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 28	99.48 20	99.54 119	99.76 76	99.42 112	99.90 1	99.55 94	98.56 112	99.78 75	99.70 201	98.65 71	99.79 230	99.65 39	99.78 128	99.41 248

mmtdpeth		96.95 365	96.71 364	97.67 384	99.33 275	94.90 410	99.89 2	99.28 329	98.15 168	99.72 96	98.57 420	86.56 423	99.90 142	99.82 27	89.02 446	98.20 415

SPE-MVS-test		99.49 30	99.48 20	99.54 119	99.78 64	99.30 132	99.89 2	99.58 74	98.56 112	99.73 91	99.69 212	98.55 78	99.82 212	99.69 33	99.85 88	99.48 227

MVSFormer		99.17 103	99.12 92	99.29 191	99.51 213	98.94 191	99.88 4	99.46 221	97.55 261	99.80 68	99.65 232	97.39 122	99.28 350	99.03 122	99.85 88	99.65 159

test_djsdf		98.67 199	98.57 200	98.98 229	98.70 405	98.91 196	99.88 4	99.46 221	97.55 261	99.22 242	99.88 50	95.73 210	99.28 350	99.03 122	97.62 309	98.75 319

OurMVSNet-221017-0		97.88 281	97.77 272	98.19 343	98.71 404	96.53 364	99.88 4	99.00 372	97.79 232	98.78 324	99.94 6	91.68 360	99.35 340	97.21 327	96.99 345	98.69 336

EC-MVSNet		99.44 47	99.39 37	99.58 110	99.56 192	99.49 103	99.88 4	99.58 74	98.38 131	99.73 91	99.69 212	98.20 100	99.70 270	99.64 41	99.82 111	99.54 203

DVP-MVS++		99.59 13	99.50 17	99.88 13	99.51 213	99.88 9	99.87 8	99.51 142	98.99 63	99.88 38	99.81 120	99.27 5	99.96 39	98.85 153	99.80 119	99.81 74

FOURS1					99.91 1	99.93 1	99.87 8	99.56 86	99.10 42	99.81 63

K. test v3		97.10 362	96.79 362	98.01 356	98.72 402	96.33 371	99.87 8	97.05 450	97.59 255	96.16 428	99.80 137	88.71 400	99.04 393	96.69 359	96.55 351	98.65 360

FC-MVSNet-test		98.75 192	98.62 193	99.15 213	99.08 344	99.45 109	99.86 11	99.60 63	98.23 158	98.70 336	99.82 105	96.80 158	99.22 364	99.07 117	96.38 354	98.79 309

v7n		97.87 283	97.52 301	98.92 240	98.76 398	98.58 236	99.84 12	99.46 221	96.20 377	98.91 302	99.70 201	94.89 247	99.44 320	96.03 376	93.89 412	98.75 319

DTE-MVSNet		97.51 338	97.19 347	98.46 314	98.63 411	98.13 269	99.84 12	99.48 188	96.68 339	97.97 390	99.67 225	92.92 323	98.56 427	96.88 352	92.60 430	98.70 332

3Dnovator	97.25 9	99.24 92	99.05 106	99.81 55	99.12 333	99.66 65	99.84 12	99.74 10	99.09 49	98.92 301	99.90 31	95.94 197	99.98 18	98.95 133	99.92 37	99.79 87

FIs		98.78 187	98.63 188	99.23 203	99.18 317	99.54 92	99.83 15	99.59 69	98.28 143	98.79 323	99.81 120	96.75 161	99.37 333	99.08 116	96.38 354	98.78 311

MGCFI-Net		99.01 152	98.85 159	99.50 143	99.42 247	99.26 138	99.82 16	99.48 188	98.60 109	99.28 224	98.81 409	97.04 143	99.76 242	99.29 88	97.87 298	99.47 233

test_fmvs3		92.10 417	91.77 420	93.08 431	96.19 449	86.25 451	99.82 16	98.62 424	96.65 342	95.19 436	96.90 451	55.05 466	95.93 458	96.63 364	90.92 439	97.06 447

jajsoiax		98.43 213	98.28 220	98.88 253	98.60 415	98.43 255	99.82 16	99.53 118	98.19 163	98.63 348	99.80 137	93.22 318	99.44 320	99.22 96	97.50 321	98.77 315

OpenMVS	96.50 16	98.47 210	98.12 231	99.52 133	99.04 352	99.53 95	99.82 16	99.72 11	94.56 416	98.08 383	99.88 50	94.73 259	99.98 18	97.47 312	99.76 134	99.06 290

SDMVSNet		99.11 128	98.90 146	99.75 71	99.81 52	99.59 82	99.81 20	99.65 35	98.78 92	99.64 130	99.88 50	94.56 271	99.93 105	99.67 35	98.26 276	99.72 126

nrg030		98.64 203	98.42 210	99.28 195	99.05 350	99.69 57	99.81 20	99.46 221	98.04 201	99.01 284	99.82 105	96.69 163	99.38 330	99.34 79	94.59 399	98.78 311

HPM-MVS		99.42 52	99.28 66	99.83 51	99.90 4	99.72 51	99.81 20	99.54 103	97.59 255	99.68 105	99.63 244	98.91 37	99.94 87	98.58 194	99.91 44	99.84 51
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EPP-MVSNet		99.13 115	98.99 124	99.53 127	99.65 149	99.06 165	99.81 20	99.33 304	97.43 278	99.60 144	99.88 50	97.14 134	99.84 189	99.13 108	98.94 225	99.69 141

3Dnovator+	97.12 13	99.18 99	98.97 128	99.82 52	99.17 325	99.68 58	99.81 20	99.51 142	99.20 29	98.72 329	99.89 39	95.68 212	99.97 27	98.86 151	99.86 81	99.81 74

sasdasda		99.02 148	98.86 156	99.51 138	99.42 247	99.32 125	99.80 25	99.48 188	98.63 104	99.31 216	98.81 409	97.09 139	99.75 245	99.27 92	97.90 295	99.47 233

FA-MVS(test-final)		98.75 192	98.53 204	99.41 165	99.55 196	99.05 167	99.80 25	99.01 371	96.59 352	99.58 148	99.59 258	95.39 222	99.90 142	97.78 278	99.49 171	99.28 265

GeoE		98.85 178	98.62 193	99.53 127	99.61 173	99.08 162	99.80 25	99.51 142	97.10 310	99.31 216	99.78 161	95.23 233	99.77 238	98.21 234	99.03 219	99.75 104

canonicalmvs		99.02 148	98.86 156	99.51 138	99.42 247	99.32 125	99.80 25	99.48 188	98.63 104	99.31 216	98.81 409	97.09 139	99.75 245	99.27 92	97.90 295	99.47 233

v8		97.95 272	97.63 291	98.93 238	98.95 367	98.81 216	99.80 25	99.41 257	96.03 391	99.10 267	99.42 316	94.92 245	99.30 348	96.94 347	94.08 409	98.66 358

Vis-MVSNet (Re-imp)		98.87 166	98.72 174	99.31 183	99.71 111	98.88 198	99.80 25	99.44 241	97.91 214	99.36 207	99.78 161	95.49 219	99.43 324	97.91 263	99.11 208	99.62 174

Anonymous20240521		96.20 381	95.89 384	97.13 402	97.72 436	94.96 409	99.79 31	99.29 327	93.01 431	97.20 413	99.03 388	89.69 390	98.36 431	91.16 437	96.13 360	98.07 422

PS-MVSNAJss		98.92 160	98.92 141	98.90 246	98.78 391	98.53 240	99.78 32	99.54 103	98.07 188	99.00 288	99.76 174	99.01 18	99.37 333	99.13 108	97.23 338	98.81 308

PEN-MVS		97.76 304	97.44 317	98.72 279	98.77 396	98.54 239	99.78 32	99.51 142	97.06 314	98.29 373	99.64 238	92.63 336	98.89 418	98.09 247	93.16 422	98.72 325

anonymousdsp		98.44 212	98.28 220	98.94 236	98.50 421	98.96 181	99.77 34	99.50 164	97.07 312	98.87 310	99.77 170	94.76 257	99.28 350	98.66 180	97.60 310	98.57 386

SixPastTwentyTwo		97.50 339	97.33 335	98.03 353	98.65 409	96.23 376	99.77 34	98.68 420	97.14 303	97.90 393	99.93 10	90.45 379	99.18 372	97.00 341	96.43 353	98.67 349

QAPM		98.67 199	98.30 219	99.80 59	99.20 311	99.67 62	99.77 34	99.72 11	94.74 413	98.73 328	99.90 31	95.78 208	99.98 18	96.96 345	99.88 70	99.76 102

SSC-MVS		92.73 416	93.73 410	89.72 441	95.02 459	81.38 461	99.76 37	99.23 339	94.87 410	92.80 448	98.93 401	94.71 261	91.37 465	74.49 464	93.80 413	96.42 451

test_vis3_rt		87.04 424	85.81 427	90.73 438	93.99 462	81.96 459	99.76 37	90.23 473	92.81 434	81.35 461	91.56 461	40.06 470	99.07 390	94.27 410	88.23 448	91.15 461

dcpmvs_2		99.23 93	99.58 7	98.16 345	99.83 44	94.68 415	99.76 37	99.52 123	99.07 52	99.98 11	99.88 50	98.56 77	99.93 105	99.67 35	99.98 4	99.87 38

RRT-MVS		98.91 161	98.75 170	99.39 170	99.46 237	98.61 234	99.76 37	99.50 164	98.06 192	99.81 63	99.88 50	93.91 302	99.94 87	99.11 111	99.27 188	99.61 176

HPM-MVS_fast		99.51 26	99.40 35	99.85 38	99.91 1	99.79 36	99.76 37	99.56 86	97.72 240	99.76 85	99.75 179	99.13 12	99.92 117	99.07 117	99.92 37	99.85 44

lecture		99.60 12	99.50 17	99.89 9	99.89 8	99.90 2	99.75 42	99.59 69	99.06 55	99.88 38	99.85 76	98.41 90	99.96 39	99.28 89	99.84 96	99.83 61

MVSMamba_PlusPlus		99.46 39	99.41 34	99.64 95	99.68 126	99.50 102	99.75 42	99.50 164	98.27 145	99.87 44	99.92 17	98.09 105	99.94 87	99.65 39	99.95 21	99.47 233

v10		97.85 286	97.52 301	98.86 260	98.99 360	98.67 225	99.75 42	99.41 257	95.70 395	98.98 291	99.41 320	94.75 258	99.23 360	96.01 378	94.63 398	98.67 349

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 72	99.89 5	99.75 42	99.56 86	99.02 56	99.88 38	99.85 76	99.18 10	99.96 39	99.22 96	99.92 37	99.90 24
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
IS-MVSNet		99.05 144	98.87 154	99.57 114	99.73 101	99.32 125	99.75 42	99.20 345	98.02 206	99.56 152	99.86 69	96.54 171	99.67 278	98.09 247	99.13 204	99.73 117

test_vis1_n		97.92 276	97.44 317	99.34 175	99.53 204	98.08 272	99.74 47	99.49 176	99.15 32	100.00 1	99.94 6	79.51 454	99.98 18	99.88 24	99.76 134	99.97 4

test_fmvs1_n		98.41 216	98.14 228	99.21 204	99.82 48	97.71 298	99.74 47	99.49 176	99.32 25	99.99 2	99.95 3	85.32 432	99.97 27	99.82 27	99.84 96	99.96 7

balanced_conf03		99.46 39	99.39 37	99.67 84	99.55 196	99.58 87	99.74 47	99.51 142	98.42 128	99.87 44	99.84 91	98.05 108	99.91 129	99.58 45	99.94 29	99.52 210

tttt0517		98.42 214	98.14 228	99.28 195	99.66 141	98.38 258	99.74 47	96.85 452	97.68 246	99.79 70	99.74 184	91.39 368	99.89 157	98.83 159	99.56 164	99.57 197

WB-MVS		93.10 414	94.10 406	90.12 440	95.51 457	81.88 460	99.73 51	99.27 332	95.05 406	93.09 447	98.91 405	94.70 262	91.89 464	76.62 462	94.02 411	96.58 450

test_fmvs2		97.25 356	97.30 338	97.09 404	99.43 245	93.31 436	99.73 51	98.87 394	98.83 82	99.28 224	99.80 137	84.45 437	99.66 281	97.88 265	97.45 326	98.30 408

SD_0403		97.55 333	97.53 300	97.62 386	99.61 173	93.64 433	99.72 53	99.44 241	98.03 203	98.62 351	99.39 328	96.06 189	99.57 302	87.88 450	99.01 222	99.66 154

MonoMVSNet		98.38 220	98.47 208	98.12 350	98.59 417	96.19 378	99.72 53	98.79 405	97.89 216	99.44 179	99.52 286	96.13 186	98.90 417	98.64 182	97.54 316	99.28 265

baseline		99.15 109	99.02 117	99.53 127	99.66 141	99.14 154	99.72 53	99.48 188	98.35 136	99.42 185	99.84 91	96.07 188	99.79 230	99.51 54	99.14 202	99.67 150

RPSCF		98.22 231	98.62 193	96.99 405	99.82 48	91.58 445	99.72 53	99.44 241	96.61 347	99.66 116	99.89 39	95.92 198	99.82 212	97.46 313	99.10 213	99.57 197

CSCG		99.32 75	99.32 51	99.32 181	99.85 28	98.29 260	99.71 57	99.66 28	98.11 179	99.41 190	99.80 137	98.37 93	99.96 39	98.99 126	99.96 15	99.72 126

dmvs_re		98.08 248	98.16 225	97.85 371	99.55 196	94.67 416	99.70 58	98.92 382	98.15 168	99.06 278	99.35 340	93.67 310	99.25 357	97.77 281	97.25 337	99.64 166

WR-MVS_H		98.13 242	97.87 262	98.90 246	99.02 354	98.84 208	99.70 58	99.59 69	97.27 292	98.40 365	99.19 372	95.53 217	99.23 360	98.34 224	93.78 414	98.61 380

mvsmamba		99.06 140	98.96 132	99.36 172	99.47 235	98.64 229	99.70 58	99.05 366	97.61 254	99.65 125	99.83 96	96.54 171	99.92 117	99.19 99	99.62 159	99.51 219

