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 26	99.48 19	99.54 114	99.76 72	99.42 109	99.90 1	99.55 89	98.56 107	99.78 67	99.70 178	98.65 71	99.79 213	99.65 37	99.78 122	99.41 224

mmtdpeth		96.95 341	96.71 340	97.67 361	99.33 251	94.90 387	99.89 2	99.28 305	98.15 156	99.72 88	98.57 396	86.56 399	99.90 137	99.82 25	89.02 421	98.20 391

SPE-MVS-test		99.49 28	99.48 19	99.54 114	99.78 60	99.30 127	99.89 2	99.58 71	98.56 107	99.73 83	99.69 189	98.55 78	99.82 198	99.69 31	99.85 84	99.48 203

MVSFormer		99.17 96	99.12 88	99.29 174	99.51 189	98.94 181	99.88 4	99.46 203	97.55 237	99.80 60	99.65 209	97.39 121	99.28 328	99.03 107	99.85 84	99.65 145

test_djsdf		98.67 177	98.57 178	98.98 212	98.70 381	98.91 186	99.88 4	99.46 203	97.55 237	99.22 220	99.88 45	95.73 192	99.28 328	99.03 107	97.62 285	98.75 295

OurMVSNet-221017-0		97.88 258	97.77 249	98.19 320	98.71 380	96.53 341	99.88 4	99.00 348	97.79 208	98.78 301	99.94 6	91.68 336	99.35 318	97.21 304	96.99 321	98.69 312

EC-MVSNet		99.44 45	99.39 35	99.58 107	99.56 172	99.49 100	99.88 4	99.58 71	98.38 125	99.73 83	99.69 189	98.20 99	99.70 251	99.64 39	99.82 105	99.54 182

DVP-MVS++		99.59 12	99.50 17	99.88 11	99.51 189	99.88 8	99.87 8	99.51 131	98.99 58	99.88 36	99.81 107	99.27 5	99.96 36	98.85 136	99.80 113	99.81 71

FOURS1					99.91 1	99.93 1	99.87 8	99.56 81	99.10 40	99.81 56

K. test v3		97.10 338	96.79 338	98.01 333	98.72 378	96.33 348	99.87 8	97.05 425	97.59 231	96.16 404	99.80 121	88.71 376	99.04 369	96.69 336	96.55 327	98.65 336

FC-MVSNet-test		98.75 170	98.62 171	99.15 196	99.08 320	99.45 106	99.86 11	99.60 61	98.23 146	98.70 313	99.82 93	96.80 146	99.22 342	99.07 103	96.38 330	98.79 285

v7n		97.87 260	97.52 277	98.92 223	98.76 374	98.58 220	99.84 12	99.46 203	96.20 353	98.91 279	99.70 178	94.89 228	99.44 298	96.03 353	93.89 388	98.75 295

DTE-MVSNet		97.51 314	97.19 323	98.46 291	98.63 387	98.13 252	99.84 12	99.48 173	96.68 315	97.97 366	99.67 202	92.92 299	98.56 403	96.88 329	92.60 406	98.70 308

3Dnovator	97.25 9	99.24 88	99.05 98	99.81 53	99.12 309	99.66 63	99.84 12	99.74 10	99.09 45	98.92 278	99.90 30	95.94 182	99.98 15	98.95 116	99.92 35	99.79 84

FIs		98.78 167	98.63 166	99.23 186	99.18 293	99.54 90	99.83 15	99.59 67	98.28 137	98.79 300	99.81 107	96.75 149	99.37 311	99.08 102	96.38 330	98.78 287

MGCFI-Net		99.01 138	98.85 141	99.50 136	99.42 223	99.26 133	99.82 16	99.48 173	98.60 104	99.28 203	98.81 385	97.04 139	99.76 224	99.29 80	97.87 274	99.47 209

test_fmvs3		92.10 392	91.77 395	93.08 406	96.19 425	86.25 426	99.82 16	98.62 400	96.65 318	95.19 412	96.90 426	55.05 441	95.93 433	96.63 341	90.92 415	97.06 422

jajsoiax		98.43 190	98.28 197	98.88 234	98.60 391	98.43 238	99.82 16	99.53 111	98.19 151	98.63 325	99.80 121	93.22 294	99.44 298	99.22 87	97.50 297	98.77 291

OpenMVS	96.50 16	98.47 187	98.12 208	99.52 128	99.04 328	99.53 93	99.82 16	99.72 11	94.56 392	98.08 359	99.88 45	94.73 240	99.98 15	97.47 289	99.76 128	99.06 266

SDMVSNet		99.11 118	98.90 131	99.75 68	99.81 48	99.59 80	99.81 20	99.65 35	98.78 87	99.64 117	99.88 45	94.56 251	99.93 100	99.67 33	98.26 252	99.72 118

nrg030		98.64 181	98.42 187	99.28 178	99.05 326	99.69 55	99.81 20	99.46 203	98.04 180	99.01 262	99.82 93	96.69 151	99.38 308	99.34 73	94.59 375	98.78 287

HPM-MVS		99.42 50	99.28 64	99.83 49	99.90 4	99.72 49	99.81 20	99.54 98	97.59 231	99.68 96	99.63 221	98.91 37	99.94 82	98.58 177	99.91 42	99.84 49
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EPP-MVSNet		99.13 106	98.99 114	99.53 122	99.65 141	99.06 160	99.81 20	99.33 280	97.43 254	99.60 130	99.88 45	97.14 133	99.84 177	99.13 95	98.94 208	99.69 131

3Dnovator+	97.12 13	99.18 94	98.97 118	99.82 50	99.17 301	99.68 56	99.81 20	99.51 131	99.20 27	98.72 306	99.89 36	95.68 194	99.97 24	98.86 134	99.86 77	99.81 71

sasdasda		99.02 134	98.86 139	99.51 131	99.42 223	99.32 120	99.80 25	99.48 173	98.63 99	99.31 195	98.81 385	97.09 135	99.75 227	99.27 83	97.90 271	99.47 209

FA-MVS(test-final)		98.75 170	98.53 182	99.41 150	99.55 176	99.05 162	99.80 25	99.01 347	96.59 328	99.58 134	99.59 235	95.39 204	99.90 137	97.78 255	99.49 165	99.28 241

GeoE		98.85 159	98.62 171	99.53 122	99.61 157	99.08 157	99.80 25	99.51 131	97.10 286	99.31 195	99.78 140	95.23 214	99.77 220	98.21 217	99.03 203	99.75 98

canonicalmvs		99.02 134	98.86 139	99.51 131	99.42 223	99.32 120	99.80 25	99.48 173	98.63 99	99.31 195	98.81 385	97.09 135	99.75 227	99.27 83	97.90 271	99.47 209

v8		97.95 249	97.63 268	98.93 221	98.95 343	98.81 200	99.80 25	99.41 234	96.03 367	99.10 245	99.42 293	94.92 226	99.30 326	96.94 324	94.08 385	98.66 334

Vis-MVSNet (Re-imp)		98.87 149	98.72 154	99.31 166	99.71 106	98.88 188	99.80 25	99.44 223	97.91 192	99.36 186	99.78 140	95.49 201	99.43 302	97.91 242	99.11 194	99.62 160

Anonymous20240521		96.20 357	95.89 360	97.13 378	97.72 412	94.96 386	99.79 31	99.29 303	93.01 406	97.20 389	99.03 364	89.69 366	98.36 407	91.16 414	96.13 336	98.07 398

PS-MVSNAJss		98.92 145	98.92 127	98.90 229	98.78 367	98.53 224	99.78 32	99.54 98	98.07 173	99.00 266	99.76 153	99.01 18	99.37 311	99.13 95	97.23 314	98.81 284

PEN-MVS		97.76 281	97.44 293	98.72 259	98.77 372	98.54 223	99.78 32	99.51 131	97.06 290	98.29 349	99.64 215	92.63 312	98.89 394	98.09 226	93.16 398	98.72 301

anonymousdsp		98.44 189	98.28 197	98.94 219	98.50 397	98.96 175	99.77 34	99.50 151	97.07 288	98.87 287	99.77 149	94.76 238	99.28 328	98.66 163	97.60 286	98.57 362

SixPastTwentyTwo		97.50 315	97.33 311	98.03 330	98.65 385	96.23 353	99.77 34	98.68 396	97.14 279	97.90 369	99.93 10	90.45 355	99.18 350	97.00 318	96.43 329	98.67 325

QAPM		98.67 177	98.30 196	99.80 56	99.20 287	99.67 60	99.77 34	99.72 11	94.74 389	98.73 305	99.90 30	95.78 190	99.98 15	96.96 322	99.88 66	99.76 97

SSC-MVS		92.73 391	93.73 386	89.72 416	95.02 435	81.38 436	99.76 37	99.23 315	94.87 386	92.80 423	98.93 377	94.71 242	91.37 440	74.49 439	93.80 389	96.42 426

test_vis3_rt		87.04 399	85.81 402	90.73 413	93.99 437	81.96 434	99.76 37	90.23 448	92.81 409	81.35 436	91.56 436	40.06 445	99.07 366	94.27 387	88.23 423	91.15 436

dcpmvs_2		99.23 89	99.58 7	98.16 322	99.83 40	94.68 391	99.76 37	99.52 116	99.07 48	99.98 10	99.88 45	98.56 77	99.93 100	99.67 33	99.98 4	99.87 36

RRT-MVS		98.91 146	98.75 152	99.39 155	99.46 213	98.61 218	99.76 37	99.50 151	98.06 177	99.81 56	99.88 45	93.91 280	99.94 82	99.11 97	99.27 182	99.61 162

HPM-MVS_fast		99.51 24	99.40 33	99.85 36	99.91 1	99.79 34	99.76 37	99.56 81	97.72 216	99.76 77	99.75 156	99.13 12	99.92 112	99.07 103	99.92 35	99.85 42

MVSMamba_PlusPlus		99.46 37	99.41 32	99.64 92	99.68 121	99.50 99	99.75 42	99.50 151	98.27 139	99.87 41	99.92 17	98.09 104	99.94 82	99.65 37	99.95 19	99.47 209

v10		97.85 263	97.52 277	98.86 241	98.99 336	98.67 209	99.75 42	99.41 234	95.70 371	98.98 269	99.41 297	94.75 239	99.23 338	96.01 355	94.63 374	98.67 325

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 68	99.89 4	99.75 42	99.56 81	99.02 51	99.88 36	99.85 68	99.18 10	99.96 36	99.22 87	99.92 35	99.90 22
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
IS-MVSNet		99.05 130	98.87 137	99.57 109	99.73 97	99.32 120	99.75 42	99.20 321	98.02 184	99.56 138	99.86 61	96.54 158	99.67 259	98.09 226	99.13 193	99.73 110

test_vis1_n		97.92 253	97.44 293	99.34 159	99.53 180	98.08 255	99.74 46	99.49 161	99.15 30	100.00 1	99.94 6	79.51 429	99.98 15	99.88 22	99.76 128	99.97 4

test_fmvs1_n		98.41 193	98.14 205	99.21 187	99.82 44	97.71 281	99.74 46	99.49 161	99.32 23	99.99 2	99.95 3	85.32 407	99.97 24	99.82 25	99.84 92	99.96 7

balanced_conf03		99.46 37	99.39 35	99.67 81	99.55 176	99.58 85	99.74 46	99.51 131	98.42 122	99.87 41	99.84 79	98.05 107	99.91 124	99.58 43	99.94 27	99.52 189

tttt0517		98.42 191	98.14 205	99.28 178	99.66 134	98.38 241	99.74 46	96.85 427	97.68 222	99.79 62	99.74 161	91.39 344	99.89 150	98.83 142	99.56 158	99.57 176

WB-MVS		93.10 389	94.10 382	90.12 415	95.51 433	81.88 435	99.73 50	99.27 308	95.05 382	93.09 422	98.91 381	94.70 243	91.89 439	76.62 437	94.02 387	96.58 425

test_fmvs2		97.25 332	97.30 314	97.09 380	99.43 221	93.31 411	99.73 50	98.87 370	98.83 77	99.28 203	99.80 121	84.45 412	99.66 262	97.88 244	97.45 302	98.30 384

MonoMVSNet		98.38 197	98.47 185	98.12 327	98.59 393	96.19 355	99.72 52	98.79 381	97.89 194	99.44 163	99.52 263	96.13 173	98.90 393	98.64 165	97.54 292	99.28 241

baseline		99.15 101	99.02 108	99.53 122	99.66 134	99.14 149	99.72 52	99.48 173	98.35 130	99.42 168	99.84 79	96.07 175	99.79 213	99.51 52	99.14 192	99.67 138

RPSCF		98.22 208	98.62 171	96.99 381	99.82 44	91.58 420	99.72 52	99.44 223	96.61 323	99.66 105	99.89 36	95.92 183	99.82 198	97.46 290	99.10 197	99.57 176

CSCG		99.32 72	99.32 49	99.32 165	99.85 26	98.29 243	99.71 55	99.66 28	98.11 165	99.41 172	99.80 121	98.37 92	99.96 36	98.99 111	99.96 14	99.72 118

dmvs_re		98.08 225	98.16 202	97.85 348	99.55 176	94.67 392	99.70 56	98.92 358	98.15 156	99.06 256	99.35 316	93.67 288	99.25 335	97.77 258	97.25 313	99.64 152

WR-MVS_H		98.13 219	97.87 239	98.90 229	99.02 330	98.84 194	99.70 56	99.59 67	97.27 268	98.40 341	99.19 348	95.53 199	99.23 338	98.34 207	93.78 390	98.61 356

mvsmamba		99.06 128	98.96 122	99.36 157	99.47 211	98.64 213	99.70 56	99.05 342	97.61 230	99.65 112	99.83 84	96.54 158	99.92 112	99.19 89	99.62 153	99.51 197

