98.37 213	94.92 270	97.17 425	97.38 401	90.95 419	97.73 191	97.70 311	85.32 352	99.63 162	91.18 393	98.33 219	98.79 257

DPM-MVS		97.55 123	96.99 159	99.23 50	99.04 131	98.55 35	97.17 425	98.35 258	94.85 239	97.93 171	98.58 223	95.07 83	99.71 144	92.60 357	99.34 139	99.43 132

c3_l		94.79 313	94.43 303	95.89 371	97.75 311	93.12 359	97.16 427	98.03 337	92.23 379	93.46 377	97.05 376	91.39 173	98.01 427	93.58 322	89.21 420	96.53 416

new-patchmatchnet		88.50 452	87.45 456	91.67 469	90.31 514	85.89 485	97.16 427	97.33 404	89.47 444	83.63 494	92.77 492	76.38 457	95.06 499	82.70 481	77.29 493	94.06 489

UnsupCasMVSNet_eth		90.99 424	89.92 422	94.19 440	94.08 473	89.83 433	97.13 429	98.67 152	93.69 309	85.83 484	96.19 430	75.15 467	96.74 474	89.14 432	79.41 486	96.00 447

IB-MVS	91.98 17	93.27 386	91.97 401	97.19 257	97.47 338	93.41 338	97.09 430	95.99 471	93.32 332	92.47 411	95.73 447	78.06 438	99.53 185	94.59 286	82.98 469	98.62 283
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
usedtu_dtu_shiyan1		94.96 303	94.28 309	96.98 276	95.93 431	96.11 177	97.08 431	98.39 244	93.62 317	93.86 356	96.40 420	88.28 284	98.21 400	92.61 354	92.36 373	96.63 394

FE-MVSNET3		94.96 303	94.28 309	96.98 276	95.93 431	96.11 177	97.08 431	98.39 244	93.62 317	93.86 356	96.40 420	88.28 284	98.21 400	92.61 354	92.36 373	96.63 394

cl____		94.51 335	94.01 332	96.02 358	97.58 327	93.40 341	97.05 433	97.96 342	91.73 394	92.76 399	97.08 368	89.06 259	98.13 408	92.61 354	90.29 402	96.52 419

DIV-MVS_self_test		94.52 334	94.03 329	95.99 362	97.57 331	93.38 342	97.05 433	97.94 343	91.74 392	92.81 397	97.10 362	89.12 256	98.07 419	92.60 357	90.30 401	96.53 416

miper_ehance_all_eth		95.01 294	94.69 285	95.97 366	97.70 317	93.31 347	97.02 435	98.07 330	92.23 379	93.51 373	96.96 387	91.85 153	98.15 406	93.68 317	91.16 390	96.44 431

CMPMVS	66.06 21	89.70 443	89.67 427	89.78 475	93.19 485	76.56 506	97.00 436	98.35 258	80.97 496	81.57 497	97.75 307	74.75 470	98.61 350	89.85 418	93.63 350	94.17 485
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
tpmrst		95.63 253	95.69 235	95.44 393	97.54 332	88.54 462	96.97 437	97.56 377	93.50 323	97.52 213	96.93 392	89.49 240	99.16 262	95.25 257	96.42 298	98.64 282

dp		94.15 362	93.90 341	94.90 412	97.31 352	86.82 480	96.97 437	97.19 422	91.22 414	96.02 283	96.61 413	85.51 346	99.02 300	90.00 417	94.30 329	98.85 250

cl22		94.68 319	94.19 316	96.13 354	98.11 269	93.60 329	96.94 439	98.31 273	92.43 371	93.32 382	96.87 397	86.51 323	98.28 397	94.10 306	91.16 390	96.51 423

dtuonlycased		91.29 413	91.26 408	91.36 471	95.63 443	84.25 490	96.93 440	97.21 418	92.16 383	88.34 469	96.47 416	79.56 423	95.18 498	87.37 453	87.70 436	94.64 478

PM-MVS		87.77 454	86.55 460	91.40 470	91.03 508	83.36 495	96.92 441	95.18 485	91.28 411	86.48 482	93.42 482	53.27 506	96.74 474	89.43 428	81.97 474	94.11 486

TinyColmap		92.31 404	91.53 405	94.65 425	96.92 377	89.75 435	96.92 441	96.68 457	90.45 427	89.62 455	97.85 298	76.06 461	98.81 334	86.74 456	92.51 371	95.41 460

our_test_3		93.65 378	93.30 374	94.69 422	95.45 452	89.68 440	96.91 443	97.65 367	91.97 387	91.66 432	96.88 395	89.67 237	97.93 435	88.02 447	91.49 385	96.48 428

test-LLR		95.10 289	94.87 277	95.80 377	96.77 387	89.70 438	96.91 443	95.21 483	95.11 217	94.83 308	95.72 449	87.71 301	98.97 305	93.06 336	98.50 193	98.72 269

