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.

CS-MVS		99.50 20	99.48 15	99.54 99	99.76 65	99.42 99	99.90 1	99.55 77	98.56 89	99.78 47	99.70 157	98.65 68	99.79 191	99.65 23	99.78 108	99.41 199

CS-MVS-test		99.49 22	99.48 15	99.54 99	99.78 56	99.30 113	99.89 2	99.58 61	98.56 89	99.73 65	99.69 167	98.55 75	99.82 177	99.69 19	99.85 73	99.48 179

mvsmamba		98.92 127	98.87 120	99.08 180	99.07 295	99.16 130	99.88 3	99.51 115	98.15 135	99.40 157	99.89 29	97.12 132	99.33 294	99.38 49	97.40 284	98.73 271

MVSFormer		99.17 84	99.12 78	99.29 156	99.51 170	98.94 168	99.88 3	99.46 187	97.55 210	99.80 40	99.65 185	97.39 121	99.28 302	99.03 88	99.85 73	99.65 129

test_djsdf		98.67 160	98.57 160	98.98 193	98.70 348	98.91 172	99.88 3	99.46 187	97.55 210	99.22 199	99.88 35	95.73 185	99.28 302	99.03 88	97.62 262	98.75 266

OurMVSNet-221017-0		97.88 238	97.77 229	98.19 297	98.71 347	96.53 318	99.88 3	99.00 323	97.79 183	98.78 275	99.94 6	91.68 316	99.35 291	97.21 277	96.99 296	98.69 282

EC-MVSNet		99.44 37	99.39 27	99.58 92	99.56 156	99.49 89	99.88 3	99.58 61	98.38 106	99.73 65	99.69 167	98.20 95	99.70 229	99.64 24	99.82 94	99.54 161

DVP-MVS++		99.59 8	99.50 13	99.88 5	99.51 170	99.88 8	99.87 8	99.51 115	98.99 45	99.88 20	99.81 89	99.27 5	99.96 30	98.85 115	99.80 101	99.81 61

FOURS1					99.91 1	99.93 1	99.87 8	99.56 69	99.10 27	99.81 37

K. test v3		97.10 311	96.79 311	98.01 309	98.72 345	96.33 325	99.87 8	97.05 393	97.59 204	96.16 371	99.80 103	88.71 352	99.04 339	96.69 308	96.55 302	98.65 304

FC-MVSNet-test		98.75 153	98.62 153	99.15 177	99.08 294	99.45 95	99.86 11	99.60 54	98.23 125	98.70 287	99.82 74	96.80 145	99.22 313	99.07 86	96.38 305	98.79 258

v7n		97.87 240	97.52 255	98.92 203	98.76 341	98.58 203	99.84 12	99.46 187	96.20 324	98.91 255	99.70 157	94.89 213	99.44 273	96.03 322	93.89 358	98.75 266

DTE-MVSNet		97.51 289	97.19 297	98.46 270	98.63 354	98.13 235	99.84 12	99.48 157	96.68 287	97.97 339	99.67 179	92.92 280	98.56 370	96.88 301	92.60 373	98.70 278

3Dnovator	97.25 9	99.24 76	99.05 87	99.81 44	99.12 283	99.66 53	99.84 12	99.74 10	99.09 32	98.92 254	99.90 25	95.94 176	99.98 13	98.95 96	99.92 28	99.79 74

FIs		98.78 149	98.63 148	99.23 167	99.18 267	99.54 79	99.83 15	99.59 57	98.28 117	98.79 274	99.81 89	96.75 148	99.37 284	99.08 85	96.38 305	98.78 259

MGCFI-Net		99.01 120	98.85 125	99.50 120	99.42 200	99.26 119	99.82 16	99.48 157	98.60 86	99.28 183	98.81 354	97.04 138	99.76 202	99.29 64	97.87 251	99.47 185

test_fmvs3		92.10 358	91.77 361	93.08 371	96.19 390	86.25 393	99.82 16	98.62 369	96.65 290	95.19 379	96.90 391	55.05 406	95.93 399	96.63 312	90.92 381	97.06 387

jajsoiax		98.43 172	98.28 178	98.88 214	98.60 358	98.43 221	99.82 16	99.53 96	98.19 130	98.63 298	99.80 103	93.22 275	99.44 273	99.22 72	97.50 273	98.77 262

OpenMVS	96.50 16	98.47 169	98.12 189	99.52 113	99.04 303	99.53 82	99.82 16	99.72 11	94.56 363	98.08 332	99.88 35	94.73 225	99.98 13	97.47 262	99.76 114	99.06 239

SDMVSNet		99.11 102	98.90 114	99.75 58	99.81 46	99.59 70	99.81 20	99.65 33	98.78 73	99.64 97	99.88 35	94.56 235	99.93 84	99.67 21	98.26 230	99.72 103

nrg030		98.64 163	98.42 168	99.28 160	99.05 302	99.69 47	99.81 20	99.46 187	98.04 159	99.01 240	99.82 74	96.69 150	99.38 281	99.34 58	94.59 346	98.78 259

HPM-MVS		99.42 42	99.28 55	99.83 40	99.90 4	99.72 42	99.81 20	99.54 85	97.59 204	99.68 78	99.63 197	98.91 34	99.94 69	98.58 155	99.91 35	99.84 40
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EPP-MVSNet		99.13 92	98.99 101	99.53 107	99.65 126	99.06 147	99.81 20	99.33 260	97.43 226	99.60 110	99.88 35	97.14 131	99.84 157	99.13 80	98.94 189	99.69 115

3Dnovator+	97.12 13	99.18 82	98.97 105	99.82 41	99.17 275	99.68 48	99.81 20	99.51 115	99.20 18	98.72 280	99.89 29	95.68 187	99.97 21	98.86 113	99.86 66	99.81 61

sasdasda		99.02 116	98.86 123	99.51 115	99.42 200	99.32 107	99.80 25	99.48 157	98.63 82	99.31 176	98.81 354	97.09 134	99.75 205	99.27 67	97.90 248	99.47 185

FA-MVS(test-final)		98.75 153	98.53 164	99.41 134	99.55 160	99.05 149	99.80 25	99.01 322	96.59 299	99.58 114	99.59 211	95.39 195	99.90 116	97.78 228	99.49 147	99.28 217

GeoE		98.85 141	98.62 153	99.53 107	99.61 141	99.08 144	99.80 25	99.51 115	97.10 258	99.31 176	99.78 122	95.23 204	99.77 198	98.21 190	99.03 184	99.75 88

canonicalmvs		99.02 116	98.86 123	99.51 115	99.42 200	99.32 107	99.80 25	99.48 157	98.63 82	99.31 176	98.81 354	97.09 134	99.75 205	99.27 67	97.90 248	99.47 185

v8		97.95 230	97.63 247	98.93 201	98.95 317	98.81 186	99.80 25	99.41 216	96.03 338	99.10 224	99.42 266	94.92 211	99.30 300	96.94 296	94.08 355	98.66 302

Vis-MVSNet (Re-imp)		98.87 131	98.72 137	99.31 148	99.71 96	98.88 174	99.80 25	99.44 206	97.91 169	99.36 167	99.78 122	95.49 193	99.43 277	97.91 215	99.11 175	99.62 142

Anonymous20240521		96.20 328	95.89 331	97.13 345	97.72 378	94.96 357	99.79 31	99.29 283	93.01 377	97.20 359	99.03 334	89.69 344	98.36 374	91.16 381	96.13 310	98.07 364

PS-MVSNAJss		98.92 127	98.92 111	98.90 209	98.78 336	98.53 207	99.78 32	99.54 85	98.07 153	99.00 244	99.76 134	99.01 18	99.37 284	99.13 80	97.23 290	98.81 257

PEN-MVS		97.76 258	97.44 269	98.72 239	98.77 340	98.54 206	99.78 32	99.51 115	97.06 262	98.29 322	99.64 191	92.63 293	98.89 361	98.09 199	93.16 366	98.72 272

anonymousdsp		98.44 171	98.28 178	98.94 199	98.50 363	98.96 162	99.77 34	99.50 135	97.07 260	98.87 263	99.77 130	94.76 223	99.28 302	98.66 142	97.60 263	98.57 330

SixPastTwentyTwo		97.50 290	97.33 286	98.03 306	98.65 352	96.23 329	99.77 34	98.68 366	97.14 251	97.90 340	99.93 9	90.45 334	99.18 321	97.00 290	96.43 304	98.67 294

QAPM		98.67 160	98.30 177	99.80 46	99.20 261	99.67 51	99.77 34	99.72 11	94.74 360	98.73 279	99.90 25	95.78 183	99.98 13	96.96 294	99.88 55	99.76 87

SSC-MVS		92.73 357	93.73 353	89.72 381	95.02 400	81.38 401	99.76 37	99.23 293	94.87 357	92.80 390	98.93 346	94.71 227	91.37 405	74.49 405	93.80 359	96.42 391

test_vis3_rt		87.04 364	85.81 367	90.73 378	93.99 402	81.96 399	99.76 37	90.23 413	92.81 379	81.35 401	91.56 401	40.06 410	99.07 336	94.27 355	88.23 388	91.15 401

dcpmvs_2		99.23 77	99.58 7	98.16 299	99.83 39	94.68 360	99.76 37	99.52 101	99.07 35	99.98 6	99.88 35	98.56 74	99.93 84	99.67 21	99.98 4	99.87 31

HPM-MVS_fast		99.51 18	99.40 25	99.85 28	99.91 1	99.79 30	99.76 37	99.56 69	97.72 191	99.76 57	99.75 137	99.13 12	99.92 95	99.07 86	99.92 28	99.85 36

v10		97.85 243	97.52 255	98.86 221	98.99 310	98.67 195	99.75 41	99.41 216	95.70 342	98.98 246	99.41 270	94.75 224	99.23 310	96.01 324	94.63 345	98.67 294

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 62	99.89 4	99.75 41	99.56 69	99.02 38	99.88 20	99.85 52	99.18 10	99.96 30	99.22 72	99.92 28	99.90 17
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
IS-MVSNet		99.05 111	98.87 120	99.57 94	99.73 87	99.32 107	99.75 41	99.20 299	98.02 162	99.56 118	99.86 47	96.54 155	99.67 237	98.09 199	99.13 174	99.73 97

test_vis1_n		97.92 234	97.44 269	99.34 141	99.53 163	98.08 237	99.74 44	99.49 144	99.15 20	100.00 1	99.94 6	79.51 394	99.98 13	99.88 14	99.76 114	99.97 4

test_fmvs1_n		98.41 175	98.14 186	99.21 168	99.82 42	97.71 261	99.74 44	99.49 144	99.32 14	99.99 2	99.95 3	85.32 377	99.97 21	99.82 16	99.84 81	99.96 7

tttt0517		98.42 173	98.14 186	99.28 160	99.66 120	98.38 224	99.74 44	96.85 394	97.68 197	99.79 42	99.74 142	91.39 324	99.89 127	98.83 121	99.56 142	99.57 156

WB-MVS		93.10 355	94.10 349	90.12 380	95.51 398	81.88 400	99.73 47	99.27 287	95.05 353	93.09 389	98.91 350	94.70 228	91.89 404	76.62 403	94.02 357	96.58 390

test_fmvs2		97.25 305	97.30 289	97.09 347	99.43 198	93.31 378	99.73 47	98.87 344	98.83 64	99.28 183	99.80 103	84.45 382	99.66 240	97.88 217	97.45 278	98.30 353

baseline		99.15 88	99.02 95	99.53 107	99.66 120	99.14 136	99.72 49	99.48 157	98.35 111	99.42 148	99.84 62	96.07 169	99.79 191	99.51 35	99.14 173	99.67 122

RPSCF		98.22 189	98.62 153	96.99 348	99.82 42	91.58 387	99.72 49	99.44 206	96.61 295	99.66 87	99.89 29	95.92 177	99.82 177	97.46 263	99.10 178	99.57 156

CSCG		99.32 61	99.32 40	99.32 147	99.85 26	98.29 226	99.71 51	99.66 28	98.11 145	99.41 152	99.80 103	98.37 88	99.96 30	98.99 92	99.96 13	99.72 103

dmvs_re		98.08 206	98.16 183	97.85 319	99.55 160	94.67 361	99.70 52	98.92 333	98.15 135	99.06 234	99.35 287	93.67 269	99.25 307	97.77 231	97.25 289	99.64 136

WR-MVS_H		98.13 200	97.87 220	98.90 209	99.02 305	98.84 180	99.70 52	99.59 57	97.27 240	98.40 314	99.19 318	95.53 191	99.23 310	98.34 182	93.78 360	98.61 324

