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	99.70 215	98.65 74	99.79 244	99.65 41	99.78 134	99.41 263

mmtdpeth		96.95 380	96.71 379	97.67 404	99.33 290	94.90 431	99.89 2	99.28 346	98.15 175	99.72 102	98.57 436	86.56 442	99.90 148	99.82 29	89.02 463	98.20 435

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	99.69 226	98.55 81	99.82 226	99.69 35	99.85 94	99.48 242

MVSFormer		99.17 109	99.12 97	99.29 206	99.51 228	98.94 197	99.88 4	99.46 237	97.55 276	99.80 74	99.65 247	97.39 125	99.28 365	99.03 133	99.85 94	99.65 174

test_djsdf		98.67 213	98.57 214	98.98 244	98.70 420	98.91 204	99.88 4	99.46 237	97.55 276	99.22 257	99.88 56	95.73 222	99.28 365	99.03 133	97.62 324	98.75 334

OurMVSNet-221017-0		97.88 296	97.77 287	98.19 359	98.71 419	96.53 380	99.88 4	99.00 393	97.79 246	98.78 340	99.94 6	91.68 375	99.35 355	97.21 347	96.99 360	98.69 351

EC-MVSNet		99.44 50	99.39 40	99.58 116	99.56 207	99.49 109	99.88 4	99.58 78	98.38 137	99.73 97	99.69 226	98.20 103	99.70 285	99.64 43	99.82 117	99.54 218

DVP-MVS++		99.59 15	99.50 19	99.88 15	99.51 228	99.88 10	99.87 8	99.51 155	98.99 69	99.88 43	99.81 133	99.27 7	99.96 41	98.85 165	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		97.10 377	96.79 377	98.01 372	98.72 417	96.33 387	99.87 8	97.05 471	97.59 270	96.16 448	99.80 151	88.71 418	99.04 411	96.69 379	96.55 367	98.65 375

FC-MVSNet-test		98.75 206	98.62 207	99.15 228	99.08 359	99.45 115	99.86 11	99.60 67	98.23 165	98.70 352	99.82 118	96.80 162	99.22 380	99.07 128	96.38 370	98.79 324

v7n		97.87 298	97.52 316	98.92 255	98.76 413	98.58 252	99.84 12	99.46 237	96.20 393	98.91 317	99.70 215	94.89 260	99.44 335	96.03 396	93.89 428	98.75 334

DTE-MVSNet		97.51 353	97.19 362	98.46 330	98.63 427	98.13 285	99.84 12	99.48 203	96.68 355	97.97 410	99.67 240	92.92 338	98.56 447	96.88 372	92.60 446	98.70 347

3Dnovator	97.25 9	99.24 97	99.05 112	99.81 60	99.12 348	99.66 71	99.84 12	99.74 13	99.09 55	98.92 316	99.90 36	95.94 209	99.98 20	98.95 145	99.92 39	99.79 92

FIs		98.78 201	98.63 202	99.23 218	99.18 332	99.54 98	99.83 15	99.59 73	98.28 150	98.79 339	99.81 133	96.75 165	99.37 348	99.08 127	96.38 370	98.78 326

MGCFI-Net		99.01 165	98.85 173	99.50 149	99.42 262	99.26 144	99.82 16	99.48 203	98.60 115	99.28 239	98.81 425	97.04 147	99.76 256	99.29 94	97.87 313	99.47 248

test_fmvs3		92.10 437	91.77 440	93.08 452	96.19 469	86.25 472	99.82 16	98.62 445	96.65 358	95.19 456	96.90 472	55.05 486	95.93 479	96.63 384	90.92 455	97.06 468

jajsoiax		98.43 227	98.28 234	98.88 269	98.60 431	98.43 271	99.82 16	99.53 125	98.19 170	98.63 364	99.80 151	93.22 333	99.44 335	99.22 103	97.50 336	98.77 330

OpenMVS	96.50 16	98.47 224	98.12 245	99.52 139	99.04 367	99.53 101	99.82 16	99.72 14	94.56 433	98.08 403	99.88 56	94.73 273	99.98 20	97.47 329	99.76 140	99.06 305

SDMVSNet		99.11 140	98.90 159	99.75 77	99.81 57	99.59 88	99.81 20	99.65 39	98.78 98	99.64 143	99.88 56	94.56 285	99.93 110	99.67 37	98.26 291	99.72 136

nrg030		98.64 217	98.42 224	99.28 210	99.05 365	99.69 63	99.81 20	99.46 237	98.04 215	99.01 299	99.82 118	96.69 167	99.38 345	99.34 81	94.59 415	98.78 326

HPM-MVS		99.42 55	99.28 69	99.83 56	99.90 4	99.72 56	99.81 20	99.54 109	97.59 270	99.68 118	99.63 259	98.91 39	99.94 92	98.58 209	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		99.13 126	98.99 137	99.53 133	99.65 159	99.06 171	99.81 20	99.33 321	97.43 293	99.60 158	99.88 56	97.14 138	99.84 196	99.13 118	98.94 240	99.69 153

3Dnovator+	97.12 13	99.18 104	98.97 141	99.82 57	99.17 340	99.68 64	99.81 20	99.51 155	99.20 33	98.72 345	99.89 45	95.68 224	99.97 29	98.86 163	99.86 87	99.81 79

sasdasda		99.02 161	98.86 170	99.51 144	99.42 262	99.32 131	99.80 25	99.48 203	98.63 110	99.31 231	98.81 425	97.09 143	99.75 259	99.27 98	97.90 310	99.47 248

FA-MVS(test-final)		98.75 206	98.53 218	99.41 179	99.55 211	99.05 173	99.80 25	99.01 392	96.59 368	99.58 162	99.59 273	95.39 234	99.90 148	97.78 293	99.49 177	99.28 280

GeoE		98.85 192	98.62 207	99.53 133	99.61 188	99.08 168	99.80 25	99.51 155	97.10 325	99.31 231	99.78 175	95.23 245	99.77 252	98.21 249	99.03 234	99.75 112

canonicalmvs		99.02 161	98.86 170	99.51 144	99.42 262	99.32 131	99.80 25	99.48 203	98.63 110	99.31 231	98.81 425	97.09 143	99.75 259	99.27 98	97.90 310	99.47 248

v8		97.95 287	97.63 306	98.93 253	98.95 382	98.81 230	99.80 25	99.41 273	96.03 407	99.10 282	99.42 331	94.92 257	99.30 363	96.94 367	94.08 425	98.66 373

Vis-MVSNet (Re-imp)		98.87 180	98.72 188	99.31 198	99.71 117	98.88 212	99.80 25	99.44 257	97.91 228	99.36 221	99.78 175	95.49 231	99.43 339	97.91 278	99.11 218	99.62 189

Anonymous20240521		96.20 396	95.89 399	97.13 422	97.72 452	94.96 430	99.79 31	99.29 344	93.01 448	97.20 433	99.03 404	89.69 408	98.36 451	91.16 458	96.13 376	98.07 442

PS-MVSNAJss		98.92 174	98.92 154	98.90 261	98.78 406	98.53 256	99.78 32	99.54 109	98.07 201	99.00 303	99.76 188	99.01 20	99.37 348	99.13 118	97.23 353	98.81 323

PEN-MVS		97.76 319	97.44 332	98.72 295	98.77 411	98.54 255	99.78 32	99.51 155	97.06 329	98.29 392	99.64 253	92.63 351	98.89 438	98.09 262	93.16 438	98.72 340

anonymousdsp		98.44 226	98.28 234	98.94 251	98.50 437	98.96 187	99.77 34	99.50 178	97.07 327	98.87 325	99.77 184	94.76 270	99.28 365	98.66 195	97.60 325	98.57 404

SixPastTwentyTwo		97.50 354	97.33 350	98.03 369	98.65 425	96.23 392	99.77 34	98.68 441	97.14 318	97.90 413	99.93 10	90.45 397	99.18 388	97.00 361	96.43 369	98.67 364

QAPM		98.67 213	98.30 233	99.80 64	99.20 326	99.67 68	99.77 34	99.72 14	94.74 430	98.73 344	99.90 36	95.78 220	99.98 20	96.96 365	99.88 76	99.76 107

SSC-MVS		92.73 436	93.73 430	89.72 462	95.02 480	81.38 482	99.76 37	99.23 359	94.87 427	92.80 469	98.93 417	94.71 275	91.37 486	74.49 485	93.80 429	96.42 472

test_vis3_rt		87.04 444	85.81 447	90.73 459	93.99 483	81.96 480	99.76 37	90.23 494	92.81 451	81.35 482	91.56 482	40.06 490	99.07 406	94.27 430	88.23 465	91.15 482

dcpmvs_2		99.23 98	99.58 9	98.16 361	99.83 47	94.68 436	99.76 37	99.52 133	99.07 58	99.98 13	99.88 56	98.56 80	99.93 110	99.67 37	99.98 4	99.87 40

RRT-MVS		98.91 175	98.75 184	99.39 185	99.46 252	98.61 250	99.76 37	99.50 178	98.06 205	99.81 69	99.88 56	93.91 317	99.94 92	99.11 121	99.27 194	99.61 191

HPM-MVS_fast		99.51 29	99.40 38	99.85 43	99.91 1	99.79 41	99.76 37	99.56 90	97.72 255	99.76 91	99.75 193	99.13 14	99.92 123	99.07 128	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 84	98.41 93	99.96 41	99.28 95	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	99.50 178	98.27 152	99.87 49	99.92 18	98.09 108	99.94 92	99.65 41	99.95 23	99.47 248

v10		97.85 301	97.52 316	98.86 276	98.99 375	98.67 241	99.75 42	99.41 273	95.70 411	98.98 306	99.41 335	94.75 271	99.23 375	96.01 398	94.63 414	98.67 364

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 84	99.18 12	99.96 41	99.22 103	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		99.05 157	98.87 167	99.57 120	99.73 107	99.32 131	99.75 42	99.20 366	98.02 220	99.56 166	99.86 77	96.54 177	99.67 293	98.09 262	99.13 211	99.73 126

test_vis1_n		97.92 291	97.44 332	99.34 190	99.53 219	98.08 288	99.74 47	99.49 191	99.15 38	100.00 1	99.94 6	79.51 474	99.98 20	99.88 26	99.76 140	99.97 4

test_fmvs1_n		98.41 230	98.14 242	99.21 219	99.82 53	97.71 314	99.74 47	99.49 191	99.32 29	99.99 2	99.95 3	85.32 452	99.97 29	99.82 29	99.84 102	99.96 7

balanced_conf03		99.46 42	99.39 40	99.67 90	99.55 211	99.58 93	99.74 47	99.51 155	98.42 134	99.87 49	99.84 99	98.05 111	99.91 135	99.58 47	99.94 31	99.52 225

tttt0517		98.42 228	98.14 242	99.28 210	99.66 149	98.38 274	99.74 47	96.85 473	97.68 261	99.79 76	99.74 198	91.39 384	99.89 163	98.83 171	99.56 170	99.57 212

WB-MVS		93.10 434	94.10 425	90.12 461	95.51 477	81.88 481	99.73 51	99.27 352	95.05 422	93.09 468	98.91 421	94.70 276	91.89 485	76.62 483	94.02 427	96.58 471

test_fmvs2		97.25 371	97.30 353	97.09 424	99.43 260	93.31 457	99.73 51	98.87 415	98.83 88	99.28 239	99.80 151	84.45 457	99.66 296	97.88 280	97.45 341	98.30 428

SD_0403		97.55 348	97.53 315	97.62 406	99.61 188	93.64 454	99.72 53	99.44 257	98.03 217	98.62 367	99.39 343	96.06 201	99.57 317	87.88 471	99.01 237	99.66 168

MonoMVSNet		98.38 234	98.47 222	98.12 366	98.59 433	96.19 394	99.72 53	98.79 426	97.89 230	99.44 193	99.52 301	96.13 198	98.90 437	98.64 197	97.54 331	99.28 280

baseline		99.15 115	99.02 127	99.53 133	99.66 149	99.14 160	99.72 53	99.48 203	98.35 142	99.42 199	99.84 99	96.07 200	99.79 244	99.51 56	99.14 208	99.67 163

RPSCF		98.22 245	98.62 207	96.99 426	99.82 53	91.58 466	99.72 53	99.44 257	96.61 363	99.66 129	99.89 45	95.92 210	99.82 226	97.46 330	99.10 225	99.57 212

CSCG		99.32 79	99.32 54	99.32 196	99.85 31	98.29 276	99.71 57	99.66 32	98.11 192	99.41 204	99.80 151	98.37 96	99.96 41	98.99 137	99.96 17	99.72 136

dmvs_re		98.08 263	98.16 239	97.85 388	99.55 211	94.67 437	99.70 58	98.92 403	98.15 175	99.06 293	99.35 355	93.67 325	99.25 372	97.77 296	97.25 352	99.64 181

WR-MVS_H		98.13 256	97.87 276	98.90 261	99.02 369	98.84 222	99.70 58	99.59 73	97.27 307	98.40 382	99.19 387	95.53 229	99.23 375	98.34 239	93.78 430	98.61 395

mvsmamba		99.06 153	98.96 145	99.36 187	99.47 250	98.64 245	99.70 58	99.05 387	97.61 269	99.65 138	99.83 105	96.54 177	99.92 123	99.19 107	99.62 165	99.51 234

LTVRE_ROB	97.16 12	98.02 275	97.90 271	98.40 340	99.23 319	96.80 369	99.70 58	99.60 67	97.12 321	98.18 399	99.70 215	91.73 374	99.72 272	98.39 232	97.45 341	98.68 356
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	99.83 105		99.95 76	98.83 171	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	99.83 105	99.30 4	99.95 76	98.83 171	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	99.83 105	99.30 4	99.95 76	99.32 84	99.89 68	99.90 25

TestfortrainingZip							99.69 62

test_f		91.90 438	91.26 442	93.84 448	95.52 476	85.92 473	99.69 62	98.53 449	95.31 416	93.87 463	96.37 475	55.33 485	98.27 452	95.70 404	90.98 454	97.32 467

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	99.37 215	99.74 198	98.81 49	99.94 92	98.79 179	99.86 87	99.84 53

