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 4	98.89 6	99.64 4	99.17 111	99.23 7	99.69 1	98.88 78	97.32 65	99.53 38	99.47 37	97.81 3	99.94 14	98.47 63	99.72 66	99.74 50

FOURS1					99.82 1	98.66 29	99.69 1	98.95 61	97.46 57	99.39 46

CS-MVS		98.44 57	98.49 36	98.31 137	99.08 126	96.73 138	99.67 3	98.47 206	97.17 80	98.94 78	99.10 122	95.73 51	99.13 261	98.71 44	99.49 117	99.09 209

SPE-MVS-test		98.49 51	98.50 34	98.46 123	99.20 109	97.05 124	99.64 4	98.50 199	97.45 58	98.88 85	99.14 111	95.25 72	99.15 256	98.83 40	99.56 106	99.20 185

EC-MVSNet		98.21 79	98.11 76	98.49 120	98.34 215	97.26 111	99.61 5	98.43 226	96.78 101	98.87 86	98.84 174	93.72 108	99.01 289	98.91 37	99.50 115	99.19 189

HPM-MVS		98.36 66	98.10 77	99.13 59	99.74 12	97.82 80	99.53 6	98.80 114	94.63 243	98.61 112	98.97 150	95.13 79	99.77 129	97.65 118	99.83 13	99.79 29
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MVSFormer		97.57 117	97.49 105	97.84 195	98.07 262	95.76 209	99.47 7	98.40 234	94.98 220	98.79 93	98.83 178	92.34 129	98.41 363	96.91 170	99.59 94	99.34 148

test_djsdf		96.00 220	95.69 225	96.93 270	95.72 424	95.49 222	99.47 7	98.40 234	94.98 220	94.58 301	97.86 285	89.16 245	98.41 363	96.91 170	94.12 324	96.88 351

HPM-MVS_fast		98.38 63	98.13 74	99.12 61	99.75 6	97.86 75	99.44 9	98.82 101	94.46 255	98.94 78	99.20 92	95.16 77	99.74 134	97.58 127	99.85 6	99.77 40

lecture		98.95 9	98.78 14	99.45 19	99.75 6	98.63 31	99.43 10	99.38 8	97.60 46	99.58 34	99.47 37	95.36 64	99.93 34	98.87 38	99.57 98	99.78 33

nrg030		96.28 211	95.72 219	97.96 189	96.90 367	98.15 64	99.39 11	98.31 264	95.47 181	94.42 311	98.35 237	92.09 143	98.69 328	97.50 139	89.05 407	97.04 333

APDe-MVS		99.02 8	98.84 10	99.55 11	99.57 39	98.96 18	99.39 11	98.93 65	97.38 62	99.41 44	99.54 20	96.66 20	99.84 88	98.86 39	99.85 6	99.87 12
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
3Dnovator+	94.38 6	97.43 135	96.78 166	99.38 24	97.83 293	98.52 34	99.37 13	98.71 137	97.09 87	92.99 380	99.13 114	89.36 239	99.89 68	96.97 166	99.57 98	99.71 63

FIs		96.51 198	96.12 201	97.67 216	97.13 353	97.54 88	99.36 14	99.22 32	95.89 148	94.03 334	98.35 237	91.98 146	98.44 354	96.40 199	92.76 354	97.01 334

FC-MVSNet-test		96.42 201	96.05 203	97.53 228	96.95 362	97.27 106	99.36 14	99.23 27	95.83 153	93.93 337	98.37 235	92.00 145	98.32 375	96.02 212	92.72 355	97.00 335

3Dnovator	94.51 5	97.46 130	96.93 155	99.07 65	97.78 296	97.64 82	99.35 16	99.06 47	97.02 89	93.75 350	99.16 107	89.25 242	99.92 43	97.22 159	99.75 53	99.64 86

sasdasda		97.67 105	97.23 129	98.98 73	98.70 166	98.38 41	99.34 17	98.39 240	96.76 103	97.67 187	97.40 330	92.26 133	99.49 191	98.28 79	96.28 293	99.08 213

GeoE		96.58 195	96.07 202	98.10 168	98.35 210	95.89 197	99.34 17	98.12 307	93.12 330	96.09 267	98.87 170	89.71 226	98.97 291	92.95 328	98.08 225	99.43 128

canonicalmvs		97.67 105	97.23 129	98.98 73	98.70 166	98.38 41	99.34 17	98.39 240	96.76 103	97.67 187	97.40 330	92.26 133	99.49 191	98.28 79	96.28 293	99.08 213

CP-MVS		98.57 41	98.36 46	99.19 51	99.66 31	97.86 75	99.34 17	98.87 85	95.96 145	98.60 113	99.13 114	96.05 40	99.94 14	97.77 107	99.86 2	99.77 40

EPP-MVSNet		97.46 130	97.28 122	97.99 182	98.64 177	95.38 232	99.33 21	98.31 264	93.61 307	97.19 213	99.07 137	94.05 103	99.23 243	96.89 174	98.43 198	99.37 141

MED-MVS test				99.52 14	99.77 2	98.86 23	99.32 22	99.24 20	96.41 123	99.30 52	99.35 62		99.92 43	98.30 75	99.80 25	99.79 29

MED-MVS		99.12 1	98.97 4	99.56 9	99.77 2	98.86 23	99.32 22	99.24 20	97.87 31	99.30 52	99.54 20	97.61 6	99.92 43	98.30 75	99.80 25	99.90 5

TestfortrainingZip a		99.05 6	98.85 9	99.65 2	99.77 2	99.13 11	99.32 22	99.01 52	97.87 31	99.74 21	99.54 20	96.71 18	99.92 43	98.35 72	99.33 139	99.90 5

TestfortrainingZip				99.43 21	99.13 119	99.06 15	99.32 22	98.57 178	96.88 97	99.42 43	99.05 139	96.54 24	99.73 136		98.59 180	99.51 104

MGCFI-Net		97.62 111	97.19 132	98.92 79	98.66 173	98.20 59	99.32 22	98.38 246	96.69 109	97.58 200	97.42 329	92.10 142	99.50 190	98.28 79	96.25 296	99.08 213

balanced_ft_v1		97.54 123	97.38 115	98.02 178	98.34 215	95.58 215	99.32 22	98.40 234	95.88 149	98.43 126	98.65 207	88.95 257	99.59 167	98.94 35	99.48 120	98.90 235

XVS		98.70 24	98.49 36	99.34 32	99.70 27	98.35 50	99.29 28	98.88 78	97.40 59	98.46 119	99.20 92	95.90 48	99.89 68	97.85 102	99.74 57	99.78 33

X-MVStestdata		94.06 358	92.30 384	99.34 32	99.70 27	98.35 50	99.29 28	98.88 78	97.40 59	98.46 119	43.50 498	95.90 48	99.89 68	97.85 102	99.74 57	99.78 33

tttt0517		96.07 217	95.51 231	97.78 201	98.41 200	94.84 263	99.28 30	94.33 477	94.26 262	97.64 193	98.64 208	84.05 367	99.47 200	95.34 238	97.60 244	99.03 221

mPP-MVS		98.51 49	98.26 62	99.25 45	99.75 6	98.04 69	99.28 30	98.81 107	96.24 131	98.35 130	99.23 86	95.46 58	99.94 14	97.42 148	99.81 16	99.77 40

test_vis1_n		95.47 250	95.13 251	96.49 317	97.77 297	90.41 411	99.27 32	98.11 310	96.58 114	99.66 29	99.18 102	67.00 476	99.62 164	99.21 28	99.40 131	99.44 126

test_fmvs1_n		95.90 228	95.99 209	95.63 373	98.67 172	88.32 454	99.26 33	98.22 286	96.40 124	99.67 28	99.26 80	73.91 461	99.70 143	99.02 33	99.50 115	98.87 237

MSP-MVS		98.74 22	98.55 29	99.29 39	99.75 6	98.23 57	99.26 33	98.88 78	97.52 50	99.41 44	98.78 187	96.00 42	99.79 121	97.79 106	99.59 94	99.85 16
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
v7n		94.19 345	93.43 358	96.47 320	95.90 419	94.38 287	99.26 33	98.34 256	91.99 370	92.76 385	97.13 349	88.31 272	98.52 345	89.48 413	87.70 421	96.52 406

MVSMamba_PlusPlus		98.31 73	98.19 73	98.67 96	98.96 141	97.36 97	99.24 36	98.57 178	94.81 231	98.99 76	98.90 166	95.22 75	99.59 167	99.15 29	99.84 11	99.07 217

WR-MVS_H		95.05 282	94.46 287	96.81 279	96.86 369	95.82 204	99.24 36	99.24 20	93.87 282	92.53 394	96.84 386	90.37 209	98.24 385	93.24 317	87.93 419	96.38 420

HFP-MVS		98.63 29	98.40 42	99.32 38	99.72 17	98.29 53	99.23 38	98.96 60	96.10 139	98.94 78	99.17 104	96.06 39	99.92 43	97.62 120	99.78 39	99.75 48

region2R		98.61 31	98.38 44	99.29 39	99.74 12	98.16 63	99.23 38	98.93 65	96.15 135	98.94 78	99.17 104	95.91 46	99.94 14	97.55 132	99.79 34	99.78 33

ACMMPR		98.59 34	98.36 46	99.29 39	99.74 12	98.15 64	99.23 38	98.95 61	96.10 139	98.93 82	99.19 99	95.70 52	99.94 14	97.62 120	99.79 34	99.78 33

QAPM		96.29 209	95.40 233	98.96 76	97.85 292	97.60 85	99.23 38	98.93 65	89.76 423	93.11 377	99.02 142	89.11 247	99.93 34	91.99 363	99.62 89	99.34 148

MP-MVS		98.33 72	98.01 82	99.28 42	99.75 6	98.18 61	99.22 42	98.79 119	96.13 136	97.92 163	99.23 86	94.54 90	99.94 14	96.74 189	99.78 39	99.73 55
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
Vis-MVSNet		97.42 136	97.11 141	98.34 135	98.66 173	96.23 167	99.22 42	99.00 53	96.63 113	98.04 146	99.21 90	88.05 283	99.35 212	96.01 213	99.21 145	99.45 123
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CSCG		97.85 94	97.74 91	98.20 149	99.67 30	95.16 244	99.22 42	99.32 12	93.04 333	97.02 223	98.92 164	95.36 64	99.91 56	97.43 146	99.64 85	99.52 101

mmtdpeth		93.12 380	92.61 376	94.63 413	97.60 312	89.68 427	99.21 45	97.32 394	94.02 270	97.72 183	94.42 450	77.01 439	99.44 203	99.05 31	77.18 474	94.78 461

SDMVSNet		96.85 178	96.42 186	98.14 157	99.30 83	96.38 159	99.21 45	99.23 27	95.92 146	95.96 273	98.76 195	85.88 327	99.44 203	97.93 96	95.59 308	98.60 272

OpenMVS	93.04 13	95.83 232	95.00 258	98.32 136	97.18 350	97.32 99	99.21 45	98.97 57	89.96 419	91.14 422	99.05 139	86.64 310	99.92 43	93.38 313	99.47 121	97.73 313

DTE-MVSNet		93.98 360	93.26 363	96.14 341	96.06 410	94.39 286	99.20 48	98.86 91	93.06 332	91.78 415	97.81 293	85.87 328	97.58 439	90.53 393	86.17 437	96.46 417

Vis-MVSNet (Re-imp)		96.87 177	96.55 180	97.83 196	98.73 161	95.46 224	99.20 48	98.30 271	94.96 222	96.60 247	98.87 170	90.05 216	98.59 340	93.67 307	98.60 179	99.46 121

test_fmvs2		93.43 368	93.58 350	92.95 445	96.97 361	83.91 473	99.19 50	97.24 402	95.74 157	95.20 287	98.27 249	69.65 468	98.72 327	96.26 203	93.73 333	96.24 426

BridgeMVS		98.45 56	98.35 48	98.74 90	98.65 176	97.55 86	99.19 50	98.60 164	96.72 108	99.35 48	98.77 190	95.06 82	99.55 181	98.95 34	99.87 1	99.12 201

ZNCC-MVS		98.49 51	98.20 71	99.35 31	99.73 16	98.39 40	99.19 50	98.86 91	95.77 156	98.31 133	99.10 122	95.46 58	99.93 34	97.57 131	99.81 16	99.74 50

IS-MVSNet		97.22 155	96.88 157	98.25 143	98.85 154	96.36 161	99.19 50	97.97 330	95.39 187	97.23 211	98.99 149	91.11 187	98.93 301	94.60 272	98.59 180	99.47 116

mvsmamba		97.25 153	96.99 151	98.02 178	98.34 215	95.54 220	99.18 54	97.47 379	95.04 213	98.15 134	98.57 217	89.46 234	99.31 220	97.68 117	99.01 155	99.22 182

PEN-MVS		94.42 330	93.73 343	96.49 317	96.28 399	94.84 263	99.17 55	99.00 53	93.51 310	92.23 406	97.83 291	86.10 323	97.90 421	92.55 349	86.92 432	96.74 366

PS-MVSNAJss		96.43 200	96.26 195	96.92 273	95.84 422	95.08 249	99.16 56	98.50 199	95.87 151	93.84 345	98.34 241	94.51 91	98.61 336	96.88 176	93.45 341	97.06 332

BP-MVS1		97.82 96	97.51 104	98.76 89	98.25 235	97.39 96	99.15 57	97.68 352	96.69 109	98.47 118	99.10 122	90.29 212	99.51 187	98.60 50	99.35 136	99.37 141

dcpmvs_2		98.08 82	98.59 25	96.56 308	99.57 39	90.34 414	99.15 57	98.38 246	96.82 100	99.29 54	99.49 34	95.78 50	99.57 171	98.94 35	99.86 2	99.77 40

APD-MVS_3200maxsize		98.53 46	98.33 58	99.15 57	99.50 48	97.92 74	99.15 57	98.81 107	96.24 131	99.20 60	99.37 56	95.30 68	99.80 109	97.73 109	99.67 74	99.72 59

TSAR-MVS + MP.		98.78 20	98.62 22	99.24 46	99.69 29	98.28 54	99.14 60	98.66 153	96.84 98	99.56 35	99.31 71	96.34 32	99.70 143	98.32 74	99.73 61	99.73 55
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
anonymousdsp		95.42 256	94.91 263	96.94 269	95.10 441	95.90 192	99.14 60	98.41 231	93.75 288	93.16 373	97.46 323	87.50 296	98.41 363	95.63 231	94.03 326	96.50 412

jajsoiax		95.45 253	95.03 257	96.73 284	95.42 437	94.63 273	99.14 60	98.52 191	95.74 157	93.22 370	98.36 236	83.87 372	98.65 333	96.95 168	94.04 325	96.91 347

PS-CasMVS		94.67 309	93.99 322	96.71 287	96.68 381	95.26 239	99.13 63	99.03 50	93.68 299	92.33 404	97.95 276	85.35 337	98.10 396	93.59 309	88.16 418	96.79 361

RRT-MVS		97.03 168	96.78 166	97.77 204	97.90 289	94.34 289	99.12 64	98.35 253	95.87 151	98.06 142	98.70 201	86.45 315	99.63 160	98.04 92	98.54 186	99.35 146

