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 97	99.76 65	99.42 96	99.90 1	99.55 77	98.56 87	99.78 47	99.70 156	98.65 68	99.79 189	99.65 23	99.78 105	99.41 195

CS-MVS-test		99.49 22	99.48 15	99.54 97	99.78 56	99.30 109	99.89 2	99.58 61	98.56 87	99.73 62	99.69 166	98.55 75	99.82 175	99.69 19	99.85 70	99.48 178

RRT_MVS		98.70 150	98.66 139	98.83 225	98.90 316	98.45 218	99.89 2	99.28 279	97.76 183	98.94 248	99.92 14	96.98 134	99.25 303	99.28 62	97.00 292	98.80 254

mvsmamba		98.92 121	98.87 115	99.08 177	99.07 292	99.16 125	99.88 4	99.51 115	98.15 134	99.40 153	99.89 30	97.12 127	99.33 290	99.38 48	97.40 280	98.73 268

MVSFormer		99.17 81	99.12 74	99.29 153	99.51 170	98.94 165	99.88 4	99.46 182	97.55 207	99.80 40	99.65 184	97.39 116	99.28 298	99.03 83	99.85 70	99.65 129

test_djsdf		98.67 154	98.57 154	98.98 190	98.70 345	98.91 169	99.88 4	99.46 182	97.55 207	99.22 195	99.88 36	95.73 179	99.28 298	99.03 83	97.62 257	98.75 263

OurMVSNet-221017-0		97.88 235	97.77 226	98.19 294	98.71 344	96.53 315	99.88 4	99.00 318	97.79 179	98.78 272	99.94 6	91.68 311	99.35 287	97.21 274	96.99 293	98.69 279

EC-MVSNet		99.44 37	99.39 27	99.58 90	99.56 156	99.49 87	99.88 4	99.58 61	98.38 104	99.73 62	99.69 166	98.20 95	99.70 225	99.64 24	99.82 91	99.54 161

DVP-MVS++		99.59 8	99.50 13	99.88 5	99.51 170	99.88 8	99.87 9	99.51 115	98.99 45	99.88 20	99.81 89	99.27 5	99.96 30	98.85 112	99.80 98	99.81 61

FOURS1					99.91 1	99.93 1	99.87 9	99.56 69	99.10 27	99.81 37

K. test v3		97.10 308	96.79 308	98.01 306	98.72 342	96.33 322	99.87 9	97.05 390	97.59 201	96.16 368	99.80 102	88.71 349	99.04 336	96.69 305	96.55 299	98.65 301

FC-MVSNet-test		98.75 146	98.62 147	99.15 174	99.08 291	99.45 93	99.86 12	99.60 54	98.23 123	98.70 284	99.82 75	96.80 139	99.22 310	99.07 81	96.38 302	98.79 255

v7n		97.87 237	97.52 252	98.92 200	98.76 338	98.58 201	99.84 13	99.46 182	96.20 321	98.91 252	99.70 156	94.89 207	99.44 268	96.03 319	93.89 355	98.75 263

DTE-MVSNet		97.51 286	97.19 294	98.46 268	98.63 351	98.13 234	99.84 13	99.48 155	96.68 284	97.97 336	99.67 178	92.92 275	98.56 367	96.88 298	92.60 370	98.70 275

3Dnovator	97.25 9	99.24 74	99.05 83	99.81 44	99.12 280	99.66 53	99.84 13	99.74 10	99.09 32	98.92 251	99.90 26	95.94 170	99.98 13	98.95 93	99.92 25	99.79 74

FIs		98.78 143	98.63 142	99.23 164	99.18 264	99.54 79	99.83 16	99.59 57	98.28 115	98.79 271	99.81 89	96.75 142	99.37 280	99.08 80	96.38 302	98.78 256

test_fmvs3		92.10 355	91.77 358	93.08 368	96.19 387	86.25 390	99.82 17	98.62 365	96.65 287	95.19 376	96.90 388	55.05 403	95.93 396	96.63 309	90.92 378	97.06 384

jajsoiax		98.43 167	98.28 173	98.88 211	98.60 355	98.43 220	99.82 17	99.53 96	98.19 129	98.63 295	99.80 102	93.22 270	99.44 268	99.22 68	97.50 268	98.77 259

OpenMVS	96.50 16	98.47 164	98.12 184	99.52 111	99.04 299	99.53 82	99.82 17	99.72 11	94.56 360	98.08 329	99.88 36	94.73 219	99.98 13	97.47 259	99.76 111	99.06 235

SDMVSNet		99.11 99	98.90 110	99.75 58	99.81 46	99.59 70	99.81 20	99.65 33	98.78 73	99.64 93	99.88 36	94.56 229	99.93 84	99.67 21	98.26 227	99.72 103

nrg030		98.64 157	98.42 163	99.28 157	99.05 298	99.69 47	99.81 20	99.46 182	98.04 155	99.01 236	99.82 75	96.69 144	99.38 276	99.34 55	94.59 343	98.78 256

HPM-MVS		99.42 42	99.28 55	99.83 40	99.90 4	99.72 42	99.81 20	99.54 85	97.59 201	99.68 74	99.63 196	98.91 34	99.94 69	98.58 152	99.91 32	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 89	98.99 97	99.53 105	99.65 126	99.06 144	99.81 20	99.33 255	97.43 223	99.60 107	99.88 36	97.14 126	99.84 155	99.13 75	98.94 186	99.69 115

3Dnovator+	97.12 13	99.18 79	98.97 101	99.82 41	99.17 272	99.68 48	99.81 20	99.51 115	99.20 18	98.72 277	99.89 30	95.68 181	99.97 21	98.86 110	99.86 63	99.81 61

FA-MVS(test-final)		98.75 146	98.53 158	99.41 129	99.55 160	99.05 146	99.80 25	99.01 317	96.59 296	99.58 111	99.59 210	95.39 189	99.90 116	97.78 225	99.49 144	99.28 212

GeoE		98.85 135	98.62 147	99.53 105	99.61 141	99.08 141	99.80 25	99.51 115	97.10 255	99.31 174	99.78 120	95.23 198	99.77 196	98.21 187	99.03 181	99.75 88

canonicalmvs		99.02 112	98.86 118	99.51 113	99.42 199	99.32 104	99.80 25	99.48 155	98.63 82	99.31 174	98.81 353	97.09 129	99.75 202	99.27 65	97.90 245	99.47 184

v8		97.95 227	97.63 244	98.93 198	98.95 313	98.81 183	99.80 25	99.41 212	96.03 335	99.10 220	99.42 265	94.92 205	99.30 296	96.94 293	94.08 352	98.66 299

Vis-MVSNet (Re-imp)		98.87 125	98.72 130	99.31 145	99.71 96	98.88 171	99.80 25	99.44 201	97.91 165	99.36 165	99.78 120	95.49 187	99.43 272	97.91 212	99.11 172	99.62 142

Anonymous20240521		96.20 325	95.89 328	97.13 342	97.72 375	94.96 354	99.79 30	99.29 277	93.01 374	97.20 356	99.03 333	89.69 339	98.36 371	91.16 378	96.13 307	98.07 361

PS-MVSNAJss		98.92 121	98.92 107	98.90 206	98.78 333	98.53 205	99.78 31	99.54 85	98.07 149	99.00 240	99.76 133	99.01 18	99.37 280	99.13 75	97.23 286	98.81 253

PEN-MVS		97.76 255	97.44 266	98.72 237	98.77 337	98.54 204	99.78 31	99.51 115	97.06 259	98.29 319	99.64 190	92.63 288	98.89 358	98.09 196	93.16 363	98.72 269

anonymousdsp		98.44 166	98.28 173	98.94 196	98.50 360	98.96 159	99.77 33	99.50 135	97.07 257	98.87 260	99.77 128	94.76 217	99.28 298	98.66 139	97.60 258	98.57 328

SixPastTwentyTwo		97.50 287	97.33 283	98.03 303	98.65 349	96.23 326	99.77 33	98.68 362	97.14 248	97.90 337	99.93 9	90.45 329	99.18 318	97.00 287	96.43 301	98.67 291

QAPM		98.67 154	98.30 172	99.80 46	99.20 258	99.67 51	99.77 33	99.72 11	94.74 357	98.73 276	99.90 26	95.78 177	99.98 13	96.96 291	99.88 52	99.76 87

SSC-MVS		92.73 354	93.73 350	89.72 378	95.02 397	81.38 398	99.76 36	99.23 288	94.87 354	92.80 387	98.93 345	94.71 221	91.37 402	74.49 402	93.80 356	96.42 388

test_vis3_rt		87.04 361	85.81 364	90.73 375	93.99 399	81.96 396	99.76 36	90.23 410	92.81 376	81.35 398	91.56 398	40.06 407	99.07 333	94.27 352	88.23 385	91.15 398

dcpmvs_2		99.23 75	99.58 7	98.16 296	99.83 39	94.68 357	99.76 36	99.52 101	99.07 35	99.98 6	99.88 36	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 36	99.56 69	97.72 188	99.76 56	99.75 136	99.13 12	99.92 95	99.07 81	99.92 25	99.85 36

v10		97.85 240	97.52 252	98.86 219	98.99 306	98.67 192	99.75 40	99.41 212	95.70 339	98.98 242	99.41 269	94.75 218	99.23 307	96.01 321	94.63 342	98.67 291

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 62	99.89 4	99.75 40	99.56 69	99.02 38	99.88 20	99.85 53	99.18 10	99.96 30	99.22 68	99.92 25	99.90 17
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
IS-MVSNet		99.05 108	98.87 115	99.57 92	99.73 87	99.32 104	99.75 40	99.20 294	98.02 158	99.56 115	99.86 48	96.54 149	99.67 233	98.09 196	99.13 171	99.73 97

test_vis1_n		97.92 231	97.44 266	99.34 138	99.53 163	98.08 236	99.74 43	99.49 143	99.15 20	100.00 1	99.94 6	79.51 391	99.98 13	99.88 14	99.76 111	99.97 4

test_fmvs1_n		98.41 170	98.14 181	99.21 165	99.82 42	97.71 260	99.74 43	99.49 143	99.32 14	99.99 2	99.95 3	85.32 374	99.97 21	99.82 16	99.84 78	99.96 7

tttt0517		98.42 168	98.14 181	99.28 157	99.66 120	98.38 223	99.74 43	96.85 391	97.68 194	99.79 42	99.74 141	91.39 319	99.89 127	98.83 118	99.56 139	99.57 156

WB-MVS		93.10 352	94.10 346	90.12 377	95.51 395	81.88 397	99.73 46	99.27 282	95.05 350	93.09 386	98.91 349	94.70 222	91.89 401	76.62 400	94.02 354	96.58 387

test_fmvs2		97.25 302	97.30 286	97.09 344	99.43 197	93.31 375	99.73 46	98.87 340	98.83 64	99.28 180	99.80 102	84.45 379	99.66 236	97.88 214	97.45 274	98.30 350

baseline		99.15 85	99.02 91	99.53 105	99.66 120	99.14 131	99.72 48	99.48 155	98.35 109	99.42 144	99.84 63	96.07 163	99.79 189	99.51 35	99.14 170	99.67 122

RPSCF		98.22 186	98.62 147	96.99 345	99.82 42	91.58 384	99.72 48	99.44 201	96.61 292	99.66 83	99.89 30	95.92 171	99.82 175	97.46 260	99.10 175	99.57 156

CSCG		99.32 59	99.32 40	99.32 144	99.85 26	98.29 225	99.71 50	99.66 28	98.11 141	99.41 148	99.80 102	98.37 88	99.96 30	98.99 89	99.96 12	99.72 103

dmvs_re		98.08 203	98.16 178	97.85 316	99.55 160	94.67 358	99.70 51	98.92 329	98.15 134	99.06 230	99.35 286	93.67 263	99.25 303	97.77 228	97.25 285	99.64 136

WR-MVS_H		98.13 197	97.87 217	98.90 206	99.02 301	98.84 177	99.70 51	99.59 57	97.27 237	98.40 311	99.19 317	95.53 185	99.23 307	98.34 179	93.78 357	98.61 322

