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 31	99.48 22	99.54 125	99.76 82	99.42 118	99.90 1	99.55 100	98.56 118	99.78 81	99.70 214	98.65 74	99.79 243	99.65 41	99.78 134	99.41 262

mmtdpeth		96.95 379	96.71 378	97.67 401	99.33 289	94.90 428	99.89 2	99.28 345	98.15 175	99.72 102	98.57 435	86.56 439	99.90 148	99.82 29	89.02 462	98.20 432

SPE-MVS-test		99.49 33	99.48 22	99.54 125	99.78 70	99.30 138	99.89 2	99.58 78	98.56 118	99.73 97	99.69 225	98.55 81	99.82 225	99.69 35	99.85 94	99.48 241

MVSFormer		99.17 109	99.12 97	99.29 205	99.51 227	98.94 197	99.88 4	99.46 236	97.55 275	99.80 74	99.65 246	97.39 125	99.28 364	99.03 132	99.85 94	99.65 173

test_djsdf		98.67 212	98.57 213	98.98 243	98.70 419	98.91 204	99.88 4	99.46 236	97.55 275	99.22 256	99.88 55	95.73 221	99.28 364	99.03 132	97.62 323	98.75 333

OurMVSNet-221017-0		97.88 295	97.77 286	98.19 358	98.71 418	96.53 379	99.88 4	99.00 390	97.79 245	98.78 339	99.94 6	91.68 374	99.35 354	97.21 344	96.99 359	98.69 350

EC-MVSNet		99.44 50	99.39 40	99.58 116	99.56 206	99.49 109	99.88 4	99.58 78	98.38 137	99.73 97	99.69 225	98.20 103	99.70 284	99.64 43	99.82 117	99.54 217

DVP-MVS++		99.59 15	99.50 19	99.88 15	99.51 227	99.88 10	99.87 8	99.51 154	98.99 69	99.88 43	99.81 132	99.27 7	99.96 41	98.85 164	99.80 125	99.81 79

FOURS1					99.91 1	99.93 1	99.87 8	99.56 90	99.10 48	99.81 69

K. test v3		97.10 376	96.79 376	98.01 371	98.72 416	96.33 386	99.87 8	97.05 468	97.59 269	96.16 445	99.80 150	88.71 415	99.04 410	96.69 376	96.55 366	98.65 374

FC-MVSNet-test		98.75 205	98.62 206	99.15 227	99.08 358	99.45 115	99.86 11	99.60 67	98.23 165	98.70 351	99.82 117	96.80 162	99.22 379	99.07 127	96.38 369	98.79 323

v7n		97.87 297	97.52 315	98.92 254	98.76 412	98.58 251	99.84 12	99.46 236	96.20 392	98.91 316	99.70 214	94.89 259	99.44 334	96.03 393	93.89 427	98.75 333

DTE-MVSNet		97.51 352	97.19 361	98.46 329	98.63 426	98.13 284	99.84 12	99.48 202	96.68 354	97.97 407	99.67 239	92.92 337	98.56 444	96.88 369	92.60 445	98.70 346

3Dnovator	97.25 9	99.24 97	99.05 112	99.81 60	99.12 347	99.66 71	99.84 12	99.74 13	99.09 55	98.92 315	99.90 35	95.94 208	99.98 20	98.95 144	99.92 39	99.79 92

FIs		98.78 200	98.63 201	99.23 217	99.18 331	99.54 98	99.83 15	99.59 73	98.28 150	98.79 338	99.81 132	96.75 165	99.37 347	99.08 126	96.38 369	98.78 325

MGCFI-Net		99.01 164	98.85 172	99.50 149	99.42 261	99.26 144	99.82 16	99.48 202	98.60 115	99.28 238	98.81 424	97.04 147	99.76 255	99.29 93	97.87 312	99.47 247

test_fmvs3		92.10 434	91.77 437	93.08 449	96.19 466	86.25 469	99.82 16	98.62 442	96.65 357	95.19 453	96.90 469	55.05 483	95.93 476	96.63 381	90.92 454	97.06 465

jajsoiax		98.43 226	98.28 233	98.88 268	98.60 430	98.43 270	99.82 16	99.53 125	98.19 170	98.63 363	99.80 150	93.22 332	99.44 334	99.22 102	97.50 335	98.77 329

OpenMVS	96.50 16	98.47 223	98.12 244	99.52 139	99.04 366	99.53 101	99.82 16	99.72 14	94.56 432	98.08 400	99.88 55	94.73 272	99.98 20	97.47 328	99.76 140	99.06 304

SDMVSNet		99.11 139	98.90 158	99.75 77	99.81 57	99.59 88	99.81 20	99.65 39	98.78 98	99.64 142	99.88 55	94.56 284	99.93 110	99.67 37	98.26 290	99.72 135

nrg030		98.64 216	98.42 223	99.28 209	99.05 364	99.69 63	99.81 20	99.46 236	98.04 214	99.01 298	99.82 117	96.69 167	99.38 344	99.34 81	94.59 414	98.78 325

HPM-MVS		99.42 55	99.28 69	99.83 56	99.90 4	99.72 56	99.81 20	99.54 109	97.59 269	99.68 117	99.63 258	98.91 39	99.94 92	98.58 208	99.91 46	99.84 53
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EPP-MVSNet		99.13 125	98.99 136	99.53 133	99.65 158	99.06 171	99.81 20	99.33 320	97.43 292	99.60 157	99.88 55	97.14 138	99.84 196	99.13 117	98.94 239	99.69 152

3Dnovator+	97.12 13	99.18 104	98.97 140	99.82 57	99.17 339	99.68 64	99.81 20	99.51 154	99.20 33	98.72 344	99.89 44	95.68 223	99.97 29	98.86 162	99.86 87	99.81 79

sasdasda		99.02 160	98.86 169	99.51 144	99.42 261	99.32 131	99.80 25	99.48 202	98.63 110	99.31 230	98.81 424	97.09 143	99.75 258	99.27 97	97.90 309	99.47 247

FA-MVS(test-final)		98.75 205	98.53 217	99.41 178	99.55 210	99.05 173	99.80 25	99.01 389	96.59 367	99.58 161	99.59 272	95.39 233	99.90 148	97.78 292	99.49 177	99.28 279

GeoE		98.85 191	98.62 206	99.53 133	99.61 187	99.08 168	99.80 25	99.51 154	97.10 324	99.31 230	99.78 174	95.23 244	99.77 251	98.21 248	99.03 233	99.75 111

canonicalmvs		99.02 160	98.86 169	99.51 144	99.42 261	99.32 131	99.80 25	99.48 202	98.63 110	99.31 230	98.81 424	97.09 143	99.75 258	99.27 97	97.90 309	99.47 247

v8		97.95 286	97.63 305	98.93 252	98.95 381	98.81 229	99.80 25	99.41 272	96.03 406	99.10 281	99.42 330	94.92 256	99.30 362	96.94 364	94.08 424	98.66 372

Vis-MVSNet (Re-imp)		98.87 179	98.72 187	99.31 197	99.71 117	98.88 211	99.80 25	99.44 256	97.91 227	99.36 220	99.78 174	95.49 230	99.43 338	97.91 277	99.11 218	99.62 188

Anonymous20240521		96.20 395	95.89 398	97.13 419	97.72 451	94.96 427	99.79 31	99.29 343	93.01 447	97.20 430	99.03 403	89.69 405	98.36 448	91.16 455	96.13 375	98.07 439

PS-MVSNAJss		98.92 173	98.92 153	98.90 260	98.78 405	98.53 255	99.78 32	99.54 109	98.07 200	99.00 302	99.76 187	99.01 20	99.37 347	99.13 117	97.23 352	98.81 322

PEN-MVS		97.76 318	97.44 331	98.72 294	98.77 410	98.54 254	99.78 32	99.51 154	97.06 328	98.29 389	99.64 252	92.63 350	98.89 435	98.09 261	93.16 437	98.72 339

anonymousdsp		98.44 225	98.28 233	98.94 250	98.50 436	98.96 187	99.77 34	99.50 177	97.07 326	98.87 324	99.77 183	94.76 269	99.28 364	98.66 194	97.60 324	98.57 401

SixPastTwentyTwo		97.50 353	97.33 349	98.03 368	98.65 424	96.23 391	99.77 34	98.68 438	97.14 317	97.90 410	99.93 10	90.45 394	99.18 387	97.00 358	96.43 368	98.67 363

QAPM		98.67 212	98.30 232	99.80 64	99.20 325	99.67 68	99.77 34	99.72 14	94.74 429	98.73 343	99.90 35	95.78 219	99.98 20	96.96 362	99.88 76	99.76 107

SSC-MVS		92.73 433	93.73 427	89.72 459	95.02 477	81.38 479	99.76 37	99.23 356	94.87 426	92.80 466	98.93 416	94.71 274	91.37 483	74.49 482	93.80 428	96.42 469

test_vis3_rt		87.04 441	85.81 444	90.73 456	93.99 480	81.96 477	99.76 37	90.23 491	92.81 450	81.35 479	91.56 479	40.06 487	99.07 405	94.27 427	88.23 464	91.15 479

dcpmvs_2		99.23 98	99.58 9	98.16 360	99.83 47	94.68 433	99.76 37	99.52 132	99.07 58	99.98 13	99.88 55	98.56 80	99.93 110	99.67 37	99.98 4	99.87 40

RRT-MVS		98.91 174	98.75 183	99.39 184	99.46 251	98.61 249	99.76 37	99.50 177	98.06 204	99.81 69	99.88 55	93.91 316	99.94 92	99.11 120	99.27 194	99.61 190

HPM-MVS_fast		99.51 29	99.40 38	99.85 43	99.91 1	99.79 41	99.76 37	99.56 90	97.72 254	99.76 91	99.75 192	99.13 14	99.92 123	99.07 127	99.92 39	99.85 46

lecture		99.60 14	99.50 19	99.89 11	99.89 8	99.90 3	99.75 42	99.59 73	99.06 61	99.88 43	99.85 83	98.41 93	99.96 41	99.28 94	99.84 102	99.83 63

MVSMamba_PlusPlus		99.46 42	99.41 37	99.64 101	99.68 133	99.50 108	99.75 42	99.50 177	98.27 152	99.87 49	99.92 18	98.09 108	99.94 92	99.65 41	99.95 23	99.47 247

v10		97.85 300	97.52 315	98.86 275	98.99 374	98.67 240	99.75 42	99.41 272	95.70 410	98.98 305	99.41 334	94.75 270	99.23 374	96.01 395	94.63 413	98.67 363

APDe-MVS		99.66 6	99.57 10	99.92 1	99.77 78	99.89 6	99.75 42	99.56 90	99.02 62	99.88 43	99.85 83	99.18 12	99.96 41	99.22 102	99.92 39	99.90 25
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
IS-MVSNet		99.05 156	98.87 166	99.57 120	99.73 107	99.32 131	99.75 42	99.20 363	98.02 219	99.56 165	99.86 76	96.54 177	99.67 292	98.09 261	99.13 211	99.73 125

test_vis1_n		97.92 290	97.44 331	99.34 189	99.53 218	98.08 287	99.74 47	99.49 190	99.15 38	100.00 1	99.94 6	79.51 471	99.98 20	99.88 26	99.76 140	99.97 4

test_fmvs1_n		98.41 229	98.14 241	99.21 218	99.82 53	97.71 313	99.74 47	99.49 190	99.32 29	99.99 2	99.95 3	85.32 449	99.97 29	99.82 29	99.84 102	99.96 7

balanced_conf03		99.46 42	99.39 40	99.67 90	99.55 210	99.58 93	99.74 47	99.51 154	98.42 134	99.87 49	99.84 98	98.05 111	99.91 135	99.58 47	99.94 31	99.52 224

tttt0517		98.42 227	98.14 241	99.28 209	99.66 149	98.38 273	99.74 47	96.85 470	97.68 260	99.79 76	99.74 197	91.39 382	99.89 163	98.83 170	99.56 170	99.57 211

WB-MVS		93.10 431	94.10 422	90.12 458	95.51 474	81.88 478	99.73 51	99.27 349	95.05 421	93.09 465	98.91 420	94.70 275	91.89 482	76.62 480	94.02 426	96.58 468

test_fmvs2		97.25 370	97.30 352	97.09 421	99.43 259	93.31 454	99.73 51	98.87 412	98.83 88	99.28 238	99.80 150	84.45 454	99.66 295	97.88 279	97.45 340	98.30 425

SD_0403		97.55 347	97.53 314	97.62 403	99.61 187	93.64 451	99.72 53	99.44 256	98.03 216	98.62 366	99.39 342	96.06 200	99.57 316	87.88 468	99.01 236	99.66 167

MonoMVSNet		98.38 233	98.47 221	98.12 365	98.59 432	96.19 393	99.72 53	98.79 423	97.89 229	99.44 192	99.52 300	96.13 197	98.90 434	98.64 196	97.54 330	99.28 279

baseline		99.15 115	99.02 126	99.53 133	99.66 149	99.14 160	99.72 53	99.48 202	98.35 142	99.42 198	99.84 98	96.07 199	99.79 243	99.51 56	99.14 208	99.67 162

RPSCF		98.22 244	98.62 206	96.99 423	99.82 53	91.58 463	99.72 53	99.44 256	96.61 362	99.66 128	99.89 44	95.92 209	99.82 225	97.46 329	99.10 225	99.57 211

CSCG		99.32 79	99.32 54	99.32 195	99.85 31	98.29 275	99.71 57	99.66 32	98.11 191	99.41 203	99.80 150	98.37 96	99.96 41	98.99 136	99.96 17	99.72 135

dmvs_re		98.08 262	98.16 238	97.85 387	99.55 210	94.67 434	99.70 58	98.92 400	98.15 175	99.06 292	99.35 354	93.67 324	99.25 371	97.77 295	97.25 351	99.64 180

WR-MVS_H		98.13 255	97.87 275	98.90 260	99.02 368	98.84 221	99.70 58	99.59 73	97.27 306	98.40 380	99.19 386	95.53 228	99.23 374	98.34 238	93.78 429	98.61 394

mvsmamba		99.06 152	98.96 144	99.36 186	99.47 249	98.64 244	99.70 58	99.05 384	97.61 268	99.65 137	99.83 104	96.54 177	99.92 123	99.19 106	99.62 165	99.51 233

LTVRE_ROB	97.16 12	98.02 274	97.90 270	98.40 339	99.23 318	96.80 368	99.70 58	99.60 67	97.12 320	98.18 396	99.70 214	91.73 373	99.72 271	98.39 231	97.45 340	98.68 355
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
MED-MVS test				99.87 21	99.88 13	99.81 33	99.69 62	99.87 6	99.34 26	99.90 34	99.83 104		99.95 76	98.83 170	99.89 68	99.83 63