LTVRE_ROB	97.16 12	98.02 218	97.90 215	98.40 279	99.23 254	96.80 308	99.70 52	99.60 54	97.12 254	98.18 329	99.70 157	91.73 315	99.72 217	98.39 176	97.45 278	98.68 287
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
test_f		91.90 359	91.26 363	93.84 368	95.52 397	85.92 394	99.69 55	98.53 373	95.31 347	93.87 385	96.37 394	55.33 405	98.27 375	95.70 330	90.98 380	97.32 386

XVS		99.53 16	99.42 22	99.87 11	99.85 26	99.83 16	99.69 55	99.68 20	98.98 48	99.37 164	99.74 142	98.81 44	99.94 69	98.79 126	99.86 66	99.84 40

X-MVStestdata		96.55 320	95.45 338	99.87 11	99.85 26	99.83 16	99.69 55	99.68 20	98.98 48	99.37 164	64.01 410	98.81 44	99.94 69	98.79 126	99.86 66	99.84 40

V42		98.06 208	97.79 224	98.86 221	98.98 313	98.84 180	99.69 55	99.34 253	96.53 301	99.30 179	99.37 281	94.67 230	99.32 297	97.57 252	94.66 344	98.42 345

mPP-MVS		99.44 37	99.30 49	99.86 21	99.88 11	99.79 30	99.69 55	99.48 157	98.12 143	99.50 130	99.75 137	98.78 48	99.97 21	98.57 158	99.89 52	99.83 49

CP-MVS		99.45 33	99.32 40	99.85 28	99.83 39	99.75 39	99.69 55	99.52 101	98.07 153	99.53 125	99.63 197	98.93 33	99.97 21	98.74 130	99.91 35	99.83 49

FE-MVS		98.48 168	98.17 182	99.40 135	99.54 162	98.96 162	99.68 61	98.81 351	95.54 344	99.62 104	99.70 157	93.82 264	99.93 84	97.35 271	99.46 148	99.32 214

PS-CasMVS		97.93 231	97.59 250	98.95 198	98.99 310	99.06 147	99.68 61	99.52 101	97.13 252	98.31 319	99.68 173	92.44 302	99.05 338	98.51 166	94.08 355	98.75 266

Vis-MVSNet		99.12 98	98.97 105	99.56 96	99.78 56	99.10 140	99.68 61	99.66 28	98.49 97	99.86 27	99.87 43	94.77 222	99.84 157	99.19 75	99.41 152	99.74 92
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_vis1_n_1920		98.63 164	98.40 170	99.31 148	99.86 20	97.94 249	99.67 64	99.62 41	99.43 7	99.99 2	99.91 19	87.29 368	100.00 1	99.92 12	99.92 28	99.98 2

EIA-MVS		99.18 82	99.09 83	99.45 128	99.49 181	99.18 127	99.67 64	99.53 96	97.66 200	99.40 157	99.44 262	98.10 99	99.81 182	98.94 97	99.62 138	99.35 209

MSP-MVS		99.42 42	99.27 59	99.88 5	99.89 8	99.80 27	99.67 64	99.50 135	98.70 78	99.77 51	99.49 247	98.21 94	99.95 59	98.46 172	99.77 111	99.88 26
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
MVS_Test		99.10 106	98.97 105	99.48 122	99.49 181	99.14 136	99.67 64	99.34 253	97.31 237	99.58 114	99.76 134	97.65 114	99.82 177	98.87 108	99.07 181	99.46 190

CP-MVSNet		98.09 204	97.78 227	99.01 189	98.97 315	99.24 122	99.67 64	99.46 187	97.25 242	98.48 311	99.64 191	93.79 265	99.06 337	98.63 145	94.10 354	98.74 269

MTAPA		99.52 17	99.39 27	99.89 4	99.90 4	99.86 13	99.66 69	99.47 177	98.79 70	99.68 78	99.81 89	98.43 83	99.97 21	98.88 105	99.90 43	99.83 49

HFP-MVS		99.49 22	99.37 30	99.86 21	99.87 15	99.80 27	99.66 69	99.67 23	98.15 135	99.68 78	99.69 167	99.06 16	99.96 30	98.69 138	99.87 58	99.84 40

mvs_tets		98.40 178	98.23 180	98.91 207	98.67 351	98.51 213	99.66 69	99.53 96	98.19 130	98.65 296	99.81 89	92.75 284	99.44 273	99.31 61	97.48 277	98.77 262

EU-MVSNet		97.98 225	98.03 201	97.81 325	98.72 345	96.65 314	99.66 69	99.66 28	98.09 148	98.35 317	99.82 74	95.25 203	98.01 381	97.41 267	95.30 332	98.78 259

ACMMPR		99.49 22	99.36 32	99.86 21	99.87 15	99.79 30	99.66 69	99.67 23	98.15 135	99.67 82	99.69 167	98.95 27	99.96 30	98.69 138	99.87 58	99.84 40

MP-MVS		99.33 59	99.15 73	99.87 11	99.88 11	99.82 22	99.66 69	99.46 187	98.09 148	99.48 134	99.74 142	98.29 91	99.96 30	97.93 214	99.87 58	99.82 54
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test_cas_vis1_n_1920		99.16 86	99.01 99	99.61 86	99.81 46	98.86 178	99.65 75	99.64 36	99.39 10	99.97 13	99.94 6	93.20 276	99.98 13	99.55 29	99.91 35	99.99 1

region2R		99.48 26	99.35 34	99.87 11	99.88 11	99.80 27	99.65 75	99.66 28	98.13 140	99.66 87	99.68 173	98.96 24	99.96 30	98.62 146	99.87 58	99.84 40

TranMVSNet+NR-MVSNet		97.93 231	97.66 242	98.76 236	98.78 336	98.62 200	99.65 75	99.49 144	97.76 187	98.49 310	99.60 209	94.23 248	98.97 355	98.00 210	92.90 368	98.70 278

mvsany_test3		93.77 353	93.45 357	94.74 366	95.78 393	88.01 392	99.64 78	98.25 377	98.28 117	94.31 383	97.97 383	68.89 398	98.51 372	97.50 258	90.37 382	97.71 378

ZNCC-MVS		99.47 29	99.33 38	99.87 11	99.87 15	99.81 25	99.64 78	99.67 23	98.08 152	99.55 122	99.64 191	98.91 34	99.96 30	98.72 133	99.90 43	99.82 54

tfpnnormal		97.84 246	97.47 261	98.98 193	99.20 261	99.22 124	99.64 78	99.61 48	96.32 315	98.27 323	99.70 157	93.35 272	99.44 273	95.69 331	95.40 330	98.27 355

casdiffmvs_mvg		99.15 88	99.02 95	99.55 98	99.66 120	99.09 141	99.64 78	99.56 69	98.26 120	99.45 139	99.87 43	96.03 171	99.81 182	99.54 30	99.15 172	99.73 97
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SR-MVS-dyc-post		99.45 33	99.31 47	99.85 28	99.76 65	99.82 22	99.63 82	99.52 101	98.38 106	99.76 57	99.82 74	98.53 76	99.95 59	98.61 149	99.81 97	99.77 82

RE-MVS-def			99.34 36		99.76 65	99.82 22	99.63 82	99.52 101	98.38 106	99.76 57	99.82 74	98.75 55		98.61 149	99.81 97	99.77 82

TSAR-MVS + MP.		99.58 9	99.50 13	99.81 44	99.91 1	99.66 53	99.63 82	99.39 225	98.91 58	99.78 47	99.85 52	99.36 2	99.94 69	98.84 118	99.88 55	99.82 54
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
Anonymous20231206		96.22 326	96.03 327	96.79 356	97.31 384	94.14 368	99.63 82	99.08 313	96.17 327	97.04 363	99.06 331	93.94 259	97.76 387	86.96 396	95.06 337	98.47 339

APD-MVS_3200maxsize		99.48 26	99.35 34	99.85 28	99.76 65	99.83 16	99.63 82	99.54 85	98.36 110	99.79 42	99.82 74	98.86 38	99.95 59	98.62 146	99.81 97	99.78 80

test0726					99.85 26	99.89 4	99.62 87	99.50 135	99.10 27	99.86 27	99.82 74	98.94 29

EPNet		98.86 134	98.71 139	99.30 153	97.20 386	98.18 231	99.62 87	98.91 337	99.28 16	98.63 298	99.81 89	95.96 173	99.99 4	99.24 71	99.72 122	99.73 97
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t		98.93 126	98.67 143	99.72 65	99.85 26	99.53 82	99.62 87	99.59 57	92.65 380	99.71 71	99.78 122	98.06 102	99.90 116	98.84 118	99.91 35	99.74 92

HY-MVS	97.30 7	98.85 141	98.64 147	99.47 125	99.42 200	99.08 144	99.62 87	99.36 243	97.39 231	99.28 183	99.68 173	96.44 160	99.92 95	98.37 179	98.22 232	99.40 201

ACMMP		99.45 33	99.32 40	99.82 41	99.89 8	99.67 51	99.62 87	99.69 18	98.12 143	99.63 100	99.84 62	98.73 60	99.96 30	98.55 164	99.83 90	99.81 61
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
DeepC-MVS	98.35 2	99.30 63	99.19 70	99.64 78	99.82 42	99.23 123	99.62 87	99.55 77	98.94 54	99.63 100	99.95 3	95.82 182	99.94 69	99.37 51	99.97 7	99.73 97
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EI-MVSNet-Vis-set		99.58 9	99.56 10	99.64 78	99.78 56	99.15 135	99.61 93	99.45 198	99.01 40	99.89 19	99.82 74	99.01 18	99.92 95	99.56 28	99.95 18	99.85 36

test2506		96.81 317	96.65 313	97.29 342	99.74 80	92.21 385	99.60 94	85.06 414	99.13 22	99.77 51	99.93 9	87.82 366	99.85 150	99.38 49	99.38 153	99.80 70

SED-MVS		99.61 7	99.52 11	99.88 5	99.84 32	99.90 2	99.60 94	99.48 157	99.08 33	99.91 16	99.81 89	99.20 7	99.96 30	98.91 102	99.85 73	99.79 74

OPU-MVS				99.64 78	99.56 156	99.72 42	99.60 94				99.70 157	99.27 5	99.42 278	98.24 189	99.80 101	99.79 74

GST-MVS		99.40 50	99.24 64	99.85 28	99.86 20	99.79 30	99.60 94	99.67 23	97.97 164	99.63 100	99.68 173	98.52 77	99.95 59	98.38 177	99.86 66	99.81 61

EI-MVSNet-UG-set		99.58 9	99.57 8	99.64 78	99.78 56	99.14 136	99.60 94	99.45 198	99.01 40	99.90 18	99.83 66	98.98 23	99.93 84	99.59 25	99.95 18	99.86 33

ACMH	97.28 8	98.10 203	97.99 205	98.44 274	99.41 205	96.96 299	99.60 94	99.56 69	98.09 148	98.15 330	99.91 19	90.87 331	99.70 229	98.88 105	97.45 278	98.67 294
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ECVR-MVS		98.04 214	98.05 199	98.00 311	99.74 80	94.37 365	99.59 100	94.98 404	99.13 22	99.66 87	99.93 9	90.67 333	99.84 157	99.40 47	99.38 153	99.80 70

SR-MVS		99.43 40	99.29 53	99.86 21	99.75 73	99.83 16	99.59 100	99.62 41	98.21 128	99.73 65	99.79 116	98.68 64	99.96 30	98.44 174	99.77 111	99.79 74

thres100view900		97.76 258	97.45 264	98.69 243	99.72 91	97.86 253	99.59 100	98.74 358	97.93 167	99.26 192	98.62 362	91.75 313	99.83 170	93.22 366	98.18 237	98.37 351

thres600view7		97.86 242	97.51 257	98.92 203	99.72 91	97.95 247	99.59 100	98.74 358	97.94 166	99.27 188	98.62 362	91.75 313	99.86 144	93.73 361	98.19 236	98.96 250

LCM-MVSNet-Re		97.83 248	98.15 185	96.87 354	99.30 237	92.25 384	99.59 100	98.26 376	97.43 226	96.20 370	99.13 324	96.27 165	98.73 367	98.17 195	98.99 187	99.64 136

baseline1		98.31 183	97.95 210	99.38 139	99.50 179	98.74 190	99.59 100	98.93 330	98.41 104	99.14 216	99.60 209	94.59 233	99.79 191	98.48 168	93.29 364	99.61 144