CPTT-MVS		97.72 101	97.32 120	98.92 79	99.64 33	97.10 122	99.12 64	98.81 107	92.34 359	98.09 139	99.08 133	93.01 117	99.92 43	96.06 210	99.77 41	99.75 48

SR-MVS-dyc-post		98.54 45	98.35 48	99.13 59	99.49 52	97.86 75	99.11 66	98.80 114	96.49 118	99.17 63	99.35 62	95.34 66	99.82 97	97.72 110	99.65 80	99.71 63

RE-MVS-def			98.34 54		99.49 52	97.86 75	99.11 66	98.80 114	96.49 118	99.17 63	99.35 62	95.29 69		97.72 110	99.65 80	99.71 63

CP-MVSNet		94.94 295	94.30 296	96.83 277	96.72 379	95.56 217	99.11 66	98.95 61	93.89 280	92.42 400	97.90 281	87.19 301	98.12 395	94.32 283	88.21 416	96.82 360

SteuartSystems-ACMMP		98.90 15	98.75 17	99.36 30	99.22 106	98.43 39	99.10 69	98.87 85	97.38 62	99.35 48	99.40 49	97.78 5	99.87 79	97.77 107	99.85 6	99.78 33
Skip Steuart: Steuart Systems R&D Blog.
SR-MVS		98.57 41	98.35 48	99.24 46	99.53 42	98.18 61	99.09 70	98.82 101	96.58 114	99.10 69	99.32 69	95.39 61	99.82 97	97.70 115	99.63 87	99.72 59

GST-MVS		98.43 59	98.12 75	99.34 32	99.72 17	98.38 41	99.09 70	98.82 101	95.71 160	98.73 99	99.06 138	95.27 70	99.93 34	97.07 163	99.63 87	99.72 59

K. test v3		92.55 388	91.91 391	94.48 419	95.64 426	89.24 435	99.07 72	94.88 471	94.04 268	86.78 460	97.59 314	77.64 432	97.64 435	92.08 358	89.43 402	96.57 396

test2506		94.44 329	93.91 327	96.04 345	99.02 131	88.99 441	99.06 73	79.47 503	96.96 93	98.36 128	99.26 80	77.21 434	99.52 186	96.78 187	99.04 152	99.59 94

test0726					99.72 17	99.25 2	99.06 73	98.88 78	97.62 43	99.56 35	99.50 31	97.42 10

GDP-MVS		97.64 108	97.28 122	98.71 93	98.30 224	97.33 98	99.05 75	98.52 191	96.34 128	98.80 92	99.05 139	89.74 225	99.51 187	96.86 182	98.86 165	99.28 169

test_vis1_n_1920		96.71 186	96.84 160	96.31 335	99.11 123	89.74 423	99.05 75	98.58 176	98.08 24	99.87 4	99.37 56	78.48 419	99.93 34	99.29 27	99.69 71	99.27 170

test_fmvs3		87.17 440	87.06 443	87.50 461	91.21 479	75.66 486	99.05 75	96.61 443	92.79 343	88.85 448	92.78 468	43.72 492	93.49 484	93.95 297	84.56 444	93.34 478

v8		94.47 327	93.77 339	96.57 307	96.36 396	94.83 265	99.05 75	98.19 291	91.92 372	93.16 373	96.97 373	88.82 262	98.48 347	91.69 371	87.79 420	96.39 419

test1111		95.94 225	95.78 216	96.41 327	98.99 138	90.12 416	99.04 79	92.45 489	96.99 92	98.03 147	99.27 79	81.40 391	99.48 196	96.87 179	99.04 152	99.63 88

SF-MVS		98.59 34	98.32 59	99.41 23	99.54 41	98.71 27	99.04 79	98.81 107	95.12 207	99.32 51	99.39 50	96.22 33	99.84 88	97.72 110	99.73 61	99.67 79

PHI-MVS		98.34 70	98.06 78	99.18 53	99.15 118	98.12 67	99.04 79	99.09 44	93.32 319	98.83 91	99.10 122	96.54 24	99.83 90	97.70 115	99.76 47	99.59 94

ECVR-MVS		95.95 222	95.71 222	96.65 293	99.02 131	90.86 397	99.03 82	91.80 490	96.96 93	98.10 138	99.26 80	81.31 392	99.51 187	96.90 173	99.04 152	99.59 94

TranMVSNet+NR-MVSNet		95.14 276	94.48 285	97.11 255	96.45 393	96.36 161	99.03 82	99.03 50	95.04 213	93.58 354	97.93 278	88.27 275	98.03 410	94.13 291	86.90 433	96.95 339

ACMMP		98.23 76	97.95 84	99.09 63	99.74 12	97.62 84	99.03 82	99.41 6	95.98 144	97.60 198	99.36 60	94.45 95	99.93 34	97.14 160	98.85 167	99.70 67
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
SED-MVS		99.09 2	98.91 5	99.63 5	99.71 24	99.24 5	99.02 85	98.87 85	97.65 41	99.73 23	99.48 35	97.53 8	99.94 14	98.43 67	99.81 16	99.70 67

OPU-MVS				99.37 28	99.24 103	99.05 16	99.02 85				99.16 107	97.81 3	99.37 211	97.24 157	99.73 61	99.70 67

EIA-MVS		97.75 99	97.58 96	98.27 139	98.38 205	96.44 155	99.01 87	98.60 164	95.88 149	97.26 209	97.53 320	94.97 84	99.33 215	97.38 153	99.20 146	99.05 218

Anonymous20231211		94.10 354	93.26 363	96.61 301	99.11 123	94.28 292	99.01 87	98.88 78	86.43 457	92.81 383	97.57 316	81.66 390	98.68 331	94.83 256	89.02 409	96.88 351

test_cas_vis1_n_1920		97.38 139	97.36 117	97.45 231	98.95 142	93.25 341	99.00 89	98.53 188	97.70 39	99.77 18	99.35 62	84.71 352	99.85 84	98.57 52	99.66 77	99.26 176

mvs_tets		95.41 258	95.00 258	96.65 293	95.58 428	94.42 284	99.00 89	98.55 184	95.73 159	93.21 371	98.38 234	83.45 378	98.63 334	97.09 162	94.00 327	96.91 347

baseline		97.64 108	97.44 110	98.25 143	98.35 210	96.20 168	99.00 89	98.32 260	96.33 130	98.03 147	99.17 104	91.35 171	99.16 252	98.10 87	98.29 213	99.39 136

KinetiMVS		97.48 126	97.05 146	98.78 87	98.37 208	97.30 102	98.99 92	98.70 140	97.18 79	99.02 71	99.01 146	87.50 296	99.67 150	95.33 239	99.33 139	99.37 141

v10		94.29 338	93.55 352	96.51 315	96.39 395	94.80 267	98.99 92	98.19 291	91.35 390	93.02 379	96.99 371	88.09 280	98.41 363	90.50 394	88.41 415	96.33 423

PGM-MVS		98.49 51	98.23 67	99.27 44	99.72 17	98.08 68	98.99 92	99.49 5	95.43 183	99.03 70	99.32 69	95.56 55	99.94 14	96.80 186	99.77 41	99.78 33

LPG-MVS_test		95.62 244	95.34 239	96.47 320	97.46 326	93.54 319	98.99 92	98.54 186	94.67 241	94.36 314	98.77 190	85.39 335	99.11 266	95.71 226	94.15 322	96.76 364

fmvsm_s_conf0.5_n_11		98.58 36	98.57 26	98.62 100	99.42 64	97.16 118	98.97 96	98.86 91	98.91 4	99.87 4	99.66 3	91.82 152	99.95 9	99.82 6	99.82 14	98.75 253

test_fmvsmvis_n_1920		98.44 57	98.51 32	98.23 146	98.33 219	96.15 171	98.97 96	99.15 41	98.55 16	98.45 122	99.55 18	94.26 100	99.97 1	99.65 18	99.66 77	98.57 278

DVP-MVS		99.03 7	98.83 11	99.63 5	99.72 17	99.25 2	98.97 96	98.58 176	97.62 43	99.45 40	99.46 42	97.42 10	99.94 14	98.47 63	99.81 16	99.69 70
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 96	98.88 78					99.94 14	98.47 63	99.81 16	99.84 18

tfpnnormal		93.66 363	92.70 374	96.55 312	96.94 363	95.94 186	98.97 96	99.19 35	91.04 401	91.38 420	97.34 333	84.94 345	98.61 336	85.45 449	89.02 409	95.11 452

V42		94.78 301	94.14 309	96.70 289	96.33 398	95.22 242	98.97 96	98.09 317	92.32 361	94.31 317	97.06 361	88.39 271	98.55 342	92.90 330	88.87 411	96.34 421

test_fmvsm_n_1920		98.87 18	99.01 3	98.45 124	99.42 64	96.43 156	98.96 102	99.36 10	98.63 13	99.86 8	99.51 28	95.91 46	99.97 1	99.72 14	99.75 53	98.94 231

test_fmvsmconf0.01_n		97.86 92	97.54 102	98.83 84	95.48 433	96.83 133	98.95 103	98.60 164	98.58 14	98.93 82	99.55 18	88.57 265	99.91 56	99.54 24	99.61 90	99.77 40

SMA-MVS		98.58 36	98.25 63	99.56 9	99.51 46	99.04 17	98.95 103	98.80 114	93.67 301	99.37 47	99.52 25	96.52 26	99.89 68	98.06 89	99.81 16	99.76 47
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		93.94 361	93.06 366	96.59 304	96.49 390	95.16 244	98.95 103	98.03 327	92.32 361	91.08 423	97.84 288	84.54 357	98.41 363	92.16 356	86.13 440	96.19 429

NormalMVS		98.07 84	97.90 87	98.59 104	99.75 6	96.60 144	98.94 106	98.60 164	97.86 33	98.71 102	99.08 133	91.22 179	99.80 109	97.40 150	99.57 98	99.37 141

SymmetryMVS		97.84 95	97.58 96	98.62 100	99.01 133	96.60 144	98.94 106	98.44 215	97.86 33	98.71 102	99.08 133	91.22 179	99.80 109	97.40 150	97.53 252	99.47 116

AstraMVS		97.34 147	97.24 128	97.65 220	98.13 256	94.15 299	98.94 106	96.25 451	97.47 56	98.60 113	99.28 76	89.67 227	99.41 206	98.73 43	98.07 226	99.38 140

reproduce_model		98.94 10	98.81 12	99.34 32	99.52 45	98.26 55	98.94 106	98.84 96	98.06 25	99.35 48	99.61 5	96.39 31	99.94 14	98.77 42	99.82 14	99.83 19

Anonymous20240521		91.18 403	90.44 401	93.42 435	93.70 459	88.47 451	98.94 106	97.56 366	88.46 441	89.56 441	95.08 445	77.15 437	96.97 450	83.92 459	89.55 398	94.82 458

VPA-MVSNet		95.75 236	95.11 254	97.69 212	97.24 342	97.27 106	98.94 106	99.23 27	95.13 206	95.51 280	97.32 336	85.73 329	98.91 304	97.33 155	89.55 398	96.89 350

casdiffseed414692147		96.97 172	96.55 180	98.25 143	98.26 233	96.28 166	98.93 112	98.33 258	94.99 218	96.87 231	99.09 130	88.97 255	99.07 274	95.70 228	97.77 237	99.39 136

MM		98.51 49	98.24 65	99.33 36	99.12 121	98.14 66	98.93 112	97.02 421	98.96 1	99.17 63	99.47 37	91.97 148	99.94 14	99.85 5	99.69 71	99.91 4

LS3D		97.16 162	96.66 175	98.68 95	98.53 186	97.19 116	98.93 112	98.90 73	92.83 342	95.99 271	99.37 56	92.12 141	99.87 79	93.67 307	99.57 98	98.97 227

MonoMVSNet		95.51 248	95.45 232	95.68 370	95.54 429	90.87 396	98.92 115	97.37 391	95.79 155	95.53 279	97.38 332	89.58 229	97.68 433	96.40 199	92.59 356	98.49 282

casdiffmvs_mvg		97.72 101	97.48 107	98.44 126	98.42 198	96.59 148	98.92 115	98.44 215	96.20 133	97.76 177	99.20 92	91.66 158	99.23 243	98.27 82	98.41 204	99.49 112
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	95.69 241	95.38 237	96.61 301	97.61 311	93.84 308	98.91 117	98.44 215	95.25 197	94.28 320	98.47 225	86.04 326	99.12 264	95.50 235	93.95 329	96.87 354
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MTAPA		98.58 36	98.29 61	99.46 18	99.76 5	98.64 30	98.90 118	98.74 129	97.27 73	98.02 149	99.39 50	94.81 87	99.96 4	97.91 98	99.79 34	99.77 40

SD-MVS		98.64 28	98.68 19	98.53 113	99.33 74	98.36 49	98.90 118	98.85 95	97.28 69	99.72 26	99.39 50	96.63 22	97.60 437	98.17 84	99.85 6	99.64 86
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)		92.67 386	91.51 393	96.15 340	96.58 385	94.65 271	98.90 118	96.73 436	90.86 404	89.46 442	97.86 285	85.62 332	98.09 400	86.45 441	81.12 460	95.71 441

EPNet		97.28 150	96.87 158	98.51 115	94.98 442	96.14 172	98.90 118	97.02 421	98.28 21	95.99 271	99.11 120	91.36 170	99.89 68	96.98 165	99.19 147	99.50 107
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
guyue		97.57 117	97.37 116	98.20 149	98.50 187	95.86 199	98.89 122	97.03 418	97.29 67	98.73 99	98.90 166	89.41 237	99.32 216	98.68 45	98.86 165	99.42 131

fmvsm_l_conf0.5_n_3		98.90 15	98.74 18	99.37 28	99.36 68	98.25 56	98.89 122	99.24 20	98.77 10	99.89 3	99.59 13	93.39 112	99.96 4	99.78 10	99.76 47	99.89 8

fmvsm_l_conf0.5_n		99.07 5	99.05 2	99.14 58	99.41 66	97.54 88	98.89 122	99.31 13	98.49 17	99.86 8	99.42 46	96.45 28	99.96 4	99.86 1	99.74 57	99.90 5

fmvsm_s_conf0.1_n_a		98.08 82	98.04 80	98.21 147	97.66 308	95.39 231	98.89 122	99.17 37	97.24 74	99.76 20	99.67 1	91.13 184	99.88 77	99.39 26	99.41 128	99.35 146

MTMP							98.89 122	94.14 480

UA-Net		97.96 87	97.62 94	98.98 73	98.86 151	97.47 92	98.89 122	99.08 45	96.67 111	98.72 101	99.54 20	93.15 116	99.81 102	94.87 254	98.83 168	99.65 83

OurMVSNet-221017-0		94.21 343	94.00 320	94.85 403	95.60 427	89.22 436	98.89 122	97.43 386	95.29 194	92.18 409	98.52 222	82.86 379	98.59 340	93.46 312	91.76 367	96.74 366

fmvsm_l_conf0.5_n_a		99.09 2	99.08 1	99.11 62	99.43 63	97.48 90	98.88 129	99.30 14	98.47 18	99.85 11	99.43 45	96.71 18	99.96 4	99.86 1	99.80 25	99.89 8

thisisatest0530		96.01 219	95.36 238	97.97 187	98.38 205	95.52 221	98.88 129	94.19 479	94.04 268	97.64 193	98.31 244	83.82 374	99.46 201	95.29 243	97.70 241	98.93 232