MED-MVS		99.66 6	99.60 8	99.87 21	99.88 13	99.81 33	99.69 62	99.87 6	99.18 34	99.90 34	99.83 104	99.30 4	99.95 76	98.83 170	99.89 68	99.83 63

TestfortrainingZip a		99.73 1	99.67 1	99.92 1	99.88 13	99.91 2	99.69 62	99.87 6	99.34 26	99.90 34	99.83 104	99.30 4	99.95 76	99.32 84	99.89 68	99.90 25

TestfortrainingZip							99.69 62

test_f		91.90 435	91.26 439	93.84 445	95.52 473	85.92 470	99.69 62	98.53 446	95.31 415	93.87 460	96.37 472	55.33 482	98.27 449	95.70 401	90.98 453	97.32 464

XVS		99.53 27	99.42 32	99.87 21	99.85 31	99.83 22	99.69 62	99.68 24	98.98 72	99.37 214	99.74 197	98.81 49	99.94 92	98.79 178	99.86 87	99.84 53

X-MVStestdata		96.55 387	95.45 406	99.87 21	99.85 31	99.83 22	99.69 62	99.68 24	98.98 72	99.37 214	64.01 488	98.81 49	99.94 92	98.79 178	99.86 87	99.84 53

V42		98.06 264	97.79 281	98.86 275	98.98 377	98.84 221	99.69 62	99.34 312	96.53 369	99.30 234	99.37 348	94.67 277	99.32 359	97.57 316	94.66 412	98.42 417

mPP-MVS		99.44 50	99.30 62	99.86 34	99.88 13	99.79 41	99.69 62	99.48 202	98.12 189	99.50 179	99.75 192	98.78 53	99.97 29	98.57 211	99.89 68	99.83 63

CP-MVS		99.45 46	99.32 54	99.85 43	99.83 47	99.75 51	99.69 62	99.52 132	98.07 200	99.53 174	99.63 258	98.93 38	99.97 29	98.74 182	99.91 46	99.83 63

FE-MVS		98.48 222	98.17 237	99.40 179	99.54 217	98.96 187	99.68 72	98.81 419	95.54 412	99.62 149	99.70 214	93.82 319	99.93 110	97.35 338	99.46 178	99.32 276

PS-CasMVS		97.93 287	97.59 309	98.95 248	98.99 374	99.06 171	99.68 72	99.52 132	97.13 318	98.31 386	99.68 233	92.44 359	99.05 409	98.51 219	94.08 424	98.75 333

Vis-MVSNet		99.12 133	98.97 140	99.56 122	99.78 70	99.10 164	99.68 72	99.66 32	98.49 125	99.86 53	99.87 68	94.77 268	99.84 196	99.19 106	99.41 182	99.74 116
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
KinetiMVS		99.12 133	98.92 153	99.70 87	99.67 136	99.40 121	99.67 75	99.63 46	98.73 102	99.94 28	99.81 132	94.54 287	99.96 41	98.40 230	99.93 33	99.74 116

BP-MVS1		99.12 133	98.94 150	99.65 95	99.51 227	99.30 138	99.67 75	98.92 400	98.48 126	99.84 56	99.69 225	94.96 251	99.92 123	99.62 44	99.79 132	99.71 146

test_vis1_n_1920		98.63 217	98.40 225	99.31 197	99.86 25	97.94 300	99.67 75	99.62 51	99.43 17	99.99 2	99.91 26	87.29 433	100.00 1	99.92 24	99.92 39	99.98 2

EIA-MVS		99.18 104	99.09 104	99.45 167	99.49 241	99.18 152	99.67 75	99.53 125	97.66 263	99.40 208	99.44 326	98.10 107	99.81 230	98.94 145	99.62 165	99.35 271

MSP-MVS		99.42 55	99.27 73	99.88 15	99.89 8	99.80 38	99.67 75	99.50 177	98.70 106	99.77 85	99.49 310	98.21 102	99.95 76	98.46 225	99.77 137	99.88 35
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		99.10 144	98.97 140	99.48 158	99.49 241	99.14 160	99.67 75	99.34 312	97.31 303	99.58 161	99.76 187	97.65 121	99.82 225	98.87 157	99.07 230	99.46 252

CP-MVSNet		98.09 259	97.78 284	99.01 239	98.97 379	99.24 147	99.67 75	99.46 236	97.25 308	98.48 377	99.64 252	93.79 320	99.06 408	98.63 198	94.10 423	98.74 337

MTAPA		99.52 28	99.39 40	99.89 11	99.90 4	99.86 18	99.66 82	99.47 224	98.79 95	99.68 117	99.81 132	98.43 89	99.97 29	98.88 154	99.90 57	99.83 63

HFP-MVS		99.49 33	99.37 44	99.86 34	99.87 20	99.80 38	99.66 82	99.67 27	98.15 175	99.68 117	99.69 225	99.06 18	99.96 41	98.69 190	99.87 79	99.84 53

mvs_tets		98.40 232	98.23 235	98.91 258	98.67 423	98.51 261	99.66 82	99.53 125	98.19 170	98.65 360	99.81 132	92.75 341	99.44 334	99.31 86	97.48 339	98.77 329

EU-MVSNet		97.98 281	98.03 256	97.81 394	98.72 416	96.65 375	99.66 82	99.66 32	98.09 195	98.35 384	99.82 117	95.25 242	98.01 455	97.41 334	95.30 400	98.78 325

ACMMPR		99.49 33	99.36 46	99.86 34	99.87 20	99.79 41	99.66 82	99.67 27	98.15 175	99.67 123	99.69 225	98.95 32	99.96 41	98.69 190	99.87 79	99.84 53

MP-MVS		99.33 77	99.15 93	99.87 21	99.88 13	99.82 28	99.66 82	99.46 236	98.09 195	99.48 183	99.74 197	98.29 99	99.96 41	97.93 276	99.87 79	99.82 72
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
NormalMVS		99.27 89	99.19 88	99.52 139	99.89 8	98.83 224	99.65 88	99.52 132	99.10 48	99.84 56	99.76 187	95.80 217	99.99 4	99.30 89	99.84 102	99.74 116

SymmetryMVS		99.15 115	99.02 126	99.52 139	99.72 111	98.83 224	99.65 88	99.34 312	99.10 48	99.84 56	99.76 187	95.80 217	99.99 4	99.30 89	98.72 260	99.73 125

Elysia		98.88 176	98.65 198	99.58 116	99.58 197	99.34 127	99.65 88	99.52 132	98.26 155	99.83 64	99.87 68	93.37 327	99.90 148	97.81 289	99.91 46	99.49 238

StellarMVS		98.88 176	98.65 198	99.58 116	99.58 197	99.34 127	99.65 88	99.52 132	98.26 155	99.83 64	99.87 68	93.37 327	99.90 148	97.81 289	99.91 46	99.49 238

test_cas_vis1_n_1920		99.16 111	99.01 132	99.61 109	99.81 57	98.86 218	99.65 88	99.64 42	99.39 22	99.97 25	99.94 6	93.20 333	99.98 20	99.55 50	99.91 46	99.99 1

region2R		99.48 37	99.35 48	99.87 21	99.88 13	99.80 38	99.65 88	99.66 32	98.13 183	99.66 128	99.68 233	98.96 27	99.96 41	98.62 199	99.87 79	99.84 53

TranMVSNet+NR-MVSNet		97.93 287	97.66 300	98.76 291	98.78 405	98.62 247	99.65 88	99.49 190	97.76 249	98.49 376	99.60 270	94.23 300	98.97 426	98.00 272	92.90 439	98.70 346

GDP-MVS		99.08 147	98.89 162	99.64 101	99.53 218	99.34 127	99.64 95	99.48 202	98.32 147	99.77 85	99.66 244	95.14 247	99.93 110	98.97 142	99.50 176	99.64 180

ttmdpeth		97.80 314	97.63 305	98.29 349	98.77 410	97.38 324	99.64 95	99.36 300	98.78 98	96.30 443	99.58 276	92.34 362	99.39 342	98.36 236	95.58 393	98.10 437

mvsany_test3		93.77 428	93.45 431	94.74 442	95.78 469	88.01 468	99.64 95	98.25 451	98.28 150	94.31 457	97.97 457	68.89 475	98.51 446	97.50 324	90.37 455	97.71 454

ZNCC-MVS		99.47 40	99.33 52	99.87 21	99.87 20	99.81 33	99.64 95	99.67 27	98.08 199	99.55 171	99.64 252	98.91 39	99.96 41	98.72 185	99.90 57	99.82 72

tfpnnormal		97.84 304	97.47 323	98.98 243	99.20 325	99.22 149	99.64 95	99.61 60	96.32 383	98.27 390	99.70 214	93.35 329	99.44 334	95.69 402	95.40 398	98.27 427

casdiffmvs_mvg		99.15 115	99.02 126	99.55 124	99.66 149	99.09 165	99.64 95	99.56 90	98.26 155	99.45 187	99.87 68	96.03 202	99.81 230	99.54 51	99.15 207	99.73 125
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 46	99.31 60	99.85 43	99.76 82	99.82 28	99.63 101	99.52 132	98.38 137	99.76 91	99.82 117	98.53 82	99.95 76	98.61 202	99.81 120	99.77 100

RE-MVS-def			99.34 50		99.76 82	99.82 28	99.63 101	99.52 132	98.38 137	99.76 91	99.82 117	98.75 60		98.61 202	99.81 120	99.77 100

TSAR-MVS + MP.		99.58 16	99.50 19	99.81 60	99.91 1	99.66 71	99.63 101	99.39 282	98.91 82	99.78 81	99.85 83	99.36 2	99.94 92	98.84 167	99.88 76	99.82 72
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
Anonymous20231206		96.22 393	96.03 394	96.79 431	97.31 457	94.14 443	99.63 101	99.08 378	96.17 395	97.04 434	99.06 399	93.94 313	97.76 461	86.96 472	95.06 405	98.47 411

APD-MVS_3200maxsize		99.48 37	99.35 48	99.85 43	99.76 82	99.83 22	99.63 101	99.54 109	98.36 141	99.79 76	99.82 117	98.86 43	99.95 76	98.62 199	99.81 120	99.78 98

test0726					99.85 31	99.89 6	99.62 106	99.50 177	99.10 48	99.86 53	99.82 117	98.94 34

EPNet		98.86 182	98.71 189	99.30 202	97.20 459	98.18 280	99.62 106	98.91 405	99.28 31	98.63 363	99.81 132	95.96 205	99.99 4	99.24 101	99.72 148	99.73 125
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t		98.93 172	98.67 193	99.72 86	99.85 31	99.53 101	99.62 106	99.59 73	92.65 452	99.71 110	99.78 174	98.06 110	99.90 148	98.84 167	99.91 46	99.74 116

HY-MVS	97.30 7	98.85 191	98.64 200	99.47 164	99.42 261	99.08 168	99.62 106	99.36 300	97.39 297	99.28 238	99.68 233	96.44 183	99.92 123	98.37 234	98.22 293	99.40 264

ACMMP		99.45 46	99.32 54	99.82 57	99.89 8	99.67 68	99.62 106	99.69 22	98.12 189	99.63 145	99.84 98	98.73 66	99.96 41	98.55 217	99.83 113	99.81 79
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 83	99.19 88	99.64 101	99.82 53	99.23 148	99.62 106	99.55 100	98.94 78	99.63 145	99.95 3	95.82 215	99.94 92	99.37 75	99.97 9	99.73 125
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 16	99.56 12	99.64 101	99.78 70	99.15 159	99.61 112	99.45 247	99.01 64	99.89 40	99.82 117	99.01 20	99.92 123	99.56 49	99.95 23	99.85 46

E6		99.15 115	99.03 117	99.50 149	99.66 149	98.90 208	99.60 113	99.53 125	98.13 183	99.72 102	99.91 26	96.31 190	99.84 196	99.30 89	99.10 225	99.76 107

E5		99.14 122	99.02 126	99.50 149	99.69 127	98.91 204	99.60 113	99.53 125	98.13 183	99.72 102	99.91 26	96.26 194	99.84 196	99.30 89	99.10 225	99.76 107

reproduce_monomvs		97.89 294	97.87 275	97.96 377	99.51 227	95.45 413	99.60 113	99.25 352	99.17 36	98.85 330	99.49 310	89.29 409	99.64 304	99.35 76	96.31 372	98.78 325

test2506		96.81 383	96.65 379	97.29 416	99.74 100	92.21 461	99.60 113	85.06 492	99.13 41	99.77 85	99.93 10	87.82 431	99.85 187	99.38 74	99.38 183	99.80 88

SED-MVS		99.61 10	99.52 14	99.88 15	99.84 38	99.90 3	99.60 113	99.48 202	99.08 56	99.91 31	99.81 132	99.20 9	99.96 41	98.91 151	99.85 94	99.79 92

OPU-MVS				99.64 101	99.56 206	99.72 56	99.60 113				99.70 214	99.27 7	99.42 340	98.24 247	99.80 125	99.79 92

GST-MVS		99.40 64	99.24 78	99.85 43	99.86 25	99.79 41	99.60 113	99.67 27	97.97 222	99.63 145	99.68 233	98.52 83	99.95 76	98.38 232	99.86 87	99.81 79

EI-MVSNet-UG-set		99.58 16	99.57 10	99.64 101	99.78 70	99.14 160	99.60 113	99.45 247	99.01 64	99.90 34	99.83 104	98.98 26	99.93 110	99.59 45	99.95 23	99.86 42

ACMH	97.28 8	98.10 258	97.99 260	98.44 334	99.41 266	96.96 356	99.60 113	99.56 90	98.09 195	98.15 398	99.91 26	90.87 391	99.70 284	98.88 154	97.45 340	98.67 363
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
VortexMVS		98.67 212	98.66 196	98.68 300	99.62 176	97.96 295	99.59 122	99.41 272	98.13 183	99.31 230	99.70 214	95.48 231	99.27 367	99.40 71	97.32 349	98.79 323

guyue		99.16 111	99.04 114	99.52 139	99.69 127	98.92 203	99.59 122	98.81 419	98.73 102	99.90 34	99.87 68	95.34 236	99.88 168	99.66 40	99.81 120	99.74 116

ECVR-MVS		98.04 270	98.05 254	98.00 373	99.74 100	94.37 440	99.59 122	94.98 480	99.13 41	99.66 128	99.93 10	90.67 393	99.84 196	99.40 71	99.38 183	99.80 88

SR-MVS		99.43 53	99.29 66	99.86 34	99.75 92	99.83 22	99.59 122	99.62 51	98.21 168	99.73 97	99.79 167	98.68 70	99.96 41	98.44 227	99.77 137	99.79 92

thres100view900		97.76 318	97.45 326	98.69 299	99.72 111	97.86 304	99.59 122	98.74 429	97.93 225	99.26 249	98.62 432	91.75 371	99.83 216	93.22 440	98.18 298	98.37 423

thres600view7		97.86 299	97.51 317	98.92 254	99.72 111	97.95 298	99.59 122	98.74 429	97.94 224	99.27 244	98.62 432	91.75 371	99.86 181	93.73 434	98.19 297	98.96 315

