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 27	99.48 20	99.54 118	99.76 75	99.42 111	99.90 1	99.55 91	98.56 111	99.78 73	99.70 193	98.65 71	99.79 223	99.65 38	99.78 127	99.41 240

mmtdpeth		96.95 357	96.71 356	97.67 376	99.33 267	94.90 402	99.89 2	99.28 321	98.15 162	99.72 94	98.57 412	86.56 415	99.90 141	99.82 26	89.02 437	98.20 407

SPE-MVS-test		99.49 29	99.48 20	99.54 118	99.78 63	99.30 131	99.89 2	99.58 73	98.56 111	99.73 89	99.69 204	98.55 78	99.82 207	99.69 32	99.85 87	99.48 219

MVSFormer		99.17 99	99.12 91	99.29 185	99.51 205	98.94 186	99.88 4	99.46 213	97.55 253	99.80 66	99.65 224	97.39 122	99.28 342	99.03 114	99.85 87	99.65 151

test_djsdf		98.67 191	98.57 192	98.98 223	98.70 397	98.91 191	99.88 4	99.46 213	97.55 253	99.22 234	99.88 46	95.73 204	99.28 342	99.03 114	97.62 301	98.75 311

OurMVSNet-221017-0		97.88 273	97.77 264	98.19 335	98.71 396	96.53 356	99.88 4	99.00 364	97.79 224	98.78 316	99.94 6	91.68 352	99.35 332	97.21 319	96.99 337	98.69 328

EC-MVSNet		99.44 46	99.39 36	99.58 109	99.56 184	99.49 102	99.88 4	99.58 73	98.38 129	99.73 89	99.69 204	98.20 100	99.70 262	99.64 40	99.82 110	99.54 195

DVP-MVS++		99.59 13	99.50 17	99.88 12	99.51 205	99.88 9	99.87 8	99.51 137	98.99 62	99.88 37	99.81 114	99.27 5	99.96 38	98.85 145	99.80 118	99.81 73

FOURS1					99.91 1	99.93 1	99.87 8	99.56 83	99.10 41	99.81 62

K. test v3		97.10 354	96.79 354	98.01 348	98.72 394	96.33 363	99.87 8	97.05 441	97.59 247	96.16 420	99.80 130	88.71 392	99.04 385	96.69 351	96.55 343	98.65 352

FC-MVSNet-test		98.75 184	98.62 185	99.15 207	99.08 336	99.45 108	99.86 11	99.60 62	98.23 152	98.70 328	99.82 100	96.80 154	99.22 356	99.07 110	96.38 346	98.79 301

v7n		97.87 275	97.52 293	98.92 234	98.76 390	98.58 230	99.84 12	99.46 213	96.20 369	98.91 294	99.70 193	94.89 241	99.44 312	96.03 368	93.89 404	98.75 311

DTE-MVSNet		97.51 330	97.19 339	98.46 306	98.63 403	98.13 263	99.84 12	99.48 181	96.68 331	97.97 382	99.67 217	92.92 315	98.56 419	96.88 344	92.60 422	98.70 324

3Dnovator	97.25 9	99.24 91	99.05 102	99.81 54	99.12 325	99.66 64	99.84 12	99.74 10	99.09 48	98.92 293	99.90 31	95.94 192	99.98 17	98.95 125	99.92 36	99.79 86

FIs		98.78 181	98.63 180	99.23 197	99.18 309	99.54 91	99.83 15	99.59 68	98.28 141	98.79 315	99.81 114	96.75 157	99.37 325	99.08 109	96.38 346	98.78 303

MGCFI-Net		99.01 146	98.85 153	99.50 142	99.42 239	99.26 137	99.82 16	99.48 181	98.60 108	99.28 217	98.81 401	97.04 142	99.76 235	99.29 84	97.87 290	99.47 225

test_fmvs3		92.10 408	91.77 411	93.08 422	96.19 441	86.25 442	99.82 16	98.62 416	96.65 334	95.19 428	96.90 442	55.05 457	95.93 449	96.63 356	90.92 431	97.06 438

jajsoiax		98.43 205	98.28 212	98.88 245	98.60 407	98.43 249	99.82 16	99.53 114	98.19 157	98.63 340	99.80 130	93.22 310	99.44 312	99.22 92	97.50 313	98.77 307

OpenMVS	96.50 16	98.47 202	98.12 223	99.52 132	99.04 344	99.53 94	99.82 16	99.72 11	94.56 408	98.08 375	99.88 46	94.73 253	99.98 17	97.47 304	99.76 133	99.06 282

SDMVSNet		99.11 124	98.90 140	99.75 70	99.81 51	99.59 81	99.81 20	99.65 35	98.78 91	99.64 126	99.88 46	94.56 265	99.93 104	99.67 34	98.26 268	99.72 122

nrg030		98.64 195	98.42 202	99.28 189	99.05 342	99.69 56	99.81 20	99.46 213	98.04 194	99.01 276	99.82 100	96.69 159	99.38 322	99.34 75	94.59 391	98.78 303

HPM-MVS		99.42 51	99.28 65	99.83 50	99.90 4	99.72 50	99.81 20	99.54 100	97.59 247	99.68 102	99.63 236	98.91 37	99.94 86	98.58 186	99.91 43	99.84 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EPP-MVSNet		99.13 111	98.99 120	99.53 126	99.65 145	99.06 164	99.81 20	99.33 296	97.43 270	99.60 140	99.88 46	97.14 134	99.84 185	99.13 102	98.94 219	99.69 135

3Dnovator+	97.12 13	99.18 97	98.97 124	99.82 51	99.17 317	99.68 57	99.81 20	99.51 137	99.20 28	98.72 321	99.89 37	95.68 206	99.97 26	98.86 143	99.86 80	99.81 73

sasdasda		99.02 142	98.86 150	99.51 137	99.42 239	99.32 124	99.80 25	99.48 181	98.63 103	99.31 209	98.81 401	97.09 138	99.75 238	99.27 88	97.90 287	99.47 225

FA-MVS(test-final)		98.75 184	98.53 196	99.41 159	99.55 188	99.05 166	99.80 25	99.01 363	96.59 344	99.58 144	99.59 250	95.39 216	99.90 141	97.78 270	99.49 170	99.28 257

GeoE		98.85 172	98.62 185	99.53 126	99.61 165	99.08 161	99.80 25	99.51 137	97.10 302	99.31 209	99.78 153	95.23 227	99.77 231	98.21 226	99.03 213	99.75 100

canonicalmvs		99.02 142	98.86 150	99.51 137	99.42 239	99.32 124	99.80 25	99.48 181	98.63 103	99.31 209	98.81 401	97.09 138	99.75 238	99.27 88	97.90 287	99.47 225

v8		97.95 264	97.63 283	98.93 232	98.95 359	98.81 210	99.80 25	99.41 249	96.03 383	99.10 259	99.42 308	94.92 239	99.30 340	96.94 339	94.08 401	98.66 350