LTVRE_ROB	97.16 12	98.02 237	97.90 234	98.40 301	99.23 280	96.80 330	99.70 56	99.60 61	97.12 282	98.18 356	99.70 178	91.73 335	99.72 239	98.39 200	97.45 302	98.68 317
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		91.90 393	91.26 397	93.84 402	95.52 432	85.92 427	99.69 60	98.53 404	95.31 376	93.87 418	96.37 429	55.33 440	98.27 408	95.70 361	90.98 414	97.32 421

XVS		99.53 22	99.42 27	99.87 17	99.85 26	99.83 19	99.69 60	99.68 20	98.98 61	99.37 183	99.74 161	98.81 47	99.94 82	98.79 147	99.86 77	99.84 49

X-MVStestdata		96.55 349	95.45 368	99.87 17	99.85 26	99.83 19	99.69 60	99.68 20	98.98 61	99.37 183	64.01 445	98.81 47	99.94 82	98.79 147	99.86 77	99.84 49

V42		98.06 227	97.79 244	98.86 241	98.98 339	98.84 194	99.69 60	99.34 273	96.53 330	99.30 199	99.37 310	94.67 245	99.32 323	97.57 279	94.66 373	98.42 376

mPP-MVS		99.44 45	99.30 57	99.86 28	99.88 11	99.79 34	99.69 60	99.48 173	98.12 163	99.50 150	99.75 156	98.78 51	99.97 24	98.57 180	99.89 62	99.83 59

CP-MVS		99.45 41	99.32 49	99.85 36	99.83 40	99.75 44	99.69 60	99.52 116	98.07 173	99.53 145	99.63 221	98.93 36	99.97 24	98.74 151	99.91 42	99.83 59

FE-MVS		98.48 186	98.17 201	99.40 151	99.54 179	98.96 175	99.68 66	98.81 377	95.54 373	99.62 124	99.70 178	93.82 283	99.93 100	97.35 298	99.46 166	99.32 238

PS-CasMVS		97.93 250	97.59 272	98.95 217	98.99 336	99.06 160	99.68 66	99.52 116	97.13 280	98.31 346	99.68 196	92.44 321	99.05 368	98.51 188	94.08 385	98.75 295

Vis-MVSNet		99.12 112	98.97 118	99.56 111	99.78 60	99.10 153	99.68 66	99.66 28	98.49 113	99.86 45	99.87 56	94.77 237	99.84 177	99.19 89	99.41 170	99.74 102
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
KinetiMVS		99.12 112	98.92 127	99.70 78	99.67 123	99.40 112	99.67 69	99.63 42	98.73 91	99.94 24	99.81 107	94.54 254	99.96 36	98.40 199	99.93 29	99.74 102

BP-MVS1		99.12 112	98.94 126	99.65 86	99.51 189	99.30 127	99.67 69	98.92 358	98.48 114	99.84 48	99.69 189	94.96 221	99.92 112	99.62 40	99.79 120	99.71 127

test_vis1_n_1920		98.63 182	98.40 189	99.31 166	99.86 20	97.94 268	99.67 69	99.62 46	99.43 13	99.99 2	99.91 23	87.29 394	100.00 1	99.92 20	99.92 35	99.98 2

EIA-MVS		99.18 94	99.09 94	99.45 144	99.49 203	99.18 141	99.67 69	99.53 111	97.66 225	99.40 177	99.44 289	98.10 103	99.81 203	98.94 117	99.62 153	99.35 233

MSP-MVS		99.42 50	99.27 67	99.88 11	99.89 8	99.80 31	99.67 69	99.50 151	98.70 95	99.77 71	99.49 273	98.21 98	99.95 69	98.46 194	99.77 125	99.88 31
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		99.10 122	98.97 118	99.48 137	99.49 203	99.14 149	99.67 69	99.34 273	97.31 265	99.58 134	99.76 153	97.65 117	99.82 198	98.87 129	99.07 200	99.46 214

CP-MVSNet		98.09 223	97.78 247	99.01 208	98.97 341	99.24 136	99.67 69	99.46 203	97.25 270	98.48 338	99.64 215	93.79 284	99.06 367	98.63 167	94.10 384	98.74 299

MTAPA		99.52 23	99.39 35	99.89 8	99.90 4	99.86 16	99.66 76	99.47 194	98.79 84	99.68 96	99.81 107	98.43 86	99.97 24	98.88 126	99.90 51	99.83 59

HFP-MVS		99.49 28	99.37 39	99.86 28	99.87 15	99.80 31	99.66 76	99.67 23	98.15 156	99.68 96	99.69 189	99.06 16	99.96 36	98.69 159	99.87 69	99.84 49

mvs_tets		98.40 196	98.23 199	98.91 227	98.67 384	98.51 230	99.66 76	99.53 111	98.19 151	98.65 322	99.81 107	92.75 303	99.44 298	99.31 77	97.48 301	98.77 291

EU-MVSNet		97.98 244	98.03 220	97.81 354	98.72 378	96.65 337	99.66 76	99.66 28	98.09 168	98.35 344	99.82 93	95.25 213	98.01 414	97.41 294	95.30 361	98.78 287

ACMMPR		99.49 28	99.36 41	99.86 28	99.87 15	99.79 34	99.66 76	99.67 23	98.15 156	99.67 100	99.69 189	98.95 30	99.96 36	98.69 159	99.87 69	99.84 49

MP-MVS		99.33 70	99.15 84	99.87 17	99.88 11	99.82 25	99.66 76	99.46 203	98.09 168	99.48 154	99.74 161	98.29 95	99.96 36	97.93 241	99.87 69	99.82 64
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 98	99.01 112	99.61 100	99.81 48	98.86 192	99.65 82	99.64 38	99.39 18	99.97 21	99.94 6	93.20 295	99.98 15	99.55 46	99.91 42	99.99 1

region2R		99.48 32	99.35 43	99.87 17	99.88 11	99.80 31	99.65 82	99.66 28	98.13 161	99.66 105	99.68 196	98.96 25	99.96 36	98.62 168	99.87 69	99.84 49

TranMVSNet+NR-MVSNet		97.93 250	97.66 263	98.76 256	98.78 367	98.62 216	99.65 82	99.49 161	97.76 212	98.49 337	99.60 233	94.23 265	98.97 385	98.00 237	92.90 400	98.70 308

GDP-MVS		99.08 125	98.89 134	99.64 92	99.53 180	99.34 118	99.64 85	99.48 173	98.32 134	99.77 71	99.66 207	95.14 217	99.93 100	98.97 115	99.50 164	99.64 152

ttmdpeth		97.80 277	97.63 268	98.29 311	98.77 372	97.38 292	99.64 85	99.36 261	98.78 87	96.30 402	99.58 239	92.34 324	99.39 306	98.36 205	95.58 354	98.10 396

mvsany_test3		93.77 386	93.45 390	94.74 399	95.78 428	88.01 425	99.64 85	98.25 408	98.28 137	94.31 416	97.97 418	68.89 433	98.51 405	97.50 285	90.37 416	97.71 413

ZNCC-MVS		99.47 35	99.33 47	99.87 17	99.87 15	99.81 29	99.64 85	99.67 23	98.08 172	99.55 142	99.64 215	98.91 37	99.96 36	98.72 154	99.90 51	99.82 64

tfpnnormal		97.84 267	97.47 285	98.98 212	99.20 287	99.22 138	99.64 85	99.61 54	96.32 344	98.27 350	99.70 178	93.35 291	99.44 298	95.69 362	95.40 359	98.27 386

casdiffmvs_mvg		99.15 101	99.02 108	99.55 113	99.66 134	99.09 154	99.64 85	99.56 81	98.26 141	99.45 158	99.87 56	96.03 177	99.81 203	99.54 47	99.15 191	99.73 110
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 41	99.31 55	99.85 36	99.76 72	99.82 25	99.63 91	99.52 116	98.38 125	99.76 77	99.82 93	98.53 79	99.95 69	98.61 171	99.81 108	99.77 92

RE-MVS-def			99.34 45		99.76 72	99.82 25	99.63 91	99.52 116	98.38 125	99.76 77	99.82 93	98.75 58		98.61 171	99.81 108	99.77 92

TSAR-MVS + MP.		99.58 13	99.50 17	99.81 53	99.91 1	99.66 63	99.63 91	99.39 244	98.91 71	99.78 67	99.85 68	99.36 2	99.94 82	98.84 139	99.88 66	99.82 64
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
Anonymous20231206		96.22 355	96.03 356	96.79 389	97.31 418	94.14 401	99.63 91	99.08 336	96.17 356	97.04 393	99.06 361	93.94 277	97.76 420	86.96 429	95.06 366	98.47 370

APD-MVS_3200maxsize		99.48 32	99.35 43	99.85 36	99.76 72	99.83 19	99.63 91	99.54 98	98.36 129	99.79 62	99.82 93	98.86 41	99.95 69	98.62 168	99.81 108	99.78 90

test0726					99.85 26	99.89 4	99.62 96	99.50 151	99.10 40	99.86 45	99.82 93	98.94 32

EPNet		98.86 152	98.71 156	99.30 171	97.20 420	98.18 248	99.62 96	98.91 363	99.28 25	98.63 325	99.81 107	95.96 179	99.99 4	99.24 86	99.72 136	99.73 110
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t		98.93 144	98.67 160	99.72 77	99.85 26	99.53 93	99.62 96	99.59 67	92.65 411	99.71 90	99.78 140	98.06 106	99.90 137	98.84 139	99.91 42	99.74 102

HY-MVS	97.30 7	98.85 159	98.64 165	99.47 141	99.42 223	99.08 157	99.62 96	99.36 261	97.39 259	99.28 203	99.68 196	96.44 164	99.92 112	98.37 203	98.22 255	99.40 226

ACMMP		99.45 41	99.32 49	99.82 50	99.89 8	99.67 60	99.62 96	99.69 18	98.12 163	99.63 120	99.84 79	98.73 63	99.96 36	98.55 186	99.83 101	99.81 71
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 75	99.19 81	99.64 92	99.82 44	99.23 137	99.62 96	99.55 89	98.94 67	99.63 120	99.95 3	95.82 188	99.94 82	99.37 67	99.97 8	99.73 110
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 13	99.56 10	99.64 92	99.78 60	99.15 148	99.61 102	99.45 214	99.01 53	99.89 33	99.82 93	99.01 18	99.92 112	99.56 45	99.95 19	99.85 42

reproduce_monomvs		97.89 257	97.87 239	97.96 339	99.51 189	95.45 372	99.60 103	99.25 311	99.17 28	98.85 292	99.49 273	89.29 370	99.64 270	99.35 68	96.31 333	98.78 287

test2506		96.81 345	96.65 341	97.29 375	99.74 90	92.21 418	99.60 103	85.06 449	99.13 33	99.77 71	99.93 10	87.82 392	99.85 170	99.38 66	99.38 171	99.80 80

SED-MVS		99.61 8	99.52 12	99.88 11	99.84 32	99.90 2	99.60 103	99.48 173	99.08 46	99.91 27	99.81 107	99.20 7	99.96 36	98.91 123	99.85 84	99.79 84

OPU-MVS				99.64 92	99.56 172	99.72 49	99.60 103				99.70 178	99.27 5	99.42 304	98.24 216	99.80 113	99.79 84

GST-MVS		99.40 57	99.24 72	99.85 36	99.86 20	99.79 34	99.60 103	99.67 23	97.97 187	99.63 120	99.68 196	98.52 80	99.95 69	98.38 201	99.86 77	99.81 71

EI-MVSNet-UG-set		99.58 13	99.57 8	99.64 92	99.78 60	99.14 149	99.60 103	99.45 214	99.01 53	99.90 30	99.83 84	98.98 24	99.93 100	99.59 41	99.95 19	99.86 38

ACMH	97.28 8	98.10 222	97.99 224	98.44 296	99.41 228	96.96 322	99.60 103	99.56 81	98.09 168	98.15 357	99.91 23	90.87 352	99.70 251	98.88 126	97.45 302	98.67 325
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
VortexMVS		98.67 177	98.66 163	98.68 264	99.62 152	97.96 263	99.59 110	99.41 234	98.13 161	99.31 195	99.70 178	95.48 202	99.27 331	99.40 64	97.32 311	98.79 285

guyue		99.16 98	99.04 100	99.52 128	99.69 116	98.92 185	99.59 110	98.81 377	98.73 91	99.90 30	99.87 56	95.34 207	99.88 155	99.66 36	99.81 108	99.74 102

ECVR-MVS		98.04 233	98.05 218	98.00 335	99.74 90	94.37 398	99.59 110	94.98 437	99.13 33	99.66 105	99.93 10	90.67 354	99.84 177	99.40 64	99.38 171	99.80 80

SR-MVS		99.43 48	99.29 61	99.86 28	99.75 82	99.83 19	99.59 110	99.62 46	98.21 149	99.73 83	99.79 133	98.68 67	99.96 36	98.44 196	99.77 125	99.79 84

thres100view900		97.76 281	97.45 288	98.69 263	99.72 101	97.86 272	99.59 110	98.74 387	97.93 190	99.26 213	98.62 393	91.75 333	99.83 190	93.22 399	98.18 260	98.37 382

thres600view7		97.86 262	97.51 279	98.92 223	99.72 101	97.95 266	99.59 110	98.74 387	97.94 189	99.27 208	98.62 393	91.75 333	99.86 164	93.73 394	98.19 259	98.96 277