UGNet		96.78 182	96.30 193	98.19 152	98.24 236	95.89 197	98.88 129	98.93 65	97.39 61	96.81 235	97.84 288	82.60 381	99.90 64	96.53 194	99.49 117	98.79 244
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		97.37 141	97.16 135	97.98 183	98.30 224	95.41 226	98.87 132	98.45 211	95.56 169	97.84 169	99.19 99	90.39 207	99.25 232	97.61 123	98.22 217	99.29 163

E6new		97.37 141	97.16 135	97.98 183	98.28 230	95.40 229	98.87 132	98.45 211	95.55 174	97.84 169	99.20 92	90.44 205	99.25 232	97.61 123	98.22 217	99.29 163

E6		97.37 141	97.16 135	97.98 183	98.28 230	95.40 229	98.87 132	98.45 211	95.55 174	97.84 169	99.20 92	90.44 205	99.25 232	97.61 123	98.22 217	99.29 163

E5		97.37 141	97.16 135	97.98 183	98.30 224	95.41 226	98.87 132	98.45 211	95.56 169	97.84 169	99.19 99	90.39 207	99.25 232	97.61 123	98.22 217	99.29 163

testing3-2		95.45 253	95.34 239	95.77 368	98.69 169	88.75 445	98.87 132	97.21 405	96.13 136	97.22 212	97.68 305	77.95 427	99.65 154	97.58 127	96.77 273	98.91 234

fmvsm_s_conf0.1_n		98.18 80	98.21 69	98.11 167	98.54 185	95.24 241	98.87 132	99.24 20	97.50 52	99.70 27	99.67 1	91.33 172	99.89 68	99.47 25	99.54 109	99.21 184

Anonymous20240529		95.10 279	94.22 302	97.75 206	99.01 133	94.26 294	98.87 132	98.83 98	85.79 463	96.64 243	98.97 150	78.73 416	99.85 84	96.27 202	94.89 313	99.12 201

thres100view900		95.38 259	94.70 273	97.41 235	98.98 139	94.92 260	98.87 132	96.90 428	95.38 188	96.61 246	96.88 382	84.29 359	99.56 174	88.11 428	96.29 290	97.76 310

fmvsm_s_conf0.5_n_10		98.66 25	98.54 31	99.02 69	99.36 68	97.21 115	98.86 140	99.23 27	98.90 5	99.83 12	99.59 13	91.57 160	99.94 14	99.79 9	99.74 57	99.89 8

reproduce-ours		98.93 11	98.78 14	99.38 24	99.49 52	98.38 41	98.86 140	98.83 98	98.06 25	99.29 54	99.58 16	96.40 29	99.94 14	98.68 45	99.81 16	99.81 25

our_new_method		98.93 11	98.78 14	99.38 24	99.49 52	98.38 41	98.86 140	98.83 98	98.06 25	99.29 54	99.58 16	96.40 29	99.94 14	98.68 45	99.81 16	99.81 25

fmvsm_s_conf0.5_n_a		98.38 63	98.42 41	98.27 139	99.09 125	95.41 226	98.86 140	99.37 9	97.69 40	99.78 17	99.61 5	92.38 127	99.91 56	99.58 23	99.43 126	99.49 112

XXY-MVS		95.20 273	94.45 290	97.46 230	96.75 377	96.56 150	98.86 140	98.65 157	93.30 321	93.27 369	98.27 249	84.85 347	98.87 311	94.82 257	91.26 375	96.96 337

fmvsm_s_conf0.5_n		98.42 60	98.51 32	98.13 162	99.30 83	95.25 240	98.85 145	99.39 7	97.94 29	99.74 21	99.62 4	92.59 123	99.91 56	99.65 18	99.52 112	99.25 178

VDDNet		95.36 262	94.53 282	97.86 194	98.10 259	95.13 247	98.85 145	97.75 350	90.46 410	98.36 128	99.39 50	73.27 463	99.64 157	97.98 93	96.58 278	98.81 243

thres600view7		95.49 249	94.77 268	97.67 216	98.98 139	95.02 251	98.85 145	96.90 428	95.38 188	96.63 244	96.90 381	84.29 359	99.59 167	88.65 425	96.33 286	98.40 286

114514_t		96.93 174	96.27 194	98.92 79	99.50 48	97.63 83	98.85 145	98.90 73	84.80 467	97.77 176	99.11 120	92.84 119	99.66 153	94.85 255	99.77 41	99.47 116

test_fmvsmconf0.1_n		98.58 36	98.44 40	98.99 71	97.73 302	97.15 119	98.84 149	98.97 57	98.75 11	99.43 42	99.54 20	93.29 114	99.93 34	99.64 20	99.79 34	99.89 8

LFMVS		95.86 230	94.98 260	98.47 122	98.87 150	96.32 163	98.84 149	96.02 452	93.40 316	98.62 111	99.20 92	74.99 453	99.63 160	97.72 110	97.20 257	99.46 121

alignmvs		97.56 119	97.07 144	99.01 70	98.66 173	98.37 48	98.83 151	98.06 325	96.74 105	98.00 153	97.65 307	90.80 195	99.48 196	98.37 71	96.56 279	99.19 189

DeepC-MVS	95.98 3	97.88 91	97.58 96	98.77 88	99.25 96	96.93 128	98.83 151	98.75 127	96.96 93	96.89 230	99.50 31	90.46 204	99.87 79	97.84 104	99.76 47	99.52 101
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 13	98.87 7	99.04 68	98.88 147	97.25 112	98.82 153	99.34 11	98.75 11	99.80 14	99.61 5	95.16 77	99.95 9	99.70 17	99.80 25	99.93 1

sd_testset		96.17 214	95.76 217	97.42 234	99.30 83	94.34 289	98.82 153	99.08 45	95.92 146	95.96 273	98.76 195	82.83 380	99.32 216	95.56 232	95.59 308	98.60 272

ACMMP_NAP		98.61 31	98.30 60	99.55 11	99.62 35	98.95 19	98.82 153	98.81 107	95.80 154	99.16 67	99.47 37	95.37 63	99.92 43	97.89 100	99.75 53	99.79 29

casdiffmvs		97.63 110	97.41 112	98.28 138	98.33 219	96.14 172	98.82 153	98.32 260	96.38 126	97.95 158	99.21 90	91.23 178	99.23 243	98.12 86	98.37 206	99.48 114
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GBi-Net		94.49 324	93.80 336	96.56 308	98.21 240	95.00 252	98.82 153	98.18 294	92.46 352	94.09 330	97.07 357	81.16 394	97.95 417	92.08 358	92.14 361	96.72 369

test1		94.49 324	93.80 336	96.56 308	98.21 240	95.00 252	98.82 153	98.18 294	92.46 352	94.09 330	97.07 357	81.16 394	97.95 417	92.08 358	92.14 361	96.72 369

FMVSNet1		93.19 377	92.07 386	96.56 308	97.54 319	95.00 252	98.82 153	98.18 294	90.38 413	92.27 405	97.07 357	73.68 462	97.95 417	89.36 415	91.30 373	96.72 369

API-MVS		97.41 137	97.25 124	97.91 190	98.70 166	96.80 134	98.82 153	98.69 142	94.53 248	98.11 137	98.28 246	94.50 94	99.57 171	94.12 292	99.49 117	97.37 326

ACMH	92.88 16	94.55 317	93.95 324	96.34 333	97.63 310	93.26 339	98.81 161	98.49 204	93.43 315	89.74 437	98.53 219	81.91 385	99.08 273	93.69 304	93.30 347	96.70 373
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.5_n_8		98.73 23	98.62 22	99.05 67	99.35 70	97.27 106	98.80 162	99.23 27	98.93 3	99.79 15	99.59 13	92.34 129	99.95 9	99.82 6	99.71 68	99.92 2

fmvsm_s_conf0.5_n_3		98.53 46	98.45 39	98.79 86	99.23 104	97.32 99	98.80 162	99.26 16	98.82 7	99.87 4	99.60 10	90.95 193	99.93 34	99.76 11	99.73 61	99.12 201

reproduce_monomvs		94.77 302	94.67 275	95.08 393	98.40 202	89.48 431	98.80 162	98.64 158	97.57 48	93.21 371	97.65 307	80.57 404	98.83 317	97.72 110	89.47 401	96.93 341

test_fmvs1		96.42 201	96.67 174	95.66 372	98.82 156	88.53 450	98.80 162	98.20 289	96.39 125	99.64 31	99.20 92	80.35 406	99.67 150	99.04 32	99.57 98	98.78 248

Effi-MVS+-dtu		96.29 209	96.56 179	95.51 377	97.89 291	90.22 415	98.80 162	98.10 313	96.57 116	96.45 257	96.66 395	90.81 194	98.91 304	95.72 225	97.99 227	97.40 323

HQP_MVS		96.14 216	95.90 212	96.85 276	97.42 331	94.60 278	98.80 162	98.56 182	97.28 69	95.34 282	98.28 246	87.09 302	99.03 283	96.07 207	94.27 316	96.92 342

plane_prior2							98.80 162		97.28 69

APD-MVS		98.35 68	98.00 83	99.42 22	99.51 46	98.72 26	98.80 162	98.82 101	94.52 250	99.23 59	99.25 85	95.54 57	99.80 109	96.52 195	99.77 41	99.74 50
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
fmvsm_s_conf0.5_n_9		98.63 29	98.66 21	98.54 110	99.40 67	95.83 202	98.79 170	99.17 37	98.94 2	99.92 1	99.61 5	92.49 124	99.93 34	99.86 1	99.76 47	99.86 13

fmvsm_s_conf0.5_n_6		98.65 26	98.55 29	98.95 78	98.50 187	97.30 102	98.79 170	99.16 39	98.14 23	99.86 8	99.41 48	93.71 109	99.91 56	99.71 15	99.64 85	99.65 83

UniMVSNet (Re)		95.78 235	95.19 249	97.58 225	96.99 360	97.47 92	98.79 170	99.18 36	95.60 165	93.92 338	97.04 365	91.68 156	98.48 347	95.80 222	87.66 422	96.79 361

FMVSNet2		94.47 327	93.61 349	97.04 260	98.21 240	96.43 156	98.79 170	98.27 274	92.46 352	93.50 360	97.09 354	81.16 394	98.00 414	91.09 382	91.93 364	96.70 373

tt0805		94.54 318	93.85 333	96.63 298	97.98 282	93.06 350	98.77 174	97.84 339	93.67 301	93.80 347	98.04 267	76.88 441	98.96 295	94.79 259	92.86 352	97.86 309

fmvsm_s_conf0.5_n_4		98.35 68	98.50 34	97.90 191	99.16 115	95.08 249	98.75 175	99.24 20	98.39 19	99.81 13	99.52 25	92.35 128	99.90 64	99.74 13	99.51 114	98.71 259

testgi		93.06 381	92.45 382	94.88 401	96.43 394	89.90 419	98.75 175	97.54 372	95.60 165	91.63 419	97.91 280	74.46 458	97.02 449	86.10 443	93.67 334	97.72 314

LCM-MVSNet-Re		95.22 271	95.32 243	94.91 398	98.18 250	87.85 460	98.75 175	95.66 459	95.11 208	88.96 445	96.85 385	90.26 214	97.65 434	95.65 230	98.44 195	99.22 182

SixPastTwentyTwo		93.34 371	92.86 370	94.75 408	95.67 425	89.41 434	98.75 175	96.67 440	93.89 280	90.15 434	98.25 252	80.87 400	98.27 384	90.90 389	90.64 382	96.57 396

Elysia		96.64 189	96.02 206	98.51 115	98.04 269	97.30 102	98.74 179	98.60 164	95.04 213	97.91 164	98.84 174	83.59 376	99.48 196	94.20 288	99.25 143	98.75 253

StellarMVS		96.64 189	96.02 206	98.51 115	98.04 269	97.30 102	98.74 179	98.60 164	95.04 213	97.91 164	98.84 174	83.59 376	99.48 196	94.20 288	99.25 143	98.75 253

UniMVSNet_ETH3D		94.24 342	93.33 360	96.97 267	97.19 349	93.38 330	98.74 179	98.57 178	91.21 399	93.81 346	98.58 214	72.85 465	98.77 324	95.05 251	93.93 330	98.77 251

MVS_Test		97.28 150	97.00 149	98.13 162	98.33 219	95.97 183	98.74 179	98.07 320	94.27 261	98.44 124	98.07 264	92.48 125	99.26 228	96.43 198	98.19 221	99.16 195

UniMVSNet_NR-MVSNet		95.71 238	95.15 250	97.40 237	96.84 370	96.97 126	98.74 179	99.24 20	95.16 201	93.88 340	97.72 299	91.68 156	98.31 377	95.81 220	87.25 428	96.92 342

NR-MVSNet		94.98 288	94.16 307	97.44 232	96.53 387	97.22 114	98.74 179	98.95 61	94.96 222	89.25 443	97.69 302	89.32 240	98.18 389	94.59 274	87.40 425	96.92 342

ETV-MVS		97.96 87	97.81 88	98.40 132	98.42 198	97.27 106	98.73 185	98.55 184	96.84 98	98.38 127	97.44 326	95.39 61	99.35 212	97.62 120	98.89 161	98.58 277

baseline1		95.84 231	95.12 253	98.01 180	98.49 191	95.98 178	98.73 185	97.03 418	95.37 190	96.22 262	98.19 256	89.96 219	99.16 252	94.60 272	87.48 423	98.90 235

MVSTER		96.06 218	95.72 219	97.08 257	98.23 238	95.93 189	98.73 185	98.27 274	94.86 228	95.07 288	98.09 263	88.21 276	98.54 343	96.59 190	93.46 339	96.79 361

ACMP	93.49 10	95.34 264	94.98 260	96.43 325	97.67 306	93.48 323	98.73 185	98.44 215	94.94 226	92.53 394	98.53 219	84.50 358	99.14 259	95.48 236	94.00 327	96.66 379
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HPM-MVS++		98.58 36	98.25 63	99.55 11	99.50 48	99.08 12	98.72 189	98.66 153	97.51 51	98.15 134	98.83 178	95.70 52	99.92 43	97.53 134	99.67 74	99.66 82

9.14			98.06 78		99.47 56		98.71 190	98.82 101	94.36 258	99.16 67	99.29 75	96.05 40	99.81 102	97.00 164	99.71 68

VPNet		94.99 286	94.19 304	97.40 237	97.16 351	96.57 149	98.71 190	98.97 57	95.67 162	94.84 293	98.24 253	80.36 405	98.67 332	96.46 196	87.32 427	96.96 337

MSLP-MVS++		98.56 43	98.57 26	98.55 108	99.26 95	96.80 134	98.71 190	99.05 49	97.28 69	98.84 88	99.28 76	96.47 27	99.40 207	98.52 61	99.70 70	99.47 116

ACMH+	92.99 14	94.30 336	93.77 339	95.88 360	97.81 295	92.04 376	98.71 190	98.37 248	93.99 275	90.60 428	98.47 225	80.86 401	99.05 277	92.75 337	92.40 358	96.55 400

fmvsm_l_conf0.5_n_9		98.90 15	98.79 13	99.24 46	99.34 71	97.83 79	98.70 194	99.26 16	98.85 6	99.92 1	99.51 28	93.91 106	99.95 9	99.86 1	99.79 34	99.92 2