TESTMET0.1,1		94.18 361	93.69 359	95.63 385	96.92 377	89.12 450	96.91 443	94.78 491	93.17 339	94.88 305	96.45 418	78.52 432	98.92 316	93.09 335	98.50 193	98.85 250

test-mter		94.08 369	93.51 367	95.80 377	96.77 387	89.70 438	96.91 443	95.21 483	92.89 353	94.83 308	95.72 449	77.69 443	98.97 305	93.06 336	98.50 193	98.72 269

USDC		93.33 385	92.71 386	95.21 399	96.83 384	90.83 412	96.91 443	97.50 387	93.84 295	90.72 442	98.14 271	77.69 443	98.82 333	89.51 426	93.21 363	95.97 448

wanda-best-256-512		91.17 418	89.60 428	95.88 372	91.33 501	92.99 363	96.89 448	97.82 354	86.89 469	92.36 415	91.75 502	81.83 398	98.06 420	92.75 350	74.82 505	96.59 403

FE-blended-shiyan7		91.17 418	89.60 428	95.88 372	91.33 501	92.99 363	96.89 448	97.82 354	86.89 469	92.36 415	91.75 502	81.83 398	98.06 420	92.75 350	74.82 505	96.59 403

MDTV_nov1_ep13_2view						84.26 489	96.89 448		90.97 418	97.90 175		89.89 231		93.91 311		99.18 202

ppachtmachnet_test		93.22 388	92.63 388	94.97 409	95.45 452	90.84 411	96.88 451	97.88 348	90.60 423	92.08 426	97.26 351	88.08 292	97.86 442	85.12 470	90.33 400	96.22 440

tpmvs		94.60 325	94.36 306	95.33 397	97.46 339	88.60 461	96.88 451	97.68 363	91.29 410	93.80 361	96.42 419	88.58 275	99.24 244	91.06 399	96.04 316	98.17 311

MDTV_nov1_ep13			95.40 243		97.48 337	88.34 466	96.85 453	97.29 409	93.74 302	97.48 214	97.26 351	89.18 254	99.05 289	91.92 379	97.43 266

PatchmatchNet		95.71 248	95.52 239	96.29 349	97.58 327	90.72 414	96.84 454	97.52 385	94.06 278	97.08 229	96.96 387	89.24 253	98.90 321	92.03 375	98.37 214	99.26 184
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MSDG		95.93 236	95.30 255	97.83 205	98.90 147	95.36 241	96.83 455	98.37 253	91.32 408	94.43 324	98.73 205	90.27 222	99.60 168	90.05 415	98.82 172	98.52 293

thisisatest0515		95.61 257	94.89 276	97.76 214	98.15 265	95.15 255	96.77 456	94.41 494	92.95 350	97.18 225	97.43 338	84.78 361	99.45 204	94.63 280	97.73 252	98.68 276

GA-MVS		94.81 312	94.03 329	97.14 261	97.15 365	93.86 318	96.76 457	97.58 374	94.00 285	94.76 312	97.04 377	80.91 411	98.48 361	91.79 382	96.25 310	99.09 219

tpm cat1		93.36 382	92.80 384	95.07 406	97.58 327	87.97 472	96.76 457	97.86 349	82.17 493	93.53 370	96.04 437	86.13 334	99.13 271	89.24 431	95.87 320	98.10 314

eth_miper_zixun_eth		94.68 319	94.41 304	95.47 391	97.64 322	91.71 395	96.73 459	98.07 330	92.71 359	93.64 365	97.21 357	90.54 211	98.17 404	93.38 325	89.76 408	96.54 414

test_post1							96.68 460				30.43 559	87.85 300	98.69 342	92.59 359

pmmvs3		86.67 459	84.86 465	92.11 468	88.16 521	87.19 479	96.63 461	94.75 492	79.88 498	87.22 475	92.75 493	66.56 493	95.20 497	81.24 487	76.56 500	93.96 491

miper_enhance_ethall		95.10 289	94.75 281	96.12 355	97.53 334	93.73 326	96.61 462	98.08 328	92.20 382	93.89 353	96.65 410	92.44 129	98.30 393	94.21 299	91.16 390	96.34 434

PatchmatchNet2					0.00 567	88.11 471	96.56 463	97.31 407	85.66 481
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
testmvs		21.48 523	24.95 526	11.09 541	14.89 565	6.47 568	96.56 463	9.87 566	7.55 557	17.93 559	39.02 556	9.43 564	5.90 562	16.56 548	12.72 560	20.91 557

test123		20.95 524	23.72 527	12.64 540	13.54 566	8.19 567	96.55 465	6.13 567	7.48 558	16.74 560	37.98 557	12.97 559	6.05 561	16.69 546	5.43 561	23.68 556