LCM-MVSNet-Re		97.83 270	98.15 204	96.87 387	99.30 260	92.25 417	99.59 110	98.26 407	97.43 254	96.20 403	99.13 354	96.27 170	98.73 400	98.17 222	98.99 206	99.64 152

baseline1		98.31 202	97.95 229	99.38 156	99.50 201	98.74 204	99.59 110	98.93 355	98.41 123	99.14 237	99.60 233	94.59 249	99.79 213	98.48 190	93.29 395	99.61 162

SteuartSystems-ACMMP		99.54 19	99.42 27	99.87 17	99.82 44	99.81 29	99.59 110	99.51 131	98.62 101	99.79 62	99.83 84	99.28 4	99.97 24	98.48 190	99.90 51	99.84 49
Skip Steuart: Steuart Systems R&D Blog.
CPTT-MVS		99.11 118	98.90 131	99.74 71	99.80 54	99.46 105	99.59 110	99.49 161	97.03 294	99.63 120	99.69 189	97.27 129	99.96 36	97.82 252	99.84 92	99.81 71

test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 65	99.38 238	99.37 114	99.58 120	99.62 46	99.41 17	99.87 41	99.92 17	98.81 47	100.00 1	99.97 1	99.93 29	99.94 14

dmvs_testset		95.02 375	96.12 353	91.72 410	99.10 314	80.43 438	99.58 120	97.87 417	97.47 246	95.22 410	98.82 384	93.99 275	95.18 435	88.09 425	94.91 371	99.56 179

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 62	99.84 32	99.44 107	99.58 120	99.69 18	99.43 13	99.98 10	99.91 23	98.62 73	100.00 1	99.97 1	99.95 19	99.90 22

test1111		98.04 233	98.11 209	97.83 351	99.74 90	93.82 403	99.58 120	95.40 436	99.12 38	99.65 112	99.93 10	90.73 353	99.84 177	99.43 63	99.38 171	99.82 64

PGM-MVS		99.45 41	99.31 55	99.86 28	99.87 15	99.78 40	99.58 120	99.65 35	97.84 202	99.71 90	99.80 121	99.12 13	99.97 24	98.33 208	99.87 69	99.83 59

LPG-MVS_test		98.22 208	98.13 207	98.49 283	99.33 251	97.05 311	99.58 120	99.55 89	97.46 247	99.24 215	99.83 84	92.58 313	99.72 239	98.09 226	97.51 295	98.68 317

PHI-MVS		99.30 75	99.17 83	99.70 78	99.56 172	99.52 97	99.58 120	99.80 8	97.12 282	99.62 124	99.73 167	98.58 75	99.90 137	98.61 171	99.91 42	99.68 135

AstraMVS		99.09 123	99.03 103	99.25 181	99.66 134	98.13 252	99.57 127	98.24 409	98.82 78	99.91 27	99.88 45	95.81 189	99.90 137	99.72 28	99.67 146	99.74 102

SF-MVS		99.38 60	99.24 72	99.79 59	99.79 58	99.68 56	99.57 127	99.54 98	97.82 207	99.71 90	99.80 121	98.95 30	99.93 100	98.19 219	99.84 92	99.74 102

DVP-MVS		99.57 16	99.47 21	99.88 11	99.85 26	99.89 4	99.57 127	99.37 260	99.10 40	99.81 56	99.80 121	98.94 32	99.96 36	98.93 120	99.86 77	99.81 71
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 3	99.84 32	99.89 4	99.57 127	99.51 131					99.96 36	98.93 120	99.86 77	99.88 31

Effi-MVS+-dtu		98.78 167	98.89 134	98.47 290	99.33 251	96.91 324	99.57 127	99.30 299	98.47 115	99.41 172	98.99 370	96.78 147	99.74 229	98.73 153	99.38 171	98.74 299

v2v482		98.06 227	97.77 249	98.92 223	98.90 349	98.82 198	99.57 127	99.36 261	96.65 318	99.19 229	99.35 316	94.20 266	99.25 335	97.72 265	94.97 368	98.69 312

DSMNet-mixed		97.25 332	97.35 305	96.95 384	97.84 408	93.61 409	99.57 127	96.63 431	96.13 361	98.87 287	98.61 395	94.59 249	97.70 421	95.08 376	98.86 215	99.55 180

reproduce_model		99.63 7	99.54 11	99.90 5	99.78 60	99.88 8	99.56 134	99.55 89	99.15 30	99.90 30	99.90 30	99.00 22	99.97 24	99.11 97	99.91 42	99.86 38

MVStest1		96.08 361	95.48 366	97.89 345	98.93 344	96.70 332	99.56 134	99.35 268	92.69 410	91.81 427	99.46 286	89.90 363	98.96 387	95.00 378	92.61 405	98.00 405

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 36	99.86 20	99.61 77	99.56 134	99.63 42	99.48 3	99.98 10	99.83 84	98.75 58	99.99 4	99.97 1	99.96 14	99.94 14

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 36	99.84 32	99.63 74	99.56 134	99.63 42	99.47 4	99.98 10	99.82 93	98.75 58	99.99 4	99.97 1	99.97 8	99.94 14

sd_testset		98.75 170	98.57 178	99.29 174	99.81 48	98.26 245	99.56 134	99.62 46	98.78 87	99.64 117	99.88 45	92.02 327	99.88 155	99.54 47	98.26 252	99.72 118

KD-MVS_self_test		95.00 376	94.34 381	96.96 383	97.07 423	95.39 375	99.56 134	99.44 223	95.11 379	97.13 391	97.32 424	91.86 331	97.27 425	90.35 417	81.23 433	98.23 390

ETV-MVS		99.26 83	99.21 77	99.40 151	99.46 213	99.30 127	99.56 134	99.52 116	98.52 111	99.44 163	99.27 338	98.41 90	99.86 164	99.10 100	99.59 156	99.04 267

SMA-MVS		99.44 45	99.30 57	99.85 36	99.73 97	99.83 19	99.56 134	99.47 194	97.45 250	99.78 67	99.82 93	99.18 10	99.91 124	98.79 147	99.89 62	99.81 71
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		98.87 149	98.72 154	99.31 166	99.86 20	98.48 234	99.56 134	99.61 54	97.85 200	99.36 186	99.85 68	95.95 180	99.85 170	96.66 338	99.83 101	99.59 169

casdiffmvs		99.13 106	98.98 117	99.56 111	99.65 141	99.16 144	99.56 134	99.50 151	98.33 133	99.41 172	99.86 61	95.92 183	99.83 190	99.45 62	99.16 188	99.70 129
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		98.38 197	98.09 213	99.24 184	99.26 272	99.32 120	99.56 134	99.55 89	97.45 250	98.71 307	99.83 84	93.23 292	99.63 276	98.88 126	96.32 332	98.76 293

ACMH+	97.24 10	97.92 253	97.78 247	98.32 308	99.46 213	96.68 336	99.56 134	99.54 98	98.41 123	97.79 375	99.87 56	90.18 361	99.66 262	98.05 234	97.18 317	98.62 347

ACMM	97.58 5	98.37 199	98.34 192	98.48 285	99.41 228	97.10 305	99.56 134	99.45 214	98.53 110	99.04 259	99.85 68	93.00 297	99.71 245	98.74 151	97.45 302	98.64 338
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LS3D		99.27 81	99.12 88	99.74 71	99.18 293	99.75 44	99.56 134	99.57 76	98.45 118	99.49 153	99.85 68	97.77 114	99.94 82	98.33 208	99.84 92	99.52 189

testing3-2		97.84 267	97.70 259	98.24 317	99.53 180	95.37 376	99.55 148	98.67 397	98.46 116	99.27 208	99.34 320	86.58 398	99.83 190	99.32 76	98.63 227	99.52 189

test_fmvsmconf0.01_n		99.22 91	99.03 103	99.79 59	98.42 400	99.48 102	99.55 148	99.51 131	99.39 18	99.78 67	99.93 10	94.80 232	99.95 69	99.93 19	99.95 19	99.94 14

test_fmvs1		98.88 148	98.79 149	99.16 192	99.69 116	97.61 285	99.55 148	99.49 161	99.32 23	99.98 10	99.91 23	91.41 343	99.96 36	99.82 25	99.92 35	99.90 22

v144192		97.92 253	97.60 271	98.87 238	98.83 361	98.65 211	99.55 148	99.34 273	96.20 353	99.32 194	99.40 301	94.36 261	99.26 334	96.37 349	95.03 367	98.70 308

API-MVS		99.04 131	99.03 103	99.06 202	99.40 233	99.31 124	99.55 148	99.56 81	98.54 109	99.33 193	99.39 305	98.76 55	99.78 218	96.98 320	99.78 122	98.07 398

fmvsm_l_conf0.5_n_3		99.61 8	99.51 16	99.92 1	99.84 32	99.82 25	99.54 153	99.66 28	99.46 7	99.98 10	99.89 36	97.27 129	99.99 4	99.97 1	99.95 19	99.95 10

fmvsm_s_conf0.1_n_a		99.26 83	99.06 97	99.85 36	99.52 186	99.62 75	99.54 153	99.62 46	98.69 96	99.99 2	99.96 1	94.47 258	99.94 82	99.88 22	99.92 35	99.98 2

APD_test1		95.87 363	96.49 345	94.00 401	99.53 180	84.01 430	99.54 153	99.32 290	95.91 369	97.99 364	99.85 68	85.49 405	99.88 155	91.96 410	98.84 217	98.12 395

thisisatest0530		98.35 200	98.03 220	99.31 166	99.63 146	98.56 221	99.54 153	96.75 429	97.53 241	99.73 83	99.65 209	91.25 348	99.89 150	98.62 168	99.56 158	99.48 203

MTMP							99.54 153	98.88 368

v1144		97.98 244	97.69 260	98.85 244	98.87 354	98.66 210	99.54 153	99.35 268	96.27 348	99.23 219	99.35 316	94.67 245	99.23 338	96.73 333	95.16 364	98.68 317

v148		97.79 279	97.55 273	98.50 282	98.74 375	97.72 278	99.54 153	99.33 280	96.26 349	98.90 281	99.51 267	94.68 244	99.14 354	97.83 251	93.15 399	98.63 345

CostFormer		97.72 291	97.73 256	97.71 359	99.15 307	94.02 402	99.54 153	99.02 346	94.67 390	99.04 259	99.35 316	92.35 323	99.77 220	98.50 189	97.94 270	99.34 236

MVSTER		98.49 185	98.32 194	99.00 210	99.35 245	99.02 164	99.54 153	99.38 252	97.41 257	99.20 226	99.73 167	93.86 282	99.36 315	98.87 129	97.56 290	98.62 347

fmvsm_s_conf0.1_n		99.29 77	99.10 90	99.86 28	99.70 111	99.65 67	99.53 162	99.62 46	98.74 90	99.99 2	99.95 3	94.53 256	99.94 82	99.89 21	99.96 14	99.97 4

reproduce-ours		99.61 8	99.52 12	99.90 5	99.76 72	99.88 8	99.52 163	99.54 98	99.13 33	99.89 33	99.89 36	98.96 25	99.96 36	99.04 105	99.90 51	99.85 42

our_new_method		99.61 8	99.52 12	99.90 5	99.76 72	99.88 8	99.52 163	99.54 98	99.13 33	99.89 33	99.89 36	98.96 25	99.96 36	99.04 105	99.90 51	99.85 42

fmvsm_s_conf0.5_n_a		99.56 17	99.47 21	99.85 36	99.83 40	99.64 73	99.52 163	99.65 35	99.10 40	99.98 10	99.92 17	97.35 125	99.96 36	99.94 17	99.92 35	99.95 10

MM		99.40 57	99.28 64	99.74 71	99.67 123	99.31 124	99.52 163	98.87 370	99.55 1	99.74 81	99.80 121	96.47 161	99.98 15	99.97 1	99.97 8	99.94 14

patch_mono-2		99.26 83	99.62 5	98.16 322	99.81 48	94.59 394	99.52 163	99.64 38	99.33 22	99.73 83	99.90 30	99.00 22	99.99 4	99.69 31	99.98 4	99.89 25

Fast-Effi-MVS+-dtu		98.77 169	98.83 145	98.60 269	99.41 228	96.99 318	99.52 163	99.49 161	98.11 165	99.24 215	99.34 320	96.96 143	99.79 213	97.95 240	99.45 167	99.02 270

Fast-Effi-MVS+		98.70 174	98.43 186	99.51 131	99.51 189	99.28 130	99.52 163	99.47 194	96.11 362	99.01 262	99.34 320	96.20 172	99.84 177	97.88 244	98.82 219	99.39 227

v1921920		97.80 277	97.45 288	98.84 245	98.80 363	98.53 224	99.52 163	99.34 273	96.15 359	99.24 215	99.47 282	93.98 276	99.29 327	95.40 370	95.13 365	98.69 312

MIMVSNet1		95.51 369	95.04 374	96.92 386	97.38 415	95.60 365	99.52 163	99.50 151	93.65 400	96.97 395	99.17 349	85.28 408	96.56 430	88.36 424	95.55 356	98.60 359

fmvsm_s_conf0.5_n_8		99.54 19	99.42 27	99.89 8	99.83 40	99.74 47	99.51 172	99.62 46	99.46 7	99.99 2	99.90 30	96.60 154	99.98 15	99.95 12	99.95 19	99.96 7

fmvsm_s_conf0.5_n		99.51 24	99.40 33	99.85 36	99.84 32	99.65 67	99.51 172	99.67 23	99.13 33	99.98 10	99.92 17	96.60 154	99.96 36	99.95 12	99.96 14	99.95 10