SteuartSystems-ACMMP		99.54 15	99.42 22	99.87 11	99.82 42	99.81 25	99.59 100	99.51 115	98.62 84	99.79 42	99.83 66	99.28 4	99.97 21	98.48 168	99.90 43	99.84 40
Skip Steuart: Steuart Systems R&D Blog.
CPTT-MVS		99.11 102	98.90 114	99.74 61	99.80 52	99.46 94	99.59 100	99.49 144	97.03 266	99.63 100	99.69 167	97.27 129	99.96 30	97.82 225	99.84 81	99.81 61

test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 55	99.38 215	99.37 103	99.58 108	99.62 41	99.41 9	99.87 25	99.92 14	98.81 44	100.00 1	99.97 1	99.93 26	99.94 11

dmvs_testset		95.02 342	96.12 324	91.72 375	99.10 288	80.43 403	99.58 108	97.87 385	97.47 219	95.22 377	98.82 353	93.99 257	95.18 400	88.09 392	94.91 342	99.56 158

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 52	99.84 32	99.44 96	99.58 108	99.69 18	99.43 7	99.98 6	99.91 19	98.62 70	100.00 1	99.97 1	99.95 18	99.90 17

test1111		98.04 214	98.11 190	97.83 322	99.74 80	93.82 370	99.58 108	95.40 403	99.12 25	99.65 93	99.93 9	90.73 332	99.84 157	99.43 46	99.38 153	99.82 54

PGM-MVS		99.45 33	99.31 47	99.86 21	99.87 15	99.78 36	99.58 108	99.65 33	97.84 177	99.71 71	99.80 103	99.12 13	99.97 21	98.33 183	99.87 58	99.83 49

LPG-MVS_test		98.22 189	98.13 188	98.49 262	99.33 229	97.05 287	99.58 108	99.55 77	97.46 220	99.24 194	99.83 66	92.58 294	99.72 217	98.09 199	97.51 271	98.68 287

PHI-MVS		99.30 63	99.17 72	99.70 67	99.56 156	99.52 85	99.58 108	99.80 8	97.12 254	99.62 104	99.73 148	98.58 72	99.90 116	98.61 149	99.91 35	99.68 119

SF-MVS		99.38 53	99.24 64	99.79 49	99.79 54	99.68 48	99.57 115	99.54 85	97.82 182	99.71 71	99.80 103	98.95 27	99.93 84	98.19 192	99.84 81	99.74 92

DVP-MVS		99.57 12	99.47 17	99.88 5	99.85 26	99.89 4	99.57 115	99.37 242	99.10 27	99.81 37	99.80 103	98.94 29	99.96 30	98.93 99	99.86 66	99.81 61
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				99.91 2	99.84 32	99.89 4	99.57 115	99.51 115					99.96 30	98.93 99	99.86 66	99.88 26

Effi-MVS+-dtu		98.78 149	98.89 118	98.47 269	99.33 229	96.91 302	99.57 115	99.30 279	98.47 98	99.41 152	98.99 339	96.78 146	99.74 207	98.73 132	99.38 153	98.74 269

v2v482		98.06 208	97.77 229	98.92 203	98.90 320	98.82 184	99.57 115	99.36 243	96.65 290	99.19 208	99.35 287	94.20 249	99.25 307	97.72 238	94.97 339	98.69 282

DSMNet-mixed		97.25 305	97.35 281	96.95 351	97.84 374	93.61 376	99.57 115	96.63 398	96.13 332	98.87 263	98.61 364	94.59 233	97.70 388	95.08 345	98.86 196	99.55 159

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 28	99.86 20	99.61 67	99.56 121	99.63 39	99.48 3	99.98 6	99.83 66	98.75 55	99.99 4	99.97 1	99.96 13	99.94 11

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 28	99.84 32	99.63 64	99.56 121	99.63 39	99.47 4	99.98 6	99.82 74	98.75 55	99.99 4	99.97 1	99.97 7	99.94 11

sd_testset		98.75 153	98.57 160	99.29 156	99.81 46	98.26 228	99.56 121	99.62 41	98.78 73	99.64 97	99.88 35	92.02 307	99.88 132	99.54 30	98.26 230	99.72 103

KD-MVS_self_test		95.00 343	94.34 348	96.96 350	97.07 389	95.39 348	99.56 121	99.44 206	95.11 350	97.13 361	97.32 389	91.86 311	97.27 391	90.35 384	81.23 398	98.23 359

ETV-MVS		99.26 71	99.21 68	99.40 135	99.46 190	99.30 113	99.56 121	99.52 101	98.52 94	99.44 144	99.27 308	98.41 86	99.86 144	99.10 83	99.59 140	99.04 240

SMA-MVS		99.44 37	99.30 49	99.85 28	99.73 87	99.83 16	99.56 121	99.47 177	97.45 223	99.78 47	99.82 74	99.18 10	99.91 105	98.79 126	99.89 52	99.81 61
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
AllTest		98.87 131	98.72 137	99.31 148	99.86 20	98.48 217	99.56 121	99.61 48	97.85 175	99.36 167	99.85 52	95.95 174	99.85 150	96.66 310	99.83 90	99.59 150

casdiffmvs		99.13 92	98.98 104	99.56 96	99.65 126	99.16 130	99.56 121	99.50 135	98.33 114	99.41 152	99.86 47	95.92 177	99.83 170	99.45 45	99.16 169	99.70 113
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
XXY-MVS		98.38 179	98.09 194	99.24 165	99.26 248	99.32 107	99.56 121	99.55 77	97.45 223	98.71 281	99.83 66	93.23 273	99.63 253	98.88 105	96.32 307	98.76 264

ACMH+	97.24 10	97.92 234	97.78 227	98.32 287	99.46 190	96.68 313	99.56 121	99.54 85	98.41 104	97.79 346	99.87 43	90.18 340	99.66 240	98.05 207	97.18 293	98.62 315

ACMM	97.58 5	98.37 180	98.34 173	98.48 264	99.41 205	97.10 281	99.56 121	99.45 198	98.53 93	99.04 237	99.85 52	93.00 278	99.71 223	98.74 130	97.45 278	98.64 306
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LS3D		99.27 69	99.12 78	99.74 61	99.18 267	99.75 39	99.56 121	99.57 64	98.45 100	99.49 133	99.85 52	97.77 110	99.94 69	98.33 183	99.84 81	99.52 167

test_fmvsmconf0.01_n		99.22 78	99.03 91	99.79 49	98.42 366	99.48 91	99.55 133	99.51 115	99.39 10	99.78 47	99.93 9	94.80 217	99.95 59	99.93 11	99.95 18	99.94 11

test_fmvs1		98.88 130	98.79 133	99.16 173	99.69 106	97.61 264	99.55 133	99.49 144	99.32 14	99.98 6	99.91 19	91.41 323	99.96 30	99.82 16	99.92 28	99.90 17

v144192		97.92 234	97.60 249	98.87 218	98.83 331	98.65 197	99.55 133	99.34 253	96.20 324	99.32 175	99.40 273	94.36 244	99.26 306	96.37 318	95.03 338	98.70 278

API-MVS		99.04 113	99.03 91	99.06 183	99.40 210	99.31 111	99.55 133	99.56 69	98.54 92	99.33 174	99.39 277	98.76 52	99.78 196	96.98 292	99.78 108	98.07 364

fmvsm_s_conf0.1_n_a		99.26 71	99.06 86	99.85 28	99.52 167	99.62 65	99.54 137	99.62 41	98.69 79	99.99 2	99.96 1	94.47 241	99.94 69	99.88 14	99.92 28	99.98 2

APD_test1		95.87 333	96.49 317	94.00 367	99.53 163	84.01 395	99.54 137	99.32 270	95.91 340	97.99 337	99.85 52	85.49 375	99.88 132	91.96 377	98.84 198	98.12 362

thisisatest0530		98.35 181	98.03 201	99.31 148	99.63 131	98.56 204	99.54 137	96.75 396	97.53 214	99.73 65	99.65 185	91.25 327	99.89 127	98.62 146	99.56 142	99.48 179

MTMP							99.54 137	98.88 342

v1144		97.98 225	97.69 239	98.85 224	98.87 325	98.66 196	99.54 137	99.35 249	96.27 319	99.23 198	99.35 287	94.67 230	99.23 310	96.73 305	95.16 335	98.68 287

v148		97.79 256	97.55 251	98.50 261	98.74 342	97.72 258	99.54 137	99.33 260	96.26 320	98.90 257	99.51 241	94.68 229	99.14 324	97.83 224	93.15 367	98.63 313

CostFormer		97.72 267	97.73 236	97.71 329	99.15 281	94.02 369	99.54 137	99.02 321	94.67 361	99.04 237	99.35 287	92.35 304	99.77 198	98.50 167	97.94 247	99.34 212

MVSTER		98.49 167	98.32 175	99.00 191	99.35 224	99.02 151	99.54 137	99.38 233	97.41 229	99.20 205	99.73 148	93.86 263	99.36 288	98.87 108	97.56 267	98.62 315

fmvsm_s_conf0.1_n		99.29 65	99.10 80	99.86 21	99.70 101	99.65 57	99.53 145	99.62 41	98.74 75	99.99 2	99.95 3	94.53 239	99.94 69	99.89 13	99.96 13	99.97 4

fmvsm_s_conf0.5_n_a		99.56 13	99.47 17	99.85 28	99.83 39	99.64 63	99.52 146	99.65 33	99.10 27	99.98 6	99.92 14	97.35 125	99.96 30	99.94 10	99.92 28	99.95 9

MM		99.40 50	99.28 55	99.74 61	99.67 111	99.31 111	99.52 146	98.87 344	99.55 1	99.74 63	99.80 103	96.47 157	99.98 13	99.97 1	99.97 7	99.94 11

patch_mono-2		99.26 71	99.62 5	98.16 299	99.81 46	94.59 362	99.52 146	99.64 36	99.33 13	99.73 65	99.90 25	99.00 22	99.99 4	99.69 19	99.98 4	99.89 20

Fast-Effi-MVS+-dtu		98.77 151	98.83 129	98.60 248	99.41 205	96.99 294	99.52 146	99.49 144	98.11 145	99.24 194	99.34 291	96.96 142	99.79 191	97.95 213	99.45 149	99.02 243

MVS_0304		99.42 42	99.32 40	99.72 65	99.70 101	99.27 117	99.52 146	97.57 390	99.51 2	99.82 35	99.78 122	98.09 100	99.96 30	99.97 1	99.97 7	99.94 11

Fast-Effi-MVS+		98.70 157	98.43 167	99.51 115	99.51 170	99.28 115	99.52 146	99.47 177	96.11 333	99.01 240	99.34 291	96.20 167	99.84 157	97.88 217	98.82 200	99.39 203

v1921920		97.80 255	97.45 264	98.84 225	98.80 332	98.53 207	99.52 146	99.34 253	96.15 330	99.24 194	99.47 256	93.98 258	99.29 301	95.40 339	95.13 336	98.69 282

MIMVSNet1		95.51 337	95.04 342	96.92 353	97.38 381	95.60 339	99.52 146	99.50 135	93.65 371	96.97 365	99.17 319	85.28 378	96.56 396	88.36 391	95.55 327	98.60 327

fmvsm_s_conf0.5_n		99.51 18	99.40 25	99.85 28	99.84 32	99.65 57	99.51 154	99.67 23	99.13 22	99.98 6	99.92 14	96.60 152	99.96 30	99.95 8	99.96 13	99.95 9

UniMVSNet_ETH3D		97.32 302	96.81 310	98.87 218	99.40 210	97.46 267	99.51 154	99.53 96	95.86 341	98.54 307	99.77 130	82.44 390	99.66 240	98.68 140	97.52 270	99.50 176

alignmvs		98.81 145	98.56 162	99.58 92	99.43 198	99.42 99	99.51 154	98.96 328	98.61 85	99.35 170	98.92 349	94.78 219	99.77 198	99.35 52	98.11 242	99.54 161

v1192		97.81 253	97.44 269	98.91 207	98.88 322	98.68 194	99.51 154	99.34 253	96.18 326	99.20 205	99.34 291	94.03 256	99.36 288	95.32 341	95.18 334	98.69 282

test20.03		96.12 330	95.96 329	96.63 357	97.44 380	95.45 346	99.51 154	99.38 233	96.55 300	96.16 371	99.25 311	93.76 267	96.17 397	87.35 395	94.22 352	98.27 355

mvs_anonymous		99.03 115	98.99 101	99.16 173	99.38 215	98.52 211	99.51 154	99.38 233	97.79 183	99.38 162	99.81 89	97.30 127	99.45 268	99.35 52	98.99 187	99.51 173