CL-MVSNet_self_test		90.11 439	89.14 436	93.02 457	91.86 494	88.23 469	96.51 466	98.07 330	90.49 424	90.49 445	94.41 469	84.75 362	95.34 494	80.79 488	74.95 504	95.50 459

GG-mvs-BLEND				96.59 316	96.34 411	94.98 266	96.51 466	88.58 522		93.10 392	94.34 474	80.34 419	98.05 423	89.53 425	96.99 275	96.74 379

new_pmnet		90.06 440	89.00 439	93.22 454	94.18 468	88.32 467	96.42 468	96.89 446	86.19 474	85.67 485	93.62 479	77.18 450	97.10 467	81.61 485	89.29 419	94.23 483

dtuonly		95.08 292	95.10 265	95.02 407	96.53 400	87.27 478	96.33 469	97.21 418	93.41 328	96.28 273	98.51 232	87.71 301	98.99 304	91.88 380	98.01 237	98.80 256

PVSNet	91.96 18	96.35 215	96.15 208	96.96 279	99.17 113	92.05 388	96.08 470	98.68 147	93.69 309	97.75 188	97.80 305	88.86 269	99.69 150	94.26 298	99.01 157	99.15 204

ADS-MVSNet2		94.58 328	94.40 305	95.11 403	98.00 286	88.74 459	96.04 471	97.30 408	90.15 432	96.47 266	96.64 411	87.89 297	97.56 458	90.08 413	97.06 273	99.02 232

ADS-MVSNet		95.00 295	94.45 301	96.63 310	98.00 286	91.91 390	96.04 471	97.74 362	90.15 432	96.47 266	96.64 411	87.89 297	98.96 309	90.08 413	97.06 273	99.02 232

PAPM		94.95 305	94.00 333	97.78 210	97.04 370	95.65 219	96.03 473	98.25 292	91.23 413	94.19 340	97.80 305	91.27 179	98.86 327	82.61 482	97.61 255	98.84 252

cascas		94.63 324	93.86 345	96.93 281	96.91 379	94.27 303	96.00 474	98.51 196	85.55 482	94.54 316	96.23 427	84.20 377	98.87 325	95.80 233	96.98 278	97.66 329

gg-mvs-nofinetune		92.21 405	90.58 414	97.13 262	96.75 390	95.09 258	95.85 475	89.40 520	85.43 483	94.50 318	81.98 524	80.80 414	98.40 383	92.16 369	98.33 219	97.88 320

FPMVS		77.62 481	77.14 480	79.05 505	79.25 540	60.97 535	95.79 476	95.94 474	65.96 520	67.93 518	94.40 470	37.73 526	88.88 522	68.83 518	88.46 429	87.29 521

CHOSEN 280x420		97.18 169	97.18 140	97.20 255	98.81 160	93.27 350	95.78 477	99.15 41	95.25 206	96.79 248	98.11 273	92.29 135	99.07 285	98.56 56	99.85 7	99.25 186

mamba_0408		96.81 191	96.38 199	98.09 173	98.19 253	95.90 197	95.69 478	98.32 268	94.51 260	96.75 249	98.73 205	90.99 197	99.27 231	95.83 229	98.43 203	99.10 215

SSM_04072		96.71 196	96.38 199	97.68 223	98.19 253	95.90 197	95.69 478	98.32 268	94.51 260	96.75 249	98.73 205	90.99 197	98.02 426	95.83 229	98.43 203	99.10 215

MIMVSNet		93.26 387	92.21 398	96.41 339	97.73 315	93.13 357	95.65 480	97.03 433	91.27 412	94.04 347	96.06 434	75.33 464	97.19 465	86.56 458	96.23 312	98.92 244

KD-MVS_2432*1600		89.61 445	87.96 453	94.54 429	94.06 474	91.59 397	95.59 481	97.63 370	89.87 437	88.95 462	94.38 471	78.28 435	96.82 472	84.83 472	68.05 521	95.21 465

miper_refine_blended		89.61 445	87.96 453	94.54 429	94.06 474	91.59 397	95.59 481	97.63 370	89.87 437	88.95 462	94.38 471	78.28 435	96.82 472	84.83 472	68.05 521	95.21 465

RoMa-SfM		83.81 466	82.08 469	89.00 478	93.33 483	79.94 503	95.51 483	92.48 511	79.75 499	79.89 502	95.69 452	46.23 510	93.20 510	78.90 497	76.93 496	93.87 493