LTVRE_ROB	97.16 12	98.02 215	97.90 211	98.40 277	99.23 251	96.80 305	99.70 51	99.60 54	97.12 251	98.18 326	99.70 156	91.73 310	99.72 213	98.39 173	97.45 274	98.68 284
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		91.90 356	91.26 360	93.84 365	95.52 394	85.92 391	99.69 54	98.53 369	95.31 344	93.87 382	96.37 391	55.33 402	98.27 372	95.70 327	90.98 377	97.32 383

XVS		99.53 16	99.42 22	99.87 11	99.85 26	99.83 16	99.69 54	99.68 20	98.98 48	99.37 161	99.74 141	98.81 44	99.94 69	98.79 123	99.86 63	99.84 40

X-MVStestdata		96.55 317	95.45 335	99.87 11	99.85 26	99.83 16	99.69 54	99.68 20	98.98 48	99.37 161	64.01 407	98.81 44	99.94 69	98.79 123	99.86 63	99.84 40

V42		98.06 205	97.79 221	98.86 219	98.98 309	98.84 177	99.69 54	99.34 248	96.53 298	99.30 176	99.37 280	94.67 224	99.32 293	97.57 249	94.66 341	98.42 342

mPP-MVS		99.44 37	99.30 49	99.86 21	99.88 11	99.79 30	99.69 54	99.48 155	98.12 139	99.50 127	99.75 136	98.78 48	99.97 21	98.57 155	99.89 49	99.83 49

CP-MVS		99.45 33	99.32 40	99.85 28	99.83 39	99.75 39	99.69 54	99.52 101	98.07 149	99.53 122	99.63 196	98.93 33	99.97 21	98.74 127	99.91 32	99.83 49

FE-MVS		98.48 163	98.17 177	99.40 131	99.54 162	98.96 159	99.68 60	98.81 347	95.54 341	99.62 101	99.70 156	93.82 258	99.93 84	97.35 268	99.46 145	99.32 209

PS-CasMVS		97.93 228	97.59 247	98.95 195	98.99 306	99.06 144	99.68 60	99.52 101	97.13 249	98.31 316	99.68 172	92.44 297	99.05 335	98.51 163	94.08 352	98.75 263

Vis-MVSNet		99.12 95	98.97 101	99.56 94	99.78 56	99.10 136	99.68 60	99.66 28	98.49 95	99.86 27	99.87 44	94.77 216	99.84 155	99.19 70	99.41 149	99.74 92
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_vis1_n_1920		98.63 158	98.40 165	99.31 145	99.86 20	97.94 248	99.67 63	99.62 41	99.43 7	99.99 2	99.91 20	87.29 365	100.00 1	99.92 12	99.92 25	99.98 2

EIA-MVS		99.18 79	99.09 79	99.45 123	99.49 181	99.18 122	99.67 63	99.53 96	97.66 197	99.40 153	99.44 261	98.10 99	99.81 180	98.94 94	99.62 135	99.35 204

MSP-MVS		99.42 42	99.27 58	99.88 5	99.89 8	99.80 27	99.67 63	99.50 135	98.70 78	99.77 51	99.49 246	98.21 94	99.95 59	98.46 169	99.77 108	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		99.10 103	98.97 101	99.48 117	99.49 181	99.14 131	99.67 63	99.34 248	97.31 234	99.58 111	99.76 133	97.65 112	99.82 175	98.87 105	99.07 178	99.46 186

CP-MVSNet		98.09 201	97.78 224	99.01 186	98.97 311	99.24 117	99.67 63	99.46 182	97.25 239	98.48 308	99.64 190	93.79 259	99.06 334	98.63 142	94.10 351	98.74 266

MTAPA		99.52 17	99.39 27	99.89 4	99.90 4	99.86 13	99.66 68	99.47 173	98.79 70	99.68 74	99.81 89	98.43 83	99.97 21	98.88 102	99.90 40	99.83 49

HFP-MVS		99.49 22	99.37 30	99.86 21	99.87 15	99.80 27	99.66 68	99.67 23	98.15 134	99.68 74	99.69 166	99.06 16	99.96 30	98.69 135	99.87 55	99.84 40

mvs_tets		98.40 173	98.23 175	98.91 204	98.67 348	98.51 211	99.66 68	99.53 96	98.19 129	98.65 293	99.81 89	92.75 279	99.44 268	99.31 58	97.48 272	98.77 259

EU-MVSNet		97.98 222	98.03 196	97.81 322	98.72 342	96.65 311	99.66 68	99.66 28	98.09 144	98.35 314	99.82 75	95.25 197	98.01 378	97.41 264	95.30 329	98.78 256

ACMMPR		99.49 22	99.36 32	99.86 21	99.87 15	99.79 30	99.66 68	99.67 23	98.15 134	99.67 78	99.69 166	98.95 27	99.96 30	98.69 135	99.87 55	99.84 40

MP-MVS		99.33 58	99.15 71	99.87 11	99.88 11	99.82 22	99.66 68	99.46 182	98.09 144	99.48 131	99.74 141	98.29 91	99.96 30	97.93 211	99.87 55	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 83	99.01 95	99.61 84	99.81 46	98.86 175	99.65 74	99.64 36	99.39 10	99.97 13	99.94 6	93.20 271	99.98 13	99.55 29	99.91 32	99.99 1

region2R		99.48 26	99.35 34	99.87 11	99.88 11	99.80 27	99.65 74	99.66 28	98.13 138	99.66 83	99.68 172	98.96 24	99.96 30	98.62 143	99.87 55	99.84 40

TranMVSNet+NR-MVSNet		97.93 228	97.66 239	98.76 235	98.78 333	98.62 197	99.65 74	99.49 143	97.76 183	98.49 307	99.60 208	94.23 242	98.97 352	98.00 207	92.90 365	98.70 275

mvsany_test3		93.77 350	93.45 354	94.74 363	95.78 390	88.01 389	99.64 77	98.25 373	98.28 115	94.31 380	97.97 380	68.89 395	98.51 369	97.50 255	90.37 379	97.71 375

ZNCC-MVS		99.47 29	99.33 38	99.87 11	99.87 15	99.81 25	99.64 77	99.67 23	98.08 148	99.55 119	99.64 190	98.91 34	99.96 30	98.72 130	99.90 40	99.82 54

tfpnnormal		97.84 243	97.47 258	98.98 190	99.20 258	99.22 119	99.64 77	99.61 48	96.32 312	98.27 320	99.70 156	93.35 267	99.44 268	95.69 328	95.40 327	98.27 352

casdiffmvs_mvg		99.15 85	99.02 91	99.55 96	99.66 120	99.09 137	99.64 77	99.56 69	98.26 118	99.45 135	99.87 44	96.03 165	99.81 180	99.54 30	99.15 169	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 81	99.52 101	98.38 104	99.76 56	99.82 75	98.53 76	99.95 59	98.61 146	99.81 94	99.77 82

RE-MVS-def			99.34 36		99.76 65	99.82 22	99.63 81	99.52 101	98.38 104	99.76 56	99.82 75	98.75 55		98.61 146	99.81 94	99.77 82

TSAR-MVS + MP.		99.58 9	99.50 13	99.81 44	99.91 1	99.66 53	99.63 81	99.39 221	98.91 58	99.78 47	99.85 53	99.36 2	99.94 69	98.84 115	99.88 52	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		96.22 323	96.03 324	96.79 353	97.31 381	94.14 365	99.63 81	99.08 308	96.17 324	97.04 360	99.06 330	93.94 253	97.76 384	86.96 393	95.06 334	98.47 336

APD-MVS_3200maxsize		99.48 26	99.35 34	99.85 28	99.76 65	99.83 16	99.63 81	99.54 85	98.36 108	99.79 42	99.82 75	98.86 38	99.95 59	98.62 143	99.81 94	99.78 80

bld_raw_dy_0_64		98.26 185	97.88 216	99.40 131	99.37 214	99.09 137	99.62 86	98.94 324	98.53 90	99.40 153	99.51 239	88.93 345	99.89 127	99.00 87	97.64 254	99.23 216

test0726					99.85 26	99.89 4	99.62 86	99.50 135	99.10 27	99.86 27	99.82 75	98.94 29

EPNet		98.86 128	98.71 132	99.30 150	97.20 383	98.18 230	99.62 86	98.91 333	99.28 16	98.63 295	99.81 89	95.96 167	99.99 4	99.24 67	99.72 119	99.73 97
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t		98.93 120	98.67 136	99.72 65	99.85 26	99.53 82	99.62 86	99.59 57	92.65 377	99.71 68	99.78 120	98.06 102	99.90 116	98.84 115	99.91 32	99.74 92

HY-MVS	97.30 7	98.85 135	98.64 141	99.47 120	99.42 199	99.08 141	99.62 86	99.36 238	97.39 228	99.28 180	99.68 172	96.44 154	99.92 95	98.37 176	98.22 229	99.40 197

ACMMP		99.45 33	99.32 40	99.82 41	99.89 8	99.67 51	99.62 86	99.69 18	98.12 139	99.63 96	99.84 63	98.73 60	99.96 30	98.55 161	99.83 87	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 61	99.19 68	99.64 78	99.82 42	99.23 118	99.62 86	99.55 77	98.94 54	99.63 96	99.95 3	95.82 176	99.94 69	99.37 50	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	99.15 130	99.61 93	99.45 193	99.01 40	99.89 19	99.82 75	99.01 18	99.92 95	99.56 28	99.95 16	99.85 36

test2506		96.81 314	96.65 310	97.29 339	99.74 80	92.21 382	99.60 94	85.06 411	99.13 22	99.77 51	99.93 9	87.82 363	99.85 148	99.38 48	99.38 150	99.80 70

SED-MVS		99.61 7	99.52 11	99.88 5	99.84 32	99.90 2	99.60 94	99.48 155	99.08 33	99.91 16	99.81 89	99.20 7	99.96 30	98.91 99	99.85 70	99.79 74

OPU-MVS				99.64 78	99.56 156	99.72 42	99.60 94				99.70 156	99.27 5	99.42 273	98.24 186	99.80 98	99.79 74

GST-MVS		99.40 50	99.24 63	99.85 28	99.86 20	99.79 30	99.60 94	99.67 23	97.97 160	99.63 96	99.68 172	98.52 77	99.95 59	98.38 174	99.86 63	99.81 61

EI-MVSNet-UG-set		99.58 9	99.57 8	99.64 78	99.78 56	99.14 131	99.60 94	99.45 193	99.01 40	99.90 18	99.83 67	98.98 23	99.93 84	99.59 25	99.95 16	99.86 33

ACMH	97.28 8	98.10 200	97.99 200	98.44 272	99.41 202	96.96 297	99.60 94	99.56 69	98.09 144	98.15 327	99.91 20	90.87 326	99.70 225	98.88 102	97.45 274	98.67 291
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ECVR-MVS		98.04 211	98.05 194	98.00 308	99.74 80	94.37 362	99.59 100	94.98 401	99.13 22	99.66 83	99.93 9	90.67 328	99.84 155	99.40 47	99.38 150	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	98.21 126	99.73 62	99.79 114	98.68 64	99.96 30	98.44 171	99.77 108	99.79 74

thres100view900		97.76 255	97.45 261	98.69 241	99.72 91	97.86 252	99.59 100	98.74 354	97.93 163	99.26 188	98.62 359	91.75 308	99.83 168	93.22 363	98.18 234	98.37 348

thres600view7		97.86 239	97.51 254	98.92 200	99.72 91	97.95 246	99.59 100	98.74 354	97.94 162	99.27 184	98.62 359	91.75 308	99.86 142	93.73 358	98.19 233	98.96 246

LCM-MVSNet-Re		97.83 245	98.15 180	96.87 351	99.30 234	92.25 381	99.59 100	98.26 372	97.43 223	96.20 367	99.13 323	96.27 159	98.73 364	98.17 192	98.99 184	99.64 136

baseline1		98.31 179	97.95 206	99.38 136	99.50 179	98.74 187	99.59 100	98.93 326	98.41 102	99.14 212	99.60 208	94.59 227	99.79 189	98.48 165	93.29 361	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 83	99.79 42	99.83 67	99.28 4	99.97 21	98.48 165	99.90 40	99.84 40
Skip Steuart: Steuart Systems R&D Blog.
CPTT-MVS		99.11 99	98.90 110	99.74 61	99.80 52	99.46 92	99.59 100	99.49 143	97.03 263	99.63 96	99.69 166	97.27 124	99.96 30	97.82 222	99.84 78	99.81 61

test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 55	99.38 211	99.37 100	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 23	99.94 11

dmvs_testset		95.02 339	96.12 321	91.72 372	99.10 285	80.43 400	99.58 108	97.87 382	97.47 216	95.22 374	98.82 352	93.99 251	95.18 397	88.09 389	94.91 339	99.56 158