Anonymous202405211		95.28 268	94.49 284	97.67 216	99.00 135	93.75 312	98.70 194	97.04 417	90.66 406	96.49 254	98.80 181	78.13 423	99.83 90	96.21 206	95.36 312	99.44 126

DP-MVS		96.59 193	95.93 211	98.57 105	99.34 71	96.19 170	98.70 194	98.39 240	89.45 429	94.52 303	99.35 62	91.85 150	99.85 84	92.89 332	98.88 162	99.68 75

ME-MVS		98.83 19	98.60 24	99.52 14	99.58 37	98.86 23	98.69 197	98.93 65	97.00 91	99.17 63	99.35 62	96.62 23	99.90 64	98.30 75	99.80 25	99.79 29

fmvsm_s_conf0.1_n_2		98.14 81	98.02 81	98.53 113	98.88 147	97.07 123	98.69 197	98.82 101	98.78 9	99.77 18	99.61 5	88.83 260	99.91 56	99.71 15	99.07 150	98.61 271

Fast-Effi-MVS+-dtu		95.87 229	95.85 213	95.91 357	97.74 301	91.74 381	98.69 197	98.15 303	95.56 169	94.92 291	97.68 305	88.98 254	98.79 322	93.19 319	97.78 236	97.20 330

VortexMVS		95.95 222	95.79 215	96.42 326	98.29 228	93.96 304	98.68 200	98.31 264	96.02 141	94.29 319	97.57 316	89.47 232	98.37 370	97.51 138	91.93 364	96.94 340

fmvsm_s_conf0.5_n_5		98.53 46	98.35 48	99.08 64	99.07 127	97.46 94	98.68 200	99.20 33	97.50 52	99.87 4	99.50 31	91.96 149	99.96 4	99.76 11	99.65 80	99.82 23

tfpn200view9		95.32 266	94.62 277	97.43 233	98.94 143	94.98 256	98.68 200	96.93 426	95.33 191	96.55 250	96.53 401	84.23 363	99.56 174	88.11 428	96.29 290	97.76 310

VDD-MVS		95.82 233	95.23 247	97.61 224	98.84 155	93.98 303	98.68 200	97.40 388	95.02 217	97.95 158	99.34 68	74.37 459	99.78 124	98.64 48	96.80 270	99.08 213

thres400		95.38 259	94.62 277	97.65 220	98.94 143	94.98 256	98.68 200	96.93 426	95.33 191	96.55 250	96.53 401	84.23 363	99.56 174	88.11 428	96.29 290	98.40 286

pmmvs6		91.77 394	90.63 399	95.17 389	94.69 449	91.24 390	98.67 205	97.92 335	86.14 459	89.62 439	97.56 319	75.79 447	98.34 372	90.75 391	84.56 444	95.94 436

v2v482		94.69 304	94.03 316	96.65 293	96.17 404	94.79 268	98.67 205	98.08 318	92.72 344	94.00 335	97.16 347	87.69 293	98.45 352	92.91 329	88.87 411	96.72 369

fmvsm_s_conf0.5_n_2		98.30 75	98.21 69	98.57 105	99.25 96	97.11 121	98.66 207	99.20 33	98.82 7	99.79 15	99.60 10	89.38 238	99.92 43	99.80 8	99.38 133	98.69 261

DU-MVS		95.42 256	94.76 269	97.40 237	96.53 387	96.97 126	98.66 207	98.99 56	95.43 183	93.88 340	97.69 302	88.57 265	98.31 377	95.81 220	87.25 428	96.92 342

MAR-MVS		96.91 175	96.40 188	98.45 124	98.69 169	96.90 130	98.66 207	98.68 145	92.40 358	97.07 220	97.96 275	91.54 164	99.75 132	93.68 305	98.92 159	98.69 261
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		93.19 377	92.48 381	95.30 386	98.07 262	92.27 364	98.64 210	97.17 408	93.94 279	93.98 336	97.04 365	67.97 473	96.01 470	88.40 426	97.14 259	97.63 317

patch_mono-2		98.36 66	98.87 7	96.82 278	99.53 42	90.68 402	98.64 210	99.29 15	97.88 30	99.19 62	99.52 25	96.80 16	99.97 1	99.11 30	99.86 2	99.82 23

h-mvs33		96.17 214	95.62 228	97.81 199	99.03 130	94.45 282	98.64 210	98.75 127	97.48 54	98.67 105	98.72 200	89.76 223	99.86 83	97.95 94	81.59 457	99.11 204

VNet		97.79 98	97.40 113	98.96 76	98.88 147	97.55 86	98.63 213	98.93 65	96.74 105	99.02 71	98.84 174	90.33 211	99.83 90	98.53 55	96.66 275	99.50 107

PVSNet_Blended_VisFu		97.70 103	97.46 108	98.44 126	99.27 93	95.91 191	98.63 213	99.16 39	94.48 254	97.67 187	98.88 169	92.80 120	99.91 56	97.11 161	99.12 149	99.50 107

PAPM_NR		97.46 130	97.11 141	98.50 118	99.50 48	96.41 158	98.63 213	98.60 164	95.18 200	97.06 221	98.06 265	94.26 100	99.57 171	93.80 303	98.87 164	99.52 101

viewmacassd2359aftdt		97.32 148	97.07 144	98.08 170	98.30 224	95.69 212	98.62 216	98.44 215	95.56 169	97.86 168	99.22 88	89.91 220	99.14 259	97.29 156	98.43 198	99.42 131

SSM_0404		97.26 152	97.00 149	98.03 176	98.46 193	95.99 177	98.62 216	98.44 215	94.77 234	97.24 210	98.93 160	91.22 179	99.28 225	96.54 192	98.74 172	98.84 240

Baseline_NR-MVSNet		94.35 333	93.81 335	95.96 355	96.20 401	94.05 302	98.61 218	96.67 440	91.44 386	93.85 344	97.60 313	88.57 265	98.14 392	94.39 279	86.93 431	95.68 442

E4		97.37 141	97.13 139	98.12 165	98.27 232	95.70 211	98.59 219	98.44 215	95.56 169	97.80 174	99.18 102	90.57 202	99.26 228	97.45 145	98.28 215	99.40 135

viewdifsd2359ckpt13		97.24 154	96.97 154	98.06 174	98.43 196	95.77 208	98.59 219	98.34 256	94.81 231	97.60 198	98.94 158	90.78 199	99.09 271	96.93 169	98.33 209	99.32 155

v1144		94.59 314	93.92 325	96.60 303	96.21 400	94.78 269	98.59 219	98.14 305	91.86 375	94.21 325	97.02 368	87.97 284	98.41 363	91.72 370	89.57 396	96.61 385

AllTest		95.24 270	94.65 276	96.99 262	99.25 96	93.21 343	98.59 219	98.18 294	91.36 388	93.52 357	98.77 190	84.67 353	99.72 137	89.70 408	97.87 232	98.02 304

E2		97.48 126	97.25 124	98.16 153	98.40 202	95.79 206	98.58 223	98.44 215	95.58 167	98.00 153	99.14 111	91.21 183	99.24 239	97.50 139	98.43 198	99.45 123

E3		97.48 126	97.25 124	98.16 153	98.38 205	95.79 206	98.58 223	98.44 215	95.58 167	98.00 153	99.14 111	91.25 177	99.24 239	97.50 139	98.44 195	99.45 123

fmvsm_s_conf0.5_n_7		98.23 76	98.35 48	97.89 193	98.86 151	94.99 255	98.58 223	99.00 53	98.29 20	99.73 23	99.60 10	91.70 155	99.92 43	99.63 21	99.73 61	98.76 252

MGCNet		98.23 76	97.91 86	99.21 50	98.06 265	97.96 73	98.58 223	95.51 461	98.58 14	98.87 86	99.26 80	92.99 118	99.95 9	99.62 22	99.67 74	99.73 55

Fast-Effi-MVS+		96.28 211	95.70 224	98.03 176	98.29 228	95.97 183	98.58 223	98.25 283	91.74 376	95.29 286	97.23 343	91.03 190	99.15 256	92.90 330	97.96 229	98.97 227

Anonymous20231206		91.66 395	91.10 395	93.33 438	94.02 458	87.35 462	98.58 223	97.26 401	90.48 409	90.16 433	96.31 408	83.83 373	96.53 462	79.36 474	89.90 392	96.12 431

v144192		94.39 332	93.70 345	96.48 319	96.06 410	94.35 288	98.58 223	98.16 302	91.45 385	94.33 316	97.02 368	87.50 296	98.45 352	91.08 384	89.11 406	96.63 381

v148		94.29 338	93.76 341	95.91 357	96.10 408	92.93 353	98.58 223	97.97 330	92.59 350	93.47 362	96.95 377	88.53 269	98.32 375	92.56 348	87.06 430	96.49 413

COLMAP_ROB	93.27 12	95.33 265	94.87 266	96.71 287	99.29 88	93.24 342	98.58 223	98.11 310	89.92 420	93.57 355	99.10 122	86.37 317	99.79 121	90.78 390	98.10 224	97.09 331
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
viewcassd2359sk11		97.53 124	97.32 120	98.16 153	98.45 195	95.83 202	98.57 232	98.42 230	95.52 178	98.07 140	99.12 117	91.81 153	99.25 232	97.46 144	98.48 193	99.41 134

viewmanbaseed2359cas		97.47 129	97.25 124	98.14 157	98.41 200	95.84 201	98.57 232	98.43 226	95.55 174	97.97 156	99.12 117	91.26 176	99.15 256	97.42 148	98.53 187	99.43 128

test_vis1_rt		91.29 400	90.65 398	93.19 442	97.45 329	86.25 467	98.57 232	90.90 494	93.30 321	86.94 459	93.59 459	62.07 484	99.11 266	97.48 142	95.58 310	94.22 466

FMVSNet3		94.97 290	94.26 300	97.11 255	98.18 250	96.62 141	98.56 235	98.26 282	93.67 301	94.09 330	97.10 350	84.25 361	98.01 412	92.08 358	92.14 361	96.70 373

E3new		97.55 120	97.35 118	98.16 153	98.48 192	95.85 200	98.55 236	98.41 231	95.42 185	98.06 142	99.12 117	92.23 136	99.24 239	97.43 146	98.45 194	99.39 136

F-COLMAP		97.09 167	96.80 162	97.97 187	99.45 61	94.95 259	98.55 236	98.62 163	93.02 334	96.17 266	98.58 214	94.01 104	99.81 102	93.95 297	98.90 160	99.14 199

dmvs_re		94.48 326	94.18 306	95.37 383	97.68 305	90.11 417	98.54 238	97.08 412	94.56 246	94.42 311	97.24 342	84.25 361	97.76 431	91.02 388	92.83 353	98.24 293

viewdifsd2359ckpt09		97.13 164	96.79 164	98.14 157	98.43 196	95.90 192	98.52 239	98.37 248	94.32 259	97.33 205	98.86 172	90.23 215	99.16 252	96.81 183	98.25 216	99.36 145

SSM_0407		97.17 161	96.87 158	98.08 170	98.19 244	95.90 192	98.52 239	98.44 215	94.77 234	96.75 238	98.93 160	91.22 179	99.22 247	96.54 192	98.43 198	99.10 206

ttmdpeth		92.61 387	91.96 390	94.55 415	94.10 454	90.60 407	98.52 239	97.29 397	92.67 346	90.18 432	97.92 279	79.75 410	97.79 428	91.09 382	86.15 439	95.26 447

v1921920		94.20 344	93.47 356	96.40 329	95.98 414	94.08 301	98.52 239	98.15 303	91.33 391	94.25 322	97.20 346	86.41 316	98.42 356	90.04 402	89.39 403	96.69 378

EU-MVSNet		93.66 363	94.14 309	92.25 452	95.96 416	83.38 476	98.52 239	98.12 307	94.69 239	92.61 390	98.13 261	87.36 300	96.39 466	91.82 367	90.00 391	96.98 336

TAMVS		97.02 169	96.79 164	97.70 211	98.06 265	95.31 238	98.52 239	98.31 264	93.95 277	97.05 222	98.61 209	93.49 111	98.52 345	95.33 239	97.81 234	99.29 163

LTVRE_ROB	92.95 15	94.60 312	93.90 328	96.68 291	97.41 334	94.42 284	98.52 239	98.59 171	91.69 379	91.21 421	98.35 237	84.87 346	99.04 280	91.06 385	93.44 342	96.60 387
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		91.06 407	89.68 410	95.21 387	85.35 496	91.49 386	98.51 246	97.07 414	91.47 384	88.83 449	97.84 288	77.31 433	99.09 271	92.79 336	77.98 472	95.04 455

v1192		94.32 335	93.58 350	96.53 313	96.10 408	94.45 282	98.50 247	98.17 300	91.54 383	94.19 326	97.06 361	86.95 306	98.43 355	90.14 397	89.57 396	96.70 373

test_0402		91.32 399	90.27 403	94.48 419	96.60 384	91.12 391	98.50 247	97.22 403	86.10 460	88.30 452	96.98 372	77.65 431	97.99 415	78.13 478	92.94 351	94.34 463

DeepC-MVS_fast	96.70 1	98.55 44	98.34 54	99.18 53	99.25 96	98.04 69	98.50 247	98.78 121	97.72 36	98.92 84	99.28 76	95.27 70	99.82 97	97.55 132	99.77 41	99.69 70
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
viewdifsd2359ckpt11		96.30 207	96.13 199	96.81 279	98.10 259	92.10 371	98.49 250	98.40 234	96.02 141	97.61 195	99.31 71	86.37 317	99.29 223	97.52 135	93.36 345	99.04 219

viewmsd2359difaftdt		96.30 207	96.13 199	96.81 279	98.10 259	92.10 371	98.49 250	98.40 234	96.02 141	97.61 195	99.31 71	86.37 317	99.30 221	97.52 135	93.37 344	99.04 219

IMVS_0403		96.74 183	96.61 177	97.12 253	97.99 276	92.82 355	98.47 252	98.27 274	95.16 201	97.13 215	98.79 183	91.44 168	99.26 228	94.74 260	97.54 248	99.27 170

CNVR-MVS		98.78 20	98.56 28	99.45 19	99.32 77	98.87 21	98.47 252	98.81 107	97.72 36	98.76 96	99.16 107	97.05 14	99.78 124	98.06 89	99.66 77	99.69 70

FE-MVSNET2		90.29 420	88.94 425	94.36 424	90.48 482	92.27 364	98.45 254	97.82 343	91.59 382	84.90 472	93.10 466	73.92 460	96.42 465	87.92 434	82.26 452	94.39 462

IMVS_0407		96.74 183	96.64 176	97.05 259	97.99 276	92.82 355	98.45 254	98.27 274	95.16 201	97.30 206	98.79 183	91.53 165	99.06 276	94.74 260	97.54 248	99.27 170