UniMVSNet_ETH3D		97.32 329	96.81 337	98.87 238	99.40 233	97.46 289	99.51 172	99.53 111	95.86 370	98.54 334	99.77 149	82.44 421	99.66 262	98.68 161	97.52 294	99.50 201

alignmvs		98.81 163	98.56 180	99.58 107	99.43 221	99.42 109	99.51 172	98.96 353	98.61 102	99.35 189	98.92 380	94.78 234	99.77 220	99.35 68	98.11 265	99.54 182

v1192		97.81 275	97.44 293	98.91 227	98.88 351	98.68 208	99.51 172	99.34 273	96.18 355	99.20 226	99.34 320	94.03 274	99.36 315	95.32 372	95.18 363	98.69 312

test20.03		96.12 359	95.96 358	96.63 390	97.44 414	95.45 372	99.51 172	99.38 252	96.55 329	96.16 404	99.25 341	93.76 286	96.17 431	87.35 428	94.22 381	98.27 386

mvs_anonymous		99.03 133	98.99 114	99.16 192	99.38 238	98.52 228	99.51 172	99.38 252	97.79 208	99.38 181	99.81 107	97.30 127	99.45 293	99.35 68	98.99 206	99.51 197

TAMVS		99.12 112	99.08 95	99.24 184	99.46 213	98.55 222	99.51 172	99.46 203	98.09 168	99.45 158	99.82 93	98.34 93	99.51 287	98.70 156	98.93 209	99.67 138

fmvsm_s_conf0.5_n_6		99.54 19	99.44 26	99.85 36	99.51 189	99.67 60	99.50 180	99.64 38	99.43 13	99.98 10	99.78 140	97.26 131	99.95 69	99.95 12	99.93 29	99.92 20

test_fmvsmconf0.1_n		99.55 18	99.45 25	99.86 28	99.44 220	99.65 67	99.50 180	99.61 54	99.45 10	99.87 41	99.92 17	97.31 126	99.97 24	99.95 12	99.99 1	99.97 4

test_yl		98.86 152	98.63 166	99.54 114	99.49 203	99.18 141	99.50 180	99.07 339	98.22 147	99.61 127	99.51 267	95.37 205	99.84 177	98.60 174	98.33 246	99.59 169

DCV-MVSNet		98.86 152	98.63 166	99.54 114	99.49 203	99.18 141	99.50 180	99.07 339	98.22 147	99.61 127	99.51 267	95.37 205	99.84 177	98.60 174	98.33 246	99.59 169

tfpn200view9		97.72 291	97.38 301	98.72 259	99.69 116	97.96 263	99.50 180	98.73 393	97.83 203	99.17 234	98.45 400	91.67 337	99.83 190	93.22 399	98.18 260	98.37 382

UA-Net		99.42 50	99.29 61	99.80 56	99.62 152	99.55 88	99.50 180	99.70 15	98.79 84	99.77 71	99.96 1	97.45 120	99.96 36	98.92 122	99.90 51	99.89 25

pm-mvs1		97.68 299	97.28 317	98.88 234	99.06 323	98.62 216	99.50 180	99.45 214	96.32 344	97.87 371	99.79 133	92.47 317	99.35 318	97.54 282	93.54 392	98.67 325

EI-MVSNet		98.67 177	98.67 160	98.68 264	99.35 245	97.97 261	99.50 180	99.38 252	96.93 303	99.20 226	99.83 84	97.87 110	99.36 315	98.38 201	97.56 290	98.71 303

CVMVSNet		98.57 184	98.67 160	98.30 310	99.35 245	95.59 366	99.50 180	99.55 89	98.60 104	99.39 179	99.83 84	94.48 257	99.45 293	98.75 150	98.56 234	99.85 42

VPA-MVSNet		98.29 205	97.95 229	99.30 171	99.16 303	99.54 90	99.50 180	99.58 71	98.27 139	99.35 189	99.37 310	92.53 315	99.65 267	99.35 68	94.46 376	98.72 301

thres400		97.77 280	97.38 301	98.92 223	99.69 116	97.96 263	99.50 180	98.73 393	97.83 203	99.17 234	98.45 400	91.67 337	99.83 190	93.22 399	98.18 260	98.96 277

APD-MVS		99.27 81	99.08 95	99.84 48	99.75 82	99.79 34	99.50 180	99.50 151	97.16 278	99.77 71	99.82 93	98.78 51	99.94 82	97.56 280	99.86 77	99.80 80
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
fmvsm_s_conf0.5_n_4		99.36 65	99.24 72	99.73 74	99.78 60	99.53 93	99.49 192	99.60 61	99.42 16	99.99 2	99.86 61	95.15 216	99.95 69	99.95 12	99.89 62	99.73 110

test_vis1_rt		95.81 365	95.65 364	96.32 394	99.67 123	91.35 421	99.49 192	96.74 430	98.25 142	95.24 409	98.10 415	74.96 430	99.90 137	99.53 49	98.85 216	97.70 415

TransMVSNet (Re)		97.15 336	96.58 342	98.86 241	99.12 309	98.85 193	99.49 192	98.91 363	95.48 374	97.16 390	99.80 121	93.38 290	99.11 362	94.16 390	91.73 409	98.62 347

UniMVSNet (Re)		98.29 205	98.00 223	99.13 197	99.00 333	99.36 117	99.49 192	99.51 131	97.95 188	98.97 271	99.13 354	96.30 169	99.38 308	98.36 205	93.34 394	98.66 334

EPMVS		97.82 273	97.65 264	98.35 305	98.88 351	95.98 358	99.49 192	94.71 439	97.57 234	99.26 213	99.48 279	92.46 320	99.71 245	97.87 246	99.08 199	99.35 233

SSC-MVS3.2		97.34 327	97.15 324	97.93 341	99.02 330	95.76 363	99.48 197	99.58 71	97.62 229	99.09 248	99.53 259	87.95 388	99.27 331	96.42 345	95.66 352	98.75 295

fmvsm_s_conf0.5_n_3		99.37 61	99.20 79	99.87 17	99.75 82	99.70 53	99.48 197	99.66 28	99.45 10	99.99 2	99.93 10	94.64 248	99.97 24	99.94 17	99.97 8	99.95 10

test_fmvsmconf_n		99.70 3	99.64 4	99.87 17	99.80 54	99.66 63	99.48 197	99.64 38	99.45 10	99.92 26	99.92 17	98.62 73	99.99 4	99.96 10	99.99 1	99.96 7

Anonymous20231211		97.88 258	97.54 276	98.90 229	99.71 106	98.53 224	99.48 197	99.57 76	94.16 395	98.81 296	99.68 196	93.23 292	99.42 304	98.84 139	94.42 378	98.76 293

v1240		97.69 296	97.32 312	98.79 253	98.85 358	98.43 238	99.48 197	99.36 261	96.11 362	99.27 208	99.36 313	93.76 286	99.24 337	94.46 384	95.23 362	98.70 308

VPNet		97.84 267	97.44 293	99.01 208	99.21 285	98.94 181	99.48 197	99.57 76	98.38 125	99.28 203	99.73 167	88.89 373	99.39 306	99.19 89	93.27 396	98.71 303

UniMVSNet_NR-MVSNet		98.22 208	97.97 226	98.96 215	98.92 346	98.98 168	99.48 197	99.53 111	97.76 212	98.71 307	99.46 286	96.43 165	99.22 342	98.57 180	92.87 402	98.69 312

TDRefinement		95.42 371	94.57 379	97.97 337	89.83 442	96.11 357	99.48 197	98.75 384	96.74 311	96.68 398	99.88 45	88.65 379	99.71 245	98.37 203	82.74 431	98.09 397

ACMMP_NAP		99.47 35	99.34 45	99.88 11	99.87 15	99.86 16	99.47 205	99.48 173	98.05 179	99.76 77	99.86 61	98.82 46	99.93 100	98.82 146	99.91 42	99.84 49

NR-MVSNet		97.97 247	97.61 270	99.02 207	98.87 354	99.26 133	99.47 205	99.42 231	97.63 227	97.08 392	99.50 270	95.07 219	99.13 357	97.86 247	93.59 391	98.68 317

PVSNet_Blended_VisFu		99.36 65	99.28 64	99.61 100	99.86 20	99.07 159	99.47 205	99.93 2	97.66 225	99.71 90	99.86 61	97.73 115	99.96 36	99.47 60	99.82 105	99.79 84

LuminaMVS		99.23 89	99.10 90	99.61 100	99.35 245	99.31 124	99.46 208	99.13 330	98.61 102	99.86 45	99.89 36	96.41 166	99.91 124	99.67 33	99.51 162	99.63 157

fmvsm_s_conf0.1_n_2		99.37 61	99.22 76	99.81 53	99.77 68	99.75 44	99.46 208	99.60 61	99.47 4	99.98 10	99.94 6	94.98 220	99.95 69	99.97 1	99.79 120	99.73 110

SD-MVS		99.41 54	99.52 12	99.05 204	99.74 90	99.68 56	99.46 208	99.52 116	99.11 39	99.88 36	99.91 23	99.43 1	97.70 421	98.72 154	99.93 29	99.77 92
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		97.28 330	96.76 339	98.82 247	99.37 241	98.07 256	99.45 211	99.36 261	97.56 236	97.89 370	98.95 375	83.70 415	98.82 395	96.03 353	98.56 234	99.58 173

tt0805		97.97 247	97.77 249	98.57 274	99.59 164	96.61 339	99.45 211	99.08 336	98.21 149	98.88 284	99.80 121	88.66 378	99.70 251	98.58 177	97.72 280	99.39 227

tpm2		97.44 322	97.34 308	97.74 358	99.15 307	94.36 399	99.45 211	98.94 354	93.45 404	98.90 281	99.44 289	91.35 345	99.59 280	97.31 299	98.07 266	99.29 240

FMVSNet2		97.72 291	97.36 303	98.80 252	99.51 189	98.84 194	99.45 211	99.42 231	96.49 332	98.86 291	99.29 333	90.26 357	98.98 378	96.44 344	96.56 326	98.58 361

CDS-MVSNet		99.09 123	99.03 103	99.25 181	99.42 223	98.73 205	99.45 211	99.46 203	98.11 165	99.46 157	99.77 149	98.01 108	99.37 311	98.70 156	98.92 211	99.66 141
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MAR-MVS		98.86 152	98.63 166	99.54 114	99.37 241	99.66 63	99.45 211	99.54 98	96.61 323	99.01 262	99.40 301	97.09 135	99.86 164	97.68 270	99.53 161	99.10 255
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
fmvsm_s_conf0.5_n_2		99.32 72	99.13 86	99.89 8	99.80 54	99.77 41	99.44 217	99.58 71	99.47 4	99.99 2	99.93 10	94.04 273	99.96 36	99.96 10	99.93 29	99.93 19

UGNet		98.87 149	98.69 158	99.40 151	99.22 284	98.72 206	99.44 217	99.68 20	99.24 26	99.18 233	99.42 293	92.74 305	99.96 36	99.34 73	99.94 27	99.53 188
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		98.86 152	98.63 166	99.54 114	99.64 143	99.19 139	99.44 217	99.54 98	97.77 211	99.30 199	99.81 107	94.20 266	99.93 100	99.17 93	98.82 219	99.49 202

test_0402		96.64 348	96.24 350	97.85 348	98.85 358	96.43 345	99.44 217	99.26 309	93.52 401	96.98 394	99.52 263	88.52 382	99.20 349	92.58 409	97.50 297	97.93 410

ACMP	97.20 11	98.06 227	97.94 231	98.45 293	99.37 241	97.01 316	99.44 217	99.49 161	97.54 240	98.45 339	99.79 133	91.95 329	99.72 239	97.91 242	97.49 300	98.62 347
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
GG-mvs-BLEND				98.45 293	98.55 395	98.16 249	99.43 222	93.68 441		97.23 386	98.46 399	89.30 369	99.22 342	95.43 369	98.22 255	97.98 407

HPM-MVS++		99.39 59	99.23 75	99.87 17	99.75 82	99.84 18	99.43 222	99.51 131	98.68 98	99.27 208	99.53 259	98.64 72	99.96 36	98.44 196	99.80 113	99.79 84

tpm cat1		97.39 324	97.36 303	97.50 369	99.17 301	93.73 405	99.43 222	99.31 294	91.27 415	98.71 307	99.08 358	94.31 264	99.77 220	96.41 347	98.50 238	99.00 271

tpm		97.67 302	97.55 273	98.03 330	99.02 330	95.01 384	99.43 222	98.54 403	96.44 338	99.12 240	99.34 320	91.83 332	99.60 279	97.75 261	96.46 328	99.48 203

GBi-Net		97.68 299	97.48 282	98.29 311	99.51 189	97.26 298	99.43 222	99.48 173	96.49 332	99.07 251	99.32 328	90.26 357	98.98 378	97.10 312	96.65 323	98.62 347

test1		97.68 299	97.48 282	98.29 311	99.51 189	97.26 298	99.43 222	99.48 173	96.49 332	99.07 251	99.32 328	90.26 357	98.98 378	97.10 312	96.65 323	98.62 347