TAMVS		99.12 98	99.08 84	99.24 165	99.46 190	98.55 205	99.51 154	99.46 187	98.09 148	99.45 139	99.82 74	98.34 89	99.51 263	98.70 135	98.93 190	99.67 122

MVSMamba_pp		99.36 55	99.28 55	99.62 83	99.38 215	99.50 87	99.50 161	99.49 144	98.55 91	99.77 51	99.82 74	97.62 116	99.88 132	99.39 48	99.96 13	99.47 185

test_fmvsmconf0.1_n		99.55 14	99.45 21	99.86 21	99.44 197	99.65 57	99.50 161	99.61 48	99.45 5	99.87 25	99.92 14	97.31 126	99.97 21	99.95 8	99.99 1	99.97 4

test_yl		98.86 134	98.63 148	99.54 99	99.49 181	99.18 127	99.50 161	99.07 316	98.22 126	99.61 107	99.51 241	95.37 196	99.84 157	98.60 152	98.33 224	99.59 150

DCV-MVSNet		98.86 134	98.63 148	99.54 99	99.49 181	99.18 127	99.50 161	99.07 316	98.22 126	99.61 107	99.51 241	95.37 196	99.84 157	98.60 152	98.33 224	99.59 150

tfpn200view9		97.72 267	97.38 277	98.72 239	99.69 106	97.96 245	99.50 161	98.73 363	97.83 178	99.17 213	98.45 367	91.67 317	99.83 170	93.22 366	98.18 237	98.37 351

UA-Net		99.42 42	99.29 53	99.80 46	99.62 137	99.55 77	99.50 161	99.70 15	98.79 70	99.77 51	99.96 1	97.45 120	99.96 30	98.92 101	99.90 43	99.89 20

iter_conf05		98.76 152	98.90 114	98.33 284	99.07 295	96.97 296	99.50 161	99.31 274	98.13 140	99.48 134	99.80 103	97.89 105	99.46 266	99.25 70	97.68 258	98.56 331

mamv4		99.33 59	99.23 66	99.62 83	99.39 213	99.50 87	99.50 161	99.50 135	98.13 140	99.76 57	99.81 89	97.69 113	99.88 132	99.35 52	99.95 18	99.49 177

pm-mvs1		97.68 274	97.28 292	98.88 214	99.06 299	98.62 200	99.50 161	99.45 198	96.32 315	97.87 342	99.79 116	92.47 298	99.35 291	97.54 255	93.54 362	98.67 294

EI-MVSNet		98.67 160	98.67 143	98.68 244	99.35 224	97.97 243	99.50 161	99.38 233	96.93 275	99.20 205	99.83 66	97.87 106	99.36 288	98.38 177	97.56 267	98.71 274

CVMVSNet		98.57 166	98.67 143	98.30 289	99.35 224	95.59 340	99.50 161	99.55 77	98.60 86	99.39 160	99.83 66	94.48 240	99.45 268	98.75 129	98.56 214	99.85 36

VPA-MVSNet		98.29 186	97.95 210	99.30 153	99.16 277	99.54 79	99.50 161	99.58 61	98.27 119	99.35 170	99.37 281	92.53 296	99.65 245	99.35 52	94.46 347	98.72 272

thres400		97.77 257	97.38 277	98.92 203	99.69 106	97.96 245	99.50 161	98.73 363	97.83 178	99.17 213	98.45 367	91.67 317	99.83 170	93.22 366	98.18 237	98.96 250

APD-MVS		99.27 69	99.08 84	99.84 39	99.75 73	99.79 30	99.50 161	99.50 135	97.16 250	99.77 51	99.82 74	98.78 48	99.94 69	97.56 253	99.86 66	99.80 70
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_vis1_rt		95.81 335	95.65 335	96.32 361	99.67 111	91.35 388	99.49 175	96.74 397	98.25 121	95.24 376	98.10 380	74.96 395	99.90 116	99.53 32	98.85 197	97.70 380

TransMVSNet (Re)		97.15 309	96.58 314	98.86 221	99.12 283	98.85 179	99.49 175	98.91 337	95.48 345	97.16 360	99.80 103	93.38 271	99.11 332	94.16 358	91.73 375	98.62 315

UniMVSNet (Re)		98.29 186	98.00 204	99.13 178	99.00 307	99.36 105	99.49 175	99.51 115	97.95 165	98.97 248	99.13 324	96.30 164	99.38 281	98.36 181	93.34 363	98.66 302

EPMVS		97.82 251	97.65 243	98.35 283	98.88 322	95.98 333	99.49 175	94.71 406	97.57 207	99.26 192	99.48 253	92.46 301	99.71 223	97.87 219	99.08 180	99.35 209

test_fmvsmconf_n		99.70 3	99.64 4	99.87 11	99.80 52	99.66 53	99.48 179	99.64 36	99.45 5	99.92 15	99.92 14	98.62 70	99.99 4	99.96 7	99.99 1	99.96 7

Anonymous20231211		97.88 238	97.54 254	98.90 209	99.71 96	98.53 207	99.48 179	99.57 64	94.16 366	98.81 270	99.68 173	93.23 273	99.42 278	98.84 118	94.42 349	98.76 264

v1240		97.69 272	97.32 287	98.79 233	98.85 329	98.43 221	99.48 179	99.36 243	96.11 333	99.27 188	99.36 284	93.76 267	99.24 309	94.46 352	95.23 333	98.70 278

VPNet		97.84 246	97.44 269	99.01 189	99.21 259	98.94 168	99.48 179	99.57 64	98.38 106	99.28 183	99.73 148	88.89 350	99.39 280	99.19 75	93.27 365	98.71 274

UniMVSNet_NR-MVSNet		98.22 189	97.97 207	98.96 196	98.92 319	98.98 155	99.48 179	99.53 96	97.76 187	98.71 281	99.46 260	96.43 161	99.22 313	98.57 158	92.87 370	98.69 282

TDRefinement		95.42 339	94.57 346	97.97 313	89.83 407	96.11 332	99.48 179	98.75 355	96.74 283	96.68 366	99.88 35	88.65 355	99.71 223	98.37 179	82.74 396	98.09 363

ACMMP_NAP		99.47 29	99.34 36	99.88 5	99.87 15	99.86 13	99.47 185	99.48 157	98.05 158	99.76 57	99.86 47	98.82 43	99.93 84	98.82 125	99.91 35	99.84 40

NR-MVSNet		97.97 228	97.61 248	99.02 188	98.87 325	99.26 119	99.47 185	99.42 214	97.63 202	97.08 362	99.50 244	95.07 207	99.13 327	97.86 220	93.59 361	98.68 287

PVSNet_Blended_VisFu		99.36 55	99.28 55	99.61 86	99.86 20	99.07 146	99.47 185	99.93 2	97.66 200	99.71 71	99.86 47	97.73 111	99.96 30	99.47 43	99.82 94	99.79 74

SD-MVS		99.41 47	99.52 11	99.05 185	99.74 80	99.68 48	99.46 188	99.52 101	99.11 26	99.88 20	99.91 19	99.43 1	97.70 388	98.72 133	99.93 26	99.77 82
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
testing3		97.28 303	96.76 312	98.82 227	99.37 219	98.07 238	99.45 189	99.36 243	97.56 209	97.89 341	98.95 344	83.70 385	98.82 362	96.03 322	98.56 214	99.58 154

tt0805		97.97 228	97.77 229	98.57 253	99.59 148	96.61 316	99.45 189	99.08 313	98.21 128	98.88 260	99.80 103	88.66 354	99.70 229	98.58 155	97.72 256	99.39 203

tpm2		97.44 297	97.34 284	97.74 328	99.15 281	94.36 366	99.45 189	98.94 329	93.45 375	98.90 257	99.44 262	91.35 325	99.59 257	97.31 272	98.07 243	99.29 216

FMVSNet2		97.72 267	97.36 279	98.80 232	99.51 170	98.84 180	99.45 189	99.42 214	96.49 303	98.86 267	99.29 303	90.26 336	98.98 348	96.44 315	96.56 301	98.58 329

CDS-MVSNet		99.09 107	99.03 91	99.25 163	99.42 200	98.73 191	99.45 189	99.46 187	98.11 145	99.46 138	99.77 130	98.01 103	99.37 284	98.70 135	98.92 192	99.66 125
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MAR-MVS		98.86 134	98.63 148	99.54 99	99.37 219	99.66 53	99.45 189	99.54 85	96.61 295	99.01 240	99.40 273	97.09 134	99.86 144	97.68 243	99.53 145	99.10 228
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
UGNet		98.87 131	98.69 141	99.40 135	99.22 258	98.72 192	99.44 195	99.68 20	99.24 17	99.18 212	99.42 266	92.74 286	99.96 30	99.34 58	99.94 24	99.53 166
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
ab-mvs		98.86 134	98.63 148	99.54 99	99.64 128	99.19 125	99.44 195	99.54 85	97.77 186	99.30 179	99.81 89	94.20 249	99.93 84	99.17 78	98.82 200	99.49 177

test_0402		96.64 319	96.24 322	97.85 319	98.85 329	96.43 322	99.44 195	99.26 288	93.52 372	96.98 364	99.52 238	88.52 357	99.20 320	92.58 376	97.50 273	97.93 375

ACMP	97.20 11	98.06 208	97.94 212	98.45 271	99.37 219	97.01 292	99.44 195	99.49 144	97.54 213	98.45 312	99.79 116	91.95 309	99.72 217	97.91 215	97.49 276	98.62 315
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
GG-mvs-BLEND				98.45 271	98.55 361	98.16 232	99.43 199	93.68 408		97.23 357	98.46 366	89.30 347	99.22 313	95.43 338	98.22 232	97.98 372

HPM-MVS++		99.39 52	99.23 66	99.87 11	99.75 73	99.84 15	99.43 199	99.51 115	98.68 81	99.27 188	99.53 235	98.64 69	99.96 30	98.44 174	99.80 101	99.79 74

tpm cat1		97.39 299	97.36 279	97.50 337	99.17 275	93.73 372	99.43 199	99.31 274	91.27 384	98.71 281	99.08 328	94.31 247	99.77 198	96.41 317	98.50 218	99.00 244

tpm		97.67 277	97.55 251	98.03 306	99.02 305	95.01 355	99.43 199	98.54 372	96.44 309	99.12 219	99.34 291	91.83 312	99.60 256	97.75 234	96.46 303	99.48 179

GBi-Net		97.68 274	97.48 259	98.29 290	99.51 170	97.26 274	99.43 199	99.48 157	96.49 303	99.07 229	99.32 298	90.26 336	98.98 348	97.10 285	96.65 298	98.62 315

test1		97.68 274	97.48 259	98.29 290	99.51 170	97.26 274	99.43 199	99.48 157	96.49 303	99.07 229	99.32 298	90.26 336	98.98 348	97.10 285	96.65 298	98.62 315

FMVSNet1		96.84 316	96.36 320	98.29 290	99.32 235	97.26 274	99.43 199	99.48 157	95.11 350	98.55 306	99.32 298	83.95 384	98.98 348	95.81 327	96.26 308	98.62 315

testgi		97.65 279	97.50 258	98.13 303	99.36 223	96.45 321	99.42 206	99.48 157	97.76 187	97.87 342	99.45 261	91.09 328	98.81 363	94.53 351	98.52 217	99.13 227

F-COLMAP		99.19 80	99.04 89	99.64 78	99.78 56	99.27 117	99.42 206	99.54 85	97.29 239	99.41 152	99.59 211	98.42 85	99.93 84	98.19 192	99.69 127	99.73 97

Anonymous202405211		98.30 185	97.98 206	99.26 162	99.57 152	98.16 232	99.41 208	98.55 371	96.03 338	99.19 208	99.74 142	91.87 310	99.92 95	99.16 79	98.29 229	99.70 113

MSLP-MVS++		99.46 31	99.47 17	99.44 132	99.60 146	99.16 130	99.41 208	99.71 13	98.98 48	99.45 139	99.78 122	99.19 9	99.54 262	99.28 65	99.84 81	99.63 140

VNet		99.11 102	98.90 114	99.73 64	99.52 167	99.56 75	99.41 208	99.39 225	99.01 40	99.74 63	99.78 122	95.56 190	99.92 95	99.52 34	98.18 237	99.72 103

baseline2		97.87 240	97.55 251	98.82 227	99.18 267	98.02 240	99.41 208	96.58 400	96.97 269	96.51 367	99.17 319	93.43 270	99.57 258	97.71 239	99.03 184	98.86 254