X-MVStestdata		96.55 388	95.45 407	99.87 21	99.85 31	99.83 22	99.69 62	99.68 24	98.98 72	99.37 215	64.01 491	98.81 49	99.94 92	98.79 179	99.86 87	99.84 53

V42		98.06 265	97.79 282	98.86 276	98.98 378	98.84 222	99.69 62	99.34 313	96.53 370	99.30 235	99.37 349	94.67 278	99.32 360	97.57 317	94.66 413	98.42 420

mPP-MVS		99.44 50	99.30 62	99.86 34	99.88 13	99.79 41	99.69 62	99.48 203	98.12 190	99.50 180	99.75 193	98.78 53	99.97 29	98.57 212	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	99.52 133	98.07 201	99.53 175	99.63 259	98.93 38	99.97 29	98.74 183	99.91 46	99.83 63

FE-MVS		98.48 223	98.17 238	99.40 180	99.54 218	98.96 187	99.68 72	98.81 422	95.54 413	99.62 150	99.70 215	93.82 320	99.93 110	97.35 339	99.46 178	99.32 277

PS-CasMVS		97.93 288	97.59 310	98.95 249	98.99 375	99.06 171	99.68 72	99.52 133	97.13 319	98.31 389	99.68 234	92.44 360	99.05 410	98.51 220	94.08 425	98.75 334

Vis-MVSNet		99.12 134	98.97 141	99.56 122	99.78 70	99.10 164	99.68 72	99.66 32	98.49 125	99.86 53	99.87 69	94.77 269	99.84 196	99.19 107	99.41 182	99.74 117
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
KinetiMVS		99.12 134	98.92 154	99.70 87	99.67 136	99.40 121	99.67 75	99.63 46	98.73 102	99.94 28	99.81 133	94.54 288	99.96 41	98.40 231	99.93 33	99.74 117

BP-MVS1		99.12 134	98.94 151	99.65 95	99.51 228	99.30 138	99.67 75	98.92 403	98.48 126	99.84 56	99.69 226	94.96 252	99.92 123	99.62 44	99.79 132	99.71 147

test_vis1_n_1920		98.63 218	98.40 226	99.31 198	99.86 25	97.94 301	99.67 75	99.62 51	99.43 17	99.99 2	99.91 26	87.29 436	100.00 1	99.92 24	99.92 39	99.98 2

EIA-MVS		99.18 104	99.09 104	99.45 168	99.49 242	99.18 152	99.67 75	99.53 125	97.66 264	99.40 209	99.44 327	98.10 107	99.81 231	98.94 146	99.62 165	99.35 272

MSP-MVS		99.42 55	99.27 73	99.88 15	99.89 8	99.80 38	99.67 75	99.50 178	98.70 106	99.77 85	99.49 311	98.21 102	99.95 76	98.46 226	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		99.10 145	98.97 141	99.48 159	99.49 242	99.14 160	99.67 75	99.34 313	97.31 304	99.58 162	99.76 188	97.65 121	99.82 226	98.87 158	99.07 231	99.46 253

CP-MVSNet		98.09 260	97.78 285	99.01 240	98.97 380	99.24 147	99.67 75	99.46 237	97.25 309	98.48 378	99.64 253	93.79 321	99.06 409	98.63 199	94.10 424	98.74 338

MTAPA		99.52 28	99.39 40	99.89 11	99.90 4	99.86 18	99.66 82	99.47 225	98.79 95	99.68 118	99.81 133	98.43 89	99.97 29	98.88 155	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	99.68 118	99.69 226	99.06 18	99.96 41	98.69 191	99.87 79	99.84 53

mvs_tets		98.40 233	98.23 236	98.91 259	98.67 424	98.51 262	99.66 82	99.53 125	98.19 170	98.65 361	99.81 133	92.75 342	99.44 335	99.31 86	97.48 340	98.77 330

EU-MVSNet		97.98 282	98.03 257	97.81 396	98.72 417	96.65 376	99.66 82	99.66 32	98.09 196	98.35 387	99.82 118	95.25 243	98.01 458	97.41 335	95.30 401	98.78 326

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	99.67 124	99.69 226	98.95 32	99.96 41	98.69 191	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	99.46 237	98.09 196	99.48 184	99.74 198	98.29 99	99.96 41	97.93 277	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	98.83 225	99.65 88	99.52 133	99.10 48	99.84 56	99.76 188	95.80 218	99.99 4	99.30 89	99.84 102	99.74 117

SymmetryMVS		99.15 115	99.02 127	99.52 139	99.72 111	98.83 225	99.65 88	99.34 313	99.10 48	99.84 56	99.76 188	95.80 218	99.99 4	99.30 89	98.72 261	99.73 126

Elysia		98.88 177	98.65 199	99.58 116	99.58 198	99.34 127	99.65 88	99.52 133	98.26 155	99.83 64	99.87 69	93.37 328	99.90 148	97.81 290	99.91 46	99.49 239

StellarMVS		98.88 177	98.65 199	99.58 116	99.58 198	99.34 127	99.65 88	99.52 133	98.26 155	99.83 64	99.87 69	93.37 328	99.90 148	97.81 290	99.91 46	99.49 239

test_cas_vis1_n_1920		99.16 111	99.01 133	99.61 109	99.81 57	98.86 219	99.65 88	99.64 42	99.39 22	99.97 25	99.94 6	93.20 334	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	99.66 129	99.68 234	98.96 27	99.96 41	98.62 200	99.87 79	99.84 53

TranMVSNet+NR-MVSNet		97.93 288	97.66 301	98.76 292	98.78 406	98.62 248	99.65 88	99.49 191	97.76 250	98.49 377	99.60 271	94.23 301	98.97 429	98.00 273	92.90 440	98.70 347

GDP-MVS		99.08 148	98.89 163	99.64 101	99.53 219	99.34 127	99.64 95	99.48 203	98.32 147	99.77 85	99.66 245	95.14 248	99.93 110	98.97 143	99.50 176	99.64 181

ttmdpeth		97.80 315	97.63 306	98.29 350	98.77 411	97.38 325	99.64 95	99.36 301	98.78 98	96.30 446	99.58 277	92.34 363	99.39 343	98.36 237	95.58 394	98.10 440

mvsany_test3		93.77 431	93.45 434	94.74 445	95.78 472	88.01 471	99.64 95	98.25 454	98.28 150	94.31 460	97.97 458	68.89 478	98.51 449	97.50 325	90.37 456	97.71 457

ZNCC-MVS		99.47 40	99.33 52	99.87 21	99.87 20	99.81 33	99.64 95	99.67 27	98.08 200	99.55 172	99.64 253	98.91 39	99.96 41	98.72 186	99.90 57	99.82 72

tfpnnormal		97.84 305	97.47 324	98.98 244	99.20 326	99.22 149	99.64 95	99.61 60	96.32 384	98.27 393	99.70 215	93.35 330	99.44 335	95.69 405	95.40 399	98.27 430

casdiffmvs_mvg		99.15 115	99.02 127	99.55 124	99.66 149	99.09 165	99.64 95	99.56 90	98.26 155	99.45 188	99.87 69	96.03 203	99.81 231	99.54 51	99.15 207	99.73 126
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	99.52 133	98.38 137	99.76 91	99.82 118	98.53 82	99.95 76	98.61 203	99.81 120	99.77 100

RE-MVS-def			99.34 50		99.76 82	99.82 28	99.63 101	99.52 133	98.38 137	99.76 91	99.82 118	98.75 60		98.61 203	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	99.39 283	98.91 82	99.78 81	99.85 84	99.36 2	99.94 92	98.84 168	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		96.22 394	96.03 395	96.79 434	97.31 458	94.14 446	99.63 101	99.08 381	96.17 396	97.04 437	99.06 400	93.94 314	97.76 464	86.96 475	95.06 406	98.47 414

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	99.82 118	98.86 43	99.95 76	98.62 200	99.81 120	99.78 98

test0726					99.85 31	99.89 6	99.62 106	99.50 178	99.10 48	99.86 53	99.82 118	98.94 34

EPNet		98.86 183	98.71 190	99.30 203	97.20 460	98.18 281	99.62 106	98.91 408	99.28 31	98.63 364	99.81 133	95.96 206	99.99 4	99.24 102	99.72 148	99.73 126
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t		98.93 173	98.67 194	99.72 86	99.85 31	99.53 101	99.62 106	99.59 73	92.65 453	99.71 111	99.78 175	98.06 110	99.90 148	98.84 168	99.91 46	99.74 117

HY-MVS	97.30 7	98.85 192	98.64 201	99.47 165	99.42 262	99.08 168	99.62 106	99.36 301	97.39 298	99.28 239	99.68 234	96.44 183	99.92 123	98.37 235	98.22 294	99.40 265

ACMMP		99.45 46	99.32 54	99.82 57	99.89 8	99.67 68	99.62 106	99.69 22	98.12 190	99.63 146	99.84 99	98.73 66	99.96 41	98.55 218	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	99.63 146	99.95 3	95.82 216	99.94 92	99.37 75	99.97 9	99.73 126
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	99.45 248	99.01 64	99.89 40	99.82 118	99.01 20	99.92 123	99.56 49	99.95 23	99.85 46

E6new		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

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		99.14 123	99.02 127	99.50 149	99.69 127	98.91 204	99.60 113	99.53 125	98.13 183	99.72 102	99.91 26	96.26 195	99.84 196	99.30 89	99.10 225	99.76 107

reproduce_monomvs		97.89 295	97.87 276	97.96 378	99.51 228	95.45 416	99.60 113	99.25 355	99.17 36	98.85 331	99.49 311	89.29 412	99.64 305	99.35 76	96.31 373	98.78 326

test2506		96.81 384	96.65 380	97.29 419	99.74 100	92.21 464	99.60 113	85.06 495	99.13 41	99.77 85	99.93 10	87.82 434	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	99.48 203	99.08 56	99.91 31	99.81 133	99.20 9	99.96 41	98.91 152	99.85 94	99.79 92

OPU-MVS				99.64 101	99.56 207	99.72 56	99.60 113				99.70 215	99.27 7	99.42 341	98.24 248	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	97.97 223	99.63 146	99.68 234	98.52 83	99.95 76	98.38 233	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	99.45 248	99.01 64	99.90 34	99.83 105	98.98 26	99.93 110	99.59 45	99.95 23	99.86 42

ACMH	97.28 8	98.10 259	97.99 261	98.44 335	99.41 267	96.96 357	99.60 113	99.56 90	98.09 196	98.15 401	99.91 26	90.87 394	99.70 285	98.88 155	97.45 341	98.67 364
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
VortexMVS		98.67 213	98.66 197	98.68 301	99.62 177	97.96 296	99.59 123	99.41 273	98.13 183	99.31 231	99.70 215	95.48 232	99.27 368	99.40 71	97.32 350	98.79 324

guyue		99.16 111	99.04 114	99.52 139	99.69 127	98.92 203	99.59 123	98.81 422	98.73 102	99.90 34	99.87 69	95.34 237	99.88 168	99.66 40	99.81 120	99.74 117

ECVR-MVS		98.04 271	98.05 255	98.00 374	99.74 100	94.37 443	99.59 123	94.98 483	99.13 41	99.66 129	99.93 10	90.67 396	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	99.59 123	99.62 51	98.21 168	99.73 97	99.79 168	98.68 70	99.96 41	98.44 228	99.77 137	99.79 92

thres100view900		97.76 319	97.45 327	98.69 300	99.72 111	97.86 305	99.59 123	98.74 432	97.93 226	99.26 250	98.62 433	91.75 372	99.83 217	93.22 443	98.18 299	98.37 426

thres600view7		97.86 300	97.51 318	98.92 255	99.72 111	97.95 299	99.59 123	98.74 432	97.94 225	99.27 245	98.62 433	91.75 372	99.86 181	93.73 437	98.19 298	98.96 316

LCM-MVSNet-Re		97.83 308	98.15 241	96.87 432	99.30 299	92.25 463	99.59 123	98.26 453	97.43 293	96.20 447	99.13 393	96.27 193	98.73 444	98.17 254	98.99 238	99.64 181

baseline1		98.31 239	97.95 266	99.38 186	99.50 240	98.74 235	99.59 123	98.93 400	98.41 135	99.14 274	99.60 271	94.59 283	99.79 244	98.48 222	93.29 435	99.61 191

SteuartSystems-ACMMP		99.54 24	99.42 32	99.87 21	99.82 53	99.81 33	99.59 123	99.51 155	98.62 112	99.79 76	99.83 105	99.28 6	99.97 29	98.48 222	99.90 57	99.84 53
Skip Steuart: Steuart Systems R&D Blog.
CPTT-MVS		99.11 140	98.90 159	99.74 80	99.80 63	99.46 114	99.59 123	99.49 191	97.03 333	99.63 146	99.69 226	97.27 133	99.96 41	97.82 288	99.84 102	99.81 79

IMVS_0403		98.86 183	98.89 163	98.78 290	99.55 211	96.93 358	99.58 133	99.44 257	98.05 208	99.68 118	99.80 151	96.81 161	99.80 238	98.15 257	98.92 243	99.60 194

test_fmvsmvis_n_1920		99.65 8	99.61 7	99.77 74	99.38 277	99.37 123	99.58 133	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		95.02 419	96.12 392	91.72 456	99.10 353	80.43 484	99.58 133	97.87 463	97.47 285	95.22 454	98.82 424	93.99 312	95.18 481	88.09 469	94.91 411	99.56 215

test_fmvsm_n_1920		99.69 5	99.66 4	99.78 71	99.84 38	99.44 116	99.58 133	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		98.04 271	98.11 246	97.83 393	99.74 100	93.82 448	99.58 133	95.40 482	99.12 46	99.65 138	99.93 10	90.73 395	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	99.58 133	99.65 39	97.84 239	99.71 111	99.80 151	99.12 15	99.97 29	98.33 240	99.87 79	99.83 63

LPG-MVS_test		98.22 245	98.13 244	98.49 322	99.33 290	97.05 344	99.58 133	99.55 100	97.46 286	99.24 252	99.83 105	92.58 352	99.72 272	98.09 262	97.51 334	98.68 356

PHI-MVS		99.30 83	99.17 91	99.70 87	99.56 207	99.52 105	99.58 133	99.80 11	97.12 321	99.62 150	99.73 204	98.58 78	99.90 148	98.61 203	99.91 46	99.68 159

fmvsm_s_conf0.5_n_11		99.32 79	99.16 92	99.80 64	99.83 47	99.70 60	99.57 141	99.56 90	99.45 11	99.99 2	99.93 10	94.18 305	99.99 4	99.96 13	99.98 4	99.73 126