PCF-MVS	93.45 11	94.68 319	93.43 371	98.42 132	98.62 182	96.77 138	95.48 484	98.20 298	84.63 486	93.34 381	98.32 253	88.55 279	99.81 104	84.80 474	98.96 161	98.68 276
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
LoFTR		83.16 467	80.62 471	90.80 473	92.28 491	80.01 502	95.35 485	94.33 496	80.44 497	70.79 517	92.93 488	46.38 508	98.17 404	75.01 508	78.03 491	94.24 482

0.4-1-1-0.1		90.89 426	88.97 440	96.67 304	94.15 470	92.76 371	95.28 486	95.03 488	89.11 450	90.43 446	89.57 512	75.41 463	99.04 292	94.70 276	77.06 495	98.20 310

mvs5depth		91.23 416	90.17 419	94.41 436	92.09 492	89.79 434	95.26 487	96.50 463	90.73 421	91.69 431	97.06 373	76.12 460	98.62 349	88.02 447	84.11 465	94.82 474

MatchFormer		80.21 470	77.20 479	89.24 477	91.79 495	77.21 505	95.16 488	93.59 504	72.46 515	67.08 520	89.93 511	43.14 516	97.90 436	67.07 519	74.55 511	92.61 503

JIA-IIPM		93.35 383	92.49 393	95.92 368	96.48 405	90.65 416	95.01 489	96.96 440	85.93 477	96.08 281	87.33 517	87.70 304	98.78 337	91.35 391	95.58 324	98.34 303

DenseAffine		84.37 464	82.38 467	90.31 474	94.17 469	82.89 496	94.98 490	94.23 499	82.16 494	79.68 503	94.33 475	46.28 509	94.25 504	80.01 491	75.62 501	93.78 495

CR-MVSNet		94.76 316	94.15 320	96.59 316	97.00 371	93.43 336	94.96 491	97.56 377	92.46 367	96.93 237	96.24 425	88.15 289	97.88 441	87.38 452	96.65 289	98.46 297

RPMNet		92.81 396	91.34 407	97.24 253	97.00 371	93.43 336	94.96 491	98.80 116	82.27 492	96.93 237	92.12 498	86.98 317	99.82 99	76.32 506	96.65 289	98.46 297

UnsupCasMVSNet_bld		87.17 456	85.12 464	93.31 452	91.94 493	88.77 457	94.92 493	98.30 280	84.30 487	82.30 495	90.04 510	63.96 499	97.25 464	85.85 464	74.47 512	93.93 492

PVSNet_0	88.72 19	91.28 415	90.03 421	95.00 408	97.99 288	87.29 477	94.84 494	98.50 201	92.06 385	89.86 452	95.19 460	79.81 421	99.39 212	92.27 368	69.79 520	98.33 304

Patchmatch-test		94.42 343	93.68 360	96.63 310	97.60 325	91.76 392	94.83 495	97.49 389	89.45 445	94.14 342	97.10 362	88.99 261	98.83 331	85.37 468	98.13 233	99.29 169

testf1		79.02 475	77.70 475	82.99 497	88.10 522	66.90 525	94.67 496	93.11 506	71.08 517	74.02 509	93.41 483	34.15 531	93.25 508	72.25 513	78.50 489	88.82 515

APD_test2		79.02 475	77.70 475	82.99 497	88.10 522	66.90 525	94.67 496	93.11 506	71.08 517	74.02 509	93.41 483	34.15 531	93.25 508	72.25 513	78.50 489	88.82 515

Patchmtry		93.22 388	92.35 396	95.84 376	96.77 387	93.09 360	94.66 498	97.56 377	87.37 463	92.90 395	96.24 425	88.15 289	97.90 436	87.37 453	90.10 405	96.53 416

DKM		81.60 469	79.57 472	87.68 481	92.65 490	78.36 504	94.65 499	91.17 515	79.69 500	76.11 507	93.98 476	37.88 525	91.54 514	79.64 494	70.38 517	93.15 500

kuosan		78.45 478	77.69 477	80.72 501	92.73 489	75.32 511	94.63 500	74.51 534	75.96 508	80.87 501	93.19 485	63.23 500	79.99 533	42.56 537	81.56 477	86.85 524

dongtai		82.47 468	81.88 470	84.22 492	95.19 457	76.03 507	94.59 501	74.14 535	82.63 490	87.19 476	96.09 433	64.10 498	87.85 523	58.91 525	84.11 465	88.78 517

PatchT		93.06 394	91.97 401	96.35 344	96.69 393	92.67 372	94.48 502	97.08 427	86.62 471	97.08 229	92.23 497	87.94 296	97.90 436	78.89 498	96.69 286	98.49 295

0.3-1-1-0.015		90.29 436	88.21 448	96.51 327	93.56 479	92.44 375	94.41 503	95.03 488	88.71 454	89.20 460	88.50 514	73.12 479	99.04 292	94.67 279	76.70 498	98.05 315