DU-MVS		98.08 206	97.79 224	98.96 196	98.87 325	98.98 155	99.41 208	99.45 198	97.87 171	98.71 281	99.50 244	94.82 215	99.22 313	98.57 158	92.87 370	98.68 287

Baseline_NR-MVSNet		97.76 258	97.45 264	98.68 244	99.09 291	98.29 226	99.41 208	98.85 346	95.65 343	98.63 298	99.67 179	94.82 215	99.10 334	98.07 206	92.89 369	98.64 306

XVG-ACMP-BASELINE		97.83 248	97.71 238	98.20 296	99.11 285	96.33 325	99.41 208	99.52 101	98.06 157	99.05 236	99.50 244	89.64 345	99.73 213	97.73 236	97.38 286	98.53 333

DP-MVS		99.16 86	98.95 109	99.78 52	99.77 62	99.53 82	99.41 208	99.50 135	97.03 266	99.04 237	99.88 35	97.39 121	99.92 95	98.66 142	99.90 43	99.87 31

9.14			99.10 80		99.72 91		99.40 216	99.51 115	97.53 214	99.64 97	99.78 122	98.84 41	99.91 105	97.63 244	99.82 94

D2MVS		98.41 175	98.50 165	98.15 302	99.26 248	96.62 315	99.40 216	99.61 48	97.71 192	98.98 246	99.36 284	96.04 170	99.67 237	98.70 135	97.41 283	98.15 361

Anonymous20240529		98.09 204	97.68 240	99.34 141	99.66 120	98.44 220	99.40 216	99.43 212	93.67 370	99.22 199	99.89 29	90.23 339	99.93 84	99.26 69	98.33 224	99.66 125

FMVSNet3		98.03 216	97.76 233	98.84 225	99.39 213	98.98 155	99.40 216	99.38 233	96.67 288	99.07 229	99.28 305	92.93 279	98.98 348	97.10 285	96.65 298	98.56 331

LFMVS		97.90 237	97.35 281	99.54 99	99.52 167	99.01 153	99.39 220	98.24 378	97.10 258	99.65 93	99.79 116	84.79 380	99.91 105	99.28 65	98.38 221	99.69 115

HQP_MVS		98.27 188	98.22 181	98.44 274	99.29 241	96.97 296	99.39 220	99.47 177	98.97 51	99.11 221	99.61 206	92.71 289	99.69 234	97.78 228	97.63 260	98.67 294

plane_prior2							99.39 220		98.97 51

CHOSEN 1792x2688		99.19 80	99.10 80	99.45 128	99.89 8	98.52 211	99.39 220	99.94 1	98.73 76	99.11 221	99.89 29	95.50 192	99.94 69	99.50 36	99.97 7	99.89 20

PAPM_NR		99.04 113	98.84 127	99.66 69	99.74 80	99.44 96	99.39 220	99.38 233	97.70 195	99.28 183	99.28 305	98.34 89	99.85 150	96.96 294	99.45 149	99.69 115

gg-mvs-nofinetune		96.17 329	95.32 340	98.73 238	98.79 333	98.14 234	99.38 225	94.09 407	91.07 387	98.07 335	91.04 403	89.62 346	99.35 291	96.75 304	99.09 179	98.68 287

VDDNet		97.55 285	97.02 304	99.16 173	99.49 181	98.12 236	99.38 225	99.30 279	95.35 346	99.68 78	99.90 25	82.62 389	99.93 84	99.31 61	98.13 241	99.42 197

pmmvs6		96.53 321	96.09 326	97.82 324	98.69 349	95.47 345	99.37 227	99.47 177	93.46 374	97.41 351	99.78 122	87.06 369	99.33 294	96.92 299	92.70 372	98.65 304

PM-MVS		92.96 356	92.23 360	95.14 365	95.61 394	89.98 391	99.37 227	98.21 379	94.80 359	95.04 381	97.69 384	65.06 399	97.90 384	94.30 353	89.98 385	97.54 384

WTY-MVS		99.06 110	98.88 119	99.61 86	99.62 137	99.16 130	99.37 227	99.56 69	98.04 159	99.53 125	99.62 202	96.84 144	99.94 69	98.85 115	98.49 219	99.72 103

IterMVS-LS		98.46 170	98.42 168	98.58 252	99.59 148	98.00 241	99.37 227	99.43 212	96.94 274	99.07 229	99.59 211	97.87 106	99.03 341	98.32 185	95.62 325	98.71 274
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
h-mvs33		97.70 271	97.28 292	98.97 195	99.70 101	97.27 272	99.36 231	99.45 198	98.94 54	99.66 87	99.64 191	94.93 209	99.99 4	99.48 41	84.36 393	99.65 129

DPE-MVS		99.46 31	99.32 40	99.91 2	99.78 56	99.88 8	99.36 231	99.51 115	98.73 76	99.88 20	99.84 62	98.72 61	99.96 30	98.16 196	99.87 58	99.88 26
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UnsupCasMVSNet_eth		96.44 323	96.12 324	97.40 339	98.65 352	95.65 338	99.36 231	99.51 115	97.13 252	96.04 373	98.99 339	88.40 358	98.17 377	96.71 306	90.27 383	98.40 348

sss		99.17 84	99.05 87	99.53 107	99.62 137	98.97 158	99.36 231	99.62 41	97.83 178	99.67 82	99.65 185	97.37 124	99.95 59	99.19 75	99.19 168	99.68 119

DeepC-MVS_fast	98.69 1	99.49 22	99.39 27	99.77 55	99.63 131	99.59 70	99.36 231	99.46 187	99.07 35	99.79 42	99.82 74	98.85 39	99.92 95	98.68 140	99.87 58	99.82 54
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CANet		99.25 75	99.14 75	99.59 89	99.41 205	99.16 130	99.35 236	99.57 64	98.82 65	99.51 129	99.61 206	96.46 158	99.95 59	99.59 25	99.98 4	99.65 129

pmmvs-eth3d		95.34 341	94.73 344	97.15 343	95.53 396	95.94 334	99.35 236	99.10 310	95.13 348	93.55 386	97.54 385	88.15 362	97.91 383	94.58 350	89.69 386	97.61 381

MDTV_nov1_ep13_2view						95.18 353	99.35 236		96.84 279	99.58 114		95.19 205		97.82 225		99.46 190

VDD-MVS		97.73 265	97.35 281	98.88 214	99.47 189	97.12 280	99.34 239	98.85 346	98.19 130	99.67 82	99.85 52	82.98 387	99.92 95	99.49 40	98.32 228	99.60 146

COLMAP_ROB	97.56 6	98.86 134	98.75 136	99.17 172	99.88 11	98.53 207	99.34 239	99.59 57	97.55 210	98.70 287	99.89 29	95.83 181	99.90 116	98.10 198	99.90 43	99.08 233
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
EGC-MVSNET		82.80 368	77.86 374	97.62 332	97.91 372	96.12 331	99.33 241	99.28 285	8.40 411	25.05 412	99.27 308	84.11 383	99.33 294	89.20 387	98.22 232	97.42 385

ETVMVS		97.50 290	96.90 308	99.29 156	99.23 254	98.78 189	99.32 242	98.90 339	97.52 216	98.56 305	98.09 381	84.72 381	99.69 234	97.86 220	97.88 250	99.39 203

FMVSNet5		96.43 324	96.19 323	97.15 343	99.11 285	95.89 335	99.32 242	99.52 101	94.47 365	98.34 318	99.07 329	87.54 367	97.07 392	92.61 375	95.72 323	98.47 339

dp		97.75 262	97.80 223	97.59 334	99.10 288	93.71 373	99.32 242	98.88 342	96.48 306	99.08 228	99.55 226	92.67 292	99.82 177	96.52 313	98.58 211	99.24 220

tpmvs		97.98 225	98.02 203	97.84 321	99.04 303	94.73 359	99.31 245	99.20 299	96.10 337	98.76 277	99.42 266	94.94 208	99.81 182	96.97 293	98.45 220	98.97 248

tpmrst		98.33 182	98.48 166	97.90 317	99.16 277	94.78 358	99.31 245	99.11 309	97.27 240	99.45 139	99.59 211	95.33 198	99.84 157	98.48 168	98.61 208	99.09 232

testing99		97.36 300	96.94 307	98.63 246	99.18 267	96.70 310	99.30 247	98.93 330	97.71 192	98.23 324	98.26 374	84.92 379	99.84 157	98.04 208	97.85 253	99.35 209

MP-MVS-pluss		99.37 54	99.20 69	99.88 5	99.90 4	99.87 12	99.30 247	99.52 101	97.18 248	99.60 110	99.79 116	98.79 47	99.95 59	98.83 121	99.91 35	99.83 49
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
NCCC		99.34 58	99.19 70	99.79 49	99.61 141	99.65 57	99.30 247	99.48 157	98.86 60	99.21 202	99.63 197	98.72 61	99.90 116	98.25 188	99.63 137	99.80 70

JIA-IIPM		97.50 290	97.02 304	98.93 201	98.73 343	97.80 255	99.30 247	98.97 326	91.73 383	98.91 255	94.86 397	95.10 206	99.71 223	97.58 248	97.98 245	99.28 217

BH-RMVSNet		98.41 175	98.08 195	99.40 135	99.41 205	98.83 183	99.30 247	98.77 354	97.70 195	98.94 252	99.65 185	92.91 282	99.74 207	96.52 313	99.55 144	99.64 136

testing11		97.50 290	97.10 301	98.71 241	99.20 261	96.91 302	99.29 252	98.82 349	97.89 170	98.21 327	98.40 369	85.63 374	99.83 170	98.45 173	98.04 244	99.37 207

Syy-MVS		97.09 312	97.14 298	96.95 351	99.00 307	92.73 382	99.29 252	99.39 225	97.06 262	97.41 351	98.15 376	93.92 261	98.68 368	91.71 378	98.34 222	99.45 193

myMVS_eth3d		96.89 314	96.37 319	98.43 276	99.00 307	97.16 278	99.29 252	99.39 225	97.06 262	97.41 351	98.15 376	83.46 386	98.68 368	95.27 342	98.34 222	99.45 193

MCST-MVS		99.43 40	99.30 49	99.82 41	99.79 54	99.74 41	99.29 252	99.40 222	98.79 70	99.52 127	99.62 202	98.91 34	99.90 116	98.64 144	99.75 116	99.82 54

LF4IMVS		97.52 287	97.46 263	97.70 330	98.98 313	95.55 341	99.29 252	98.82 349	98.07 153	98.66 290	99.64 191	89.97 341	99.61 255	97.01 289	96.68 297	97.94 374

hse-mvs2		97.50 290	97.14 298	98.59 249	99.49 181	97.05 287	99.28 257	99.22 295	98.94 54	99.66 87	99.42 266	94.93 209	99.65 245	99.48 41	83.80 395	99.08 233

OPM-MVS		98.19 193	98.10 191	98.45 271	98.88 322	97.07 285	99.28 257	99.38 233	98.57 88	99.22 199	99.81 89	92.12 305	99.66 240	98.08 203	97.54 269	98.61 324
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
diffmvs		99.14 90	99.02 95	99.51 115	99.61 141	98.96 162	99.28 257	99.49 144	98.46 99	99.72 70	99.71 153	96.50 156	99.88 132	99.31 61	99.11 175	99.67 122
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_BlendedMVS		98.86 134	98.80 130	99.03 187	99.76 65	98.79 187	99.28 257	99.91 3	97.42 228	99.67 82	99.37 281	97.53 118	99.88 132	98.98 93	97.29 288	98.42 345

OMC-MVS		99.08 108	99.04 89	99.20 169	99.67 111	98.22 230	99.28 257	99.52 101	98.07 153	99.66 87	99.81 89	97.79 109	99.78 196	97.79 227	99.81 97	99.60 146

testing222		97.16 308	96.50 316	99.16 173	99.16 277	98.47 219	99.27 262	98.66 367	97.71 192	98.23 324	98.15 376	82.28 391	99.84 157	97.36 270	97.66 259	99.18 223

AUN-MVS		96.88 315	96.31 321	98.59 249	99.48 188	97.04 290	99.27 262	99.22 295	97.44 225	98.51 308	99.41 270	91.97 308	99.66 240	97.71 239	83.83 394	99.07 238

pmmvs5		97.52 287	97.30 289	98.16 299	98.57 360	96.73 309	99.27 262	98.90 339	96.14 331	98.37 316	99.53 235	91.54 322	99.14 324	97.51 257	95.87 318	98.63 313