FMVSNet1		96.84 344	96.36 348	98.29 311	99.32 258	97.26 298	99.43 222	99.48 173	95.11 379	98.55 333	99.32 328	83.95 414	98.98 378	95.81 358	96.26 334	98.62 347

fmvsm_s_conf0.5_n_7		99.34 68	99.29 61	99.48 137	99.70 111	98.63 214	99.42 229	99.63 42	99.46 7	99.98 10	99.88 45	95.59 197	99.96 36	99.97 1	99.98 4	99.85 42

fmvsm_s_conf0.5_n_5		99.37 61	99.21 77	99.86 28	99.80 54	99.68 56	99.42 229	99.61 54	99.37 20	99.97 21	99.86 61	94.96 221	99.99 4	99.97 1	99.93 29	99.92 20

mamv4		99.33 70	99.42 27	99.07 200	99.67 123	97.73 276	99.42 229	99.60 61	98.15 156	99.94 24	99.91 23	98.42 88	99.94 82	99.72 28	99.96 14	99.54 182

testgi		97.65 304	97.50 280	98.13 326	99.36 244	96.45 344	99.42 229	99.48 173	97.76 212	97.87 371	99.45 288	91.09 349	98.81 396	94.53 383	98.52 237	99.13 254

F-COLMAP		99.19 92	99.04 100	99.64 92	99.78 60	99.27 132	99.42 229	99.54 98	97.29 267	99.41 172	99.59 235	98.42 88	99.93 100	98.19 219	99.69 141	99.73 110

Anonymous202405211		98.30 204	97.98 225	99.26 180	99.57 168	98.16 249	99.41 234	98.55 402	96.03 367	99.19 229	99.74 161	91.87 330	99.92 112	99.16 94	98.29 251	99.70 129

MSLP-MVS++		99.46 37	99.47 21	99.44 148	99.60 162	99.16 144	99.41 234	99.71 13	98.98 61	99.45 158	99.78 140	99.19 9	99.54 285	99.28 81	99.84 92	99.63 157

VNet		99.11 118	98.90 131	99.73 74	99.52 186	99.56 86	99.41 234	99.39 244	99.01 53	99.74 81	99.78 140	95.56 198	99.92 112	99.52 51	98.18 260	99.72 118

baseline2		97.87 260	97.55 273	98.82 247	99.18 293	98.02 258	99.41 234	96.58 433	96.97 297	96.51 399	99.17 349	93.43 289	99.57 281	97.71 266	99.03 203	98.86 281

DU-MVS		98.08 225	97.79 244	98.96 215	98.87 354	98.98 168	99.41 234	99.45 214	97.87 196	98.71 307	99.50 270	94.82 230	99.22 342	98.57 180	92.87 402	98.68 317

Baseline_NR-MVSNet		97.76 281	97.45 288	98.68 264	99.09 317	98.29 243	99.41 234	98.85 372	95.65 372	98.63 325	99.67 202	94.82 230	99.10 364	98.07 233	92.89 401	98.64 338

XVG-ACMP-BASELINE		97.83 270	97.71 258	98.20 319	99.11 311	96.33 348	99.41 234	99.52 116	98.06 177	99.05 258	99.50 270	89.64 367	99.73 235	97.73 263	97.38 309	98.53 364

DP-MVS		99.16 98	98.95 124	99.78 62	99.77 68	99.53 93	99.41 234	99.50 151	97.03 294	99.04 259	99.88 45	97.39 121	99.92 112	98.66 163	99.90 51	99.87 36

9.14			99.10 90		99.72 101		99.40 242	99.51 131	97.53 241	99.64 117	99.78 140	98.84 44	99.91 124	97.63 271	99.82 105

D2MVS		98.41 193	98.50 183	98.15 325	99.26 272	96.62 338	99.40 242	99.61 54	97.71 217	98.98 269	99.36 313	96.04 176	99.67 259	98.70 156	97.41 307	98.15 394

Anonymous20240529		98.09 223	97.68 261	99.34 159	99.66 134	98.44 237	99.40 242	99.43 229	93.67 399	99.22 220	99.89 36	90.23 360	99.93 100	99.26 85	98.33 246	99.66 141

FMVSNet3		98.03 235	97.76 253	98.84 245	99.39 236	98.98 168	99.40 242	99.38 252	96.67 316	99.07 251	99.28 335	92.93 298	98.98 378	97.10 312	96.65 323	98.56 363

LFMVS		97.90 256	97.35 305	99.54 114	99.52 186	99.01 166	99.39 246	98.24 409	97.10 286	99.65 112	99.79 133	84.79 410	99.91 124	99.28 81	98.38 243	99.69 131

HQP_MVS		98.27 207	98.22 200	98.44 296	99.29 264	96.97 320	99.39 246	99.47 194	98.97 64	99.11 242	99.61 230	92.71 308	99.69 256	97.78 255	97.63 283	98.67 325

plane_prior2							99.39 246		98.97 64

CHOSEN 1792x2688		99.19 92	99.10 90	99.45 144	99.89 8	98.52 228	99.39 246	99.94 1	98.73 91	99.11 242	99.89 36	95.50 200	99.94 82	99.50 53	99.97 8	99.89 25

PAPM_NR		99.04 131	98.84 143	99.66 82	99.74 90	99.44 107	99.39 246	99.38 252	97.70 220	99.28 203	99.28 335	98.34 93	99.85 170	96.96 322	99.45 167	99.69 131

gg-mvs-nofinetune		96.17 358	95.32 370	98.73 257	98.79 364	98.14 251	99.38 251	94.09 440	91.07 418	98.07 362	91.04 438	89.62 368	99.35 318	96.75 332	99.09 198	98.68 317

VDDNet		97.55 310	97.02 331	99.16 192	99.49 203	98.12 254	99.38 251	99.30 299	95.35 375	99.68 96	99.90 30	82.62 420	99.93 100	99.31 77	98.13 264	99.42 221

MVS_0304		99.15 101	98.96 122	99.73 74	98.92 346	99.37 114	99.37 253	96.92 426	99.51 2	99.66 105	99.78 140	96.69 151	99.97 24	99.84 24	99.97 8	99.84 49

pmmvs6		96.53 350	96.09 355	97.82 353	98.69 382	95.47 371	99.37 253	99.47 194	93.46 403	97.41 380	99.78 140	87.06 396	99.33 321	96.92 327	92.70 404	98.65 336

PM-MVS		92.96 390	92.23 394	95.14 398	95.61 429	89.98 424	99.37 253	98.21 411	94.80 388	95.04 414	97.69 419	65.06 434	97.90 417	94.30 385	89.98 419	97.54 419

WTY-MVS		99.06 128	98.88 136	99.61 100	99.62 152	99.16 144	99.37 253	99.56 81	98.04 180	99.53 145	99.62 226	96.84 145	99.94 82	98.85 136	98.49 239	99.72 118

IterMVS-LS		98.46 188	98.42 187	98.58 273	99.59 164	98.00 259	99.37 253	99.43 229	96.94 302	99.07 251	99.59 235	97.87 110	99.03 371	98.32 210	95.62 353	98.71 303
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
h-mvs33		97.70 295	97.28 317	98.97 214	99.70 111	97.27 296	99.36 258	99.45 214	98.94 67	99.66 105	99.64 215	94.93 224	99.99 4	99.48 58	84.36 428	99.65 145

DPE-MVS		99.46 37	99.32 49	99.91 3	99.78 60	99.88 8	99.36 258	99.51 131	98.73 91	99.88 36	99.84 79	98.72 64	99.96 36	98.16 223	99.87 69	99.88 31
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UnsupCasMVSNet_eth		96.44 352	96.12 353	97.40 372	98.65 385	95.65 364	99.36 258	99.51 131	97.13 280	96.04 406	98.99 370	88.40 383	98.17 410	96.71 334	90.27 417	98.40 379

sss		99.17 96	99.05 98	99.53 122	99.62 152	98.97 171	99.36 258	99.62 46	97.83 203	99.67 100	99.65 209	97.37 124	99.95 69	99.19 89	99.19 187	99.68 135

DeepC-MVS_fast	98.69 1	99.49 28	99.39 35	99.77 65	99.63 146	99.59 80	99.36 258	99.46 203	99.07 48	99.79 62	99.82 93	98.85 42	99.92 112	98.68 161	99.87 69	99.82 64
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 87	99.14 85	99.59 104	99.41 228	99.16 144	99.35 263	99.57 76	98.82 78	99.51 149	99.61 230	96.46 162	99.95 69	99.59 41	99.98 4	99.65 145

pmmvs-eth3d		95.34 373	94.73 376	97.15 376	95.53 431	95.94 359	99.35 263	99.10 333	95.13 377	93.55 419	97.54 420	88.15 387	97.91 416	94.58 382	89.69 420	97.61 416

MDTV_nov1_ep13_2view						95.18 381	99.35 263		96.84 307	99.58 134		95.19 215		97.82 252		99.46 214

VDD-MVS		97.73 289	97.35 305	98.88 234	99.47 211	97.12 304	99.34 266	98.85 372	98.19 151	99.67 100	99.85 68	82.98 418	99.92 112	99.49 57	98.32 250	99.60 165

COLMAP_ROB	97.56 6	98.86 152	98.75 152	99.17 191	99.88 11	98.53 224	99.34 266	99.59 67	97.55 237	98.70 313	99.89 36	95.83 187	99.90 137	98.10 225	99.90 51	99.08 260
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
myMVS_eth3d28		97.69 296	97.34 308	98.73 257	99.27 269	97.52 287	99.33 268	98.78 382	98.03 182	98.82 295	98.49 398	86.64 397	99.46 291	98.44 196	98.24 254	99.23 248

EGC-MVSNET		82.80 403	77.86 409	97.62 363	97.91 406	96.12 356	99.33 268	99.28 305	8.40 446	25.05 447	99.27 338	84.11 413	99.33 321	89.20 420	98.22 255	97.42 420

ETVMVS		97.50 315	96.90 335	99.29 174	99.23 280	98.78 203	99.32 270	98.90 365	97.52 243	98.56 332	98.09 416	84.72 411	99.69 256	97.86 247	97.88 273	99.39 227

FMVSNet5		96.43 353	96.19 352	97.15 376	99.11 311	95.89 360	99.32 270	99.52 116	94.47 394	98.34 345	99.07 359	87.54 393	97.07 426	92.61 408	95.72 350	98.47 370

dp		97.75 285	97.80 243	97.59 366	99.10 314	93.71 406	99.32 270	98.88 368	96.48 335	99.08 250	99.55 250	92.67 311	99.82 198	96.52 342	98.58 231	99.24 247

tpmvs		97.98 244	98.02 222	97.84 350	99.04 328	94.73 389	99.31 273	99.20 321	96.10 366	98.76 303	99.42 293	94.94 223	99.81 203	96.97 321	98.45 240	98.97 275

tpmrst		98.33 201	98.48 184	97.90 344	99.16 303	94.78 388	99.31 273	99.11 332	97.27 268	99.45 158	99.59 235	95.33 208	99.84 177	98.48 190	98.61 228	99.09 259

testing99		97.36 325	96.94 334	98.63 267	99.18 293	96.70 332	99.30 275	98.93 355	97.71 217	98.23 351	98.26 408	84.92 409	99.84 177	98.04 235	97.85 276	99.35 233

MP-MVS-pluss		99.37 61	99.20 79	99.88 11	99.90 4	99.87 15	99.30 275	99.52 116	97.18 276	99.60 130	99.79 133	98.79 50	99.95 69	98.83 142	99.91 42	99.83 59
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
NCCC		99.34 68	99.19 81	99.79 59	99.61 157	99.65 67	99.30 275	99.48 173	98.86 73	99.21 223	99.63 221	98.72 64	99.90 137	98.25 215	99.63 152	99.80 80

JIA-IIPM		97.50 315	97.02 331	98.93 221	98.73 376	97.80 274	99.30 275	98.97 351	91.73 414	98.91 279	94.86 432	95.10 218	99.71 245	97.58 275	97.98 268	99.28 241

BH-RMVSNet		98.41 193	98.08 214	99.40 151	99.41 228	98.83 197	99.30 275	98.77 383	97.70 220	98.94 276	99.65 209	92.91 301	99.74 229	96.52 342	99.55 160	99.64 152

testing11		97.50 315	97.10 328	98.71 261	99.20 287	96.91 324	99.29 280	98.82 375	97.89 194	98.21 354	98.40 402	85.63 404	99.83 190	98.45 195	98.04 267	99.37 231

Syy-MVS		97.09 339	97.14 325	96.95 384	99.00 333	92.73 415	99.29 280	99.39 244	97.06 290	97.41 380	98.15 411	93.92 279	98.68 401	91.71 411	98.34 244	99.45 217

myMVS_eth3d		96.89 342	96.37 347	98.43 298	99.00 333	97.16 302	99.29 280	99.39 244	97.06 290	97.41 380	98.15 411	83.46 417	98.68 401	95.27 373	98.34 244	99.45 217

MCST-MVS		99.43 48	99.30 57	99.82 50	99.79 58	99.74 47	99.29 280	99.40 241	98.79 84	99.52 147	99.62 226	98.91 37	99.90 137	98.64 165	99.75 130	99.82 64

LF4IMVS		97.52 312	97.46 287	97.70 360	98.98 339	95.55 367	99.29 280	98.82 375	98.07 173	98.66 316	99.64 215	89.97 362	99.61 278	97.01 317	96.68 322	97.94 409

hse-mvs2		97.50 315	97.14 325	98.59 270	99.49 203	97.05 311	99.28 285	99.22 317	98.94 67	99.66 105	99.42 293	94.93 224	99.65 267	99.48 58	83.80 430	99.08 260