AstraMVS		99.09 146	99.03 117	99.25 213	99.66 149	98.13 285	99.57 141	98.24 455	98.82 89	99.91 31	99.88 56	95.81 217	99.90 148	99.72 32	99.67 158	99.74 117

SF-MVS		99.38 67	99.24 78	99.79 68	99.79 68	99.68 64	99.57 141	99.54 109	97.82 245	99.71 111	99.80 151	98.95 32	99.93 110	98.19 251	99.84 102	99.74 117

DVP-MVS		99.57 20	99.47 24	99.88 15	99.85 31	99.89 6	99.57 141	99.37 299	99.10 48	99.81 69	99.80 151	98.94 34	99.96 41	98.93 149	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	99.57 141	99.51 155					99.96 41	98.93 149	99.86 87	99.88 35

Effi-MVS+-dtu		98.78 201	98.89 163	98.47 329	99.33 290	96.91 363	99.57 141	99.30 340	98.47 127	99.41 204	98.99 410	96.78 163	99.74 262	98.73 185	99.38 183	98.74 338

v2v482		98.06 265	97.77 287	98.92 255	98.90 388	98.82 228	99.57 141	99.36 301	96.65 358	99.19 266	99.35 355	94.20 302	99.25 372	97.72 303	94.97 408	98.69 351

DSMNet-mixed		97.25 371	97.35 344	96.95 429	97.84 448	93.61 455	99.57 141	96.63 477	96.13 401	98.87 325	98.61 435	94.59 283	97.70 465	95.08 419	98.86 251	99.55 216

FE-MVSNET		94.07 430	93.36 435	96.22 440	94.05 482	94.71 435	99.56 149	98.36 451	93.15 447	93.76 464	97.55 465	86.47 443	96.49 476	87.48 472	89.83 461	97.48 465

reproduce_model		99.63 9	99.54 13	99.90 8	99.78 70	99.88 10	99.56 149	99.55 100	99.15 38	99.90 34	99.90 36	99.00 24	99.97 29	99.11 121	99.91 46	99.86 42

MVStest1		96.08 400	95.48 405	97.89 384	98.93 383	96.70 371	99.56 149	99.35 308	92.69 452	91.81 473	99.46 324	89.90 405	98.96 431	95.00 421	92.61 445	98.00 449

fmvsm_l_conf0.5_n_a		99.71 2	99.67 1	99.85 43	99.86 25	99.61 85	99.56 149	99.63 46	99.48 3	99.98 13	99.83 105	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	99.56 149	99.63 46	99.47 4	99.98 13	99.82 118	98.75 60	99.99 4	99.97 2	99.97 9	99.94 17

sd_testset		98.75 206	98.57 214	99.29 206	99.81 57	98.26 278	99.56 149	99.62 51	98.78 98	99.64 143	99.88 56	92.02 366	99.88 168	99.54 51	98.26 291	99.72 136

KD-MVS_self_test		95.00 420	94.34 424	96.96 428	97.07 463	95.39 419	99.56 149	99.44 257	95.11 419	97.13 435	97.32 470	91.86 370	97.27 470	90.35 461	81.23 476	98.23 434

ETV-MVS		99.26 92	99.21 84	99.40 180	99.46 252	99.30 138	99.56 149	99.52 133	98.52 122	99.44 193	99.27 377	98.41 93	99.86 181	99.10 124	99.59 168	99.04 306

SMA-MVS		99.44 50	99.30 62	99.85 43	99.73 107	99.83 22	99.56 149	99.47 225	97.45 289	99.78 81	99.82 118	99.18 12	99.91 135	98.79 179	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		98.87 180	98.72 188	99.31 198	99.86 25	98.48 267	99.56 149	99.61 60	97.85 236	99.36 221	99.85 84	95.95 207	99.85 187	96.66 381	99.83 113	99.59 205

casdiffmvs		99.13 126	98.98 140	99.56 122	99.65 159	99.16 155	99.56 149	99.50 178	98.33 145	99.41 204	99.86 77	95.92 210	99.83 217	99.45 68	99.16 204	99.70 150
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		98.38 234	98.09 250	99.24 216	99.26 311	99.32 131	99.56 149	99.55 100	97.45 289	98.71 346	99.83 105	93.23 331	99.63 311	98.88 155	96.32 372	98.76 332

ACMH+	97.24 10	97.92 291	97.78 285	98.32 347	99.46 252	96.68 375	99.56 149	99.54 109	98.41 135	97.79 419	99.87 69	90.18 403	99.66 296	98.05 270	97.18 356	98.62 386

ACMM	97.58 5	98.37 236	98.34 229	98.48 324	99.41 267	97.10 338	99.56 149	99.45 248	98.53 121	99.04 296	99.85 84	93.00 336	99.71 278	98.74 183	97.45 341	98.64 377
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	99.18 332	99.75 51	99.56 149	99.57 85	98.45 130	99.49 183	99.85 84	97.77 118	99.94 92	98.33 240	99.84 102	99.52 225

testing3-2		97.84 305	97.70 297	98.24 356	99.53 219	95.37 420	99.55 164	98.67 442	98.46 128	99.27 245	99.34 359	86.58 441	99.83 217	99.32 84	98.63 264	99.52 225

test_fmvsmconf0.01_n		99.22 100	99.03 117	99.79 68	98.42 440	99.48 111	99.55 164	99.51 155	99.39 22	99.78 81	99.93 10	94.80 264	99.95 76	99.93 23	99.95 23	99.94 17

test_fmvs1		98.88 177	98.79 181	99.16 224	99.69 127	97.61 318	99.55 164	99.49 191	99.32 29	99.98 13	99.91 26	91.41 383	99.96 41	99.82 29	99.92 39	99.90 25

v144192		97.92 291	97.60 309	98.87 273	98.83 400	98.65 243	99.55 164	99.34 313	96.20 393	99.32 230	99.40 339	94.36 295	99.26 371	96.37 392	95.03 407	98.70 347

API-MVS		99.04 158	99.03 117	99.06 234	99.40 272	99.31 135	99.55 164	99.56 90	98.54 120	99.33 229	99.39 343	98.76 57	99.78 250	96.98 363	99.78 134	98.07 442

fmvsm_l_conf0.5_n_3		99.61 10	99.51 18	99.92 1	99.84 38	99.82 28	99.54 169	99.66 32	99.46 7	99.98 13	99.89 45	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	99.52 225	99.62 83	99.54 169	99.62 51	98.69 107	99.99 2	99.96 1	94.47 292	99.94 92	99.88 26	99.92 39	99.98 2

APD_test1		95.87 402	96.49 384	94.00 447	99.53 219	84.01 476	99.54 169	99.32 331	95.91 409	97.99 408	99.85 84	85.49 450	99.88 168	91.96 454	98.84 253	98.12 439

thisisatest0530		98.35 237	98.03 257	99.31 198	99.63 168	98.56 253	99.54 169	96.75 475	97.53 280	99.73 97	99.65 247	91.25 388	99.89 163	98.62 200	99.56 170	99.48 242

MTMP							99.54 169	98.88 413

v1144		97.98 282	97.69 298	98.85 279	98.87 393	98.66 242	99.54 169	99.35 308	96.27 388	99.23 256	99.35 355	94.67 278	99.23 375	96.73 376	95.16 404	98.68 356

v148		97.79 317	97.55 311	98.50 321	98.74 414	97.72 311	99.54 169	99.33 321	96.26 389	98.90 319	99.51 305	94.68 277	99.14 393	97.83 287	93.15 439	98.63 384

CostFormer		97.72 329	97.73 294	97.71 402	99.15 346	94.02 447	99.54 169	99.02 391	94.67 431	99.04 296	99.35 355	92.35 362	99.77 252	98.50 221	97.94 309	99.34 275

MVSTER		98.49 222	98.32 231	99.00 242	99.35 284	99.02 175	99.54 169	99.38 291	97.41 296	99.20 263	99.73 204	93.86 319	99.36 352	98.87 158	97.56 329	98.62 386

fmvsm_s_conf0.5_n_10		99.41 59	99.24 78	99.92 1	99.83 47	99.84 20	99.53 178	99.56 90	99.45 11	99.99 2	99.92 18	94.92 257	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	99.53 178	99.62 51	98.74 101	99.99 2	99.95 3	94.53 290	99.94 92	99.89 25	99.96 17	99.97 4

E4		99.13 126	99.01 133	99.49 155	99.68 133	98.90 208	99.52 180	99.52 133	98.13 183	99.71 111	99.90 36	96.32 188	99.84 196	99.21 105	99.11 218	99.75 112

reproduce-ours		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 180	99.54 109	99.13 41	99.89 40	99.89 45	98.96 27	99.96 41	99.04 131	99.90 57	99.85 46

our_new_method		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 180	99.54 109	99.13 41	99.89 40	99.89 45	98.96 27	99.96 41	99.04 131	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	99.52 180	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	99.52 180	98.87 415	99.55 1	99.74 95	99.80 151	96.47 180	99.98 20	99.97 2	99.97 9	99.94 17

patch_mono-2		99.26 92	99.62 6	98.16 361	99.81 57	94.59 439	99.52 180	99.64 42	99.33 28	99.73 97	99.90 36	99.00 24	99.99 4	99.69 35	99.98 4	99.89 29

Fast-Effi-MVS+-dtu		98.77 205	98.83 177	98.60 306	99.41 267	96.99 353	99.52 180	99.49 191	98.11 192	99.24 252	99.34 359	96.96 152	99.79 244	97.95 276	99.45 179	99.02 309

Fast-Effi-MVS+		98.70 210	98.43 223	99.51 144	99.51 228	99.28 141	99.52 180	99.47 225	96.11 402	99.01 299	99.34 359	96.20 196	99.84 196	97.88 280	98.82 255	99.39 266

v1921920		97.80 315	97.45 327	98.84 280	98.80 402	98.53 256	99.52 180	99.34 313	96.15 399	99.24 252	99.47 320	93.98 313	99.29 364	95.40 413	95.13 405	98.69 351

MIMVSNet1		95.51 409	95.04 413	96.92 431	97.38 455	95.60 409	99.52 180	99.50 178	93.65 441	96.97 439	99.17 388	85.28 453	96.56 475	88.36 468	95.55 396	98.60 398

FE-MVSNET2		95.10 417	94.44 422	97.08 425	95.08 478	95.97 398	99.51 190	99.37 299	95.02 423	94.10 461	97.57 464	86.18 445	97.66 467	93.28 442	89.86 460	97.61 460

viewmacassd2359aftdt		99.08 148	98.94 151	99.50 149	99.66 149	98.96 187	99.51 190	99.54 109	98.27 152	99.42 199	99.89 45	95.88 214	99.80 238	99.20 106	99.11 218	99.76 107

SSM_0407		99.13 126	99.03 117	99.43 176	99.62 177	98.88 212	99.51 190	99.50 178	98.14 180	99.37 215	99.85 84	96.85 155	99.83 217	99.19 107	99.25 197	99.60 194

fmvsm_s_conf0.5_n_8		99.54 24	99.42 32	99.89 11	99.83 47	99.74 54	99.51 190	99.62 51	99.46 7	99.99 2	99.90 36	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	99.51 190	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		97.32 368	96.81 376	98.87 273	99.40 272	97.46 322	99.51 190	99.53 125	95.86 410	98.54 374	99.77 184	82.44 466	99.66 296	98.68 193	97.52 333	99.50 238

alignmvs		98.81 196	98.56 216	99.58 116	99.43 260	99.42 118	99.51 190	98.96 398	98.61 113	99.35 224	98.92 420	94.78 266	99.77 252	99.35 76	98.11 304	99.54 218

v1192		97.81 313	97.44 332	98.91 259	98.88 390	98.68 240	99.51 190	99.34 313	96.18 395	99.20 263	99.34 359	94.03 311	99.36 352	95.32 415	95.18 403	98.69 351

test20.03		96.12 398	95.96 397	96.63 435	97.44 454	95.45 416	99.51 190	99.38 291	96.55 369	96.16 448	99.25 380	93.76 323	96.17 477	87.35 474	94.22 421	98.27 430

mvs_anonymous		99.03 160	98.99 137	99.16 224	99.38 277	98.52 260	99.51 190	99.38 291	97.79 246	99.38 213	99.81 133	97.30 131	99.45 330	99.35 76	98.99 238	99.51 234

TAMVS		99.12 134	99.08 105	99.24 216	99.46 252	98.55 254	99.51 190	99.46 237	98.09 196	99.45 188	99.82 118	98.34 97	99.51 324	98.70 188	98.93 241	99.67 163

viewdifsd2359ckpt13		99.06 153	98.93 153	99.45 168	99.63 168	98.96 187	99.50 201	99.51 155	97.83 240	99.28 239	99.80 151	96.68 169	99.71 278	99.05 130	99.12 216	99.68 159

viewdifsd2359ckpt11		98.78 201	98.74 186	98.89 265	99.67 136	97.04 347	99.50 201	99.58 78	98.26 155	99.56 166	99.90 36	94.36 295	99.87 175	99.49 61	98.32 287	99.77 100

viewmsd2359difaftdt		98.78 201	98.74 186	98.90 261	99.67 136	97.04 347	99.50 201	99.58 78	98.26 155	99.56 166	99.90 36	94.36 295	99.87 175	99.49 61	98.32 287	99.77 100

IMVS_0407		98.86 183	98.91 157	98.72 295	99.55 211	96.93 358	99.50 201	99.44 257	98.05 208	99.66 129	99.80 151	97.13 139	99.65 301	98.15 257	98.92 243	99.60 194

viewmanbaseed2359cas		99.18 104	99.07 109	99.50 149	99.62 177	99.01 177	99.50 201	99.52 133	98.25 160	99.68 118	99.82 118	96.93 153	99.80 238	99.15 117	99.11 218	99.70 150

fmvsm_s_conf0.5_n_6		99.54 24	99.44 31	99.85 43	99.51 228	99.67 68	99.50 201	99.64 42	99.43 17	99.98 13	99.78 175	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	99.44 259	99.65 75	99.50 201	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		98.86 183	98.63 202	99.54 125	99.49 242	99.18 152	99.50 201	99.07 384	98.22 166	99.61 155	99.51 305	95.37 235	99.84 196	98.60 206	98.33 283	99.59 205