Vis-MVSNet (Re-imp)		98.87 160	98.72 166	99.31 177	99.71 110	98.88 193	99.80 25	99.44 233	97.91 207	99.36 200	99.78 153	95.49 213	99.43 316	97.91 255	99.11 204	99.62 166

Anonymous20240521		96.20 373	95.89 376	97.13 394	97.72 428	94.96 401	99.79 31	99.29 319	93.01 422	97.20 405	99.03 380	89.69 382	98.36 423	91.16 429	96.13 352	98.07 414

PS-MVSNAJss		98.92 154	98.92 135	98.90 240	98.78 383	98.53 234	99.78 32	99.54 100	98.07 181	99.00 280	99.76 166	99.01 18	99.37 325	99.13 102	97.23 330	98.81 300

PEN-MVS		97.76 296	97.44 309	98.72 271	98.77 388	98.54 233	99.78 32	99.51 137	97.06 306	98.29 365	99.64 230	92.63 328	98.89 410	98.09 239	93.16 414	98.72 317

anonymousdsp		98.44 204	98.28 212	98.94 230	98.50 413	98.96 179	99.77 34	99.50 157	97.07 304	98.87 302	99.77 162	94.76 251	99.28 342	98.66 172	97.60 302	98.57 378

SixPastTwentyTwo		97.50 331	97.33 327	98.03 345	98.65 401	96.23 368	99.77 34	98.68 412	97.14 295	97.90 385	99.93 10	90.45 371	99.18 364	97.00 333	96.43 345	98.67 341

QAPM		98.67 191	98.30 211	99.80 58	99.20 303	99.67 61	99.77 34	99.72 11	94.74 405	98.73 320	99.90 31	95.78 202	99.98 17	96.96 337	99.88 69	99.76 99

SSC-MVS		92.73 407	93.73 402	89.72 432	95.02 451	81.38 452	99.76 37	99.23 331	94.87 402	92.80 439	98.93 393	94.71 255	91.37 456	74.49 455	93.80 405	96.42 442

test_vis3_rt		87.04 415	85.81 418	90.73 429	93.99 453	81.96 450	99.76 37	90.23 464	92.81 425	81.35 452	91.56 452	40.06 461	99.07 382	94.27 402	88.23 439	91.15 452

dcpmvs_2		99.23 92	99.58 7	98.16 337	99.83 43	94.68 406	99.76 37	99.52 119	99.07 51	99.98 11	99.88 46	98.56 77	99.93 104	99.67 34	99.98 4	99.87 37

RRT-MVS		98.91 155	98.75 164	99.39 164	99.46 229	98.61 228	99.76 37	99.50 157	98.06 185	99.81 62	99.88 46	93.91 294	99.94 86	99.11 104	99.27 187	99.61 168

HPM-MVS_fast		99.51 25	99.40 34	99.85 37	99.91 1	99.79 35	99.76 37	99.56 83	97.72 232	99.76 83	99.75 171	99.13 12	99.92 116	99.07 110	99.92 36	99.85 43

lecture		99.60 12	99.50 17	99.89 8	99.89 8	99.90 2	99.75 42	99.59 68	99.06 54	99.88 37	99.85 71	98.41 90	99.96 38	99.28 85	99.84 95	99.83 60

MVSMamba_PlusPlus		99.46 38	99.41 33	99.64 94	99.68 125	99.50 101	99.75 42	99.50 157	98.27 143	99.87 43	99.92 17	98.09 105	99.94 86	99.65 38	99.95 20	99.47 225

v10		97.85 278	97.52 293	98.86 252	98.99 352	98.67 219	99.75 42	99.41 249	95.70 387	98.98 283	99.41 312	94.75 252	99.23 352	96.01 370	94.63 390	98.67 341

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 71	99.89 5	99.75 42	99.56 83	99.02 55	99.88 37	99.85 71	99.18 10	99.96 38	99.22 92	99.92 36	99.90 23
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
IS-MVSNet		99.05 138	98.87 148	99.57 113	99.73 100	99.32 124	99.75 42	99.20 337	98.02 199	99.56 148	99.86 64	96.54 166	99.67 270	98.09 239	99.13 202	99.73 113

test_vis1_n		97.92 268	97.44 309	99.34 169	99.53 196	98.08 266	99.74 47	99.49 169	99.15 31	100.00 1	99.94 6	79.51 445	99.98 17	99.88 23	99.76 133	99.97 4

test_fmvs1_n		98.41 208	98.14 220	99.21 198	99.82 47	97.71 292	99.74 47	99.49 169	99.32 24	99.99 2	99.95 3	85.32 423	99.97 26	99.82 26	99.84 95	99.96 7

balanced_conf03		99.46 38	99.39 36	99.67 83	99.55 188	99.58 86	99.74 47	99.51 137	98.42 126	99.87 43	99.84 86	98.05 108	99.91 128	99.58 44	99.94 28	99.52 202

tttt0517		98.42 206	98.14 220	99.28 189	99.66 138	98.38 252	99.74 47	96.85 443	97.68 238	99.79 68	99.74 176	91.39 360	99.89 156	98.83 151	99.56 163	99.57 189

WB-MVS		93.10 405	94.10 398	90.12 431	95.51 449	81.88 451	99.73 51	99.27 324	95.05 398	93.09 438	98.91 397	94.70 256	91.89 455	76.62 453	94.02 403	96.58 441

test_fmvs2		97.25 348	97.30 330	97.09 396	99.43 237	93.31 427	99.73 51	98.87 386	98.83 81	99.28 217	99.80 130	84.45 428	99.66 273	97.88 257	97.45 318	98.30 400

SD_0403		97.55 325	97.53 292	97.62 378	99.61 165	93.64 424	99.72 53	99.44 233	98.03 196	98.62 343	99.39 320	96.06 184	99.57 294	87.88 442	99.01 216	99.66 146

MonoMVSNet		98.38 212	98.47 200	98.12 342	98.59 409	96.19 370	99.72 53	98.79 397	97.89 209	99.44 173	99.52 278	96.13 181	98.90 409	98.64 174	97.54 308	99.28 257

baseline		99.15 105	99.02 113	99.53 126	99.66 138	99.14 153	99.72 53	99.48 181	98.35 134	99.42 179	99.84 86	96.07 183	99.79 223	99.51 53	99.14 201	99.67 142

RPSCF		98.22 223	98.62 185	96.99 397	99.82 47	91.58 436	99.72 53	99.44 233	96.61 339	99.66 112	99.89 37	95.92 193	99.82 207	97.46 305	99.10 207	99.57 189

CSCG		99.32 74	99.32 50	99.32 175	99.85 28	98.29 254	99.71 57	99.66 28	98.11 173	99.41 183	99.80 130	98.37 93	99.96 38	98.99 118	99.96 15	99.72 122

dmvs_re		98.08 240	98.16 217	97.85 363	99.55 188	94.67 407	99.70 58	98.92 374	98.15 162	99.06 270	99.35 332	93.67 302	99.25 349	97.77 273	97.25 329	99.64 158