LCM-MVSNet-Re		97.83 307	98.15 240	96.87 429	99.30 298	92.25 460	99.59 122	98.26 450	97.43 292	96.20 444	99.13 392	96.27 192	98.73 441	98.17 253	98.99 237	99.64 180

baseline1		98.31 238	97.95 265	99.38 185	99.50 239	98.74 234	99.59 122	98.93 397	98.41 135	99.14 273	99.60 270	94.59 282	99.79 243	98.48 221	93.29 434	99.61 190

SteuartSystems-ACMMP		99.54 24	99.42 32	99.87 21	99.82 53	99.81 33	99.59 122	99.51 154	98.62 112	99.79 76	99.83 104	99.28 6	99.97 29	98.48 221	99.90 57	99.84 53
Skip Steuart: Steuart Systems R&D Blog.
CPTT-MVS		99.11 139	98.90 158	99.74 80	99.80 63	99.46 114	99.59 122	99.49 190	97.03 332	99.63 145	99.69 225	97.27 133	99.96 41	97.82 287	99.84 102	99.81 79

IMVS_0403		98.86 182	98.89 162	98.78 289	99.55 210	96.93 357	99.58 132	99.44 256	98.05 207	99.68 117	99.80 150	96.81 161	99.80 237	98.15 256	98.92 242	99.60 193

test_fmvsmvis_n_1920		99.65 8	99.61 7	99.77 74	99.38 276	99.37 123	99.58 132	99.62 51	99.41 21	99.87 49	99.92 18	98.81 49	100.00 1	99.97 2	99.93 33	99.94 17

dmvs_testset		95.02 416	96.12 391	91.72 453	99.10 352	80.43 481	99.58 132	97.87 460	97.47 284	95.22 451	98.82 423	93.99 311	95.18 478	88.09 466	94.91 410	99.56 214

test_fmvsm_n_1920		99.69 5	99.66 4	99.78 71	99.84 38	99.44 116	99.58 132	99.69 22	99.43 17	99.98 13	99.91 26	98.62 76	100.00 1	99.97 2	99.95 23	99.90 25

test1111		98.04 270	98.11 245	97.83 391	99.74 100	93.82 445	99.58 132	95.40 479	99.12 46	99.65 137	99.93 10	90.73 392	99.84 196	99.43 69	99.38 183	99.82 72

PGM-MVS		99.45 46	99.31 60	99.86 34	99.87 20	99.78 47	99.58 132	99.65 39	97.84 238	99.71 110	99.80 150	99.12 15	99.97 29	98.33 239	99.87 79	99.83 63

LPG-MVS_test		98.22 244	98.13 243	98.49 321	99.33 289	97.05 343	99.58 132	99.55 100	97.46 285	99.24 251	99.83 104	92.58 351	99.72 271	98.09 261	97.51 333	98.68 355

PHI-MVS		99.30 83	99.17 91	99.70 87	99.56 206	99.52 105	99.58 132	99.80 11	97.12 320	99.62 149	99.73 203	98.58 78	99.90 148	98.61 202	99.91 46	99.68 158

fmvsm_s_conf0.5_n_11		99.32 79	99.16 92	99.80 64	99.83 47	99.70 60	99.57 140	99.56 90	99.45 11	99.99 2	99.93 10	94.18 304	99.99 4	99.96 13	99.98 4	99.73 125

AstraMVS		99.09 145	99.03 117	99.25 212	99.66 149	98.13 284	99.57 140	98.24 452	98.82 89	99.91 31	99.88 55	95.81 216	99.90 148	99.72 32	99.67 158	99.74 116

SF-MVS		99.38 67	99.24 78	99.79 68	99.79 68	99.68 64	99.57 140	99.54 109	97.82 244	99.71 110	99.80 150	98.95 32	99.93 110	98.19 250	99.84 102	99.74 116

DVP-MVS		99.57 20	99.47 24	99.88 15	99.85 31	99.89 6	99.57 140	99.37 298	99.10 48	99.81 69	99.80 150	98.94 34	99.96 41	98.93 148	99.86 87	99.81 79
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 6	99.84 38	99.89 6	99.57 140	99.51 154					99.96 41	98.93 148	99.86 87	99.88 35

Effi-MVS+-dtu		98.78 200	98.89 162	98.47 328	99.33 289	96.91 362	99.57 140	99.30 339	98.47 127	99.41 203	98.99 409	96.78 163	99.74 261	98.73 184	99.38 183	98.74 337

v2v482		98.06 264	97.77 286	98.92 254	98.90 387	98.82 227	99.57 140	99.36 300	96.65 357	99.19 265	99.35 354	94.20 301	99.25 371	97.72 302	94.97 407	98.69 350

DSMNet-mixed		97.25 370	97.35 343	96.95 426	97.84 447	93.61 452	99.57 140	96.63 474	96.13 400	98.87 324	98.61 434	94.59 282	97.70 462	95.08 416	98.86 250	99.55 215

FE-MVSNET		94.07 427	93.36 432	96.22 437	94.05 479	94.71 432	99.56 148	98.36 448	93.15 446	93.76 461	97.55 462	86.47 440	96.49 473	87.48 469	89.83 460	97.48 462

reproduce_model		99.63 9	99.54 13	99.90 8	99.78 70	99.88 10	99.56 148	99.55 100	99.15 38	99.90 34	99.90 35	99.00 24	99.97 29	99.11 120	99.91 46	99.86 42

MVStest1		96.08 399	95.48 404	97.89 383	98.93 382	96.70 370	99.56 148	99.35 307	92.69 451	91.81 470	99.46 323	89.90 402	98.96 428	95.00 418	92.61 444	98.00 446

fmvsm_l_conf0.5_n_a		99.71 2	99.67 1	99.85 43	99.86 25	99.61 85	99.56 148	99.63 46	99.48 3	99.98 13	99.83 104	98.75 60	99.99 4	99.97 2	99.96 17	99.94 17

fmvsm_l_conf0.5_n		99.71 2	99.67 1	99.85 43	99.84 38	99.63 82	99.56 148	99.63 46	99.47 4	99.98 13	99.82 117	98.75 60	99.99 4	99.97 2	99.97 9	99.94 17

sd_testset		98.75 205	98.57 213	99.29 205	99.81 57	98.26 277	99.56 148	99.62 51	98.78 98	99.64 142	99.88 55	92.02 365	99.88 168	99.54 51	98.26 290	99.72 135

KD-MVS_self_test		95.00 417	94.34 421	96.96 425	97.07 462	95.39 416	99.56 148	99.44 256	95.11 418	97.13 432	97.32 467	91.86 369	97.27 467	90.35 458	81.23 475	98.23 431

ETV-MVS		99.26 92	99.21 84	99.40 179	99.46 251	99.30 138	99.56 148	99.52 132	98.52 122	99.44 192	99.27 376	98.41 93	99.86 181	99.10 123	99.59 168	99.04 305

SMA-MVS		99.44 50	99.30 62	99.85 43	99.73 107	99.83 22	99.56 148	99.47 224	97.45 288	99.78 81	99.82 117	99.18 12	99.91 135	98.79 178	99.89 68	99.81 79
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		98.87 179	98.72 187	99.31 197	99.86 25	98.48 266	99.56 148	99.61 60	97.85 235	99.36 220	99.85 83	95.95 206	99.85 187	96.66 378	99.83 113	99.59 204

casdiffmvs		99.13 125	98.98 139	99.56 122	99.65 158	99.16 155	99.56 148	99.50 177	98.33 145	99.41 203	99.86 76	95.92 209	99.83 216	99.45 68	99.16 204	99.70 149
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		98.38 233	98.09 249	99.24 215	99.26 310	99.32 131	99.56 148	99.55 100	97.45 288	98.71 345	99.83 104	93.23 330	99.63 310	98.88 154	96.32 371	98.76 331

ACMH+	97.24 10	97.92 290	97.78 284	98.32 346	99.46 251	96.68 374	99.56 148	99.54 109	98.41 135	97.79 416	99.87 68	90.18 400	99.66 295	98.05 269	97.18 355	98.62 385

ACMM	97.58 5	98.37 235	98.34 228	98.48 323	99.41 266	97.10 337	99.56 148	99.45 247	98.53 121	99.04 295	99.85 83	93.00 335	99.71 277	98.74 182	97.45 340	98.64 376
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LS3D		99.27 89	99.12 97	99.74 80	99.18 331	99.75 51	99.56 148	99.57 85	98.45 130	99.49 182	99.85 83	97.77 118	99.94 92	98.33 239	99.84 102	99.52 224

testing3-2		97.84 304	97.70 296	98.24 355	99.53 218	95.37 417	99.55 163	98.67 439	98.46 128	99.27 244	99.34 358	86.58 438	99.83 216	99.32 84	98.63 263	99.52 224

test_fmvsmconf0.01_n		99.22 100	99.03 117	99.79 68	98.42 439	99.48 111	99.55 163	99.51 154	99.39 22	99.78 81	99.93 10	94.80 263	99.95 76	99.93 23	99.95 23	99.94 17

test_fmvs1		98.88 176	98.79 180	99.16 223	99.69 127	97.61 317	99.55 163	99.49 190	99.32 29	99.98 13	99.91 26	91.41 381	99.96 41	99.82 29	99.92 39	99.90 25

v144192		97.92 290	97.60 308	98.87 272	98.83 399	98.65 242	99.55 163	99.34 312	96.20 392	99.32 229	99.40 338	94.36 294	99.26 370	96.37 389	95.03 406	98.70 346

API-MVS		99.04 157	99.03 117	99.06 233	99.40 271	99.31 135	99.55 163	99.56 90	98.54 120	99.33 228	99.39 342	98.76 57	99.78 249	96.98 360	99.78 134	98.07 439

fmvsm_l_conf0.5_n_3		99.61 10	99.51 18	99.92 1	99.84 38	99.82 28	99.54 168	99.66 32	99.46 7	99.98 13	99.89 44	97.27 133	99.99 4	99.97 2	99.95 23	99.95 11

fmvsm_s_conf0.1_n_a		99.26 92	99.06 110	99.85 43	99.52 224	99.62 83	99.54 168	99.62 51	98.69 107	99.99 2	99.96 1	94.47 291	99.94 92	99.88 26	99.92 39	99.98 2

APD_test1		95.87 401	96.49 383	94.00 444	99.53 218	84.01 473	99.54 168	99.32 330	95.91 408	97.99 405	99.85 83	85.49 447	99.88 168	91.96 451	98.84 252	98.12 436

thisisatest0530		98.35 236	98.03 256	99.31 197	99.63 167	98.56 252	99.54 168	96.75 472	97.53 279	99.73 97	99.65 246	91.25 386	99.89 163	98.62 199	99.56 170	99.48 241

MTMP							99.54 168	98.88 410

v1144		97.98 281	97.69 297	98.85 278	98.87 392	98.66 241	99.54 168	99.35 307	96.27 387	99.23 255	99.35 354	94.67 277	99.23 374	96.73 373	95.16 403	98.68 355

v148		97.79 316	97.55 310	98.50 320	98.74 413	97.72 310	99.54 168	99.33 320	96.26 388	98.90 318	99.51 304	94.68 276	99.14 392	97.83 286	93.15 438	98.63 383

CostFormer		97.72 328	97.73 293	97.71 399	99.15 345	94.02 444	99.54 168	99.02 388	94.67 430	99.04 295	99.35 354	92.35 361	99.77 251	98.50 220	97.94 308	99.34 274

MVSTER		98.49 221	98.32 230	99.00 241	99.35 283	99.02 175	99.54 168	99.38 290	97.41 295	99.20 262	99.73 203	93.86 318	99.36 351	98.87 157	97.56 328	98.62 385

fmvsm_s_conf0.5_n_10		99.41 59	99.24 78	99.92 1	99.83 47	99.84 20	99.53 177	99.56 90	99.45 11	99.99 2	99.92 18	94.92 256	99.99 4	99.97 2	99.97 9	99.95 11

fmvsm_s_conf0.1_n		99.29 85	99.10 99	99.86 34	99.70 122	99.65 75	99.53 177	99.62 51	98.74 101	99.99 2	99.95 3	94.53 289	99.94 92	99.89 25	99.96 17	99.97 4

E4		99.13 125	99.01 132	99.49 154	99.68 133	98.90 208	99.52 179	99.52 132	98.13 183	99.71 110	99.90 35	96.32 188	99.84 196	99.21 104	99.11 218	99.75 111

reproduce-ours		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 179	99.54 109	99.13 41	99.89 40	99.89 44	98.96 27	99.96 41	99.04 130	99.90 57	99.85 46

our_new_method		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 179	99.54 109	99.13 41	99.89 40	99.89 44	98.96 27	99.96 41	99.04 130	99.90 57	99.85 46

fmvsm_s_conf0.5_n_a		99.56 21	99.47 24	99.85 43	99.83 47	99.64 81	99.52 179	99.65 39	99.10 48	99.98 13	99.92 18	97.35 129	99.96 41	99.94 21	99.92 39	99.95 11

MM		99.40 64	99.28 69	99.74 80	99.67 136	99.31 135	99.52 179	98.87 412	99.55 1	99.74 95	99.80 150	96.47 180	99.98 20	99.97 2	99.97 9	99.94 17

patch_mono-2		99.26 92	99.62 6	98.16 360	99.81 57	94.59 436	99.52 179	99.64 42	99.33 28	99.73 97	99.90 35	99.00 24	99.99 4	99.69 35	99.98 4	99.89 29

Fast-Effi-MVS+-dtu		98.77 204	98.83 176	98.60 305	99.41 266	96.99 352	99.52 179	99.49 190	98.11 191	99.24 251	99.34 358	96.96 152	99.79 243	97.95 275	99.45 179	99.02 308

Fast-Effi-MVS+		98.70 209	98.43 222	99.51 144	99.51 227	99.28 141	99.52 179	99.47 224	96.11 401	99.01 298	99.34 358	96.20 195	99.84 196	97.88 279	98.82 254	99.39 265

v1921920		97.80 314	97.45 326	98.84 279	98.80 401	98.53 255	99.52 179	99.34 312	96.15 398	99.24 251	99.47 319	93.98 312	99.29 363	95.40 410	95.13 404	98.69 350

MIMVSNet1		95.51 407	95.04 412	96.92 428	97.38 454	95.60 406	99.52 179	99.50 177	93.65 440	96.97 436	99.17 387	85.28 450	96.56 472	88.36 465	95.55 395	98.60 397

FE-MVSNET2		95.10 414	94.44 419	97.08 422	95.08 475	95.97 397	99.51 189	99.37 298	95.02 422	94.10 458	97.57 461	86.18 442	97.66 464	93.28 439	89.86 459	97.61 457

viewmacassd2359aftdt		99.08 147	98.94 150	99.50 149	99.66 149	98.96 187	99.51 189	99.54 109	98.27 152	99.42 198	99.89 44	95.88 213	99.80 237	99.20 105	99.11 218	99.76 107