LCM-MVSNet		78.70 477	76.24 483	86.08 484	77.26 545	71.99 518	94.34 504	96.72 454	61.62 522	76.53 506	89.33 513	33.91 534	92.78 512	81.85 484	74.60 510	93.46 496

RoMa-HiRes		79.77 471	77.89 474	85.41 487	90.81 509	74.77 515	94.26 505	86.78 524	75.97 507	77.00 505	94.37 473	39.39 520	90.60 516	74.98 509	67.46 523	90.84 509

PMMVS2		77.95 480	75.44 484	85.46 486	82.54 533	74.95 513	94.23 506	93.08 508	72.80 513	74.68 508	87.38 516	36.36 528	91.56 513	73.95 511	63.94 525	89.87 512

MVS-HIRNet		89.46 448	88.40 445	92.64 461	97.58 327	82.15 498	94.16 507	93.05 509	75.73 511	90.90 440	82.52 522	79.42 426	98.33 388	83.53 479	98.68 176	97.43 334

0.4-1-1-0.2		90.43 433	88.45 444	96.38 342	93.34 482	92.12 382	93.88 508	95.04 487	88.62 456	90.00 451	88.31 515	75.31 465	99.03 295	94.61 283	76.91 497	98.01 319

DKM-HiRes		79.25 472	77.01 481	85.98 485	91.20 505	75.07 512	93.65 509	87.84 523	75.94 509	73.36 512	92.80 490	34.20 530	90.26 517	76.66 505	67.44 524	92.62 502

MASt3R-SfM		85.54 461	85.89 461	84.50 491	90.13 515	66.13 527	92.89 510	95.33 482	85.73 480	88.77 466	96.36 422	52.50 507	94.89 501	86.66 457	84.65 461	92.50 504

Patchmatch-RL test		91.49 409	90.85 411	93.41 449	91.37 500	84.40 488	92.81 511	95.93 475	91.87 390	87.25 474	94.87 464	88.99 261	96.53 481	92.54 363	82.00 473	99.30 166

ambc				89.49 476	86.66 524	75.78 508	92.66 512	96.72 454		86.55 481	92.50 494	46.01 511	97.90 436	90.32 409	82.09 472	94.80 476

EMVS		64.07 499	63.26 501	66.53 519	81.73 536	58.81 538	91.85 513	84.75 526	51.93 527	59.09 533	75.13 537	43.32 514	79.09 534	42.03 538	39.47 544	61.69 537

E-PMN		64.94 498	64.25 499	67.02 518	82.28 534	59.36 537	91.83 514	85.63 525	52.69 525	60.22 529	77.28 534	41.06 518	80.12 532	46.15 531	41.14 543	61.57 538

ELoFTR		75.37 482	72.33 485	84.51 490	84.48 531	68.41 524	91.57 515	88.78 521	73.84 512	62.84 524	90.14 508	27.38 540	94.11 506	71.45 516	60.46 529	91.00 507

SP-SuperGlue		68.14 491	66.58 491	72.81 515	90.65 511	55.53 541	91.37 516	73.04 537	49.07 531	61.03 526	80.24 529	38.13 524	74.06 538	45.46 533	70.26 518	88.84 514

SP-LightGlue		68.17 490	66.54 492	73.06 513	91.08 507	55.79 540	91.09 517	72.78 538	48.55 532	60.77 528	79.95 530	38.55 523	74.10 537	45.47 532	70.64 516	89.28 513

SP-MNN		66.66 495	64.70 498	72.53 516	90.32 513	55.08 543	91.01 518	71.05 542	44.81 535	56.48 536	79.62 532	35.87 529	74.11 536	43.13 536	69.98 519	88.39 519

ANet_high		69.08 488	65.37 495	80.22 503	65.99 559	71.96 519	90.91 519	90.09 519	82.62 491	49.93 541	78.39 533	29.36 538	81.75 530	62.49 522	38.52 546	86.95 523

PDCNetPlus		71.79 485	69.26 488	79.39 504	85.67 528	69.92 520	90.34 520	62.32 547	72.62 514	65.36 522	90.26 507	39.20 522	86.38 525	75.32 507	42.24 542	81.88 526

SP-NN		67.39 493	65.69 494	72.49 517	90.68 510	55.34 542	90.33 521	71.01 543	46.77 534	59.09 533	79.83 531	37.26 527	73.38 540	44.68 534	71.51 515	88.74 518

PMatch-SfM		73.49 484	70.32 486	83.00 496	85.01 530	68.63 523	90.17 522	79.05 531	71.64 516	63.27 523	91.93 500	17.27 550	89.10 521	74.59 510	59.95 530	91.26 505