LTVRE_ROB	97.16 12	98.02 260	97.90 257	98.40 324	99.23 304	96.80 353	99.70 58	99.60 63	97.12 306	98.18 380	99.70 201	91.73 359	99.72 257	98.39 217	97.45 326	98.68 341
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
test_f		91.90 418	91.26 422	93.84 427	95.52 456	85.92 452	99.69 62	98.53 428	95.31 400	93.87 442	96.37 454	55.33 465	98.27 432	95.70 384	90.98 438	97.32 446

XVS		99.53 24	99.42 29	99.87 19	99.85 28	99.83 20	99.69 62	99.68 20	98.98 66	99.37 201	99.74 184	98.81 47	99.94 87	98.79 164	99.86 81	99.84 51

X-MVStestdata		96.55 373	95.45 392	99.87 19	99.85 28	99.83 20	99.69 62	99.68 20	98.98 66	99.37 201	64.01 470	98.81 47	99.94 87	98.79 164	99.86 81	99.84 51

V42		98.06 250	97.79 267	98.86 260	98.98 363	98.84 208	99.69 62	99.34 296	96.53 354	99.30 220	99.37 334	94.67 264	99.32 345	97.57 302	94.66 397	98.42 400

mPP-MVS		99.44 47	99.30 59	99.86 30	99.88 13	99.79 36	99.69 62	99.48 188	98.12 177	99.50 166	99.75 179	98.78 51	99.97 27	98.57 197	99.89 66	99.83 61

CP-MVS		99.45 43	99.32 51	99.85 38	99.83 44	99.75 46	99.69 62	99.52 123	98.07 188	99.53 161	99.63 244	98.93 36	99.97 27	98.74 168	99.91 44	99.83 61

FE-MVS		98.48 209	98.17 224	99.40 166	99.54 203	98.96 181	99.68 68	98.81 401	95.54 397	99.62 137	99.70 201	93.82 305	99.93 105	97.35 321	99.46 172	99.32 262

PS-CasMVS		97.93 273	97.59 295	98.95 234	98.99 360	99.06 165	99.68 68	99.52 123	97.13 304	98.31 370	99.68 219	92.44 345	99.05 392	98.51 205	94.08 409	98.75 319

Vis-MVSNet		99.12 122	98.97 128	99.56 116	99.78 64	99.10 158	99.68 68	99.66 28	98.49 119	99.86 48	99.87 61	94.77 256	99.84 189	99.19 99	99.41 176	99.74 108
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
KinetiMVS		99.12 122	98.92 141	99.70 81	99.67 128	99.40 115	99.67 71	99.63 42	98.73 96	99.94 26	99.81 120	94.54 274	99.96 39	98.40 216	99.93 31	99.74 108

BP-MVS1		99.12 122	98.94 138	99.65 89	99.51 213	99.30 132	99.67 71	98.92 382	98.48 120	99.84 51	99.69 212	94.96 240	99.92 117	99.62 42	99.79 126	99.71 135

test_vis1_n_1920		98.63 204	98.40 212	99.31 183	99.86 22	97.94 285	99.67 71	99.62 47	99.43 15	99.99 2	99.91 24	87.29 418	100.00 1	99.92 22	99.92 37	99.98 2

EIA-MVS		99.18 99	99.09 99	99.45 155	99.49 227	99.18 146	99.67 71	99.53 118	97.66 249	99.40 195	99.44 312	98.10 104	99.81 217	98.94 134	99.62 159	99.35 257

MSP-MVS		99.42 52	99.27 70	99.88 13	99.89 8	99.80 33	99.67 71	99.50 164	98.70 100	99.77 79	99.49 296	98.21 99	99.95 74	98.46 211	99.77 131	99.88 33
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		99.10 132	98.97 128	99.48 147	99.49 227	99.14 154	99.67 71	99.34 296	97.31 289	99.58 148	99.76 174	97.65 118	99.82 212	98.87 146	99.07 216	99.46 238

CP-MVSNet		98.09 246	97.78 270	99.01 225	98.97 365	99.24 141	99.67 71	99.46 221	97.25 294	98.48 362	99.64 238	93.79 306	99.06 391	98.63 184	94.10 408	98.74 323

MTAPA		99.52 25	99.39 37	99.89 9	99.90 4	99.86 17	99.66 78	99.47 210	98.79 89	99.68 105	99.81 120	98.43 86	99.97 27	98.88 143	99.90 55	99.83 61

HFP-MVS		99.49 30	99.37 41	99.86 30	99.87 17	99.80 33	99.66 78	99.67 23	98.15 168	99.68 105	99.69 212	99.06 16	99.96 39	98.69 176	99.87 73	99.84 51

mvs_tets		98.40 219	98.23 222	98.91 244	98.67 408	98.51 246	99.66 78	99.53 118	98.19 163	98.65 345	99.81 120	92.75 327	99.44 320	99.31 83	97.48 325	98.77 315

EU-MVSNet		97.98 267	98.03 243	97.81 377	98.72 402	96.65 360	99.66 78	99.66 28	98.09 183	98.35 368	99.82 105	95.25 231	98.01 438	97.41 317	95.30 385	98.78 311

ACMMPR		99.49 30	99.36 43	99.86 30	99.87 17	99.79 36	99.66 78	99.67 23	98.15 168	99.67 111	99.69 212	98.95 30	99.96 39	98.69 176	99.87 73	99.84 51

MP-MVS		99.33 73	99.15 88	99.87 19	99.88 13	99.82 26	99.66 78	99.46 221	98.09 183	99.48 170	99.74 184	98.29 96	99.96 39	97.93 262	99.87 73	99.82 67
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
NormalMVS		99.27 84	99.19 84	99.52 133	99.89 8	98.83 211	99.65 84	99.52 123	99.10 42	99.84 51	99.76 174	95.80 206	99.99 4	99.30 86	99.84 96	99.74 108

SymmetryMVS		99.15 109	99.02 117	99.52 133	99.72 105	98.83 211	99.65 84	99.34 296	99.10 42	99.84 51	99.76 174	95.80 206	99.99 4	99.30 86	98.72 246	99.73 117

Elysia		98.88 163	98.65 185	99.58 110	99.58 183	99.34 121	99.65 84	99.52 123	98.26 148	99.83 59	99.87 61	93.37 313	99.90 142	97.81 275	99.91 44	99.49 224

StellarMVS		98.88 163	98.65 185	99.58 110	99.58 183	99.34 121	99.65 84	99.52 123	98.26 148	99.83 59	99.87 61	93.37 313	99.90 142	97.81 275	99.91 44	99.49 224

test_cas_vis1_n_1920		99.16 105	99.01 122	99.61 103	99.81 52	98.86 205	99.65 84	99.64 38	99.39 20	99.97 23	99.94 6	93.20 319	99.98 18	99.55 48	99.91 44	99.99 1

region2R		99.48 34	99.35 45	99.87 19	99.88 13	99.80 33	99.65 84	99.66 28	98.13 175	99.66 116	99.68 219	98.96 25	99.96 39	98.62 185	99.87 73	99.84 51

TranMVSNet+NR-MVSNet		97.93 273	97.66 286	98.76 276	98.78 391	98.62 232	99.65 84	99.49 176	97.76 236	98.49 361	99.60 256	94.23 287	98.97 409	98.00 258	92.90 424	98.70 332

GDP-MVS		99.08 135	98.89 150	99.64 95	99.53 204	99.34 121	99.64 91	99.48 188	98.32 140	99.77 79	99.66 230	95.14 236	99.93 105	98.97 132	99.50 170	99.64 166

ttmdpeth		97.80 300	97.63 291	98.29 334	98.77 396	97.38 309	99.64 91	99.36 284	98.78 92	96.30 426	99.58 262	92.34 348	99.39 328	98.36 222	95.58 378	98.10 420

mvsany_test3		93.77 411	93.45 414	94.74 424	95.78 452	88.01 450	99.64 91	98.25 433	98.28 143	94.31 440	97.97 442	68.89 458	98.51 429	97.50 308	90.37 440	97.71 437

ZNCC-MVS		99.47 37	99.33 49	99.87 19	99.87 17	99.81 31	99.64 91	99.67 23	98.08 187	99.55 158	99.64 238	98.91 37	99.96 39	98.72 171	99.90 55	99.82 67

tfpnnormal		97.84 290	97.47 309	98.98 229	99.20 311	99.22 143	99.64 91	99.61 56	96.32 368	98.27 374	99.70 201	93.35 315	99.44 320	95.69 385	95.40 383	98.27 410

casdiffmvs_mvg		99.15 109	99.02 117	99.55 118	99.66 141	99.09 159	99.64 91	99.56 86	98.26 148	99.45 174	99.87 61	96.03 191	99.81 217	99.54 49	99.15 201	99.73 117
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 43	99.31 57	99.85 38	99.76 76	99.82 26	99.63 97	99.52 123	98.38 131	99.76 85	99.82 105	98.53 79	99.95 74	98.61 188	99.81 114	99.77 95

RE-MVS-def			99.34 47		99.76 76	99.82 26	99.63 97	99.52 123	98.38 131	99.76 85	99.82 105	98.75 58		98.61 188	99.81 114	99.77 95

TSAR-MVS + MP.		99.58 14	99.50 17	99.81 55	99.91 1	99.66 65	99.63 97	99.39 267	98.91 76	99.78 75	99.85 76	99.36 2	99.94 87	98.84 156	99.88 70	99.82 67
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
Anonymous20231206		96.22 379	96.03 380	96.79 413	97.31 442	94.14 425	99.63 97	99.08 360	96.17 380	97.04 417	99.06 385	93.94 299	97.76 444	86.96 454	95.06 390	98.47 394

APD-MVS_3200maxsize		99.48 34	99.35 45	99.85 38	99.76 76	99.83 20	99.63 97	99.54 103	98.36 135	99.79 70	99.82 105	98.86 41	99.95 74	98.62 185	99.81 114	99.78 93

test0726					99.85 28	99.89 5	99.62 102	99.50 164	99.10 42	99.86 48	99.82 105	98.94 32

EPNet		98.86 169	98.71 176	99.30 188	97.20 444	98.18 265	99.62 102	98.91 387	99.28 27	98.63 348	99.81 120	95.96 194	99.99 4	99.24 95	99.72 142	99.73 117
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t		98.93 159	98.67 180	99.72 80	99.85 28	99.53 95	99.62 102	99.59 69	92.65 436	99.71 99	99.78 161	98.06 107	99.90 142	98.84 156	99.91 44	99.74 108

HY-MVS	97.30 7	98.85 178	98.64 187	99.47 152	99.42 247	99.08 162	99.62 102	99.36 284	97.39 283	99.28 224	99.68 219	96.44 177	99.92 117	98.37 220	98.22 279	99.40 250

ACMMP		99.45 43	99.32 51	99.82 52	99.89 8	99.67 62	99.62 102	99.69 18	98.12 177	99.63 133	99.84 91	98.73 63	99.96 39	98.55 203	99.83 107	99.81 74
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 78	99.19 84	99.64 95	99.82 48	99.23 142	99.62 102	99.55 94	98.94 72	99.63 133	99.95 3	95.82 204	99.94 87	99.37 73	99.97 8	99.73 117
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 14	99.56 10	99.64 95	99.78 64	99.15 153	99.61 108	99.45 232	99.01 58	99.89 35	99.82 105	99.01 18	99.92 117	99.56 47	99.95 21	99.85 44

reproduce_monomvs		97.89 280	97.87 262	97.96 362	99.51 213	95.45 395	99.60 109	99.25 335	99.17 30	98.85 315	99.49 296	89.29 394	99.64 290	99.35 74	96.31 357	98.78 311

test2506		96.81 369	96.65 365	97.29 399	99.74 94	92.21 443	99.60 109	85.06 474	99.13 35	99.77 79	99.93 10	87.82 416	99.85 180	99.38 72	99.38 177	99.80 83

SED-MVS		99.61 8	99.52 12	99.88 13	99.84 35	99.90 2	99.60 109	99.48 188	99.08 50	99.91 29	99.81 120	99.20 7	99.96 39	98.91 140	99.85 88	99.79 87

OPU-MVS				99.64 95	99.56 192	99.72 51	99.60 109				99.70 201	99.27 5	99.42 326	98.24 233	99.80 119	99.79 87

GST-MVS		99.40 60	99.24 75	99.85 38	99.86 22	99.79 36	99.60 109	99.67 23	97.97 209	99.63 133	99.68 219	98.52 80	99.95 74	98.38 218	99.86 81	99.81 74

EI-MVSNet-UG-set		99.58 14	99.57 8	99.64 95	99.78 64	99.14 154	99.60 109	99.45 232	99.01 58	99.90 32	99.83 96	98.98 24	99.93 105	99.59 43	99.95 21	99.86 40

ACMH	97.28 8	98.10 245	97.99 247	98.44 319	99.41 252	96.96 341	99.60 109	99.56 86	98.09 183	98.15 381	99.91 24	90.87 376	99.70 270	98.88 143	97.45 326	98.67 349
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
VortexMVS		98.67 199	98.66 183	98.68 285	99.62 164	97.96 280	99.59 116	99.41 257	98.13 175	99.31 216	99.70 201	95.48 220	99.27 353	99.40 69	97.32 335	98.79 309

guyue		99.16 105	99.04 108	99.52 133	99.69 121	98.92 195	99.59 116	98.81 401	98.73 96	99.90 32	99.87 61	95.34 225	99.88 162	99.66 38	99.81 114	99.74 108

ECVR-MVS		98.04 256	98.05 241	98.00 358	99.74 94	94.37 422	99.59 116	94.98 462	99.13 35	99.66 116	99.93 10	90.67 378	99.84 189	99.40 69	99.38 177	99.80 83

SR-MVS		99.43 50	99.29 63	99.86 30	99.75 86	99.83 20	99.59 116	99.62 47	98.21 161	99.73 91	99.79 154	98.68 67	99.96 39	98.44 213	99.77 131	99.79 87

thres100view900		97.76 304	97.45 312	98.69 284	99.72 105	97.86 289	99.59 116	98.74 411	97.93 212	99.26 235	98.62 417	91.75 357	99.83 203	93.22 422	98.18 284	98.37 406

thres600view7		97.86 285	97.51 303	98.92 240	99.72 105	97.95 283	99.59 116	98.74 411	97.94 211	99.27 230	98.62 417	91.75 357	99.86 174	93.73 417	98.19 283	98.96 301