WR-MVS_H		98.13 234	97.87 254	98.90 240	99.02 346	98.84 202	99.70 58	99.59 68	97.27 284	98.40 357	99.19 364	95.53 211	99.23 352	98.34 216	93.78 406	98.61 372

mvsmamba		99.06 135	98.96 128	99.36 166	99.47 227	98.64 223	99.70 58	99.05 358	97.61 246	99.65 121	99.83 91	96.54 166	99.92 116	99.19 94	99.62 158	99.51 211

LTVRE_ROB	97.16 12	98.02 252	97.90 249	98.40 316	99.23 296	96.80 345	99.70 58	99.60 62	97.12 298	98.18 372	99.70 193	91.73 351	99.72 250	98.39 209	97.45 318	98.68 333
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		91.90 409	91.26 413	93.84 418	95.52 448	85.92 443	99.69 62	98.53 420	95.31 392	93.87 434	96.37 445	55.33 456	98.27 424	95.70 376	90.98 430	97.32 437

XVS		99.53 23	99.42 28	99.87 18	99.85 28	99.83 20	99.69 62	99.68 20	98.98 65	99.37 194	99.74 176	98.81 47	99.94 86	98.79 156	99.86 80	99.84 50

X-MVStestdata		96.55 365	95.45 384	99.87 18	99.85 28	99.83 20	99.69 62	99.68 20	98.98 65	99.37 194	64.01 461	98.81 47	99.94 86	98.79 156	99.86 80	99.84 50

V42		98.06 242	97.79 259	98.86 252	98.98 355	98.84 202	99.69 62	99.34 288	96.53 346	99.30 213	99.37 326	94.67 258	99.32 337	97.57 294	94.66 389	98.42 392

mPP-MVS		99.44 46	99.30 58	99.86 29	99.88 13	99.79 35	99.69 62	99.48 181	98.12 171	99.50 160	99.75 171	98.78 51	99.97 26	98.57 189	99.89 65	99.83 60

CP-MVS		99.45 42	99.32 50	99.85 37	99.83 43	99.75 45	99.69 62	99.52 119	98.07 181	99.53 155	99.63 236	98.93 36	99.97 26	98.74 160	99.91 43	99.83 60

FE-MVS		98.48 201	98.17 216	99.40 160	99.54 195	98.96 179	99.68 68	98.81 393	95.54 389	99.62 133	99.70 193	93.82 297	99.93 104	97.35 313	99.46 171	99.32 254

PS-CasMVS		97.93 265	97.59 287	98.95 228	98.99 352	99.06 164	99.68 68	99.52 119	97.13 296	98.31 362	99.68 211	92.44 337	99.05 384	98.51 197	94.08 401	98.75 311

Vis-MVSNet		99.12 118	98.97 124	99.56 115	99.78 63	99.10 157	99.68 68	99.66 28	98.49 117	99.86 47	99.87 57	94.77 250	99.84 185	99.19 94	99.41 175	99.74 104
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
KinetiMVS		99.12 118	98.92 135	99.70 80	99.67 127	99.40 114	99.67 71	99.63 42	98.73 95	99.94 25	99.81 114	94.54 268	99.96 38	98.40 208	99.93 30	99.74 104

BP-MVS1		99.12 118	98.94 134	99.65 88	99.51 205	99.30 131	99.67 71	98.92 374	98.48 118	99.84 50	99.69 204	94.96 234	99.92 116	99.62 41	99.79 125	99.71 131

test_vis1_n_1920		98.63 196	98.40 204	99.31 177	99.86 22	97.94 279	99.67 71	99.62 46	99.43 14	99.99 2	99.91 24	87.29 410	100.00 1	99.92 21	99.92 36	99.98 2

EIA-MVS		99.18 97	99.09 97	99.45 150	99.49 219	99.18 145	99.67 71	99.53 114	97.66 241	99.40 188	99.44 304	98.10 104	99.81 212	98.94 126	99.62 158	99.35 249

MSP-MVS		99.42 51	99.27 69	99.88 12	99.89 8	99.80 32	99.67 71	99.50 157	98.70 99	99.77 77	99.49 288	98.21 99	99.95 73	98.46 203	99.77 130	99.88 32
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		99.10 128	98.97 124	99.48 143	99.49 219	99.14 153	99.67 71	99.34 288	97.31 281	99.58 144	99.76 166	97.65 118	99.82 207	98.87 138	99.07 210	99.46 230

CP-MVSNet		98.09 238	97.78 262	99.01 219	98.97 357	99.24 140	99.67 71	99.46 213	97.25 286	98.48 354	99.64 230	93.79 298	99.06 383	98.63 176	94.10 400	98.74 315

MTAPA		99.52 24	99.39 36	99.89 8	99.90 4	99.86 17	99.66 78	99.47 202	98.79 88	99.68 102	99.81 114	98.43 86	99.97 26	98.88 135	99.90 54	99.83 60

HFP-MVS		99.49 29	99.37 40	99.86 29	99.87 17	99.80 32	99.66 78	99.67 23	98.15 162	99.68 102	99.69 204	99.06 16	99.96 38	98.69 168	99.87 72	99.84 50

mvs_tets		98.40 211	98.23 214	98.91 238	98.67 400	98.51 240	99.66 78	99.53 114	98.19 157	98.65 337	99.81 114	92.75 319	99.44 312	99.31 79	97.48 317	98.77 307

EU-MVSNet		97.98 259	98.03 235	97.81 369	98.72 394	96.65 352	99.66 78	99.66 28	98.09 176	98.35 360	99.82 100	95.25 225	98.01 430	97.41 309	95.30 377	98.78 303

ACMMPR		99.49 29	99.36 42	99.86 29	99.87 17	99.79 35	99.66 78	99.67 23	98.15 162	99.67 107	99.69 204	98.95 30	99.96 38	98.69 168	99.87 72	99.84 50

MP-MVS		99.33 72	99.15 87	99.87 18	99.88 13	99.82 26	99.66 78	99.46 213	98.09 176	99.48 164	99.74 176	98.29 96	99.96 38	97.93 254	99.87 72	99.82 66
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
NormalMVS		99.27 83	99.19 83	99.52 132	99.89 8	98.83 205	99.65 84	99.52 119	99.10 41	99.84 50	99.76 166	95.80 200	99.99 4	99.30 82	99.84 95	99.74 104

SymmetryMVS		99.15 105	99.02 113	99.52 132	99.72 104	98.83 205	99.65 84	99.34 288	99.10 41	99.84 50	99.76 166	95.80 200	99.99 4	99.30 82	98.72 240	99.73 113

Elysia		98.88 157	98.65 177	99.58 109	99.58 175	99.34 120	99.65 84	99.52 119	98.26 145	99.83 58	99.87 57	93.37 305	99.90 141	97.81 267	99.91 43	99.49 216