OPM-MVS		98.19 212	98.10 210	98.45 293	98.88 351	97.07 309	99.28 285	99.38 252	98.57 106	99.22 220	99.81 107	92.12 325	99.66 262	98.08 230	97.54 292	98.61 356
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
diffmvs		99.14 104	99.02 108	99.51 131	99.61 157	98.96 175	99.28 285	99.49 161	98.46 116	99.72 88	99.71 174	96.50 160	99.88 155	99.31 77	99.11 194	99.67 138
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		98.86 152	98.80 146	99.03 206	99.76 72	98.79 201	99.28 285	99.91 3	97.42 256	99.67 100	99.37 310	97.53 118	99.88 155	98.98 112	97.29 312	98.42 376

OMC-MVS		99.08 125	99.04 100	99.20 188	99.67 123	98.22 247	99.28 285	99.52 116	98.07 173	99.66 105	99.81 107	97.79 113	99.78 218	97.79 254	99.81 108	99.60 165

testing222		97.16 335	96.50 344	99.16 192	99.16 303	98.47 236	99.27 290	98.66 398	97.71 217	98.23 351	98.15 411	82.28 423	99.84 177	97.36 297	97.66 282	99.18 251

AUN-MVS		96.88 343	96.31 349	98.59 270	99.48 210	97.04 314	99.27 290	99.22 317	97.44 253	98.51 335	99.41 297	91.97 328	99.66 262	97.71 266	83.83 429	99.07 265

pmmvs5		97.52 312	97.30 314	98.16 322	98.57 394	96.73 331	99.27 290	98.90 365	96.14 360	98.37 343	99.53 259	91.54 342	99.14 354	97.51 284	95.87 345	98.63 345

1314		98.68 176	98.54 181	99.11 198	98.89 350	98.65 211	99.27 290	99.49 161	96.89 304	97.99 364	99.56 247	97.72 116	99.83 190	97.74 262	99.27 182	98.84 283

MVS		97.28 330	96.55 343	99.48 137	98.78 367	98.95 178	99.27 290	99.39 244	83.53 432	98.08 359	99.54 255	96.97 142	99.87 161	94.23 388	99.16 188	99.63 157

BH-untuned		98.42 191	98.36 190	98.59 270	99.49 203	96.70 332	99.27 290	99.13 330	97.24 272	98.80 298	99.38 307	95.75 191	99.74 229	97.07 316	99.16 188	99.33 237

MDTV_nov1_ep13			98.32 194		99.11 311	94.44 396	99.27 290	98.74 387	97.51 244	99.40 177	99.62 226	94.78 234	99.76 224	97.59 274	98.81 221

DP-MVS Recon		99.12 112	98.95 124	99.65 86	99.74 90	99.70 53	99.27 290	99.57 76	96.40 342	99.42 168	99.68 196	98.75 58	99.80 210	97.98 238	99.72 136	99.44 219

PatchmatchNet		98.31 202	98.36 190	98.19 320	99.16 303	95.32 377	99.27 290	98.92 358	97.37 260	99.37 183	99.58 239	94.90 227	99.70 251	97.43 293	99.21 185	99.54 182
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thres200		97.61 307	97.28 317	98.62 268	99.64 143	98.03 257	99.26 299	98.74 387	97.68 222	99.09 248	98.32 406	91.66 339	99.81 203	92.88 404	98.22 255	98.03 401

CNVR-MVS		99.42 50	99.30 57	99.78 62	99.62 152	99.71 51	99.26 299	99.52 116	98.82 78	99.39 179	99.71 174	98.96 25	99.85 170	98.59 176	99.80 113	99.77 92

tt0320		95.71 368	95.07 372	97.62 363	99.05 326	95.02 383	99.25 301	99.52 116	86.81 427	97.97 366	99.72 171	83.58 416	99.15 352	96.38 348	93.35 393	98.68 317

1112_ss		98.98 140	98.77 150	99.59 104	99.68 121	99.02 164	99.25 301	99.48 173	97.23 273	99.13 238	99.58 239	96.93 144	99.90 137	98.87 129	98.78 222	99.84 49

TAPA-MVS	97.07 15	97.74 287	97.34 308	98.94 219	99.70 111	97.53 286	99.25 301	99.51 131	91.90 413	99.30 199	99.63 221	98.78 51	99.64 270	88.09 425	99.87 69	99.65 145
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
UWE-MVS-28		97.36 325	97.24 321	97.75 356	98.84 360	94.44 396	99.24 304	97.58 422	97.98 186	99.00 266	99.00 368	91.35 345	99.53 286	93.75 393	98.39 242	99.27 245

UBG		97.85 263	97.48 282	98.95 217	99.25 276	97.64 283	99.24 304	98.74 387	97.90 193	98.64 323	98.20 410	88.65 379	99.81 203	98.27 213	98.40 241	99.42 221

PLC	97.94 4	99.02 134	98.85 141	99.53 122	99.66 134	99.01 166	99.24 304	99.52 116	96.85 306	99.27 208	99.48 279	98.25 97	99.91 124	97.76 259	99.62 153	99.65 145
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test_post1							99.23 307				65.14 444	94.18 269	99.71 245	97.58 275

ADS-MVSNet2		98.02 237	98.07 217	97.87 346	99.33 251	95.19 380	99.23 307	99.08 336	96.24 350	99.10 245	99.67 202	94.11 270	98.93 390	96.81 330	99.05 201	99.48 203

ADS-MVSNet		98.20 211	98.08 214	98.56 277	99.33 251	96.48 343	99.23 307	99.15 327	96.24 350	99.10 245	99.67 202	94.11 270	99.71 245	96.81 330	99.05 201	99.48 203

EPNet_dtu		98.03 235	97.96 227	98.23 318	98.27 402	95.54 369	99.23 307	98.75 384	99.02 51	97.82 373	99.71 174	96.11 174	99.48 288	93.04 402	99.65 149	99.69 131
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		98.17 215	97.93 232	98.87 238	99.18 293	98.49 232	99.22 311	99.33 280	96.96 298	99.56 138	99.38 307	94.33 262	99.00 376	94.83 381	98.58 231	99.14 252

RPMNet		96.72 346	95.90 359	99.19 189	99.18 293	98.49 232	99.22 311	99.52 116	88.72 425	99.56 138	97.38 422	94.08 272	99.95 69	86.87 430	98.58 231	99.14 252

sc_t1		95.75 366	95.05 373	97.87 346	98.83 361	94.61 393	99.21 313	99.45 214	87.45 426	97.97 366	99.85 68	81.19 426	99.43 302	98.27 213	93.20 397	99.57 176

WBMVS		97.74 287	97.50 280	98.46 291	99.24 278	97.43 290	99.21 313	99.42 231	97.45 250	98.96 273	99.41 297	88.83 374	99.23 338	98.94 117	96.02 338	98.71 303

plane_prior						96.97 320	99.21 313		98.45 118						97.60 286

tt0320-xc		95.31 374	94.59 378	97.45 370	98.92 346	94.73 389	99.20 316	99.31 294	86.74 428	97.23 386	99.72 171	81.14 427	98.95 388	97.08 315	91.98 408	98.67 325

testing91		97.44 322	97.02 331	98.71 261	99.18 293	96.89 326	99.19 317	99.04 343	97.78 210	98.31 346	98.29 407	85.41 406	99.85 170	98.01 236	97.95 269	99.39 227

WR-MVS		98.06 227	97.73 256	99.06 202	98.86 357	99.25 135	99.19 317	99.35 268	97.30 266	98.66 316	99.43 291	93.94 277	99.21 347	98.58 177	94.28 380	98.71 303

new-patchmatchnet		94.48 382	94.08 383	95.67 397	95.08 434	92.41 416	99.18 319	99.28 305	94.55 393	93.49 420	97.37 423	87.86 391	97.01 427	91.57 412	88.36 422	97.61 416

AdaColmap		99.01 138	98.80 146	99.66 82	99.56 172	99.54 90	99.18 319	99.70 15	98.18 154	99.35 189	99.63 221	96.32 168	99.90 137	97.48 287	99.77 125	99.55 180

EG-PatchMatch MVS		95.97 362	95.69 363	96.81 388	97.78 409	92.79 414	99.16 321	98.93 355	96.16 357	94.08 417	99.22 344	82.72 419	99.47 289	95.67 364	97.50 297	98.17 392

PatchT		97.03 340	96.44 346	98.79 253	98.99 336	98.34 242	99.16 321	99.07 339	92.13 412	99.52 147	97.31 425	94.54 254	98.98 378	88.54 423	98.73 224	99.03 268

CNLPA		99.14 104	98.99 114	99.59 104	99.58 166	99.41 111	99.16 321	99.44 223	98.45 118	99.19 229	99.49 273	98.08 105	99.89 150	97.73 263	99.75 130	99.48 203

MDA-MVSNet-bldmvs		94.96 377	93.98 384	97.92 342	98.24 403	97.27 296	99.15 324	99.33 280	93.80 398	80.09 439	99.03 364	88.31 384	97.86 418	93.49 397	94.36 379	98.62 347

CDPH-MVS		99.13 106	98.91 130	99.80 56	99.75 82	99.71 51	99.15 324	99.41 234	96.60 326	99.60 130	99.55 250	98.83 45	99.90 137	97.48 287	99.83 101	99.78 90

save fliter					99.76 72	99.59 80	99.14 326	99.40 241	99.00 56

WB-MVSnew		97.65 304	97.65 264	97.63 362	98.78 367	97.62 284	99.13 327	98.33 406	97.36 261	99.07 251	98.94 376	95.64 196	99.15 352	92.95 403	98.68 226	96.12 430

testf1		90.42 397	90.68 398	89.65 417	97.78 409	73.97 445	99.13 327	98.81 377	89.62 420	91.80 428	98.93 377	62.23 437	98.80 397	86.61 431	91.17 411	96.19 428

APD_test2		90.42 397	90.68 398	89.65 417	97.78 409	73.97 445	99.13 327	98.81 377	89.62 420	91.80 428	98.93 377	62.23 437	98.80 397	86.61 431	91.17 411	96.19 428

xiu_mvs_v1_base_debu		99.29 77	99.27 67	99.34 159	99.63 146	98.97 171	99.12 330	99.51 131	98.86 73	99.84 48	99.47 282	98.18 100	99.99 4	99.50 53	99.31 179	99.08 260

xiu_mvs_v1_base		99.29 77	99.27 67	99.34 159	99.63 146	98.97 171	99.12 330	99.51 131	98.86 73	99.84 48	99.47 282	98.18 100	99.99 4	99.50 53	99.31 179	99.08 260

xiu_mvs_v1_base_debi		99.29 77	99.27 67	99.34 159	99.63 146	98.97 171	99.12 330	99.51 131	98.86 73	99.84 48	99.47 282	98.18 100	99.99 4	99.50 53	99.31 179	99.08 260

XVG-OURS-SEG-HR		98.69 175	98.62 171	98.89 232	99.71 106	97.74 275	99.12 330	99.54 98	98.44 121	99.42 168	99.71 174	94.20 266	99.92 112	98.54 187	98.90 213	99.00 271

jason		99.13 106	99.03 103	99.45 144	99.46 213	98.87 189	99.12 330	99.26 309	98.03 182	99.79 62	99.65 209	97.02 140	99.85 170	99.02 109	99.90 51	99.65 145
jason: jason.
N_pmnet		94.95 378	95.83 361	92.31 408	98.47 398	79.33 440	99.12 330	92.81 446	93.87 397	97.68 376	99.13 354	93.87 281	99.01 375	91.38 413	96.19 335	98.59 360

MDA-MVSNet_test_wron		95.45 370	94.60 377	98.01 333	98.16 404	97.21 301	99.11 336	99.24 314	93.49 402	80.73 438	98.98 372	93.02 296	98.18 409	94.22 389	94.45 377	98.64 338

Patchmtry		97.75 285	97.40 300	98.81 250	99.10 314	98.87 189	99.11 336	99.33 280	94.83 387	98.81 296	99.38 307	94.33 262	99.02 373	96.10 351	95.57 355	98.53 364

YYNet1		95.36 372	94.51 380	97.92 342	97.89 407	97.10 305	99.10 338	99.23 315	93.26 405	80.77 437	99.04 363	92.81 302	98.02 413	94.30 385	94.18 382	98.64 338

CANet_DTU		98.97 142	98.87 137	99.25 181	99.33 251	98.42 240	99.08 339	99.30 299	99.16 29	99.43 165	99.75 156	95.27 210	99.97 24	98.56 183	99.95 19	99.36 232

SCA		98.19 212	98.16 202	98.27 316	99.30 260	95.55 367	99.07 340	98.97 351	97.57 234	99.43 165	99.57 244	92.72 306	99.74 229	97.58 275	99.20 186	99.52 189

TSAR-MVS + GP.		99.36 65	99.36 41	99.36 157	99.67 123	98.61 218	99.07 340	99.33 280	99.00 56	99.82 55	99.81 107	99.06 16	99.84 177	99.09 101	99.42 169	99.65 145

MG-MVS		99.13 106	99.02 108	99.45 144	99.57 168	98.63 214	99.07 340	99.34 273	98.99 58	99.61 127	99.82 93	97.98 109	99.87 161	97.00 318	99.80 113	99.85 42

PatchMatch-RL		98.84 162	98.62 171	99.52 128	99.71 106	99.28 130	99.06 343	99.77 9	97.74 215	99.50 150	99.53 259	95.41 203	99.84 177	97.17 311	99.64 150	99.44 219

OpenMVS_ROB	92.34 20	94.38 383	93.70 389	96.41 393	97.38 415	93.17 412	99.06 343	98.75 384	86.58 429	94.84 415	98.26 408	81.53 424	99.32 323	89.01 421	97.87 274	96.76 423