LCM-MVSNet-Re		97.83 293	98.15 227	96.87 411	99.30 284	92.25 442	99.59 116	98.26 432	97.43 278	96.20 427	99.13 378	96.27 183	98.73 424	98.17 239	98.99 223	99.64 166

baseline1		98.31 225	97.95 252	99.38 171	99.50 225	98.74 220	99.59 116	98.93 379	98.41 129	99.14 259	99.60 256	94.59 269	99.79 230	98.48 207	93.29 419	99.61 176

SteuartSystems-ACMMP		99.54 21	99.42 29	99.87 19	99.82 48	99.81 31	99.59 116	99.51 142	98.62 106	99.79 70	99.83 96	99.28 4	99.97 27	98.48 207	99.90 55	99.84 51
Skip Steuart: Steuart Systems R&D Blog.
CPTT-MVS		99.11 128	98.90 146	99.74 74	99.80 58	99.46 108	99.59 116	99.49 176	97.03 318	99.63 133	99.69 212	97.27 130	99.96 39	97.82 273	99.84 96	99.81 74

IMVS_0403		98.86 169	98.89 150	98.78 274	99.55 196	96.93 342	99.58 126	99.44 241	98.05 194	99.68 105	99.80 137	96.81 157	99.80 224	98.15 242	98.92 228	99.60 179

test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 68	99.38 262	99.37 117	99.58 126	99.62 47	99.41 19	99.87 44	99.92 17	98.81 47	100.00 1	99.97 2	99.93 31	99.94 16

dmvs_testset		95.02 399	96.12 377	91.72 435	99.10 338	80.43 463	99.58 126	97.87 442	97.47 270	95.22 434	98.82 408	93.99 297	95.18 460	88.09 448	94.91 395	99.56 200

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 65	99.84 35	99.44 110	99.58 126	99.69 18	99.43 15	99.98 11	99.91 24	98.62 73	100.00 1	99.97 2	99.95 21	99.90 24

test1111		98.04 256	98.11 232	97.83 374	99.74 94	93.82 427	99.58 126	95.40 461	99.12 40	99.65 125	99.93 10	90.73 377	99.84 189	99.43 67	99.38 177	99.82 67

PGM-MVS		99.45 43	99.31 57	99.86 30	99.87 17	99.78 42	99.58 126	99.65 35	97.84 225	99.71 99	99.80 137	99.12 13	99.97 27	98.33 225	99.87 73	99.83 61

LPG-MVS_test		98.22 231	98.13 230	98.49 306	99.33 275	97.05 328	99.58 126	99.55 94	97.46 271	99.24 237	99.83 96	92.58 337	99.72 257	98.09 247	97.51 319	98.68 341

PHI-MVS		99.30 78	99.17 87	99.70 81	99.56 192	99.52 99	99.58 126	99.80 8	97.12 306	99.62 137	99.73 190	98.58 75	99.90 142	98.61 188	99.91 44	99.68 146

AstraMVS		99.09 133	99.03 111	99.25 198	99.66 141	98.13 269	99.57 134	98.24 434	98.82 83	99.91 29	99.88 50	95.81 205	99.90 142	99.72 30	99.67 152	99.74 108

SF-MVS		99.38 63	99.24 75	99.79 62	99.79 62	99.68 58	99.57 134	99.54 103	97.82 231	99.71 99	99.80 137	98.95 30	99.93 105	98.19 236	99.84 96	99.74 108

DVP-MVS		99.57 18	99.47 22	99.88 13	99.85 28	99.89 5	99.57 134	99.37 283	99.10 42	99.81 63	99.80 137	98.94 32	99.96 39	98.93 137	99.86 81	99.81 74
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 4	99.84 35	99.89 5	99.57 134	99.51 142					99.96 39	98.93 137	99.86 81	99.88 33

Effi-MVS+-dtu		98.78 187	98.89 150	98.47 313	99.33 275	96.91 347	99.57 134	99.30 323	98.47 121	99.41 190	98.99 394	96.78 159	99.74 247	98.73 170	99.38 177	98.74 323

v2v482		98.06 250	97.77 272	98.92 240	98.90 373	98.82 214	99.57 134	99.36 284	96.65 342	99.19 251	99.35 340	94.20 288	99.25 357	97.72 288	94.97 392	98.69 336

DSMNet-mixed		97.25 356	97.35 329	96.95 408	97.84 432	93.61 434	99.57 134	96.63 456	96.13 385	98.87 310	98.61 419	94.59 269	97.70 445	95.08 399	98.86 236	99.55 201

FE-MVSNET		94.07 410	93.36 415	96.22 419	94.05 461	94.71 414	99.56 141	98.36 430	93.15 430	93.76 443	97.55 444	86.47 424	96.49 455	87.48 451	89.83 444	97.48 444

reproduce_model		99.63 7	99.54 11	99.90 6	99.78 64	99.88 9	99.56 141	99.55 94	99.15 32	99.90 32	99.90 31	99.00 22	99.97 27	99.11 111	99.91 44	99.86 40

MVStest1		96.08 385	95.48 390	97.89 368	98.93 368	96.70 355	99.56 141	99.35 291	92.69 435	91.81 452	99.46 309	89.90 387	98.96 411	95.00 401	92.61 429	98.00 429

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 38	99.86 22	99.61 79	99.56 141	99.63 42	99.48 3	99.98 11	99.83 96	98.75 58	99.99 4	99.97 2	99.96 15	99.94 16

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 38	99.84 35	99.63 76	99.56 141	99.63 42	99.47 4	99.98 11	99.82 105	98.75 58	99.99 4	99.97 2	99.97 8	99.94 16

sd_testset		98.75 192	98.57 200	99.29 191	99.81 52	98.26 262	99.56 141	99.62 47	98.78 92	99.64 130	99.88 50	92.02 351	99.88 162	99.54 49	98.26 276	99.72 126

KD-MVS_self_test		95.00 400	94.34 405	96.96 407	97.07 447	95.39 398	99.56 141	99.44 241	95.11 403	97.13 415	97.32 449	91.86 355	97.27 449	90.35 440	81.23 458	98.23 414

ETV-MVS		99.26 87	99.21 80	99.40 166	99.46 237	99.30 132	99.56 141	99.52 123	98.52 116	99.44 179	99.27 362	98.41 90	99.86 174	99.10 114	99.59 162	99.04 291

SMA-MVS		99.44 47	99.30 59	99.85 38	99.73 101	99.83 20	99.56 141	99.47 210	97.45 274	99.78 75	99.82 105	99.18 10	99.91 129	98.79 164	99.89 66	99.81 74
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		98.87 166	98.72 174	99.31 183	99.86 22	98.48 251	99.56 141	99.61 56	97.85 222	99.36 207	99.85 76	95.95 195	99.85 180	96.66 361	99.83 107	99.59 190

casdiffmvs		99.13 115	98.98 127	99.56 116	99.65 149	99.16 149	99.56 141	99.50 164	98.33 139	99.41 190	99.86 69	95.92 198	99.83 203	99.45 66	99.16 198	99.70 138
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
XXY-MVS		98.38 220	98.09 236	99.24 201	99.26 296	99.32 125	99.56 141	99.55 94	97.45 274	98.71 330	99.83 96	93.23 316	99.63 296	98.88 143	96.32 356	98.76 317

ACMH+	97.24 10	97.92 276	97.78 270	98.32 331	99.46 237	96.68 359	99.56 141	99.54 103	98.41 129	97.79 399	99.87 61	90.18 385	99.66 281	98.05 255	97.18 341	98.62 371

ACMM	97.58 5	98.37 222	98.34 215	98.48 308	99.41 252	97.10 322	99.56 141	99.45 232	98.53 115	99.04 281	99.85 76	93.00 321	99.71 263	98.74 168	97.45 326	98.64 362
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LS3D		99.27 84	99.12 92	99.74 74	99.18 317	99.75 46	99.56 141	99.57 81	98.45 124	99.49 169	99.85 76	97.77 115	99.94 87	98.33 225	99.84 96	99.52 210

testing3-2		97.84 290	97.70 282	98.24 340	99.53 204	95.37 399	99.55 156	98.67 421	98.46 122	99.27 230	99.34 344	86.58 422	99.83 203	99.32 82	98.63 249	99.52 210

test_fmvsmconf0.01_n		99.22 95	99.03 111	99.79 62	98.42 424	99.48 105	99.55 156	99.51 142	99.39 20	99.78 75	99.93 10	94.80 251	99.95 74	99.93 21	99.95 21	99.94 16

test_fmvs1		98.88 163	98.79 167	99.16 209	99.69 121	97.61 302	99.55 156	99.49 176	99.32 25	99.98 11	99.91 24	91.41 367	99.96 39	99.82 27	99.92 37	99.90 24

v144192		97.92 276	97.60 294	98.87 257	98.83 385	98.65 227	99.55 156	99.34 296	96.20 377	99.32 215	99.40 324	94.36 281	99.26 356	96.37 372	95.03 391	98.70 332

API-MVS		99.04 145	99.03 111	99.06 219	99.40 257	99.31 129	99.55 156	99.56 86	98.54 114	99.33 214	99.39 328	98.76 55	99.78 236	96.98 343	99.78 128	98.07 422

fmvsm_l_conf0.5_n_3		99.61 8	99.51 16	99.92 1	99.84 35	99.82 26	99.54 161	99.66 28	99.46 7	99.98 11	99.89 39	97.27 130	99.99 4	99.97 2	99.95 21	99.95 11

fmvsm_s_conf0.1_n_a		99.26 87	99.06 104	99.85 38	99.52 210	99.62 77	99.54 161	99.62 47	98.69 101	99.99 2	99.96 1	94.47 278	99.94 87	99.88 24	99.92 37	99.98 2

APD_test1		95.87 387	96.49 369	94.00 426	99.53 204	84.01 455	99.54 161	99.32 314	95.91 393	97.99 388	99.85 76	85.49 430	99.88 162	91.96 433	98.84 238	98.12 419

thisisatest0530		98.35 223	98.03 243	99.31 183	99.63 157	98.56 237	99.54 161	96.75 454	97.53 265	99.73 91	99.65 232	91.25 372	99.89 157	98.62 185	99.56 164	99.48 227

MTMP							99.54 161	98.88 392

v1144		97.98 267	97.69 283	98.85 263	98.87 378	98.66 226	99.54 161	99.35 291	96.27 372	99.23 241	99.35 340	94.67 264	99.23 360	96.73 356	95.16 388	98.68 341

v148		97.79 302	97.55 296	98.50 305	98.74 399	97.72 295	99.54 161	99.33 304	96.26 373	98.90 304	99.51 290	94.68 263	99.14 377	97.83 272	93.15 423	98.63 369

CostFormer		97.72 314	97.73 279	97.71 382	99.15 331	94.02 426	99.54 161	99.02 370	94.67 414	99.04 281	99.35 340	92.35 347	99.77 238	98.50 206	97.94 294	99.34 260

MVSTER		98.49 208	98.32 217	99.00 227	99.35 269	99.02 169	99.54 161	99.38 275	97.41 281	99.20 248	99.73 190	93.86 304	99.36 337	98.87 146	97.56 314	98.62 371

fmvsm_s_conf0.1_n		99.29 80	99.10 94	99.86 30	99.70 116	99.65 69	99.53 170	99.62 47	98.74 95	99.99 2	99.95 3	94.53 276	99.94 87	99.89 23	99.96 15	99.97 4

reproduce-ours		99.61 8	99.52 12	99.90 6	99.76 76	99.88 9	99.52 171	99.54 103	99.13 35	99.89 35	99.89 39	98.96 25	99.96 39	99.04 120	99.90 55	99.85 44

our_new_method		99.61 8	99.52 12	99.90 6	99.76 76	99.88 9	99.52 171	99.54 103	99.13 35	99.89 35	99.89 39	98.96 25	99.96 39	99.04 120	99.90 55	99.85 44

fmvsm_s_conf0.5_n_a		99.56 19	99.47 22	99.85 38	99.83 44	99.64 75	99.52 171	99.65 35	99.10 42	99.98 11	99.92 17	97.35 126	99.96 39	99.94 19	99.92 37	99.95 11

MM		99.40 60	99.28 66	99.74 74	99.67 128	99.31 129	99.52 171	98.87 394	99.55 1	99.74 89	99.80 137	96.47 174	99.98 18	99.97 2	99.97 8	99.94 16

patch_mono-2		99.26 87	99.62 5	98.16 345	99.81 52	94.59 418	99.52 171	99.64 38	99.33 24	99.73 91	99.90 31	99.00 22	99.99 4	99.69 33	99.98 4	99.89 27

Fast-Effi-MVS+-dtu		98.77 191	98.83 163	98.60 290	99.41 252	96.99 337	99.52 171	99.49 176	98.11 179	99.24 237	99.34 344	96.96 148	99.79 230	97.95 261	99.45 173	99.02 294

Fast-Effi-MVS+		98.70 196	98.43 209	99.51 138	99.51 213	99.28 135	99.52 171	99.47 210	96.11 386	99.01 284	99.34 344	96.20 185	99.84 189	97.88 265	98.82 240	99.39 251

v1921920		97.80 300	97.45 312	98.84 264	98.80 387	98.53 240	99.52 171	99.34 296	96.15 383	99.24 237	99.47 305	93.98 298	99.29 349	95.40 393	95.13 389	98.69 336

MIMVSNet1		95.51 393	95.04 398	96.92 410	97.38 439	95.60 388	99.52 171	99.50 164	93.65 424	96.97 419	99.17 373	85.28 433	96.56 454	88.36 447	95.55 380	98.60 383

viewmacassd2359aftdt		99.08 135	98.94 138	99.50 143	99.66 141	98.96 181	99.51 180	99.54 103	98.27 145	99.42 185	99.89 39	95.88 202	99.80 224	99.20 98	99.11 208	99.76 102

SSM_0407		99.13 115	99.03 111	99.43 163	99.62 164	98.88 198	99.51 180	99.50 164	98.14 173	99.37 201	99.85 76	96.85 151	99.83 203	99.19 99	99.25 191	99.60 179

fmvsm_s_conf0.5_n_8		99.54 21	99.42 29	99.89 9	99.83 44	99.74 49	99.51 180	99.62 47	99.46 7	99.99 2	99.90 31	96.60 167	99.98 18	99.95 14	99.95 21	99.96 7

fmvsm_s_conf0.5_n		99.51 26	99.40 35	99.85 38	99.84 35	99.65 69	99.51 180	99.67 23	99.13 35	99.98 11	99.92 17	96.60 167	99.96 39	99.95 14	99.96 15	99.95 11