StellarMVS		98.88 157	98.65 177	99.58 109	99.58 175	99.34 120	99.65 84	99.52 119	98.26 145	99.83 58	99.87 57	93.37 305	99.90 141	97.81 267	99.91 43	99.49 216

test_cas_vis1_n_1920		99.16 101	99.01 118	99.61 102	99.81 51	98.86 200	99.65 84	99.64 38	99.39 19	99.97 22	99.94 6	93.20 311	99.98 17	99.55 47	99.91 43	99.99 1

region2R		99.48 33	99.35 44	99.87 18	99.88 13	99.80 32	99.65 84	99.66 28	98.13 169	99.66 112	99.68 211	98.96 25	99.96 38	98.62 177	99.87 72	99.84 50

TranMVSNet+NR-MVSNet		97.93 265	97.66 278	98.76 268	98.78 383	98.62 226	99.65 84	99.49 169	97.76 228	98.49 353	99.60 248	94.23 279	98.97 401	98.00 250	92.90 416	98.70 324

GDP-MVS		99.08 131	98.89 144	99.64 94	99.53 196	99.34 120	99.64 91	99.48 181	98.32 138	99.77 77	99.66 222	95.14 230	99.93 104	98.97 124	99.50 169	99.64 158

ttmdpeth		97.80 292	97.63 283	98.29 326	98.77 388	97.38 303	99.64 91	99.36 276	98.78 91	96.30 418	99.58 254	92.34 340	99.39 320	98.36 214	95.58 370	98.10 412

mvsany_test3		93.77 402	93.45 406	94.74 415	95.78 444	88.01 441	99.64 91	98.25 424	98.28 141	94.31 432	97.97 434	68.89 449	98.51 421	97.50 300	90.37 432	97.71 429

ZNCC-MVS		99.47 36	99.33 48	99.87 18	99.87 17	99.81 30	99.64 91	99.67 23	98.08 180	99.55 152	99.64 230	98.91 37	99.96 38	98.72 163	99.90 54	99.82 66

tfpnnormal		97.84 282	97.47 301	98.98 223	99.20 303	99.22 142	99.64 91	99.61 55	96.32 360	98.27 366	99.70 193	93.35 307	99.44 312	95.69 377	95.40 375	98.27 402

casdiffmvs_mvg		99.15 105	99.02 113	99.55 117	99.66 138	99.09 158	99.64 91	99.56 83	98.26 145	99.45 168	99.87 57	96.03 186	99.81 212	99.54 48	99.15 200	99.73 113
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SR-MVS-dyc-post		99.45 42	99.31 56	99.85 37	99.76 75	99.82 26	99.63 97	99.52 119	98.38 129	99.76 83	99.82 100	98.53 79	99.95 73	98.61 180	99.81 113	99.77 94

RE-MVS-def			99.34 46		99.76 75	99.82 26	99.63 97	99.52 119	98.38 129	99.76 83	99.82 100	98.75 58		98.61 180	99.81 113	99.77 94

TSAR-MVS + MP.		99.58 14	99.50 17	99.81 54	99.91 1	99.66 64	99.63 97	99.39 259	98.91 75	99.78 73	99.85 71	99.36 2	99.94 86	98.84 148	99.88 69	99.82 66
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
Anonymous20231206		96.22 371	96.03 372	96.79 405	97.31 434	94.14 416	99.63 97	99.08 352	96.17 372	97.04 409	99.06 377	93.94 291	97.76 436	86.96 445	95.06 382	98.47 386

APD-MVS_3200maxsize		99.48 33	99.35 44	99.85 37	99.76 75	99.83 20	99.63 97	99.54 100	98.36 133	99.79 68	99.82 100	98.86 41	99.95 73	98.62 177	99.81 113	99.78 92

test0726					99.85 28	99.89 5	99.62 102	99.50 157	99.10 41	99.86 47	99.82 100	98.94 32

EPNet		98.86 163	98.71 168	99.30 182	97.20 436	98.18 259	99.62 102	98.91 379	99.28 26	98.63 340	99.81 114	95.96 189	99.99 4	99.24 91	99.72 141	99.73 113
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t		98.93 153	98.67 172	99.72 79	99.85 28	99.53 94	99.62 102	99.59 68	92.65 427	99.71 96	99.78 153	98.06 107	99.90 141	98.84 148	99.91 43	99.74 104

HY-MVS	97.30 7	98.85 172	98.64 179	99.47 147	99.42 239	99.08 161	99.62 102	99.36 276	97.39 275	99.28 217	99.68 211	96.44 172	99.92 116	98.37 212	98.22 271	99.40 242

ACMMP		99.45 42	99.32 50	99.82 51	99.89 8	99.67 61	99.62 102	99.69 18	98.12 171	99.63 129	99.84 86	98.73 63	99.96 38	98.55 195	99.83 106	99.81 73
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 77	99.19 83	99.64 94	99.82 47	99.23 141	99.62 102	99.55 91	98.94 71	99.63 129	99.95 3	95.82 198	99.94 86	99.37 69	99.97 8	99.73 113
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 94	99.78 63	99.15 152	99.61 108	99.45 224	99.01 57	99.89 34	99.82 100	99.01 18	99.92 116	99.56 46	99.95 20	99.85 43

reproduce_monomvs		97.89 272	97.87 254	97.96 354	99.51 205	95.45 387	99.60 109	99.25 327	99.17 29	98.85 307	99.49 288	89.29 386	99.64 282	99.35 70	96.31 349	98.78 303

test2506		96.81 361	96.65 357	97.29 391	99.74 93	92.21 434	99.60 109	85.06 465	99.13 34	99.77 77	99.93 10	87.82 408	99.85 176	99.38 68	99.38 176	99.80 82

SED-MVS		99.61 8	99.52 12	99.88 12	99.84 34	99.90 2	99.60 109	99.48 181	99.08 49	99.91 28	99.81 114	99.20 7	99.96 38	98.91 132	99.85 87	99.79 86

OPU-MVS				99.64 94	99.56 184	99.72 50	99.60 109				99.70 193	99.27 5	99.42 318	98.24 225	99.80 118	99.79 86

GST-MVS		99.40 59	99.24 74	99.85 37	99.86 22	99.79 35	99.60 109	99.67 23	97.97 202	99.63 129	99.68 211	98.52 80	99.95 73	98.38 210	99.86 80	99.81 73

EI-MVSNet-UG-set		99.58 14	99.57 8	99.64 94	99.78 63	99.14 153	99.60 109	99.45 224	99.01 57	99.90 31	99.83 91	98.98 24	99.93 104	99.59 42	99.95 20	99.86 39

ACMH	97.28 8	98.10 237	97.99 239	98.44 311	99.41 244	96.96 333	99.60 109	99.56 83	98.09 176	98.15 373	99.91 24	90.87 368	99.70 262	98.88 135	97.45 318	98.67 341
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
VortexMVS		98.67 191	98.66 175	98.68 277	99.62 157	97.96 274	99.59 116	99.41 249	98.13 169	99.31 209	99.70 193	95.48 214	99.27 345	99.40 66	97.32 327	98.79 301

guyue		99.16 101	99.04 104	99.52 132	99.69 120	98.92 190	99.59 116	98.81 393	98.73 95	99.90 31	99.87 57	95.34 219	99.88 161	99.66 37	99.81 113	99.74 104