DCV-MVSNet		98.86 183	98.63 202	99.54 125	99.49 242	99.18 152	99.50 201	99.07 384	98.22 166	99.61 155	99.51 305	95.37 235	99.84 196	98.60 206	98.33 283	99.59 205

tfpn200view9		97.72 329	97.38 340	98.72 295	99.69 127	97.96 296	99.50 201	98.73 438	97.83 240	99.17 271	98.45 440	91.67 376	99.83 217	93.22 443	98.18 299	98.37 426

UA-Net		99.42 55	99.29 66	99.80 64	99.62 177	99.55 96	99.50 201	99.70 18	98.79 95	99.77 85	99.96 1	97.45 124	99.96 41	98.92 151	99.90 57	99.89 29

pm-mvs1		97.68 337	97.28 356	98.88 269	99.06 362	98.62 248	99.50 201	99.45 248	96.32 384	97.87 415	99.79 168	92.47 356	99.35 355	97.54 320	93.54 432	98.67 364

EI-MVSNet		98.67 213	98.67 194	98.68 301	99.35 284	97.97 294	99.50 201	99.38 291	96.93 342	99.20 263	99.83 105	97.87 114	99.36 352	98.38 233	97.56 329	98.71 342

CVMVSNet		98.57 220	98.67 194	98.30 349	99.35 284	95.59 410	99.50 201	99.55 100	98.60 115	99.39 211	99.83 105	94.48 291	99.45 330	98.75 182	98.56 271	99.85 46

VPA-MVSNet		98.29 242	97.95 266	99.30 203	99.16 342	99.54 98	99.50 201	99.58 78	98.27 152	99.35 224	99.37 349	92.53 354	99.65 301	99.35 76	94.46 416	98.72 340

thres400		97.77 318	97.38 340	98.92 255	99.69 127	97.96 296	99.50 201	98.73 438	97.83 240	99.17 271	98.45 440	91.67 376	99.83 217	93.22 443	98.18 299	98.96 316

APD-MVS		99.27 89	99.08 105	99.84 55	99.75 92	99.79 41	99.50 201	99.50 178	97.16 317	99.77 85	99.82 118	98.78 53	99.94 92	97.56 318	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	99.49 155	99.65 159	98.93 202	99.49 218	99.52 133	98.14 180	99.72 102	99.88 56	96.57 176	99.84 196	99.17 113	99.13 211	99.72 136

E3		99.15 115	99.03 117	99.49 155	99.62 177	98.91 204	99.49 218	99.52 133	98.13 183	99.72 102	99.88 56	96.61 171	99.84 196	99.17 113	99.13 211	99.72 136

SSM_0404		99.16 111	99.06 110	99.44 173	99.65 159	98.96 187	99.49 218	99.50 178	98.14 180	99.62 150	99.85 84	96.85 155	99.85 187	99.19 107	99.26 196	99.52 225

fmvsm_s_conf0.5_n_4		99.36 72	99.24 78	99.73 83	99.78 70	99.53 101	99.49 218	99.60 67	99.42 20	99.99 2	99.86 77	95.15 247	99.95 76	99.95 16	99.89 68	99.73 126

test_vis1_rt		95.81 404	95.65 403	96.32 439	99.67 136	91.35 467	99.49 218	96.74 476	98.25 160	95.24 453	98.10 455	74.96 475	99.90 148	99.53 53	98.85 252	97.70 459

TransMVSNet (Re)		97.15 375	96.58 381	98.86 276	99.12 348	98.85 220	99.49 218	98.91 408	95.48 414	97.16 434	99.80 151	93.38 327	99.11 402	94.16 433	91.73 449	98.62 386

UniMVSNet (Re)		98.29 242	98.00 260	99.13 229	99.00 372	99.36 126	99.49 218	99.51 155	97.95 224	98.97 308	99.13 393	96.30 192	99.38 345	98.36 237	93.34 434	98.66 373

EPMVS		97.82 311	97.65 302	98.35 344	98.88 390	95.98 397	99.49 218	94.71 485	97.57 273	99.26 250	99.48 317	92.46 359	99.71 278	97.87 282	99.08 230	99.35 272

viewcassd2359sk11		99.18 104	99.08 105	99.49 155	99.65 159	98.95 193	99.48 226	99.51 155	98.10 195	99.72 102	99.87 69	97.13 139	99.84 196	99.13 118	99.14 208	99.69 153

fmvsm_s_conf0.5_n_9		99.41 59	99.28 69	99.81 60	99.84 38	99.52 105	99.48 226	99.62 51	99.46 7	99.99 2	99.92 18	95.24 244	99.96 41	99.97 2	99.97 9	99.96 7

SSC-MVS3.2		97.34 366	97.15 363	97.93 380	99.02 369	95.76 406	99.48 226	99.58 78	97.62 268	99.09 285	99.53 297	87.95 430	99.27 368	96.42 388	95.66 392	98.75 334

fmvsm_s_conf0.5_n_3		99.37 68	99.20 86	99.87 21	99.75 92	99.70 60	99.48 226	99.66 32	99.45 11	99.99 2	99.93 10	94.64 282	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	99.48 226	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		97.88 296	97.54 314	98.90 261	99.71 117	98.53 256	99.48 226	99.57 85	94.16 436	98.81 335	99.68 234	93.23 331	99.42 341	98.84 168	94.42 418	98.76 332

v1240		97.69 334	97.32 351	98.79 288	98.85 397	98.43 271	99.48 226	99.36 301	96.11 402	99.27 245	99.36 352	93.76 323	99.24 374	94.46 427	95.23 402	98.70 347

VPNet		97.84 305	97.44 332	99.01 240	99.21 324	98.94 197	99.48 226	99.57 85	98.38 137	99.28 239	99.73 204	88.89 415	99.39 343	99.19 107	93.27 436	98.71 342

UniMVSNet_NR-MVSNet		98.22 245	97.97 263	98.96 247	98.92 385	98.98 180	99.48 226	99.53 125	97.76 250	98.71 346	99.46 324	96.43 184	99.22 380	98.57 212	92.87 442	98.69 351

TDRefinement		95.42 412	94.57 420	97.97 376	89.83 488	96.11 396	99.48 226	98.75 429	96.74 351	96.68 442	99.88 56	88.65 421	99.71 278	98.37 235	82.74 473	98.09 441

fmvsm_l_conf0.5_n_9		99.58 16	99.47 24	99.92 1	99.85 31	99.82 28	99.47 236	99.63 46	99.45 11	99.98 13	99.89 45	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	99.47 236	99.48 203	98.05 208	99.76 91	99.86 77	98.82 48	99.93 110	98.82 178	99.91 46	99.84 53

NR-MVSNet		97.97 285	97.61 308	99.02 239	98.87 393	99.26 144	99.47 236	99.42 270	97.63 266	97.08 436	99.50 308	95.07 250	99.13 396	97.86 283	93.59 431	98.68 356

PVSNet_Blended_VisFu		99.36 72	99.28 69	99.61 109	99.86 25	99.07 170	99.47 236	99.93 2	97.66 264	99.71 111	99.86 77	97.73 119	99.96 41	99.47 66	99.82 117	99.79 92

E3new		99.18 104	99.08 105	99.48 159	99.63 168	98.94 197	99.46 240	99.50 178	98.06 205	99.72 102	99.84 99	97.27 133	99.84 196	99.10 124	99.13 211	99.67 163

LuminaMVS		99.23 98	99.10 99	99.61 109	99.35 284	99.31 135	99.46 240	99.13 375	98.61 113	99.86 53	99.89 45	96.41 186	99.91 135	99.67 37	99.51 174	99.63 186

fmvsm_s_conf0.1_n_2		99.37 68	99.22 83	99.81 60	99.77 78	99.75 51	99.46 240	99.60 67	99.47 4	99.98 13	99.94 6	94.98 251	99.95 76	99.97 2	99.79 132	99.73 126

SD-MVS		99.41 59	99.52 14	99.05 236	99.74 100	99.68 64	99.46 240	99.52 133	99.11 47	99.88 43	99.91 26	99.43 1	97.70 465	98.72 186	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		99.11 140	99.00 136	99.43 176	99.63 168	98.73 236	99.45 244	99.54 109	98.33 145	99.62 150	99.81 133	96.17 197	99.87 175	99.27 98	99.14 208	99.69 153

testing3		97.28 369	96.76 378	98.82 282	99.37 280	98.07 289	99.45 244	99.36 301	97.56 275	97.89 414	98.95 415	83.70 460	98.82 439	96.03 396	98.56 271	99.58 209

tt0805		97.97 285	97.77 287	98.57 311	99.59 196	96.61 378	99.45 244	99.08 381	98.21 168	98.88 322	99.80 151	88.66 420	99.70 285	98.58 209	97.72 319	99.39 266

tpm2		97.44 361	97.34 347	97.74 401	99.15 346	94.36 444	99.45 244	98.94 399	93.45 445	98.90 319	99.44 327	91.35 385	99.59 315	97.31 340	98.07 305	99.29 279

FMVSNet2		97.72 329	97.36 342	98.80 287	99.51 228	98.84 222	99.45 244	99.42 270	96.49 372	98.86 330	99.29 372	90.26 399	98.98 422	96.44 387	96.56 366	98.58 403

CDS-MVSNet		99.09 146	99.03 117	99.25 213	99.42 262	98.73 236	99.45 244	99.46 237	98.11 192	99.46 187	99.77 184	98.01 112	99.37 348	98.70 188	98.92 243	99.66 168
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MAR-MVS		98.86 183	98.63 202	99.54 125	99.37 280	99.66 71	99.45 244	99.54 109	96.61 363	99.01 299	99.40 339	97.09 143	99.86 181	97.68 308	99.53 173	99.10 294
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		99.01 165	98.87 167	99.40 180	99.62 177	98.79 231	99.44 251	99.51 155	97.76 250	99.35 224	99.69 226	96.42 185	99.75 259	98.97 143	99.11 218	99.66 168

fmvsm_s_conf0.5_n_2		99.32 79	99.13 95	99.89 11	99.80 63	99.77 48	99.44 251	99.58 78	99.47 4	99.99 2	99.93 10	94.04 310	99.96 41	99.96 13	99.93 33	99.93 22

UGNet		98.87 180	98.69 192	99.40 180	99.22 323	98.72 238	99.44 251	99.68 24	99.24 32	99.18 270	99.42 331	92.74 344	99.96 41	99.34 81	99.94 31	99.53 224
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		98.86 183	98.63 202	99.54 125	99.64 164	99.19 150	99.44 251	99.54 109	97.77 249	99.30 235	99.81 133	94.20 302	99.93 110	99.17 113	98.82 255	99.49 239

test_0402		96.64 387	96.24 389	97.85 388	98.85 397	96.43 384	99.44 251	99.26 353	93.52 442	96.98 438	99.52 301	88.52 424	99.20 387	92.58 453	97.50 336	97.93 454

ACMP	97.20 11	98.06 265	97.94 268	98.45 332	99.37 280	97.01 351	99.44 251	99.49 191	97.54 279	98.45 379	99.79 168	91.95 368	99.72 272	97.91 278	97.49 339	98.62 386
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
GG-mvs-BLEND				98.45 332	98.55 435	98.16 282	99.43 257	93.68 487		97.23 430	98.46 439	89.30 411	99.22 380	95.43 412	98.22 294	97.98 451

HPM-MVS++		99.39 66	99.23 82	99.87 21	99.75 92	99.84 20	99.43 257	99.51 155	98.68 109	99.27 245	99.53 297	98.64 75	99.96 41	98.44 228	99.80 125	99.79 92

tpm cat1		97.39 363	97.36 342	97.50 413	99.17 340	93.73 450	99.43 257	99.31 335	91.27 460	98.71 346	99.08 397	94.31 300	99.77 252	96.41 390	98.50 275	99.00 310

tpm		97.67 340	97.55 311	98.03 369	99.02 369	95.01 428	99.43 257	98.54 448	96.44 378	99.12 277	99.34 359	91.83 371	99.60 314	97.75 299	96.46 368	99.48 242

GBi-Net		97.68 337	97.48 321	98.29 350	99.51 228	97.26 331	99.43 257	99.48 203	96.49 372	99.07 288	99.32 367	90.26 399	98.98 422	97.10 355	96.65 363	98.62 386

test1		97.68 337	97.48 321	98.29 350	99.51 228	97.26 331	99.43 257	99.48 203	96.49 372	99.07 288	99.32 367	90.26 399	98.98 422	97.10 355	96.65 363	98.62 386

FMVSNet1		96.84 383	96.36 387	98.29 350	99.32 297	97.26 331	99.43 257	99.48 203	95.11 419	98.55 373	99.32 367	83.95 459	98.98 422	95.81 401	96.26 374	98.62 386

fmvsm_s_conf0.5_n_7		99.34 75	99.29 66	99.48 159	99.70 122	98.63 246	99.42 264	99.63 46	99.46 7	99.98 13	99.88 56	95.59 227	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	99.42 264	99.61 60	99.37 24	99.97 25	99.86 77	94.96 252	99.99 4	99.97 2	99.93 33	99.92 23

mamv4		99.33 77	99.42 32	99.07 232	99.67 136	97.73 309	99.42 264	99.60 67	98.15 175	99.94 28	99.91 26	98.42 91	99.94 92	99.72 32	99.96 17	99.54 218

testgi		97.65 342	97.50 319	98.13 365	99.36 283	96.45 383	99.42 264	99.48 203	97.76 250	97.87 415	99.45 326	91.09 391	98.81 440	94.53 426	98.52 274	99.13 293

F-COLMAP		99.19 101	99.04 114	99.64 101	99.78 70	99.27 143	99.42 264	99.54 109	97.29 306	99.41 204	99.59 273	98.42 91	99.93 110	98.19 251	99.69 153	99.73 126

Anonymous202405211		98.30 241	97.98 262	99.26 212	99.57 203	98.16 282	99.41 269	98.55 447	96.03 407	99.19 266	99.74 198	91.87 369	99.92 123	99.16 116	98.29 290	99.70 150