UniMVSNet_ETH3D		97.32 353	96.81 361	98.87 257	99.40 257	97.46 306	99.51 180	99.53 118	95.86 394	98.54 358	99.77 170	82.44 446	99.66 281	98.68 178	97.52 318	99.50 223

alignmvs		98.81 182	98.56 202	99.58 110	99.43 245	99.42 112	99.51 180	98.96 377	98.61 107	99.35 210	98.92 404	94.78 253	99.77 238	99.35 74	98.11 289	99.54 203

v1192		97.81 298	97.44 317	98.91 244	98.88 375	98.68 224	99.51 180	99.34 296	96.18 379	99.20 248	99.34 344	94.03 296	99.36 337	95.32 395	95.18 387	98.69 336

test20.03		96.12 383	95.96 382	96.63 414	97.44 438	95.45 395	99.51 180	99.38 275	96.55 353	96.16 428	99.25 365	93.76 308	96.17 456	87.35 453	94.22 405	98.27 410

mvs_anonymous		99.03 147	98.99 124	99.16 209	99.38 262	98.52 244	99.51 180	99.38 275	97.79 232	99.38 199	99.81 120	97.30 128	99.45 315	99.35 74	98.99 223	99.51 219

TAMVS		99.12 122	99.08 100	99.24 201	99.46 237	98.55 238	99.51 180	99.46 221	98.09 183	99.45 174	99.82 105	98.34 94	99.51 309	98.70 173	98.93 226	99.67 150

viewdifsd2359ckpt13		99.06 140	98.93 140	99.45 155	99.63 157	98.96 181	99.50 190	99.51 142	97.83 226	99.28 224	99.80 137	96.68 165	99.71 263	99.05 119	99.12 206	99.68 146

viewdifsd2359ckpt11		98.78 187	98.74 172	98.89 250	99.67 128	97.04 331	99.50 190	99.58 74	98.26 148	99.56 152	99.90 31	94.36 281	99.87 169	99.49 59	98.32 272	99.77 95

viewmsd2359difaftdt		98.78 187	98.74 172	98.90 246	99.67 128	97.04 331	99.50 190	99.58 74	98.26 148	99.56 152	99.90 31	94.36 281	99.87 169	99.49 59	98.32 272	99.77 95

IMVS_0407		98.86 169	98.91 144	98.72 279	99.55 196	96.93 342	99.50 190	99.44 241	98.05 194	99.66 116	99.80 137	97.13 135	99.65 286	98.15 242	98.92 228	99.60 179

viewmanbaseed2359cas		99.18 99	99.07 103	99.50 143	99.62 164	99.01 171	99.50 190	99.52 123	98.25 153	99.68 105	99.82 105	96.93 149	99.80 224	99.15 107	99.11 208	99.70 138

fmvsm_s_conf0.5_n_6		99.54 21	99.44 28	99.85 38	99.51 213	99.67 62	99.50 190	99.64 38	99.43 15	99.98 11	99.78 161	97.26 132	99.95 74	99.95 14	99.93 31	99.92 22

test_fmvsmconf0.1_n		99.55 20	99.45 27	99.86 30	99.44 244	99.65 69	99.50 190	99.61 56	99.45 11	99.87 44	99.92 17	97.31 127	99.97 27	99.95 14	99.99 1	99.97 4

test_yl		98.86 169	98.63 188	99.54 119	99.49 227	99.18 146	99.50 190	99.07 363	98.22 159	99.61 141	99.51 290	95.37 223	99.84 189	98.60 191	98.33 268	99.59 190

DCV-MVSNet		98.86 169	98.63 188	99.54 119	99.49 227	99.18 146	99.50 190	99.07 363	98.22 159	99.61 141	99.51 290	95.37 223	99.84 189	98.60 191	98.33 268	99.59 190

tfpn200view9		97.72 314	97.38 325	98.72 279	99.69 121	97.96 280	99.50 190	98.73 417	97.83 226	99.17 256	98.45 424	91.67 361	99.83 203	93.22 422	98.18 284	98.37 406

UA-Net		99.42 52	99.29 63	99.80 59	99.62 164	99.55 90	99.50 190	99.70 15	98.79 89	99.77 79	99.96 1	97.45 121	99.96 39	98.92 139	99.90 55	99.89 27

pm-mvs1		97.68 322	97.28 341	98.88 253	99.06 347	98.62 232	99.50 190	99.45 232	96.32 368	97.87 395	99.79 154	92.47 341	99.35 340	97.54 305	93.54 416	98.67 349

EI-MVSNet		98.67 199	98.67 180	98.68 285	99.35 269	97.97 278	99.50 190	99.38 275	96.93 327	99.20 248	99.83 96	97.87 111	99.36 337	98.38 218	97.56 314	98.71 327

CVMVSNet		98.57 206	98.67 180	98.30 333	99.35 269	95.59 389	99.50 190	99.55 94	98.60 109	99.39 197	99.83 96	94.48 277	99.45 315	98.75 167	98.56 256	99.85 44

VPA-MVSNet		98.29 228	97.95 252	99.30 188	99.16 327	99.54 92	99.50 190	99.58 74	98.27 145	99.35 210	99.37 334	92.53 339	99.65 286	99.35 74	94.46 400	98.72 325

thres400		97.77 303	97.38 325	98.92 240	99.69 121	97.96 280	99.50 190	98.73 417	97.83 226	99.17 256	98.45 424	91.67 361	99.83 203	93.22 422	98.18 284	98.96 301

APD-MVS		99.27 84	99.08 100	99.84 50	99.75 86	99.79 36	99.50 190	99.50 164	97.16 302	99.77 79	99.82 105	98.78 51	99.94 87	97.56 303	99.86 81	99.80 83
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SSM_0404		99.16 105	99.06 104	99.44 160	99.65 149	98.96 181	99.49 207	99.50 164	98.14 173	99.62 137	99.85 76	96.85 151	99.85 180	99.19 99	99.26 190	99.52 210

fmvsm_s_conf0.5_n_4		99.36 68	99.24 75	99.73 77	99.78 64	99.53 95	99.49 207	99.60 63	99.42 18	99.99 2	99.86 69	95.15 235	99.95 74	99.95 14	99.89 66	99.73 117

test_vis1_rt		95.81 389	95.65 388	96.32 418	99.67 128	91.35 446	99.49 207	96.74 455	98.25 153	95.24 433	98.10 439	74.96 455	99.90 142	99.53 51	98.85 237	97.70 439

TransMVSNet (Re)		97.15 360	96.58 366	98.86 260	99.12 333	98.85 206	99.49 207	98.91 387	95.48 398	97.16 414	99.80 137	93.38 312	99.11 386	94.16 413	91.73 433	98.62 371

UniMVSNet (Re)		98.29 228	98.00 246	99.13 214	99.00 357	99.36 120	99.49 207	99.51 142	97.95 210	98.97 293	99.13 378	96.30 182	99.38 330	98.36 222	93.34 418	98.66 358

EPMVS		97.82 296	97.65 287	98.35 328	98.88 375	95.98 381	99.49 207	94.71 464	97.57 258	99.26 235	99.48 302	92.46 344	99.71 263	97.87 267	99.08 215	99.35 257

viewcassd2359sk11		99.18 99	99.08 100	99.49 146	99.65 149	98.95 187	99.48 213	99.51 142	98.10 182	99.72 96	99.87 61	97.13 135	99.84 189	99.13 108	99.14 202	99.69 141

fmvsm_s_conf0.5_n_9		99.41 56	99.28 66	99.81 55	99.84 35	99.52 99	99.48 213	99.62 47	99.46 7	99.99 2	99.92 17	95.24 232	99.96 39	99.97 2	99.97 8	99.96 7

SSC-MVS3.2		97.34 351	97.15 348	97.93 364	99.02 354	95.76 386	99.48 213	99.58 74	97.62 253	99.09 270	99.53 282	87.95 412	99.27 353	96.42 368	95.66 376	98.75 319

fmvsm_s_conf0.5_n_3		99.37 64	99.20 82	99.87 19	99.75 86	99.70 55	99.48 213	99.66 28	99.45 11	99.99 2	99.93 10	94.64 268	99.97 27	99.94 19	99.97 8	99.95 11

test_fmvsmconf_n		99.70 3	99.64 4	99.87 19	99.80 58	99.66 65	99.48 213	99.64 38	99.45 11	99.92 28	99.92 17	98.62 73	99.99 4	99.96 12	99.99 1	99.96 7

Anonymous20231211		97.88 281	97.54 299	98.90 246	99.71 111	98.53 240	99.48 213	99.57 81	94.16 419	98.81 319	99.68 219	93.23 316	99.42 326	98.84 156	94.42 402	98.76 317

v1240		97.69 319	97.32 336	98.79 272	98.85 382	98.43 255	99.48 213	99.36 284	96.11 386	99.27 230	99.36 337	93.76 308	99.24 359	94.46 407	95.23 386	98.70 332

VPNet		97.84 290	97.44 317	99.01 225	99.21 309	98.94 191	99.48 213	99.57 81	98.38 131	99.28 224	99.73 190	88.89 397	99.39 328	99.19 99	93.27 420	98.71 327

UniMVSNet_NR-MVSNet		98.22 231	97.97 249	98.96 232	98.92 370	98.98 174	99.48 213	99.53 118	97.76 236	98.71 330	99.46 309	96.43 178	99.22 364	98.57 197	92.87 426	98.69 336

TDRefinement		95.42 395	94.57 403	97.97 360	89.83 467	96.11 380	99.48 213	98.75 408	96.74 335	96.68 422	99.88 50	88.65 403	99.71 263	98.37 220	82.74 456	98.09 421

fmvsm_l_conf0.5_n_9		99.58 14	99.47 22	99.92 1	99.85 28	99.82 26	99.47 223	99.63 42	99.45 11	99.98 11	99.89 39	97.02 144	99.99 4	99.98 1	99.96 15	99.95 11

ACMMP_NAP		99.47 37	99.34 47	99.88 13	99.87 17	99.86 17	99.47 223	99.48 188	98.05 194	99.76 85	99.86 69	98.82 46	99.93 105	98.82 163	99.91 44	99.84 51

NR-MVSNet		97.97 270	97.61 293	99.02 224	98.87 378	99.26 138	99.47 223	99.42 254	97.63 251	97.08 416	99.50 293	95.07 238	99.13 380	97.86 268	93.59 415	98.68 341

PVSNet_Blended_VisFu		99.36 68	99.28 66	99.61 103	99.86 22	99.07 164	99.47 223	99.93 2	97.66 249	99.71 99	99.86 69	97.73 116	99.96 39	99.47 64	99.82 111	99.79 87

LuminaMVS		99.23 93	99.10 94	99.61 103	99.35 269	99.31 129	99.46 227	99.13 354	98.61 107	99.86 48	99.89 39	96.41 179	99.91 129	99.67 35	99.51 168	99.63 171

fmvsm_s_conf0.1_n_2		99.37 64	99.22 79	99.81 55	99.77 72	99.75 46	99.46 227	99.60 63	99.47 4	99.98 11	99.94 6	94.98 239	99.95 74	99.97 2	99.79 126	99.73 117

SD-MVS		99.41 56	99.52 12	99.05 221	99.74 94	99.68 58	99.46 227	99.52 123	99.11 41	99.88 38	99.91 24	99.43 1	97.70 445	98.72 171	99.93 31	99.77 95
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
testing3		97.28 354	96.76 363	98.82 266	99.37 265	98.07 273	99.45 230	99.36 284	97.56 260	97.89 394	98.95 399	83.70 440	98.82 419	96.03 376	98.56 256	99.58 194

tt0805		97.97 270	97.77 272	98.57 295	99.59 181	96.61 362	99.45 230	99.08 360	98.21 161	98.88 307	99.80 137	88.66 402	99.70 270	98.58 194	97.72 304	99.39 251

tpm2		97.44 346	97.34 332	97.74 381	99.15 331	94.36 423	99.45 230	98.94 378	93.45 428	98.90 304	99.44 312	91.35 369	99.59 300	97.31 322	98.07 290	99.29 264

FMVSNet2		97.72 314	97.36 327	98.80 271	99.51 213	98.84 208	99.45 230	99.42 254	96.49 356	98.86 314	99.29 357	90.26 381	98.98 402	96.44 367	96.56 350	98.58 385

CDS-MVSNet		99.09 133	99.03 111	99.25 198	99.42 247	98.73 221	99.45 230	99.46 221	98.11 179	99.46 173	99.77 170	98.01 109	99.37 333	98.70 173	98.92 228	99.66 154
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MAR-MVS		98.86 169	98.63 188	99.54 119	99.37 265	99.66 65	99.45 230	99.54 103	96.61 347	99.01 284	99.40 324	97.09 139	99.86 174	97.68 293	99.53 167	99.10 279
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
fmvsm_s_conf0.5_n_2		99.32 75	99.13 90	99.89 9	99.80 58	99.77 43	99.44 236	99.58 74	99.47 4	99.99 2	99.93 10	94.04 295	99.96 39	99.96 12	99.93 31	99.93 21

UGNet		98.87 166	98.69 178	99.40 166	99.22 308	98.72 222	99.44 236	99.68 20	99.24 28	99.18 255	99.42 316	92.74 329	99.96 39	99.34 79	99.94 29	99.53 209
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		98.86 169	98.63 188	99.54 119	99.64 153	99.19 144	99.44 236	99.54 103	97.77 235	99.30 220	99.81 120	94.20 288	99.93 105	99.17 105	98.82 240	99.49 224

test_0402		96.64 372	96.24 374	97.85 371	98.85 382	96.43 368	99.44 236	99.26 333	93.52 425	96.98 418	99.52 286	88.52 406	99.20 371	92.58 432	97.50 321	97.93 434

ACMP	97.20 11	98.06 250	97.94 254	98.45 316	99.37 265	97.01 335	99.44 236	99.49 176	97.54 264	98.45 363	99.79 154	91.95 353	99.72 257	97.91 263	97.49 324	98.62 371
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
GG-mvs-BLEND				98.45 316	98.55 419	98.16 266	99.43 241	93.68 466		97.23 410	98.46 423	89.30 393	99.22 364	95.43 392	98.22 279	97.98 431