ECVR-MVS		98.04 248	98.05 233	98.00 350	99.74 93	94.37 413	99.59 116	94.98 453	99.13 34	99.66 112	99.93 10	90.67 370	99.84 185	99.40 66	99.38 176	99.80 82

SR-MVS		99.43 49	99.29 62	99.86 29	99.75 85	99.83 20	99.59 116	99.62 46	98.21 155	99.73 89	99.79 146	98.68 67	99.96 38	98.44 205	99.77 130	99.79 86

thres100view900		97.76 296	97.45 304	98.69 276	99.72 104	97.86 283	99.59 116	98.74 403	97.93 205	99.26 227	98.62 409	91.75 349	99.83 198	93.22 414	98.18 276	98.37 398

thres600view7		97.86 277	97.51 295	98.92 234	99.72 104	97.95 277	99.59 116	98.74 403	97.94 204	99.27 222	98.62 409	91.75 349	99.86 170	93.73 409	98.19 275	98.96 293

LCM-MVSNet-Re		97.83 285	98.15 219	96.87 403	99.30 276	92.25 433	99.59 116	98.26 423	97.43 270	96.20 419	99.13 370	96.27 178	98.73 416	98.17 231	98.99 217	99.64 158

baseline1		98.31 217	97.95 244	99.38 165	99.50 217	98.74 214	99.59 116	98.93 371	98.41 127	99.14 251	99.60 248	94.59 263	99.79 223	98.48 199	93.29 411	99.61 168

SteuartSystems-ACMMP		99.54 20	99.42 28	99.87 18	99.82 47	99.81 30	99.59 116	99.51 137	98.62 105	99.79 68	99.83 91	99.28 4	99.97 26	98.48 199	99.90 54	99.84 50
Skip Steuart: Steuart Systems R&D Blog.
CPTT-MVS		99.11 124	98.90 140	99.74 73	99.80 57	99.46 107	99.59 116	99.49 169	97.03 310	99.63 129	99.69 204	97.27 130	99.96 38	97.82 265	99.84 95	99.81 73

icg_test_0403		98.86 163	98.89 144	98.78 266	99.55 188	96.93 334	99.58 126	99.44 233	98.05 187	99.68 102	99.80 130	96.81 153	99.80 219	98.15 234	98.92 222	99.60 171

test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 67	99.38 254	99.37 116	99.58 126	99.62 46	99.41 18	99.87 43	99.92 17	98.81 47	100.00 1	99.97 1	99.93 30	99.94 15

dmvs_testset		95.02 391	96.12 369	91.72 426	99.10 330	80.43 454	99.58 126	97.87 433	97.47 262	95.22 426	98.82 400	93.99 289	95.18 451	88.09 440	94.91 387	99.56 192

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 64	99.84 34	99.44 109	99.58 126	99.69 18	99.43 14	99.98 11	99.91 24	98.62 73	100.00 1	99.97 1	99.95 20	99.90 23

test1111		98.04 248	98.11 224	97.83 366	99.74 93	93.82 418	99.58 126	95.40 452	99.12 39	99.65 121	99.93 10	90.73 369	99.84 185	99.43 64	99.38 176	99.82 66

PGM-MVS		99.45 42	99.31 56	99.86 29	99.87 17	99.78 41	99.58 126	99.65 35	97.84 218	99.71 96	99.80 130	99.12 13	99.97 26	98.33 217	99.87 72	99.83 60

LPG-MVS_test		98.22 223	98.13 222	98.49 298	99.33 267	97.05 322	99.58 126	99.55 91	97.46 263	99.24 229	99.83 91	92.58 329	99.72 250	98.09 239	97.51 311	98.68 333

PHI-MVS		99.30 77	99.17 86	99.70 80	99.56 184	99.52 98	99.58 126	99.80 8	97.12 298	99.62 133	99.73 182	98.58 75	99.90 141	98.61 180	99.91 43	99.68 139

AstraMVS		99.09 129	99.03 107	99.25 192	99.66 138	98.13 263	99.57 134	98.24 425	98.82 82	99.91 28	99.88 46	95.81 199	99.90 141	99.72 29	99.67 151	99.74 104

SF-MVS		99.38 62	99.24 74	99.79 61	99.79 61	99.68 57	99.57 134	99.54 100	97.82 223	99.71 96	99.80 130	98.95 30	99.93 104	98.19 228	99.84 95	99.74 104

DVP-MVS		99.57 17	99.47 22	99.88 12	99.85 28	99.89 5	99.57 134	99.37 275	99.10 41	99.81 62	99.80 130	98.94 32	99.96 38	98.93 129	99.86 80	99.81 73
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				99.91 3	99.84 34	99.89 5	99.57 134	99.51 137					99.96 38	98.93 129	99.86 80	99.88 32

Effi-MVS+-dtu		98.78 181	98.89 144	98.47 305	99.33 267	96.91 339	99.57 134	99.30 315	98.47 119	99.41 183	98.99 386	96.78 155	99.74 240	98.73 162	99.38 176	98.74 315

v2v482		98.06 242	97.77 264	98.92 234	98.90 365	98.82 208	99.57 134	99.36 276	96.65 334	99.19 243	99.35 332	94.20 280	99.25 349	97.72 280	94.97 384	98.69 328

DSMNet-mixed		97.25 348	97.35 321	96.95 400	97.84 424	93.61 425	99.57 134	96.63 447	96.13 377	98.87 302	98.61 411	94.59 263	97.70 437	95.08 391	98.86 230	99.55 193

reproduce_model		99.63 7	99.54 11	99.90 5	99.78 63	99.88 9	99.56 141	99.55 91	99.15 31	99.90 31	99.90 31	99.00 22	99.97 26	99.11 104	99.91 43	99.86 39

MVStest1		96.08 377	95.48 382	97.89 360	98.93 360	96.70 347	99.56 141	99.35 283	92.69 426	91.81 443	99.46 301	89.90 379	98.96 403	95.00 393	92.61 421	98.00 421

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 37	99.86 22	99.61 78	99.56 141	99.63 42	99.48 3	99.98 11	99.83 91	98.75 58	99.99 4	99.97 1	99.96 15	99.94 15

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 37	99.84 34	99.63 75	99.56 141	99.63 42	99.47 4	99.98 11	99.82 100	98.75 58	99.99 4	99.97 1	99.97 8	99.94 15

sd_testset		98.75 184	98.57 192	99.29 185	99.81 51	98.26 256	99.56 141	99.62 46	98.78 91	99.64 126	99.88 46	92.02 343	99.88 161	99.54 48	98.26 268	99.72 122