LuminaMVS		97.49 125	97.18 133	98.42 130	97.50 323	97.15 119	98.45 254	97.68 352	96.56 117	98.68 104	98.78 187	89.84 222	99.32 216	98.60 50	98.57 183	98.79 244

test_yl		97.22 155	96.78 166	98.54 110	98.73 161	96.60 144	98.45 254	98.31 264	94.70 237	98.02 149	98.42 229	90.80 195	99.70 143	96.81 183	96.79 271	99.34 148

DCV-MVSNet		97.22 155	96.78 166	98.54 110	98.73 161	96.60 144	98.45 254	98.31 264	94.70 237	98.02 149	98.42 229	90.80 195	99.70 143	96.81 183	96.79 271	99.34 148

NCCC		98.61 31	98.35 48	99.38 24	99.28 92	98.61 32	98.45 254	98.76 125	97.82 35	98.45 122	98.93 160	96.65 21	99.83 90	97.38 153	99.41 128	99.71 63

v1240		94.06 358	93.29 362	96.34 333	96.03 412	93.90 306	98.44 260	98.17 300	91.18 400	94.13 329	97.01 370	86.05 324	98.42 356	89.13 419	89.50 400	96.70 373

plane_prior						94.60 278	98.44 260		96.74 105						94.22 318

sc_t1		91.01 409	89.39 414	95.85 363	95.99 413	90.39 412	98.43 262	97.64 358	78.79 479	92.20 408	97.94 277	66.00 478	98.60 339	91.59 374	85.94 441	98.57 278

MP-MVS-pluss		98.31 73	97.92 85	99.49 16	99.72 17	98.88 20	98.43 262	98.78 121	94.10 266	97.69 186	99.42 46	95.25 72	99.92 43	98.09 88	99.80 25	99.67 79
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
OPM-MVS		95.69 241	95.33 242	96.76 283	96.16 406	94.63 273	98.43 262	98.39 240	96.64 112	95.02 290	98.78 187	85.15 342	99.05 277	95.21 248	94.20 319	96.60 387
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DPE-MVS		98.92 13	98.67 20	99.65 2	99.58 37	99.20 9	98.42 265	98.91 72	97.58 47	99.54 37	99.46 42	97.10 13	99.94 14	97.64 119	99.84 11	99.83 19
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MCST-MVS		98.65 26	98.37 45	99.48 17	99.60 36	98.87 21	98.41 266	98.68 145	97.04 88	98.52 117	98.80 181	96.78 17	99.83 90	97.93 96	99.61 90	99.74 50

viewdifsd2359ckpt07		97.20 158	97.05 146	97.65 220	98.40 202	94.33 291	98.39 267	98.43 226	95.67 162	97.66 191	99.08 133	90.04 217	99.32 216	97.47 143	98.29 213	99.31 156

hse-mvs2		95.71 238	95.30 245	96.93 270	98.50 187	93.53 321	98.36 268	98.10 313	97.48 54	98.67 105	97.99 272	89.76 223	99.02 287	97.95 94	80.91 463	98.22 295

CANet		98.05 85	97.76 90	98.90 82	98.73 161	97.27 106	98.35 269	98.78 121	97.37 64	97.72 183	98.96 155	91.53 165	99.92 43	98.79 41	99.65 80	99.51 104

AUN-MVS		94.53 320	93.73 343	96.92 273	98.50 187	93.52 322	98.34 270	98.10 313	93.83 285	95.94 275	97.98 274	85.59 333	99.03 283	94.35 281	80.94 462	98.22 295

test20.03		90.89 411	90.38 402	92.43 447	93.48 461	88.14 457	98.33 271	97.56 366	93.40 316	87.96 453	96.71 393	80.69 403	94.13 483	79.15 475	86.17 437	95.01 457

DP-MVS Recon		97.86 92	97.46 108	99.06 66	99.53 42	98.35 50	98.33 271	98.89 75	92.62 348	98.05 144	98.94 158	95.34 66	99.65 154	96.04 211	99.42 127	99.19 189

RPSCF		94.87 297	95.40 233	93.26 440	98.89 146	82.06 480	98.33 271	98.06 325	90.30 415	96.56 248	99.26 80	87.09 302	99.49 191	93.82 302	96.32 287	98.24 293

TAPA-MVS	93.98 7	95.35 263	94.56 281	97.74 207	99.13 119	94.83 265	98.33 271	98.64 158	86.62 455	96.29 261	98.61 209	94.00 105	99.29 223	80.00 472	99.41 128	99.09 209
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
IterMVS-LS		95.46 251	95.21 248	96.22 339	98.12 257	93.72 315	98.32 275	98.13 306	93.71 294	94.26 321	97.31 337	92.24 135	98.10 396	94.63 268	90.12 389	96.84 357
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SD_0403		94.28 340	94.46 287	93.73 431	98.02 272	85.32 470	98.31 276	98.40 234	94.75 236	93.59 352	98.16 258	89.01 250	96.54 461	82.32 465	97.58 246	99.34 148

mvs_anonymous		96.70 188	96.53 183	97.18 247	98.19 244	93.78 309	98.31 276	98.19 291	94.01 273	94.47 305	98.27 249	92.08 144	98.46 351	97.39 152	97.91 230	99.31 156

WTY-MVS		97.37 141	96.92 156	98.72 92	98.86 151	96.89 132	98.31 276	98.71 137	95.26 196	97.67 187	98.56 218	92.21 138	99.78 124	95.89 215	96.85 269	99.48 114

D2MVS		95.18 274	95.08 255	95.48 378	97.10 355	92.07 374	98.30 279	99.13 43	94.02 270	92.90 381	96.73 391	89.48 231	98.73 326	94.48 277	93.60 338	95.65 443

EI-MVSNet-Vis-set		98.47 54	98.39 43	98.69 94	99.46 58	96.49 153	98.30 279	98.69 142	97.21 76	98.84 88	99.36 60	95.41 60	99.78 124	98.62 49	99.65 80	99.80 28

DSMNet-mixed		92.52 390	92.58 378	92.33 449	94.15 452	82.65 478	98.30 279	94.26 478	89.08 435	92.65 389	95.73 431	85.01 344	95.76 472	86.24 442	97.76 238	98.59 275

EI-MVSNet-UG-set		98.41 61	98.34 54	98.61 102	99.45 61	96.32 163	98.28 282	98.68 145	97.17 80	98.74 97	99.37 56	95.25 72	99.79 121	98.57 52	99.54 109	99.73 55

OMC-MVS		97.55 120	97.34 119	98.20 149	99.33 74	95.92 190	98.28 282	98.59 171	95.52 178	97.97 156	99.10 122	93.28 115	99.49 191	95.09 249	98.88 162	99.19 189

baseline2		95.11 278	94.52 283	96.87 275	96.65 383	93.56 318	98.27 284	94.10 481	93.45 314	92.02 414	97.43 327	87.45 299	99.19 249	93.88 300	97.41 255	97.87 308

PVSNet_BlendedMVS		96.73 185	96.60 178	97.12 253	99.25 96	95.35 235	98.26 285	99.26 16	94.28 260	97.94 160	97.46 323	92.74 121	99.81 102	96.88 176	93.32 346	96.20 428

MVStest1		89.53 431	87.99 436	94.14 429	94.39 450	90.42 410	98.25 286	96.84 435	82.81 471	81.18 481	97.33 335	77.09 438	96.94 451	85.27 451	78.79 468	95.06 454

BH-untuned		95.95 222	95.72 219	96.65 293	98.55 184	92.26 366	98.23 287	97.79 348	93.73 291	94.62 300	98.01 270	88.97 255	99.00 290	93.04 325	98.51 189	98.68 263

sss		97.39 138	96.98 153	98.61 102	98.60 181	96.61 143	98.22 288	98.93 65	93.97 276	98.01 152	98.48 224	91.98 146	99.85 84	96.45 197	98.15 222	99.39 136

save fliter					99.46 58	98.38 41	98.21 289	98.71 137	97.95 28

WR-MVS		95.15 275	94.46 287	97.22 243	96.67 382	96.45 154	98.21 289	98.81 107	94.15 264	93.16 373	97.69 302	87.51 294	98.30 379	95.29 243	88.62 413	96.90 349

pmmvs5		93.65 365	92.97 369	95.68 370	95.49 432	92.37 363	98.20 291	97.28 399	89.66 425	92.58 391	97.26 339	82.14 384	98.09 400	93.18 320	90.95 380	96.58 394

thres200		95.25 269	94.57 280	97.28 241	98.81 157	94.92 260	98.20 291	97.11 410	95.24 199	96.54 252	96.22 414	84.58 356	99.53 183	87.93 433	96.50 282	97.39 324

CDS-MVSNet		96.99 171	96.69 172	97.90 191	98.05 267	95.98 178	98.20 291	98.33 258	93.67 301	96.95 224	98.49 223	93.54 110	98.42 356	95.24 246	97.74 239	99.31 156
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
ETVMVS		94.50 323	93.44 357	97.68 214	98.18 250	95.35 235	98.19 294	97.11 410	93.73 291	96.40 258	95.39 439	74.53 456	98.84 314	91.10 381	96.31 288	98.84 240

WB-MVS		84.86 445	85.33 446	83.46 469	89.48 486	69.56 495	98.19 294	96.42 448	89.55 427	81.79 478	94.67 448	84.80 348	90.12 491	52.44 494	80.64 464	90.69 482

1314		96.25 213	95.73 218	97.79 200	97.13 353	95.55 219	98.19 294	98.59 171	93.47 313	92.03 413	97.82 292	91.33 172	99.49 191	94.62 270	98.44 195	98.32 292

MVS		94.67 309	93.54 353	98.08 170	96.88 368	96.56 150	98.19 294	98.50 199	78.05 482	92.69 388	98.02 268	91.07 189	99.63 160	90.09 398	98.36 208	98.04 303

BH-RMVSNet		95.92 227	95.32 243	97.69 212	98.32 222	94.64 272	98.19 294	97.45 384	94.56 246	96.03 269	98.61 209	85.02 343	99.12 264	90.68 392	99.06 151	99.30 160

1112_ss		96.63 191	96.00 208	98.50 118	98.56 182	96.37 160	98.18 299	98.10 313	92.92 338	94.84 293	98.43 227	92.14 140	99.58 170	94.35 281	96.51 281	99.56 100

tt0320		90.26 422	88.73 427	94.86 402	96.12 407	90.62 405	98.17 300	97.63 359	77.46 483	89.68 438	96.04 421	69.19 470	97.79 428	88.98 420	85.29 443	96.16 430

viewmambaseed2359dif		97.01 170	96.84 160	97.51 229	98.19 244	94.21 297	98.16 301	98.23 285	93.61 307	97.78 175	99.13 114	90.79 198	99.18 251	97.24 157	98.40 205	99.15 196

tt0320-xc		89.79 426	88.11 433	94.84 405	96.19 402	90.61 406	98.16 301	97.22 403	77.35 484	88.75 450	96.70 394	65.94 479	97.63 436	89.31 416	83.39 449	96.28 425

EPNet_dtu		95.21 272	94.95 262	95.99 350	96.17 404	90.45 409	98.16 301	97.27 400	96.77 102	93.14 376	98.33 242	90.34 210	98.42 356	85.57 447	98.81 170	99.09 209
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FE-MVSNET		88.56 435	87.09 442	92.99 444	89.93 484	89.99 418	98.15 304	95.59 460	88.42 442	84.87 473	92.90 467	74.82 454	94.99 480	77.88 479	81.21 459	93.99 472

HY-MVS	93.96 8	96.82 180	96.23 197	98.57 105	98.46 193	97.00 125	98.14 305	98.21 287	93.95 277	96.72 241	97.99 272	91.58 159	99.76 130	94.51 276	96.54 280	98.95 230

PLC	95.07 4	97.20 158	96.78 166	98.44 126	99.29 88	96.31 165	98.14 305	98.76 125	92.41 357	96.39 259	98.31 244	94.92 86	99.78 124	94.06 295	98.77 171	99.23 180
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EG-PatchMatch MVS		91.13 406	90.12 405	94.17 428	94.73 448	89.00 440	98.13 307	97.81 347	89.22 433	85.32 470	96.46 403	67.71 474	98.42 356	87.89 435	93.82 332	95.08 453

usedtu_blend_shiyan5		90.87 413	89.15 419	96.01 347	91.33 476	93.35 333	98.12 308	97.36 392	81.93 476	92.36 401	91.75 478	81.83 386	98.09 400	92.88 333	74.82 483	96.59 390

diffmvs_AUTHOR		97.59 115	97.44 110	98.01 180	98.26 233	95.47 223	98.12 308	98.36 252	96.38 126	98.84 88	99.10 122	91.13 184	99.26 228	98.24 83	98.56 184	99.30 160

EI-MVSNet		95.96 221	95.83 214	96.36 331	97.93 287	93.70 316	98.12 308	98.27 274	93.70 296	95.07 288	99.02 142	92.23 136	98.54 343	94.68 265	93.46 339	96.84 357

CVMVSNet		95.43 255	96.04 204	93.57 434	97.93 287	83.62 474	98.12 308	98.59 171	95.68 161	96.56 248	99.02 142	87.51 294	97.51 442	93.56 311	97.44 253	99.60 92

TSAR-MVS + GP.		98.38 63	98.24 65	98.81 85	99.22 106	97.25 112	98.11 312	98.29 273	97.19 78	98.99 76	99.02 142	96.22 33	99.67 150	98.52 61	98.56 184	99.51 104

XVG-ACMP-BASELINE		94.54 318	94.14 309	95.75 369	96.55 386	91.65 383	98.11 312	98.44 215	94.96 222	94.22 324	97.90 281	79.18 414	99.11 266	94.05 296	93.85 331	96.48 415

testing99		94.83 298	94.08 312	97.07 258	97.94 285	93.13 345	98.10 314	97.17 408	94.86 228	95.34 282	96.00 425	76.31 443	99.40 207	95.08 250	95.90 304	98.68 263

testing11		95.00 284	94.28 297	97.16 249	97.96 284	93.36 332	98.09 315	97.06 416	94.94 226	95.33 285	96.15 416	76.89 440	99.40 207	95.77 224	96.30 289	98.72 256

SSC-MVS		84.27 447	84.71 449	82.96 473	89.19 488	68.83 496	98.08 316	96.30 450	89.04 436	81.37 480	94.47 449	84.60 355	89.89 492	49.80 496	79.52 466	90.15 483

CNLPA		97.45 133	97.03 148	98.73 91	99.05 128	97.44 95	98.07 317	98.53 188	95.32 193	96.80 236	98.53 219	93.32 113	99.72 137	94.31 284	99.31 141	99.02 222

diffmvs		97.58 116	97.40 113	98.13 162	98.32 222	95.81 205	98.06 318	98.37 248	96.20 133	98.74 97	98.89 168	91.31 174	99.25 232	98.16 85	98.52 188	99.34 148
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		97.12 165	96.80 162	98.08 170	99.30 83	94.56 280	98.05 319	99.71 1	93.57 309	97.09 217	98.91 165	88.17 277	99.89 68	96.87 179	99.56 106	99.81 25

HQP-NCC					97.20 346		98.05 319		96.43 120	94.45 306

ACMP_Plane					97.20 346		98.05 319		96.43 120	94.45 306

HQP-MVS		95.72 237	95.40 233	96.69 290	97.20 346	94.25 295	98.05 319	98.46 207	96.43 120	94.45 306	97.73 297	86.75 308	98.96 295	95.30 241	94.18 320	96.86 356

myMVS_eth3d28		95.12 277	94.62 277	96.64 297	98.17 253	92.17 367	98.02 323	97.32 394	95.41 186	96.22 262	96.05 420	78.01 425	99.13 261	95.22 247	97.16 258	98.60 272