SSM_0407		99.13 125	99.03 117	99.43 175	99.62 176	98.88 211	99.51 189	99.50 177	98.14 180	99.37 214	99.85 83	96.85 155	99.83 216	99.19 106	99.25 197	99.60 193

fmvsm_s_conf0.5_n_8		99.54 24	99.42 32	99.89 11	99.83 47	99.74 54	99.51 189	99.62 51	99.46 7	99.99 2	99.90 35	96.60 172	99.98 20	99.95 16	99.95 23	99.96 7

fmvsm_s_conf0.5_n		99.51 29	99.40 38	99.85 43	99.84 38	99.65 75	99.51 189	99.67 27	99.13 41	99.98 13	99.92 18	96.60 172	99.96 41	99.95 16	99.96 17	99.95 11

UniMVSNet_ETH3D		97.32 367	96.81 375	98.87 272	99.40 271	97.46 321	99.51 189	99.53 125	95.86 409	98.54 373	99.77 183	82.44 463	99.66 295	98.68 192	97.52 332	99.50 237

alignmvs		98.81 195	98.56 215	99.58 116	99.43 259	99.42 118	99.51 189	98.96 395	98.61 113	99.35 223	98.92 419	94.78 265	99.77 251	99.35 76	98.11 303	99.54 217

v1192		97.81 312	97.44 331	98.91 258	98.88 389	98.68 239	99.51 189	99.34 312	96.18 394	99.20 262	99.34 358	94.03 310	99.36 351	95.32 412	95.18 402	98.69 350

test20.03		96.12 397	95.96 396	96.63 432	97.44 453	95.45 413	99.51 189	99.38 290	96.55 368	96.16 445	99.25 379	93.76 322	96.17 474	87.35 471	94.22 420	98.27 427

mvs_anonymous		99.03 159	98.99 136	99.16 223	99.38 276	98.52 259	99.51 189	99.38 290	97.79 245	99.38 212	99.81 132	97.30 131	99.45 329	99.35 76	98.99 237	99.51 233

TAMVS		99.12 133	99.08 105	99.24 215	99.46 251	98.55 253	99.51 189	99.46 236	98.09 195	99.45 187	99.82 117	98.34 97	99.51 323	98.70 187	98.93 240	99.67 162

viewdifsd2359ckpt13		99.06 152	98.93 152	99.45 167	99.63 167	98.96 187	99.50 200	99.51 154	97.83 239	99.28 238	99.80 150	96.68 169	99.71 277	99.05 129	99.12 216	99.68 158

viewdifsd2359ckpt11		98.78 200	98.74 185	98.89 264	99.67 136	97.04 346	99.50 200	99.58 78	98.26 155	99.56 165	99.90 35	94.36 294	99.87 175	99.49 61	98.32 286	99.77 100

viewmsd2359difaftdt		98.78 200	98.74 185	98.90 260	99.67 136	97.04 346	99.50 200	99.58 78	98.26 155	99.56 165	99.90 35	94.36 294	99.87 175	99.49 61	98.32 286	99.77 100

IMVS_0407		98.86 182	98.91 156	98.72 294	99.55 210	96.93 357	99.50 200	99.44 256	98.05 207	99.66 128	99.80 150	97.13 139	99.65 300	98.15 256	98.92 242	99.60 193

viewmanbaseed2359cas		99.18 104	99.07 109	99.50 149	99.62 176	99.01 177	99.50 200	99.52 132	98.25 160	99.68 117	99.82 117	96.93 153	99.80 237	99.15 116	99.11 218	99.70 149

fmvsm_s_conf0.5_n_6		99.54 24	99.44 31	99.85 43	99.51 227	99.67 68	99.50 200	99.64 42	99.43 17	99.98 13	99.78 174	97.26 136	99.95 76	99.95 16	99.93 33	99.92 23

test_fmvsmconf0.1_n		99.55 23	99.45 30	99.86 34	99.44 258	99.65 75	99.50 200	99.61 60	99.45 11	99.87 49	99.92 18	97.31 130	99.97 29	99.95 16	99.99 1	99.97 4

test_yl		98.86 182	98.63 201	99.54 125	99.49 241	99.18 152	99.50 200	99.07 381	98.22 166	99.61 154	99.51 304	95.37 234	99.84 196	98.60 205	98.33 282	99.59 204

DCV-MVSNet		98.86 182	98.63 201	99.54 125	99.49 241	99.18 152	99.50 200	99.07 381	98.22 166	99.61 154	99.51 304	95.37 234	99.84 196	98.60 205	98.33 282	99.59 204

tfpn200view9		97.72 328	97.38 339	98.72 294	99.69 127	97.96 295	99.50 200	98.73 435	97.83 239	99.17 270	98.45 439	91.67 375	99.83 216	93.22 440	98.18 298	98.37 423

UA-Net		99.42 55	99.29 66	99.80 64	99.62 176	99.55 96	99.50 200	99.70 18	98.79 95	99.77 85	99.96 1	97.45 124	99.96 41	98.92 150	99.90 57	99.89 29

pm-mvs1		97.68 336	97.28 355	98.88 268	99.06 361	98.62 247	99.50 200	99.45 247	96.32 383	97.87 412	99.79 167	92.47 355	99.35 354	97.54 319	93.54 431	98.67 363

EI-MVSNet		98.67 212	98.67 193	98.68 300	99.35 283	97.97 293	99.50 200	99.38 290	96.93 341	99.20 262	99.83 104	97.87 114	99.36 351	98.38 232	97.56 328	98.71 341

CVMVSNet		98.57 219	98.67 193	98.30 348	99.35 283	95.59 407	99.50 200	99.55 100	98.60 115	99.39 210	99.83 104	94.48 290	99.45 329	98.75 181	98.56 270	99.85 46

VPA-MVSNet		98.29 241	97.95 265	99.30 202	99.16 341	99.54 98	99.50 200	99.58 78	98.27 152	99.35 223	99.37 348	92.53 353	99.65 300	99.35 76	94.46 415	98.72 339

thres400		97.77 317	97.38 339	98.92 254	99.69 127	97.96 295	99.50 200	98.73 435	97.83 239	99.17 270	98.45 439	91.67 375	99.83 216	93.22 440	98.18 298	98.96 315

APD-MVS		99.27 89	99.08 105	99.84 55	99.75 92	99.79 41	99.50 200	99.50 177	97.16 316	99.77 85	99.82 117	98.78 53	99.94 92	97.56 317	99.86 87	99.80 88
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
E2		99.15 115	99.03 117	99.49 154	99.65 158	98.93 202	99.49 217	99.52 132	98.14 180	99.72 102	99.88 55	96.57 176	99.84 196	99.17 112	99.13 211	99.72 135

E3		99.15 115	99.03 117	99.49 154	99.62 176	98.91 204	99.49 217	99.52 132	98.13 183	99.72 102	99.88 55	96.61 171	99.84 196	99.17 112	99.13 211	99.72 135

SSM_0404		99.16 111	99.06 110	99.44 172	99.65 158	98.96 187	99.49 217	99.50 177	98.14 180	99.62 149	99.85 83	96.85 155	99.85 187	99.19 106	99.26 196	99.52 224

fmvsm_s_conf0.5_n_4		99.36 72	99.24 78	99.73 83	99.78 70	99.53 101	99.49 217	99.60 67	99.42 20	99.99 2	99.86 76	95.15 246	99.95 76	99.95 16	99.89 68	99.73 125

test_vis1_rt		95.81 403	95.65 402	96.32 436	99.67 136	91.35 464	99.49 217	96.74 473	98.25 160	95.24 450	98.10 454	74.96 472	99.90 148	99.53 53	98.85 251	97.70 456

TransMVSNet (Re)		97.15 374	96.58 380	98.86 275	99.12 347	98.85 219	99.49 217	98.91 405	95.48 413	97.16 431	99.80 150	93.38 326	99.11 401	94.16 430	91.73 448	98.62 385

UniMVSNet (Re)		98.29 241	98.00 259	99.13 228	99.00 371	99.36 126	99.49 217	99.51 154	97.95 223	98.97 307	99.13 392	96.30 191	99.38 344	98.36 236	93.34 433	98.66 372

EPMVS		97.82 310	97.65 301	98.35 343	98.88 389	95.98 396	99.49 217	94.71 482	97.57 272	99.26 249	99.48 316	92.46 358	99.71 277	97.87 281	99.08 229	99.35 271

viewcassd2359sk11		99.18 104	99.08 105	99.49 154	99.65 158	98.95 193	99.48 225	99.51 154	98.10 194	99.72 102	99.87 68	97.13 139	99.84 196	99.13 117	99.14 208	99.69 152

fmvsm_s_conf0.5_n_9		99.41 59	99.28 69	99.81 60	99.84 38	99.52 105	99.48 225	99.62 51	99.46 7	99.99 2	99.92 18	95.24 243	99.96 41	99.97 2	99.97 9	99.96 7

SSC-MVS3.2		97.34 365	97.15 362	97.93 379	99.02 368	95.76 404	99.48 225	99.58 78	97.62 267	99.09 284	99.53 296	87.95 427	99.27 367	96.42 385	95.66 391	98.75 333

fmvsm_s_conf0.5_n_3		99.37 68	99.20 86	99.87 21	99.75 92	99.70 60	99.48 225	99.66 32	99.45 11	99.99 2	99.93 10	94.64 281	99.97 29	99.94 21	99.97 9	99.95 11

test_fmvsmconf_n		99.70 4	99.64 5	99.87 21	99.80 63	99.66 71	99.48 225	99.64 42	99.45 11	99.92 30	99.92 18	98.62 76	99.99 4	99.96 13	99.99 1	99.96 7

Anonymous20231211		97.88 295	97.54 313	98.90 260	99.71 117	98.53 255	99.48 225	99.57 85	94.16 435	98.81 334	99.68 233	93.23 330	99.42 340	98.84 167	94.42 417	98.76 331

v1240		97.69 333	97.32 350	98.79 287	98.85 396	98.43 270	99.48 225	99.36 300	96.11 401	99.27 244	99.36 351	93.76 322	99.24 373	94.46 424	95.23 401	98.70 346

VPNet		97.84 304	97.44 331	99.01 239	99.21 323	98.94 197	99.48 225	99.57 85	98.38 137	99.28 238	99.73 203	88.89 412	99.39 342	99.19 106	93.27 435	98.71 341

UniMVSNet_NR-MVSNet		98.22 244	97.97 262	98.96 246	98.92 384	98.98 180	99.48 225	99.53 125	97.76 249	98.71 345	99.46 323	96.43 184	99.22 379	98.57 211	92.87 441	98.69 350

TDRefinement		95.42 409	94.57 417	97.97 375	89.83 485	96.11 395	99.48 225	98.75 426	96.74 350	96.68 439	99.88 55	88.65 418	99.71 277	98.37 234	82.74 472	98.09 438

fmvsm_l_conf0.5_n_9		99.58 16	99.47 24	99.92 1	99.85 31	99.82 28	99.47 235	99.63 46	99.45 11	99.98 13	99.89 44	97.02 148	99.99 4	99.98 1	99.96 17	99.95 11

ACMMP_NAP		99.47 40	99.34 50	99.88 15	99.87 20	99.86 18	99.47 235	99.48 202	98.05 207	99.76 91	99.86 76	98.82 48	99.93 110	98.82 177	99.91 46	99.84 53

NR-MVSNet		97.97 284	97.61 307	99.02 238	98.87 392	99.26 144	99.47 235	99.42 269	97.63 265	97.08 433	99.50 307	95.07 249	99.13 395	97.86 282	93.59 430	98.68 355

PVSNet_Blended_VisFu		99.36 72	99.28 69	99.61 109	99.86 25	99.07 170	99.47 235	99.93 2	97.66 263	99.71 110	99.86 76	97.73 119	99.96 41	99.47 66	99.82 117	99.79 92

E3new		99.18 104	99.08 105	99.48 158	99.63 167	98.94 197	99.46 239	99.50 177	98.06 204	99.72 102	99.84 98	97.27 133	99.84 196	99.10 123	99.13 211	99.67 162

LuminaMVS		99.23 98	99.10 99	99.61 109	99.35 283	99.31 135	99.46 239	99.13 372	98.61 113	99.86 53	99.89 44	96.41 186	99.91 135	99.67 37	99.51 174	99.63 185

fmvsm_s_conf0.1_n_2		99.37 68	99.22 83	99.81 60	99.77 78	99.75 51	99.46 239	99.60 67	99.47 4	99.98 13	99.94 6	94.98 250	99.95 76	99.97 2	99.79 132	99.73 125

SD-MVS		99.41 59	99.52 14	99.05 235	99.74 100	99.68 64	99.46 239	99.52 132	99.11 47	99.88 43	99.91 26	99.43 1	97.70 462	98.72 185	99.93 33	99.77 100
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
viewdifsd2359ckpt07		99.11 139	99.00 135	99.43 175	99.63 167	98.73 235	99.45 243	99.54 109	98.33 145	99.62 149	99.81 132	96.17 196	99.87 175	99.27 97	99.14 208	99.69 152

testing3		97.28 368	96.76 377	98.82 281	99.37 279	98.07 288	99.45 243	99.36 300	97.56 274	97.89 411	98.95 414	83.70 457	98.82 436	96.03 393	98.56 270	99.58 208

tt0805		97.97 284	97.77 286	98.57 310	99.59 195	96.61 377	99.45 243	99.08 378	98.21 168	98.88 321	99.80 150	88.66 417	99.70 284	98.58 208	97.72 318	99.39 265

tpm2		97.44 360	97.34 346	97.74 398	99.15 345	94.36 441	99.45 243	98.94 396	93.45 444	98.90 318	99.44 326	91.35 383	99.59 314	97.31 339	98.07 304	99.29 278

FMVSNet2		97.72 328	97.36 341	98.80 286	99.51 227	98.84 221	99.45 243	99.42 269	96.49 371	98.86 329	99.29 371	90.26 396	98.98 419	96.44 384	96.56 365	98.58 400

CDS-MVSNet		99.09 145	99.03 117	99.25 212	99.42 261	98.73 235	99.45 243	99.46 236	98.11 191	99.46 186	99.77 183	98.01 112	99.37 347	98.70 187	98.92 242	99.66 167
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MAR-MVS		98.86 182	98.63 201	99.54 125	99.37 279	99.66 71	99.45 243	99.54 109	96.61 362	99.01 298	99.40 338	97.09 143	99.86 181	97.68 307	99.53 173	99.10 293
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
viewdifsd2359ckpt09		99.01 164	98.87 166	99.40 179	99.62 176	98.79 230	99.44 250	99.51 154	97.76 249	99.35 223	99.69 225	96.42 185	99.75 258	98.97 142	99.11 218	99.66 167

fmvsm_s_conf0.5_n_2		99.32 79	99.13 95	99.89 11	99.80 63	99.77 48	99.44 250	99.58 78	99.47 4	99.99 2	99.93 10	94.04 309	99.96 41	99.96 13	99.93 33	99.93 22