KD-MVS_self_test		95.00 392	94.34 397	96.96 399	97.07 439	95.39 390	99.56 141	99.44 233	95.11 395	97.13 407	97.32 440	91.86 347	97.27 441	90.35 432	81.23 449	98.23 406

ETV-MVS		99.26 86	99.21 79	99.40 160	99.46 229	99.30 131	99.56 141	99.52 119	98.52 115	99.44 173	99.27 354	98.41 90	99.86 170	99.10 107	99.59 161	99.04 283

SMA-MVS		99.44 46	99.30 58	99.85 37	99.73 100	99.83 20	99.56 141	99.47 202	97.45 266	99.78 73	99.82 100	99.18 10	99.91 128	98.79 156	99.89 65	99.81 73
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		98.87 160	98.72 166	99.31 177	99.86 22	98.48 245	99.56 141	99.61 55	97.85 215	99.36 200	99.85 71	95.95 190	99.85 176	96.66 353	99.83 106	99.59 182

casdiffmvs		99.13 111	98.98 123	99.56 115	99.65 145	99.16 148	99.56 141	99.50 157	98.33 137	99.41 183	99.86 64	95.92 193	99.83 198	99.45 63	99.16 197	99.70 133
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		98.38 212	98.09 228	99.24 195	99.26 288	99.32 124	99.56 141	99.55 91	97.45 266	98.71 322	99.83 91	93.23 308	99.63 288	98.88 135	96.32 348	98.76 309

ACMH+	97.24 10	97.92 268	97.78 262	98.32 323	99.46 229	96.68 351	99.56 141	99.54 100	98.41 127	97.79 391	99.87 57	90.18 377	99.66 273	98.05 247	97.18 333	98.62 363

ACMM	97.58 5	98.37 214	98.34 207	98.48 300	99.41 244	97.10 316	99.56 141	99.45 224	98.53 114	99.04 273	99.85 71	93.00 313	99.71 256	98.74 160	97.45 318	98.64 354
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LS3D		99.27 83	99.12 91	99.74 73	99.18 309	99.75 45	99.56 141	99.57 78	98.45 122	99.49 163	99.85 71	97.77 115	99.94 86	98.33 217	99.84 95	99.52 202

testing3-2		97.84 282	97.70 274	98.24 332	99.53 196	95.37 391	99.55 155	98.67 413	98.46 120	99.27 222	99.34 336	86.58 414	99.83 198	99.32 78	98.63 243	99.52 202

test_fmvsmconf0.01_n		99.22 94	99.03 107	99.79 61	98.42 416	99.48 104	99.55 155	99.51 137	99.39 19	99.78 73	99.93 10	94.80 245	99.95 73	99.93 20	99.95 20	99.94 15

test_fmvs1		98.88 157	98.79 161	99.16 203	99.69 120	97.61 296	99.55 155	99.49 169	99.32 24	99.98 11	99.91 24	91.41 359	99.96 38	99.82 26	99.92 36	99.90 23

v144192		97.92 268	97.60 286	98.87 249	98.83 377	98.65 221	99.55 155	99.34 288	96.20 369	99.32 208	99.40 316	94.36 275	99.26 348	96.37 364	95.03 383	98.70 324

API-MVS		99.04 139	99.03 107	99.06 213	99.40 249	99.31 128	99.55 155	99.56 83	98.54 113	99.33 207	99.39 320	98.76 55	99.78 229	96.98 335	99.78 127	98.07 414

fmvsm_l_conf0.5_n_3		99.61 8	99.51 16	99.92 1	99.84 34	99.82 26	99.54 160	99.66 28	99.46 7	99.98 11	99.89 37	97.27 130	99.99 4	99.97 1	99.95 20	99.95 11

fmvsm_s_conf0.1_n_a		99.26 86	99.06 100	99.85 37	99.52 202	99.62 76	99.54 160	99.62 46	98.69 100	99.99 2	99.96 1	94.47 272	99.94 86	99.88 23	99.92 36	99.98 2

APD_test1		95.87 379	96.49 361	94.00 417	99.53 196	84.01 446	99.54 160	99.32 306	95.91 385	97.99 380	99.85 71	85.49 421	99.88 161	91.96 425	98.84 232	98.12 411

thisisatest0530		98.35 215	98.03 235	99.31 177	99.63 151	98.56 231	99.54 160	96.75 445	97.53 257	99.73 89	99.65 224	91.25 364	99.89 156	98.62 177	99.56 163	99.48 219

MTMP							99.54 160	98.88 384

v1144		97.98 259	97.69 275	98.85 255	98.87 370	98.66 220	99.54 160	99.35 283	96.27 364	99.23 233	99.35 332	94.67 258	99.23 352	96.73 348	95.16 380	98.68 333

v148		97.79 294	97.55 288	98.50 297	98.74 391	97.72 289	99.54 160	99.33 296	96.26 365	98.90 296	99.51 282	94.68 257	99.14 369	97.83 264	93.15 415	98.63 361

CostFormer		97.72 306	97.73 271	97.71 374	99.15 323	94.02 417	99.54 160	99.02 362	94.67 406	99.04 273	99.35 332	92.35 339	99.77 231	98.50 198	97.94 286	99.34 252

MVSTER		98.49 200	98.32 209	99.00 221	99.35 261	99.02 168	99.54 160	99.38 267	97.41 273	99.20 240	99.73 182	93.86 296	99.36 329	98.87 138	97.56 306	98.62 363

fmvsm_s_conf0.1_n		99.29 79	99.10 93	99.86 29	99.70 115	99.65 68	99.53 169	99.62 46	98.74 94	99.99 2	99.95 3	94.53 270	99.94 86	99.89 22	99.96 15	99.97 4

reproduce-ours		99.61 8	99.52 12	99.90 5	99.76 75	99.88 9	99.52 170	99.54 100	99.13 34	99.89 34	99.89 37	98.96 25	99.96 38	99.04 112	99.90 54	99.85 43

our_new_method		99.61 8	99.52 12	99.90 5	99.76 75	99.88 9	99.52 170	99.54 100	99.13 34	99.89 34	99.89 37	98.96 25	99.96 38	99.04 112	99.90 54	99.85 43

fmvsm_s_conf0.5_n_a		99.56 18	99.47 22	99.85 37	99.83 43	99.64 74	99.52 170	99.65 35	99.10 41	99.98 11	99.92 17	97.35 126	99.96 38	99.94 18	99.92 36	99.95 11

MM		99.40 59	99.28 65	99.74 73	99.67 127	99.31 128	99.52 170	98.87 386	99.55 1	99.74 87	99.80 130	96.47 169	99.98 17	99.97 1	99.97 8	99.94 15

patch_mono-2		99.26 86	99.62 5	98.16 337	99.81 51	94.59 409	99.52 170	99.64 38	99.33 23	99.73 89	99.90 31	99.00 22	99.99 4	99.69 32	99.98 4	99.89 26