HPM-MVS++		99.39 62	99.23 78	99.87 19	99.75 86	99.84 19	99.43 241	99.51 142	98.68 103	99.27 230	99.53 282	98.64 72	99.96 39	98.44 213	99.80 119	99.79 87

tpm cat1		97.39 348	97.36 327	97.50 393	99.17 325	93.73 429	99.43 241	99.31 318	91.27 440	98.71 330	99.08 382	94.31 286	99.77 238	96.41 370	98.50 260	99.00 295

tpm		97.67 325	97.55 296	98.03 353	99.02 354	95.01 407	99.43 241	98.54 427	96.44 362	99.12 262	99.34 344	91.83 356	99.60 299	97.75 284	96.46 352	99.48 227

GBi-Net		97.68 322	97.48 306	98.29 334	99.51 213	97.26 315	99.43 241	99.48 188	96.49 356	99.07 273	99.32 352	90.26 381	98.98 402	97.10 335	96.65 347	98.62 371

test1		97.68 322	97.48 306	98.29 334	99.51 213	97.26 315	99.43 241	99.48 188	96.49 356	99.07 273	99.32 352	90.26 381	98.98 402	97.10 335	96.65 347	98.62 371

FMVSNet1		96.84 368	96.36 372	98.29 334	99.32 282	97.26 315	99.43 241	99.48 188	95.11 403	98.55 357	99.32 352	83.95 439	98.98 402	95.81 381	96.26 358	98.62 371

fmvsm_s_conf0.5_n_7		99.34 71	99.29 63	99.48 147	99.70 116	98.63 230	99.42 248	99.63 42	99.46 7	99.98 11	99.88 50	95.59 215	99.96 39	99.97 2	99.98 4	99.85 44

fmvsm_s_conf0.5_n_5		99.37 64	99.21 80	99.86 30	99.80 58	99.68 58	99.42 248	99.61 56	99.37 22	99.97 23	99.86 69	94.96 240	99.99 4	99.97 2	99.93 31	99.92 22

mamv4		99.33 73	99.42 29	99.07 217	99.67 128	97.73 293	99.42 248	99.60 63	98.15 168	99.94 26	99.91 24	98.42 88	99.94 87	99.72 30	99.96 15	99.54 203

testgi		97.65 327	97.50 304	98.13 349	99.36 268	96.45 367	99.42 248	99.48 188	97.76 236	97.87 395	99.45 311	91.09 373	98.81 420	94.53 406	98.52 259	99.13 278

F-COLMAP		99.19 96	99.04 108	99.64 95	99.78 64	99.27 137	99.42 248	99.54 103	97.29 291	99.41 190	99.59 258	98.42 88	99.93 105	98.19 236	99.69 147	99.73 117

Anonymous202405211		98.30 227	97.98 248	99.26 197	99.57 188	98.16 266	99.41 253	98.55 426	96.03 391	99.19 251	99.74 184	91.87 354	99.92 117	99.16 106	98.29 275	99.70 138

MSLP-MVS++		99.46 39	99.47 22	99.44 160	99.60 179	99.16 149	99.41 253	99.71 13	98.98 66	99.45 174	99.78 161	99.19 9	99.54 307	99.28 89	99.84 96	99.63 171

VNet		99.11 128	98.90 146	99.73 77	99.52 210	99.56 88	99.41 253	99.39 267	99.01 58	99.74 89	99.78 161	95.56 216	99.92 117	99.52 53	98.18 284	99.72 126

baseline2		97.87 283	97.55 296	98.82 266	99.18 317	98.02 275	99.41 253	96.58 458	96.97 321	96.51 423	99.17 373	93.43 311	99.57 302	97.71 289	99.03 219	98.86 305

DU-MVS		98.08 248	97.79 267	98.96 232	98.87 378	98.98 174	99.41 253	99.45 232	97.87 218	98.71 330	99.50 293	94.82 249	99.22 364	98.57 197	92.87 426	98.68 341

Baseline_NR-MVSNet		97.76 304	97.45 312	98.68 285	99.09 341	98.29 260	99.41 253	98.85 396	95.65 396	98.63 348	99.67 225	94.82 249	99.10 388	98.07 254	92.89 425	98.64 362

XVG-ACMP-BASELINE		97.83 293	97.71 281	98.20 342	99.11 335	96.33 371	99.41 253	99.52 123	98.06 192	99.05 280	99.50 293	89.64 391	99.73 253	97.73 286	97.38 333	98.53 388

DP-MVS		99.16 105	98.95 136	99.78 65	99.77 72	99.53 95	99.41 253	99.50 164	97.03 318	99.04 281	99.88 50	97.39 122	99.92 117	98.66 180	99.90 55	99.87 38

9.14			99.10 94		99.72 105		99.40 261	99.51 142	97.53 265	99.64 130	99.78 161	98.84 44	99.91 129	97.63 294	99.82 111

D2MVS		98.41 216	98.50 206	98.15 348	99.26 296	96.62 361	99.40 261	99.61 56	97.71 241	98.98 291	99.36 337	96.04 190	99.67 278	98.70 173	97.41 331	98.15 418

Anonymous20240529		98.09 246	97.68 284	99.34 175	99.66 141	98.44 254	99.40 261	99.43 252	93.67 423	99.22 242	99.89 39	90.23 384	99.93 105	99.26 94	98.33 268	99.66 154

FMVSNet3		98.03 258	97.76 276	98.84 264	99.39 260	98.98 174	99.40 261	99.38 275	96.67 340	99.07 273	99.28 359	92.93 322	98.98 402	97.10 335	96.65 347	98.56 387

LFMVS		97.90 279	97.35 329	99.54 119	99.52 210	99.01 171	99.39 265	98.24 434	97.10 310	99.65 125	99.79 154	84.79 435	99.91 129	99.28 89	98.38 265	99.69 141

HQP_MVS		98.27 230	98.22 223	98.44 319	99.29 288	96.97 339	99.39 265	99.47 210	98.97 69	99.11 264	99.61 253	92.71 332	99.69 275	97.78 278	97.63 307	98.67 349

plane_prior2							99.39 265		98.97 69

CHOSEN 1792x2688		99.19 96	99.10 94	99.45 155	99.89 8	98.52 244	99.39 265	99.94 1	98.73 96	99.11 264	99.89 39	95.50 218	99.94 87	99.50 55	99.97 8	99.89 27

PAPM_NR		99.04 145	98.84 161	99.66 85	99.74 94	99.44 110	99.39 265	99.38 275	97.70 244	99.28 224	99.28 359	98.34 94	99.85 180	96.96 345	99.45 173	99.69 141

gg-mvs-nofinetune		96.17 382	95.32 394	98.73 277	98.79 388	98.14 268	99.38 270	94.09 465	91.07 443	98.07 386	91.04 463	89.62 392	99.35 340	96.75 355	99.09 214	98.68 341

VDDNet		97.55 333	97.02 355	99.16 209	99.49 227	98.12 271	99.38 270	99.30 323	95.35 399	99.68 105	99.90 31	82.62 445	99.93 105	99.31 83	98.13 288	99.42 245

MVS_0304		99.15 109	98.96 132	99.73 77	98.92 370	99.37 117	99.37 272	96.92 451	99.51 2	99.66 116	99.78 161	96.69 163	99.97 27	99.84 26	99.97 8	99.84 51

pmmvs6		96.53 374	96.09 379	97.82 376	98.69 406	95.47 394	99.37 272	99.47 210	93.46 427	97.41 404	99.78 161	87.06 420	99.33 343	96.92 350	92.70 428	98.65 360

PM-MVS		92.96 415	92.23 419	95.14 423	95.61 453	89.98 449	99.37 272	98.21 436	94.80 412	95.04 438	97.69 443	65.06 459	97.90 441	94.30 408	89.98 443	97.54 443

WTY-MVS		99.06 140	98.88 153	99.61 103	99.62 164	99.16 149	99.37 272	99.56 86	98.04 201	99.53 161	99.62 249	96.84 155	99.94 87	98.85 153	98.49 261	99.72 126

IterMVS-LS		98.46 211	98.42 210	98.58 294	99.59 181	98.00 276	99.37 272	99.43 252	96.94 326	99.07 273	99.59 258	97.87 111	99.03 395	98.32 227	95.62 377	98.71 327
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
h-mvs33		97.70 318	97.28 341	98.97 231	99.70 116	97.27 313	99.36 277	99.45 232	98.94 72	99.66 116	99.64 238	94.93 243	99.99 4	99.48 62	84.36 453	99.65 159

DPE-MVS		99.46 39	99.32 51	99.91 4	99.78 64	99.88 9	99.36 277	99.51 142	98.73 96	99.88 38	99.84 91	98.72 64	99.96 39	98.16 240	99.87 73	99.88 33
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UnsupCasMVSNet_eth		96.44 376	96.12 377	97.40 396	98.65 409	95.65 387	99.36 277	99.51 142	97.13 304	96.04 430	98.99 394	88.40 407	98.17 434	96.71 357	90.27 441	98.40 403

sss		99.17 103	99.05 106	99.53 127	99.62 164	98.97 177	99.36 277	99.62 47	97.83 226	99.67 111	99.65 232	97.37 125	99.95 74	99.19 99	99.19 197	99.68 146

DeepC-MVS_fast	98.69 1	99.49 30	99.39 37	99.77 68	99.63 157	99.59 82	99.36 277	99.46 221	99.07 52	99.79 70	99.82 105	98.85 42	99.92 117	98.68 178	99.87 73	99.82 67
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 91	99.14 89	99.59 107	99.41 252	99.16 149	99.35 282	99.57 81	98.82 83	99.51 165	99.61 253	96.46 175	99.95 74	99.59 43	99.98 4	99.65 159

pmmvs-eth3d		95.34 397	94.73 400	97.15 400	95.53 455	95.94 382	99.35 282	99.10 357	95.13 401	93.55 444	97.54 445	88.15 411	97.91 440	94.58 405	89.69 445	97.61 440

MDTV_nov1_ep13_2view						95.18 404	99.35 282		96.84 331	99.58 148		95.19 234		97.82 273		99.46 238

VDD-MVS		97.73 312	97.35 329	98.88 253	99.47 235	97.12 321	99.34 285	98.85 396	98.19 163	99.67 111	99.85 76	82.98 443	99.92 117	99.49 59	98.32 272	99.60 179

COLMAP_ROB	97.56 6	98.86 169	98.75 170	99.17 208	99.88 13	98.53 240	99.34 285	99.59 69	97.55 261	98.70 336	99.89 39	95.83 203	99.90 142	98.10 246	99.90 55	99.08 284
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
viewmambaseed2359dif		99.01 152	98.90 146	99.32 181	99.58 183	98.51 246	99.33 287	99.54 103	97.85 222	99.44 179	99.85 76	96.01 192	99.79 230	99.41 68	99.13 204	99.67 150

myMVS_eth3d28		97.69 319	97.34 332	98.73 277	99.27 293	97.52 304	99.33 287	98.78 406	98.03 203	98.82 318	98.49 422	86.64 421	99.46 313	98.44 213	98.24 278	99.23 272

EGC-MVSNET		82.80 428	77.86 434	97.62 386	97.91 430	96.12 379	99.33 287	99.28 329	8.40 471	25.05 472	99.27 362	84.11 438	99.33 343	89.20 443	98.22 279	97.42 445

diffmvs_AUTHOR		99.19 96	99.10 94	99.48 147	99.64 153	98.85 206	99.32 290	99.48 188	98.50 118	99.81 63	99.81 120	96.82 156	99.88 162	99.40 69	99.12 206	99.71 135

ETVMVS		97.50 339	96.90 359	99.29 191	99.23 304	98.78 219	99.32 290	98.90 389	97.52 267	98.56 356	98.09 440	84.72 436	99.69 275	97.86 268	97.88 297	99.39 251

FMVSNet5		96.43 377	96.19 376	97.15 400	99.11 335	95.89 383	99.32 290	99.52 123	94.47 418	98.34 369	99.07 383	87.54 417	97.07 450	92.61 431	95.72 374	98.47 394

dp		97.75 308	97.80 266	97.59 390	99.10 338	93.71 430	99.32 290	98.88 392	96.48 359	99.08 272	99.55 273	92.67 335	99.82 212	96.52 365	98.58 253	99.24 271

tpmvs		97.98 267	98.02 245	97.84 373	99.04 352	94.73 412	99.31 294	99.20 345	96.10 390	98.76 326	99.42 316	94.94 242	99.81 217	96.97 344	98.45 262	98.97 299

tpmrst		98.33 224	98.48 207	97.90 367	99.16 327	94.78 411	99.31 294	99.11 356	97.27 292	99.45 174	99.59 258	95.33 226	99.84 189	98.48 207	98.61 250	99.09 283

testing99		97.36 349	96.94 358	98.63 288	99.18 317	96.70 355	99.30 296	98.93 379	97.71 241	98.23 375	98.26 432	84.92 434	99.84 189	98.04 256	97.85 300	99.35 257

MP-MVS-pluss		99.37 64	99.20 82	99.88 13	99.90 4	99.87 16	99.30 296	99.52 123	97.18 300	99.60 144	99.79 154	98.79 50	99.95 74	98.83 159	99.91 44	99.83 61
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
NCCC		99.34 71	99.19 84	99.79 62	99.61 173	99.65 69	99.30 296	99.48 188	98.86 78	99.21 245	99.63 244	98.72 64	99.90 142	98.25 232	99.63 158	99.80 83

JIA-IIPM		97.50 339	97.02 355	98.93 238	98.73 400	97.80 291	99.30 296	98.97 375	91.73 439	98.91 302	94.86 457	95.10 237	99.71 263	97.58 298	97.98 292	99.28 265

BH-RMVSNet		98.41 216	98.08 237	99.40 166	99.41 252	98.83 211	99.30 296	98.77 407	97.70 244	98.94 299	99.65 232	92.91 325	99.74 247	96.52 365	99.55 166	99.64 166

testing11		97.50 339	97.10 352	98.71 282	99.20 311	96.91 347	99.29 301	98.82 399	97.89 216	98.21 378	98.40 426	85.63 429	99.83 203	98.45 212	98.04 291	99.37 255