1314		98.68 159	98.54 163	99.11 179	98.89 321	98.65 197	99.27 262	99.49 144	96.89 276	97.99 337	99.56 222	97.72 112	99.83 170	97.74 235	99.27 164	98.84 256

MVS		97.28 303	96.55 315	99.48 122	98.78 336	98.95 165	99.27 262	99.39 225	83.53 397	98.08 332	99.54 231	96.97 141	99.87 140	94.23 356	99.16 169	99.63 140

BH-untuned		98.42 173	98.36 171	98.59 249	99.49 181	96.70 310	99.27 262	99.13 308	97.24 244	98.80 272	99.38 278	95.75 184	99.74 207	97.07 288	99.16 169	99.33 213

MDTV_nov1_ep13			98.32 175		99.11 285	94.44 364	99.27 262	98.74 358	97.51 217	99.40 157	99.62 202	94.78 219	99.76 202	97.59 247	98.81 202

DP-MVS Recon		99.12 98	98.95 109	99.65 73	99.74 80	99.70 46	99.27 262	99.57 64	96.40 313	99.42 148	99.68 173	98.75 55	99.80 188	97.98 211	99.72 122	99.44 195

PatchmatchNet		98.31 183	98.36 171	98.19 297	99.16 277	95.32 349	99.27 262	98.92 333	97.37 232	99.37 164	99.58 215	94.90 212	99.70 229	97.43 266	99.21 166	99.54 161
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thres200		97.61 282	97.28 292	98.62 247	99.64 128	98.03 239	99.26 271	98.74 358	97.68 197	99.09 227	98.32 372	91.66 319	99.81 182	92.88 371	98.22 232	98.03 367

CNVR-MVS		99.42 42	99.30 49	99.78 52	99.62 137	99.71 44	99.26 271	99.52 101	98.82 65	99.39 160	99.71 153	98.96 24	99.85 150	98.59 154	99.80 101	99.77 82

1112_ss		98.98 122	98.77 134	99.59 89	99.68 110	99.02 151	99.25 273	99.48 157	97.23 245	99.13 217	99.58 215	96.93 143	99.90 116	98.87 108	98.78 203	99.84 40

TAPA-MVS	97.07 15	97.74 264	97.34 284	98.94 199	99.70 101	97.53 265	99.25 273	99.51 115	91.90 382	99.30 179	99.63 197	98.78 48	99.64 248	88.09 392	99.87 58	99.65 129
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PLC	97.94 4	99.02 116	98.85 125	99.53 107	99.66 120	99.01 153	99.24 275	99.52 101	96.85 278	99.27 188	99.48 253	98.25 93	99.91 105	97.76 232	99.62 138	99.65 129
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test_post1							99.23 276				65.14 409	94.18 252	99.71 223	97.58 248

ADS-MVSNet2		98.02 218	98.07 198	97.87 318	99.33 229	95.19 352	99.23 276	99.08 313	96.24 321	99.10 224	99.67 179	94.11 253	98.93 358	96.81 302	99.05 182	99.48 179

ADS-MVSNet		98.20 192	98.08 195	98.56 256	99.33 229	96.48 320	99.23 276	99.15 305	96.24 321	99.10 224	99.67 179	94.11 253	99.71 223	96.81 302	99.05 182	99.48 179

EPNet_dtu		98.03 216	97.96 208	98.23 295	98.27 368	95.54 343	99.23 276	98.75 355	99.02 38	97.82 344	99.71 153	96.11 168	99.48 264	93.04 369	99.65 134	99.69 115
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		98.17 196	97.93 213	98.87 218	99.18 267	98.49 215	99.22 280	99.33 260	96.96 270	99.56 118	99.38 278	94.33 245	99.00 346	94.83 349	98.58 211	99.14 225

RPMNet		96.72 318	95.90 330	99.19 170	99.18 267	98.49 215	99.22 280	99.52 101	88.72 393	99.56 118	97.38 387	94.08 255	99.95 59	86.87 397	98.58 211	99.14 225

plane_prior						96.97 296	99.21 282		98.45 100						97.60 263

testing91		97.44 297	97.02 304	98.71 241	99.18 267	96.89 304	99.19 283	99.04 319	97.78 185	98.31 319	98.29 373	85.41 376	99.85 150	98.01 209	97.95 246	99.39 203

WR-MVS		98.06 208	97.73 236	99.06 183	98.86 328	99.25 121	99.19 283	99.35 249	97.30 238	98.66 290	99.43 264	93.94 259	99.21 318	98.58 155	94.28 351	98.71 274

new-patchmatchnet		94.48 349	94.08 350	95.67 364	95.08 399	92.41 383	99.18 285	99.28 285	94.55 364	93.49 387	97.37 388	87.86 365	97.01 393	91.57 379	88.36 387	97.61 381

AdaColmap		99.01 120	98.80 130	99.66 69	99.56 156	99.54 79	99.18 285	99.70 15	98.18 133	99.35 170	99.63 197	96.32 163	99.90 116	97.48 260	99.77 111	99.55 159

EG-PatchMatch MVS		95.97 332	95.69 334	96.81 355	97.78 375	92.79 381	99.16 287	98.93 330	96.16 328	94.08 384	99.22 314	82.72 388	99.47 265	95.67 333	97.50 273	98.17 360

PatchT		97.03 313	96.44 318	98.79 233	98.99 310	98.34 225	99.16 287	99.07 316	92.13 381	99.52 127	97.31 390	94.54 238	98.98 348	88.54 390	98.73 205	99.03 241

CNLPA		99.14 90	98.99 101	99.59 89	99.58 150	99.41 101	99.16 287	99.44 206	98.45 100	99.19 208	99.49 247	98.08 101	99.89 127	97.73 236	99.75 116	99.48 179

MDA-MVSNet-bldmvs		94.96 344	93.98 351	97.92 315	98.24 369	97.27 272	99.15 290	99.33 260	93.80 369	80.09 404	99.03 334	88.31 359	97.86 385	93.49 364	94.36 350	98.62 315

CDPH-MVS		99.13 92	98.91 113	99.80 46	99.75 73	99.71 44	99.15 290	99.41 216	96.60 297	99.60 110	99.55 226	98.83 42	99.90 116	97.48 260	99.83 90	99.78 80

save fliter					99.76 65	99.59 70	99.14 292	99.40 222	99.00 43

WB-MVSnew		97.65 279	97.65 243	97.63 331	98.78 336	97.62 263	99.13 293	98.33 375	97.36 233	99.07 229	98.94 345	95.64 189	99.15 323	92.95 370	98.68 207	96.12 395

testf1		90.42 362	90.68 364	89.65 382	97.78 375	73.97 410	99.13 293	98.81 351	89.62 389	91.80 393	98.93 346	62.23 402	98.80 364	86.61 398	91.17 377	96.19 393

APD_test2		90.42 362	90.68 364	89.65 382	97.78 375	73.97 410	99.13 293	98.81 351	89.62 389	91.80 393	98.93 346	62.23 402	98.80 364	86.61 398	91.17 377	96.19 393

xiu_mvs_v1_base_debu		99.29 65	99.27 59	99.34 141	99.63 131	98.97 158	99.12 296	99.51 115	98.86 60	99.84 29	99.47 256	98.18 96	99.99 4	99.50 36	99.31 161	99.08 233

xiu_mvs_v1_base		99.29 65	99.27 59	99.34 141	99.63 131	98.97 158	99.12 296	99.51 115	98.86 60	99.84 29	99.47 256	98.18 96	99.99 4	99.50 36	99.31 161	99.08 233

xiu_mvs_v1_base_debi		99.29 65	99.27 59	99.34 141	99.63 131	98.97 158	99.12 296	99.51 115	98.86 60	99.84 29	99.47 256	98.18 96	99.99 4	99.50 36	99.31 161	99.08 233

XVG-OURS-SEG-HR		98.69 158	98.62 153	98.89 212	99.71 96	97.74 256	99.12 296	99.54 85	98.44 103	99.42 148	99.71 153	94.20 249	99.92 95	98.54 165	98.90 194	99.00 244

jason		99.13 92	99.03 91	99.45 128	99.46 190	98.87 175	99.12 296	99.26 288	98.03 161	99.79 42	99.65 185	97.02 139	99.85 150	99.02 90	99.90 43	99.65 129
jason: jason.
N_pmnet		94.95 345	95.83 332	92.31 373	98.47 364	79.33 405	99.12 296	92.81 411	93.87 368	97.68 347	99.13 324	93.87 262	99.01 345	91.38 380	96.19 309	98.59 328

MDA-MVSNet_test_wron		95.45 338	94.60 345	98.01 309	98.16 370	97.21 277	99.11 302	99.24 292	93.49 373	80.73 403	98.98 341	93.02 277	98.18 376	94.22 357	94.45 348	98.64 306

Patchmtry		97.75 262	97.40 276	98.81 230	99.10 288	98.87 175	99.11 302	99.33 260	94.83 358	98.81 270	99.38 278	94.33 245	99.02 343	96.10 320	95.57 326	98.53 333

YYNet1		95.36 340	94.51 347	97.92 315	97.89 373	97.10 281	99.10 304	99.23 293	93.26 376	80.77 402	99.04 333	92.81 283	98.02 380	94.30 353	94.18 353	98.64 306

CANet_DTU		98.97 124	98.87 120	99.25 163	99.33 229	98.42 223	99.08 305	99.30 279	99.16 19	99.43 145	99.75 137	95.27 200	99.97 21	98.56 161	99.95 18	99.36 208

SCA		98.19 193	98.16 183	98.27 294	99.30 237	95.55 341	99.07 306	98.97 326	97.57 207	99.43 145	99.57 219	92.72 287	99.74 207	97.58 248	99.20 167	99.52 167

TSAR-MVS + GP.		99.36 55	99.36 32	99.36 140	99.67 111	98.61 202	99.07 306	99.33 260	99.00 43	99.82 35	99.81 89	99.06 16	99.84 157	99.09 84	99.42 151	99.65 129

MG-MVS		99.13 92	99.02 95	99.45 128	99.57 152	98.63 199	99.07 306	99.34 253	98.99 45	99.61 107	99.82 74	97.98 104	99.87 140	97.00 290	99.80 101	99.85 36

PatchMatch-RL		98.84 144	98.62 153	99.52 113	99.71 96	99.28 115	99.06 309	99.77 9	97.74 190	99.50 130	99.53 235	95.41 194	99.84 157	97.17 284	99.64 135	99.44 195

OpenMVS_ROB	92.34 20	94.38 350	93.70 356	96.41 360	97.38 381	93.17 379	99.06 309	98.75 355	86.58 394	94.84 382	98.26 374	81.53 392	99.32 297	89.01 388	97.87 251	96.76 388

TEST9					99.67 111	99.65 57	99.05 311	99.41 216	96.22 323	98.95 250	99.49 247	98.77 51	99.91 105

train_agg		99.02 116	98.77 134	99.77 55	99.67 111	99.65 57	99.05 311	99.41 216	96.28 317	98.95 250	99.49 247	98.76 52	99.91 105	97.63 244	99.72 122	99.75 88

lupinMVS		99.13 92	99.01 99	99.46 127	99.51 170	98.94 168	99.05 311	99.16 304	97.86 172	99.80 40	99.56 222	97.39 121	99.86 144	98.94 97	99.85 73	99.58 154

DELS-MVS		99.48 26	99.42 22	99.65 73	99.72 91	99.40 102	99.05 311	99.66 28	99.14 21	99.57 117	99.80 103	98.46 81	99.94 69	99.57 27	99.84 81	99.60 146
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
new_pmnet		96.38 325	96.03 327	97.41 338	98.13 371	95.16 354	99.05 311	99.20 299	93.94 367	97.39 354	98.79 357	91.61 321	99.04 339	90.43 383	95.77 320	98.05 366

Patchmatch-test		97.93 231	97.65 243	98.77 235	99.18 267	97.07 285	99.03 316	99.14 307	96.16 328	98.74 278	99.57 219	94.56 235	99.72 217	93.36 365	99.11 175	99.52 167

test_8					99.67 111	99.61 67	99.03 316	99.41 216	96.28 317	98.93 253	99.48 253	98.76 52	99.91 105

Test_1112_low_res		98.89 129	98.66 146	99.57 94	99.69 106	98.95 165	99.03 316	99.47 177	96.98 268	99.15 215	99.23 313	96.77 147	99.89 127	98.83 121	98.78 203	99.86 33

bld_raw_dy_0_64		99.05 111	99.15 73	98.74 237	99.46 190	96.95 300	99.02 319	99.47 177	98.15 135	99.75 62	99.56 222	97.63 115	99.88 132	99.35 52	99.97 7	99.40 201