Fast-Effi-MVS+-dtu		98.77 183	98.83 157	98.60 282	99.41 244	96.99 329	99.52 170	99.49 169	98.11 173	99.24 229	99.34 336	96.96 146	99.79 223	97.95 253	99.45 172	99.02 286

Fast-Effi-MVS+		98.70 188	98.43 201	99.51 137	99.51 205	99.28 134	99.52 170	99.47 202	96.11 378	99.01 276	99.34 336	96.20 180	99.84 185	97.88 257	98.82 234	99.39 243

v1921920		97.80 292	97.45 304	98.84 256	98.80 379	98.53 234	99.52 170	99.34 288	96.15 375	99.24 229	99.47 297	93.98 290	99.29 341	95.40 385	95.13 381	98.69 328

MIMVSNet1		95.51 385	95.04 390	96.92 402	97.38 431	95.60 380	99.52 170	99.50 157	93.65 416	96.97 411	99.17 365	85.28 424	96.56 446	88.36 439	95.55 372	98.60 375

mamba_test_0407		99.13 111	99.03 107	99.43 157	99.62 157	98.88 193	99.51 179	99.50 157	98.14 167	99.37 194	99.85 71	96.85 148	99.83 198	99.19 94	99.25 190	99.60 171

fmvsm_s_conf0.5_n_8		99.54 20	99.42 28	99.89 8	99.83 43	99.74 48	99.51 179	99.62 46	99.46 7	99.99 2	99.90 31	96.60 162	99.98 17	99.95 13	99.95 20	99.96 7

fmvsm_s_conf0.5_n		99.51 25	99.40 34	99.85 37	99.84 34	99.65 68	99.51 179	99.67 23	99.13 34	99.98 11	99.92 17	96.60 162	99.96 38	99.95 13	99.96 15	99.95 11

UniMVSNet_ETH3D		97.32 345	96.81 353	98.87 249	99.40 249	97.46 300	99.51 179	99.53 114	95.86 386	98.54 350	99.77 162	82.44 437	99.66 273	98.68 170	97.52 310	99.50 215

alignmvs		98.81 176	98.56 194	99.58 109	99.43 237	99.42 111	99.51 179	98.96 369	98.61 106	99.35 203	98.92 396	94.78 247	99.77 231	99.35 70	98.11 281	99.54 195

v1192		97.81 290	97.44 309	98.91 238	98.88 367	98.68 218	99.51 179	99.34 288	96.18 371	99.20 240	99.34 336	94.03 288	99.36 329	95.32 387	95.18 379	98.69 328

test20.03		96.12 375	95.96 374	96.63 406	97.44 430	95.45 387	99.51 179	99.38 267	96.55 345	96.16 420	99.25 357	93.76 300	96.17 447	87.35 444	94.22 397	98.27 402

mvs_anonymous		99.03 141	98.99 120	99.16 203	99.38 254	98.52 238	99.51 179	99.38 267	97.79 224	99.38 192	99.81 114	97.30 128	99.45 307	99.35 70	98.99 217	99.51 211

TAMVS		99.12 118	99.08 98	99.24 195	99.46 229	98.55 232	99.51 179	99.46 213	98.09 176	99.45 168	99.82 100	98.34 94	99.51 301	98.70 165	98.93 220	99.67 142

icg_test_0407		98.86 163	98.91 138	98.72 271	99.55 188	96.93 334	99.50 188	99.44 233	98.05 187	99.66 112	99.80 130	97.13 135	99.65 278	98.15 234	98.92 222	99.60 171

fmvsm_s_conf0.5_n_6		99.54 20	99.44 27	99.85 37	99.51 205	99.67 61	99.50 188	99.64 38	99.43 14	99.98 11	99.78 153	97.26 132	99.95 73	99.95 13	99.93 30	99.92 21

test_fmvsmconf0.1_n		99.55 19	99.45 26	99.86 29	99.44 236	99.65 68	99.50 188	99.61 55	99.45 11	99.87 43	99.92 17	97.31 127	99.97 26	99.95 13	99.99 1	99.97 4

test_yl		98.86 163	98.63 180	99.54 118	99.49 219	99.18 145	99.50 188	99.07 355	98.22 153	99.61 137	99.51 282	95.37 217	99.84 185	98.60 183	98.33 262	99.59 182

DCV-MVSNet		98.86 163	98.63 180	99.54 118	99.49 219	99.18 145	99.50 188	99.07 355	98.22 153	99.61 137	99.51 282	95.37 217	99.84 185	98.60 183	98.33 262	99.59 182

tfpn200view9		97.72 306	97.38 317	98.72 271	99.69 120	97.96 274	99.50 188	98.73 409	97.83 219	99.17 248	98.45 416	91.67 353	99.83 198	93.22 414	98.18 276	98.37 398

UA-Net		99.42 51	99.29 62	99.80 58	99.62 157	99.55 89	99.50 188	99.70 15	98.79 88	99.77 77	99.96 1	97.45 121	99.96 38	98.92 131	99.90 54	99.89 26

pm-mvs1		97.68 314	97.28 333	98.88 245	99.06 339	98.62 226	99.50 188	99.45 224	96.32 360	97.87 387	99.79 146	92.47 333	99.35 332	97.54 297	93.54 408	98.67 341

EI-MVSNet		98.67 191	98.67 172	98.68 277	99.35 261	97.97 272	99.50 188	99.38 267	96.93 319	99.20 240	99.83 91	97.87 111	99.36 329	98.38 210	97.56 306	98.71 319

CVMVSNet		98.57 198	98.67 172	98.30 325	99.35 261	95.59 381	99.50 188	99.55 91	98.60 108	99.39 190	99.83 91	94.48 271	99.45 307	98.75 159	98.56 250	99.85 43

VPA-MVSNet		98.29 220	97.95 244	99.30 182	99.16 319	99.54 91	99.50 188	99.58 73	98.27 143	99.35 203	99.37 326	92.53 331	99.65 278	99.35 70	94.46 392	98.72 317

thres400		97.77 295	97.38 317	98.92 234	99.69 120	97.96 274	99.50 188	98.73 409	97.83 219	99.17 248	98.45 416	91.67 353	99.83 198	93.22 414	98.18 276	98.96 293

APD-MVS		99.27 83	99.08 98	99.84 49	99.75 85	99.79 35	99.50 188	99.50 157	97.16 294	99.77 77	99.82 100	98.78 51	99.94 86	97.56 295	99.86 80	99.80 82
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mamba_0404		99.16 101	99.06 100	99.44 154	99.65 145	98.96 179	99.49 201	99.50 157	98.14 167	99.62 133	99.85 71	96.85 148	99.85 176	99.19 94	99.26 189	99.52 202

fmvsm_s_conf0.5_n_4		99.36 67	99.24 74	99.73 76	99.78 63	99.53 94	99.49 201	99.60 62	99.42 17	99.99 2	99.86 64	95.15 229	99.95 73	99.95 13	99.89 65	99.73 113

test_vis1_rt		95.81 381	95.65 380	96.32 410	99.67 127	91.35 437	99.49 201	96.74 446	98.25 148	95.24 425	98.10 431	74.96 446	99.90 141	99.53 50	98.85 231	97.70 431