Syy-MVS		97.09 363	97.14 349	96.95 408	99.00 357	92.73 440	99.29 301	99.39 267	97.06 314	97.41 404	98.15 435	93.92 301	98.68 425	91.71 434	98.34 266	99.45 241

myMVS_eth3d		96.89 366	96.37 371	98.43 321	99.00 357	97.16 319	99.29 301	99.39 267	97.06 314	97.41 404	98.15 435	83.46 442	98.68 425	95.27 396	98.34 266	99.45 241

MCST-MVS		99.43 50	99.30 59	99.82 52	99.79 62	99.74 49	99.29 301	99.40 264	98.79 89	99.52 163	99.62 249	98.91 37	99.90 142	98.64 182	99.75 136	99.82 67

LF4IMVS		97.52 336	97.46 311	97.70 383	98.98 363	95.55 390	99.29 301	98.82 399	98.07 188	98.66 339	99.64 238	89.97 386	99.61 298	97.01 340	96.68 346	97.94 433

hse-mvs2		97.50 339	97.14 349	98.59 291	99.49 227	97.05 328	99.28 306	99.22 341	98.94 72	99.66 116	99.42 316	94.93 243	99.65 286	99.48 62	83.80 455	99.08 284

OPM-MVS		98.19 235	98.10 233	98.45 316	98.88 375	97.07 326	99.28 306	99.38 275	98.57 111	99.22 242	99.81 120	92.12 349	99.66 281	98.08 251	97.54 316	98.61 380
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
diffmvs		99.14 113	99.02 117	99.51 138	99.61 173	98.96 181	99.28 306	99.49 176	98.46 122	99.72 96	99.71 197	96.50 173	99.88 162	99.31 83	99.11 208	99.67 150
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_BlendedMVS		98.86 169	98.80 164	99.03 223	99.76 76	98.79 217	99.28 306	99.91 3	97.42 280	99.67 111	99.37 334	97.53 119	99.88 162	98.98 127	97.29 336	98.42 400

OMC-MVS		99.08 135	99.04 108	99.20 205	99.67 128	98.22 264	99.28 306	99.52 123	98.07 188	99.66 116	99.81 120	97.79 114	99.78 236	97.79 277	99.81 114	99.60 179

testing222		97.16 359	96.50 368	99.16 209	99.16 327	98.47 253	99.27 311	98.66 422	97.71 241	98.23 375	98.15 435	82.28 448	99.84 189	97.36 320	97.66 306	99.18 275

AUN-MVS		96.88 367	96.31 373	98.59 291	99.48 234	97.04 331	99.27 311	99.22 341	97.44 277	98.51 359	99.41 320	91.97 352	99.66 281	97.71 289	83.83 454	99.07 289

pmmvs5		97.52 336	97.30 338	98.16 345	98.57 418	96.73 354	99.27 311	98.90 389	96.14 384	98.37 367	99.53 282	91.54 366	99.14 377	97.51 307	95.87 369	98.63 369

1314		98.68 198	98.54 203	99.11 215	98.89 374	98.65 227	99.27 311	99.49 176	96.89 328	97.99 388	99.56 270	97.72 117	99.83 203	97.74 285	99.27 188	98.84 307

MVS		97.28 354	96.55 367	99.48 147	98.78 391	98.95 187	99.27 311	99.39 267	83.53 457	98.08 383	99.54 278	96.97 147	99.87 169	94.23 411	99.16 198	99.63 171

BH-untuned		98.42 214	98.36 213	98.59 291	99.49 227	96.70 355	99.27 311	99.13 354	97.24 296	98.80 321	99.38 331	95.75 209	99.74 247	97.07 339	99.16 198	99.33 261

MDTV_nov1_ep13			98.32 217		99.11 335	94.44 420	99.27 311	98.74 411	97.51 268	99.40 195	99.62 249	94.78 253	99.76 242	97.59 297	98.81 242

DP-MVS Recon		99.12 122	98.95 136	99.65 89	99.74 94	99.70 55	99.27 311	99.57 81	96.40 366	99.42 185	99.68 219	98.75 58	99.80 224	97.98 259	99.72 142	99.44 243

PatchmatchNet		98.31 225	98.36 213	98.19 343	99.16 327	95.32 400	99.27 311	98.92 382	97.37 284	99.37 201	99.58 262	94.90 246	99.70 270	97.43 316	99.21 195	99.54 203
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thres200		97.61 330	97.28 341	98.62 289	99.64 153	98.03 274	99.26 320	98.74 411	97.68 246	99.09 270	98.32 430	91.66 363	99.81 217	92.88 427	98.22 279	98.03 425

CNVR-MVS		99.42 52	99.30 59	99.78 65	99.62 164	99.71 53	99.26 320	99.52 123	98.82 83	99.39 197	99.71 197	98.96 25	99.85 180	98.59 193	99.80 119	99.77 95

mamba_0408		99.08 135	98.96 132	99.44 160	99.62 164	98.88 198	99.25 322	99.47 210	98.05 194	99.37 201	99.81 120	96.85 151	99.85 180	98.98 127	99.25 191	99.60 179

SSM_04072		99.06 140	98.96 132	99.35 174	99.62 164	98.88 198	99.25 322	99.47 210	98.05 194	99.37 201	99.81 120	96.85 151	99.58 301	98.98 127	99.25 191	99.60 179

tt0320		95.71 392	95.07 396	97.62 386	99.05 350	95.02 406	99.25 322	99.52 123	86.81 452	97.97 390	99.72 194	83.58 441	99.15 375	96.38 371	93.35 417	98.68 341

1112_ss		98.98 155	98.77 168	99.59 107	99.68 126	99.02 169	99.25 322	99.48 188	97.23 297	99.13 260	99.58 262	96.93 149	99.90 142	98.87 146	98.78 243	99.84 51

TAPA-MVS	97.07 15	97.74 310	97.34 332	98.94 236	99.70 116	97.53 303	99.25 322	99.51 142	91.90 438	99.30 220	99.63 244	98.78 51	99.64 290	88.09 448	99.87 73	99.65 159
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
UWE-MVS-28		97.36 349	97.24 345	97.75 379	98.84 384	94.44 420	99.24 327	97.58 447	97.98 208	99.00 288	99.00 392	91.35 369	99.53 308	93.75 416	98.39 264	99.27 269

UBG		97.85 286	97.48 306	98.95 234	99.25 300	97.64 300	99.24 327	98.74 411	97.90 215	98.64 346	98.20 434	88.65 403	99.81 217	98.27 230	98.40 263	99.42 245

PLC	97.94 4	99.02 148	98.85 159	99.53 127	99.66 141	99.01 171	99.24 327	99.52 123	96.85 330	99.27 230	99.48 302	98.25 98	99.91 129	97.76 282	99.62 159	99.65 159
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test_post1							99.23 330				65.14 469	94.18 291	99.71 263	97.58 298

ADS-MVSNet2		98.02 260	98.07 240	97.87 369	99.33 275	95.19 403	99.23 330	99.08 360	96.24 374	99.10 267	99.67 225	94.11 292	98.93 414	96.81 353	99.05 217	99.48 227

ADS-MVSNet		98.20 234	98.08 237	98.56 299	99.33 275	96.48 366	99.23 330	99.15 351	96.24 374	99.10 267	99.67 225	94.11 292	99.71 263	96.81 353	99.05 217	99.48 227

EPNet_dtu		98.03 258	97.96 250	98.23 341	98.27 426	95.54 392	99.23 330	98.75 408	99.02 56	97.82 397	99.71 197	96.11 187	99.48 310	93.04 425	99.65 155	99.69 141
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		98.17 238	97.93 255	98.87 257	99.18 317	98.49 249	99.22 334	99.33 304	96.96 322	99.56 152	99.38 331	94.33 284	99.00 400	94.83 404	98.58 253	99.14 276

RPMNet		96.72 370	95.90 383	99.19 206	99.18 317	98.49 249	99.22 334	99.52 123	88.72 450	99.56 152	97.38 447	94.08 294	99.95 74	86.87 455	98.58 253	99.14 276

sc_t1		95.75 390	95.05 397	97.87 369	98.83 385	94.61 417	99.21 336	99.45 232	87.45 451	97.97 390	99.85 76	81.19 451	99.43 324	98.27 230	93.20 421	99.57 197

WBMVS		97.74 310	97.50 304	98.46 314	99.24 302	97.43 307	99.21 336	99.42 254	97.45 274	98.96 295	99.41 320	88.83 398	99.23 360	98.94 134	96.02 362	98.71 327

plane_prior						96.97 339	99.21 336		98.45 124						97.60 310

IMVS_0404		98.53 207	98.52 205	98.55 301	99.55 196	96.93 342	99.20 339	99.44 241	98.05 194	98.96 295	99.80 137	94.66 266	99.13 380	98.15 242	98.92 228	99.60 179

tt0320-xc		95.31 398	94.59 402	97.45 394	98.92 370	94.73 412	99.20 339	99.31 318	86.74 453	97.23 410	99.72 194	81.14 452	98.95 412	97.08 338	91.98 432	98.67 349

testing91		97.44 346	97.02 355	98.71 282	99.18 317	96.89 349	99.19 341	99.04 367	97.78 234	98.31 370	98.29 431	85.41 431	99.85 180	98.01 257	97.95 293	99.39 251

WR-MVS		98.06 250	97.73 279	99.06 219	98.86 381	99.25 140	99.19 341	99.35 291	97.30 290	98.66 339	99.43 314	93.94 299	99.21 369	98.58 194	94.28 404	98.71 327

new-patchmatchnet		94.48 406	94.08 407	95.67 422	95.08 458	92.41 441	99.18 343	99.28 329	94.55 417	93.49 445	97.37 448	87.86 415	97.01 451	91.57 435	88.36 447	97.61 440

AdaColmap		99.01 152	98.80 164	99.66 85	99.56 192	99.54 92	99.18 343	99.70 15	98.18 166	99.35 210	99.63 244	96.32 181	99.90 142	97.48 310	99.77 131	99.55 201

EG-PatchMatch MVS		95.97 386	95.69 387	96.81 412	97.78 433	92.79 439	99.16 345	98.93 379	96.16 381	94.08 441	99.22 368	82.72 444	99.47 311	95.67 387	97.50 321	98.17 416

PatchT		97.03 364	96.44 370	98.79 272	98.99 360	98.34 259	99.16 345	99.07 363	92.13 437	99.52 163	97.31 450	94.54 274	98.98 402	88.54 446	98.73 245	99.03 292

CNLPA		99.14 113	98.99 124	99.59 107	99.58 183	99.41 114	99.16 345	99.44 241	98.45 124	99.19 251	99.49 296	98.08 106	99.89 157	97.73 286	99.75 136	99.48 227

MDA-MVSNet-bldmvs		94.96 401	93.98 408	97.92 365	98.24 427	97.27 313	99.15 348	99.33 304	93.80 422	80.09 464	99.03 388	88.31 408	97.86 442	93.49 420	94.36 403	98.62 371

CDPH-MVS		99.13 115	98.91 144	99.80 59	99.75 86	99.71 53	99.15 348	99.41 257	96.60 350	99.60 144	99.55 273	98.83 45	99.90 142	97.48 310	99.83 107	99.78 93

save fliter					99.76 76	99.59 82	99.14 350	99.40 264	99.00 61

WB-MVSnew		97.65 327	97.65 287	97.63 385	98.78 391	97.62 301	99.13 351	98.33 431	97.36 285	99.07 273	98.94 400	95.64 214	99.15 375	92.95 426	98.68 248	96.12 455

testf1		90.42 422	90.68 423	89.65 442	97.78 433	73.97 470	99.13 351	98.81 401	89.62 445	91.80 453	98.93 401	62.23 462	98.80 421	86.61 456	91.17 435	96.19 453

APD_test2		90.42 422	90.68 423	89.65 442	97.78 433	73.97 470	99.13 351	98.81 401	89.62 445	91.80 453	98.93 401	62.23 462	98.80 421	86.61 456	91.17 435	96.19 453

xiu_mvs_v1_base_debu		99.29 80	99.27 70	99.34 175	99.63 157	98.97 177	99.12 354	99.51 142	98.86 78	99.84 51	99.47 305	98.18 101	99.99 4	99.50 55	99.31 185	99.08 284

xiu_mvs_v1_base		99.29 80	99.27 70	99.34 175	99.63 157	98.97 177	99.12 354	99.51 142	98.86 78	99.84 51	99.47 305	98.18 101	99.99 4	99.50 55	99.31 185	99.08 284

xiu_mvs_v1_base_debi		99.29 80	99.27 70	99.34 175	99.63 157	98.97 177	99.12 354	99.51 142	98.86 78	99.84 51	99.47 305	98.18 101	99.99 4	99.50 55	99.31 185	99.08 284

XVG-OURS-SEG-HR		98.69 197	98.62 193	98.89 250	99.71 111	97.74 292	99.12 354	99.54 103	98.44 127	99.42 185	99.71 197	94.20 288	99.92 117	98.54 204	98.90 234	99.00 295

jason		99.13 115	99.03 111	99.45 155	99.46 237	98.87 202	99.12 354	99.26 333	98.03 203	99.79 70	99.65 232	97.02 144	99.85 180	99.02 124	99.90 55	99.65 159
jason: jason.
N_pmnet		94.95 402	95.83 385	92.31 433	98.47 422	79.33 465	99.12 354	92.81 471	93.87 421	97.68 400	99.13 378	93.87 303	99.01 399	91.38 436	96.19 359	98.59 384

MDA-MVSNet_test_wron		95.45 394	94.60 401	98.01 356	98.16 428	97.21 318	99.11 360	99.24 338	93.49 426	80.73 463	98.98 396	93.02 320	98.18 433	94.22 412	94.45 401	98.64 362

Patchmtry		97.75 308	97.40 324	98.81 269	99.10 338	98.87 202	99.11 360	99.33 304	94.83 411	98.81 319	99.38 331	94.33 284	99.02 397	96.10 374	95.57 379	98.53 388

YYNet1		95.36 396	94.51 404	97.92 365	97.89 431	97.10 322	99.10 362	99.23 339	93.26 429	80.77 462	99.04 387	92.81 326	98.02 437	94.30 408	94.18 406	98.64 362