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 52	99.84 32	99.44 94	99.58 108	99.69 18	99.43 7	99.98 6	99.91 20	98.62 70	100.00 1	99.97 1	99.95 16	99.90 17

test1111		98.04 211	98.11 185	97.83 319	99.74 80	93.82 367	99.58 108	95.40 400	99.12 25	99.65 89	99.93 9	90.73 327	99.84 155	99.43 46	99.38 150	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	97.84 173	99.71 68	99.80 102	99.12 13	99.97 21	98.33 180	99.87 55	99.83 49

LPG-MVS_test		98.22 186	98.13 183	98.49 260	99.33 226	97.05 286	99.58 108	99.55 77	97.46 217	99.24 190	99.83 67	92.58 289	99.72 213	98.09 196	97.51 266	98.68 284

PHI-MVS		99.30 61	99.17 70	99.70 67	99.56 156	99.52 85	99.58 108	99.80 8	97.12 251	99.62 101	99.73 147	98.58 72	99.90 116	98.61 146	99.91 32	99.68 119

SF-MVS		99.38 53	99.24 63	99.79 49	99.79 54	99.68 48	99.57 115	99.54 85	97.82 178	99.71 68	99.80 102	98.95 27	99.93 84	98.19 189	99.84 78	99.74 92

DVP-MVS		99.57 12	99.47 17	99.88 5	99.85 26	99.89 4	99.57 115	99.37 237	99.10 27	99.81 37	99.80 102	98.94 29	99.96 30	98.93 96	99.86 63	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 96	99.86 63	99.88 26

Effi-MVS+-dtu		98.78 143	98.89 113	98.47 267	99.33 226	96.91 299	99.57 115	99.30 273	98.47 96	99.41 148	98.99 338	96.78 140	99.74 203	98.73 129	99.38 150	98.74 266

v2v482		98.06 205	97.77 226	98.92 200	98.90 316	98.82 181	99.57 115	99.36 238	96.65 287	99.19 204	99.35 286	94.20 243	99.25 303	97.72 235	94.97 336	98.69 279

DSMNet-mixed		97.25 302	97.35 278	96.95 348	97.84 371	93.61 373	99.57 115	96.63 395	96.13 329	98.87 260	98.61 361	94.59 227	97.70 385	95.08 342	98.86 193	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 67	98.75 55	99.99 4	99.97 1	99.96 12	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 75	98.75 55	99.99 4	99.97 1	99.97 7	99.94 11

sd_testset		98.75 146	98.57 154	99.29 153	99.81 46	98.26 227	99.56 121	99.62 41	98.78 73	99.64 93	99.88 36	92.02 302	99.88 133	99.54 30	98.26 227	99.72 103

KD-MVS_self_test		95.00 340	94.34 345	96.96 347	97.07 386	95.39 345	99.56 121	99.44 201	95.11 347	97.13 358	97.32 386	91.86 306	97.27 388	90.35 381	81.23 395	98.23 356

ETV-MVS		99.26 69	99.21 66	99.40 131	99.46 190	99.30 109	99.56 121	99.52 101	98.52 92	99.44 140	99.27 307	98.41 86	99.86 142	99.10 78	99.59 137	99.04 236

SMA-MVS		99.44 37	99.30 49	99.85 28	99.73 87	99.83 16	99.56 121	99.47 173	97.45 220	99.78 47	99.82 75	99.18 10	99.91 105	98.79 123	99.89 49	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		98.87 125	98.72 130	99.31 145	99.86 20	98.48 215	99.56 121	99.61 48	97.85 171	99.36 165	99.85 53	95.95 168	99.85 148	96.66 307	99.83 87	99.59 150

casdiffmvs		99.13 89	98.98 100	99.56 94	99.65 126	99.16 125	99.56 121	99.50 135	98.33 112	99.41 148	99.86 48	95.92 171	99.83 168	99.45 45	99.16 166	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		98.38 174	98.09 189	99.24 162	99.26 245	99.32 104	99.56 121	99.55 77	97.45 220	98.71 278	99.83 67	93.23 268	99.63 249	98.88 102	96.32 304	98.76 261

ACMH+	97.24 10	97.92 231	97.78 224	98.32 284	99.46 190	96.68 310	99.56 121	99.54 85	98.41 102	97.79 343	99.87 44	90.18 335	99.66 236	98.05 204	97.18 289	98.62 313

ACMM	97.58 5	98.37 175	98.34 168	98.48 262	99.41 202	97.10 280	99.56 121	99.45 193	98.53 90	99.04 233	99.85 53	93.00 273	99.71 219	98.74 127	97.45 274	98.64 303
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LS3D		99.27 67	99.12 74	99.74 61	99.18 264	99.75 39	99.56 121	99.57 64	98.45 98	99.49 130	99.85 53	97.77 109	99.94 69	98.33 180	99.84 78	99.52 167

test_fmvsmconf0.01_n		99.22 76	99.03 87	99.79 49	98.42 363	99.48 89	99.55 133	99.51 115	99.39 10	99.78 47	99.93 9	94.80 211	99.95 59	99.93 11	99.95 16	99.94 11

test_fmvs1		98.88 124	98.79 126	99.16 170	99.69 106	97.61 263	99.55 133	99.49 143	99.32 14	99.98 6	99.91 20	91.41 318	99.96 30	99.82 16	99.92 25	99.90 17

v144192		97.92 231	97.60 246	98.87 215	98.83 328	98.65 194	99.55 133	99.34 248	96.20 321	99.32 173	99.40 272	94.36 238	99.26 302	96.37 315	95.03 335	98.70 275

iter_conf05		98.55 161	98.44 161	98.87 215	99.34 224	98.60 200	99.55 133	99.42 209	98.21 126	99.37 161	99.77 128	93.55 264	99.38 276	99.30 61	97.48 272	98.63 310

API-MVS		99.04 109	99.03 87	99.06 180	99.40 207	99.31 107	99.55 133	99.56 69	98.54 89	99.33 172	99.39 276	98.76 52	99.78 194	96.98 289	99.78 105	98.07 361

fmvsm_s_conf0.1_n_a		99.26 69	99.06 82	99.85 28	99.52 167	99.62 65	99.54 138	99.62 41	98.69 79	99.99 2	99.96 1	94.47 235	99.94 69	99.88 14	99.92 25	99.98 2

APD_test1		95.87 330	96.49 314	94.00 364	99.53 163	84.01 392	99.54 138	99.32 265	95.91 337	97.99 334	99.85 53	85.49 372	99.88 133	91.96 374	98.84 195	98.12 359

thisisatest0530		98.35 176	98.03 196	99.31 145	99.63 131	98.56 202	99.54 138	96.75 393	97.53 211	99.73 62	99.65 184	91.25 322	99.89 127	98.62 143	99.56 139	99.48 178

MTMP							99.54 138	98.88 338

v1144		97.98 222	97.69 236	98.85 222	98.87 322	98.66 193	99.54 138	99.35 244	96.27 316	99.23 194	99.35 286	94.67 224	99.23 307	96.73 302	95.16 332	98.68 284

v148		97.79 253	97.55 248	98.50 259	98.74 339	97.72 257	99.54 138	99.33 255	96.26 317	98.90 254	99.51 239	94.68 223	99.14 321	97.83 221	93.15 364	98.63 310

CostFormer		97.72 264	97.73 233	97.71 326	99.15 278	94.02 366	99.54 138	99.02 316	94.67 358	99.04 233	99.35 286	92.35 299	99.77 196	98.50 164	97.94 244	99.34 207

MVSTER		98.49 162	98.32 170	99.00 188	99.35 220	99.02 148	99.54 138	99.38 229	97.41 226	99.20 201	99.73 147	93.86 257	99.36 284	98.87 105	97.56 262	98.62 313

fmvsm_s_conf0.1_n		99.29 63	99.10 76	99.86 21	99.70 101	99.65 57	99.53 146	99.62 41	98.74 75	99.99 2	99.95 3	94.53 233	99.94 69	99.89 13	99.96 12	99.97 4

fmvsm_s_conf0.5_n_a		99.56 13	99.47 17	99.85 28	99.83 39	99.64 63	99.52 147	99.65 33	99.10 27	99.98 6	99.92 14	97.35 120	99.96 30	99.94 10	99.92 25	99.95 9

MM		99.40 50	99.28 55	99.74 61	99.67 111	99.31 107	99.52 147	98.87 340	99.55 1	99.74 60	99.80 102	96.47 151	99.98 13	99.97 1	99.97 7	99.94 11

patch_mono-2		99.26 69	99.62 5	98.16 296	99.81 46	94.59 359	99.52 147	99.64 36	99.33 13	99.73 62	99.90 26	99.00 22	99.99 4	99.69 19	99.98 4	99.89 20

Fast-Effi-MVS+-dtu		98.77 145	98.83 122	98.60 246	99.41 202	96.99 293	99.52 147	99.49 143	98.11 141	99.24 190	99.34 290	96.96 136	99.79 189	97.95 210	99.45 146	99.02 239

MVS_0304		99.42 42	99.32 40	99.72 65	99.70 101	99.27 113	99.52 147	97.57 387	99.51 2	99.82 35	99.78 120	98.09 100	99.96 30	99.97 1	99.97 7	99.94 11

Fast-Effi-MVS+		98.70 150	98.43 162	99.51 113	99.51 170	99.28 111	99.52 147	99.47 173	96.11 330	99.01 236	99.34 290	96.20 161	99.84 155	97.88 214	98.82 197	99.39 198

v1921920		97.80 252	97.45 261	98.84 223	98.80 329	98.53 205	99.52 147	99.34 248	96.15 327	99.24 190	99.47 254	93.98 252	99.29 297	95.40 336	95.13 333	98.69 279

MIMVSNet1		95.51 334	95.04 339	96.92 350	97.38 378	95.60 336	99.52 147	99.50 135	93.65 368	96.97 362	99.17 318	85.28 375	96.56 393	88.36 388	95.55 324	98.60 325

fmvsm_s_conf0.5_n		99.51 18	99.40 25	99.85 28	99.84 32	99.65 57	99.51 155	99.67 23	99.13 22	99.98 6	99.92 14	96.60 146	99.96 30	99.95 8	99.96 12	99.95 9

UniMVSNet_ETH3D		97.32 299	96.81 307	98.87 215	99.40 207	97.46 266	99.51 155	99.53 96	95.86 338	98.54 304	99.77 128	82.44 387	99.66 236	98.68 137	97.52 265	99.50 176

alignmvs		98.81 139	98.56 156	99.58 90	99.43 197	99.42 96	99.51 155	98.96 323	98.61 84	99.35 168	98.92 348	94.78 213	99.77 196	99.35 51	98.11 239	99.54 161

v1192		97.81 250	97.44 266	98.91 204	98.88 319	98.68 191	99.51 155	99.34 248	96.18 323	99.20 201	99.34 290	94.03 250	99.36 284	95.32 338	95.18 331	98.69 279

test20.03		96.12 327	95.96 326	96.63 354	97.44 377	95.45 343	99.51 155	99.38 229	96.55 297	96.16 368	99.25 310	93.76 261	96.17 394	87.35 392	94.22 349	98.27 352

mvs_anonymous		99.03 111	98.99 97	99.16 170	99.38 211	98.52 209	99.51 155	99.38 229	97.79 179	99.38 159	99.81 89	97.30 122	99.45 263	99.35 51	98.99 184	99.51 173