ALIKED-LG		67.40 492	65.16 496	74.11 509	93.21 484	62.30 531	88.98 523	71.99 539	55.04 523	59.47 532	82.33 523	39.27 521	85.49 527	32.61 544	63.58 527	74.55 531

ALIKED-MNN		65.35 497	62.68 502	73.35 510	93.70 477	61.07 534	88.63 524	70.76 544	47.76 533	57.06 535	80.59 527	34.03 533	85.39 528	32.73 543	58.87 531	73.59 533

SP-DiffGlue		70.13 486	69.16 489	73.04 514	77.73 543	57.48 539	88.44 525	74.91 533	50.96 528	66.64 521	85.99 518	41.44 517	73.46 539	64.21 521	72.15 514	88.19 520

PMatch-Up-SfM		70.03 487	66.48 493	80.70 502	82.00 535	63.20 530	88.10 526	71.07 541	67.59 519	60.07 530	90.10 509	14.49 555	87.80 524	71.95 515	52.95 535	91.09 506

ALIKED-NN		66.93 494	64.81 497	73.32 511	93.41 481	62.03 532	87.55 527	71.25 540	50.21 529	59.98 531	82.57 521	39.72 519	84.03 529	34.94 541	63.64 526	73.90 532

tmp_tt		68.90 489	66.97 490	74.68 507	50.78 561	59.95 536	87.13 528	83.47 527	38.80 537	62.21 525	96.23 427	64.70 497	76.91 535	88.91 436	30.49 550	87.19 522

MVE	62.14 22	63.28 500	59.38 503	74.99 506	74.33 550	65.47 528	85.55 529	80.50 529	52.02 526	51.10 539	75.00 538	10.91 562	80.50 531	51.60 529	53.40 534	78.99 528
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	61.03 23	65.95 496	63.57 500	73.09 512	57.90 560	51.22 546	85.05 530	93.93 503	54.45 524	44.32 543	83.57 519	13.22 557	89.15 520	58.68 526	81.00 480	78.91 529
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_method		79.03 474	78.17 473	81.63 500	86.06 527	54.40 544	82.75 531	96.89 446	39.54 536	80.98 500	95.57 456	58.37 503	94.73 502	84.74 475	78.61 488	95.75 454

Gipuma		78.40 479	76.75 482	83.38 495	95.54 446	80.43 501	79.42 532	97.40 399	64.67 521	73.46 511	80.82 526	45.65 512	93.14 511	66.32 520	87.43 440	76.56 530
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
GLUNet-SfM		61.12 501	56.63 504	74.58 508	69.78 555	53.99 545	78.71 533	76.81 532	49.09 530	49.42 542	80.47 528	24.43 542	85.82 526	51.80 528	29.17 551	83.92 525

XFeat-MNN		55.84 503	55.19 507	57.82 520	69.33 556	43.25 551	78.25 534	62.64 546	37.53 539	50.90 540	76.32 536	32.43 537	68.13 541	42.00 539	47.26 541	62.07 536

XFeat-NN		56.16 502	56.10 505	56.36 521	72.10 552	42.54 556	76.45 535	61.18 548	38.16 538	53.08 537	76.48 535	32.95 536	65.67 542	44.15 535	50.31 539	60.87 539

SIFT-NN		49.27 506	49.25 509	49.32 523	83.88 532	45.20 547	74.57 536	53.44 549	32.44 540	42.88 544	64.93 541	20.60 544	61.35 543	16.59 547	53.96 533	41.40 541

SIFT-MNN		47.78 507	47.47 510	48.69 524	81.04 537	44.17 548	73.46 537	53.36 550	31.82 541	38.54 545	63.76 542	18.11 548	61.27 544	15.96 549	51.17 537	40.64 544

SIFT-NN-NCMNet		47.55 508	47.18 511	48.67 525	79.60 539	44.09 549	73.43 538	52.90 551	31.82 541	38.38 546	63.56 545	18.47 545	61.19 545	15.91 550	50.50 538	40.74 543

SIFT-NCM-Cal		44.98 510	44.20 513	47.33 527	79.81 538	43.05 552	72.12 539	49.31 553	30.81 546	25.90 554	61.87 550	15.80 551	60.28 546	14.09 558	48.07 540	38.66 547

SIFT-NN-UMatch		44.69 511	43.84 514	47.24 528	74.56 549	42.59 555	71.89 540	49.78 552	31.80 543	29.27 551	63.70 543	18.26 546	59.43 547	15.86 552	39.43 545	39.71 545

SIFT-UMatch		42.35 514	41.04 517	46.29 530	76.09 547	41.80 557	70.21 541	45.21 557	30.75 547	27.33 553	62.62 546	15.13 553	59.11 550	14.72 555	27.30 553	37.95 548