CANet_DTU		98.97 157	98.87 154	99.25 198	99.33 275	98.42 257	99.08 363	99.30 323	99.16 31	99.43 182	99.75 179	95.27 228	99.97 27	98.56 200	99.95 21	99.36 256

icg_test_0407_2		98.79 186	98.86 156	98.57 295	99.55 196	96.93 342	99.07 364	99.44 241	98.05 194	99.66 116	99.80 137	97.13 135	99.18 372	98.15 242	98.92 228	99.60 179

SCA		98.19 235	98.16 225	98.27 339	99.30 284	95.55 390	99.07 364	98.97 375	97.57 258	99.43 182	99.57 267	92.72 330	99.74 247	97.58 298	99.20 196	99.52 210

TSAR-MVS + GP.		99.36 68	99.36 43	99.36 172	99.67 128	98.61 234	99.07 364	99.33 304	99.00 61	99.82 62	99.81 120	99.06 16	99.84 189	99.09 115	99.42 175	99.65 159

MG-MVS		99.13 115	99.02 117	99.45 155	99.57 188	98.63 230	99.07 364	99.34 296	98.99 63	99.61 141	99.82 105	97.98 110	99.87 169	97.00 341	99.80 119	99.85 44

PatchMatch-RL		98.84 181	98.62 193	99.52 133	99.71 111	99.28 135	99.06 368	99.77 9	97.74 239	99.50 166	99.53 282	95.41 221	99.84 189	97.17 334	99.64 156	99.44 243

OpenMVS_ROB	92.34 20	94.38 407	93.70 413	96.41 417	97.38 439	93.17 437	99.06 368	98.75 408	86.58 454	94.84 439	98.26 432	81.53 449	99.32 345	89.01 444	97.87 298	96.76 448

TEST9					99.67 128	99.65 69	99.05 370	99.41 257	96.22 376	98.95 297	99.49 296	98.77 54	99.91 129

train_agg		99.02 148	98.77 168	99.77 68	99.67 128	99.65 69	99.05 370	99.41 257	96.28 370	98.95 297	99.49 296	98.76 55	99.91 129	97.63 294	99.72 142	99.75 104

lupinMVS		99.13 115	99.01 122	99.46 154	99.51 213	98.94 191	99.05 370	99.16 350	97.86 219	99.80 68	99.56 270	97.39 122	99.86 174	98.94 134	99.85 88	99.58 194

DELS-MVS		99.48 34	99.42 29	99.65 89	99.72 105	99.40 115	99.05 370	99.66 28	99.14 34	99.57 151	99.80 137	98.46 84	99.94 87	99.57 46	99.84 96	99.60 179
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		96.38 378	96.03 380	97.41 395	98.13 429	95.16 405	99.05 370	99.20 345	93.94 420	97.39 407	98.79 412	91.61 365	99.04 393	90.43 439	95.77 371	98.05 424

Patchmatch-test		97.93 273	97.65 287	98.77 275	99.18 317	97.07 326	99.03 375	99.14 353	96.16 381	98.74 327	99.57 267	94.56 271	99.72 257	93.36 421	99.11 208	99.52 210

test_8					99.67 128	99.61 79	99.03 375	99.41 257	96.28 370	98.93 300	99.48 302	98.76 55	99.91 129

Test_1112_low_res		98.89 162	98.66 183	99.57 114	99.69 121	98.95 187	99.03 375	99.47 210	96.98 320	99.15 258	99.23 367	96.77 160	99.89 157	98.83 159	98.78 243	99.86 40

IterMVS-SCA-FT		97.82 296	97.75 277	98.06 352	99.57 188	96.36 370	99.02 378	99.49 176	97.18 300	98.71 330	99.72 194	92.72 330	99.14 377	97.44 315	95.86 370	98.67 349

xiu_mvs_v2_base		99.26 87	99.25 74	99.29 191	99.53 204	98.91 196	99.02 378	99.45 232	98.80 88	99.71 99	99.26 364	98.94 32	99.98 18	99.34 79	99.23 194	98.98 298

MIMVSNet		97.73 312	97.45 312	98.57 295	99.45 243	97.50 305	99.02 378	98.98 374	96.11 386	99.41 190	99.14 377	90.28 380	98.74 423	95.74 383	98.93 226	99.47 233

IterMVS		97.83 293	97.77 272	98.02 355	99.58 183	96.27 374	99.02 378	99.48 188	97.22 298	98.71 330	99.70 201	92.75 327	99.13 380	97.46 313	96.00 364	98.67 349
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		99.11 128	98.92 141	99.65 89	99.90 4	99.37 117	99.02 378	99.91 3	97.67 248	99.59 147	99.75 179	95.90 200	99.73 253	99.53 51	99.02 221	99.86 40

UWE-MVS		97.58 332	97.29 340	98.48 308	99.09 341	96.25 375	99.01 383	96.61 457	97.86 219	99.19 251	99.01 391	88.72 399	99.90 142	97.38 319	98.69 247	99.28 265

新几何2							99.01 383

BH-w/o		98.00 265	97.89 261	98.32 331	99.35 269	96.20 377	99.01 383	98.90 389	96.42 364	98.38 366	99.00 392	95.26 230	99.72 257	96.06 375	98.61 250	99.03 292

test_prior4						99.56 88	98.99 386

无先验							98.99 386	99.51 142	96.89 328				99.93 105	97.53 306		99.72 126

pmmvs4		98.13 242	97.90 257	98.81 269	98.61 414	98.87 202	98.99 386	99.21 344	96.44 362	99.06 278	99.58 262	95.90 200	99.11 386	97.18 333	96.11 361	98.46 397

HQP-NCC					99.19 314		98.98 389		98.24 155	98.66 339

ACMP_Plane					99.19 314		98.98 389		98.24 155	98.66 339

HQP-MVS		98.02 260	97.90 257	98.37 327	99.19 314	96.83 350	98.98 389	99.39 267	98.24 155	98.66 339	99.40 324	92.47 341	99.64 290	97.19 331	97.58 312	98.64 362

PS-MVSNAJ		99.32 75	99.32 51	99.30 188	99.57 188	98.94 191	98.97 392	99.46 221	98.92 75	99.71 99	99.24 366	99.01 18	99.98 18	99.35 74	99.66 153	98.97 299

MVP-Stereo		97.81 298	97.75 277	97.99 359	97.53 437	96.60 363	98.96 393	98.85 396	97.22 298	97.23 410	99.36 337	95.28 227	99.46 313	95.51 389	99.78 128	97.92 435
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test_prior2							98.96 393		98.34 137	99.01 284	99.52 286	98.68 67		97.96 260	99.74 139

旧先验2							98.96 393		96.70 338	99.47 171			99.94 87	98.19 236

原ACMM2							98.95 396

MVS_111021_HR		99.41 56	99.32 51	99.66 85	99.72 105	99.47 107	98.95 396	99.85 6	98.82 83	99.54 159	99.73 190	98.51 81	99.74 247	98.91 140	99.88 70	99.77 95

mvsany_test1		99.50 28	99.46 26	99.62 102	99.61 173	99.09 159	98.94 398	99.48 188	99.10 42	99.96 25	99.91 24	98.85 42	99.96 39	99.72 30	99.58 163	99.82 67

MVS_111021_LR		99.41 56	99.33 49	99.65 89	99.77 72	99.51 101	98.94 398	99.85 6	98.82 83	99.65 125	99.74 184	98.51 81	99.80 224	98.83 159	99.89 66	99.64 166

pmmvs3		94.09 409	93.25 416	96.60 415	94.76 460	94.49 419	98.92 400	98.18 438	89.66 444	96.48 424	98.06 441	86.28 425	97.33 448	89.68 442	87.20 450	97.97 432

XVG-OURS		98.73 195	98.68 179	98.88 253	99.70 116	97.73 293	98.92 400	99.55 94	98.52 116	99.45 174	99.84 91	95.27 228	99.91 129	98.08 251	98.84 238	99.00 295

test222					99.75 86	99.49 103	98.91 402	99.49 176	96.42 364	99.34 213	99.65 232	98.28 97			99.69 147	99.72 126

PMMVS2		86.87 425	85.37 429	91.35 437	90.21 466	83.80 456	98.89 403	97.45 449	83.13 458	91.67 455	95.03 455	48.49 468	94.70 461	85.86 458	77.62 460	95.54 456

miper_lstm_enhance		98.00 265	97.91 256	98.28 338	99.34 274	97.43 307	98.88 404	99.36 284	96.48 359	98.80 321	99.55 273	95.98 193	98.91 415	97.27 324	95.50 382	98.51 390

MVS-HIRNet		95.75 390	95.16 395	97.51 392	99.30 284	93.69 431	98.88 404	95.78 459	85.09 456	98.78 324	92.65 459	91.29 371	99.37 333	94.85 403	99.85 88	99.46 238

TR-MVS		97.76 304	97.41 323	98.82 266	99.06 347	97.87 287	98.87 406	98.56 425	96.63 346	98.68 338	99.22 368	92.49 340	99.65 286	95.40 393	97.79 302	98.95 303

testdata1							98.85 407		98.32 140

ET-MVSNet_ETH3D		96.49 375	95.64 389	99.05 221	99.53 204	98.82 214	98.84 408	97.51 448	97.63 251	84.77 457	99.21 371	92.09 350	98.91 415	98.98 127	92.21 431	99.41 248

our_test_3		97.65 327	97.68 284	97.55 391	98.62 412	94.97 408	98.84 408	99.30 323	96.83 333	98.19 379	99.34 344	97.01 146	99.02 397	95.00 401	96.01 363	98.64 362

MS-PatchMatch		97.24 358	97.32 336	96.99 405	98.45 423	93.51 435	98.82 410	99.32 314	97.41 281	98.13 382	99.30 355	88.99 396	99.56 304	95.68 386	99.80 119	97.90 436

c3_l		98.12 244	98.04 242	98.38 326	99.30 284	97.69 299	98.81 411	99.33 304	96.67 340	98.83 316	99.34 344	97.11 138	98.99 401	97.58 298	95.34 384	98.48 392

ppachtmachnet_test		97.49 344	97.45 312	97.61 389	98.62 412	95.24 401	98.80 412	99.46 221	96.11 386	98.22 377	99.62 249	96.45 176	98.97 409	93.77 415	95.97 368	98.61 380

PAPR		98.63 204	98.34 215	99.51 138	99.40 257	99.03 168	98.80 412	99.36 284	96.33 367	99.00 288	99.12 381	98.46 84	99.84 189	95.23 397	99.37 184	99.66 154

test0.0.03 1		97.71 317	97.42 322	98.56 299	98.41 425	97.82 290	98.78 414	98.63 423	97.34 286	98.05 387	98.98 396	94.45 279	98.98 402	95.04 400	97.15 342	98.89 304

PVSNet_Blended		99.08 135	98.97 128	99.42 164	99.76 76	98.79 217	98.78 414	99.91 3	96.74 335	99.67 111	99.49 296	97.53 119	99.88 162	98.98 127	99.85 88	99.60 179

PMMVS		98.80 185	98.62 193	99.34 175	99.27 293	98.70 223	98.76 416	99.31 318	97.34 286	99.21 245	99.07 383	97.20 133	99.82 212	98.56 200	98.87 235	99.52 210

test123		39.01 437	42.50 439	28.53 452	39.17 475	20.91 477	98.75 417	19.17 477	19.83 470	38.57 469	66.67 467	33.16 472	15.42 471	37.50 471	29.66 469	49.26 466

MSDG		98.98 155	98.80 164	99.53 127	99.76 76	99.19 144	98.75 417	99.55 94	97.25 294	99.47 171	99.77 170	97.82 113	99.87 169	96.93 348	99.90 55	99.54 203

CLD-MVS		98.16 239	98.10 233	98.33 329	99.29 288	96.82 352	98.75 417	99.44 241	97.83 226	99.13 260	99.55 273	92.92 323	99.67 278	98.32 227	97.69 305	98.48 392
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		98.18 237	98.10 233	98.41 322	99.23 304	97.72 295	98.72 420	99.31 318	96.60 350	98.88 307	99.29 357	97.29 129	99.13 380	97.60 296	95.99 365	98.38 405

cl____		98.01 263	97.84 265	98.55 301	99.25 300	97.97 278	98.71 421	99.34 296	96.47 361	98.59 355	99.54 278	95.65 213	99.21 369	97.21 327	95.77 371	98.46 397

DIV-MVS_self_test		98.01 263	97.85 264	98.48 308	99.24 302	97.95 283	98.71 421	99.35 291	96.50 355	98.60 354	99.54 278	95.72 211	99.03 395	97.21 327	95.77 371	98.46 397

test-LLR		98.06 250	97.90 257	98.55 301	98.79 388	97.10 322	98.67 423	97.75 443	97.34 286	98.61 352	98.85 406	94.45 279	99.45 315	97.25 325	99.38 177	99.10 279

TESTMET0.1,1		97.55 333	97.27 344	98.40 324	98.93 368	96.53 364	98.67 423	97.61 446	96.96 322	98.64 346	99.28 359	88.63 405	99.45 315	97.30 323	99.38 177	99.21 274

test-mter		97.49 344	97.13 351	98.55 301	98.79 388	97.10 322	98.67 423	97.75 443	96.65 342	98.61 352	98.85 406	88.23 409	99.45 315	97.25 325	99.38 177	99.10 279

mvs5depth		96.66 371	96.22 375	97.97 360	97.00 448	96.28 373	98.66 426	99.03 369	96.61 347	96.93 420	99.79 154	87.20 419	99.47 311	96.65 363	94.13 407	98.16 417

IB-MVS	95.67 18	96.22 379	95.44 393	98.57 295	99.21 309	96.70 355	98.65 427	97.74 445	96.71 337	97.27 409	98.54 421	86.03 426	99.92 117	98.47 210	86.30 451	99.10 279
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		98.95 158	98.71 176	99.66 85	99.63 157	99.55 90	98.64 428	99.10 357	97.93 212	99.42 185	99.55 273	98.67 69	99.80 224	95.80 382	99.68 150	99.61 176

thisisatest0515		98.14 241	97.79 267	99.19 206	99.50 225	98.50 248	98.61 429	96.82 453	96.95 324	99.54 159	99.43 314	91.66 363	99.86 174	98.08 251	99.51 168	99.22 273