MSLP-MVS++		99.46 42	99.47 24	99.44 173	99.60 194	99.16 155	99.41 269	99.71 16	98.98 72	99.45 188	99.78 175	99.19 11	99.54 322	99.28 95	99.84 102	99.63 186

VNet		99.11 140	98.90 159	99.73 83	99.52 225	99.56 94	99.41 269	99.39 283	99.01 64	99.74 95	99.78 175	95.56 228	99.92 123	99.52 55	98.18 299	99.72 136

baseline2		97.87 298	97.55 311	98.82 282	99.18 332	98.02 291	99.41 269	96.58 479	96.97 336	96.51 443	99.17 388	93.43 326	99.57 317	97.71 304	99.03 234	98.86 320

DU-MVS		98.08 263	97.79 282	98.96 247	98.87 393	98.98 180	99.41 269	99.45 248	97.87 232	98.71 346	99.50 308	94.82 262	99.22 380	98.57 212	92.87 442	98.68 356

Baseline_NR-MVSNet		97.76 319	97.45 327	98.68 301	99.09 356	98.29 276	99.41 269	98.85 417	95.65 412	98.63 364	99.67 240	94.82 262	99.10 404	98.07 269	92.89 441	98.64 377

XVG-ACMP-BASELINE		97.83 308	97.71 296	98.20 358	99.11 350	96.33 387	99.41 269	99.52 133	98.06 205	99.05 295	99.50 308	89.64 409	99.73 268	97.73 301	97.38 348	98.53 407

DP-MVS		99.16 111	98.95 149	99.78 71	99.77 78	99.53 101	99.41 269	99.50 178	97.03 333	99.04 296	99.88 56	97.39 125	99.92 123	98.66 195	99.90 57	99.87 40

9.14			99.10 99		99.72 111		99.40 277	99.51 155	97.53 280	99.64 143	99.78 175	98.84 46	99.91 135	97.63 309	99.82 117

D2MVS		98.41 230	98.50 220	98.15 364	99.26 311	96.62 377	99.40 277	99.61 60	97.71 256	98.98 306	99.36 352	96.04 202	99.67 293	98.70 188	97.41 346	98.15 438

Anonymous20240529		98.09 260	97.68 299	99.34 190	99.66 149	98.44 270	99.40 277	99.43 268	93.67 440	99.22 257	99.89 45	90.23 402	99.93 110	99.26 101	98.33 283	99.66 168

FMVSNet3		98.03 273	97.76 291	98.84 280	99.39 275	98.98 180	99.40 277	99.38 291	96.67 356	99.07 288	99.28 374	92.93 337	98.98 422	97.10 355	96.65 363	98.56 405

LFMVS		97.90 294	97.35 344	99.54 125	99.52 225	99.01 177	99.39 281	98.24 455	97.10 325	99.65 138	99.79 168	84.79 455	99.91 135	99.28 95	98.38 280	99.69 153

HQP_MVS		98.27 244	98.22 237	98.44 335	99.29 303	96.97 355	99.39 281	99.47 225	98.97 75	99.11 279	99.61 268	92.71 347	99.69 290	97.78 293	97.63 322	98.67 364

plane_prior2							99.39 281		98.97 75

CHOSEN 1792x2688		99.19 101	99.10 99	99.45 168	99.89 8	98.52 260	99.39 281	99.94 1	98.73 102	99.11 279	99.89 45	95.50 230	99.94 92	99.50 57	99.97 9	99.89 29

PAPM_NR		99.04 158	98.84 175	99.66 91	99.74 100	99.44 116	99.39 281	99.38 291	97.70 259	99.28 239	99.28 374	98.34 97	99.85 187	96.96 365	99.45 179	99.69 153

gg-mvs-nofinetune		96.17 397	95.32 409	98.73 293	98.79 403	98.14 284	99.38 286	94.09 486	91.07 463	98.07 406	91.04 484	89.62 410	99.35 355	96.75 375	99.09 229	98.68 356

VDDNet		97.55 348	97.02 370	99.16 224	99.49 242	98.12 287	99.38 286	99.30 340	95.35 415	99.68 118	99.90 36	82.62 465	99.93 110	99.31 86	98.13 303	99.42 260

ME-MVS		99.56 21	99.46 28	99.86 34	99.80 63	99.81 33	99.37 288	99.70 18	99.18 34	99.83 64	99.83 105	98.74 65	99.93 110	98.83 171	99.89 68	99.83 63

MGCNet		99.15 115	98.96 145	99.73 83	98.92 385	99.37 123	99.37 288	96.92 472	99.51 2	99.66 129	99.78 175	96.69 167	99.97 29	99.84 28	99.97 9	99.84 53

pmmvs6		96.53 389	96.09 394	97.82 395	98.69 422	95.47 415	99.37 288	99.47 225	93.46 444	97.41 424	99.78 175	87.06 439	99.33 358	96.92 370	92.70 444	98.65 375

PM-MVS		92.96 435	92.23 439	95.14 444	95.61 473	89.98 470	99.37 288	98.21 457	94.80 429	95.04 458	97.69 461	65.06 479	97.90 461	94.30 428	89.98 459	97.54 464

WTY-MVS		99.06 153	98.88 166	99.61 109	99.62 177	99.16 155	99.37 288	99.56 90	98.04 215	99.53 175	99.62 264	96.84 159	99.94 92	98.85 165	98.49 276	99.72 136

IterMVS-LS		98.46 225	98.42 224	98.58 310	99.59 196	98.00 292	99.37 288	99.43 268	96.94 341	99.07 288	99.59 273	97.87 114	99.03 413	98.32 242	95.62 393	98.71 342
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
h-mvs33		97.70 333	97.28 356	98.97 246	99.70 122	97.27 329	99.36 294	99.45 248	98.94 78	99.66 129	99.64 253	94.93 255	99.99 4	99.48 64	84.36 470	99.65 174

DPE-MVS		99.46 42	99.32 54	99.91 6	99.78 70	99.88 10	99.36 294	99.51 155	98.73 102	99.88 43	99.84 99	98.72 67	99.96 41	98.16 255	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		96.44 391	96.12 392	97.40 416	98.65 425	95.65 408	99.36 294	99.51 155	97.13 319	96.04 450	98.99 410	88.40 425	98.17 454	96.71 377	90.27 457	98.40 423

sss		99.17 109	99.05 112	99.53 133	99.62 177	98.97 183	99.36 294	99.62 51	97.83 240	99.67 124	99.65 247	97.37 128	99.95 76	99.19 107	99.19 203	99.68 159

DeepC-MVS_fast	98.69 1	99.49 33	99.39 40	99.77 74	99.63 168	99.59 88	99.36 294	99.46 237	99.07 58	99.79 76	99.82 118	98.85 44	99.92 123	98.68 193	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	99.41 267	99.16 155	99.35 299	99.57 85	98.82 89	99.51 179	99.61 268	96.46 181	99.95 76	99.59 45	99.98 4	99.65 174

pmmvs-eth3d		95.34 414	94.73 416	97.15 420	95.53 475	95.94 399	99.35 299	99.10 378	95.13 417	93.55 465	97.54 466	88.15 429	97.91 460	94.58 425	89.69 462	97.61 460

MDTV_nov1_ep13_2view						95.18 425	99.35 299		96.84 346	99.58 162		95.19 246		97.82 288		99.46 253

VDD-MVS		97.73 327	97.35 344	98.88 269	99.47 250	97.12 337	99.34 302	98.85 417	98.19 170	99.67 124	99.85 84	82.98 463	99.92 123	99.49 61	98.32 287	99.60 194

COLMAP_ROB	97.56 6	98.86 183	98.75 184	99.17 223	99.88 13	98.53 256	99.34 302	99.59 73	97.55 276	98.70 352	99.89 45	95.83 215	99.90 148	98.10 261	99.90 57	99.08 299
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
viewmambaseed2359dif		99.01 165	98.90 159	99.32 196	99.58 198	98.51 262	99.33 304	99.54 109	97.85 236	99.44 193	99.85 84	96.01 204	99.79 244	99.41 70	99.13 211	99.67 163

myMVS_eth3d28		97.69 334	97.34 347	98.73 293	99.27 308	97.52 320	99.33 304	98.78 427	98.03 217	98.82 334	98.49 438	86.64 440	99.46 328	98.44 228	98.24 293	99.23 287

EGC-MVSNET		82.80 448	77.86 454	97.62 406	97.91 446	96.12 395	99.33 304	99.28 346	8.40 492	25.05 493	99.27 377	84.11 458	99.33 358	89.20 464	98.22 294	97.42 466

diffmvs_AUTHOR		99.19 101	99.10 99	99.48 159	99.64 164	98.85 220	99.32 307	99.48 203	98.50 124	99.81 69	99.81 133	96.82 160	99.88 168	99.40 71	99.12 216	99.71 147

ETVMVS		97.50 354	96.90 374	99.29 206	99.23 319	98.78 234	99.32 307	98.90 410	97.52 282	98.56 372	98.09 456	84.72 456	99.69 290	97.86 283	97.88 312	99.39 266

FMVSNet5		96.43 392	96.19 391	97.15 420	99.11 350	95.89 402	99.32 307	99.52 133	94.47 435	98.34 388	99.07 398	87.54 435	97.07 471	92.61 452	95.72 390	98.47 414

dp		97.75 323	97.80 281	97.59 410	99.10 353	93.71 451	99.32 307	98.88 413	96.48 375	99.08 287	99.55 288	92.67 350	99.82 226	96.52 385	98.58 268	99.24 286

tpmvs		97.98 282	98.02 259	97.84 390	99.04 367	94.73 433	99.31 311	99.20 366	96.10 406	98.76 342	99.42 331	94.94 254	99.81 231	96.97 364	98.45 277	98.97 314

tpmrst		98.33 238	98.48 221	97.90 383	99.16 342	94.78 432	99.31 311	99.11 377	97.27 307	99.45 188	99.59 273	95.33 238	99.84 196	98.48 222	98.61 265	99.09 298

testing99		97.36 364	96.94 373	98.63 304	99.18 332	96.70 371	99.30 313	98.93 400	97.71 256	98.23 394	98.26 448	84.92 454	99.84 196	98.04 271	97.85 315	99.35 272

MP-MVS-pluss		99.37 68	99.20 86	99.88 15	99.90 4	99.87 17	99.30 313	99.52 133	97.18 315	99.60 158	99.79 168	98.79 52	99.95 76	98.83 171	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	99.61 188	99.65 75	99.30 313	99.48 203	98.86 84	99.21 260	99.63 259	98.72 67	99.90 148	98.25 247	99.63 164	99.80 88

JIA-IIPM		97.50 354	97.02 370	98.93 253	98.73 415	97.80 307	99.30 313	98.97 396	91.73 459	98.91 317	94.86 478	95.10 249	99.71 278	97.58 313	97.98 307	99.28 280

BH-RMVSNet		98.41 230	98.08 251	99.40 180	99.41 267	98.83 225	99.30 313	98.77 428	97.70 259	98.94 314	99.65 247	92.91 340	99.74 262	96.52 385	99.55 172	99.64 181

usedtu_blend_shiyan5		95.04 418	94.10 425	97.86 387	96.45 467	95.92 400	99.29 318	99.22 361	86.17 475	98.36 385	97.68 462	91.20 389	99.07 406	97.53 321	80.97 477	98.60 398

testing11		97.50 354	97.10 367	98.71 298	99.20 326	96.91 363	99.29 318	98.82 420	97.89 230	98.21 397	98.40 442	85.63 449	99.83 217	98.45 227	98.04 306	99.37 270

Syy-MVS		97.09 378	97.14 364	96.95 429	99.00 372	92.73 461	99.29 318	99.39 283	97.06 329	97.41 424	98.15 451	93.92 316	98.68 445	91.71 455	98.34 281	99.45 256

myMVS_eth3d		96.89 381	96.37 386	98.43 337	99.00 372	97.16 335	99.29 318	99.39 283	97.06 329	97.41 424	98.15 451	83.46 462	98.68 445	95.27 416	98.34 281	99.45 256

MCST-MVS		99.43 53	99.30 62	99.82 57	99.79 68	99.74 54	99.29 318	99.40 280	98.79 95	99.52 177	99.62 264	98.91 39	99.90 148	98.64 197	99.75 142	99.82 72

LF4IMVS		97.52 351	97.46 326	97.70 403	98.98 378	95.55 411	99.29 318	98.82 420	98.07 201	98.66 355	99.64 253	89.97 404	99.61 313	97.01 360	96.68 362	97.94 453

hse-mvs2		97.50 354	97.14 364	98.59 307	99.49 242	97.05 344	99.28 324	99.22 361	98.94 78	99.66 129	99.42 331	94.93 255	99.65 301	99.48 64	83.80 472	99.08 299

OPM-MVS		98.19 249	98.10 247	98.45 332	98.88 390	97.07 342	99.28 324	99.38 291	98.57 117	99.22 257	99.81 133	92.12 364	99.66 296	98.08 266	97.54 331	98.61 395
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
diffmvs		99.14 123	99.02 127	99.51 144	99.61 188	98.96 187	99.28 324	99.49 191	98.46 128	99.72 102	99.71 211	96.50 179	99.88 168	99.31 86	99.11 218	99.67 163
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		98.86 183	98.80 178	99.03 238	99.76 82	98.79 231	99.28 324	99.91 3	97.42 295	99.67 124	99.37 349	97.53 122	99.88 168	98.98 138	97.29 351	98.42 420

OMC-MVS		99.08 148	99.04 114	99.20 220	99.67 136	98.22 280	99.28 324	99.52 133	98.07 201	99.66 129	99.81 133	97.79 117	99.78 250	97.79 292	99.81 120	99.60 194

testing222		97.16 374	96.50 383	99.16 224	99.16 342	98.47 269	99.27 329	98.66 443	97.71 256	98.23 394	98.15 451	82.28 468	99.84 196	97.36 338	97.66 321	99.18 290

AUN-MVS		96.88 382	96.31 388	98.59 307	99.48 249	97.04 347	99.27 329	99.22 361	97.44 292	98.51 375	99.41 335	91.97 367	99.66 296	97.71 304	83.83 471	99.07 304

pmmvs5		97.52 351	97.30 353	98.16 361	98.57 434	96.73 370	99.27 329	98.90 410	96.14 400	98.37 384	99.53 297	91.54 381	99.14 393	97.51 324	95.87 385	98.63 384