TEST9					99.67 123	99.65 67	99.05 345	99.41 234	96.22 352	98.95 274	99.49 273	98.77 54	99.91 124

train_agg		99.02 134	98.77 150	99.77 65	99.67 123	99.65 67	99.05 345	99.41 234	96.28 346	98.95 274	99.49 273	98.76 55	99.91 124	97.63 271	99.72 136	99.75 98

lupinMVS		99.13 106	99.01 112	99.46 143	99.51 189	98.94 181	99.05 345	99.16 326	97.86 197	99.80 60	99.56 247	97.39 121	99.86 164	98.94 117	99.85 84	99.58 173

DELS-MVS		99.48 32	99.42 27	99.65 86	99.72 101	99.40 112	99.05 345	99.66 28	99.14 32	99.57 137	99.80 121	98.46 84	99.94 82	99.57 44	99.84 92	99.60 165
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		96.38 354	96.03 356	97.41 371	98.13 405	95.16 382	99.05 345	99.20 321	93.94 396	97.39 383	98.79 388	91.61 341	99.04 369	90.43 416	95.77 347	98.05 400

Patchmatch-test		97.93 250	97.65 264	98.77 255	99.18 293	97.07 309	99.03 350	99.14 329	96.16 357	98.74 304	99.57 244	94.56 251	99.72 239	93.36 398	99.11 194	99.52 189

test_8					99.67 123	99.61 77	99.03 350	99.41 234	96.28 346	98.93 277	99.48 279	98.76 55	99.91 124

Test_1112_low_res		98.89 147	98.66 163	99.57 109	99.69 116	98.95 178	99.03 350	99.47 194	96.98 296	99.15 236	99.23 343	96.77 148	99.89 150	98.83 142	98.78 222	99.86 38

IterMVS-SCA-FT		97.82 273	97.75 254	98.06 329	99.57 168	96.36 347	99.02 353	99.49 161	97.18 276	98.71 307	99.72 171	92.72 306	99.14 354	97.44 292	95.86 346	98.67 325

xiu_mvs_v2_base		99.26 83	99.25 71	99.29 174	99.53 180	98.91 186	99.02 353	99.45 214	98.80 83	99.71 90	99.26 340	98.94 32	99.98 15	99.34 73	99.23 184	98.98 274

MIMVSNet		97.73 289	97.45 288	98.57 274	99.45 219	97.50 288	99.02 353	98.98 350	96.11 362	99.41 172	99.14 353	90.28 356	98.74 399	95.74 360	98.93 209	99.47 209

IterMVS		97.83 270	97.77 249	98.02 332	99.58 166	96.27 351	99.02 353	99.48 173	97.22 274	98.71 307	99.70 178	92.75 303	99.13 357	97.46 290	96.00 340	98.67 325
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		99.11 118	98.92 127	99.65 86	99.90 4	99.37 114	99.02 353	99.91 3	97.67 224	99.59 133	99.75 156	95.90 185	99.73 235	99.53 49	99.02 205	99.86 38

UWE-MVS		97.58 309	97.29 316	98.48 285	99.09 317	96.25 352	99.01 358	96.61 432	97.86 197	99.19 229	99.01 367	88.72 375	99.90 137	97.38 296	98.69 225	99.28 241

新几何2							99.01 358

BH-w/o		98.00 242	97.89 238	98.32 308	99.35 245	96.20 354	99.01 358	98.90 365	96.42 340	98.38 342	99.00 368	95.26 212	99.72 239	96.06 352	98.61 228	99.03 268

test_prior4						99.56 86	98.99 361

无先验							98.99 361	99.51 131	96.89 304				99.93 100	97.53 283		99.72 118

pmmvs4		98.13 219	97.90 234	98.81 250	98.61 390	98.87 189	98.99 361	99.21 320	96.44 338	99.06 256	99.58 239	95.90 185	99.11 362	97.18 310	96.11 337	98.46 373

HQP-NCC					99.19 290		98.98 364		98.24 143	98.66 316

ACMP_Plane					99.19 290		98.98 364		98.24 143	98.66 316

HQP-MVS		98.02 237	97.90 234	98.37 304	99.19 290	96.83 327	98.98 364	99.39 244	98.24 143	98.66 316	99.40 301	92.47 317	99.64 270	97.19 308	97.58 288	98.64 338

PS-MVSNAJ		99.32 72	99.32 49	99.30 171	99.57 168	98.94 181	98.97 367	99.46 203	98.92 70	99.71 90	99.24 342	99.01 18	99.98 15	99.35 68	99.66 147	98.97 275

MVP-Stereo		97.81 275	97.75 254	97.99 336	97.53 413	96.60 340	98.96 368	98.85 372	97.22 274	97.23 386	99.36 313	95.28 209	99.46 291	95.51 366	99.78 122	97.92 411
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test_prior2							98.96 368		98.34 131	99.01 262	99.52 263	98.68 67		97.96 239	99.74 133

旧先验2							98.96 368		96.70 314	99.47 155			99.94 82	98.19 219

原ACMM2							98.95 371

MVS_111021_HR		99.41 54	99.32 49	99.66 82	99.72 101	99.47 104	98.95 371	99.85 6	98.82 78	99.54 143	99.73 167	98.51 81	99.74 229	98.91 123	99.88 66	99.77 92

mvsany_test1		99.50 26	99.46 24	99.62 99	99.61 157	99.09 154	98.94 373	99.48 173	99.10 40	99.96 23	99.91 23	98.85 42	99.96 36	99.72 28	99.58 157	99.82 64

MVS_111021_LR		99.41 54	99.33 47	99.65 86	99.77 68	99.51 98	98.94 373	99.85 6	98.82 78	99.65 112	99.74 161	98.51 81	99.80 210	98.83 142	99.89 62	99.64 152

pmmvs3		94.09 385	93.25 391	96.60 391	94.76 436	94.49 395	98.92 375	98.18 413	89.66 419	96.48 400	98.06 417	86.28 400	97.33 424	89.68 419	87.20 425	97.97 408

XVG-OURS		98.73 173	98.68 159	98.88 234	99.70 111	97.73 276	98.92 375	99.55 89	98.52 111	99.45 158	99.84 79	95.27 210	99.91 124	98.08 230	98.84 217	99.00 271

test222					99.75 82	99.49 100	98.91 377	99.49 161	96.42 340	99.34 192	99.65 209	98.28 96			99.69 141	99.72 118

PMMVS2		86.87 400	85.37 404	91.35 412	90.21 441	83.80 431	98.89 378	97.45 424	83.13 433	91.67 430	95.03 430	48.49 443	94.70 436	85.86 433	77.62 435	95.54 431

miper_lstm_enhance		98.00 242	97.91 233	98.28 315	99.34 250	97.43 290	98.88 379	99.36 261	96.48 335	98.80 298	99.55 250	95.98 178	98.91 391	97.27 301	95.50 358	98.51 366

MVS-HIRNet		95.75 366	95.16 371	97.51 368	99.30 260	93.69 407	98.88 379	95.78 434	85.09 431	98.78 301	92.65 434	91.29 347	99.37 311	94.85 380	99.85 84	99.46 214

TR-MVS		97.76 281	97.41 299	98.82 247	99.06 323	97.87 270	98.87 381	98.56 401	96.63 322	98.68 315	99.22 344	92.49 316	99.65 267	95.40 370	97.79 278	98.95 279

testdata1							98.85 382		98.32 134

ET-MVSNet_ETH3D		96.49 351	95.64 365	99.05 204	99.53 180	98.82 198	98.84 383	97.51 423	97.63 227	84.77 432	99.21 347	92.09 326	98.91 391	98.98 112	92.21 407	99.41 224

our_test_3		97.65 304	97.68 261	97.55 367	98.62 388	94.97 385	98.84 383	99.30 299	96.83 309	98.19 355	99.34 320	97.01 141	99.02 373	95.00 378	96.01 339	98.64 338

MS-PatchMatch		97.24 334	97.32 312	96.99 381	98.45 399	93.51 410	98.82 385	99.32 290	97.41 257	98.13 358	99.30 331	88.99 372	99.56 282	95.68 363	99.80 113	97.90 412

c3_l		98.12 221	98.04 219	98.38 303	99.30 260	97.69 282	98.81 386	99.33 280	96.67 316	98.83 293	99.34 320	97.11 134	98.99 377	97.58 275	95.34 360	98.48 368

ppachtmachnet_test		97.49 320	97.45 288	97.61 365	98.62 388	95.24 378	98.80 387	99.46 203	96.11 362	98.22 353	99.62 226	96.45 163	98.97 385	93.77 392	95.97 344	98.61 356

PAPR		98.63 182	98.34 192	99.51 131	99.40 233	99.03 163	98.80 387	99.36 261	96.33 343	99.00 266	99.12 357	98.46 84	99.84 177	95.23 374	99.37 178	99.66 141

test0.0.03 1		97.71 294	97.42 298	98.56 277	98.41 401	97.82 273	98.78 389	98.63 399	97.34 262	98.05 363	98.98 372	94.45 259	98.98 378	95.04 377	97.15 318	98.89 280

PVSNet_Blended		99.08 125	98.97 118	99.42 149	99.76 72	98.79 201	98.78 389	99.91 3	96.74 311	99.67 100	99.49 273	97.53 118	99.88 155	98.98 112	99.85 84	99.60 165

PMMVS		98.80 166	98.62 171	99.34 159	99.27 269	98.70 207	98.76 391	99.31 294	97.34 262	99.21 223	99.07 359	97.20 132	99.82 198	98.56 183	98.87 214	99.52 189

test123		39.01 412	42.50 414	28.53 427	39.17 450	20.91 452	98.75 392	19.17 452	19.83 445	38.57 444	66.67 442	33.16 447	15.42 446	37.50 446	29.66 444	49.26 441

MSDG		98.98 140	98.80 146	99.53 122	99.76 72	99.19 139	98.75 392	99.55 89	97.25 270	99.47 155	99.77 149	97.82 112	99.87 161	96.93 325	99.90 51	99.54 182

CLD-MVS		98.16 216	98.10 210	98.33 306	99.29 264	96.82 329	98.75 392	99.44 223	97.83 203	99.13 238	99.55 250	92.92 299	99.67 259	98.32 210	97.69 281	98.48 368
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		98.18 214	98.10 210	98.41 299	99.23 280	97.72 278	98.72 395	99.31 294	96.60 326	98.88 284	99.29 333	97.29 128	99.13 357	97.60 273	95.99 341	98.38 381

cl____		98.01 240	97.84 242	98.55 279	99.25 276	97.97 261	98.71 396	99.34 273	96.47 337	98.59 331	99.54 255	95.65 195	99.21 347	97.21 304	95.77 347	98.46 373

DIV-MVS_self_test		98.01 240	97.85 241	98.48 285	99.24 278	97.95 266	98.71 396	99.35 268	96.50 331	98.60 330	99.54 255	95.72 193	99.03 371	97.21 304	95.77 347	98.46 373

test-LLR		98.06 227	97.90 234	98.55 279	98.79 364	97.10 305	98.67 398	97.75 418	97.34 262	98.61 328	98.85 382	94.45 259	99.45 293	97.25 302	99.38 171	99.10 255

TESTMET0.1,1		97.55 310	97.27 320	98.40 301	98.93 344	96.53 341	98.67 398	97.61 421	96.96 298	98.64 323	99.28 335	88.63 381	99.45 293	97.30 300	99.38 171	99.21 250

test-mter		97.49 320	97.13 327	98.55 279	98.79 364	97.10 305	98.67 398	97.75 418	96.65 318	98.61 328	98.85 382	88.23 385	99.45 293	97.25 302	99.38 171	99.10 255

mvs5depth		96.66 347	96.22 351	97.97 337	97.00 424	96.28 350	98.66 401	99.03 345	96.61 323	96.93 396	99.79 133	87.20 395	99.47 289	96.65 340	94.13 383	98.16 393

IB-MVS	95.67 18	96.22 355	95.44 369	98.57 274	99.21 285	96.70 332	98.65 402	97.74 420	96.71 313	97.27 385	98.54 397	86.03 401	99.92 112	98.47 193	86.30 426	99.10 255
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		98.95 143	98.71 156	99.66 82	99.63 146	99.55 88	98.64 403	99.10 333	97.93 190	99.42 168	99.55 250	98.67 69	99.80 210	95.80 359	99.68 144	99.61 162

thisisatest0515		98.14 218	97.79 244	99.19 189	99.50 201	98.50 231	98.61 404	96.82 428	96.95 300	99.54 143	99.43 291	91.66 339	99.86 164	98.08 230	99.51 162	99.22 249

DeepPCF-MVS	98.18 3	98.81 163	99.37 39	97.12 379	99.60 162	91.75 419	98.61 404	99.44 223	99.35 21	99.83 54	99.85 68	98.70 66	99.81 203	99.02 109	99.91 42	99.81 71

cl22		97.85 263	97.64 267	98.48 285	99.09 317	97.87 270	98.60 406	99.33 280	97.11 285	98.87 287	99.22 344	92.38 322	99.17 351	98.21 217	95.99 341	98.42 376

GA-MVS		97.85 263	97.47 285	99.00 210	99.38 238	97.99 260	98.57 407	99.15 327	97.04 293	98.90 281	99.30 331	89.83 364	99.38 308	96.70 335	98.33 246	99.62 160

TinyColmap		97.12 337	96.89 336	97.83 351	99.07 321	95.52 370	98.57 407	98.74 387	97.58 233	97.81 374	99.79 133	88.16 386	99.56 282	95.10 375	97.21 315	98.39 380

eth_miper_zixun_eth		98.05 232	97.96 227	98.33 306	99.26 272	97.38 292	98.56 409	99.31 294	96.65 318	98.88 284	99.52 263	96.58 156	99.12 361	97.39 295	95.53 357	98.47 370