DeepPCF-MVS	98.18 3	98.81 182	99.37 41	97.12 403	99.60 179	91.75 444	98.61 429	99.44 241	99.35 23	99.83 59	99.85 76	98.70 66	99.81 217	99.02 124	99.91 44	99.81 74

cl22		97.85 286	97.64 290	98.48 308	99.09 341	97.87 287	98.60 431	99.33 304	97.11 309	98.87 310	99.22 368	92.38 346	99.17 374	98.21 234	95.99 365	98.42 400

GA-MVS		97.85 286	97.47 309	99.00 227	99.38 262	97.99 277	98.57 432	99.15 351	97.04 317	98.90 304	99.30 355	89.83 388	99.38 330	96.70 358	98.33 268	99.62 174

TinyColmap		97.12 361	96.89 360	97.83 374	99.07 345	95.52 393	98.57 432	98.74 411	97.58 257	97.81 398	99.79 154	88.16 410	99.56 304	95.10 398	97.21 339	98.39 404

eth_miper_zixun_eth		98.05 255	97.96 250	98.33 329	99.26 296	97.38 309	98.56 434	99.31 318	96.65 342	98.88 307	99.52 286	96.58 169	99.12 385	97.39 318	95.53 381	98.47 394

CMPMVS	69.68 23	94.13 408	94.90 399	91.84 434	97.24 443	80.01 464	98.52 435	99.48 188	89.01 448	91.99 451	99.67 225	85.67 428	99.13 380	95.44 391	97.03 344	96.39 452
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
USDC		97.34 351	97.20 346	97.75 379	99.07 345	95.20 402	98.51 436	99.04 367	97.99 207	98.31 370	99.86 69	89.02 395	99.55 306	95.67 387	97.36 334	98.49 391

ambc				93.06 432	92.68 463	82.36 457	98.47 437	98.73 417		95.09 437	97.41 446	55.55 464	99.10 388	96.42 368	91.32 434	97.71 437

miper_enhance_ethall		98.16 239	98.08 237	98.41 322	98.96 366	97.72 295	98.45 438	99.32 314	96.95 324	98.97 293	99.17 373	97.06 142	99.22 364	97.86 268	95.99 365	98.29 409

CHOSEN 280x420		99.12 122	99.13 90	99.08 216	99.66 141	97.89 286	98.43 439	99.71 13	98.88 77	99.62 137	99.76 174	96.63 166	99.70 270	99.46 65	99.99 1	99.66 154

testmvs		39.17 436	43.78 438	25.37 453	36.04 476	16.84 478	98.36 440	26.56 475	20.06 469	38.51 470	67.32 466	29.64 473	15.30 472	37.59 470	39.90 468	43.98 467

FPMVS		84.93 427	85.65 428	82.75 448	86.77 469	63.39 474	98.35 441	98.92 382	74.11 460	83.39 459	98.98 396	50.85 467	92.40 463	84.54 459	94.97 392	92.46 458

KD-MVS_2432*1600		94.62 403	93.72 411	97.31 397	97.19 445	95.82 384	98.34 442	99.20 345	95.00 407	97.57 401	98.35 428	87.95 412	98.10 435	92.87 428	77.00 461	98.01 426

miper_refine_blended		94.62 403	93.72 411	97.31 397	97.19 445	95.82 384	98.34 442	99.20 345	95.00 407	97.57 401	98.35 428	87.95 412	98.10 435	92.87 428	77.00 461	98.01 426

CL-MVSNet_self_test		94.49 405	93.97 409	96.08 420	96.16 450	93.67 432	98.33 444	99.38 275	95.13 401	97.33 408	98.15 435	92.69 334	96.57 453	88.67 445	79.87 459	97.99 430

PVSNet	96.02 17	98.85 178	98.84 161	98.89 250	99.73 101	97.28 312	98.32 445	99.60 63	97.86 219	99.50 166	99.57 267	96.75 161	99.86 174	98.56 200	99.70 146	99.54 203

PAPM		97.59 331	97.09 353	99.07 217	99.06 347	98.26 262	98.30 446	99.10 357	94.88 409	98.08 383	99.34 344	96.27 183	99.64 290	89.87 441	98.92 228	99.31 263

Patchmatch-RL test		95.84 388	95.81 386	95.95 421	95.61 453	90.57 447	98.24 447	98.39 429	95.10 405	95.20 435	98.67 416	94.78 253	97.77 443	96.28 373	90.02 442	99.51 219

UnsupCasMVSNet_bld		93.53 412	92.51 418	96.58 416	97.38 439	93.82 427	98.24 447	99.48 188	91.10 442	93.10 446	96.66 452	74.89 456	98.37 430	94.03 414	87.71 449	97.56 442

LCM-MVSNet		86.80 426	85.22 430	91.53 436	87.81 468	80.96 462	98.23 449	98.99 373	71.05 461	90.13 456	96.51 453	48.45 469	96.88 452	90.51 438	85.30 452	96.76 448

cascas		97.69 319	97.43 321	98.48 308	98.60 415	97.30 311	98.18 450	99.39 267	92.96 432	98.41 364	98.78 413	93.77 307	99.27 353	98.16 240	98.61 250	98.86 305

kuosan		90.92 421	90.11 426	93.34 429	98.78 391	85.59 454	98.15 451	93.16 469	89.37 447	92.07 450	98.38 427	81.48 450	95.19 459	62.54 468	97.04 343	99.25 270

Effi-MVS+		98.81 182	98.59 199	99.48 147	99.46 237	99.12 157	98.08 452	99.50 164	97.50 269	99.38 199	99.41 320	96.37 180	99.81 217	99.11 111	98.54 258	99.51 219

PCF-MVS	97.08 14	97.66 326	97.06 354	99.47 152	99.61 173	99.09 159	98.04 453	99.25 335	91.24 441	98.51 359	99.70 201	94.55 273	99.91 129	92.76 430	99.85 88	99.42 245
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet_0	94.43 19	96.09 384	95.47 391	97.94 363	99.31 283	94.34 424	97.81 454	99.70 15	97.12 306	97.46 403	98.75 414	89.71 389	99.79 230	97.69 292	81.69 457	99.68 146

E-PMN		80.61 430	79.88 432	82.81 447	90.75 465	76.38 468	97.69 455	95.76 460	66.44 465	83.52 458	92.25 460	62.54 461	87.16 467	68.53 466	61.40 464	84.89 465

dongtai		93.26 413	92.93 417	94.25 425	99.39 260	85.68 453	97.68 456	93.27 467	92.87 433	96.85 421	99.39 328	82.33 447	97.48 447	76.78 461	97.80 301	99.58 194

ANet_high		77.30 432	74.86 436	84.62 446	75.88 472	77.61 466	97.63 457	93.15 470	88.81 449	64.27 467	89.29 464	36.51 471	83.93 469	75.89 463	52.31 466	92.33 460

EMVS		80.02 431	79.22 433	82.43 449	91.19 464	76.40 467	97.55 458	92.49 472	66.36 466	83.01 460	91.27 462	64.63 460	85.79 468	65.82 467	60.65 465	85.08 464

MVE	76.82 21	76.91 433	74.31 437	84.70 445	85.38 471	76.05 469	96.88 459	93.17 468	67.39 464	71.28 466	89.01 465	21.66 476	87.69 466	71.74 465	72.29 463	90.35 462
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		91.10 419	91.36 421	90.31 439	95.85 451	73.72 472	94.89 460	99.25 335	68.39 463	95.82 431	99.02 390	80.50 453	98.95 412	93.64 418	94.89 396	98.25 412

Gipuma		90.99 420	90.15 425	93.51 428	98.73 400	90.12 448	93.98 461	99.45 232	79.32 459	92.28 449	94.91 456	69.61 457	97.98 439	87.42 452	95.67 375	92.45 459
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	70.75 22	75.98 434	74.97 435	79.01 450	70.98 473	55.18 475	93.37 462	98.21 436	65.08 467	61.78 468	93.83 458	21.74 475	92.53 462	78.59 460	91.12 437	89.34 463
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		82.80 428	81.52 431	86.66 444	66.61 474	68.44 473	92.79 463	97.92 440	68.96 462	80.04 465	99.85 76	85.77 427	96.15 457	97.86 268	43.89 467	95.39 457

wuyk23d		40.18 435	41.29 440	36.84 451	86.18 470	49.12 476	79.73 464	22.81 476	27.64 468	25.46 471	28.45 471	21.98 474	48.89 470	55.80 469	23.56 470	12.51 468

mmdepth		0.02 442	0.03 445	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.27 473	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

monomultidepth		0.02 442	0.03 445	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.27 473	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

test_blank		0.13 441	0.17 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	1.57 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

uanet_test		0.02 442	0.03 445	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.27 473	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

DCPMVS		0.02 442	0.03 445	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.27 473	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

cdsmvs_eth3d_5k		24.64 438	32.85 441	0.00 454	0.00 477	0.00 479	0.00 465	99.51 142	0.00 472	0.00 473	99.56 270	96.58 169	0.00 473	0.00 472	0.00 471	0.00 469

pcd_1.5k_mvsjas		8.27 440	11.03 443	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.27 473	99.01 18	0.00 473	0.00 472	0.00 471	0.00 469

sosnet-low-res		0.02 442	0.03 445	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.27 473	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

sosnet		0.02 442	0.03 445	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.27 473	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

uncertanet		0.02 442	0.03 445	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.27 473	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

Regformer		0.02 442	0.03 445	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.27 473	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

ab-mvs-re		8.30 439	11.06 442	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	99.58 262	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

uanet		0.02 442	0.03 445	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.27 473	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

WAC-MVS						97.16 319								95.47 390

MSC_two_6792asdad				99.87 19	99.51 213	99.76 44		99.33 304					99.96 39	98.87 146	99.84 96	99.89 27

PC_three_1452									98.18 166	99.84 51	99.70 201	99.31 3	98.52 428	98.30 229	99.80 119	99.81 74

No_MVS				99.87 19	99.51 213	99.76 44		99.33 304					99.96 39	98.87 146	99.84 96	99.89 27

test_one_0601					99.81 52	99.88 9		99.49 176	98.97 69	99.65 125	99.81 120	99.09 14

eth-test2					0.00 477

eth-test					0.00 477

ZD-MVS					99.71 111	99.79 36		99.61 56	96.84 331	99.56 152	99.54 278	98.58 75	99.96 39	96.93 348	99.75 136

IU-MVS					99.84 35	99.88 9		99.32 314	98.30 142	99.84 51				98.86 151	99.85 88	99.89 27

test_241102_TWO								99.48 188	99.08 50	99.88 38	99.81 120	98.94 32	99.96 39	98.91 140	99.84 96	99.88 33

test_241102_ONE					99.84 35	99.90 2		99.48 188	99.07 52	99.91 29	99.74 184	99.20 7	99.76 242

test_0728_THIRD									98.99 63	99.81 63	99.80 137	99.09 14	99.96 39	98.85 153	99.90 55	99.88 33

GSMVS																99.52 210

test_part2					99.81 52	99.83 20				99.77 79

sam_mvs1												94.86 248				99.52 210

sam_mvs												94.72 260

MTGPA								99.47 210

test_post											65.99 468	94.65 267	99.73 253

patchmatchnet-post											98.70 415	94.79 252	99.74 247

gm-plane-assit					98.54 420	92.96 438			94.65 415		99.15 376		99.64 290	97.56 303

test9_res														97.49 309	99.72 142	99.75 104

agg_prior2														97.21 327	99.73 141	99.75 104

agg_prior					99.67 128	99.62 77		99.40 264		98.87 310			99.91 129

TestCases				99.31 183	99.86 22	98.48 251		99.61 56	97.85 222	99.36 207	99.85 76	95.95 195	99.85 180	96.66 361	99.83 107	99.59 190

test_prior				99.68 83	99.67 128	99.48 105		99.56 86					99.83 203			99.74 108

新几何1				99.75 71	99.75 86	99.59 82		99.54 103	96.76 334	99.29 223	99.64 238	98.43 86	99.94 87	96.92 350	99.66 153	99.72 126

旧先验1					99.74 94	99.59 82		99.54 103			99.69 212	98.47 83			99.68 150	99.73 117

原ACMM1				99.65 89	99.73 101	99.33 124		99.47 210	97.46 271	99.12 262	99.66 230	98.67 69	99.91 129	97.70 291	99.69 147	99.71 135

testdata2													99.95 74	96.67 360

segment_acmp												98.96 25

testdata				99.54 119	99.75 86	98.95 187		99.51 142	97.07 312	99.43 182	99.70 201	98.87 40	99.94 87	97.76 282	99.64 156	99.72 126

test12				99.75 71	99.64 153	99.61 79		99.29 327		99.21 245		98.38 92	99.89 157		99.74 139	99.74 108

plane_prior7					99.29 288	97.03 334

plane_prior6					99.27 293	96.98 338						92.71 332

plane_prior5								99.47 210					99.69 275	97.78 278	97.63 307	98.67 349

plane_prior4											99.61 253

plane_prior3						97.00 336			98.69 101	99.11 264

plane_prior1					99.26 296

n2								0.00 478

nn								0.00 478

door-mid								98.05 439

lessismore_v0				97.79 378	98.69 406	95.44 397		94.75 463		95.71 432	99.87 61	88.69 401	99.32 345	95.89 379	94.93 394	98.62 371

LGP-MVS_train				98.49 306	99.33 275	97.05 328		99.55 94	97.46 271	99.24 237	99.83 96	92.58 337	99.72 257	98.09 247	97.51 319	98.68 341

test11								99.35 291

door								97.92 440

HQP5-MVS						96.83 350

BP-MVS														97.19 331

HQP4-MVS										98.66 339			99.64 290			98.64 362

HQP3-MVS								99.39 267							97.58 312

HQP2-MVS												92.47 341

NP-MVS					99.23 304	96.92 346					99.40 324

ACMMP++_ref															97.19 340

ACMMP++															97.43 330

Test By Simon												98.75 58

ITE_SJBPF				98.08 351	99.29 288	96.37 369		98.92 382	98.34 137	98.83 316	99.75 179	91.09 373	99.62 297	95.82 380	97.40 332	98.25 412

DeepMVS_CX				93.34 429	99.29 288	82.27 458		99.22 341	85.15 455	96.33 425	99.05 386	90.97 375	99.73 253	93.57 419	97.77 303	98.01 426

High-resolution multi-view benchmark