1314		98.68 212	98.54 217	99.11 230	98.89 389	98.65 243	99.27 329	99.49 191	96.89 343	97.99 408	99.56 285	97.72 120	99.83 217	97.74 300	99.27 194	98.84 322

MVS		97.28 369	96.55 382	99.48 159	98.78 406	98.95 193	99.27 329	99.39 283	83.53 478	98.08 403	99.54 293	96.97 151	99.87 175	94.23 431	99.16 204	99.63 186

BH-untuned		98.42 228	98.36 227	98.59 307	99.49 242	96.70 371	99.27 329	99.13 375	97.24 311	98.80 337	99.38 346	95.75 221	99.74 262	97.07 359	99.16 204	99.33 276

MDTV_nov1_ep13			98.32 231		99.11 350	94.44 441	99.27 329	98.74 432	97.51 283	99.40 209	99.62 264	94.78 266	99.76 256	97.59 312	98.81 257

DP-MVS Recon		99.12 134	98.95 149	99.65 95	99.74 100	99.70 60	99.27 329	99.57 85	96.40 382	99.42 199	99.68 234	98.75 60	99.80 238	97.98 274	99.72 148	99.44 258

PatchmatchNet		98.31 239	98.36 227	98.19 359	99.16 342	95.32 421	99.27 329	98.92 403	97.37 299	99.37 215	99.58 277	94.90 259	99.70 285	97.43 334	99.21 201	99.54 218
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thres200		97.61 345	97.28 356	98.62 305	99.64 164	98.03 290	99.26 338	98.74 432	97.68 261	99.09 285	98.32 446	91.66 378	99.81 231	92.88 448	98.22 294	98.03 445

CNVR-MVS		99.42 55	99.30 62	99.78 71	99.62 177	99.71 58	99.26 338	99.52 133	98.82 89	99.39 211	99.71 211	98.96 27	99.85 187	98.59 208	99.80 125	99.77 100

mamba_0408		99.08 148	98.96 145	99.44 173	99.62 177	98.88 212	99.25 340	99.47 225	98.05 208	99.37 215	99.81 133	96.85 155	99.85 187	98.98 138	99.25 197	99.60 194

SSM_04072		99.06 153	98.96 145	99.35 189	99.62 177	98.88 212	99.25 340	99.47 225	98.05 208	99.37 215	99.81 133	96.85 155	99.58 316	98.98 138	99.25 197	99.60 194

tt0320		95.71 407	95.07 411	97.62 406	99.05 365	95.02 427	99.25 340	99.52 133	86.81 472	97.97 410	99.72 208	83.58 461	99.15 391	96.38 391	93.35 433	98.68 356

1112_ss		98.98 169	98.77 182	99.59 113	99.68 133	99.02 175	99.25 340	99.48 203	97.23 312	99.13 275	99.58 277	96.93 153	99.90 148	98.87 158	98.78 258	99.84 53

TAPA-MVS	97.07 15	97.74 325	97.34 347	98.94 251	99.70 122	97.53 319	99.25 340	99.51 155	91.90 458	99.30 235	99.63 259	98.78 53	99.64 305	88.09 469	99.87 79	99.65 174
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
UWE-MVS-28		97.36 364	97.24 360	97.75 399	98.84 399	94.44 441	99.24 345	97.58 468	97.98 222	99.00 303	99.00 408	91.35 385	99.53 323	93.75 436	98.39 279	99.27 284

UBG		97.85 301	97.48 321	98.95 249	99.25 315	97.64 316	99.24 345	98.74 432	97.90 229	98.64 362	98.20 450	88.65 421	99.81 231	98.27 245	98.40 278	99.42 260

PLC	97.94 4	99.02 161	98.85 173	99.53 133	99.66 149	99.01 177	99.24 345	99.52 133	96.85 345	99.27 245	99.48 317	98.25 101	99.91 135	97.76 297	99.62 165	99.65 174
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test_post1							99.23 348				65.14 490	94.18 305	99.71 278	97.58 313

ADS-MVSNet2		98.02 275	98.07 254	97.87 385	99.33 290	95.19 424	99.23 348	99.08 381	96.24 390	99.10 282	99.67 240	94.11 307	98.93 434	96.81 373	99.05 232	99.48 242

ADS-MVSNet		98.20 248	98.08 251	98.56 315	99.33 290	96.48 382	99.23 348	99.15 372	96.24 390	99.10 282	99.67 240	94.11 307	99.71 278	96.81 373	99.05 232	99.48 242

EPNet_dtu		98.03 273	97.96 264	98.23 357	98.27 442	95.54 413	99.23 348	98.75 429	99.02 62	97.82 417	99.71 211	96.11 199	99.48 325	93.04 446	99.65 161	99.69 153
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		98.17 252	97.93 269	98.87 273	99.18 332	98.49 265	99.22 352	99.33 321	96.96 337	99.56 166	99.38 346	94.33 298	99.00 420	94.83 424	98.58 268	99.14 291

RPMNet		96.72 385	95.90 398	99.19 221	99.18 332	98.49 265	99.22 352	99.52 133	88.72 470	99.56 166	97.38 468	94.08 309	99.95 76	86.87 476	98.58 268	99.14 291

sc_t1		95.75 405	95.05 412	97.87 385	98.83 400	94.61 438	99.21 354	99.45 248	87.45 471	97.97 410	99.85 84	81.19 471	99.43 339	98.27 245	93.20 437	99.57 212

WBMVS		97.74 325	97.50 319	98.46 330	99.24 317	97.43 323	99.21 354	99.42 270	97.45 289	98.96 310	99.41 335	88.83 416	99.23 375	98.94 146	96.02 378	98.71 342

plane_prior						96.97 355	99.21 354		98.45 130						97.60 325

IMVS_0404		98.53 221	98.52 219	98.55 317	99.55 211	96.93 358	99.20 357	99.44 257	98.05 208	98.96 310	99.80 151	94.66 280	99.13 396	98.15 257	98.92 243	99.60 194

tt0320-xc		95.31 415	94.59 419	97.45 414	98.92 385	94.73 433	99.20 357	99.31 335	86.74 473	97.23 430	99.72 208	81.14 472	98.95 432	97.08 358	91.98 448	98.67 364

testing91		97.44 361	97.02 370	98.71 298	99.18 332	96.89 365	99.19 359	99.04 388	97.78 248	98.31 389	98.29 447	85.41 451	99.85 187	98.01 272	97.95 308	99.39 266

WR-MVS		98.06 265	97.73 294	99.06 234	98.86 396	99.25 146	99.19 359	99.35 308	97.30 305	98.66 355	99.43 329	93.94 314	99.21 385	98.58 209	94.28 420	98.71 342

new-patchmatchnet		94.48 426	94.08 427	95.67 443	95.08 478	92.41 462	99.18 361	99.28 346	94.55 434	93.49 466	97.37 469	87.86 433	97.01 472	91.57 456	88.36 464	97.61 460

AdaColmap		99.01 165	98.80 178	99.66 91	99.56 207	99.54 98	99.18 361	99.70 18	98.18 173	99.35 224	99.63 259	96.32 188	99.90 148	97.48 327	99.77 137	99.55 216

EG-PatchMatch MVS		95.97 401	95.69 402	96.81 433	97.78 449	92.79 460	99.16 363	98.93 400	96.16 397	94.08 462	99.22 383	82.72 464	99.47 326	95.67 407	97.50 336	98.17 436

PatchT		97.03 379	96.44 385	98.79 288	98.99 375	98.34 275	99.16 363	99.07 384	92.13 457	99.52 177	97.31 471	94.54 288	98.98 422	88.54 467	98.73 260	99.03 307

CNLPA		99.14 123	98.99 137	99.59 113	99.58 198	99.41 120	99.16 363	99.44 257	98.45 130	99.19 266	99.49 311	98.08 109	99.89 163	97.73 301	99.75 142	99.48 242

MDA-MVSNet-bldmvs		94.96 421	93.98 428	97.92 381	98.24 443	97.27 329	99.15 366	99.33 321	93.80 439	80.09 485	99.03 404	88.31 426	97.86 462	93.49 440	94.36 419	98.62 386

CDPH-MVS		99.13 126	98.91 157	99.80 64	99.75 92	99.71 58	99.15 366	99.41 273	96.60 366	99.60 158	99.55 288	98.83 47	99.90 148	97.48 327	99.83 113	99.78 98

save fliter					99.76 82	99.59 88	99.14 368	99.40 280	99.00 67

WB-MVSnew		97.65 342	97.65 302	97.63 405	98.78 406	97.62 317	99.13 369	98.33 452	97.36 300	99.07 288	98.94 416	95.64 226	99.15 391	92.95 447	98.68 263	96.12 476

testf1		90.42 442	90.68 443	89.65 463	97.78 449	73.97 491	99.13 369	98.81 422	89.62 465	91.80 474	98.93 417	62.23 482	98.80 441	86.61 477	91.17 451	96.19 474

APD_test2		90.42 442	90.68 443	89.65 463	97.78 449	73.97 491	99.13 369	98.81 422	89.62 465	91.80 474	98.93 417	62.23 482	98.80 441	86.61 477	91.17 451	96.19 474

xiu_mvs_v1_base_debu		99.29 85	99.27 73	99.34 190	99.63 168	98.97 183	99.12 372	99.51 155	98.86 84	99.84 56	99.47 320	98.18 104	99.99 4	99.50 57	99.31 191	99.08 299

xiu_mvs_v1_base		99.29 85	99.27 73	99.34 190	99.63 168	98.97 183	99.12 372	99.51 155	98.86 84	99.84 56	99.47 320	98.18 104	99.99 4	99.50 57	99.31 191	99.08 299

xiu_mvs_v1_base_debi		99.29 85	99.27 73	99.34 190	99.63 168	98.97 183	99.12 372	99.51 155	98.86 84	99.84 56	99.47 320	98.18 104	99.99 4	99.50 57	99.31 191	99.08 299

XVG-OURS-SEG-HR		98.69 211	98.62 207	98.89 265	99.71 117	97.74 308	99.12 372	99.54 109	98.44 133	99.42 199	99.71 211	94.20 302	99.92 123	98.54 219	98.90 249	99.00 310

jason		99.13 126	99.03 117	99.45 168	99.46 252	98.87 216	99.12 372	99.26 353	98.03 217	99.79 76	99.65 247	97.02 148	99.85 187	99.02 135	99.90 57	99.65 174
jason: jason.
N_pmnet		94.95 422	95.83 400	92.31 454	98.47 438	79.33 486	99.12 372	92.81 492	93.87 438	97.68 420	99.13 393	93.87 318	99.01 419	91.38 457	96.19 375	98.59 402

MDA-MVSNet_test_wron		95.45 410	94.60 418	98.01 372	98.16 444	97.21 334	99.11 378	99.24 358	93.49 443	80.73 484	98.98 412	93.02 335	98.18 453	94.22 432	94.45 417	98.64 377

Patchmtry		97.75 323	97.40 339	98.81 285	99.10 353	98.87 216	99.11 378	99.33 321	94.83 428	98.81 335	99.38 346	94.33 298	99.02 416	96.10 394	95.57 395	98.53 407

YYNet1		95.36 413	94.51 421	97.92 381	97.89 447	97.10 338	99.10 380	99.23 359	93.26 446	80.77 483	99.04 403	92.81 341	98.02 457	94.30 428	94.18 422	98.64 377

CANet_DTU		98.97 171	98.87 167	99.25 213	99.33 290	98.42 273	99.08 381	99.30 340	99.16 37	99.43 196	99.75 193	95.27 240	99.97 29	98.56 215	99.95 23	99.36 271

icg_test_0407_2		98.79 200	98.86 170	98.57 311	99.55 211	96.93 358	99.07 382	99.44 257	98.05 208	99.66 129	99.80 151	97.13 139	99.18 388	98.15 257	98.92 243	99.60 194

SCA		98.19 249	98.16 239	98.27 355	99.30 299	95.55 411	99.07 382	98.97 396	97.57 273	99.43 196	99.57 282	92.72 345	99.74 262	97.58 313	99.20 202	99.52 225

TSAR-MVS + GP.		99.36 72	99.36 46	99.36 187	99.67 136	98.61 250	99.07 382	99.33 321	99.00 67	99.82 68	99.81 133	99.06 18	99.84 196	99.09 126	99.42 181	99.65 174

MG-MVS		99.13 126	99.02 127	99.45 168	99.57 203	98.63 246	99.07 382	99.34 313	98.99 69	99.61 155	99.82 118	97.98 113	99.87 175	97.00 361	99.80 125	99.85 46

PatchMatch-RL		98.84 195	98.62 207	99.52 139	99.71 117	99.28 141	99.06 386	99.77 12	97.74 254	99.50 180	99.53 297	95.41 233	99.84 196	97.17 354	99.64 162	99.44 258

OpenMVS_ROB	92.34 20	94.38 427	93.70 433	96.41 438	97.38 455	93.17 458	99.06 386	98.75 429	86.58 474	94.84 459	98.26 448	81.53 469	99.32 360	89.01 465	97.87 313	96.76 469

TEST9					99.67 136	99.65 75	99.05 388	99.41 273	96.22 392	98.95 312	99.49 311	98.77 56	99.91 135

train_agg		99.02 161	98.77 182	99.77 74	99.67 136	99.65 75	99.05 388	99.41 273	96.28 386	98.95 312	99.49 311	98.76 57	99.91 135	97.63 309	99.72 148	99.75 112

lupinMVS		99.13 126	99.01 133	99.46 167	99.51 228	98.94 197	99.05 388	99.16 371	97.86 233	99.80 74	99.56 285	97.39 125	99.86 181	98.94 146	99.85 94	99.58 209

DELS-MVS		99.48 37	99.42 32	99.65 95	99.72 111	99.40 121	99.05 388	99.66 32	99.14 40	99.57 165	99.80 151	98.46 87	99.94 92	99.57 48	99.84 102	99.60 194
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		96.38 393	96.03 395	97.41 415	98.13 445	95.16 426	99.05 388	99.20 366	93.94 437	97.39 427	98.79 428	91.61 380	99.04 411	90.43 460	95.77 387	98.05 444