CMPMVS	69.68 23	94.13 384	94.90 375	91.84 409	97.24 419	80.01 439	98.52 410	99.48 173	89.01 423	91.99 426	99.67 202	85.67 403	99.13 357	95.44 368	97.03 320	96.39 427
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
USDC		97.34 327	97.20 322	97.75 356	99.07 321	95.20 379	98.51 411	99.04 343	97.99 185	98.31 346	99.86 61	89.02 371	99.55 284	95.67 364	97.36 310	98.49 367

ambc				93.06 407	92.68 438	82.36 432	98.47 412	98.73 393		95.09 413	97.41 421	55.55 439	99.10 364	96.42 345	91.32 410	97.71 413

miper_enhance_ethall		98.16 216	98.08 214	98.41 299	98.96 342	97.72 278	98.45 413	99.32 290	96.95 300	98.97 271	99.17 349	97.06 138	99.22 342	97.86 247	95.99 341	98.29 385

CHOSEN 280x420		99.12 112	99.13 86	99.08 199	99.66 134	97.89 269	98.43 414	99.71 13	98.88 72	99.62 124	99.76 153	96.63 153	99.70 251	99.46 61	99.99 1	99.66 141

testmvs		39.17 411	43.78 413	25.37 428	36.04 451	16.84 453	98.36 415	26.56 450	20.06 444	38.51 445	67.32 441	29.64 448	15.30 447	37.59 445	39.90 443	43.98 442

FPMVS		84.93 402	85.65 403	82.75 423	86.77 444	63.39 449	98.35 416	98.92 358	74.11 435	83.39 434	98.98 372	50.85 442	92.40 438	84.54 434	94.97 368	92.46 433

KD-MVS_2432*1600		94.62 379	93.72 387	97.31 373	97.19 421	95.82 361	98.34 417	99.20 321	95.00 383	97.57 377	98.35 404	87.95 388	98.10 411	92.87 405	77.00 436	98.01 402

miper_refine_blended		94.62 379	93.72 387	97.31 373	97.19 421	95.82 361	98.34 417	99.20 321	95.00 383	97.57 377	98.35 404	87.95 388	98.10 411	92.87 405	77.00 436	98.01 402

CL-MVSNet_self_test		94.49 381	93.97 385	96.08 395	96.16 426	93.67 408	98.33 419	99.38 252	95.13 377	97.33 384	98.15 411	92.69 310	96.57 429	88.67 422	79.87 434	97.99 406

PVSNet	96.02 17	98.85 159	98.84 143	98.89 232	99.73 97	97.28 295	98.32 420	99.60 61	97.86 197	99.50 150	99.57 244	96.75 149	99.86 164	98.56 183	99.70 140	99.54 182

PAPM		97.59 308	97.09 329	99.07 200	99.06 323	98.26 245	98.30 421	99.10 333	94.88 385	98.08 359	99.34 320	96.27 170	99.64 270	89.87 418	98.92 211	99.31 239

Patchmatch-RL test		95.84 364	95.81 362	95.95 396	95.61 429	90.57 422	98.24 422	98.39 405	95.10 381	95.20 411	98.67 392	94.78 234	97.77 419	96.28 350	90.02 418	99.51 197

UnsupCasMVSNet_bld		93.53 387	92.51 393	96.58 392	97.38 415	93.82 403	98.24 422	99.48 173	91.10 417	93.10 421	96.66 427	74.89 431	98.37 406	94.03 391	87.71 424	97.56 418

LCM-MVSNet		86.80 401	85.22 405	91.53 411	87.81 443	80.96 437	98.23 424	98.99 349	71.05 436	90.13 431	96.51 428	48.45 444	96.88 428	90.51 415	85.30 427	96.76 423

cascas		97.69 296	97.43 297	98.48 285	98.60 391	97.30 294	98.18 425	99.39 244	92.96 407	98.41 340	98.78 389	93.77 285	99.27 331	98.16 223	98.61 228	98.86 281

kuosan		90.92 396	90.11 401	93.34 404	98.78 367	85.59 429	98.15 426	93.16 444	89.37 422	92.07 425	98.38 403	81.48 425	95.19 434	62.54 443	97.04 319	99.25 246

Effi-MVS+		98.81 163	98.59 177	99.48 137	99.46 213	99.12 152	98.08 427	99.50 151	97.50 245	99.38 181	99.41 297	96.37 167	99.81 203	99.11 97	98.54 236	99.51 197

PCF-MVS	97.08 14	97.66 303	97.06 330	99.47 141	99.61 157	99.09 154	98.04 428	99.25 311	91.24 416	98.51 335	99.70 178	94.55 253	99.91 124	92.76 407	99.85 84	99.42 221
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet_0	94.43 19	96.09 360	95.47 367	97.94 340	99.31 259	94.34 400	97.81 429	99.70 15	97.12 282	97.46 379	98.75 390	89.71 365	99.79 213	97.69 269	81.69 432	99.68 135

E-PMN		80.61 405	79.88 407	82.81 422	90.75 440	76.38 443	97.69 430	95.76 435	66.44 440	83.52 433	92.25 435	62.54 436	87.16 442	68.53 441	61.40 439	84.89 440

dongtai		93.26 388	92.93 392	94.25 400	99.39 236	85.68 428	97.68 431	93.27 442	92.87 408	96.85 397	99.39 305	82.33 422	97.48 423	76.78 436	97.80 277	99.58 173

ANet_high		77.30 407	74.86 411	84.62 421	75.88 447	77.61 441	97.63 432	93.15 445	88.81 424	64.27 442	89.29 439	36.51 446	83.93 444	75.89 438	52.31 441	92.33 435

EMVS		80.02 406	79.22 408	82.43 424	91.19 439	76.40 442	97.55 433	92.49 447	66.36 441	83.01 435	91.27 437	64.63 435	85.79 443	65.82 442	60.65 440	85.08 439

MVE	76.82 21	76.91 408	74.31 412	84.70 420	85.38 446	76.05 444	96.88 434	93.17 443	67.39 439	71.28 441	89.01 440	21.66 451	87.69 441	71.74 440	72.29 438	90.35 437
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		91.10 394	91.36 396	90.31 414	95.85 427	73.72 447	94.89 435	99.25 311	68.39 438	95.82 407	99.02 366	80.50 428	98.95 388	93.64 395	94.89 372	98.25 388

Gipuma		90.99 395	90.15 400	93.51 403	98.73 376	90.12 423	93.98 436	99.45 214	79.32 434	92.28 424	94.91 431	69.61 432	97.98 415	87.42 427	95.67 351	92.45 434
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	70.75 22	75.98 409	74.97 410	79.01 425	70.98 448	55.18 450	93.37 437	98.21 411	65.08 442	61.78 443	93.83 433	21.74 450	92.53 437	78.59 435	91.12 413	89.34 438
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		82.80 403	81.52 406	86.66 419	66.61 449	68.44 448	92.79 438	97.92 415	68.96 437	80.04 440	99.85 68	85.77 402	96.15 432	97.86 247	43.89 442	95.39 432

wuyk23d		40.18 410	41.29 415	36.84 426	86.18 445	49.12 451	79.73 439	22.81 451	27.64 443	25.46 446	28.45 446	21.98 449	48.89 445	55.80 444	23.56 445	12.51 443

mmdepth		0.02 417	0.03 420	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	0.27 448	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

monomultidepth		0.02 417	0.03 420	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	0.27 448	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

test_blank		0.13 416	0.17 419	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	1.57 447	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

uanet_test		0.02 417	0.03 420	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	0.27 448	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

DCPMVS		0.02 417	0.03 420	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	0.27 448	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

cdsmvs_eth3d_5k		24.64 413	32.85 416	0.00 429	0.00 452	0.00 454	0.00 440	99.51 131	0.00 447	0.00 448	99.56 247	96.58 156	0.00 448	0.00 447	0.00 446	0.00 444

pcd_1.5k_mvsjas		8.27 415	11.03 418	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	0.27 448	99.01 18	0.00 448	0.00 447	0.00 446	0.00 444

sosnet-low-res		0.02 417	0.03 420	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	0.27 448	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

sosnet		0.02 417	0.03 420	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	0.27 448	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

uncertanet		0.02 417	0.03 420	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	0.27 448	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

Regformer		0.02 417	0.03 420	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	0.27 448	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

ab-mvs-re		8.30 414	11.06 417	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	99.58 239	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

uanet		0.02 417	0.03 420	0.00 429	0.00 452	0.00 454	0.00 440	0.00 453	0.00 447	0.00 448	0.27 448	0.00 452	0.00 448	0.00 447	0.00 446	0.00 444

WAC-MVS						97.16 302								95.47 367

MSC_two_6792asdad				99.87 17	99.51 189	99.76 42		99.33 280					99.96 36	98.87 129	99.84 92	99.89 25

PC_three_1452									98.18 154	99.84 48	99.70 178	99.31 3	98.52 404	98.30 212	99.80 113	99.81 71

No_MVS				99.87 17	99.51 189	99.76 42		99.33 280					99.96 36	98.87 129	99.84 92	99.89 25

test_one_0601					99.81 48	99.88 8		99.49 161	98.97 64	99.65 112	99.81 107	99.09 14

eth-test2					0.00 452

eth-test					0.00 452

ZD-MVS					99.71 106	99.79 34		99.61 54	96.84 307	99.56 138	99.54 255	98.58 75	99.96 36	96.93 325	99.75 130

IU-MVS					99.84 32	99.88 8		99.32 290	98.30 136	99.84 48				98.86 134	99.85 84	99.89 25

test_241102_TWO								99.48 173	99.08 46	99.88 36	99.81 107	98.94 32	99.96 36	98.91 123	99.84 92	99.88 31

test_241102_ONE					99.84 32	99.90 2		99.48 173	99.07 48	99.91 27	99.74 161	99.20 7	99.76 224

test_0728_THIRD									98.99 58	99.81 56	99.80 121	99.09 14	99.96 36	98.85 136	99.90 51	99.88 31

GSMVS																99.52 189

test_part2					99.81 48	99.83 19				99.77 71

sam_mvs1												94.86 229				99.52 189

sam_mvs												94.72 241

MTGPA								99.47 194

test_post											65.99 443	94.65 247	99.73 235

patchmatchnet-post											98.70 391	94.79 233	99.74 229

gm-plane-assit					98.54 396	92.96 413			94.65 391		99.15 352		99.64 270	97.56 280

test9_res														97.49 286	99.72 136	99.75 98

agg_prior2														97.21 304	99.73 135	99.75 98

agg_prior					99.67 123	99.62 75		99.40 241		98.87 287			99.91 124

TestCases				99.31 166	99.86 20	98.48 234		99.61 54	97.85 200	99.36 186	99.85 68	95.95 180	99.85 170	96.66 338	99.83 101	99.59 169

test_prior				99.68 80	99.67 123	99.48 102		99.56 81					99.83 190			99.74 102

新几何1				99.75 68	99.75 82	99.59 80		99.54 98	96.76 310	99.29 202	99.64 215	98.43 86	99.94 82	96.92 327	99.66 147	99.72 118

旧先验1					99.74 90	99.59 80		99.54 98			99.69 189	98.47 83			99.68 144	99.73 110

原ACMM1				99.65 86	99.73 97	99.33 119		99.47 194	97.46 247	99.12 240	99.66 207	98.67 69	99.91 124	97.70 268	99.69 141	99.71 127

testdata2													99.95 69	96.67 337

segment_acmp												98.96 25

testdata				99.54 114	99.75 82	98.95 178		99.51 131	97.07 288	99.43 165	99.70 178	98.87 40	99.94 82	97.76 259	99.64 150	99.72 118

test12				99.75 68	99.64 143	99.61 77		99.29 303		99.21 223		98.38 91	99.89 150		99.74 133	99.74 102

plane_prior7					99.29 264	97.03 315

plane_prior6					99.27 269	96.98 319						92.71 308

plane_prior5								99.47 194					99.69 256	97.78 255	97.63 283	98.67 325

plane_prior4											99.61 230

plane_prior3						97.00 317			98.69 96	99.11 242

plane_prior1					99.26 272

n2								0.00 453

nn								0.00 453

door-mid								98.05 414

lessismore_v0				97.79 355	98.69 382	95.44 374		94.75 438		95.71 408	99.87 56	88.69 377	99.32 323	95.89 356	94.93 370	98.62 347

LGP-MVS_train				98.49 283	99.33 251	97.05 311		99.55 89	97.46 247	99.24 215	99.83 84	92.58 313	99.72 239	98.09 226	97.51 295	98.68 317

test11								99.35 268

door								97.92 415

HQP5-MVS						96.83 327

BP-MVS														97.19 308

HQP4-MVS										98.66 316			99.64 270			98.64 338

HQP3-MVS								99.39 244							97.58 288

HQP2-MVS												92.47 317

NP-MVS					99.23 280	96.92 323					99.40 301

ACMMP++_ref															97.19 316

ACMMP++															97.43 306

Test By Simon												98.75 58

ITE_SJBPF				98.08 328	99.29 264	96.37 346		98.92 358	98.34 131	98.83 293	99.75 156	91.09 349	99.62 277	95.82 357	97.40 308	98.25 388

DeepMVS_CX				93.34 404	99.29 264	82.27 433		99.22 317	85.15 430	96.33 401	99.05 362	90.97 351	99.73 235	93.57 396	97.77 279	98.01 402

High-resolution multi-view benchmark