IterMVS-SCA-FT		97.82 251	97.75 234	98.06 305	99.57 152	96.36 324	99.02 319	99.49 144	97.18 248	98.71 281	99.72 152	92.72 287	99.14 324	97.44 265	95.86 319	98.67 294

xiu_mvs_v2_base		99.26 71	99.25 63	99.29 156	99.53 163	98.91 172	99.02 319	99.45 198	98.80 69	99.71 71	99.26 310	98.94 29	99.98 13	99.34 58	99.23 165	98.98 247

MIMVSNet		97.73 265	97.45 264	98.57 253	99.45 196	97.50 266	99.02 319	98.98 325	96.11 333	99.41 152	99.14 323	90.28 335	98.74 366	95.74 329	98.93 190	99.47 185

IterMVS		97.83 248	97.77 229	98.02 308	99.58 150	96.27 327	99.02 319	99.48 157	97.22 246	98.71 281	99.70 157	92.75 284	99.13 327	97.46 263	96.00 313	98.67 294
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		99.11 102	98.92 111	99.65 73	99.90 4	99.37 103	99.02 319	99.91 3	97.67 199	99.59 113	99.75 137	95.90 179	99.73 213	99.53 32	99.02 186	99.86 33

UWE-MVS		97.58 284	97.29 291	98.48 264	99.09 291	96.25 328	99.01 325	96.61 399	97.86 172	99.19 208	99.01 337	88.72 351	99.90 116	97.38 269	98.69 206	99.28 217

新几何2							99.01 325

BH-w/o		98.00 223	97.89 219	98.32 287	99.35 224	96.20 330	99.01 325	98.90 339	96.42 311	98.38 315	99.00 338	95.26 202	99.72 217	96.06 321	98.61 208	99.03 241

test_prior4						99.56 75	98.99 328

无先验							98.99 328	99.51 115	96.89 276				99.93 84	97.53 256		99.72 103

pmmvs4		98.13 200	97.90 215	98.81 230	98.61 357	98.87 175	98.99 328	99.21 298	96.44 309	99.06 234	99.58 215	95.90 179	99.11 332	97.18 283	96.11 311	98.46 342

HQP-NCC					99.19 264		98.98 331		98.24 122	98.66 290

ACMP_Plane					99.19 264		98.98 331		98.24 122	98.66 290

HQP-MVS		98.02 218	97.90 215	98.37 282	99.19 264	96.83 305	98.98 331	99.39 225	98.24 122	98.66 290	99.40 273	92.47 298	99.64 248	97.19 281	97.58 265	98.64 306

PS-MVSNAJ		99.32 61	99.32 40	99.30 153	99.57 152	98.94 168	98.97 334	99.46 187	98.92 57	99.71 71	99.24 312	99.01 18	99.98 13	99.35 52	99.66 132	98.97 248

MVP-Stereo		97.81 253	97.75 234	97.99 312	97.53 379	96.60 317	98.96 335	98.85 346	97.22 246	97.23 357	99.36 284	95.28 199	99.46 266	95.51 335	99.78 108	97.92 376
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test_prior2							98.96 335		98.34 112	99.01 240	99.52 238	98.68 64		97.96 212	99.74 119

旧先验2							98.96 335		96.70 286	99.47 136			99.94 69	98.19 192

iter_conf05_11		99.22 78	99.13 76	99.49 121	99.37 219	99.43 98	98.95 338	99.38 233	98.52 94	99.70 77	99.49 247	97.62 116	99.87 140	99.20 74	99.94 24	99.16 224

原ACMM2							98.95 338

MVS_111021_HR		99.41 47	99.32 40	99.66 69	99.72 91	99.47 93	98.95 338	99.85 6	98.82 65	99.54 123	99.73 148	98.51 78	99.74 207	98.91 102	99.88 55	99.77 82

mvsany_test1		99.50 20	99.46 20	99.62 83	99.61 141	99.09 141	98.94 341	99.48 157	99.10 27	99.96 14	99.91 19	98.85 39	99.96 30	99.72 18	99.58 141	99.82 54

MVS_111021_LR		99.41 47	99.33 38	99.65 73	99.77 62	99.51 86	98.94 341	99.85 6	98.82 65	99.65 93	99.74 142	98.51 78	99.80 188	98.83 121	99.89 52	99.64 136

pmmvs3		94.09 352	93.25 358	96.60 358	94.76 401	94.49 363	98.92 343	98.18 381	89.66 388	96.48 368	98.06 382	86.28 370	97.33 390	89.68 386	87.20 390	97.97 373

XVG-OURS		98.73 156	98.68 142	98.88 214	99.70 101	97.73 257	98.92 343	99.55 77	98.52 94	99.45 139	99.84 62	95.27 200	99.91 105	98.08 203	98.84 198	99.00 244

test222					99.75 73	99.49 89	98.91 345	99.49 144	96.42 311	99.34 173	99.65 185	98.28 92			99.69 127	99.72 103

PMMVS2		86.87 365	85.37 369	91.35 377	90.21 406	83.80 396	98.89 346	97.45 392	83.13 398	91.67 395	95.03 395	48.49 408	94.70 401	85.86 400	77.62 400	95.54 396

miper_lstm_enhance		98.00 223	97.91 214	98.28 293	99.34 228	97.43 268	98.88 347	99.36 243	96.48 306	98.80 272	99.55 226	95.98 172	98.91 359	97.27 274	95.50 329	98.51 335

MVS-HIRNet		95.75 336	95.16 341	97.51 336	99.30 237	93.69 374	98.88 347	95.78 401	85.09 396	98.78 275	92.65 399	91.29 326	99.37 284	94.85 348	99.85 73	99.46 190

TR-MVS		97.76 258	97.41 275	98.82 227	99.06 299	97.87 251	98.87 349	98.56 370	96.63 294	98.68 289	99.22 314	92.49 297	99.65 245	95.40 339	97.79 254	98.95 252

testdata1							98.85 350		98.32 115

ET-MVSNet_ETH3D		96.49 322	95.64 336	99.05 185	99.53 163	98.82 184	98.84 351	97.51 391	97.63 202	84.77 397	99.21 317	92.09 306	98.91 359	98.98 93	92.21 374	99.41 199

our_test_3		97.65 279	97.68 240	97.55 335	98.62 355	94.97 356	98.84 351	99.30 279	96.83 281	98.19 328	99.34 291	97.01 140	99.02 343	95.00 347	96.01 312	98.64 306

MS-PatchMatch		97.24 307	97.32 287	96.99 348	98.45 365	93.51 377	98.82 353	99.32 270	97.41 229	98.13 331	99.30 301	88.99 349	99.56 259	95.68 332	99.80 101	97.90 377

c3_l		98.12 202	98.04 200	98.38 281	99.30 237	97.69 262	98.81 354	99.33 260	96.67 288	98.83 268	99.34 291	97.11 133	98.99 347	97.58 248	95.34 331	98.48 337

ppachtmachnet_test		97.49 295	97.45 264	97.61 333	98.62 355	95.24 350	98.80 355	99.46 187	96.11 333	98.22 326	99.62 202	96.45 159	98.97 355	93.77 360	95.97 317	98.61 324

PAPR		98.63 164	98.34 173	99.51 115	99.40 210	99.03 150	98.80 355	99.36 243	96.33 314	99.00 244	99.12 327	98.46 81	99.84 157	95.23 343	99.37 160	99.66 125

test0.0.03 1		97.71 270	97.42 274	98.56 256	98.41 367	97.82 254	98.78 357	98.63 368	97.34 234	98.05 336	98.98 341	94.45 242	98.98 348	95.04 346	97.15 294	98.89 253

PVSNet_Blended		99.08 108	98.97 105	99.42 133	99.76 65	98.79 187	98.78 357	99.91 3	96.74 283	99.67 82	99.49 247	97.53 118	99.88 132	98.98 93	99.85 73	99.60 146

PMMVS		98.80 148	98.62 153	99.34 141	99.27 246	98.70 193	98.76 359	99.31 274	97.34 234	99.21 202	99.07 329	97.20 130	99.82 177	98.56 161	98.87 195	99.52 167

test123		39.01 377	42.50 379	28.53 392	39.17 415	20.91 417	98.75 360	19.17 417	19.83 410	38.57 409	66.67 407	33.16 412	15.42 411	37.50 411	29.66 409	49.26 406

MSDG		98.98 122	98.80 130	99.53 107	99.76 65	99.19 125	98.75 360	99.55 77	97.25 242	99.47 136	99.77 130	97.82 108	99.87 140	96.93 297	99.90 43	99.54 161

CLD-MVS		98.16 197	98.10 191	98.33 284	99.29 241	96.82 307	98.75 360	99.44 206	97.83 178	99.13 217	99.55 226	92.92 280	99.67 237	98.32 185	97.69 257	98.48 337
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
miper_ehance_all_eth		98.18 195	98.10 191	98.41 277	99.23 254	97.72 258	98.72 363	99.31 274	96.60 297	98.88 260	99.29 303	97.29 128	99.13 327	97.60 246	95.99 314	98.38 350

cl____		98.01 221	97.84 222	98.55 258	99.25 252	97.97 243	98.71 364	99.34 253	96.47 308	98.59 304	99.54 231	95.65 188	99.21 318	97.21 277	95.77 320	98.46 342

DIV-MVS_self_test		98.01 221	97.85 221	98.48 264	99.24 253	97.95 247	98.71 364	99.35 249	96.50 302	98.60 303	99.54 231	95.72 186	99.03 341	97.21 277	95.77 320	98.46 342

test-LLR		98.06 208	97.90 215	98.55 258	98.79 333	97.10 281	98.67 366	97.75 386	97.34 234	98.61 301	98.85 351	94.45 242	99.45 268	97.25 275	99.38 153	99.10 228

TESTMET0.1,1		97.55 285	97.27 295	98.40 279	98.93 318	96.53 318	98.67 366	97.61 389	96.96 270	98.64 297	99.28 305	88.63 356	99.45 268	97.30 273	99.38 153	99.21 222

test-mter		97.49 295	97.13 300	98.55 258	98.79 333	97.10 281	98.67 366	97.75 386	96.65 290	98.61 301	98.85 351	88.23 360	99.45 268	97.25 275	99.38 153	99.10 228

IB-MVS	95.67 18	96.22 326	95.44 339	98.57 253	99.21 259	96.70 310	98.65 369	97.74 388	96.71 285	97.27 356	98.54 365	86.03 371	99.92 95	98.47 171	86.30 391	99.10 228
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
DPM-MVS		98.95 125	98.71 139	99.66 69	99.63 131	99.55 77	98.64 370	99.10 310	97.93 167	99.42 148	99.55 226	98.67 66	99.80 188	95.80 328	99.68 130	99.61 144

thisisatest0515		98.14 199	97.79 224	99.19 170	99.50 179	98.50 214	98.61 371	96.82 395	96.95 272	99.54 123	99.43 264	91.66 319	99.86 144	98.08 203	99.51 146	99.22 221

DeepPCF-MVS	98.18 3	98.81 145	99.37 30	97.12 346	99.60 146	91.75 386	98.61 371	99.44 206	99.35 12	99.83 34	99.85 52	98.70 63	99.81 182	99.02 90	99.91 35	99.81 61

cl22		97.85 243	97.64 246	98.48 264	99.09 291	97.87 251	98.60 373	99.33 260	97.11 257	98.87 263	99.22 314	92.38 303	99.17 322	98.21 190	95.99 314	98.42 345

GA-MVS		97.85 243	97.47 261	99.00 191	99.38 215	97.99 242	98.57 374	99.15 305	97.04 265	98.90 257	99.30 301	89.83 342	99.38 281	96.70 307	98.33 224	99.62 142

TinyColmap		97.12 310	96.89 309	97.83 322	99.07 295	95.52 344	98.57 374	98.74 358	97.58 206	97.81 345	99.79 116	88.16 361	99.56 259	95.10 344	97.21 291	98.39 349

eth_miper_zixun_eth		98.05 213	97.96 208	98.33 284	99.26 248	97.38 269	98.56 376	99.31 274	96.65 290	98.88 260	99.52 238	96.58 153	99.12 331	97.39 268	95.53 328	98.47 339