UGNet		98.87 179	98.69 191	99.40 179	99.22 322	98.72 237	99.44 250	99.68 24	99.24 32	99.18 269	99.42 330	92.74 343	99.96 41	99.34 81	99.94 31	99.53 223
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		98.86 182	98.63 201	99.54 125	99.64 163	99.19 150	99.44 250	99.54 109	97.77 248	99.30 234	99.81 132	94.20 301	99.93 110	99.17 112	98.82 254	99.49 238

test_0402		96.64 386	96.24 388	97.85 387	98.85 396	96.43 383	99.44 250	99.26 350	93.52 441	96.98 435	99.52 300	88.52 421	99.20 386	92.58 450	97.50 335	97.93 451

ACMP	97.20 11	98.06 264	97.94 267	98.45 331	99.37 279	97.01 350	99.44 250	99.49 190	97.54 278	98.45 378	99.79 167	91.95 367	99.72 271	97.91 277	97.49 338	98.62 385
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
GG-mvs-BLEND				98.45 331	98.55 434	98.16 281	99.43 256	93.68 484		97.23 427	98.46 438	89.30 408	99.22 379	95.43 409	98.22 293	97.98 448

HPM-MVS++		99.39 66	99.23 82	99.87 21	99.75 92	99.84 20	99.43 256	99.51 154	98.68 109	99.27 244	99.53 296	98.64 75	99.96 41	98.44 227	99.80 125	99.79 92

tpm cat1		97.39 362	97.36 341	97.50 410	99.17 339	93.73 447	99.43 256	99.31 334	91.27 457	98.71 345	99.08 396	94.31 299	99.77 251	96.41 387	98.50 274	99.00 309

tpm		97.67 339	97.55 310	98.03 368	99.02 368	95.01 425	99.43 256	98.54 445	96.44 377	99.12 276	99.34 358	91.83 370	99.60 313	97.75 298	96.46 367	99.48 241

GBi-Net		97.68 336	97.48 320	98.29 349	99.51 227	97.26 330	99.43 256	99.48 202	96.49 371	99.07 287	99.32 366	90.26 396	98.98 419	97.10 352	96.65 362	98.62 385

test1		97.68 336	97.48 320	98.29 349	99.51 227	97.26 330	99.43 256	99.48 202	96.49 371	99.07 287	99.32 366	90.26 396	98.98 419	97.10 352	96.65 362	98.62 385

FMVSNet1		96.84 382	96.36 386	98.29 349	99.32 296	97.26 330	99.43 256	99.48 202	95.11 418	98.55 372	99.32 366	83.95 456	98.98 419	95.81 398	96.26 373	98.62 385

fmvsm_s_conf0.5_n_7		99.34 75	99.29 66	99.48 158	99.70 122	98.63 245	99.42 263	99.63 46	99.46 7	99.98 13	99.88 55	95.59 226	99.96 41	99.97 2	99.98 4	99.85 46

fmvsm_s_conf0.5_n_5		99.37 68	99.21 84	99.86 34	99.80 63	99.68 64	99.42 263	99.61 60	99.37 24	99.97 25	99.86 76	94.96 251	99.99 4	99.97 2	99.93 33	99.92 23

mamv4		99.33 77	99.42 32	99.07 231	99.67 136	97.73 308	99.42 263	99.60 67	98.15 175	99.94 28	99.91 26	98.42 91	99.94 92	99.72 32	99.96 17	99.54 217

testgi		97.65 341	97.50 318	98.13 364	99.36 282	96.45 382	99.42 263	99.48 202	97.76 249	97.87 412	99.45 325	91.09 388	98.81 437	94.53 423	98.52 273	99.13 292

F-COLMAP		99.19 101	99.04 114	99.64 101	99.78 70	99.27 143	99.42 263	99.54 109	97.29 305	99.41 203	99.59 272	98.42 91	99.93 110	98.19 250	99.69 153	99.73 125

Anonymous202405211		98.30 240	97.98 261	99.26 211	99.57 202	98.16 281	99.41 268	98.55 444	96.03 406	99.19 265	99.74 197	91.87 368	99.92 123	99.16 115	98.29 289	99.70 149

MSLP-MVS++		99.46 42	99.47 24	99.44 172	99.60 193	99.16 155	99.41 268	99.71 16	98.98 72	99.45 187	99.78 174	99.19 11	99.54 321	99.28 94	99.84 102	99.63 185

VNet		99.11 139	98.90 158	99.73 83	99.52 224	99.56 94	99.41 268	99.39 282	99.01 64	99.74 95	99.78 174	95.56 227	99.92 123	99.52 55	98.18 298	99.72 135

baseline2		97.87 297	97.55 310	98.82 281	99.18 331	98.02 290	99.41 268	96.58 476	96.97 335	96.51 440	99.17 387	93.43 325	99.57 316	97.71 303	99.03 233	98.86 319

DU-MVS		98.08 262	97.79 281	98.96 246	98.87 392	98.98 180	99.41 268	99.45 247	97.87 231	98.71 345	99.50 307	94.82 261	99.22 379	98.57 211	92.87 441	98.68 355

Baseline_NR-MVSNet		97.76 318	97.45 326	98.68 300	99.09 355	98.29 275	99.41 268	98.85 414	95.65 411	98.63 363	99.67 239	94.82 261	99.10 403	98.07 268	92.89 440	98.64 376

XVG-ACMP-BASELINE		97.83 307	97.71 295	98.20 357	99.11 349	96.33 386	99.41 268	99.52 132	98.06 204	99.05 294	99.50 307	89.64 406	99.73 267	97.73 300	97.38 347	98.53 404

DP-MVS		99.16 111	98.95 148	99.78 71	99.77 78	99.53 101	99.41 268	99.50 177	97.03 332	99.04 295	99.88 55	97.39 125	99.92 123	98.66 194	99.90 57	99.87 40

9.14			99.10 99		99.72 111		99.40 276	99.51 154	97.53 279	99.64 142	99.78 174	98.84 46	99.91 135	97.63 308	99.82 117

D2MVS		98.41 229	98.50 219	98.15 363	99.26 310	96.62 376	99.40 276	99.61 60	97.71 255	98.98 305	99.36 351	96.04 201	99.67 292	98.70 187	97.41 345	98.15 435

Anonymous20240529		98.09 259	97.68 298	99.34 189	99.66 149	98.44 269	99.40 276	99.43 267	93.67 439	99.22 256	99.89 44	90.23 399	99.93 110	99.26 100	98.33 282	99.66 167

FMVSNet3		98.03 272	97.76 290	98.84 279	99.39 274	98.98 180	99.40 276	99.38 290	96.67 355	99.07 287	99.28 373	92.93 336	98.98 419	97.10 352	96.65 362	98.56 402

LFMVS		97.90 293	97.35 343	99.54 125	99.52 224	99.01 177	99.39 280	98.24 452	97.10 324	99.65 137	99.79 167	84.79 452	99.91 135	99.28 94	98.38 279	99.69 152

HQP_MVS		98.27 243	98.22 236	98.44 334	99.29 302	96.97 354	99.39 280	99.47 224	98.97 75	99.11 278	99.61 267	92.71 346	99.69 289	97.78 292	97.63 321	98.67 363

plane_prior2							99.39 280		98.97 75

CHOSEN 1792x2688		99.19 101	99.10 99	99.45 167	99.89 8	98.52 259	99.39 280	99.94 1	98.73 102	99.11 278	99.89 44	95.50 229	99.94 92	99.50 57	99.97 9	99.89 29

PAPM_NR		99.04 157	98.84 174	99.66 91	99.74 100	99.44 116	99.39 280	99.38 290	97.70 258	99.28 238	99.28 373	98.34 97	99.85 187	96.96 362	99.45 179	99.69 152

gg-mvs-nofinetune		96.17 396	95.32 408	98.73 292	98.79 402	98.14 283	99.38 285	94.09 483	91.07 460	98.07 403	91.04 481	89.62 407	99.35 354	96.75 372	99.09 228	98.68 355

VDDNet		97.55 347	97.02 369	99.16 223	99.49 241	98.12 286	99.38 285	99.30 339	95.35 414	99.68 117	99.90 35	82.62 462	99.93 110	99.31 86	98.13 302	99.42 259

ME-MVS		99.56 21	99.46 28	99.86 34	99.80 63	99.81 33	99.37 287	99.70 18	99.18 34	99.83 64	99.83 104	98.74 65	99.93 110	98.83 170	99.89 68	99.83 63

MGCNet		99.15 115	98.96 144	99.73 83	98.92 384	99.37 123	99.37 287	96.92 469	99.51 2	99.66 128	99.78 174	96.69 167	99.97 29	99.84 28	99.97 9	99.84 53

pmmvs6		96.53 388	96.09 393	97.82 393	98.69 421	95.47 412	99.37 287	99.47 224	93.46 443	97.41 421	99.78 174	87.06 436	99.33 357	96.92 367	92.70 443	98.65 374

PM-MVS		92.96 432	92.23 436	95.14 441	95.61 470	89.98 467	99.37 287	98.21 454	94.80 428	95.04 455	97.69 459	65.06 476	97.90 458	94.30 425	89.98 458	97.54 461

WTY-MVS		99.06 152	98.88 165	99.61 109	99.62 176	99.16 155	99.37 287	99.56 90	98.04 214	99.53 174	99.62 263	96.84 159	99.94 92	98.85 164	98.49 275	99.72 135

IterMVS-LS		98.46 224	98.42 223	98.58 309	99.59 195	98.00 291	99.37 287	99.43 267	96.94 340	99.07 287	99.59 272	97.87 114	99.03 412	98.32 241	95.62 392	98.71 341
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
h-mvs33		97.70 332	97.28 355	98.97 245	99.70 122	97.27 328	99.36 293	99.45 247	98.94 78	99.66 128	99.64 252	94.93 254	99.99 4	99.48 64	84.36 469	99.65 173

DPE-MVS		99.46 42	99.32 54	99.91 6	99.78 70	99.88 10	99.36 293	99.51 154	98.73 102	99.88 43	99.84 98	98.72 67	99.96 41	98.16 254	99.87 79	99.88 35
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UnsupCasMVSNet_eth		96.44 390	96.12 391	97.40 413	98.65 424	95.65 405	99.36 293	99.51 154	97.13 318	96.04 447	98.99 409	88.40 422	98.17 451	96.71 374	90.27 456	98.40 420

sss		99.17 109	99.05 112	99.53 133	99.62 176	98.97 183	99.36 293	99.62 51	97.83 239	99.67 123	99.65 246	97.37 128	99.95 76	99.19 106	99.19 203	99.68 158

DeepC-MVS_fast	98.69 1	99.49 33	99.39 40	99.77 74	99.63 167	99.59 88	99.36 293	99.46 236	99.07 58	99.79 76	99.82 117	98.85 44	99.92 123	98.68 192	99.87 79	99.82 72
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 96	99.14 94	99.59 113	99.41 266	99.16 155	99.35 298	99.57 85	98.82 89	99.51 178	99.61 267	96.46 181	99.95 76	99.59 45	99.98 4	99.65 173

pmmvs-eth3d		95.34 411	94.73 414	97.15 417	95.53 472	95.94 398	99.35 298	99.10 375	95.13 416	93.55 462	97.54 463	88.15 426	97.91 457	94.58 422	89.69 461	97.61 457

MDTV_nov1_ep13_2view						95.18 422	99.35 298		96.84 345	99.58 161		95.19 245		97.82 287		99.46 252

VDD-MVS		97.73 326	97.35 343	98.88 268	99.47 249	97.12 336	99.34 301	98.85 414	98.19 170	99.67 123	99.85 83	82.98 460	99.92 123	99.49 61	98.32 286	99.60 193

COLMAP_ROB	97.56 6	98.86 182	98.75 183	99.17 222	99.88 13	98.53 255	99.34 301	99.59 73	97.55 275	98.70 351	99.89 44	95.83 214	99.90 148	98.10 260	99.90 57	99.08 298
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
viewmambaseed2359dif		99.01 164	98.90 158	99.32 195	99.58 197	98.51 261	99.33 303	99.54 109	97.85 235	99.44 192	99.85 83	96.01 203	99.79 243	99.41 70	99.13 211	99.67 162

myMVS_eth3d28		97.69 333	97.34 346	98.73 292	99.27 307	97.52 319	99.33 303	98.78 424	98.03 216	98.82 333	98.49 437	86.64 437	99.46 327	98.44 227	98.24 292	99.23 286

EGC-MVSNET		82.80 445	77.86 451	97.62 403	97.91 445	96.12 394	99.33 303	99.28 345	8.40 489	25.05 490	99.27 376	84.11 455	99.33 357	89.20 461	98.22 293	97.42 463

diffmvs_AUTHOR		99.19 101	99.10 99	99.48 158	99.64 163	98.85 219	99.32 306	99.48 202	98.50 124	99.81 69	99.81 132	96.82 160	99.88 168	99.40 71	99.12 216	99.71 146

ETVMVS		97.50 353	96.90 373	99.29 205	99.23 318	98.78 233	99.32 306	98.90 407	97.52 281	98.56 371	98.09 455	84.72 453	99.69 289	97.86 282	97.88 311	99.39 265

FMVSNet5		96.43 391	96.19 390	97.15 417	99.11 349	95.89 401	99.32 306	99.52 132	94.47 434	98.34 385	99.07 397	87.54 432	97.07 468	92.61 449	95.72 389	98.47 411

dp		97.75 322	97.80 280	97.59 407	99.10 352	93.71 448	99.32 306	98.88 410	96.48 374	99.08 286	99.55 287	92.67 349	99.82 225	96.52 382	98.58 267	99.24 285

tpmvs		97.98 281	98.02 258	97.84 389	99.04 366	94.73 430	99.31 310	99.20 363	96.10 405	98.76 341	99.42 330	94.94 253	99.81 230	96.97 361	98.45 276	98.97 313

tpmrst		98.33 237	98.48 220	97.90 382	99.16 341	94.78 429	99.31 310	99.11 374	97.27 306	99.45 187	99.59 272	95.33 237	99.84 196	98.48 221	98.61 264	99.09 297

testing99		97.36 363	96.94 372	98.63 303	99.18 331	96.70 370	99.30 312	98.93 397	97.71 255	98.23 391	98.26 447	84.92 451	99.84 196	98.04 270	97.85 314	99.35 271

MP-MVS-pluss		99.37 68	99.20 86	99.88 15	99.90 4	99.87 17	99.30 312	99.52 132	97.18 314	99.60 157	99.79 167	98.79 52	99.95 76	98.83 170	99.91 46	99.83 63
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
NCCC		99.34 75	99.19 88	99.79 68	99.61 187	99.65 75	99.30 312	99.48 202	98.86 84	99.21 259	99.63 258	98.72 67	99.90 148	98.25 246	99.63 164	99.80 88