TAMVS		99.12 95	99.08 80	99.24 162	99.46 190	98.55 203	99.51 155	99.46 182	98.09 144	99.45 135	99.82 75	98.34 89	99.51 259	98.70 132	98.93 187	99.67 122

test_fmvsmconf0.1_n		99.55 14	99.45 21	99.86 21	99.44 196	99.65 57	99.50 162	99.61 48	99.45 5	99.87 25	99.92 14	97.31 121	99.97 21	99.95 8	99.99 1	99.97 4

test_yl		98.86 128	98.63 142	99.54 97	99.49 181	99.18 122	99.50 162	99.07 311	98.22 124	99.61 104	99.51 239	95.37 190	99.84 155	98.60 149	98.33 221	99.59 150

DCV-MVSNet		98.86 128	98.63 142	99.54 97	99.49 181	99.18 122	99.50 162	99.07 311	98.22 124	99.61 104	99.51 239	95.37 190	99.84 155	98.60 149	98.33 221	99.59 150

tfpn200view9		97.72 264	97.38 274	98.72 237	99.69 106	97.96 244	99.50 162	98.73 359	97.83 174	99.17 209	98.45 364	91.67 312	99.83 168	93.22 363	98.18 234	98.37 348

UA-Net		99.42 42	99.29 53	99.80 46	99.62 137	99.55 77	99.50 162	99.70 15	98.79 70	99.77 51	99.96 1	97.45 115	99.96 30	98.92 98	99.90 40	99.89 20

pm-mvs1		97.68 271	97.28 289	98.88 211	99.06 295	98.62 197	99.50 162	99.45 193	96.32 312	97.87 339	99.79 114	92.47 293	99.35 287	97.54 252	93.54 359	98.67 291

EI-MVSNet		98.67 154	98.67 136	98.68 242	99.35 220	97.97 242	99.50 162	99.38 229	96.93 272	99.20 201	99.83 67	97.87 105	99.36 284	98.38 174	97.56 262	98.71 271

CVMVSNet		98.57 160	98.67 136	98.30 286	99.35 220	95.59 337	99.50 162	99.55 77	98.60 85	99.39 157	99.83 67	94.48 234	99.45 263	98.75 126	98.56 211	99.85 36

VPA-MVSNet		98.29 182	97.95 206	99.30 150	99.16 274	99.54 79	99.50 162	99.58 61	98.27 117	99.35 168	99.37 280	92.53 291	99.65 241	99.35 51	94.46 344	98.72 269

thres400		97.77 254	97.38 274	98.92 200	99.69 106	97.96 244	99.50 162	98.73 359	97.83 174	99.17 209	98.45 364	91.67 312	99.83 168	93.22 363	98.18 234	98.96 246

APD-MVS		99.27 67	99.08 80	99.84 39	99.75 73	99.79 30	99.50 162	99.50 135	97.16 247	99.77 51	99.82 75	98.78 48	99.94 69	97.56 250	99.86 63	99.80 70
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_vis1_rt		95.81 332	95.65 332	96.32 358	99.67 111	91.35 385	99.49 173	96.74 394	98.25 119	95.24 373	98.10 377	74.96 392	99.90 116	99.53 32	98.85 194	97.70 377

TransMVSNet (Re)		97.15 306	96.58 311	98.86 219	99.12 280	98.85 176	99.49 173	98.91 333	95.48 342	97.16 357	99.80 102	93.38 266	99.11 329	94.16 355	91.73 372	98.62 313

UniMVSNet (Re)		98.29 182	98.00 199	99.13 175	99.00 303	99.36 102	99.49 173	99.51 115	97.95 161	98.97 244	99.13 323	96.30 158	99.38 276	98.36 178	93.34 360	98.66 299

EPMVS		97.82 248	97.65 240	98.35 281	98.88 319	95.98 330	99.49 173	94.71 403	97.57 204	99.26 188	99.48 251	92.46 296	99.71 219	97.87 216	99.08 177	99.35 204

test_fmvsmconf_n		99.70 3	99.64 4	99.87 11	99.80 52	99.66 53	99.48 177	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		97.88 235	97.54 251	98.90 206	99.71 96	98.53 205	99.48 177	99.57 64	94.16 363	98.81 267	99.68 172	93.23 268	99.42 273	98.84 115	94.42 346	98.76 261

v1240		97.69 269	97.32 284	98.79 232	98.85 326	98.43 220	99.48 177	99.36 238	96.11 330	99.27 184	99.36 283	93.76 261	99.24 306	94.46 349	95.23 330	98.70 275

VPNet		97.84 243	97.44 266	99.01 186	99.21 256	98.94 165	99.48 177	99.57 64	98.38 104	99.28 180	99.73 147	88.89 346	99.39 275	99.19 70	93.27 362	98.71 271

UniMVSNet_NR-MVSNet		98.22 186	97.97 203	98.96 193	98.92 315	98.98 152	99.48 177	99.53 96	97.76 183	98.71 278	99.46 258	96.43 155	99.22 310	98.57 155	92.87 367	98.69 279

TDRefinement		95.42 336	94.57 343	97.97 310	89.83 404	96.11 329	99.48 177	98.75 351	96.74 280	96.68 363	99.88 36	88.65 352	99.71 219	98.37 176	82.74 393	98.09 360

ACMMP_NAP		99.47 29	99.34 36	99.88 5	99.87 15	99.86 13	99.47 183	99.48 155	98.05 154	99.76 56	99.86 48	98.82 43	99.93 84	98.82 122	99.91 32	99.84 40

NR-MVSNet		97.97 225	97.61 245	99.02 185	98.87 322	99.26 115	99.47 183	99.42 209	97.63 199	97.08 359	99.50 243	95.07 201	99.13 324	97.86 217	93.59 358	98.68 284

PVSNet_Blended_VisFu		99.36 55	99.28 55	99.61 84	99.86 20	99.07 143	99.47 183	99.93 2	97.66 197	99.71 68	99.86 48	97.73 110	99.96 30	99.47 43	99.82 91	99.79 74

SD-MVS		99.41 47	99.52 11	99.05 182	99.74 80	99.68 48	99.46 186	99.52 101	99.11 26	99.88 20	99.91 20	99.43 1	97.70 385	98.72 130	99.93 23	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		97.28 300	96.76 309	98.82 226	99.37 214	98.07 237	99.45 187	99.36 238	97.56 206	97.89 338	98.95 343	83.70 382	98.82 359	96.03 319	98.56 211	99.58 154

tt0805		97.97 225	97.77 226	98.57 251	99.59 148	96.61 313	99.45 187	99.08 308	98.21 126	98.88 257	99.80 102	88.66 351	99.70 225	98.58 152	97.72 251	99.39 198

tpm2		97.44 294	97.34 281	97.74 325	99.15 278	94.36 363	99.45 187	98.94 324	93.45 372	98.90 254	99.44 261	91.35 320	99.59 253	97.31 269	98.07 240	99.29 211

FMVSNet2		97.72 264	97.36 276	98.80 231	99.51 170	98.84 177	99.45 187	99.42 209	96.49 300	98.86 264	99.29 302	90.26 331	98.98 345	96.44 312	96.56 298	98.58 327

CDS-MVSNet		99.09 104	99.03 87	99.25 160	99.42 199	98.73 188	99.45 187	99.46 182	98.11 141	99.46 134	99.77 128	98.01 103	99.37 280	98.70 132	98.92 189	99.66 125
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MAR-MVS		98.86 128	98.63 142	99.54 97	99.37 214	99.66 53	99.45 187	99.54 85	96.61 292	99.01 236	99.40 272	97.09 129	99.86 142	97.68 240	99.53 142	99.10 224
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		98.87 125	98.69 134	99.40 131	99.22 255	98.72 189	99.44 193	99.68 20	99.24 17	99.18 208	99.42 265	92.74 281	99.96 30	99.34 55	99.94 22	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		98.86 128	98.63 142	99.54 97	99.64 128	99.19 120	99.44 193	99.54 85	97.77 182	99.30 176	99.81 89	94.20 243	99.93 84	99.17 73	98.82 197	99.49 177

test_0402		96.64 316	96.24 319	97.85 316	98.85 326	96.43 319	99.44 193	99.26 283	93.52 369	96.98 361	99.52 236	88.52 354	99.20 317	92.58 373	97.50 268	97.93 372

ACMP	97.20 11	98.06 205	97.94 208	98.45 269	99.37 214	97.01 291	99.44 193	99.49 143	97.54 210	98.45 309	99.79 114	91.95 304	99.72 213	97.91 212	97.49 271	98.62 313
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
GG-mvs-BLEND				98.45 269	98.55 358	98.16 231	99.43 197	93.68 405		97.23 354	98.46 363	89.30 342	99.22 310	95.43 335	98.22 229	97.98 369

HPM-MVS++		99.39 52	99.23 65	99.87 11	99.75 73	99.84 15	99.43 197	99.51 115	98.68 81	99.27 184	99.53 233	98.64 69	99.96 30	98.44 171	99.80 98	99.79 74

tpm cat1		97.39 296	97.36 276	97.50 334	99.17 272	93.73 369	99.43 197	99.31 269	91.27 381	98.71 278	99.08 327	94.31 241	99.77 196	96.41 314	98.50 215	99.00 240

tpm		97.67 274	97.55 248	98.03 303	99.02 301	95.01 352	99.43 197	98.54 368	96.44 306	99.12 215	99.34 290	91.83 307	99.60 252	97.75 231	96.46 300	99.48 178

GBi-Net		97.68 271	97.48 256	98.29 287	99.51 170	97.26 273	99.43 197	99.48 155	96.49 300	99.07 225	99.32 297	90.26 331	98.98 345	97.10 282	96.65 295	98.62 313

test1		97.68 271	97.48 256	98.29 287	99.51 170	97.26 273	99.43 197	99.48 155	96.49 300	99.07 225	99.32 297	90.26 331	98.98 345	97.10 282	96.65 295	98.62 313

FMVSNet1		96.84 313	96.36 317	98.29 287	99.32 232	97.26 273	99.43 197	99.48 155	95.11 347	98.55 303	99.32 297	83.95 381	98.98 345	95.81 324	96.26 305	98.62 313

testgi		97.65 276	97.50 255	98.13 300	99.36 219	96.45 318	99.42 204	99.48 155	97.76 183	97.87 339	99.45 260	91.09 323	98.81 360	94.53 348	98.52 214	99.13 223

F-COLMAP		99.19 77	99.04 85	99.64 78	99.78 56	99.27 113	99.42 204	99.54 85	97.29 236	99.41 148	99.59 210	98.42 85	99.93 84	98.19 189	99.69 124	99.73 97

Anonymous202405211		98.30 181	97.98 202	99.26 159	99.57 152	98.16 231	99.41 206	98.55 367	96.03 335	99.19 204	99.74 141	91.87 305	99.92 95	99.16 74	98.29 226	99.70 113

MSLP-MVS++		99.46 31	99.47 17	99.44 127	99.60 146	99.16 125	99.41 206	99.71 13	98.98 48	99.45 135	99.78 120	99.19 9	99.54 258	99.28 62	99.84 78	99.63 140

VNet		99.11 99	98.90 110	99.73 64	99.52 167	99.56 75	99.41 206	99.39 221	99.01 40	99.74 60	99.78 120	95.56 184	99.92 95	99.52 34	98.18 234	99.72 103

baseline2		97.87 237	97.55 248	98.82 226	99.18 264	98.02 239	99.41 206	96.58 397	96.97 266	96.51 364	99.17 318	93.43 265	99.57 254	97.71 236	99.03 181	98.86 250

DU-MVS		98.08 203	97.79 221	98.96 193	98.87 322	98.98 152	99.41 206	99.45 193	97.87 167	98.71 278	99.50 243	94.82 209	99.22 310	98.57 155	92.87 367	98.68 284

Baseline_NR-MVSNet		97.76 255	97.45 261	98.68 242	99.09 288	98.29 225	99.41 206	98.85 342	95.65 340	98.63 295	99.67 178	94.82 209	99.10 331	98.07 203	92.89 366	98.64 303

XVG-ACMP-BASELINE		97.83 245	97.71 235	98.20 293	99.11 282	96.33 322	99.41 206	99.52 101	98.06 153	99.05 232	99.50 243	89.64 340	99.73 209	97.73 233	97.38 282	98.53 330