MIMVSNet1		89.67 428	88.28 431	93.82 430	92.81 466	91.08 392	98.01 324	97.45 384	87.95 444	87.90 454	95.87 427	67.63 475	94.56 482	78.73 477	88.18 417	95.83 439

AdaColmap		97.15 163	96.70 171	98.48 121	99.16 115	96.69 140	98.01 324	98.89 75	94.44 256	96.83 232	98.68 203	90.69 200	99.76 130	94.36 280	99.29 142	98.98 226

testing91		94.98 288	94.25 301	97.20 244	97.94 285	93.41 326	98.00 326	97.58 363	94.99 218	95.45 281	96.04 421	77.20 435	99.42 205	94.97 253	96.02 303	98.78 248

FMVSNet5		91.81 393	90.92 396	94.49 418	97.21 345	92.09 373	98.00 326	97.55 371	89.31 432	90.86 425	95.61 437	74.48 457	95.32 476	85.57 447	89.70 394	96.07 433

CANet_DTU		96.96 173	96.55 180	98.21 147	98.17 253	96.07 176	97.98 328	98.21 287	97.24 74	97.13 215	98.93 160	86.88 307	99.91 56	95.00 252	99.37 135	98.66 267

MVP-Stereo		94.28 340	93.92 325	95.35 384	94.95 443	92.60 361	97.97 329	97.65 356	91.61 381	90.68 427	97.09 354	86.32 320	98.42 356	89.70 408	99.34 137	95.02 456
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SSC-MVS3.2		93.59 367	93.13 365	94.97 396	96.81 373	89.71 424	97.95 330	98.49 204	94.59 245	93.50 360	96.91 380	77.74 428	98.37 370	91.69 371	90.47 384	96.83 359

KD-MVS_self_test		90.38 418	89.38 416	93.40 437	92.85 465	88.94 443	97.95 330	97.94 333	90.35 414	90.25 431	93.96 456	79.82 408	95.94 471	84.62 458	76.69 478	95.33 446

MVS_111021_LR		98.34 70	98.23 67	98.67 96	99.27 93	96.90 130	97.95 330	99.58 3	97.14 83	98.44 124	99.01 146	95.03 83	99.62 164	97.91 98	99.75 53	99.50 107

testing222		94.12 352	93.03 367	97.37 240	98.02 272	94.66 270	97.94 333	96.65 442	94.63 243	95.78 276	95.76 428	71.49 466	98.92 302	91.17 380	95.88 305	98.52 280

UWE-MVS-28		92.79 384	92.51 379	93.62 433	96.46 392	86.28 466	97.93 334	92.71 488	94.17 263	94.78 298	97.16 347	81.05 397	96.43 464	81.45 468	96.86 267	98.14 300

TEST9					99.31 79	98.50 35	97.92 335	98.73 132	92.63 347	97.74 180	98.68 203	96.20 35	99.80 109

train_agg		97.97 86	97.52 103	99.33 36	99.31 79	98.50 35	97.92 335	98.73 132	92.98 335	97.74 180	98.68 203	96.20 35	99.80 109	96.59 190	99.57 98	99.68 75

Syy-MVS		92.55 388	92.61 376	92.38 448	97.39 335	83.41 475	97.91 337	97.46 380	93.16 327	93.42 364	95.37 440	84.75 350	96.12 468	77.00 482	96.99 263	97.60 318

myMVS_eth3d		92.73 385	92.01 387	94.89 400	97.39 335	90.94 394	97.91 337	97.46 380	93.16 327	93.42 364	95.37 440	68.09 472	96.12 468	88.34 427	96.99 263	97.60 318

CDPH-MVS		97.94 89	97.49 105	99.28 42	99.47 56	98.44 37	97.91 337	98.67 150	92.57 351	98.77 95	98.85 173	95.93 45	99.72 137	95.56 232	99.69 71	99.68 75

MVS_111021_HR		98.47 54	98.34 54	98.88 83	99.22 106	97.32 99	97.91 337	99.58 3	97.20 77	98.33 131	99.00 148	95.99 43	99.64 157	98.05 91	99.76 47	99.69 70

PatchMatch-RL		96.59 193	96.03 205	98.27 139	99.31 79	96.51 152	97.91 337	99.06 47	93.72 293	96.92 228	98.06 265	88.50 270	99.65 154	91.77 369	99.00 157	98.66 267

OpenMVS_ROB	86.42 20	89.00 433	87.43 441	93.69 432	93.08 464	89.42 433	97.91 337	96.89 430	78.58 480	85.86 465	94.69 447	69.48 469	98.29 382	77.13 481	93.29 348	93.36 477

test_8					99.29 88	98.44 37	97.89 343	98.72 134	92.98 335	97.70 185	98.66 206	96.20 35	99.80 109

ab-mvs		96.42 201	95.71 222	98.55 108	98.63 178	96.75 137	97.88 344	98.74 129	93.84 283	96.54 252	98.18 257	85.34 338	99.75 132	95.93 214	96.35 285	99.15 196

UBG		95.32 266	94.72 272	97.13 251	98.05 267	93.26 339	97.87 345	97.20 406	94.96 222	96.18 265	95.66 436	80.97 398	99.35 212	94.47 278	97.08 260	98.78 248

jason		97.32 148	97.08 143	98.06 174	97.45 329	95.59 214	97.87 345	97.91 336	94.79 233	98.55 116	98.83 178	91.12 186	99.23 243	97.58 127	99.60 92	99.34 148
jason: jason.
WB-MVSnew		94.19 345	94.04 314	94.66 411	96.82 372	92.14 368	97.86 347	95.96 455	93.50 311	95.64 278	96.77 390	88.06 282	97.99 415	84.87 453	96.86 267	93.85 475

xiu_mvs_v1_base_debu		97.60 112	97.56 99	97.72 208	98.35 210	95.98 178	97.86 347	98.51 194	97.13 84	99.01 73	98.40 231	91.56 161	99.80 109	98.53 55	98.68 173	97.37 326

xiu_mvs_v1_base		97.60 112	97.56 99	97.72 208	98.35 210	95.98 178	97.86 347	98.51 194	97.13 84	99.01 73	98.40 231	91.56 161	99.80 109	98.53 55	98.68 173	97.37 326

xiu_mvs_v1_base_debi		97.60 112	97.56 99	97.72 208	98.35 210	95.98 178	97.86 347	98.51 194	97.13 84	99.01 73	98.40 231	91.56 161	99.80 109	98.53 55	98.68 173	97.37 326

test_prior4						98.01 71	97.86 347

mvsany_test3		88.80 434	88.04 434	91.09 456	89.78 485	81.57 481	97.83 352	95.49 462	93.81 286	87.53 455	93.95 457	56.14 487	97.43 443	94.68 265	83.13 450	94.26 464

WBMVS		94.56 316	94.04 314	96.10 344	98.03 271	93.08 349	97.82 353	98.18 294	94.02 270	93.77 349	96.82 387	81.28 393	98.34 372	95.47 237	91.00 379	96.88 351

FA-MVS(test-final)		96.41 204	95.94 210	97.82 198	98.21 240	95.20 243	97.80 354	97.58 363	93.21 324	97.36 204	97.70 300	89.47 232	99.56 174	94.12 292	97.99 227	98.71 259

test_prior2							97.80 354		96.12 138	97.89 167	98.69 202	95.96 44		96.89 174	99.60 92

XVG-OURS-SEG-HR		96.51 198	96.34 191	97.02 261	98.77 159	93.76 310	97.79 356	98.50 199	95.45 182	96.94 225	99.09 130	87.87 288	99.55 181	96.76 188	95.83 307	97.74 312

usedtu_dtu_shiyan2		84.80 446	82.31 450	92.27 451	86.38 494	85.55 469	97.77 357	96.56 444	78.34 481	83.90 475	93.50 460	54.16 488	95.32 476	77.55 480	72.62 490	95.92 437

MS-PatchMatch		93.84 362	93.63 348	94.46 421	96.18 403	89.45 432	97.76 358	98.27 274	92.23 364	92.13 411	97.49 321	79.50 411	98.69 328	89.75 406	99.38 133	95.25 448

DELS-MVS		98.40 62	98.20 71	98.99 71	99.00 135	97.66 81	97.75 359	98.89 75	97.71 38	98.33 131	98.97 150	94.97 84	99.88 77	98.42 69	99.76 47	99.42 131
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 97	97.60 95	98.44 126	99.12 121	95.97 183	97.75 359	98.78 121	96.89 96	98.46 119	99.22 88	93.90 107	99.68 149	94.81 258	99.52 112	99.67 79

test_f		86.07 444	85.39 445	88.10 460	89.28 487	75.57 487	97.73 361	96.33 449	89.41 431	85.35 469	91.56 481	43.31 494	95.53 473	91.32 378	84.23 446	93.21 479

Test_1112_low_res		96.34 206	95.66 227	98.36 134	98.56 182	95.94 186	97.71 362	98.07 320	92.10 368	94.79 297	97.29 338	91.75 154	99.56 174	94.17 290	96.50 282	99.58 98

BH-w/o		95.38 259	95.08 255	96.26 338	98.34 215	91.79 378	97.70 363	97.43 386	92.87 340	94.24 323	97.22 344	88.66 263	98.84 314	91.55 375	97.70 241	98.16 299

lupinMVS		97.44 134	97.22 131	98.12 165	98.07 262	95.76 209	97.68 364	97.76 349	94.50 253	98.79 93	98.61 209	92.34 129	99.30 221	97.58 127	99.59 94	99.31 156

原ACMM2							97.67 365

test_vis3_rt		79.22 449	77.40 456	84.67 466	86.44 493	74.85 490	97.66 366	81.43 501	84.98 466	67.12 494	81.91 492	28.09 502	97.60 437	88.96 421	80.04 465	81.55 492

LF4IMVS		93.14 379	92.79 372	94.20 426	95.88 420	88.67 447	97.66 366	97.07 414	93.81 286	91.71 416	97.65 307	77.96 426	98.81 320	91.47 376	91.92 366	95.12 451

EGC-MVSNET		75.22 458	69.54 461	92.28 450	94.81 446	89.58 429	97.64 368	96.50 445	1.82 503	5.57 504	95.74 429	68.21 471	96.26 467	73.80 485	91.71 368	90.99 481

新几何2							97.64 368

MDA-MVSNet-bldmvs		89.97 425	88.35 430	94.83 406	95.21 439	91.34 387	97.64 368	97.51 375	88.36 443	71.17 492	96.13 417	79.22 413	96.63 460	83.65 460	86.27 436	96.52 406

pmmvs-eth3d		90.36 419	89.05 421	94.32 425	91.10 480	92.12 369	97.63 371	96.95 425	88.86 437	84.91 471	93.13 465	78.32 420	96.74 455	88.70 423	81.81 456	94.09 469

TR-MVS		94.94 295	94.20 303	97.17 248	97.75 298	94.14 300	97.59 372	97.02 421	92.28 363	95.75 277	97.64 310	83.88 371	98.96 295	89.77 405	96.15 300	98.40 286

无先验							97.58 373	98.72 134	91.38 387				99.87 79	93.36 315		99.60 92

旧先验2							97.57 374		91.30 393	98.67 105			99.80 109	95.70 228

mvsany_test1		97.69 104	97.70 92	97.66 219	98.24 236	94.18 298	97.53 375	97.53 373	95.52 178	99.66 29	99.51 28	94.30 98	99.56 174	98.38 70	98.62 178	99.23 180

CostFormer		94.95 293	94.73 271	95.60 375	97.28 340	89.06 438	97.53 375	96.89 430	89.66 425	96.82 234	96.72 392	86.05 324	98.95 300	95.53 234	96.13 301	98.79 244

UWE-MVS		94.30 336	93.89 330	95.53 376	97.83 293	88.95 442	97.52 377	93.25 483	94.44 256	96.63 244	97.07 357	78.70 417	99.28 225	91.99 363	97.56 247	98.36 289

XVG-OURS		96.55 197	96.41 187	96.99 262	98.75 160	93.76 310	97.50 378	98.52 191	95.67 162	96.83 232	99.30 74	88.95 257	99.53 183	95.88 216	96.26 295	97.69 315

blended_shiyan8		91.42 397	89.89 408	96.01 347	91.50 472	93.30 336	97.48 379	97.83 340	86.93 450	92.57 393	92.37 472	82.46 382	98.13 393	92.86 335	74.99 480	96.61 385

blended_shiyan6		91.37 398	89.84 409	95.98 353	91.49 473	93.28 337	97.48 379	97.83 340	86.93 450	92.43 399	92.36 473	82.44 383	98.06 405	92.74 340	74.82 483	96.59 390

blend_shiyan4		90.76 414	89.01 422	95.99 350	91.69 471	93.35 333	97.44 381	97.83 340	86.93 450	92.23 406	91.98 476	75.19 451	98.09 400	92.88 333	74.96 481	96.52 406

xiu_mvs_v2_base		97.66 107	97.70 92	97.56 227	98.61 180	95.46 224	97.44 381	98.46 207	97.15 82	98.65 110	98.15 259	94.33 97	99.80 109	97.84 104	98.66 177	97.41 322

tpm		94.13 350	93.80 336	95.12 390	96.50 389	87.91 459	97.44 381	95.89 458	92.62 348	96.37 260	96.30 409	84.13 366	98.30 379	93.24 317	91.66 370	99.14 199

DeepPCF-MVS	96.37 2	97.93 90	98.48 38	96.30 336	99.00 135	89.54 430	97.43 384	98.87 85	98.16 22	99.26 58	99.38 55	96.12 38	99.64 157	98.30 75	99.77 41	99.72 59

test222					99.23 104	97.17 117	97.40 385	98.66 153	88.68 439	98.05 144	98.96 155	94.14 102			99.53 111	99.61 90

pmmvs4		94.69 304	93.99 322	96.81 279	95.74 423	95.94 186	97.40 385	97.67 355	90.42 412	93.37 366	97.59 314	89.08 248	98.20 388	92.97 327	91.67 369	96.30 424

test0.0.03 1		94.08 356	93.51 354	95.80 365	95.53 431	92.89 354	97.38 387	95.97 454	95.11 208	92.51 396	96.66 395	87.71 290	96.94 451	87.03 438	93.67 334	97.57 320

HyFIR lowres test		96.90 176	96.49 185	98.14 157	99.33 74	95.56 217	97.38 387	99.65 2	92.34 359	97.61 195	98.20 255	89.29 241	99.10 270	96.97 166	97.60 244	99.77 40

Effi-MVS+		97.12 165	96.69 172	98.39 133	98.19 244	96.72 139	97.37 389	98.43 226	93.71 294	97.65 192	98.02 268	92.20 139	99.25 232	96.87 179	97.79 235	99.19 189

N_pmnet		87.12 442	87.77 439	85.17 465	95.46 434	61.92 501	97.37 389	70.66 506	85.83 462	88.73 451	96.04 421	85.33 339	97.76 431	80.02 471	90.48 383	95.84 438