JIA-IIPM		97.50 353	97.02 369	98.93 252	98.73 414	97.80 306	99.30 312	98.97 393	91.73 456	98.91 316	94.86 475	95.10 248	99.71 277	97.58 312	97.98 306	99.28 279

BH-RMVSNet		98.41 229	98.08 250	99.40 179	99.41 266	98.83 224	99.30 312	98.77 425	97.70 258	98.94 313	99.65 246	92.91 339	99.74 261	96.52 382	99.55 172	99.64 180

usedtu_blend_shiyan5		95.04 415	94.10 422	97.86 386	96.45 465	95.92 399	99.29 317	99.22 358	86.17 472	98.36 383	97.68 460	91.20 387	99.07 405	97.53 320	80.97 476	98.60 397

testing11		97.50 353	97.10 366	98.71 297	99.20 325	96.91 362	99.29 317	98.82 417	97.89 229	98.21 394	98.40 441	85.63 446	99.83 216	98.45 226	98.04 305	99.37 269

Syy-MVS		97.09 377	97.14 363	96.95 426	99.00 371	92.73 458	99.29 317	99.39 282	97.06 328	97.41 421	98.15 450	93.92 315	98.68 442	91.71 452	98.34 280	99.45 255

myMVS_eth3d		96.89 380	96.37 385	98.43 336	99.00 371	97.16 334	99.29 317	99.39 282	97.06 328	97.41 421	98.15 450	83.46 459	98.68 442	95.27 413	98.34 280	99.45 255

MCST-MVS		99.43 53	99.30 62	99.82 57	99.79 68	99.74 54	99.29 317	99.40 279	98.79 95	99.52 176	99.62 263	98.91 39	99.90 148	98.64 196	99.75 142	99.82 72

LF4IMVS		97.52 350	97.46 325	97.70 400	98.98 377	95.55 408	99.29 317	98.82 417	98.07 200	98.66 354	99.64 252	89.97 401	99.61 312	97.01 357	96.68 361	97.94 450

hse-mvs2		97.50 353	97.14 363	98.59 306	99.49 241	97.05 343	99.28 323	99.22 358	98.94 78	99.66 128	99.42 330	94.93 254	99.65 300	99.48 64	83.80 471	99.08 298

OPM-MVS		98.19 248	98.10 246	98.45 331	98.88 389	97.07 341	99.28 323	99.38 290	98.57 117	99.22 256	99.81 132	92.12 363	99.66 295	98.08 265	97.54 330	98.61 394
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
diffmvs		99.14 122	99.02 126	99.51 144	99.61 187	98.96 187	99.28 323	99.49 190	98.46 128	99.72 102	99.71 210	96.50 179	99.88 168	99.31 86	99.11 218	99.67 162
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		98.86 182	98.80 177	99.03 237	99.76 82	98.79 230	99.28 323	99.91 3	97.42 294	99.67 123	99.37 348	97.53 122	99.88 168	98.98 137	97.29 350	98.42 417

OMC-MVS		99.08 147	99.04 114	99.20 219	99.67 136	98.22 279	99.28 323	99.52 132	98.07 200	99.66 128	99.81 132	97.79 117	99.78 249	97.79 291	99.81 120	99.60 193

testing222		97.16 373	96.50 382	99.16 223	99.16 341	98.47 268	99.27 328	98.66 440	97.71 255	98.23 391	98.15 450	82.28 465	99.84 196	97.36 337	97.66 320	99.18 289

AUN-MVS		96.88 381	96.31 387	98.59 306	99.48 248	97.04 346	99.27 328	99.22 358	97.44 291	98.51 374	99.41 334	91.97 366	99.66 295	97.71 303	83.83 470	99.07 303

pmmvs5		97.52 350	97.30 352	98.16 360	98.57 433	96.73 369	99.27 328	98.90 407	96.14 399	98.37 382	99.53 296	91.54 380	99.14 392	97.51 323	95.87 384	98.63 383

1314		98.68 211	98.54 216	99.11 229	98.89 388	98.65 242	99.27 328	99.49 190	96.89 342	97.99 405	99.56 284	97.72 120	99.83 216	97.74 299	99.27 194	98.84 321

MVS		97.28 368	96.55 381	99.48 158	98.78 405	98.95 193	99.27 328	99.39 282	83.53 475	98.08 400	99.54 292	96.97 151	99.87 175	94.23 428	99.16 204	99.63 185

BH-untuned		98.42 227	98.36 226	98.59 306	99.49 241	96.70 370	99.27 328	99.13 372	97.24 310	98.80 336	99.38 345	95.75 220	99.74 261	97.07 356	99.16 204	99.33 275

MDTV_nov1_ep13			98.32 230		99.11 349	94.44 438	99.27 328	98.74 429	97.51 282	99.40 208	99.62 263	94.78 265	99.76 255	97.59 311	98.81 256

DP-MVS Recon		99.12 133	98.95 148	99.65 95	99.74 100	99.70 60	99.27 328	99.57 85	96.40 381	99.42 198	99.68 233	98.75 60	99.80 237	97.98 273	99.72 148	99.44 257

PatchmatchNet		98.31 238	98.36 226	98.19 358	99.16 341	95.32 418	99.27 328	98.92 400	97.37 298	99.37 214	99.58 276	94.90 258	99.70 284	97.43 333	99.21 201	99.54 217
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thres200		97.61 344	97.28 355	98.62 304	99.64 163	98.03 289	99.26 337	98.74 429	97.68 260	99.09 284	98.32 445	91.66 377	99.81 230	92.88 445	98.22 293	98.03 442

CNVR-MVS		99.42 55	99.30 62	99.78 71	99.62 176	99.71 58	99.26 337	99.52 132	98.82 89	99.39 210	99.71 210	98.96 27	99.85 187	98.59 207	99.80 125	99.77 100

mamba_0408		99.08 147	98.96 144	99.44 172	99.62 176	98.88 211	99.25 339	99.47 224	98.05 207	99.37 214	99.81 132	96.85 155	99.85 187	98.98 137	99.25 197	99.60 193

SSM_04072		99.06 152	98.96 144	99.35 188	99.62 176	98.88 211	99.25 339	99.47 224	98.05 207	99.37 214	99.81 132	96.85 155	99.58 315	98.98 137	99.25 197	99.60 193

tt0320		95.71 406	95.07 410	97.62 403	99.05 364	95.02 424	99.25 339	99.52 132	86.81 469	97.97 407	99.72 207	83.58 458	99.15 390	96.38 388	93.35 432	98.68 355

1112_ss		98.98 168	98.77 181	99.59 113	99.68 133	99.02 175	99.25 339	99.48 202	97.23 311	99.13 274	99.58 276	96.93 153	99.90 148	98.87 157	98.78 257	99.84 53

TAPA-MVS	97.07 15	97.74 324	97.34 346	98.94 250	99.70 122	97.53 318	99.25 339	99.51 154	91.90 455	99.30 234	99.63 258	98.78 53	99.64 304	88.09 466	99.87 79	99.65 173
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
UWE-MVS-28		97.36 363	97.24 359	97.75 396	98.84 398	94.44 438	99.24 344	97.58 465	97.98 221	99.00 302	99.00 407	91.35 383	99.53 322	93.75 433	98.39 278	99.27 283

UBG		97.85 300	97.48 320	98.95 248	99.25 314	97.64 315	99.24 344	98.74 429	97.90 228	98.64 361	98.20 449	88.65 418	99.81 230	98.27 244	98.40 277	99.42 259

PLC	97.94 4	99.02 160	98.85 172	99.53 133	99.66 149	99.01 177	99.24 344	99.52 132	96.85 344	99.27 244	99.48 316	98.25 101	99.91 135	97.76 296	99.62 165	99.65 173
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test_post1							99.23 347				65.14 487	94.18 304	99.71 277	97.58 312

ADS-MVSNet2		98.02 274	98.07 253	97.87 384	99.33 289	95.19 421	99.23 347	99.08 378	96.24 389	99.10 281	99.67 239	94.11 306	98.93 431	96.81 370	99.05 231	99.48 241

ADS-MVSNet		98.20 247	98.08 250	98.56 314	99.33 289	96.48 381	99.23 347	99.15 369	96.24 389	99.10 281	99.67 239	94.11 306	99.71 277	96.81 370	99.05 231	99.48 241

EPNet_dtu		98.03 272	97.96 263	98.23 356	98.27 441	95.54 410	99.23 347	98.75 426	99.02 62	97.82 414	99.71 210	96.11 198	99.48 324	93.04 443	99.65 161	99.69 152
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		98.17 251	97.93 268	98.87 272	99.18 331	98.49 264	99.22 351	99.33 320	96.96 336	99.56 165	99.38 345	94.33 297	99.00 417	94.83 421	98.58 267	99.14 290

RPMNet		96.72 384	95.90 397	99.19 220	99.18 331	98.49 264	99.22 351	99.52 132	88.72 467	99.56 165	97.38 465	94.08 308	99.95 76	86.87 473	98.58 267	99.14 290

sc_t1		95.75 404	95.05 411	97.87 384	98.83 399	94.61 435	99.21 353	99.45 247	87.45 468	97.97 407	99.85 83	81.19 468	99.43 338	98.27 244	93.20 436	99.57 211

WBMVS		97.74 324	97.50 318	98.46 329	99.24 316	97.43 322	99.21 353	99.42 269	97.45 288	98.96 309	99.41 334	88.83 413	99.23 374	98.94 145	96.02 377	98.71 341

plane_prior						96.97 354	99.21 353		98.45 130						97.60 324

IMVS_0404		98.53 220	98.52 218	98.55 316	99.55 210	96.93 357	99.20 356	99.44 256	98.05 207	98.96 309	99.80 150	94.66 279	99.13 395	98.15 256	98.92 242	99.60 193

tt0320-xc		95.31 412	94.59 416	97.45 411	98.92 384	94.73 430	99.20 356	99.31 334	86.74 470	97.23 427	99.72 207	81.14 469	98.95 429	97.08 355	91.98 447	98.67 363

testing91		97.44 360	97.02 369	98.71 297	99.18 331	96.89 364	99.19 358	99.04 385	97.78 247	98.31 386	98.29 446	85.41 448	99.85 187	98.01 271	97.95 307	99.39 265

WR-MVS		98.06 264	97.73 293	99.06 233	98.86 395	99.25 146	99.19 358	99.35 307	97.30 304	98.66 354	99.43 328	93.94 313	99.21 384	98.58 208	94.28 419	98.71 341

new-patchmatchnet		94.48 423	94.08 424	95.67 440	95.08 475	92.41 459	99.18 360	99.28 345	94.55 433	93.49 463	97.37 466	87.86 430	97.01 469	91.57 453	88.36 463	97.61 457

AdaColmap		99.01 164	98.80 177	99.66 91	99.56 206	99.54 98	99.18 360	99.70 18	98.18 173	99.35 223	99.63 258	96.32 188	99.90 148	97.48 326	99.77 137	99.55 215

EG-PatchMatch MVS		95.97 400	95.69 401	96.81 430	97.78 448	92.79 457	99.16 362	98.93 397	96.16 396	94.08 459	99.22 382	82.72 461	99.47 325	95.67 404	97.50 335	98.17 433

PatchT		97.03 378	96.44 384	98.79 287	98.99 374	98.34 274	99.16 362	99.07 381	92.13 454	99.52 176	97.31 468	94.54 287	98.98 419	88.54 464	98.73 259	99.03 306

CNLPA		99.14 122	98.99 136	99.59 113	99.58 197	99.41 120	99.16 362	99.44 256	98.45 130	99.19 265	99.49 310	98.08 109	99.89 163	97.73 300	99.75 142	99.48 241

MDA-MVSNet-bldmvs		94.96 418	93.98 425	97.92 380	98.24 442	97.27 328	99.15 365	99.33 320	93.80 438	80.09 482	99.03 403	88.31 423	97.86 459	93.49 437	94.36 418	98.62 385

CDPH-MVS		99.13 125	98.91 156	99.80 64	99.75 92	99.71 58	99.15 365	99.41 272	96.60 365	99.60 157	99.55 287	98.83 47	99.90 148	97.48 326	99.83 113	99.78 98

save fliter					99.76 82	99.59 88	99.14 367	99.40 279	99.00 67

WB-MVSnew		97.65 341	97.65 301	97.63 402	98.78 405	97.62 316	99.13 368	98.33 449	97.36 299	99.07 287	98.94 415	95.64 225	99.15 390	92.95 444	98.68 262	96.12 473

testf1		90.42 439	90.68 440	89.65 460	97.78 448	73.97 488	99.13 368	98.81 419	89.62 462	91.80 471	98.93 416	62.23 479	98.80 438	86.61 474	91.17 450	96.19 471

APD_test2		90.42 439	90.68 440	89.65 460	97.78 448	73.97 488	99.13 368	98.81 419	89.62 462	91.80 471	98.93 416	62.23 479	98.80 438	86.61 474	91.17 450	96.19 471

xiu_mvs_v1_base_debu		99.29 85	99.27 73	99.34 189	99.63 167	98.97 183	99.12 371	99.51 154	98.86 84	99.84 56	99.47 319	98.18 104	99.99 4	99.50 57	99.31 191	99.08 298

xiu_mvs_v1_base		99.29 85	99.27 73	99.34 189	99.63 167	98.97 183	99.12 371	99.51 154	98.86 84	99.84 56	99.47 319	98.18 104	99.99 4	99.50 57	99.31 191	99.08 298

xiu_mvs_v1_base_debi		99.29 85	99.27 73	99.34 189	99.63 167	98.97 183	99.12 371	99.51 154	98.86 84	99.84 56	99.47 319	98.18 104	99.99 4	99.50 57	99.31 191	99.08 298

XVG-OURS-SEG-HR		98.69 210	98.62 206	98.89 264	99.71 117	97.74 307	99.12 371	99.54 109	98.44 133	99.42 198	99.71 210	94.20 301	99.92 123	98.54 218	98.90 248	99.00 309

jason		99.13 125	99.03 117	99.45 167	99.46 251	98.87 215	99.12 371	99.26 350	98.03 216	99.79 76	99.65 246	97.02 148	99.85 187	99.02 134	99.90 57	99.65 173
jason: jason.
N_pmnet		94.95 419	95.83 399	92.31 451	98.47 437	79.33 483	99.12 371	92.81 489	93.87 437	97.68 417	99.13 392	93.87 317	99.01 416	91.38 454	96.19 374	98.59 399

MDA-MVSNet_test_wron		95.45 408	94.60 415	98.01 371	98.16 443	97.21 333	99.11 377	99.24 355	93.49 442	80.73 481	98.98 411	93.02 334	98.18 450	94.22 429	94.45 416	98.64 376