DP-MVS		99.16 83	98.95 105	99.78 52	99.77 62	99.53 82	99.41 206	99.50 135	97.03 263	99.04 233	99.88 36	97.39 116	99.92 95	98.66 139	99.90 40	99.87 31

9.14			99.10 76		99.72 91		99.40 214	99.51 115	97.53 211	99.64 93	99.78 120	98.84 41	99.91 105	97.63 241	99.82 91

D2MVS		98.41 170	98.50 159	98.15 299	99.26 245	96.62 312	99.40 214	99.61 48	97.71 189	98.98 242	99.36 283	96.04 164	99.67 233	98.70 132	97.41 279	98.15 358

Anonymous20240529		98.09 201	97.68 237	99.34 138	99.66 120	98.44 219	99.40 214	99.43 207	93.67 367	99.22 195	99.89 30	90.23 334	99.93 84	99.26 66	98.33 221	99.66 125

FMVSNet3		98.03 213	97.76 230	98.84 223	99.39 210	98.98 152	99.40 214	99.38 229	96.67 285	99.07 225	99.28 304	92.93 274	98.98 345	97.10 282	96.65 295	98.56 329

LFMVS		97.90 234	97.35 278	99.54 97	99.52 167	99.01 150	99.39 218	98.24 374	97.10 255	99.65 89	99.79 114	84.79 377	99.91 105	99.28 62	98.38 218	99.69 115

HQP_MVS		98.27 184	98.22 176	98.44 272	99.29 238	96.97 295	99.39 218	99.47 173	98.97 51	99.11 217	99.61 205	92.71 284	99.69 230	97.78 225	97.63 255	98.67 291

plane_prior2							99.39 218		98.97 51

CHOSEN 1792x2688		99.19 77	99.10 76	99.45 123	99.89 8	98.52 209	99.39 218	99.94 1	98.73 76	99.11 217	99.89 30	95.50 186	99.94 69	99.50 36	99.97 7	99.89 20

PAPM_NR		99.04 109	98.84 120	99.66 69	99.74 80	99.44 94	99.39 218	99.38 229	97.70 192	99.28 180	99.28 304	98.34 89	99.85 148	96.96 291	99.45 146	99.69 115

gg-mvs-nofinetune		96.17 326	95.32 337	98.73 236	98.79 330	98.14 233	99.38 223	94.09 404	91.07 384	98.07 332	91.04 400	89.62 341	99.35 287	96.75 301	99.09 176	98.68 284

VDDNet		97.55 282	97.02 301	99.16 170	99.49 181	98.12 235	99.38 223	99.30 273	95.35 343	99.68 74	99.90 26	82.62 386	99.93 84	99.31 58	98.13 238	99.42 193

pmmvs6		96.53 318	96.09 323	97.82 321	98.69 346	95.47 342	99.37 225	99.47 173	93.46 371	97.41 348	99.78 120	87.06 366	99.33 290	96.92 296	92.70 369	98.65 301

PM-MVS		92.96 353	92.23 357	95.14 362	95.61 391	89.98 388	99.37 225	98.21 376	94.80 356	95.04 378	97.69 381	65.06 396	97.90 381	94.30 350	89.98 382	97.54 381

WTY-MVS		99.06 107	98.88 114	99.61 84	99.62 137	99.16 125	99.37 225	99.56 69	98.04 155	99.53 122	99.62 201	96.84 138	99.94 69	98.85 112	98.49 216	99.72 103

IterMVS-LS		98.46 165	98.42 163	98.58 250	99.59 148	98.00 240	99.37 225	99.43 207	96.94 271	99.07 225	99.59 210	97.87 105	99.03 338	98.32 182	95.62 322	98.71 271
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
h-mvs33		97.70 268	97.28 289	98.97 192	99.70 101	97.27 271	99.36 229	99.45 193	98.94 54	99.66 83	99.64 190	94.93 203	99.99 4	99.48 41	84.36 390	99.65 129

DPE-MVS		99.46 31	99.32 40	99.91 2	99.78 56	99.88 8	99.36 229	99.51 115	98.73 76	99.88 20	99.84 63	98.72 61	99.96 30	98.16 193	99.87 55	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		96.44 320	96.12 321	97.40 336	98.65 349	95.65 335	99.36 229	99.51 115	97.13 249	96.04 370	98.99 338	88.40 355	98.17 374	96.71 303	90.27 380	98.40 345

sss		99.17 81	99.05 83	99.53 105	99.62 137	98.97 155	99.36 229	99.62 41	97.83 174	99.67 78	99.65 184	97.37 119	99.95 59	99.19 70	99.19 165	99.68 119

DeepC-MVS_fast	98.69 1	99.49 22	99.39 27	99.77 55	99.63 131	99.59 70	99.36 229	99.46 182	99.07 35	99.79 42	99.82 75	98.85 39	99.92 95	98.68 137	99.87 55	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 73	99.14 72	99.59 87	99.41 202	99.16 125	99.35 234	99.57 64	98.82 65	99.51 126	99.61 205	96.46 152	99.95 59	99.59 25	99.98 4	99.65 129

pmmvs-eth3d		95.34 338	94.73 341	97.15 340	95.53 393	95.94 331	99.35 234	99.10 305	95.13 345	93.55 383	97.54 382	88.15 359	97.91 380	94.58 347	89.69 383	97.61 378

MDTV_nov1_ep13_2view						95.18 350	99.35 234		96.84 276	99.58 111		95.19 199		97.82 222		99.46 186

VDD-MVS		97.73 262	97.35 278	98.88 211	99.47 189	97.12 279	99.34 237	98.85 342	98.19 129	99.67 78	99.85 53	82.98 384	99.92 95	99.49 40	98.32 225	99.60 146

COLMAP_ROB	97.56 6	98.86 128	98.75 129	99.17 169	99.88 11	98.53 205	99.34 237	99.59 57	97.55 207	98.70 284	99.89 30	95.83 175	99.90 116	98.10 195	99.90 40	99.08 229
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
EGC-MVSNET		82.80 365	77.86 371	97.62 329	97.91 369	96.12 328	99.33 239	99.28 279	8.40 408	25.05 409	99.27 307	84.11 380	99.33 290	89.20 384	98.22 229	97.42 382

ETVMVS		97.50 287	96.90 305	99.29 153	99.23 251	98.78 186	99.32 240	98.90 335	97.52 213	98.56 302	98.09 378	84.72 378	99.69 230	97.86 217	97.88 246	99.39 198

FMVSNet5		96.43 321	96.19 320	97.15 340	99.11 282	95.89 332	99.32 240	99.52 101	94.47 362	98.34 315	99.07 328	87.54 364	97.07 389	92.61 372	95.72 320	98.47 336

dp		97.75 259	97.80 220	97.59 331	99.10 285	93.71 370	99.32 240	98.88 338	96.48 303	99.08 224	99.55 224	92.67 287	99.82 175	96.52 310	98.58 208	99.24 215

tpmvs		97.98 222	98.02 198	97.84 318	99.04 299	94.73 356	99.31 243	99.20 294	96.10 334	98.76 274	99.42 265	94.94 202	99.81 180	96.97 290	98.45 217	98.97 244

tpmrst		98.33 178	98.48 160	97.90 314	99.16 274	94.78 355	99.31 243	99.11 304	97.27 237	99.45 135	99.59 210	95.33 192	99.84 155	98.48 165	98.61 205	99.09 228

testing99		97.36 297	96.94 304	98.63 244	99.18 264	96.70 307	99.30 245	98.93 326	97.71 189	98.23 321	98.26 371	84.92 376	99.84 155	98.04 205	97.85 248	99.35 204

MP-MVS-pluss		99.37 54	99.20 67	99.88 5	99.90 4	99.87 12	99.30 245	99.52 101	97.18 245	99.60 107	99.79 114	98.79 47	99.95 59	98.83 118	99.91 32	99.83 49
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
NCCC		99.34 57	99.19 68	99.79 49	99.61 141	99.65 57	99.30 245	99.48 155	98.86 60	99.21 198	99.63 196	98.72 61	99.90 116	98.25 185	99.63 134	99.80 70

JIA-IIPM		97.50 287	97.02 301	98.93 198	98.73 340	97.80 254	99.30 245	98.97 321	91.73 380	98.91 252	94.86 394	95.10 200	99.71 219	97.58 245	97.98 242	99.28 212

BH-RMVSNet		98.41 170	98.08 190	99.40 131	99.41 202	98.83 180	99.30 245	98.77 350	97.70 192	98.94 248	99.65 184	92.91 277	99.74 203	96.52 310	99.55 141	99.64 136

testing11		97.50 287	97.10 298	98.71 239	99.20 258	96.91 299	99.29 250	98.82 345	97.89 166	98.21 324	98.40 366	85.63 371	99.83 168	98.45 170	98.04 241	99.37 202

Syy-MVS		97.09 309	97.14 295	96.95 348	99.00 303	92.73 379	99.29 250	99.39 221	97.06 259	97.41 348	98.15 373	93.92 255	98.68 365	91.71 375	98.34 219	99.45 189

myMVS_eth3d		96.89 311	96.37 316	98.43 274	99.00 303	97.16 277	99.29 250	99.39 221	97.06 259	97.41 348	98.15 373	83.46 383	98.68 365	95.27 339	98.34 219	99.45 189

MCST-MVS		99.43 40	99.30 49	99.82 41	99.79 54	99.74 41	99.29 250	99.40 218	98.79 70	99.52 124	99.62 201	98.91 34	99.90 116	98.64 141	99.75 113	99.82 54

LF4IMVS		97.52 284	97.46 260	97.70 327	98.98 309	95.55 338	99.29 250	98.82 345	98.07 149	98.66 287	99.64 190	89.97 336	99.61 251	97.01 286	96.68 294	97.94 371

hse-mvs2		97.50 287	97.14 295	98.59 247	99.49 181	97.05 286	99.28 255	99.22 290	98.94 54	99.66 83	99.42 265	94.93 203	99.65 241	99.48 41	83.80 392	99.08 229

OPM-MVS		98.19 190	98.10 186	98.45 269	98.88 319	97.07 284	99.28 255	99.38 229	98.57 86	99.22 195	99.81 89	92.12 300	99.66 236	98.08 200	97.54 264	98.61 322
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
diffmvs		99.14 87	99.02 91	99.51 113	99.61 141	98.96 159	99.28 255	99.49 143	98.46 97	99.72 67	99.71 152	96.50 150	99.88 133	99.31 58	99.11 172	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		98.86 128	98.80 123	99.03 184	99.76 65	98.79 184	99.28 255	99.91 3	97.42 225	99.67 78	99.37 280	97.53 113	99.88 133	98.98 90	97.29 284	98.42 342

OMC-MVS		99.08 105	99.04 85	99.20 166	99.67 111	98.22 229	99.28 255	99.52 101	98.07 149	99.66 83	99.81 89	97.79 108	99.78 194	97.79 224	99.81 94	99.60 146

testing222		97.16 305	96.50 313	99.16 170	99.16 274	98.47 217	99.27 260	98.66 363	97.71 189	98.23 321	98.15 373	82.28 388	99.84 155	97.36 267	97.66 253	99.18 220

AUN-MVS		96.88 312	96.31 318	98.59 247	99.48 188	97.04 289	99.27 260	99.22 290	97.44 222	98.51 305	99.41 269	91.97 303	99.66 236	97.71 236	83.83 391	99.07 234

pmmvs5		97.52 284	97.30 286	98.16 296	98.57 357	96.73 306	99.27 260	98.90 335	96.14 328	98.37 313	99.53 233	91.54 317	99.14 321	97.51 254	95.87 315	98.63 310

1314		98.68 153	98.54 157	99.11 176	98.89 318	98.65 194	99.27 260	99.49 143	96.89 273	97.99 334	99.56 221	97.72 111	99.83 168	97.74 232	99.27 161	98.84 252

MVS		97.28 300	96.55 312	99.48 117	98.78 333	98.95 162	99.27 260	99.39 221	83.53 394	98.08 329	99.54 229	96.97 135	99.87 138	94.23 353	99.16 166	99.63 140

BH-untuned		98.42 168	98.36 166	98.59 247	99.49 181	96.70 307	99.27 260	99.13 303	97.24 241	98.80 269	99.38 277	95.75 178	99.74 203	97.07 285	99.16 166	99.33 208