PAPR		96.84 179	96.24 196	98.65 98	98.72 165	96.92 129	97.36 391	98.57 178	93.33 318	96.67 242	97.57 316	94.30 98	99.56 174	91.05 387	98.59 180	99.47 116

PMMVS		96.60 192	96.33 192	97.41 235	97.90 289	93.93 305	97.35 392	98.41 231	92.84 341	97.76 177	97.45 325	91.10 188	99.20 248	96.26 203	97.91 230	99.11 204

PS-MVSNAJ		97.73 100	97.77 89	97.62 223	98.68 171	95.58 215	97.34 393	98.51 194	97.29 67	98.66 109	97.88 284	94.51 91	99.90 64	97.87 101	99.17 148	97.39 324

SCA		95.46 251	95.13 251	96.46 323	97.67 306	91.29 389	97.33 394	97.60 362	94.68 240	96.92 228	97.10 350	83.97 369	98.89 308	92.59 346	98.32 212	99.20 185

testdata1							97.32 395		96.34 128

ET-MVSNet_ETH3D		94.13 350	92.98 368	97.58 225	98.22 239	96.20 168	97.31 396	95.37 463	94.53 248	79.56 484	97.63 312	86.51 311	97.53 441	96.91 170	90.74 381	99.02 222

tpm2		94.19 345	93.76 341	95.46 380	97.23 343	89.04 439	97.31 396	96.85 434	87.08 448	96.21 264	96.79 389	83.75 375	98.74 325	92.43 354	96.23 298	98.59 275

PVSNet_Blended		97.38 139	97.12 140	98.14 157	99.25 96	95.35 235	97.28 398	99.26 16	93.13 329	97.94 160	98.21 254	92.74 121	99.81 102	96.88 176	99.40 131	99.27 170

CLD-MVS		95.62 244	95.34 239	96.46 323	97.52 322	93.75 312	97.27 399	98.46 207	95.53 177	94.42 311	98.00 271	86.21 321	98.97 291	96.25 205	94.37 314	96.66 379
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
IMVS_0404		95.82 233	95.52 229	96.73 284	97.99 276	92.82 355	97.23 400	98.27 274	95.16 201	94.31 317	98.79 183	85.63 331	98.10 396	94.74 260	97.54 248	99.27 170

EPMVS		94.99 286	94.48 285	96.52 314	97.22 344	91.75 380	97.23 400	91.66 491	94.11 265	97.28 208	96.81 388	85.70 330	98.84 314	93.04 325	97.28 256	98.97 227

miper_lstm_enhance		94.33 334	94.07 313	95.11 391	97.75 298	90.97 393	97.22 402	98.03 327	91.67 380	92.76 385	96.97 373	90.03 218	97.78 430	92.51 351	89.64 395	96.56 398

APD_test1		88.22 437	88.01 435	88.86 459	95.98 414	74.66 491	97.21 403	96.44 447	83.96 470	86.66 462	97.90 281	60.95 485	97.84 427	82.73 462	90.23 388	94.09 469

dmvs_testset		87.64 439	88.93 426	83.79 468	95.25 438	63.36 500	97.20 404	91.17 492	93.07 331	85.64 468	95.98 426	85.30 341	91.52 490	69.42 488	87.33 426	96.49 413

YYNet1		90.70 416	89.39 414	94.62 414	94.79 447	90.65 403	97.20 404	97.46 380	87.54 446	72.54 490	95.74 429	86.51 311	96.66 459	86.00 444	86.76 435	96.54 401

gbinet_0.2-2-1-0.02		91.03 408	89.37 418	96.01 347	91.39 474	93.41 326	97.19 406	97.82 343	87.00 449	92.18 409	91.87 477	78.97 415	98.04 409	93.13 321	74.75 487	96.60 387

MDA-MVSNet_test_wron		90.71 415	89.38 416	94.68 410	94.83 445	90.78 400	97.19 406	97.46 380	87.60 445	72.41 491	95.72 433	86.51 311	96.71 458	85.92 445	86.80 434	96.56 398

icg_test_0407_2		96.56 196	96.50 184	96.73 284	97.99 276	92.82 355	97.18 408	98.27 274	95.16 201	97.30 206	98.79 183	91.53 165	98.10 396	94.74 260	97.54 248	99.27 170

IterMVS-SCA-FT		94.11 353	93.87 331	94.85 403	97.98 282	90.56 408	97.18 408	98.11 310	93.75 288	92.58 391	97.48 322	83.97 369	97.41 444	92.48 353	91.30 373	96.58 394

IterMVS		94.09 355	93.85 333	94.80 407	97.99 276	90.35 413	97.18 408	98.12 307	93.68 299	92.46 398	97.34 333	84.05 367	97.41 444	92.51 351	91.33 372	96.62 384
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FE-MVS		95.62 244	94.90 264	97.78 201	98.37 208	94.92 260	97.17 411	97.38 390	90.95 403	97.73 182	97.70 300	85.32 340	99.63 160	91.18 379	98.33 209	98.79 244

DPM-MVS		97.55 120	96.99 151	99.23 49	99.04 129	98.55 33	97.17 411	98.35 253	94.85 230	97.93 162	98.58 214	95.07 81	99.71 142	92.60 344	99.34 137	99.43 128

c3_l		94.79 300	94.43 292	95.89 359	97.75 298	93.12 347	97.16 413	98.03 327	92.23 364	93.46 363	97.05 364	91.39 169	98.01 412	93.58 310	89.21 405	96.53 403

new-patchmatchnet		88.50 436	87.45 440	91.67 454	90.31 483	85.89 468	97.16 413	97.33 393	89.47 428	83.63 476	92.77 469	76.38 442	95.06 479	82.70 463	77.29 473	94.06 471

UnsupCasMVSNet_eth		90.99 410	89.92 407	94.19 427	94.08 455	89.83 420	97.13 415	98.67 150	93.69 297	85.83 466	96.19 415	75.15 452	96.74 455	89.14 418	79.41 467	96.00 434

IB-MVS	91.98 17	93.27 373	91.97 388	97.19 246	97.47 325	93.41 326	97.09 416	95.99 453	93.32 319	92.47 397	95.73 431	78.06 424	99.53 183	94.59 274	82.98 451	98.62 270
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		94.96 291	94.28 297	96.98 265	95.93 417	96.11 174	97.08 417	98.39 240	93.62 305	93.86 342	96.40 406	88.28 273	98.21 386	92.61 341	92.36 359	96.63 381

FE-MVSNET3		94.96 291	94.28 297	96.98 265	95.93 417	96.11 174	97.08 417	98.39 240	93.62 305	93.86 342	96.40 406	88.28 273	98.21 386	92.61 341	92.36 359	96.63 381

cl____		94.51 322	94.01 319	96.02 346	97.58 314	93.40 329	97.05 419	97.96 332	91.73 378	92.76 385	97.08 356	89.06 249	98.13 393	92.61 341	90.29 387	96.52 406

DIV-MVS_self_test		94.52 321	94.03 316	95.99 350	97.57 318	93.38 330	97.05 419	97.94 333	91.74 376	92.81 383	97.10 350	89.12 246	98.07 404	92.60 344	90.30 386	96.53 403

miper_ehance_all_eth		95.01 283	94.69 274	95.97 354	97.70 304	93.31 335	97.02 421	98.07 320	92.23 364	93.51 359	96.96 375	91.85 150	98.15 391	93.68 305	91.16 376	96.44 418

CMPMVS	66.06 21	89.70 427	89.67 411	89.78 457	93.19 463	76.56 483	97.00 422	98.35 253	80.97 477	81.57 479	97.75 296	74.75 455	98.61 336	89.85 404	93.63 336	94.17 467
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
tpmrst		95.63 243	95.69 225	95.44 381	97.54 319	88.54 449	96.97 423	97.56 366	93.50 311	97.52 202	96.93 379	89.49 230	99.16 252	95.25 245	96.42 284	98.64 269

dp		94.15 349	93.90 328	94.90 399	97.31 339	86.82 465	96.97 423	97.19 407	91.22 398	96.02 270	96.61 400	85.51 334	99.02 287	90.00 403	94.30 315	98.85 238

cl22		94.68 306	94.19 304	96.13 342	98.11 258	93.60 317	96.94 425	98.31 264	92.43 356	93.32 368	96.87 384	86.51 311	98.28 383	94.10 294	91.16 376	96.51 410

PM-MVS		87.77 438	86.55 444	91.40 455	91.03 481	83.36 477	96.92 426	95.18 466	91.28 395	86.48 464	93.42 461	53.27 489	96.74 455	89.43 414	81.97 455	94.11 468

TinyColmap		92.31 391	91.53 392	94.65 412	96.92 364	89.75 422	96.92 426	96.68 439	90.45 411	89.62 439	97.85 287	76.06 446	98.81 320	86.74 439	92.51 357	95.41 445

our_test_3		93.65 365	93.30 361	94.69 409	95.45 435	89.68 427	96.91 428	97.65 356	91.97 371	91.66 418	96.88 382	89.67 227	97.93 420	88.02 431	91.49 371	96.48 415

test-LLR		95.10 279	94.87 266	95.80 365	96.77 374	89.70 425	96.91 428	95.21 464	95.11 208	94.83 295	95.72 433	87.71 290	98.97 291	93.06 323	98.50 190	98.72 256

TESTMET0.1,1		94.18 348	93.69 346	95.63 373	96.92 364	89.12 437	96.91 428	94.78 472	93.17 326	94.88 292	96.45 404	78.52 418	98.92 302	93.09 322	98.50 190	98.85 238

test-mter		94.08 356	93.51 354	95.80 365	96.77 374	89.70 425	96.91 428	95.21 464	92.89 339	94.83 295	95.72 433	77.69 429	98.97 291	93.06 323	98.50 190	98.72 256

USDC		93.33 372	92.71 373	95.21 387	96.83 371	90.83 399	96.91 428	97.50 376	93.84 283	90.72 426	98.14 260	77.69 429	98.82 319	89.51 412	93.21 349	95.97 435

wanda-best-256-512		91.17 404	89.60 412	95.88 360	91.33 476	92.99 351	96.89 433	97.82 343	86.89 453	92.36 401	91.75 478	81.83 386	98.06 405	92.75 337	74.82 483	96.59 390

FE-blended-shiyan7		91.17 404	89.60 412	95.88 360	91.33 476	92.99 351	96.89 433	97.82 343	86.89 453	92.36 401	91.75 478	81.83 386	98.06 405	92.75 337	74.82 483	96.59 390

MDTV_nov1_ep13_2view						84.26 472	96.89 433		90.97 402	97.90 166		89.89 221		93.91 299		99.18 194

ppachtmachnet_test		93.22 375	92.63 375	94.97 396	95.45 435	90.84 398	96.88 436	97.88 337	90.60 407	92.08 412	97.26 339	88.08 281	97.86 426	85.12 452	90.33 385	96.22 427

tpmvs		94.60 312	94.36 295	95.33 385	97.46 326	88.60 448	96.88 436	97.68 352	91.29 394	93.80 347	96.42 405	88.58 264	99.24 239	91.06 385	96.04 302	98.17 298

MDTV_nov1_ep13			95.40 233		97.48 324	88.34 453	96.85 438	97.29 397	93.74 290	97.48 203	97.26 339	89.18 244	99.05 277	91.92 366	97.43 254

PatchmatchNet		95.71 238	95.52 229	96.29 337	97.58 314	90.72 401	96.84 439	97.52 374	94.06 267	97.08 218	96.96 375	89.24 243	98.90 307	92.03 362	98.37 206	99.26 176
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MSDG		95.93 226	95.30 245	97.83 196	98.90 145	95.36 233	96.83 440	98.37 248	91.32 392	94.43 310	98.73 197	90.27 213	99.60 166	90.05 401	98.82 169	98.52 280

thisisatest0515		95.61 247	94.89 265	97.76 205	98.15 255	95.15 246	96.77 441	94.41 475	92.95 337	97.18 214	97.43 327	84.78 349	99.45 202	94.63 268	97.73 240	98.68 263

GA-MVS		94.81 299	94.03 316	97.14 250	97.15 352	93.86 307	96.76 442	97.58 363	94.00 274	94.76 299	97.04 365	80.91 399	98.48 347	91.79 368	96.25 296	99.09 209

tpm cat1		93.36 369	92.80 371	95.07 394	97.58 314	87.97 458	96.76 442	97.86 338	82.17 475	93.53 356	96.04 421	86.13 322	99.13 261	89.24 417	95.87 306	98.10 301

eth_miper_zixun_eth		94.68 306	94.41 293	95.47 379	97.64 309	91.71 382	96.73 444	98.07 320	92.71 345	93.64 351	97.21 345	90.54 203	98.17 390	93.38 313	89.76 393	96.54 401

test_post1							96.68 445				30.43 502	87.85 289	98.69 328	92.59 346

pmmvs3		86.67 443	84.86 448	92.11 453	88.16 489	87.19 464	96.63 446	94.75 473	79.88 478	87.22 457	92.75 470	66.56 477	95.20 478	81.24 469	76.56 479	93.96 473

miper_enhance_ethall		95.10 279	94.75 270	96.12 343	97.53 321	93.73 314	96.61 447	98.08 318	92.20 367	93.89 339	96.65 397	92.44 126	98.30 379	94.21 287	91.16 376	96.34 421

testmvs		21.48 467	24.95 470	11.09 485	14.89 507	6.47 510	96.56 448	9.87 508	7.55 501	17.93 501	39.02 499	9.43 507	5.90 504	16.56 502	12.72 501	20.91 499

test123		20.95 468	23.72 471	12.64 484	13.54 508	8.19 509	96.55 449	6.13 509	7.48 502	16.74 502	37.98 500	12.97 504	6.05 503	16.69 501	5.43 502	23.68 498

CL-MVSNet_self_test		90.11 423	89.14 420	93.02 443	91.86 470	88.23 456	96.51 450	98.07 320	90.49 408	90.49 429	94.41 451	84.75 350	95.34 475	80.79 470	74.95 482	95.50 444

GG-mvs-BLEND				96.59 304	96.34 397	94.98 256	96.51 450	88.58 497		93.10 378	94.34 455	80.34 407	98.05 408	89.53 411	96.99 263	96.74 366

new_pmnet		90.06 424	89.00 423	93.22 441	94.18 451	88.32 454	96.42 452	96.89 430	86.19 458	85.67 467	93.62 458	77.18 436	97.10 448	81.61 467	89.29 404	94.23 465

PVSNet	91.96 18	96.35 205	96.15 198	96.96 268	99.17 111	92.05 375	96.08 453	98.68 145	93.69 297	97.75 179	97.80 294	88.86 259	99.69 148	94.26 286	99.01 155	99.15 196

ADS-MVSNet2		94.58 315	94.40 294	95.11 391	98.00 274	88.74 446	96.04 454	97.30 396	90.15 416	96.47 255	96.64 398	87.89 286	97.56 440	90.08 399	97.06 261	99.02 222

ADS-MVSNet		95.00 284	94.45 290	96.63 298	98.00 274	91.91 377	96.04 454	97.74 351	90.15 416	96.47 255	96.64 398	87.89 286	98.96 295	90.08 399	97.06 261	99.02 222