SIFT-NN-CMatch		45.31 509	44.49 512	47.75 526	76.46 546	42.98 554	70.17 542	49.20 554	31.63 544	37.94 547	63.68 544	18.19 547	59.32 549	15.91 550	37.27 547	40.95 542

SIFT-NN-PointCN		43.09 513	42.61 515	44.51 532	72.48 551	37.95 560	70.10 543	46.55 556	30.16 550	34.48 549	61.93 549	18.02 549	55.90 554	15.40 553	34.41 548	39.69 546

SIFT-ConvMatch		43.26 512	42.18 516	46.50 529	78.34 542	43.05 552	68.67 544	47.17 555	31.06 545	30.28 550	62.56 547	15.43 552	58.95 551	14.92 554	31.22 549	37.51 549

SIFT-UM-Cal		39.93 516	38.61 520	43.88 533	76.08 548	39.30 559	68.10 545	37.89 560	30.49 548	22.74 556	62.27 548	13.89 556	56.16 553	14.17 556	21.90 556	36.17 551

wuyk23d		30.17 521	30.18 525	30.16 539	78.61 541	43.29 550	66.79 546	14.21 565	17.31 556	14.82 561	11.93 560	11.55 561	41.43 558	37.08 540	19.30 558	5.76 558

SIFT-PointCN		37.89 517	37.50 521	39.07 535	71.45 553	31.31 562	66.27 547	41.69 558	27.82 552	22.63 557	56.73 553	12.00 560	50.56 556	12.18 560	26.71 554	35.34 552

SIFT-CM-Cal		41.25 515	40.03 518	44.88 531	77.37 544	41.08 558	65.71 548	41.18 559	30.42 549	28.83 552	61.42 551	14.88 554	56.40 552	14.13 557	26.37 555	37.16 550

VLMVS_CLIP		53.81 504	55.23 506	49.55 522	44.37 562	26.59 565	64.46 549	73.52 536	28.42 551	60.82 527	83.22 520	22.09 543	59.35 548	62.16 523	58.00 532	62.70 535

SIFT-PCN-Cal		36.85 519	36.40 522	38.19 536	71.43 554	30.42 563	64.34 550	37.72 561	27.48 553	22.98 555	57.03 552	12.99 558	51.22 555	12.51 559	21.13 557	32.92 553

MVS_clip		51.49 505	54.55 508	42.29 534	67.55 558	32.35 561	60.25 551	21.09 564	22.72 555	71.30 515	91.13 506	33.91 534	28.07 559	61.97 524	61.05 528	66.44 534

SIFT-NCMNet		32.45 520	31.84 524	34.30 537	68.74 557	28.10 564	57.85 552	24.54 563	27.25 554	19.31 558	52.59 554	9.75 563	45.69 557	10.92 561	15.56 559	29.13 555

VLMVS		37.31 518	39.19 519	31.67 538	40.61 563	24.46 566	44.56 553	28.63 562	5.66 559	51.94 538	71.15 539	25.03 541	27.90 560	33.30 542	51.87 536	42.64 540

MVS_baseline		19.65 525	22.57 528	10.89 542	26.60 564	2.25 569	14.08 554	3.93 568	1.15 561	37.00 548	69.35 540	4.91 565	0.00 563	17.88 545	28.24 552	30.42 554

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	0.00 563	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	0.00 563	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	0.00 563	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	0.00 563	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	0.00 563	0.00 562	0.00 562	0.00 559

cdsmvs_eth3d_5k		23.98 522	31.98 523	0.00 543	0.00 567	0.00 570	0.00 555	98.59 173	0.00 562	0.00 563	98.61 217	90.60 209	0.00 563	0.00 562	0.00 562	0.00 559

pcd_1.5k_mvsjas		7.88 527	10.50 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	94.51 93	0.00 563	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	0.00 563	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	0.00 563	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	0.00 563	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	0.00 563	0.00 562	0.00 562	0.00 559

ab-mvs-re		8.20 526	10.94 529	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	98.43 237	0.00 566	0.00 563	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	0.00 563	0.00 562	0.00 562	0.00 559

Meshroom													0.00 563
: In preparation.
AliceVision / Meshro													0.00 563
: In preparation.
AliceVision_Meshroom													0.00 563
: In preparation.
PatchmatchNet1														80.13 489	90.51 397	95.88 451
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													97.78 446
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
test-260524					99.64 33	99.18 10		98.83 99		99.13 70		96.51 28	99.92 44	99.03 34	99.80 26

WAC-MVS						90.94 407								88.66 438

MSC_two_6792asdad				99.62 7	99.17 113	99.08 13		98.63 163					99.94 15	98.53 57	99.80 26	99.86 14