MDTV_nov1_ep13			98.32 170		99.11 282	94.44 361	99.27 260	98.74 354	97.51 214	99.40 153	99.62 201	94.78 213	99.76 200	97.59 244	98.81 199

DP-MVS Recon		99.12 95	98.95 105	99.65 73	99.74 80	99.70 46	99.27 260	99.57 64	96.40 310	99.42 144	99.68 172	98.75 55	99.80 186	97.98 208	99.72 119	99.44 191

PatchmatchNet		98.31 179	98.36 166	98.19 294	99.16 274	95.32 346	99.27 260	98.92 329	97.37 229	99.37 161	99.58 214	94.90 206	99.70 225	97.43 263	99.21 163	99.54 161
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thres200		97.61 279	97.28 289	98.62 245	99.64 128	98.03 238	99.26 269	98.74 354	97.68 194	99.09 223	98.32 369	91.66 314	99.81 180	92.88 368	98.22 229	98.03 364

CNVR-MVS		99.42 42	99.30 49	99.78 52	99.62 137	99.71 44	99.26 269	99.52 101	98.82 65	99.39 157	99.71 152	98.96 24	99.85 148	98.59 151	99.80 98	99.77 82

1112_ss		98.98 116	98.77 127	99.59 87	99.68 110	99.02 148	99.25 271	99.48 155	97.23 242	99.13 213	99.58 214	96.93 137	99.90 116	98.87 105	98.78 200	99.84 40

TAPA-MVS	97.07 15	97.74 261	97.34 281	98.94 196	99.70 101	97.53 264	99.25 271	99.51 115	91.90 379	99.30 176	99.63 196	98.78 48	99.64 244	88.09 389	99.87 55	99.65 129
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PLC	97.94 4	99.02 112	98.85 119	99.53 105	99.66 120	99.01 150	99.24 273	99.52 101	96.85 275	99.27 184	99.48 251	98.25 93	99.91 105	97.76 229	99.62 135	99.65 129
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test_post1							99.23 274				65.14 406	94.18 246	99.71 219	97.58 245

ADS-MVSNet2		98.02 215	98.07 193	97.87 315	99.33 226	95.19 349	99.23 274	99.08 308	96.24 318	99.10 220	99.67 178	94.11 247	98.93 355	96.81 299	99.05 179	99.48 178

ADS-MVSNet		98.20 189	98.08 190	98.56 254	99.33 226	96.48 317	99.23 274	99.15 300	96.24 318	99.10 220	99.67 178	94.11 247	99.71 219	96.81 299	99.05 179	99.48 178

EPNet_dtu		98.03 213	97.96 204	98.23 292	98.27 365	95.54 340	99.23 274	98.75 351	99.02 38	97.82 341	99.71 152	96.11 162	99.48 260	93.04 366	99.65 131	99.69 115
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		98.17 193	97.93 209	98.87 215	99.18 264	98.49 213	99.22 278	99.33 255	96.96 267	99.56 115	99.38 277	94.33 239	99.00 343	94.83 346	98.58 208	99.14 221

RPMNet		96.72 315	95.90 327	99.19 167	99.18 264	98.49 213	99.22 278	99.52 101	88.72 390	99.56 115	97.38 384	94.08 249	99.95 59	86.87 394	98.58 208	99.14 221

plane_prior						96.97 295	99.21 280		98.45 98						97.60 258

testing91		97.44 294	97.02 301	98.71 239	99.18 264	96.89 301	99.19 281	99.04 314	97.78 181	98.31 316	98.29 370	85.41 373	99.85 148	98.01 206	97.95 243	99.39 198

WR-MVS		98.06 205	97.73 233	99.06 180	98.86 325	99.25 116	99.19 281	99.35 244	97.30 235	98.66 287	99.43 263	93.94 253	99.21 315	98.58 152	94.28 348	98.71 271

new-patchmatchnet		94.48 346	94.08 347	95.67 361	95.08 396	92.41 380	99.18 283	99.28 279	94.55 361	93.49 384	97.37 385	87.86 362	97.01 390	91.57 376	88.36 384	97.61 378

AdaColmap		99.01 115	98.80 123	99.66 69	99.56 156	99.54 79	99.18 283	99.70 15	98.18 132	99.35 168	99.63 196	96.32 157	99.90 116	97.48 257	99.77 108	99.55 159

EG-PatchMatch MVS		95.97 329	95.69 331	96.81 352	97.78 372	92.79 378	99.16 285	98.93 326	96.16 325	94.08 381	99.22 313	82.72 385	99.47 261	95.67 330	97.50 268	98.17 357

PatchT		97.03 310	96.44 315	98.79 232	98.99 306	98.34 224	99.16 285	99.07 311	92.13 378	99.52 124	97.31 387	94.54 232	98.98 345	88.54 387	98.73 202	99.03 237

CNLPA		99.14 87	98.99 97	99.59 87	99.58 150	99.41 98	99.16 285	99.44 201	98.45 98	99.19 204	99.49 246	98.08 101	99.89 127	97.73 233	99.75 113	99.48 178

MDA-MVSNet-bldmvs		94.96 341	93.98 348	97.92 312	98.24 366	97.27 271	99.15 288	99.33 255	93.80 366	80.09 401	99.03 333	88.31 356	97.86 382	93.49 361	94.36 347	98.62 313

CDPH-MVS		99.13 89	98.91 109	99.80 46	99.75 73	99.71 44	99.15 288	99.41 212	96.60 294	99.60 107	99.55 224	98.83 42	99.90 116	97.48 257	99.83 87	99.78 80

save fliter					99.76 65	99.59 70	99.14 290	99.40 218	99.00 43

WB-MVSnew		97.65 276	97.65 240	97.63 328	98.78 333	97.62 262	99.13 291	98.33 371	97.36 230	99.07 225	98.94 344	95.64 183	99.15 320	92.95 367	98.68 204	96.12 392

testf1		90.42 359	90.68 361	89.65 379	97.78 372	73.97 407	99.13 291	98.81 347	89.62 386	91.80 390	98.93 345	62.23 399	98.80 361	86.61 395	91.17 374	96.19 390

APD_test2		90.42 359	90.68 361	89.65 379	97.78 372	73.97 407	99.13 291	98.81 347	89.62 386	91.80 390	98.93 345	62.23 399	98.80 361	86.61 395	91.17 374	96.19 390

xiu_mvs_v1_base_debu		99.29 63	99.27 58	99.34 138	99.63 131	98.97 155	99.12 294	99.51 115	98.86 60	99.84 29	99.47 254	98.18 96	99.99 4	99.50 36	99.31 158	99.08 229

xiu_mvs_v1_base		99.29 63	99.27 58	99.34 138	99.63 131	98.97 155	99.12 294	99.51 115	98.86 60	99.84 29	99.47 254	98.18 96	99.99 4	99.50 36	99.31 158	99.08 229

xiu_mvs_v1_base_debi		99.29 63	99.27 58	99.34 138	99.63 131	98.97 155	99.12 294	99.51 115	98.86 60	99.84 29	99.47 254	98.18 96	99.99 4	99.50 36	99.31 158	99.08 229

XVG-OURS-SEG-HR		98.69 152	98.62 147	98.89 209	99.71 96	97.74 255	99.12 294	99.54 85	98.44 101	99.42 144	99.71 152	94.20 243	99.92 95	98.54 162	98.90 191	99.00 240

jason		99.13 89	99.03 87	99.45 123	99.46 190	98.87 172	99.12 294	99.26 283	98.03 157	99.79 42	99.65 184	97.02 132	99.85 148	99.02 85	99.90 40	99.65 129
jason: jason.
N_pmnet		94.95 342	95.83 329	92.31 370	98.47 361	79.33 402	99.12 294	92.81 408	93.87 365	97.68 344	99.13 323	93.87 256	99.01 342	91.38 377	96.19 306	98.59 326

MDA-MVSNet_test_wron		95.45 335	94.60 342	98.01 306	98.16 367	97.21 276	99.11 300	99.24 287	93.49 370	80.73 400	98.98 340	93.02 272	98.18 373	94.22 354	94.45 345	98.64 303

Patchmtry		97.75 259	97.40 273	98.81 229	99.10 285	98.87 172	99.11 300	99.33 255	94.83 355	98.81 267	99.38 277	94.33 239	99.02 340	96.10 317	95.57 323	98.53 330

YYNet1		95.36 337	94.51 344	97.92 312	97.89 370	97.10 280	99.10 302	99.23 288	93.26 373	80.77 399	99.04 332	92.81 278	98.02 377	94.30 350	94.18 350	98.64 303

CANet_DTU		98.97 118	98.87 115	99.25 160	99.33 226	98.42 222	99.08 303	99.30 273	99.16 19	99.43 141	99.75 136	95.27 194	99.97 21	98.56 158	99.95 16	99.36 203

SCA		98.19 190	98.16 178	98.27 291	99.30 234	95.55 338	99.07 304	98.97 321	97.57 204	99.43 141	99.57 218	92.72 282	99.74 203	97.58 245	99.20 164	99.52 167

TSAR-MVS + GP.		99.36 55	99.36 32	99.36 137	99.67 111	98.61 199	99.07 304	99.33 255	99.00 43	99.82 35	99.81 89	99.06 16	99.84 155	99.09 79	99.42 148	99.65 129

MG-MVS		99.13 89	99.02 91	99.45 123	99.57 152	98.63 196	99.07 304	99.34 248	98.99 45	99.61 104	99.82 75	97.98 104	99.87 138	97.00 287	99.80 98	99.85 36

PatchMatch-RL		98.84 138	98.62 147	99.52 111	99.71 96	99.28 111	99.06 307	99.77 9	97.74 187	99.50 127	99.53 233	95.41 188	99.84 155	97.17 281	99.64 132	99.44 191

OpenMVS_ROB	92.34 20	94.38 347	93.70 353	96.41 357	97.38 378	93.17 376	99.06 307	98.75 351	86.58 391	94.84 379	98.26 371	81.53 389	99.32 293	89.01 385	97.87 247	96.76 385

TEST9					99.67 111	99.65 57	99.05 309	99.41 212	96.22 320	98.95 246	99.49 246	98.77 51	99.91 105

train_agg		99.02 112	98.77 127	99.77 55	99.67 111	99.65 57	99.05 309	99.41 212	96.28 314	98.95 246	99.49 246	98.76 52	99.91 105	97.63 241	99.72 119	99.75 88

lupinMVS		99.13 89	99.01 95	99.46 122	99.51 170	98.94 165	99.05 309	99.16 299	97.86 168	99.80 40	99.56 221	97.39 116	99.86 142	98.94 94	99.85 70	99.58 154

DELS-MVS		99.48 26	99.42 22	99.65 73	99.72 91	99.40 99	99.05 309	99.66 28	99.14 21	99.57 114	99.80 102	98.46 81	99.94 69	99.57 27	99.84 78	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		96.38 322	96.03 324	97.41 335	98.13 368	95.16 351	99.05 309	99.20 294	93.94 364	97.39 351	98.79 354	91.61 316	99.04 336	90.43 380	95.77 317	98.05 363

Patchmatch-test		97.93 228	97.65 240	98.77 234	99.18 264	97.07 284	99.03 314	99.14 302	96.16 325	98.74 275	99.57 218	94.56 229	99.72 213	93.36 362	99.11 172	99.52 167

test_8					99.67 111	99.61 67	99.03 314	99.41 212	96.28 314	98.93 250	99.48 251	98.76 52	99.91 105

Test_1112_low_res		98.89 123	98.66 139	99.57 92	99.69 106	98.95 162	99.03 314	99.47 173	96.98 265	99.15 211	99.23 312	96.77 141	99.89 127	98.83 118	98.78 200	99.86 33

IterMVS-SCA-FT		97.82 248	97.75 231	98.06 302	99.57 152	96.36 321	99.02 317	99.49 143	97.18 245	98.71 278	99.72 151	92.72 282	99.14 321	97.44 262	95.86 316	98.67 291

xiu_mvs_v2_base		99.26 69	99.25 62	99.29 153	99.53 163	98.91 169	99.02 317	99.45 193	98.80 69	99.71 68	99.26 309	98.94 29	99.98 13	99.34 55	99.23 162	98.98 243