PAPM		94.95 293	94.00 320	97.78 201	97.04 357	95.65 213	96.03 456	98.25 283	91.23 397	94.19 326	97.80 294	91.27 175	98.86 313	82.61 464	97.61 243	98.84 240

cascas		94.63 311	93.86 332	96.93 270	96.91 366	94.27 293	96.00 457	98.51 194	85.55 464	94.54 302	96.23 412	84.20 365	98.87 311	95.80 222	96.98 266	97.66 316

gg-mvs-nofinetune		92.21 392	90.58 400	97.13 251	96.75 377	95.09 248	95.85 458	89.40 496	85.43 465	94.50 304	81.98 491	80.80 402	98.40 369	92.16 356	98.33 209	97.88 307

FPMVS		77.62 457	77.14 457	79.05 477	79.25 500	60.97 502	95.79 459	95.94 456	65.96 491	67.93 493	94.40 452	37.73 496	88.88 494	68.83 489	88.46 414	87.29 488

CHOSEN 280x420		97.18 160	97.18 133	97.20 244	98.81 157	93.27 338	95.78 460	99.15 41	95.25 197	96.79 237	98.11 262	92.29 132	99.07 274	98.56 54	99.85 6	99.25 178

mamba_0408		96.81 181	96.38 189	98.09 169	98.19 244	95.90 192	95.69 461	98.32 260	94.51 251	96.75 238	98.73 197	90.99 191	99.27 227	95.83 218	98.43 198	99.10 206

SSM_04072		96.71 186	96.38 189	97.68 214	98.19 244	95.90 192	95.69 461	98.32 260	94.51 251	96.75 238	98.73 197	90.99 191	98.02 411	95.83 218	98.43 198	99.10 206

MIMVSNet		93.26 374	92.21 385	96.41 327	97.73 302	93.13 345	95.65 463	97.03 418	91.27 396	94.04 333	96.06 419	75.33 449	97.19 447	86.56 440	96.23 298	98.92 233

KD-MVS_2432*1600		89.61 429	87.96 437	94.54 416	94.06 456	91.59 384	95.59 464	97.63 359	89.87 421	88.95 446	94.38 453	78.28 421	96.82 453	84.83 454	68.05 492	95.21 449

miper_refine_blended		89.61 429	87.96 437	94.54 416	94.06 456	91.59 384	95.59 464	97.63 359	89.87 421	88.95 446	94.38 453	78.28 421	96.82 453	84.83 454	68.05 492	95.21 449

PCF-MVS	93.45 11	94.68 306	93.43 358	98.42 130	98.62 179	96.77 136	95.48 466	98.20 289	84.63 468	93.34 367	98.32 243	88.55 268	99.81 102	84.80 456	98.96 158	98.68 263
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
0.4-1-1-0.1		90.89 411	88.97 424	96.67 292	94.15 452	92.76 359	95.28 467	95.03 469	89.11 434	90.43 430	89.57 483	75.41 448	99.04 280	94.70 264	77.06 475	98.20 297

mvs5depth		91.23 402	90.17 404	94.41 423	92.09 468	89.79 421	95.26 468	96.50 445	90.73 405	91.69 417	97.06 361	76.12 445	98.62 335	88.02 431	84.11 447	94.82 458

JIA-IIPM		93.35 370	92.49 380	95.92 356	96.48 391	90.65 403	95.01 469	96.96 424	85.93 461	96.08 268	87.33 488	87.70 292	98.78 323	91.35 377	95.58 310	98.34 290

CR-MVSNet		94.76 303	94.15 308	96.59 304	97.00 358	93.43 324	94.96 470	97.56 366	92.46 352	96.93 226	96.24 410	88.15 278	97.88 425	87.38 436	96.65 276	98.46 284

RPMNet		92.81 383	91.34 394	97.24 242	97.00 358	93.43 324	94.96 470	98.80 114	82.27 474	96.93 226	92.12 475	86.98 305	99.82 97	76.32 483	96.65 276	98.46 284

UnsupCasMVSNet_bld		87.17 440	85.12 447	93.31 439	91.94 469	88.77 444	94.92 472	98.30 271	84.30 469	82.30 477	90.04 482	63.96 482	97.25 446	85.85 446	74.47 489	93.93 474

PVSNet_0	88.72 19	91.28 401	90.03 406	95.00 395	97.99 276	87.29 463	94.84 473	98.50 199	92.06 369	89.86 436	95.19 442	79.81 409	99.39 210	92.27 355	69.79 491	98.33 291

Patchmatch-test		94.42 330	93.68 347	96.63 298	97.60 312	91.76 379	94.83 474	97.49 378	89.45 429	94.14 328	97.10 350	88.99 251	98.83 317	85.37 450	98.13 223	99.29 163

testf1		79.02 451	77.70 453	82.99 471	88.10 490	66.90 497	94.67 475	93.11 484	71.08 489	74.02 487	93.41 462	34.15 498	93.25 485	72.25 486	78.50 470	88.82 485

APD_test2		79.02 451	77.70 453	82.99 471	88.10 490	66.90 497	94.67 475	93.11 484	71.08 489	74.02 487	93.41 462	34.15 498	93.25 485	72.25 486	78.50 470	88.82 485

Patchmtry		93.22 375	92.35 383	95.84 364	96.77 374	93.09 348	94.66 477	97.56 366	87.37 447	92.90 381	96.24 410	88.15 278	97.90 421	87.37 437	90.10 390	96.53 403

kuosan		78.45 454	77.69 455	80.72 475	92.73 467	75.32 488	94.63 478	74.51 504	75.96 485	80.87 483	93.19 464	63.23 483	79.99 499	42.56 498	81.56 458	86.85 491

dongtai		82.47 448	81.88 451	84.22 467	95.19 440	76.03 484	94.59 479	74.14 505	82.63 472	87.19 458	96.09 418	64.10 481	87.85 495	58.91 492	84.11 447	88.78 487

PatchT		93.06 381	91.97 388	96.35 332	96.69 380	92.67 360	94.48 480	97.08 412	86.62 455	97.08 218	92.23 474	87.94 285	97.90 421	78.89 476	96.69 274	98.49 282

0.3-1-1-0.015		90.29 420	88.21 432	96.51 315	93.56 460	92.44 362	94.41 481	95.03 469	88.71 438	89.20 444	88.50 485	73.12 464	99.04 280	94.67 267	76.70 477	98.05 302

LCM-MVSNet		78.70 453	76.24 459	86.08 463	77.26 502	71.99 493	94.34 482	96.72 437	61.62 493	76.53 485	89.33 484	33.91 500	92.78 488	81.85 466	74.60 488	93.46 476

PMMVS2		77.95 456	75.44 460	85.46 464	82.54 497	74.95 489	94.23 483	93.08 486	72.80 488	74.68 486	87.38 487	36.36 497	91.56 489	73.95 484	63.94 494	89.87 484

MVS-HIRNet		89.46 432	88.40 429	92.64 446	97.58 314	82.15 479	94.16 484	93.05 487	75.73 487	90.90 424	82.52 490	79.42 412	98.33 374	83.53 461	98.68 173	97.43 321

0.4-1-1-0.2		90.43 417	88.45 428	96.38 330	93.34 462	92.12 369	93.88 485	95.04 468	88.62 440	90.00 435	88.31 486	75.31 450	99.03 283	94.61 271	76.91 476	98.01 306

Patchmatch-RL test		91.49 396	90.85 397	93.41 436	91.37 475	84.40 471	92.81 486	95.93 457	91.87 374	87.25 456	94.87 446	88.99 251	96.53 462	92.54 350	82.00 454	99.30 160

ambc				89.49 458	86.66 492	75.78 485	92.66 487	96.72 437		86.55 463	92.50 471	46.01 490	97.90 421	90.32 395	82.09 453	94.80 460

EMVS		64.07 463	63.26 466	66.53 482	81.73 499	58.81 505	91.85 488	84.75 499	51.93 497	59.09 497	75.13 496	43.32 493	79.09 500	42.03 499	39.47 497	61.69 496

E-PMN		64.94 462	64.25 464	67.02 481	82.28 498	59.36 504	91.83 489	85.63 498	52.69 495	60.22 496	77.28 495	41.06 495	80.12 498	46.15 497	41.14 496	61.57 497

ANet_high		69.08 459	65.37 463	80.22 476	65.99 504	71.96 494	90.91 490	90.09 495	82.62 473	49.93 499	78.39 494	29.36 501	81.75 496	62.49 491	38.52 498	86.95 490

tmp_tt		68.90 460	66.97 462	74.68 479	50.78 506	59.95 503	87.13 491	83.47 500	38.80 499	62.21 495	96.23 412	64.70 480	76.91 501	88.91 422	30.49 499	87.19 489

MVE	62.14 22	63.28 464	59.38 467	74.99 478	74.33 503	65.47 499	85.55 492	80.50 502	52.02 496	51.10 498	75.00 497	10.91 506	80.50 497	51.60 495	53.40 495	78.99 493
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	61.03 23	65.95 461	63.57 465	73.09 480	57.90 505	51.22 507	85.05 493	93.93 482	54.45 494	44.32 500	83.57 489	13.22 503	89.15 493	58.68 493	81.00 461	78.91 494
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_method		79.03 450	78.17 452	81.63 474	86.06 495	54.40 506	82.75 494	96.89 430	39.54 498	80.98 482	95.57 438	58.37 486	94.73 481	84.74 457	78.61 469	95.75 440

Gipuma		78.40 455	76.75 458	83.38 470	95.54 429	80.43 482	79.42 495	97.40 388	64.67 492	73.46 489	80.82 493	45.65 491	93.14 487	66.32 490	87.43 424	76.56 495
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
wuyk23d		30.17 465	30.18 469	30.16 483	78.61 501	43.29 508	66.79 496	14.21 507	17.31 500	14.82 503	11.93 503	11.55 505	41.43 502	37.08 500	19.30 500	5.76 500

mmdepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

monomultidepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

test_blank		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet_test		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

DCPMVS		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

cdsmvs_eth3d_5k		23.98 466	31.98 468	0.00 486	0.00 509	0.00 511	0.00 497	98.59 171	0.00 504	0.00 505	98.61 209	90.60 201	0.00 505	0.00 503	0.00 503	0.00 501

pcd_1.5k_mvsjas		7.88 470	10.50 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	94.51 91	0.00 505	0.00 503	0.00 503	0.00 501

sosnet-low-res		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

sosnet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uncertanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

Regformer		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

ab-mvs-re		8.20 469	10.94 472	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	98.43 227	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

WAC-MVS						90.94 394								88.66 424

MSC_two_6792asdad				99.62 7	99.17 111	99.08 12		98.63 161					99.94 14	98.53 55	99.80 25	99.86 13

PC_three_1452									95.08 212	99.60 33	99.16 107	97.86 2	98.47 350	97.52 135	99.72 66	99.74 50

No_MVS				99.62 7	99.17 111	99.08 12		98.63 161					99.94 14	98.53 55	99.80 25	99.86 13

test_one_0601					99.66 31	99.25 2		98.86 91	97.55 49	99.20 60	99.47 37	97.57 7

eth-test2					0.00 509

eth-test					0.00 509

ZD-MVS					99.46 58	98.70 28		98.79 119	93.21 324	98.67 105	98.97 150	95.70 52	99.83 90	96.07 207	99.58 97

IU-MVS					99.71 24	99.23 7		98.64 158	95.28 195	99.63 32				98.35 72	99.81 16	99.83 19

test_241102_TWO								98.87 85	97.65 41	99.53 38	99.48 35	97.34 12	99.94 14	98.43 67	99.80 25	99.83 19

test_241102_ONE					99.71 24	99.24 5		98.87 85	97.62 43	99.73 23	99.39 50	97.53 8	99.74 134

test_0728_THIRD									97.32 65	99.45 40	99.46 42	97.88 1	99.94 14	98.47 63	99.86 2	99.85 16

GSMVS																99.20 185

test_part2					99.63 34	99.18 10				99.27 57

sam_mvs1												89.45 235				99.20 185

sam_mvs												88.99 251

MTGPA								98.74 129

test_post											31.83 501	88.83 260	98.91 304

patchmatchnet-post											95.10 444	89.42 236	98.89 308

gm-plane-assit					95.88 420	87.47 461			89.74 424		96.94 378		99.19 249	93.32 316

test9_res														96.39 201	99.57 98	99.69 70

agg_prior2														95.87 217	99.57 98	99.68 75

agg_prior					99.30 83	98.38 41		98.72 134		97.57 201			99.81 102

TestCases				96.99 262	99.25 96	93.21 343		98.18 294	91.36 388	93.52 357	98.77 190	84.67 353	99.72 137	89.70 408	97.87 232	98.02 304

test_prior				99.19 51	99.31 79	98.22 58		98.84 96					99.70 143			99.65 83

新几何1				99.16 56	99.34 71	98.01 71		98.69 142	90.06 418	98.13 136	98.95 157	94.60 89	99.89 68	91.97 365	99.47 121	99.59 94

旧先验1					99.29 88	97.48 90		98.70 140			99.09 130	95.56 55			99.47 121	99.61 90

原ACMM1				98.65 98	99.32 77	96.62 141		98.67 150	93.27 323	97.81 173	98.97 150	95.18 76	99.83 90	93.84 301	99.46 124	99.50 107

testdata2													99.89 68	91.65 373

segment_acmp												96.85 15

testdata				98.26 142	99.20 109	95.36 233		98.68 145	91.89 373	98.60 113	99.10 122	94.44 96	99.82 97	94.27 285	99.44 125	99.58 98

test12				99.18 53	99.16 115	98.19 60		98.53 188		98.07 140		95.13 79	99.72 137		99.56 106	99.63 88

plane_prior7					97.42 331	94.63 273

plane_prior6					97.35 338	94.61 276						87.09 302

plane_prior5								98.56 182					99.03 283	96.07 207	94.27 316	96.92 342

plane_prior4											98.28 246

plane_prior3						94.61 276			97.02 89	95.34 282

plane_prior1					97.37 337

n2								0.00 510

nn								0.00 510

door-mid								94.37 476

lessismore_v0				94.45 422	94.93 444	88.44 452		91.03 493		86.77 461	97.64 310	76.23 444	98.42 356	90.31 396	85.64 442	96.51 410

LGP-MVS_train				96.47 320	97.46 326	93.54 319		98.54 186	94.67 241	94.36 314	98.77 190	85.39 335	99.11 266	95.71 226	94.15 322	96.76 364

test11								98.66 153

door								94.64 474

HQP5-MVS						94.25 295

BP-MVS														95.30 241

HQP4-MVS										94.45 306			98.96 295			96.87 354

HQP3-MVS								98.46 207							94.18 320

HQP2-MVS												86.75 308

NP-MVS					97.28 340	94.51 281					97.73 297

ACMMP++_ref															92.97 350

ACMMP++															93.61 337

Test By Simon												94.64 88

ITE_SJBPF				95.44 381	97.42 331	91.32 388		97.50 376	95.09 211	93.59 352	98.35 237	81.70 389	98.88 310	89.71 407	93.39 343	96.12 431

DeepMVS_CX				86.78 462	97.09 356	72.30 492		95.17 467	75.92 486	84.34 474	95.19 442	70.58 467	95.35 474	79.98 473	89.04 408	92.68 480

High-resolution multi-view benchmark