Patchmtry		97.75 322	97.40 338	98.81 284	99.10 352	98.87 215	99.11 377	99.33 320	94.83 427	98.81 334	99.38 345	94.33 297	99.02 414	96.10 391	95.57 394	98.53 404

YYNet1		95.36 410	94.51 418	97.92 380	97.89 446	97.10 337	99.10 379	99.23 356	93.26 445	80.77 480	99.04 402	92.81 340	98.02 454	94.30 425	94.18 421	98.64 376

CANet_DTU		98.97 170	98.87 166	99.25 212	99.33 289	98.42 272	99.08 380	99.30 339	99.16 37	99.43 195	99.75 192	95.27 239	99.97 29	98.56 214	99.95 23	99.36 270

icg_test_0407_2		98.79 199	98.86 169	98.57 310	99.55 210	96.93 357	99.07 381	99.44 256	98.05 207	99.66 128	99.80 150	97.13 139	99.18 387	98.15 256	98.92 242	99.60 193

SCA		98.19 248	98.16 238	98.27 354	99.30 298	95.55 408	99.07 381	98.97 393	97.57 272	99.43 195	99.57 281	92.72 344	99.74 261	97.58 312	99.20 202	99.52 224

TSAR-MVS + GP.		99.36 72	99.36 46	99.36 186	99.67 136	98.61 249	99.07 381	99.33 320	99.00 67	99.82 68	99.81 132	99.06 18	99.84 196	99.09 125	99.42 181	99.65 173

MG-MVS		99.13 125	99.02 126	99.45 167	99.57 202	98.63 245	99.07 381	99.34 312	98.99 69	99.61 154	99.82 117	97.98 113	99.87 175	97.00 358	99.80 125	99.85 46

PatchMatch-RL		98.84 194	98.62 206	99.52 139	99.71 117	99.28 141	99.06 385	99.77 12	97.74 253	99.50 179	99.53 296	95.41 232	99.84 196	97.17 351	99.64 162	99.44 257

OpenMVS_ROB	92.34 20	94.38 424	93.70 430	96.41 435	97.38 454	93.17 455	99.06 385	98.75 426	86.58 471	94.84 456	98.26 447	81.53 466	99.32 359	89.01 462	97.87 312	96.76 466

TEST9					99.67 136	99.65 75	99.05 387	99.41 272	96.22 391	98.95 311	99.49 310	98.77 56	99.91 135

train_agg		99.02 160	98.77 181	99.77 74	99.67 136	99.65 75	99.05 387	99.41 272	96.28 385	98.95 311	99.49 310	98.76 57	99.91 135	97.63 308	99.72 148	99.75 111

lupinMVS		99.13 125	99.01 132	99.46 166	99.51 227	98.94 197	99.05 387	99.16 368	97.86 232	99.80 74	99.56 284	97.39 125	99.86 181	98.94 145	99.85 94	99.58 208

DELS-MVS		99.48 37	99.42 32	99.65 95	99.72 111	99.40 121	99.05 387	99.66 32	99.14 40	99.57 164	99.80 150	98.46 87	99.94 92	99.57 48	99.84 102	99.60 193
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		96.38 392	96.03 394	97.41 412	98.13 444	95.16 423	99.05 387	99.20 363	93.94 436	97.39 424	98.79 427	91.61 379	99.04 410	90.43 457	95.77 386	98.05 441

Patchmatch-test		97.93 287	97.65 301	98.77 290	99.18 331	97.07 341	99.03 392	99.14 371	96.16 396	98.74 342	99.57 281	94.56 284	99.72 271	93.36 438	99.11 218	99.52 224

test_8					99.67 136	99.61 85	99.03 392	99.41 272	96.28 385	98.93 314	99.48 316	98.76 57	99.91 135

Test_1112_low_res		98.89 175	98.66 196	99.57 120	99.69 127	98.95 193	99.03 392	99.47 224	96.98 334	99.15 272	99.23 381	96.77 164	99.89 163	98.83 170	98.78 257	99.86 42

IterMVS-SCA-FT		97.82 310	97.75 291	98.06 367	99.57 202	96.36 385	99.02 395	99.49 190	97.18 314	98.71 345	99.72 207	92.72 344	99.14 392	97.44 332	95.86 385	98.67 363

xiu_mvs_v2_base		99.26 92	99.25 77	99.29 205	99.53 218	98.91 204	99.02 395	99.45 247	98.80 94	99.71 110	99.26 378	98.94 34	99.98 20	99.34 81	99.23 200	98.98 312

MIMVSNet		97.73 326	97.45 326	98.57 310	99.45 257	97.50 320	99.02 395	98.98 392	96.11 401	99.41 203	99.14 391	90.28 395	98.74 440	95.74 400	98.93 240	99.47 247

IterMVS		97.83 307	97.77 286	98.02 370	99.58 197	96.27 389	99.02 395	99.48 202	97.22 312	98.71 345	99.70 214	92.75 341	99.13 395	97.46 329	96.00 379	98.67 363
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		99.11 139	98.92 153	99.65 95	99.90 4	99.37 123	99.02 395	99.91 3	97.67 262	99.59 160	99.75 192	95.90 211	99.73 267	99.53 53	99.02 235	99.86 42

UWE-MVS		97.58 346	97.29 354	98.48 323	99.09 355	96.25 390	99.01 400	96.61 475	97.86 232	99.19 265	99.01 406	88.72 414	99.90 148	97.38 336	98.69 261	99.28 279

新几何2							99.01 400

BH-w/o		98.00 279	97.89 274	98.32 346	99.35 283	96.20 392	99.01 400	98.90 407	96.42 379	98.38 381	99.00 407	95.26 241	99.72 271	96.06 392	98.61 264	99.03 306

test_prior4						99.56 94	98.99 403

无先验							98.99 403	99.51 154	96.89 342				99.93 110	97.53 320		99.72 135

pmmvs4		98.13 255	97.90 270	98.81 284	98.61 429	98.87 215	98.99 403	99.21 362	96.44 377	99.06 292	99.58 276	95.90 211	99.11 401	97.18 350	96.11 376	98.46 414

HQP-NCC					99.19 328		98.98 406		98.24 162	98.66 354

ACMP_Plane					99.19 328		98.98 406		98.24 162	98.66 354

HQP-MVS		98.02 274	97.90 270	98.37 342	99.19 328	96.83 365	98.98 406	99.39 282	98.24 162	98.66 354	99.40 338	92.47 355	99.64 304	97.19 348	97.58 326	98.64 376

PS-MVSNAJ		99.32 79	99.32 54	99.30 202	99.57 202	98.94 197	98.97 409	99.46 236	98.92 81	99.71 110	99.24 380	99.01 20	99.98 20	99.35 76	99.66 159	98.97 313

MVP-Stereo		97.81 312	97.75 291	97.99 374	97.53 452	96.60 378	98.96 410	98.85 414	97.22 312	97.23 427	99.36 351	95.28 238	99.46 327	95.51 406	99.78 134	97.92 452
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test_prior2							98.96 410		98.34 143	99.01 298	99.52 300	98.68 70		97.96 274	99.74 145

旧先验2							98.96 410		96.70 353	99.47 184			99.94 92	98.19 250

原ACMM2							98.95 413

MVS_111021_HR		99.41 59	99.32 54	99.66 91	99.72 111	99.47 113	98.95 413	99.85 9	98.82 89	99.54 172	99.73 203	98.51 84	99.74 261	98.91 151	99.88 76	99.77 100

mvsany_test1		99.50 31	99.46 28	99.62 108	99.61 187	99.09 165	98.94 415	99.48 202	99.10 48	99.96 27	99.91 26	98.85 44	99.96 41	99.72 32	99.58 169	99.82 72

MVS_111021_LR		99.41 59	99.33 52	99.65 95	99.77 78	99.51 107	98.94 415	99.85 9	98.82 89	99.65 137	99.74 197	98.51 84	99.80 237	98.83 170	99.89 68	99.64 180

pmmvs3		94.09 426	93.25 433	96.60 433	94.76 478	94.49 437	98.92 417	98.18 456	89.66 461	96.48 441	98.06 456	86.28 441	97.33 466	89.68 460	87.20 466	97.97 449

XVG-OURS		98.73 208	98.68 192	98.88 268	99.70 122	97.73 308	98.92 417	99.55 100	98.52 122	99.45 187	99.84 98	95.27 239	99.91 135	98.08 265	98.84 252	99.00 309

test222					99.75 92	99.49 109	98.91 419	99.49 190	96.42 379	99.34 227	99.65 246	98.28 100			99.69 153	99.72 135

PMMVS2		86.87 442	85.37 446	91.35 455	90.21 484	83.80 474	98.89 420	97.45 467	83.13 476	91.67 473	95.03 473	48.49 485	94.70 479	85.86 476	77.62 478	95.54 474

miper_lstm_enhance		98.00 279	97.91 269	98.28 353	99.34 288	97.43 322	98.88 421	99.36 300	96.48 374	98.80 336	99.55 287	95.98 204	98.91 432	97.27 341	95.50 397	98.51 407

MVS-HIRNet		95.75 404	95.16 409	97.51 409	99.30 298	93.69 449	98.88 421	95.78 477	85.09 474	98.78 339	92.65 477	91.29 385	99.37 347	94.85 420	99.85 94	99.46 252

TR-MVS		97.76 318	97.41 337	98.82 281	99.06 361	97.87 302	98.87 423	98.56 443	96.63 361	98.68 353	99.22 382	92.49 354	99.65 300	95.40 410	97.79 316	98.95 317

testdata1							98.85 424		98.32 147

blend_shiyan4		95.25 413	94.39 420	97.84 389	96.70 464	95.92 399	98.84 425	99.28 345	92.21 453	98.16 397	97.84 458	87.10 435	99.07 405	97.53 320	81.87 473	98.54 403

ET-MVSNet_ETH3D		96.49 389	95.64 403	99.05 235	99.53 218	98.82 227	98.84 425	97.51 466	97.63 265	84.77 475	99.21 385	92.09 364	98.91 432	98.98 137	92.21 446	99.41 262

our_test_3		97.65 341	97.68 298	97.55 408	98.62 427	94.97 426	98.84 425	99.30 339	96.83 347	98.19 395	99.34 358	97.01 150	99.02 414	95.00 418	96.01 378	98.64 376

MS-PatchMatch		97.24 372	97.32 350	96.99 423	98.45 438	93.51 453	98.82 428	99.32 330	97.41 295	98.13 399	99.30 369	88.99 411	99.56 318	95.68 403	99.80 125	97.90 453

c3_l		98.12 257	98.04 255	98.38 341	99.30 298	97.69 314	98.81 429	99.33 320	96.67 355	98.83 331	99.34 358	97.11 142	98.99 418	97.58 312	95.34 399	98.48 409

ppachtmachnet_test		97.49 358	97.45 326	97.61 406	98.62 427	95.24 419	98.80 430	99.46 236	96.11 401	98.22 393	99.62 263	96.45 182	98.97 426	93.77 432	95.97 383	98.61 394

PAPR		98.63 217	98.34 228	99.51 144	99.40 271	99.03 174	98.80 430	99.36 300	96.33 382	99.00 302	99.12 395	98.46 87	99.84 196	95.23 414	99.37 190	99.66 167

test0.0.03 1		97.71 331	97.42 336	98.56 314	98.41 440	97.82 305	98.78 432	98.63 441	97.34 300	98.05 404	98.98 411	94.45 292	98.98 419	95.04 417	97.15 356	98.89 318

PVSNet_Blended		99.08 147	98.97 140	99.42 177	99.76 82	98.79 230	98.78 432	99.91 3	96.74 350	99.67 123	99.49 310	97.53 122	99.88 168	98.98 137	99.85 94	99.60 193

PMMVS		98.80 198	98.62 206	99.34 189	99.27 307	98.70 238	98.76 434	99.31 334	97.34 300	99.21 259	99.07 397	97.20 137	99.82 225	98.56 214	98.87 249	99.52 224

test123		39.01 454	42.50 456	28.53 470	39.17 493	20.91 495	98.75 435	19.17 495	19.83 488	38.57 487	66.67 485	33.16 489	15.42 489	37.50 489	29.66 487	49.26 484

MSDG		98.98 168	98.80 177	99.53 133	99.76 82	99.19 150	98.75 435	99.55 100	97.25 308	99.47 184	99.77 183	97.82 116	99.87 175	96.93 365	99.90 57	99.54 217

CLD-MVS		98.16 252	98.10 246	98.33 344	99.29 302	96.82 367	98.75 435	99.44 256	97.83 239	99.13 274	99.55 287	92.92 337	99.67 292	98.32 241	97.69 319	98.48 409
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		98.18 250	98.10 246	98.41 337	99.23 318	97.72 310	98.72 438	99.31 334	96.60 365	98.88 321	99.29 371	97.29 132	99.13 395	97.60 310	95.99 380	98.38 422

cl____		98.01 277	97.84 278	98.55 316	99.25 314	97.97 293	98.71 439	99.34 312	96.47 376	98.59 370	99.54 292	95.65 224	99.21 384	97.21 344	95.77 386	98.46 414

DIV-MVS_self_test		98.01 277	97.85 277	98.48 323	99.24 316	97.95 298	98.71 439	99.35 307	96.50 370	98.60 369	99.54 292	95.72 222	99.03 412	97.21 344	95.77 386	98.46 414

test-LLR		98.06 264	97.90 270	98.55 316	98.79 402	97.10 337	98.67 441	97.75 461	97.34 300	98.61 367	98.85 421	94.45 292	99.45 329	97.25 342	99.38 183	99.10 293

TESTMET0.1,1		97.55 347	97.27 358	98.40 339	98.93 382	96.53 379	98.67 441	97.61 464	96.96 336	98.64 361	99.28 373	88.63 420	99.45 329	97.30 340	99.38 183	99.21 288

test-mter		97.49 358	97.13 365	98.55 316	98.79 402	97.10 337	98.67 441	97.75 461	96.65 357	98.61 367	98.85 421	88.23 424	99.45 329	97.25 342	99.38 183	99.10 293

mvs5depth		96.66 385	96.22 389	97.97 375	97.00 463	96.28 388	98.66 444	99.03 387	96.61 362	96.93 437	99.79 167	87.20 434	99.47 325	96.65 380	94.13 422	98.16 434

IB-MVS	95.67 18	96.22 393	95.44 407	98.57 310	99.21 323	96.70 370	98.65 445	97.74 463	96.71 352	97.27 426	98.54 436	86.03 443	99.92 123	98.47 224	86.30 467	99.10 293
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		98.95 171	98.71 189	99.66 91	99.63 167	99.55 96	98.64 446	99.10 375	97.93 225	99.42 198	99.55 287	98.67 72	99.80 237	95.80 399	99.68 156	99.61 190

thisisatest0515		98.14 254	97.79 281	99.19 220	99.50 239	98.50 263	98.61 447	96.82 471	96.95 338	99.54 172	99.43 328	91.66 377	99.86 181	98.08 265	99.51 174	99.22 287