Patchmatch-test		97.93 288	97.65 302	98.77 291	99.18 332	97.07 342	99.03 393	99.14 374	96.16 397	98.74 343	99.57 282	94.56 285	99.72 272	93.36 441	99.11 218	99.52 225

test_8					99.67 136	99.61 85	99.03 393	99.41 273	96.28 386	98.93 315	99.48 317	98.76 57	99.91 135

Test_1112_low_res		98.89 176	98.66 197	99.57 120	99.69 127	98.95 193	99.03 393	99.47 225	96.98 335	99.15 273	99.23 382	96.77 164	99.89 163	98.83 171	98.78 258	99.86 42

IterMVS-SCA-FT		97.82 311	97.75 292	98.06 368	99.57 203	96.36 386	99.02 396	99.49 191	97.18 315	98.71 346	99.72 208	92.72 345	99.14 393	97.44 333	95.86 386	98.67 364

xiu_mvs_v2_base		99.26 92	99.25 77	99.29 206	99.53 219	98.91 204	99.02 396	99.45 248	98.80 94	99.71 111	99.26 379	98.94 34	99.98 20	99.34 81	99.23 200	98.98 313

MIMVSNet		97.73 327	97.45 327	98.57 311	99.45 258	97.50 321	99.02 396	98.98 395	96.11 402	99.41 204	99.14 392	90.28 398	98.74 443	95.74 403	98.93 241	99.47 248

IterMVS		97.83 308	97.77 287	98.02 371	99.58 198	96.27 390	99.02 396	99.48 203	97.22 313	98.71 346	99.70 215	92.75 342	99.13 396	97.46 330	96.00 380	98.67 364
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		99.11 140	98.92 154	99.65 95	99.90 4	99.37 123	99.02 396	99.91 3	97.67 263	99.59 161	99.75 193	95.90 212	99.73 268	99.53 53	99.02 236	99.86 42

UWE-MVS		97.58 347	97.29 355	98.48 324	99.09 356	96.25 391	99.01 401	96.61 478	97.86 233	99.19 266	99.01 407	88.72 417	99.90 148	97.38 337	98.69 262	99.28 280

新几何2							99.01 401

BH-w/o		98.00 280	97.89 275	98.32 347	99.35 284	96.20 393	99.01 401	98.90 410	96.42 380	98.38 383	99.00 408	95.26 242	99.72 272	96.06 395	98.61 265	99.03 307

test_prior4						99.56 94	98.99 404

无先验							98.99 404	99.51 155	96.89 343				99.93 110	97.53 321		99.72 136

pmmvs4		98.13 256	97.90 271	98.81 285	98.61 430	98.87 216	98.99 404	99.21 365	96.44 378	99.06 293	99.58 277	95.90 212	99.11 402	97.18 353	96.11 377	98.46 417

HQP-NCC					99.19 329		98.98 407		98.24 162	98.66 355

ACMP_Plane					99.19 329		98.98 407		98.24 162	98.66 355

HQP-MVS		98.02 275	97.90 271	98.37 343	99.19 329	96.83 366	98.98 407	99.39 283	98.24 162	98.66 355	99.40 339	92.47 356	99.64 305	97.19 351	97.58 327	98.64 377

PS-MVSNAJ		99.32 79	99.32 54	99.30 203	99.57 203	98.94 197	98.97 410	99.46 237	98.92 81	99.71 111	99.24 381	99.01 20	99.98 20	99.35 76	99.66 159	98.97 314

MVP-Stereo		97.81 313	97.75 292	97.99 375	97.53 453	96.60 379	98.96 411	98.85 417	97.22 313	97.23 430	99.36 352	95.28 239	99.46 328	95.51 409	99.78 134	97.92 455
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test_prior2							98.96 411		98.34 143	99.01 299	99.52 301	98.68 70		97.96 275	99.74 145

旧先验2							98.96 411		96.70 354	99.47 185			99.94 92	98.19 251

原ACMM2							98.95 414

MVS_111021_HR		99.41 59	99.32 54	99.66 91	99.72 111	99.47 113	98.95 414	99.85 9	98.82 89	99.54 173	99.73 204	98.51 84	99.74 262	98.91 152	99.88 76	99.77 100

mvsany_test1		99.50 31	99.46 28	99.62 108	99.61 188	99.09 165	98.94 416	99.48 203	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	98.94 416	99.85 9	98.82 89	99.65 138	99.74 198	98.51 84	99.80 238	98.83 171	99.89 68	99.64 181

pmmvs3		94.09 429	93.25 436	96.60 436	94.76 481	94.49 440	98.92 418	98.18 459	89.66 464	96.48 444	98.06 457	86.28 444	97.33 469	89.68 463	87.20 467	97.97 452

XVG-OURS		98.73 209	98.68 193	98.88 269	99.70 122	97.73 309	98.92 418	99.55 100	98.52 122	99.45 188	99.84 99	95.27 240	99.91 135	98.08 266	98.84 253	99.00 310

test222					99.75 92	99.49 109	98.91 420	99.49 191	96.42 380	99.34 228	99.65 247	98.28 100			99.69 153	99.72 136

PMMVS2		86.87 445	85.37 449	91.35 458	90.21 487	83.80 477	98.89 421	97.45 470	83.13 479	91.67 476	95.03 476	48.49 488	94.70 482	85.86 479	77.62 481	95.54 477

miper_lstm_enhance		98.00 280	97.91 270	98.28 354	99.34 289	97.43 323	98.88 422	99.36 301	96.48 375	98.80 337	99.55 288	95.98 205	98.91 435	97.27 344	95.50 398	98.51 410

MVS-HIRNet		95.75 405	95.16 410	97.51 412	99.30 299	93.69 452	98.88 422	95.78 480	85.09 477	98.78 340	92.65 480	91.29 387	99.37 348	94.85 423	99.85 94	99.46 253

TR-MVS		97.76 319	97.41 338	98.82 282	99.06 362	97.87 303	98.87 424	98.56 446	96.63 362	98.68 354	99.22 383	92.49 355	99.65 301	95.40 413	97.79 317	98.95 318

blended_shiyan6		95.54 408	94.78 415	97.84 390	96.60 466	95.89 402	98.85 425	99.28 346	92.17 456	98.43 380	97.95 459	91.44 382	99.02 416	97.30 342	80.97 477	98.60 398

testdata1							98.85 425		98.32 147

blend_shiyan4		95.25 416	94.39 423	97.84 390	96.70 465	95.92 400	98.84 427	99.28 346	92.21 454	98.16 400	97.84 460	87.10 438	99.07 406	97.53 321	81.87 474	98.54 406

ET-MVSNet_ETH3D		96.49 390	95.64 404	99.05 236	99.53 219	98.82 228	98.84 427	97.51 469	97.63 266	84.77 478	99.21 386	92.09 365	98.91 435	98.98 138	92.21 447	99.41 263

our_test_3		97.65 342	97.68 299	97.55 411	98.62 428	94.97 429	98.84 427	99.30 340	96.83 348	98.19 398	99.34 359	97.01 150	99.02 416	95.00 421	96.01 379	98.64 377

MS-PatchMatch		97.24 373	97.32 351	96.99 426	98.45 439	93.51 456	98.82 430	99.32 331	97.41 296	98.13 402	99.30 370	88.99 414	99.56 319	95.68 406	99.80 125	97.90 456

c3_l		98.12 258	98.04 256	98.38 342	99.30 299	97.69 315	98.81 431	99.33 321	96.67 356	98.83 332	99.34 359	97.11 142	98.99 421	97.58 313	95.34 400	98.48 412

ppachtmachnet_test		97.49 359	97.45 327	97.61 409	98.62 428	95.24 422	98.80 432	99.46 237	96.11 402	98.22 396	99.62 264	96.45 182	98.97 429	93.77 435	95.97 384	98.61 395

PAPR		98.63 218	98.34 229	99.51 144	99.40 272	99.03 174	98.80 432	99.36 301	96.33 383	99.00 303	99.12 396	98.46 87	99.84 196	95.23 417	99.37 190	99.66 168

test0.0.03 1		97.71 332	97.42 337	98.56 315	98.41 441	97.82 306	98.78 434	98.63 444	97.34 301	98.05 407	98.98 412	94.45 293	98.98 422	95.04 420	97.15 357	98.89 319

PVSNet_Blended		99.08 148	98.97 141	99.42 178	99.76 82	98.79 231	98.78 434	99.91 3	96.74 351	99.67 124	99.49 311	97.53 122	99.88 168	98.98 138	99.85 94	99.60 194

PMMVS		98.80 199	98.62 207	99.34 190	99.27 308	98.70 239	98.76 436	99.31 335	97.34 301	99.21 260	99.07 398	97.20 137	99.82 226	98.56 215	98.87 250	99.52 225

test123		39.01 457	42.50 459	28.53 473	39.17 496	20.91 498	98.75 437	19.17 498	19.83 491	38.57 490	66.67 488	33.16 492	15.42 492	37.50 492	29.66 490	49.26 487

MSDG		98.98 169	98.80 178	99.53 133	99.76 82	99.19 150	98.75 437	99.55 100	97.25 309	99.47 185	99.77 184	97.82 116	99.87 175	96.93 368	99.90 57	99.54 218

CLD-MVS		98.16 253	98.10 247	98.33 345	99.29 303	96.82 368	98.75 437	99.44 257	97.83 240	99.13 275	99.55 288	92.92 338	99.67 293	98.32 242	97.69 320	98.48 412
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		98.18 251	98.10 247	98.41 338	99.23 319	97.72 311	98.72 440	99.31 335	96.60 366	98.88 322	99.29 372	97.29 132	99.13 396	97.60 311	95.99 381	98.38 425

cl____		98.01 278	97.84 279	98.55 317	99.25 315	97.97 294	98.71 441	99.34 313	96.47 377	98.59 371	99.54 293	95.65 225	99.21 385	97.21 347	95.77 387	98.46 417

DIV-MVS_self_test		98.01 278	97.85 278	98.48 324	99.24 317	97.95 299	98.71 441	99.35 308	96.50 371	98.60 370	99.54 293	95.72 223	99.03 413	97.21 347	95.77 387	98.46 417

test-LLR		98.06 265	97.90 271	98.55 317	98.79 403	97.10 338	98.67 443	97.75 464	97.34 301	98.61 368	98.85 422	94.45 293	99.45 330	97.25 345	99.38 183	99.10 294

TESTMET0.1,1		97.55 348	97.27 359	98.40 340	98.93 383	96.53 380	98.67 443	97.61 467	96.96 337	98.64 362	99.28 374	88.63 423	99.45 330	97.30 342	99.38 183	99.21 289

test-mter		97.49 359	97.13 366	98.55 317	98.79 403	97.10 338	98.67 443	97.75 464	96.65 358	98.61 368	98.85 422	88.23 427	99.45 330	97.25 345	99.38 183	99.10 294

mvs5depth		96.66 386	96.22 390	97.97 376	97.00 464	96.28 389	98.66 446	99.03 390	96.61 363	96.93 440	99.79 168	87.20 437	99.47 326	96.65 383	94.13 423	98.16 437

IB-MVS	95.67 18	96.22 394	95.44 408	98.57 311	99.21 324	96.70 371	98.65 447	97.74 466	96.71 353	97.27 429	98.54 437	86.03 446	99.92 123	98.47 225	86.30 468	99.10 294
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		98.95 172	98.71 190	99.66 91	99.63 168	99.55 96	98.64 448	99.10 378	97.93 226	99.42 199	99.55 288	98.67 72	99.80 238	95.80 402	99.68 156	99.61 191

thisisatest0515		98.14 255	97.79 282	99.19 221	99.50 240	98.50 264	98.61 449	96.82 474	96.95 339	99.54 173	99.43 329	91.66 378	99.86 181	98.08 266	99.51 174	99.22 288

DeepPCF-MVS	98.18 3	98.81 196	99.37 44	97.12 423	99.60 194	91.75 465	98.61 449	99.44 257	99.35 25	99.83 64	99.85 84	98.70 69	99.81 231	99.02 135	99.91 46	99.81 79

cl22		97.85 301	97.64 305	98.48 324	99.09 356	97.87 303	98.60 451	99.33 321	97.11 324	98.87 325	99.22 383	92.38 361	99.17 390	98.21 249	95.99 381	98.42 420

FE-MVSNET3		98.09 260	97.82 280	98.89 265	98.70 420	98.90 208	98.57 452	99.47 225	96.78 349	98.87 325	99.05 401	94.75 271	99.23 375	97.45 332	96.74 361	98.53 407

GA-MVS		97.85 301	97.47 324	99.00 242	99.38 277	97.99 293	98.57 452	99.15 372	97.04 332	98.90 319	99.30 370	89.83 406	99.38 345	96.70 378	98.33 283	99.62 189

TinyColmap		97.12 376	96.89 375	97.83 393	99.07 360	95.52 414	98.57 452	98.74 432	97.58 272	97.81 418	99.79 168	88.16 428	99.56 319	95.10 418	97.21 354	98.39 424

eth_miper_zixun_eth		98.05 270	97.96 264	98.33 345	99.26 311	97.38 325	98.56 455	99.31 335	96.65 358	98.88 322	99.52 301	96.58 174	99.12 401	97.39 336	95.53 397	98.47 414

CMPMVS	69.68 23	94.13 428	94.90 414	91.84 455	97.24 459	80.01 485	98.52 456	99.48 203	89.01 468	91.99 472	99.67 240	85.67 448	99.13 396	95.44 411	97.03 359	96.39 473
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
USDC		97.34 366	97.20 361	97.75 399	99.07 360	95.20 423	98.51 457	99.04 388	97.99 221	98.31 389	99.86 77	89.02 413	99.55 321	95.67 407	97.36 349	98.49 411

FE-blended-shiyan7		95.43 411	94.66 417	97.77 398	96.45 467	95.68 407	98.48 458	99.28 346	92.18 455	98.36 385	97.68 462	91.20 389	99.03 413	97.31 340	80.97 477	98.60 398

ambc				93.06 453	92.68 484	82.36 478	98.47 459	98.73 438		95.09 457	97.41 467	55.55 484	99.10 404	96.42 388	91.32 450	97.71 457

miper_enhance_ethall		98.16 253	98.08 251	98.41 338	98.96 381	97.72 311	98.45 460	99.32 331	96.95 339	98.97 308	99.17 388	97.06 146	99.22 380	97.86 283	95.99 381	98.29 429