MIMVSNet		97.73 262	97.45 261	98.57 251	99.45 195	97.50 265	99.02 317	98.98 320	96.11 330	99.41 148	99.14 322	90.28 330	98.74 363	95.74 326	98.93 187	99.47 184

IterMVS		97.83 245	97.77 226	98.02 305	99.58 150	96.27 324	99.02 317	99.48 155	97.22 243	98.71 278	99.70 156	92.75 279	99.13 324	97.46 260	96.00 310	98.67 291
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		99.11 99	98.92 107	99.65 73	99.90 4	99.37 100	99.02 317	99.91 3	97.67 196	99.59 110	99.75 136	95.90 173	99.73 209	99.53 32	99.02 183	99.86 33

UWE-MVS		97.58 281	97.29 288	98.48 262	99.09 288	96.25 325	99.01 322	96.61 396	97.86 168	99.19 204	99.01 336	88.72 348	99.90 116	97.38 266	98.69 203	99.28 212

新几何2							99.01 322

BH-w/o		98.00 220	97.89 215	98.32 284	99.35 220	96.20 327	99.01 322	98.90 335	96.42 308	98.38 312	99.00 337	95.26 196	99.72 213	96.06 318	98.61 205	99.03 237

test_prior4						99.56 75	98.99 325

无先验							98.99 325	99.51 115	96.89 273				99.93 84	97.53 253		99.72 103

pmmvs4		98.13 197	97.90 211	98.81 229	98.61 354	98.87 172	98.99 325	99.21 293	96.44 306	99.06 230	99.58 214	95.90 173	99.11 329	97.18 280	96.11 308	98.46 339

HQP-NCC					99.19 261		98.98 328		98.24 120	98.66 287

ACMP_Plane					99.19 261		98.98 328		98.24 120	98.66 287

HQP-MVS		98.02 215	97.90 211	98.37 280	99.19 261	96.83 302	98.98 328	99.39 221	98.24 120	98.66 287	99.40 272	92.47 293	99.64 244	97.19 278	97.58 260	98.64 303

PS-MVSNAJ		99.32 59	99.32 40	99.30 150	99.57 152	98.94 165	98.97 331	99.46 182	98.92 57	99.71 68	99.24 311	99.01 18	99.98 13	99.35 51	99.66 129	98.97 244

iter_conf05_11		98.35 176	97.99 200	99.41 129	99.37 214	99.13 134	98.96 332	98.23 375	98.50 94	99.63 96	99.46 258	88.83 347	99.87 138	99.00 87	99.95 16	99.23 216

MVP-Stereo		97.81 250	97.75 231	97.99 309	97.53 376	96.60 314	98.96 332	98.85 342	97.22 243	97.23 354	99.36 283	95.28 193	99.46 262	95.51 332	99.78 105	97.92 373
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test_prior2							98.96 332		98.34 110	99.01 236	99.52 236	98.68 64		97.96 209	99.74 116

旧先验2							98.96 332		96.70 283	99.47 132			99.94 69	98.19 189

原ACMM2							98.95 336

MVS_111021_HR		99.41 47	99.32 40	99.66 69	99.72 91	99.47 91	98.95 336	99.85 6	98.82 65	99.54 120	99.73 147	98.51 78	99.74 203	98.91 99	99.88 52	99.77 82

mvsany_test1		99.50 20	99.46 20	99.62 83	99.61 141	99.09 137	98.94 338	99.48 155	99.10 27	99.96 14	99.91 20	98.85 39	99.96 30	99.72 18	99.58 138	99.82 54

MVS_111021_LR		99.41 47	99.33 38	99.65 73	99.77 62	99.51 86	98.94 338	99.85 6	98.82 65	99.65 89	99.74 141	98.51 78	99.80 186	98.83 118	99.89 49	99.64 136

pmmvs3		94.09 349	93.25 355	96.60 355	94.76 398	94.49 360	98.92 340	98.18 378	89.66 385	96.48 365	98.06 379	86.28 367	97.33 387	89.68 383	87.20 387	97.97 370

XVG-OURS		98.73 149	98.68 135	98.88 211	99.70 101	97.73 256	98.92 340	99.55 77	98.52 92	99.45 135	99.84 63	95.27 194	99.91 105	98.08 200	98.84 195	99.00 240

test222					99.75 73	99.49 87	98.91 342	99.49 143	96.42 308	99.34 171	99.65 184	98.28 92			99.69 124	99.72 103

PMMVS2		86.87 362	85.37 366	91.35 374	90.21 403	83.80 393	98.89 343	97.45 389	83.13 395	91.67 392	95.03 392	48.49 405	94.70 398	85.86 397	77.62 397	95.54 393

miper_lstm_enhance		98.00 220	97.91 210	98.28 290	99.34 224	97.43 267	98.88 344	99.36 238	96.48 303	98.80 269	99.55 224	95.98 166	98.91 356	97.27 271	95.50 326	98.51 332

MVS-HIRNet		95.75 333	95.16 338	97.51 333	99.30 234	93.69 371	98.88 344	95.78 398	85.09 393	98.78 272	92.65 396	91.29 321	99.37 280	94.85 345	99.85 70	99.46 186

TR-MVS		97.76 255	97.41 272	98.82 226	99.06 295	97.87 250	98.87 346	98.56 366	96.63 291	98.68 286	99.22 313	92.49 292	99.65 241	95.40 336	97.79 249	98.95 248

testdata1							98.85 347		98.32 113

ET-MVSNet_ETH3D		96.49 319	95.64 333	99.05 182	99.53 163	98.82 181	98.84 348	97.51 388	97.63 199	84.77 394	99.21 316	92.09 301	98.91 356	98.98 90	92.21 371	99.41 195

our_test_3		97.65 276	97.68 237	97.55 332	98.62 352	94.97 353	98.84 348	99.30 273	96.83 278	98.19 325	99.34 290	97.01 133	99.02 340	95.00 344	96.01 309	98.64 303

MS-PatchMatch		97.24 304	97.32 284	96.99 345	98.45 362	93.51 374	98.82 350	99.32 265	97.41 226	98.13 328	99.30 300	88.99 344	99.56 255	95.68 329	99.80 98	97.90 374

c3_l		98.12 199	98.04 195	98.38 279	99.30 234	97.69 261	98.81 351	99.33 255	96.67 285	98.83 265	99.34 290	97.11 128	98.99 344	97.58 245	95.34 328	98.48 334

ppachtmachnet_test		97.49 292	97.45 261	97.61 330	98.62 352	95.24 347	98.80 352	99.46 182	96.11 330	98.22 323	99.62 201	96.45 153	98.97 352	93.77 357	95.97 314	98.61 322

PAPR		98.63 158	98.34 168	99.51 113	99.40 207	99.03 147	98.80 352	99.36 238	96.33 311	99.00 240	99.12 326	98.46 81	99.84 155	95.23 340	99.37 157	99.66 125

test0.0.03 1		97.71 267	97.42 271	98.56 254	98.41 364	97.82 253	98.78 354	98.63 364	97.34 231	98.05 333	98.98 340	94.45 236	98.98 345	95.04 343	97.15 290	98.89 249

PVSNet_Blended		99.08 105	98.97 101	99.42 128	99.76 65	98.79 184	98.78 354	99.91 3	96.74 280	99.67 78	99.49 246	97.53 113	99.88 133	98.98 90	99.85 70	99.60 146

PMMVS		98.80 142	98.62 147	99.34 138	99.27 243	98.70 190	98.76 356	99.31 269	97.34 231	99.21 198	99.07 328	97.20 125	99.82 175	98.56 158	98.87 192	99.52 167

test123		39.01 374	42.50 376	28.53 389	39.17 412	20.91 414	98.75 357	19.17 414	19.83 407	38.57 406	66.67 404	33.16 409	15.42 408	37.50 408	29.66 406	49.26 403

MSDG		98.98 116	98.80 123	99.53 105	99.76 65	99.19 120	98.75 357	99.55 77	97.25 239	99.47 132	99.77 128	97.82 107	99.87 138	96.93 294	99.90 40	99.54 161

CLD-MVS		98.16 194	98.10 186	98.33 282	99.29 238	96.82 304	98.75 357	99.44 201	97.83 174	99.13 213	99.55 224	92.92 275	99.67 233	98.32 182	97.69 252	98.48 334
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		98.18 192	98.10 186	98.41 275	99.23 251	97.72 257	98.72 360	99.31 269	96.60 294	98.88 257	99.29 302	97.29 123	99.13 324	97.60 243	95.99 311	98.38 347

cl____		98.01 218	97.84 219	98.55 256	99.25 249	97.97 242	98.71 361	99.34 248	96.47 305	98.59 301	99.54 229	95.65 182	99.21 315	97.21 274	95.77 317	98.46 339

DIV-MVS_self_test		98.01 218	97.85 218	98.48 262	99.24 250	97.95 246	98.71 361	99.35 244	96.50 299	98.60 300	99.54 229	95.72 180	99.03 338	97.21 274	95.77 317	98.46 339

test-LLR		98.06 205	97.90 211	98.55 256	98.79 330	97.10 280	98.67 363	97.75 383	97.34 231	98.61 298	98.85 350	94.45 236	99.45 263	97.25 272	99.38 150	99.10 224

TESTMET0.1,1		97.55 282	97.27 292	98.40 277	98.93 314	96.53 315	98.67 363	97.61 386	96.96 267	98.64 294	99.28 304	88.63 353	99.45 263	97.30 270	99.38 150	99.21 219

test-mter		97.49 292	97.13 297	98.55 256	98.79 330	97.10 280	98.67 363	97.75 383	96.65 287	98.61 298	98.85 350	88.23 357	99.45 263	97.25 272	99.38 150	99.10 224

IB-MVS	95.67 18	96.22 323	95.44 336	98.57 251	99.21 256	96.70 307	98.65 366	97.74 385	96.71 282	97.27 353	98.54 362	86.03 368	99.92 95	98.47 168	86.30 388	99.10 224
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		98.95 119	98.71 132	99.66 69	99.63 131	99.55 77	98.64 367	99.10 305	97.93 163	99.42 144	99.55 224	98.67 66	99.80 186	95.80 325	99.68 127	99.61 144

thisisatest0515		98.14 196	97.79 221	99.19 167	99.50 179	98.50 212	98.61 368	96.82 392	96.95 269	99.54 120	99.43 263	91.66 314	99.86 142	98.08 200	99.51 143	99.22 218

DeepPCF-MVS	98.18 3	98.81 139	99.37 30	97.12 343	99.60 146	91.75 383	98.61 368	99.44 201	99.35 12	99.83 34	99.85 53	98.70 63	99.81 180	99.02 85	99.91 32	99.81 61

cl22		97.85 240	97.64 243	98.48 262	99.09 288	97.87 250	98.60 370	99.33 255	97.11 254	98.87 260	99.22 313	92.38 298	99.17 319	98.21 187	95.99 311	98.42 342

GA-MVS		97.85 240	97.47 258	99.00 188	99.38 211	97.99 241	98.57 371	99.15 300	97.04 262	98.90 254	99.30 300	89.83 337	99.38 276	96.70 304	98.33 221	99.62 142

TinyColmap		97.12 307	96.89 306	97.83 319	99.07 292	95.52 341	98.57 371	98.74 354	97.58 203	97.81 342	99.79 114	88.16 358	99.56 255	95.10 341	97.21 287	98.39 346

eth_miper_zixun_eth		98.05 210	97.96 204	98.33 282	99.26 245	97.38 268	98.56 373	99.31 269	96.65 287	98.88 257	99.52 236	96.58 147	99.12 328	97.39 265	95.53 325	98.47 336