DeepPCF-MVS	98.18 3	98.81 195	99.37 44	97.12 420	99.60 193	91.75 462	98.61 447	99.44 256	99.35 25	99.83 64	99.85 83	98.70 69	99.81 230	99.02 134	99.91 46	99.81 79

cl22		97.85 300	97.64 304	98.48 323	99.09 355	97.87 302	98.60 449	99.33 320	97.11 323	98.87 324	99.22 382	92.38 360	99.17 389	98.21 248	95.99 380	98.42 417

FE-MVSNET3		98.09 259	97.82 279	98.89 264	98.70 419	98.90 208	98.57 450	99.47 224	96.78 348	98.87 324	99.05 400	94.75 270	99.23 374	97.45 331	96.74 360	98.53 404

GA-MVS		97.85 300	97.47 323	99.00 241	99.38 276	97.99 292	98.57 450	99.15 369	97.04 331	98.90 318	99.30 369	89.83 403	99.38 344	96.70 375	98.33 282	99.62 188

TinyColmap		97.12 375	96.89 374	97.83 391	99.07 359	95.52 411	98.57 450	98.74 429	97.58 271	97.81 415	99.79 167	88.16 425	99.56 318	95.10 415	97.21 353	98.39 421

eth_miper_zixun_eth		98.05 269	97.96 263	98.33 344	99.26 310	97.38 324	98.56 453	99.31 334	96.65 357	98.88 321	99.52 300	96.58 174	99.12 400	97.39 335	95.53 396	98.47 411

CMPMVS	69.68 23	94.13 425	94.90 413	91.84 452	97.24 458	80.01 482	98.52 454	99.48 202	89.01 465	91.99 469	99.67 239	85.67 445	99.13 395	95.44 408	97.03 358	96.39 470
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
USDC		97.34 365	97.20 360	97.75 396	99.07 359	95.20 420	98.51 455	99.04 385	97.99 220	98.31 386	99.86 76	89.02 410	99.55 320	95.67 404	97.36 348	98.49 408

ambc				93.06 450	92.68 481	82.36 475	98.47 456	98.73 435		95.09 454	97.41 464	55.55 481	99.10 403	96.42 385	91.32 449	97.71 454

miper_enhance_ethall		98.16 252	98.08 250	98.41 337	98.96 380	97.72 310	98.45 457	99.32 330	96.95 338	98.97 307	99.17 387	97.06 146	99.22 379	97.86 282	95.99 380	98.29 426

CHOSEN 280x420		99.12 133	99.13 95	99.08 230	99.66 149	97.89 301	98.43 458	99.71 16	98.88 83	99.62 149	99.76 187	96.63 170	99.70 284	99.46 67	99.99 1	99.66 167

testmvs		39.17 453	43.78 455	25.37 471	36.04 494	16.84 496	98.36 459	26.56 493	20.06 487	38.51 488	67.32 484	29.64 490	15.30 490	37.59 488	39.90 486	43.98 485

FPMVS		84.93 444	85.65 445	82.75 466	86.77 487	63.39 492	98.35 460	98.92 400	74.11 478	83.39 477	98.98 411	50.85 484	92.40 481	84.54 477	94.97 407	92.46 476

KD-MVS_2432*1600		94.62 420	93.72 428	97.31 414	97.19 460	95.82 402	98.34 461	99.20 363	95.00 423	97.57 418	98.35 443	87.95 427	98.10 452	92.87 446	77.00 479	98.01 443

miper_refine_blended		94.62 420	93.72 428	97.31 414	97.19 460	95.82 402	98.34 461	99.20 363	95.00 423	97.57 418	98.35 443	87.95 427	98.10 452	92.87 446	77.00 479	98.01 443

CL-MVSNet_self_test		94.49 422	93.97 426	96.08 438	96.16 467	93.67 450	98.33 463	99.38 290	95.13 416	97.33 425	98.15 450	92.69 348	96.57 471	88.67 463	79.87 477	97.99 447

PVSNet	96.02 17	98.85 191	98.84 174	98.89 264	99.73 107	97.28 327	98.32 464	99.60 67	97.86 232	99.50 179	99.57 281	96.75 165	99.86 181	98.56 214	99.70 152	99.54 217

PAPM		97.59 345	97.09 367	99.07 231	99.06 361	98.26 277	98.30 465	99.10 375	94.88 425	98.08 400	99.34 358	96.27 192	99.64 304	89.87 459	98.92 242	99.31 277

Patchmatch-RL test		95.84 402	95.81 400	95.95 439	95.61 470	90.57 465	98.24 466	98.39 447	95.10 420	95.20 452	98.67 431	94.78 265	97.77 460	96.28 390	90.02 457	99.51 233

UnsupCasMVSNet_bld		93.53 429	92.51 435	96.58 434	97.38 454	93.82 445	98.24 466	99.48 202	91.10 459	93.10 464	96.66 470	74.89 473	98.37 447	94.03 431	87.71 465	97.56 460

LCM-MVSNet		86.80 443	85.22 447	91.53 454	87.81 486	80.96 480	98.23 468	98.99 391	71.05 479	90.13 474	96.51 471	48.45 486	96.88 470	90.51 456	85.30 468	96.76 466

cascas		97.69 333	97.43 335	98.48 323	98.60 430	97.30 326	98.18 469	99.39 282	92.96 448	98.41 379	98.78 428	93.77 321	99.27 367	98.16 254	98.61 264	98.86 319

kuosan		90.92 438	90.11 443	93.34 447	98.78 405	85.59 472	98.15 470	93.16 487	89.37 464	92.07 468	98.38 442	81.48 467	95.19 477	62.54 486	97.04 357	99.25 284

Effi-MVS+		98.81 195	98.59 212	99.48 158	99.46 251	99.12 163	98.08 471	99.50 177	97.50 283	99.38 212	99.41 334	96.37 187	99.81 230	99.11 120	98.54 272	99.51 233

PCF-MVS	97.08 14	97.66 340	97.06 368	99.47 164	99.61 187	99.09 165	98.04 472	99.25 352	91.24 458	98.51 374	99.70 214	94.55 286	99.91 135	92.76 448	99.85 94	99.42 259
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet_0	94.43 19	96.09 398	95.47 405	97.94 378	99.31 297	94.34 442	97.81 473	99.70 18	97.12 320	97.46 420	98.75 429	89.71 404	99.79 243	97.69 306	81.69 474	99.68 158

E-PMN		80.61 447	79.88 449	82.81 465	90.75 483	76.38 486	97.69 474	95.76 478	66.44 483	83.52 476	92.25 478	62.54 478	87.16 485	68.53 484	61.40 482	84.89 483

dongtai		93.26 430	92.93 434	94.25 443	99.39 274	85.68 471	97.68 475	93.27 485	92.87 449	96.85 438	99.39 342	82.33 464	97.48 465	76.78 479	97.80 315	99.58 208

ANet_high		77.30 449	74.86 453	84.62 464	75.88 490	77.61 484	97.63 476	93.15 488	88.81 466	64.27 485	89.29 482	36.51 488	83.93 487	75.89 481	52.31 484	92.33 478

EMVS		80.02 448	79.22 450	82.43 467	91.19 482	76.40 485	97.55 477	92.49 490	66.36 484	83.01 478	91.27 480	64.63 477	85.79 486	65.82 485	60.65 483	85.08 482

MVE	76.82 21	76.91 450	74.31 454	84.70 463	85.38 489	76.05 487	96.88 478	93.17 486	67.39 482	71.28 484	89.01 483	21.66 493	87.69 484	71.74 483	72.29 481	90.35 480
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		91.10 436	91.36 438	90.31 457	95.85 468	73.72 490	94.89 479	99.25 352	68.39 481	95.82 448	99.02 405	80.50 470	98.95 429	93.64 435	94.89 411	98.25 429

Gipuma		90.99 437	90.15 442	93.51 446	98.73 414	90.12 466	93.98 480	99.45 247	79.32 477	92.28 467	94.91 474	69.61 474	97.98 456	87.42 470	95.67 390	92.45 477
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	70.75 22	75.98 451	74.97 452	79.01 468	70.98 491	55.18 493	93.37 481	98.21 454	65.08 485	61.78 486	93.83 476	21.74 492	92.53 480	78.59 478	91.12 452	89.34 481
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		82.80 445	81.52 448	86.66 462	66.61 492	68.44 491	92.79 482	97.92 458	68.96 480	80.04 483	99.85 83	85.77 444	96.15 475	97.86 282	43.89 485	95.39 475

wuyk23d		40.18 452	41.29 457	36.84 469	86.18 488	49.12 494	79.73 483	22.81 494	27.64 486	25.46 489	28.45 489	21.98 491	48.89 488	55.80 487	23.56 488	12.51 486

mmdepth		0.02 459	0.03 462	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.27 491	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

monomultidepth		0.02 459	0.03 462	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.27 491	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

test_blank		0.13 458	0.17 461	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	1.57 490	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

uanet_test		0.02 459	0.03 462	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.27 491	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

DCPMVS		0.02 459	0.03 462	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.27 491	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

cdsmvs_eth3d_5k		24.64 455	32.85 458	0.00 472	0.00 495	0.00 497	0.00 484	99.51 154	0.00 490	0.00 491	99.56 284	96.58 174	0.00 491	0.00 490	0.00 489	0.00 487

pcd_1.5k_mvsjas		8.27 457	11.03 460	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.27 491	99.01 20	0.00 491	0.00 490	0.00 489	0.00 487

sosnet-low-res		0.02 459	0.03 462	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.27 491	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

sosnet		0.02 459	0.03 462	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.27 491	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

uncertanet		0.02 459	0.03 462	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.27 491	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

Regformer		0.02 459	0.03 462	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.27 491	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

ab-mvs-re		8.30 456	11.06 459	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	99.58 276	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

uanet		0.02 459	0.03 462	0.00 472	0.00 495	0.00 497	0.00 484	0.00 496	0.00 490	0.00 491	0.27 491	0.00 494	0.00 491	0.00 490	0.00 489	0.00 487

WAC-MVS						97.16 334								95.47 407

MSC_two_6792asdad				99.87 21	99.51 227	99.76 49		99.33 320					99.96 41	98.87 157	99.84 102	99.89 29

PC_three_1452									98.18 173	99.84 56	99.70 214	99.31 3	98.52 445	98.30 243	99.80 125	99.81 79

No_MVS				99.87 21	99.51 227	99.76 49		99.33 320					99.96 41	98.87 157	99.84 102	99.89 29

test_one_0601					99.81 57	99.88 10		99.49 190	98.97 75	99.65 137	99.81 132	99.09 16

eth-test2					0.00 495

eth-test					0.00 495

ZD-MVS					99.71 117	99.79 41		99.61 60	96.84 345	99.56 165	99.54 292	98.58 78	99.96 41	96.93 365	99.75 142

IU-MVS					99.84 38	99.88 10		99.32 330	98.30 149	99.84 56				98.86 162	99.85 94	99.89 29

test_241102_TWO								99.48 202	99.08 56	99.88 43	99.81 132	98.94 34	99.96 41	98.91 151	99.84 102	99.88 35

test_241102_ONE					99.84 38	99.90 3		99.48 202	99.07 58	99.91 31	99.74 197	99.20 9	99.76 255

test_0728_THIRD									98.99 69	99.81 69	99.80 150	99.09 16	99.96 41	98.85 164	99.90 57	99.88 35

GSMVS																99.52 224

test_part2					99.81 57	99.83 22				99.77 85

sam_mvs1												94.86 260				99.52 224

sam_mvs												94.72 273

MTGPA								99.47 224

test_post											65.99 486	94.65 280	99.73 267

patchmatchnet-post											98.70 430	94.79 264	99.74 261

gm-plane-assit					98.54 435	92.96 456			94.65 431		99.15 390		99.64 304	97.56 317

test9_res														97.49 325	99.72 148	99.75 111

agg_prior2														97.21 344	99.73 147	99.75 111

agg_prior					99.67 136	99.62 83		99.40 279		98.87 324			99.91 135

TestCases				99.31 197	99.86 25	98.48 266		99.61 60	97.85 235	99.36 220	99.85 83	95.95 206	99.85 187	96.66 378	99.83 113	99.59 204

test_prior				99.68 89	99.67 136	99.48 111		99.56 90					99.83 216			99.74 116

新几何1				99.75 77	99.75 92	99.59 88		99.54 109	96.76 349	99.29 237	99.64 252	98.43 89	99.94 92	96.92 367	99.66 159	99.72 135

旧先验1					99.74 100	99.59 88		99.54 109			99.69 225	98.47 86			99.68 156	99.73 125

原ACMM1				99.65 95	99.73 107	99.33 130		99.47 224	97.46 285	99.12 276	99.66 244	98.67 72	99.91 135	97.70 305	99.69 153	99.71 146

testdata2													99.95 76	96.67 377

segment_acmp												98.96 27

testdata				99.54 125	99.75 92	98.95 193		99.51 154	97.07 326	99.43 195	99.70 214	98.87 42	99.94 92	97.76 296	99.64 162	99.72 135

test12				99.75 77	99.64 163	99.61 85		99.29 343		99.21 259		98.38 95	99.89 163		99.74 145	99.74 116

plane_prior7					99.29 302	97.03 349

plane_prior6					99.27 307	96.98 353						92.71 346

plane_prior5								99.47 224					99.69 289	97.78 292	97.63 321	98.67 363

plane_prior4											99.61 267

plane_prior3						97.00 351			98.69 107	99.11 278

plane_prior1					99.26 310

n2								0.00 496

nn								0.00 496

door-mid								98.05 457

lessismore_v0				97.79 395	98.69 421	95.44 415		94.75 481		95.71 449	99.87 68	88.69 416	99.32 359	95.89 396	94.93 409	98.62 385

LGP-MVS_train				98.49 321	99.33 289	97.05 343		99.55 100	97.46 285	99.24 251	99.83 104	92.58 351	99.72 271	98.09 261	97.51 333	98.68 355

test11								99.35 307

door								97.92 458

HQP5-MVS						96.83 365

BP-MVS														97.19 348

HQP4-MVS										98.66 354			99.64 304			98.64 376

HQP3-MVS								99.39 282							97.58 326

HQP2-MVS												92.47 355

NP-MVS					99.23 318	96.92 361					99.40 338

ACMMP++_ref															97.19 354

ACMMP++															97.43 344

Test By Simon												98.75 60

ITE_SJBPF				98.08 366	99.29 302	96.37 384		98.92 400	98.34 143	98.83 331	99.75 192	91.09 388	99.62 311	95.82 397	97.40 346	98.25 429

DeepMVS_CX				93.34 447	99.29 302	82.27 476		99.22 358	85.15 473	96.33 442	99.05 400	90.97 390	99.73 267	93.57 436	97.77 317	98.01 443

High-resolution multi-view benchmark