CHOSEN 280x420		99.12 134	99.13 95	99.08 231	99.66 149	97.89 302	98.43 461	99.71 16	98.88 83	99.62 150	99.76 188	96.63 170	99.70 285	99.46 67	99.99 1	99.66 168

testmvs		39.17 456	43.78 458	25.37 474	36.04 497	16.84 499	98.36 462	26.56 496	20.06 490	38.51 491	67.32 487	29.64 493	15.30 493	37.59 491	39.90 489	43.98 488

FPMVS		84.93 447	85.65 448	82.75 469	86.77 490	63.39 495	98.35 463	98.92 403	74.11 481	83.39 480	98.98 412	50.85 487	92.40 484	84.54 480	94.97 408	92.46 479

KD-MVS_2432*1600		94.62 423	93.72 431	97.31 417	97.19 461	95.82 404	98.34 464	99.20 366	95.00 424	97.57 421	98.35 444	87.95 430	98.10 455	92.87 449	77.00 482	98.01 446

miper_refine_blended		94.62 423	93.72 431	97.31 417	97.19 461	95.82 404	98.34 464	99.20 366	95.00 424	97.57 421	98.35 444	87.95 430	98.10 455	92.87 449	77.00 482	98.01 446

CL-MVSNet_self_test		94.49 425	93.97 429	96.08 441	96.16 470	93.67 453	98.33 466	99.38 291	95.13 417	97.33 428	98.15 451	92.69 349	96.57 474	88.67 466	79.87 480	97.99 450

PVSNet	96.02 17	98.85 192	98.84 175	98.89 265	99.73 107	97.28 328	98.32 467	99.60 67	97.86 233	99.50 180	99.57 282	96.75 165	99.86 181	98.56 215	99.70 152	99.54 218

PAPM		97.59 346	97.09 368	99.07 232	99.06 362	98.26 278	98.30 468	99.10 378	94.88 426	98.08 403	99.34 359	96.27 193	99.64 305	89.87 462	98.92 243	99.31 278

Patchmatch-RL test		95.84 403	95.81 401	95.95 442	95.61 473	90.57 468	98.24 469	98.39 450	95.10 421	95.20 455	98.67 432	94.78 266	97.77 463	96.28 393	90.02 458	99.51 234

UnsupCasMVSNet_bld		93.53 432	92.51 438	96.58 437	97.38 455	93.82 448	98.24 469	99.48 203	91.10 462	93.10 467	96.66 473	74.89 476	98.37 450	94.03 434	87.71 466	97.56 463

LCM-MVSNet		86.80 446	85.22 450	91.53 457	87.81 489	80.96 483	98.23 471	98.99 394	71.05 482	90.13 477	96.51 474	48.45 489	96.88 473	90.51 459	85.30 469	96.76 469

cascas		97.69 334	97.43 336	98.48 324	98.60 431	97.30 327	98.18 472	99.39 283	92.96 449	98.41 381	98.78 429	93.77 322	99.27 368	98.16 255	98.61 265	98.86 320

kuosan		90.92 441	90.11 446	93.34 450	98.78 406	85.59 475	98.15 473	93.16 490	89.37 467	92.07 471	98.38 443	81.48 470	95.19 480	62.54 489	97.04 358	99.25 285

Effi-MVS+		98.81 196	98.59 213	99.48 159	99.46 252	99.12 163	98.08 474	99.50 178	97.50 284	99.38 213	99.41 335	96.37 187	99.81 231	99.11 121	98.54 273	99.51 234

PCF-MVS	97.08 14	97.66 341	97.06 369	99.47 165	99.61 188	99.09 165	98.04 475	99.25 355	91.24 461	98.51 375	99.70 215	94.55 287	99.91 135	92.76 451	99.85 94	99.42 260
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet_0	94.43 19	96.09 399	95.47 406	97.94 379	99.31 298	94.34 445	97.81 476	99.70 18	97.12 321	97.46 423	98.75 430	89.71 407	99.79 244	97.69 307	81.69 475	99.68 159

E-PMN		80.61 450	79.88 452	82.81 468	90.75 486	76.38 489	97.69 477	95.76 481	66.44 486	83.52 479	92.25 481	62.54 481	87.16 488	68.53 487	61.40 485	84.89 486

dongtai		93.26 433	92.93 437	94.25 446	99.39 275	85.68 474	97.68 478	93.27 488	92.87 450	96.85 441	99.39 343	82.33 467	97.48 468	76.78 482	97.80 316	99.58 209

ANet_high		77.30 452	74.86 456	84.62 467	75.88 493	77.61 487	97.63 479	93.15 491	88.81 469	64.27 488	89.29 485	36.51 491	83.93 490	75.89 484	52.31 487	92.33 481

EMVS		80.02 451	79.22 453	82.43 470	91.19 485	76.40 488	97.55 480	92.49 493	66.36 487	83.01 481	91.27 483	64.63 480	85.79 489	65.82 488	60.65 486	85.08 485

MVE	76.82 21	76.91 453	74.31 457	84.70 466	85.38 492	76.05 490	96.88 481	93.17 489	67.39 485	71.28 487	89.01 486	21.66 496	87.69 487	71.74 486	72.29 484	90.35 483
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		91.10 439	91.36 441	90.31 460	95.85 471	73.72 493	94.89 482	99.25 355	68.39 484	95.82 451	99.02 406	80.50 473	98.95 432	93.64 438	94.89 412	98.25 432

Gipuma		90.99 440	90.15 445	93.51 449	98.73 415	90.12 469	93.98 483	99.45 248	79.32 480	92.28 470	94.91 477	69.61 477	97.98 459	87.42 473	95.67 391	92.45 480
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	70.75 22	75.98 454	74.97 455	79.01 471	70.98 494	55.18 496	93.37 484	98.21 457	65.08 488	61.78 489	93.83 479	21.74 495	92.53 483	78.59 481	91.12 453	89.34 484
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		82.80 448	81.52 451	86.66 465	66.61 495	68.44 494	92.79 485	97.92 461	68.96 483	80.04 486	99.85 84	85.77 447	96.15 478	97.86 283	43.89 488	95.39 478

wuyk23d		40.18 455	41.29 460	36.84 472	86.18 491	49.12 497	79.73 486	22.81 497	27.64 489	25.46 492	28.45 492	21.98 494	48.89 491	55.80 490	23.56 491	12.51 489

mmdepth		0.02 462	0.03 465	0.00 475	0.00 498	0.00 500	0.00 487	0.00 499	0.00 493	0.00 494	0.27 494	0.00 497	0.00 494	0.00 493	0.00 492	0.00 490

monomultidepth		0.02 462	0.03 465	0.00 475	0.00 498	0.00 500	0.00 487	0.00 499	0.00 493	0.00 494	0.27 494	0.00 497	0.00 494	0.00 493	0.00 492	0.00 490

test_blank		0.13 461	0.17 464	0.00 475	0.00 498	0.00 500	0.00 487	0.00 499	0.00 493	0.00 494	1.57 493	0.00 497	0.00 494	0.00 493	0.00 492	0.00 490

uanet_test		0.02 462	0.03 465	0.00 475	0.00 498	0.00 500	0.00 487	0.00 499	0.00 493	0.00 494	0.27 494	0.00 497	0.00 494	0.00 493	0.00 492	0.00 490

DCPMVS		0.02 462	0.03 465	0.00 475	0.00 498	0.00 500	0.00 487	0.00 499	0.00 493	0.00 494	0.27 494	0.00 497	0.00 494	0.00 493	0.00 492	0.00 490

cdsmvs_eth3d_5k		24.64 458	32.85 461	0.00 475	0.00 498	0.00 500	0.00 487	99.51 155	0.00 493	0.00 494	99.56 285	96.58 174	0.00 494	0.00 493	0.00 492	0.00 490

pcd_1.5k_mvsjas		8.27 460	11.03 463	0.00 475	0.00 498	0.00 500	0.00 487	0.00 499	0.00 493	0.00 494	0.27 494	99.01 20	0.00 494	0.00 493	0.00 492	0.00 490

sosnet-low-res		0.02 462	0.03 465	0.00 475	0.00 498	0.00 500	0.00 487	0.00 499	0.00 493	0.00 494	0.27 494	0.00 497	0.00 494	0.00 493	0.00 492	0.00 490

sosnet		0.02 462	0.03 465	0.00 475	0.00 498	0.00 500	0.00 487	0.00 499	0.00 493	0.00 494	0.27 494	0.00 497	0.00 494	0.00 493	0.00 492	0.00 490

uncertanet		0.02 462	0.03 465	0.00 475	0.00 498	0.00 500	0.00 487	0.00 499	0.00 493	0.00 494	0.27 494	0.00 497	0.00 494	0.00 493	0.00 492	0.00 490

Regformer		0.02 462	0.03 465	0.00 475	0.00 498	0.00 500	0.00 487	0.00 499	0.00 493	0.00 494	0.27 494	0.00 497	0.00 494	0.00 493	0.00 492	0.00 490

ab-mvs-re		8.30 459	11.06 462	0.00 475	0.00 498	0.00 500	0.00 487	0.00 499	0.00 493	0.00 494	99.58 277	0.00 497	0.00 494	0.00 493	0.00 492	0.00 490

uanet		0.02 462	0.03 465	0.00 475	0.00 498	0.00 500	0.00 487	0.00 499	0.00 493	0.00 494	0.27 494	0.00 497	0.00 494	0.00 493	0.00 492	0.00 490

WAC-MVS						97.16 335								95.47 410

MSC_two_6792asdad				99.87 21	99.51 228	99.76 49		99.33 321					99.96 41	98.87 158	99.84 102	99.89 29

PC_three_1452									98.18 173	99.84 56	99.70 215	99.31 3	98.52 448	98.30 244	99.80 125	99.81 79

No_MVS				99.87 21	99.51 228	99.76 49		99.33 321					99.96 41	98.87 158	99.84 102	99.89 29

test_one_0601					99.81 57	99.88 10		99.49 191	98.97 75	99.65 138	99.81 133	99.09 16

eth-test2					0.00 498

eth-test					0.00 498

ZD-MVS					99.71 117	99.79 41		99.61 60	96.84 346	99.56 166	99.54 293	98.58 78	99.96 41	96.93 368	99.75 142

IU-MVS					99.84 38	99.88 10		99.32 331	98.30 149	99.84 56				98.86 163	99.85 94	99.89 29

test_241102_TWO								99.48 203	99.08 56	99.88 43	99.81 133	98.94 34	99.96 41	98.91 152	99.84 102	99.88 35

test_241102_ONE					99.84 38	99.90 3		99.48 203	99.07 58	99.91 31	99.74 198	99.20 9	99.76 256

test_0728_THIRD									98.99 69	99.81 69	99.80 151	99.09 16	99.96 41	98.85 165	99.90 57	99.88 35

GSMVS																99.52 225

test_part2					99.81 57	99.83 22				99.77 85

sam_mvs1												94.86 261				99.52 225

sam_mvs												94.72 274

MTGPA								99.47 225

test_post											65.99 489	94.65 281	99.73 268

patchmatchnet-post											98.70 431	94.79 265	99.74 262

gm-plane-assit					98.54 436	92.96 459			94.65 432		99.15 391		99.64 305	97.56 318

test9_res														97.49 326	99.72 148	99.75 112

agg_prior2														97.21 347	99.73 147	99.75 112

agg_prior					99.67 136	99.62 83		99.40 280		98.87 325			99.91 135

TestCases				99.31 198	99.86 25	98.48 267		99.61 60	97.85 236	99.36 221	99.85 84	95.95 207	99.85 187	96.66 381	99.83 113	99.59 205

test_prior				99.68 89	99.67 136	99.48 111		99.56 90					99.83 217			99.74 117

新几何1				99.75 77	99.75 92	99.59 88		99.54 109	96.76 350	99.29 238	99.64 253	98.43 89	99.94 92	96.92 370	99.66 159	99.72 136

旧先验1					99.74 100	99.59 88		99.54 109			99.69 226	98.47 86			99.68 156	99.73 126

原ACMM1				99.65 95	99.73 107	99.33 130		99.47 225	97.46 286	99.12 277	99.66 245	98.67 72	99.91 135	97.70 306	99.69 153	99.71 147

testdata2													99.95 76	96.67 380

segment_acmp												98.96 27

testdata				99.54 125	99.75 92	98.95 193		99.51 155	97.07 327	99.43 196	99.70 215	98.87 42	99.94 92	97.76 297	99.64 162	99.72 136

test12				99.75 77	99.64 164	99.61 85		99.29 344		99.21 260		98.38 95	99.89 163		99.74 145	99.74 117

plane_prior7					99.29 303	97.03 350

plane_prior6					99.27 308	96.98 354						92.71 347

plane_prior5								99.47 225					99.69 290	97.78 293	97.63 322	98.67 364

plane_prior4											99.61 268

plane_prior3						97.00 352			98.69 107	99.11 279

plane_prior1					99.26 311

n2								0.00 499

nn								0.00 499

door-mid								98.05 460

lessismore_v0				97.79 397	98.69 422	95.44 418		94.75 484		95.71 452	99.87 69	88.69 419	99.32 360	95.89 399	94.93 410	98.62 386

LGP-MVS_train				98.49 322	99.33 290	97.05 344		99.55 100	97.46 286	99.24 252	99.83 105	92.58 352	99.72 272	98.09 262	97.51 334	98.68 356

test11								99.35 308

door								97.92 461

HQP5-MVS						96.83 366

BP-MVS														97.19 351

HQP4-MVS										98.66 355			99.64 305			98.64 377

HQP3-MVS								99.39 283							97.58 327

HQP2-MVS												92.47 356

NP-MVS					99.23 319	96.92 362					99.40 339

ACMMP++_ref															97.19 355

ACMMP++															97.43 345

Test By Simon												98.75 60

ITE_SJBPF				98.08 367	99.29 303	96.37 385		98.92 403	98.34 143	98.83 332	99.75 193	91.09 391	99.62 312	95.82 400	97.40 347	98.25 432

DeepMVS_CX				93.34 450	99.29 303	82.27 479		99.22 361	85.15 476	96.33 445	99.05 401	90.97 393	99.73 268	93.57 439	97.77 318	98.01 446

High-resolution multi-view benchmark