PC_three_1452									95.08 221	99.60 34	99.16 111	97.86 2	98.47 364	97.52 144	99.72 68	99.74 51

No_MVS				99.62 7	99.17 113	99.08 13		98.63 163					99.94 15	98.53 57	99.80 26	99.86 14

test_one_0601					99.66 31	99.25 2		98.86 91	97.55 50	99.20 61	99.47 38	97.57 7

eth-test2					0.00 567

eth-test					0.00 567

ZD-MVS					99.46 59	98.70 29		98.79 121	93.21 337	98.67 108	98.97 157	95.70 54	99.83 92	96.07 218	99.58 99

IU-MVS					99.71 24	99.23 7		98.64 160	95.28 204	99.63 33				98.35 74	99.81 17	99.83 20

test_241102_TWO								98.87 85	97.65 42	99.53 39	99.48 36	97.34 12	99.94 15	98.43 69	99.80 26	99.83 20

test_241102_ONE					99.71 24	99.24 5		98.87 85	97.62 44	99.73 24	99.39 51	97.53 8	99.74 136

test_0728_THIRD									97.32 66	99.45 41	99.46 43	97.88 1	99.94 15	98.47 65	99.86 2	99.85 17

GSMVS																99.20 193

test_part2					99.63 35	99.18 10				99.27 58

sam_mvs1												89.45 245				99.20 193

sam_mvs												88.99 261

MTGPA								98.74 131

test_post											31.83 558	88.83 270	98.91 318

patchmatchnet-post											95.10 462	89.42 246	98.89 322

gm-plane-assit					95.88 435	87.47 475			89.74 440		96.94 391		99.19 255	93.32 328

test9_res														96.39 212	99.57 100	99.69 72

agg_prior2														95.87 228	99.57 100	99.68 77

agg_prior					99.30 85	98.38 43		98.72 136		97.57 212			99.81 104

TestCases				96.99 273	99.25 98	93.21 355		98.18 304	91.36 404	93.52 371	98.77 198	84.67 365	99.72 139	89.70 422	97.87 243	98.02 317

test_prior				99.19 52	99.31 81	98.22 60		98.84 97					99.70 145			99.65 85

新几何1				99.16 57	99.34 73	98.01 73		98.69 144	90.06 434	98.13 143	98.95 164	94.60 91	99.89 70	91.97 378	99.47 123	99.59 96

旧先验1					99.29 90	97.48 92		98.70 142			99.09 136	95.56 57			99.47 123	99.61 92

原ACMM1				98.65 99	99.32 79	96.62 143		98.67 152	93.27 336	97.81 182	98.97 157	95.18 78	99.83 92	93.84 313	99.46 126	99.50 109

testdata2													99.89 70	91.65 387

segment_acmp												96.85 16

testdata				98.26 144	99.20 111	95.36 241		98.68 147	91.89 389	98.60 117	99.10 128	94.44 98	99.82 99	94.27 297	99.44 127	99.58 100

test12				99.18 54	99.16 117	98.19 62		98.53 190		98.07 149		95.13 81	99.72 139		99.56 108	99.63 90

plane_prior7					97.42 344	94.63 283

plane_prior6					97.35 351	94.61 286						87.09 314

plane_prior5								98.56 184					99.03 295	96.07 218	94.27 330	96.92 355

plane_prior4											98.28 257

plane_prior3						94.61 286			97.02 90	95.34 295

plane_prior1					97.37 350

n2								0.00 569

nn								0.00 569

door-mid								94.37 495

lessismore_v0				94.45 435	94.93 461	88.44 465		91.03 517		86.77 479	97.64 321	76.23 459	98.42 370	90.31 410	85.64 458	96.51 423

LGP-MVS_train				96.47 332	97.46 339	93.54 331		98.54 188	94.67 250	94.36 328	98.77 198	85.39 347	99.11 276	95.71 237	94.15 336	96.76 377

test11								98.66 155

door								94.64 493

HQP5-MVS						94.25 305

BP-MVS														95.30 253

HQP4-MVS										94.45 320			98.96 309			96.87 367

HQP3-MVS								98.46 209							94.18 334

HQP2-MVS												86.75 320

NP-MVS					97.28 353	94.51 291					97.73 308

ACMMP++_ref															92.97 364

ACMMP++															93.61 351

Test By Simon												94.64 90

ITE_SJBPF				95.44 393	97.42 344	91.32 401		97.50 387	95.09 220	93.59 366	98.35 247	81.70 401	98.88 324	89.71 421	93.39 357	96.12 444

DeepMVS_CX				86.78 483	97.09 369	72.30 517		95.17 486	75.92 510	84.34 492	95.19 460	70.58 482	95.35 493	79.98 493	89.04 423	92.68 501

High-resolution multi-view benchmark