CMPMVS	69.68 23	94.13 348	94.90 340	91.84 371	97.24 382	80.01 401	98.52 374	99.48 155	89.01 388	91.99 389	99.67 178	85.67 370	99.13 324	95.44 334	97.03 291	96.39 389
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
USDC		97.34 298	97.20 293	97.75 324	99.07 292	95.20 348	98.51 375	99.04 314	97.99 159	98.31 316	99.86 48	89.02 343	99.55 257	95.67 330	97.36 283	98.49 333

ambc				93.06 369	92.68 400	82.36 394	98.47 376	98.73 359		95.09 377	97.41 383	55.55 401	99.10 331	96.42 313	91.32 373	97.71 375

miper_enhance_ethall		98.16 194	98.08 190	98.41 275	98.96 312	97.72 257	98.45 377	99.32 265	96.95 269	98.97 244	99.17 318	97.06 131	99.22 310	97.86 217	95.99 311	98.29 351

CHOSEN 280x420		99.12 95	99.13 73	99.08 177	99.66 120	97.89 249	98.43 378	99.71 13	98.88 59	99.62 101	99.76 133	96.63 145	99.70 225	99.46 44	99.99 1	99.66 125

testmvs		39.17 373	43.78 375	25.37 390	36.04 413	16.84 415	98.36 379	26.56 412	20.06 406	38.51 407	67.32 403	29.64 410	15.30 409	37.59 407	39.90 405	43.98 404

FPMVS		84.93 364	85.65 365	82.75 385	86.77 406	63.39 411	98.35 380	98.92 329	74.11 397	83.39 396	98.98 340	50.85 404	92.40 400	84.54 398	94.97 336	92.46 395

KD-MVS_2432*1600		94.62 343	93.72 351	97.31 337	97.19 384	95.82 333	98.34 381	99.20 294	95.00 351	97.57 345	98.35 367	87.95 360	98.10 375	92.87 369	77.00 398	98.01 365

miper_refine_blended		94.62 343	93.72 351	97.31 337	97.19 384	95.82 333	98.34 381	99.20 294	95.00 351	97.57 345	98.35 367	87.95 360	98.10 375	92.87 369	77.00 398	98.01 365

CL-MVSNet_self_test		94.49 345	93.97 349	96.08 359	96.16 388	93.67 372	98.33 383	99.38 229	95.13 345	97.33 352	98.15 373	92.69 286	96.57 392	88.67 386	79.87 396	97.99 368

PVSNet	96.02 17	98.85 135	98.84 120	98.89 209	99.73 87	97.28 270	98.32 384	99.60 54	97.86 168	99.50 127	99.57 218	96.75 142	99.86 142	98.56 158	99.70 123	99.54 161

PAPM		97.59 280	97.09 299	99.07 179	99.06 295	98.26 227	98.30 385	99.10 305	94.88 353	98.08 329	99.34 290	96.27 159	99.64 244	89.87 382	98.92 189	99.31 210

Patchmatch-RL test		95.84 331	95.81 330	95.95 360	95.61 391	90.57 386	98.24 386	98.39 370	95.10 349	95.20 375	98.67 358	94.78 213	97.77 383	96.28 316	90.02 381	99.51 173

UnsupCasMVSNet_bld		93.53 351	92.51 356	96.58 356	97.38 378	93.82 367	98.24 386	99.48 155	91.10 383	93.10 385	96.66 389	74.89 393	98.37 370	94.03 356	87.71 386	97.56 380

LCM-MVSNet		86.80 363	85.22 367	91.53 373	87.81 405	80.96 399	98.23 388	98.99 319	71.05 398	90.13 393	96.51 390	48.45 406	96.88 391	90.51 379	85.30 389	96.76 385

cascas		97.69 269	97.43 270	98.48 262	98.60 355	97.30 269	98.18 389	99.39 221	92.96 375	98.41 310	98.78 355	93.77 260	99.27 301	98.16 193	98.61 205	98.86 250

Effi-MVS+		98.81 139	98.59 153	99.48 117	99.46 190	99.12 135	98.08 390	99.50 135	97.50 215	99.38 159	99.41 269	96.37 156	99.81 180	99.11 77	98.54 213	99.51 173

PCF-MVS	97.08 14	97.66 275	97.06 300	99.47 120	99.61 141	99.09 137	98.04 391	99.25 285	91.24 382	98.51 305	99.70 156	94.55 231	99.91 105	92.76 371	99.85 70	99.42 193
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet_0	94.43 19	96.09 328	95.47 334	97.94 311	99.31 233	94.34 364	97.81 392	99.70 15	97.12 251	97.46 347	98.75 356	89.71 338	99.79 189	97.69 239	81.69 394	99.68 119

E-PMN		80.61 367	79.88 369	82.81 384	90.75 402	76.38 405	97.69 393	95.76 399	66.44 402	83.52 395	92.25 397	62.54 398	87.16 404	68.53 404	61.40 401	84.89 402

ANet_high		77.30 369	74.86 373	84.62 383	75.88 409	77.61 403	97.63 394	93.15 407	88.81 389	64.27 404	89.29 401	36.51 408	83.93 406	75.89 401	52.31 403	92.33 397

EMVS		80.02 368	79.22 370	82.43 386	91.19 401	76.40 404	97.55 395	92.49 409	66.36 403	83.01 397	91.27 399	64.63 397	85.79 405	65.82 405	60.65 402	85.08 401

MVE	76.82 21	76.91 370	74.31 374	84.70 382	85.38 408	76.05 406	96.88 396	93.17 406	67.39 401	71.28 403	89.01 402	21.66 413	87.69 403	71.74 403	72.29 400	90.35 399
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		91.10 357	91.36 359	90.31 376	95.85 389	73.72 409	94.89 397	99.25 285	68.39 400	95.82 371	99.02 335	80.50 390	98.95 354	93.64 359	94.89 340	98.25 354

Gipuma		90.99 358	90.15 363	93.51 366	98.73 340	90.12 387	93.98 398	99.45 193	79.32 396	92.28 388	94.91 393	69.61 394	97.98 379	87.42 391	95.67 321	92.45 396
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	70.75 22	75.98 371	74.97 372	79.01 387	70.98 410	55.18 412	93.37 399	98.21 376	65.08 404	61.78 405	93.83 395	21.74 412	92.53 399	78.59 399	91.12 376	89.34 400
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		82.80 365	81.52 368	86.66 381	66.61 411	68.44 410	92.79 400	97.92 380	68.96 399	80.04 402	99.85 53	85.77 369	96.15 395	97.86 217	43.89 404	95.39 394

wuyk23d		40.18 372	41.29 377	36.84 388	86.18 407	49.12 413	79.73 401	22.81 413	27.64 405	25.46 408	28.45 408	21.98 411	48.89 407	55.80 406	23.56 407	12.51 405

test_blank		0.13 378	0.17 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	1.57 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet_test		0.02 379	0.03 382	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.27 410	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

DCPMVS		0.02 379	0.03 382	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.27 410	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

cdsmvs_eth3d_5k		24.64 375	32.85 378	0.00 391	0.00 414	0.00 416	0.00 402	99.51 115	0.00 409	0.00 410	99.56 221	96.58 147	0.00 410	0.00 409	0.00 408	0.00 406

pcd_1.5k_mvsjas		8.27 377	11.03 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.27 410	99.01 18	0.00 410	0.00 409	0.00 408	0.00 406

sosnet-low-res		0.02 379	0.03 382	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.27 410	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

sosnet		0.02 379	0.03 382	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.27 410	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uncertanet		0.02 379	0.03 382	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.27 410	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

Regformer		0.02 379	0.03 382	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.27 410	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

ab-mvs-re		8.30 376	11.06 379	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	99.58 214	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet		0.02 379	0.03 382	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.27 410	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

WAC-MVS						97.16 277								95.47 333

MSC_two_6792asdad				99.87 11	99.51 170	99.76 37		99.33 255					99.96 30	98.87 105	99.84 78	99.89 20

PC_three_1452									98.18 132	99.84 29	99.70 156	99.31 3	98.52 368	98.30 184	99.80 98	99.81 61

No_MVS				99.87 11	99.51 170	99.76 37		99.33 255					99.96 30	98.87 105	99.84 78	99.89 20

test_one_0601					99.81 46	99.88 8		99.49 143	98.97 51	99.65 89	99.81 89	99.09 14

eth-test2					0.00 414

eth-test					0.00 414

ZD-MVS					99.71 96	99.79 30		99.61 48	96.84 276	99.56 115	99.54 229	98.58 72	99.96 30	96.93 294	99.75 113

IU-MVS					99.84 32	99.88 8		99.32 265	98.30 114	99.84 29				98.86 110	99.85 70	99.89 20

test_241102_TWO								99.48 155	99.08 33	99.88 20	99.81 89	98.94 29	99.96 30	98.91 99	99.84 78	99.88 26

test_241102_ONE					99.84 32	99.90 2		99.48 155	99.07 35	99.91 16	99.74 141	99.20 7	99.76 200

test_0728_THIRD									98.99 45	99.81 37	99.80 102	99.09 14	99.96 30	98.85 112	99.90 40	99.88 26

GSMVS																99.52 167

test_part2					99.81 46	99.83 16				99.77 51

sam_mvs1												94.86 208				99.52 167

sam_mvs												94.72 220

MTGPA								99.47 173

test_post											65.99 405	94.65 226	99.73 209

patchmatchnet-post											98.70 357	94.79 212	99.74 203

gm-plane-assit					98.54 359	92.96 377			94.65 359		99.15 321		99.64 244	97.56 250

test9_res														97.49 256	99.72 119	99.75 88

agg_prior2														97.21 274	99.73 118	99.75 88

agg_prior					99.67 111	99.62 65		99.40 218		98.87 260			99.91 105

TestCases				99.31 145	99.86 20	98.48 215		99.61 48	97.85 171	99.36 165	99.85 53	95.95 168	99.85 148	96.66 307	99.83 87	99.59 150

test_prior				99.68 68	99.67 111	99.48 89		99.56 69					99.83 168			99.74 92

新几何1				99.75 58	99.75 73	99.59 70		99.54 85	96.76 279	99.29 179	99.64 190	98.43 83	99.94 69	96.92 296	99.66 129	99.72 103

旧先验1					99.74 80	99.59 70		99.54 85			99.69 166	98.47 80			99.68 127	99.73 97

原ACMM1				99.65 73	99.73 87	99.33 103		99.47 173	97.46 217	99.12 215	99.66 183	98.67 66	99.91 105	97.70 238	99.69 124	99.71 112

testdata2													99.95 59	96.67 306

segment_acmp												98.96 24

testdata				99.54 97	99.75 73	98.95 162		99.51 115	97.07 257	99.43 141	99.70 156	98.87 37	99.94 69	97.76 229	99.64 132	99.72 103

test12				99.75 58	99.64 128	99.61 67		99.29 277		99.21 198		98.38 87	99.89 127		99.74 116	99.74 92

plane_prior7					99.29 238	97.03 290

plane_prior6					99.27 243	96.98 294						92.71 284

plane_prior5								99.47 173					99.69 230	97.78 225	97.63 255	98.67 291

plane_prior4											99.61 205

plane_prior3						97.00 292			98.69 79	99.11 217

plane_prior1					99.26 245

n2								0.00 415

nn								0.00 415

door-mid								98.05 379

lessismore_v0				97.79 323	98.69 346	95.44 344		94.75 402		95.71 372	99.87 44	88.69 350	99.32 293	95.89 322	94.93 338	98.62 313

LGP-MVS_train				98.49 260	99.33 226	97.05 286		99.55 77	97.46 217	99.24 190	99.83 67	92.58 289	99.72 213	98.09 196	97.51 266	98.68 284

test11								99.35 244

door								97.92 380

HQP5-MVS						96.83 302

BP-MVS														97.19 278

HQP4-MVS										98.66 287			99.64 244			98.64 303

HQP3-MVS								99.39 221							97.58 260

HQP2-MVS												92.47 293

NP-MVS					99.23 251	96.92 298					99.40 272

ACMMP++_ref															97.19 288

ACMMP++															97.43 278

Test By Simon												98.75 55

ITE_SJBPF				98.08 301	99.29 238	96.37 320		98.92 329	98.34 110	98.83 265	99.75 136	91.09 323	99.62 250	95.82 323	97.40 280	98.25 354

DeepMVS_CX				93.34 367	99.29 238	82.27 395		99.22 290	85.15 392	96.33 366	99.05 331	90.97 325	99.73 209	93.57 360	97.77 250	98.01 365

High-resolution multi-view benchmark