CMPMVS	69.68 23	94.13 351	94.90 343	91.84 374	97.24 385	80.01 404	98.52 377	99.48 157	89.01 391	91.99 392	99.67 179	85.67 373	99.13 327	95.44 337	97.03 295	96.39 392
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
USDC		97.34 301	97.20 296	97.75 327	99.07 295	95.20 351	98.51 378	99.04 319	97.99 163	98.31 319	99.86 47	89.02 348	99.55 261	95.67 333	97.36 287	98.49 336

ambc				93.06 372	92.68 403	82.36 397	98.47 379	98.73 363		95.09 380	97.41 386	55.55 404	99.10 334	96.42 316	91.32 376	97.71 378

miper_enhance_ethall		98.16 197	98.08 195	98.41 277	98.96 316	97.72 258	98.45 380	99.32 270	96.95 272	98.97 248	99.17 319	97.06 137	99.22 313	97.86 220	95.99 314	98.29 354

CHOSEN 280x420		99.12 98	99.13 76	99.08 180	99.66 120	97.89 250	98.43 381	99.71 13	98.88 59	99.62 104	99.76 134	96.63 151	99.70 229	99.46 44	99.99 1	99.66 125

testmvs		39.17 376	43.78 378	25.37 393	36.04 416	16.84 418	98.36 382	26.56 415	20.06 409	38.51 410	67.32 406	29.64 413	15.30 412	37.59 410	39.90 408	43.98 407

FPMVS		84.93 367	85.65 368	82.75 388	86.77 409	63.39 414	98.35 383	98.92 333	74.11 400	83.39 399	98.98 341	50.85 407	92.40 403	84.54 401	94.97 339	92.46 398

KD-MVS_2432*1600		94.62 346	93.72 354	97.31 340	97.19 387	95.82 336	98.34 384	99.20 299	95.00 354	97.57 348	98.35 370	87.95 363	98.10 378	92.87 372	77.00 401	98.01 368

miper_refine_blended		94.62 346	93.72 354	97.31 340	97.19 387	95.82 336	98.34 384	99.20 299	95.00 354	97.57 348	98.35 370	87.95 363	98.10 378	92.87 372	77.00 401	98.01 368

CL-MVSNet_self_test		94.49 348	93.97 352	96.08 362	96.16 391	93.67 375	98.33 386	99.38 233	95.13 348	97.33 355	98.15 376	92.69 291	96.57 395	88.67 389	79.87 399	97.99 371

PVSNet	96.02 17	98.85 141	98.84 127	98.89 212	99.73 87	97.28 271	98.32 387	99.60 54	97.86 172	99.50 130	99.57 219	96.75 148	99.86 144	98.56 161	99.70 126	99.54 161

PAPM		97.59 283	97.09 302	99.07 182	99.06 299	98.26 228	98.30 388	99.10 310	94.88 356	98.08 332	99.34 291	96.27 165	99.64 248	89.87 385	98.92 192	99.31 215

Patchmatch-RL test		95.84 334	95.81 333	95.95 363	95.61 394	90.57 389	98.24 389	98.39 374	95.10 352	95.20 378	98.67 361	94.78 219	97.77 386	96.28 319	90.02 384	99.51 173

UnsupCasMVSNet_bld		93.53 354	92.51 359	96.58 359	97.38 381	93.82 370	98.24 389	99.48 157	91.10 386	93.10 388	96.66 392	74.89 396	98.37 373	94.03 359	87.71 389	97.56 383

LCM-MVSNet		86.80 366	85.22 370	91.53 376	87.81 408	80.96 402	98.23 391	98.99 324	71.05 401	90.13 396	96.51 393	48.45 409	96.88 394	90.51 382	85.30 392	96.76 388

cascas		97.69 272	97.43 273	98.48 264	98.60 358	97.30 270	98.18 392	99.39 225	92.96 378	98.41 313	98.78 358	93.77 266	99.27 305	98.16 196	98.61 208	98.86 254

Effi-MVS+		98.81 145	98.59 159	99.48 122	99.46 190	99.12 139	98.08 393	99.50 135	97.50 218	99.38 162	99.41 270	96.37 162	99.81 182	99.11 82	98.54 216	99.51 173

PCF-MVS	97.08 14	97.66 278	97.06 303	99.47 125	99.61 141	99.09 141	98.04 394	99.25 290	91.24 385	98.51 308	99.70 157	94.55 237	99.91 105	92.76 374	99.85 73	99.42 197
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet_0	94.43 19	96.09 331	95.47 337	97.94 314	99.31 236	94.34 367	97.81 395	99.70 15	97.12 254	97.46 350	98.75 359	89.71 343	99.79 191	97.69 242	81.69 397	99.68 119

E-PMN		80.61 370	79.88 372	82.81 387	90.75 405	76.38 408	97.69 396	95.76 402	66.44 405	83.52 398	92.25 400	62.54 401	87.16 407	68.53 407	61.40 404	84.89 405

ANet_high		77.30 372	74.86 376	84.62 386	75.88 412	77.61 406	97.63 397	93.15 410	88.81 392	64.27 407	89.29 404	36.51 411	83.93 409	75.89 404	52.31 406	92.33 400

EMVS		80.02 371	79.22 373	82.43 389	91.19 404	76.40 407	97.55 398	92.49 412	66.36 406	83.01 400	91.27 402	64.63 400	85.79 408	65.82 408	60.65 405	85.08 404

MVE	76.82 21	76.91 373	74.31 377	84.70 385	85.38 411	76.05 409	96.88 399	93.17 409	67.39 404	71.28 406	89.01 405	21.66 416	87.69 406	71.74 406	72.29 403	90.35 402
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		91.10 360	91.36 362	90.31 379	95.85 392	73.72 412	94.89 400	99.25 290	68.39 403	95.82 374	99.02 336	80.50 393	98.95 357	93.64 362	94.89 343	98.25 357

Gipuma		90.99 361	90.15 366	93.51 369	98.73 343	90.12 390	93.98 401	99.45 198	79.32 399	92.28 391	94.91 396	69.61 397	97.98 382	87.42 394	95.67 324	92.45 399
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	70.75 22	75.98 374	74.97 375	79.01 390	70.98 413	55.18 415	93.37 402	98.21 379	65.08 407	61.78 408	93.83 398	21.74 415	92.53 402	78.59 402	91.12 379	89.34 403
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		82.80 368	81.52 371	86.66 384	66.61 414	68.44 413	92.79 403	97.92 383	68.96 402	80.04 405	99.85 52	85.77 372	96.15 398	97.86 220	43.89 407	95.39 397

wuyk23d		40.18 375	41.29 380	36.84 391	86.18 410	49.12 416	79.73 404	22.81 416	27.64 408	25.46 411	28.45 411	21.98 414	48.89 410	55.80 409	23.56 410	12.51 408

test_blank		0.13 381	0.17 384	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	1.57 412	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

uanet_test		0.02 382	0.03 385	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.27 413	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

DCPMVS		0.02 382	0.03 385	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.27 413	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

cdsmvs_eth3d_5k		24.64 378	32.85 381	0.00 394	0.00 417	0.00 419	0.00 405	99.51 115	0.00 412	0.00 413	99.56 222	96.58 153	0.00 413	0.00 412	0.00 411	0.00 409

pcd_1.5k_mvsjas		8.27 380	11.03 383	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.27 413	99.01 18	0.00 413	0.00 412	0.00 411	0.00 409

sosnet-low-res		0.02 382	0.03 385	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.27 413	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

sosnet		0.02 382	0.03 385	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.27 413	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

uncertanet		0.02 382	0.03 385	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.27 413	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

Regformer		0.02 382	0.03 385	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.27 413	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

ab-mvs-re		8.30 379	11.06 382	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	99.58 215	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

uanet		0.02 382	0.03 385	0.00 394	0.00 417	0.00 419	0.00 405	0.00 418	0.00 412	0.00 413	0.27 413	0.00 417	0.00 413	0.00 412	0.00 411	0.00 409

WAC-MVS						97.16 278								95.47 336

MSC_two_6792asdad				99.87 11	99.51 170	99.76 37		99.33 260					99.96 30	98.87 108	99.84 81	99.89 20

PC_three_1452									98.18 133	99.84 29	99.70 157	99.31 3	98.52 371	98.30 187	99.80 101	99.81 61

No_MVS				99.87 11	99.51 170	99.76 37		99.33 260					99.96 30	98.87 108	99.84 81	99.89 20

test_one_0601					99.81 46	99.88 8		99.49 144	98.97 51	99.65 93	99.81 89	99.09 14

eth-test2					0.00 417

eth-test					0.00 417

ZD-MVS					99.71 96	99.79 30		99.61 48	96.84 279	99.56 118	99.54 231	98.58 72	99.96 30	96.93 297	99.75 116

IU-MVS					99.84 32	99.88 8		99.32 270	98.30 116	99.84 29				98.86 113	99.85 73	99.89 20

test_241102_TWO								99.48 157	99.08 33	99.88 20	99.81 89	98.94 29	99.96 30	98.91 102	99.84 81	99.88 26

test_241102_ONE					99.84 32	99.90 2		99.48 157	99.07 35	99.91 16	99.74 142	99.20 7	99.76 202

test_0728_THIRD									98.99 45	99.81 37	99.80 103	99.09 14	99.96 30	98.85 115	99.90 43	99.88 26

GSMVS																99.52 167

test_part2					99.81 46	99.83 16				99.77 51

sam_mvs1												94.86 214				99.52 167

sam_mvs												94.72 226

MTGPA								99.47 177

test_post											65.99 408	94.65 232	99.73 213

patchmatchnet-post											98.70 360	94.79 218	99.74 207

gm-plane-assit					98.54 362	92.96 380			94.65 362		99.15 322		99.64 248	97.56 253

test9_res														97.49 259	99.72 122	99.75 88

agg_prior2														97.21 277	99.73 121	99.75 88

agg_prior					99.67 111	99.62 65		99.40 222		98.87 263			99.91 105

TestCases				99.31 148	99.86 20	98.48 217		99.61 48	97.85 175	99.36 167	99.85 52	95.95 174	99.85 150	96.66 310	99.83 90	99.59 150

test_prior				99.68 68	99.67 111	99.48 91		99.56 69					99.83 170			99.74 92

新几何1				99.75 58	99.75 73	99.59 70		99.54 85	96.76 282	99.29 182	99.64 191	98.43 83	99.94 69	96.92 299	99.66 132	99.72 103

旧先验1					99.74 80	99.59 70		99.54 85			99.69 167	98.47 80			99.68 130	99.73 97

原ACMM1				99.65 73	99.73 87	99.33 106		99.47 177	97.46 220	99.12 219	99.66 184	98.67 66	99.91 105	97.70 241	99.69 127	99.71 112

testdata2													99.95 59	96.67 309

segment_acmp												98.96 24

testdata				99.54 99	99.75 73	98.95 165		99.51 115	97.07 260	99.43 145	99.70 157	98.87 37	99.94 69	97.76 232	99.64 135	99.72 103

test12				99.75 58	99.64 128	99.61 67		99.29 283		99.21 202		98.38 87	99.89 127		99.74 119	99.74 92

plane_prior7					99.29 241	97.03 291

plane_prior6					99.27 246	96.98 295						92.71 289

plane_prior5								99.47 177					99.69 234	97.78 228	97.63 260	98.67 294

plane_prior4											99.61 206

plane_prior3						97.00 293			98.69 79	99.11 221

plane_prior1					99.26 248

n2								0.00 418

nn								0.00 418

door-mid								98.05 382

lessismore_v0				97.79 326	98.69 349	95.44 347		94.75 405		95.71 375	99.87 43	88.69 353	99.32 297	95.89 325	94.93 341	98.62 315

LGP-MVS_train				98.49 262	99.33 229	97.05 287		99.55 77	97.46 220	99.24 194	99.83 66	92.58 294	99.72 217	98.09 199	97.51 271	98.68 287

test11								99.35 249

door								97.92 383

HQP5-MVS						96.83 305

BP-MVS														97.19 281

HQP4-MVS										98.66 290			99.64 248			98.64 306

HQP3-MVS								99.39 225							97.58 265

HQP2-MVS												92.47 298

NP-MVS					99.23 254	96.92 301					99.40 273

ACMMP++_ref															97.19 292

ACMMP++															97.43 282

Test By Simon												98.75 55

ITE_SJBPF				98.08 304	99.29 241	96.37 323		98.92 333	98.34 112	98.83 268	99.75 137	91.09 328	99.62 254	95.82 326	97.40 284	98.25 357

DeepMVS_CX				93.34 370	99.29 241	82.27 398		99.22 295	85.15 395	96.33 369	99.05 332	90.97 330	99.73 213	93.57 363	97.77 255	98.01 368

High-resolution multi-view benchmark