TransMVSNet (Re)		97.15 352	96.58 358	98.86 252	99.12 325	98.85 201	99.49 201	98.91 379	95.48 390	97.16 406	99.80 130	93.38 304	99.11 378	94.16 405	91.73 425	98.62 363

UniMVSNet (Re)		98.29 220	98.00 238	99.13 208	99.00 349	99.36 119	99.49 201	99.51 137	97.95 203	98.97 285	99.13 370	96.30 177	99.38 322	98.36 214	93.34 410	98.66 350

EPMVS		97.82 288	97.65 279	98.35 320	98.88 367	95.98 373	99.49 201	94.71 455	97.57 250	99.26 227	99.48 294	92.46 336	99.71 256	97.87 259	99.08 209	99.35 249

fmvsm_s_conf0.5_n_9		99.41 55	99.28 65	99.81 54	99.84 34	99.52 98	99.48 207	99.62 46	99.46 7	99.99 2	99.92 17	95.24 226	99.96 38	99.97 1	99.97 8	99.96 7

SSC-MVS3.2		97.34 343	97.15 340	97.93 356	99.02 346	95.76 378	99.48 207	99.58 73	97.62 245	99.09 262	99.53 274	87.95 404	99.27 345	96.42 360	95.66 368	98.75 311

fmvsm_s_conf0.5_n_3		99.37 63	99.20 81	99.87 18	99.75 85	99.70 54	99.48 207	99.66 28	99.45 11	99.99 2	99.93 10	94.64 262	99.97 26	99.94 18	99.97 8	99.95 11

test_fmvsmconf_n		99.70 3	99.64 4	99.87 18	99.80 57	99.66 64	99.48 207	99.64 38	99.45 11	99.92 27	99.92 17	98.62 73	99.99 4	99.96 11	99.99 1	99.96 7

Anonymous20231211		97.88 273	97.54 291	98.90 240	99.71 110	98.53 234	99.48 207	99.57 78	94.16 411	98.81 311	99.68 211	93.23 308	99.42 318	98.84 148	94.42 394	98.76 309

v1240		97.69 311	97.32 328	98.79 264	98.85 374	98.43 249	99.48 207	99.36 276	96.11 378	99.27 222	99.36 329	93.76 300	99.24 351	94.46 399	95.23 378	98.70 324

VPNet		97.84 282	97.44 309	99.01 219	99.21 301	98.94 186	99.48 207	99.57 78	98.38 129	99.28 217	99.73 182	88.89 389	99.39 320	99.19 94	93.27 412	98.71 319

UniMVSNet_NR-MVSNet		98.22 223	97.97 241	98.96 226	98.92 362	98.98 172	99.48 207	99.53 114	97.76 228	98.71 322	99.46 301	96.43 173	99.22 356	98.57 189	92.87 418	98.69 328

TDRefinement		95.42 387	94.57 395	97.97 352	89.83 458	96.11 372	99.48 207	98.75 400	96.74 327	96.68 414	99.88 46	88.65 395	99.71 256	98.37 212	82.74 447	98.09 413

ACMMP_NAP		99.47 36	99.34 46	99.88 12	99.87 17	99.86 17	99.47 216	99.48 181	98.05 187	99.76 83	99.86 64	98.82 46	99.93 104	98.82 155	99.91 43	99.84 50

NR-MVSNet		97.97 262	97.61 285	99.02 218	98.87 370	99.26 137	99.47 216	99.42 246	97.63 243	97.08 408	99.50 285	95.07 232	99.13 372	97.86 260	93.59 407	98.68 333

PVSNet_Blended_VisFu		99.36 67	99.28 65	99.61 102	99.86 22	99.07 163	99.47 216	99.93 2	97.66 241	99.71 96	99.86 64	97.73 116	99.96 38	99.47 61	99.82 110	99.79 86

LuminaMVS		99.23 92	99.10 93	99.61 102	99.35 261	99.31 128	99.46 219	99.13 346	98.61 106	99.86 47	99.89 37	96.41 174	99.91 128	99.67 34	99.51 167	99.63 163

fmvsm_s_conf0.1_n_2		99.37 63	99.22 78	99.81 54	99.77 71	99.75 45	99.46 219	99.60 62	99.47 4	99.98 11	99.94 6	94.98 233	99.95 73	99.97 1	99.79 125	99.73 113

SD-MVS		99.41 55	99.52 12	99.05 215	99.74 93	99.68 57	99.46 219	99.52 119	99.11 40	99.88 37	99.91 24	99.43 1	97.70 437	98.72 163	99.93 30	99.77 94
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		97.28 346	96.76 355	98.82 258	99.37 257	98.07 267	99.45 222	99.36 276	97.56 252	97.89 386	98.95 391	83.70 431	98.82 411	96.03 368	98.56 250	99.58 186

tt0805		97.97 262	97.77 264	98.57 287	99.59 173	96.61 354	99.45 222	99.08 352	98.21 155	98.88 299	99.80 130	88.66 394	99.70 262	98.58 186	97.72 296	99.39 243

tpm2		97.44 338	97.34 324	97.74 373	99.15 323	94.36 414	99.45 222	98.94 370	93.45 420	98.90 296	99.44 304	91.35 361	99.59 292	97.31 314	98.07 282	99.29 256

FMVSNet2		97.72 306	97.36 319	98.80 263	99.51 205	98.84 202	99.45 222	99.42 246	96.49 348	98.86 306	99.29 349	90.26 373	98.98 394	96.44 359	96.56 342	98.58 377

CDS-MVSNet		99.09 129	99.03 107	99.25 192	99.42 239	98.73 215	99.45 222	99.46 213	98.11 173	99.46 167	99.77 162	98.01 109	99.37 325	98.70 165	98.92 222	99.66 146
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MAR-MVS		98.86 163	98.63 180	99.54 118	99.37 257	99.66 64	99.45 222	99.54 100	96.61 339	99.01 276	99.40 316	97.09 138	99.86 170	97.68 285	99.53 166	99.10 271
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 74	99.13 89	99.89 8	99.80 57	99.77 42	99.44 228	99.58 73	99.47 4	99.99 2	99.93 10	94.04 287	99.96 38	99.96 11	99.93 30	99.93 20

UGNet		98.87 160	98.69 170	99.40 160	99.22 300	98.72 216	99.44 228	99.68 20	99.24 27	99.18 247	99.42 308	92.74 321	99.96 38	99.34 75	99.94 28	99.53 201
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		98.86 163	98.63 180	99.54 118	99.64 148	99.19 143	99.44 228	99.54 100	97.77 227	99.30 213	99.81 114	94.20 280	99.93 104	99.17 100	98.82 234	99.49 216

test_0402		96.64 364	96.24 366	97.85 363	98.85 374	96.43 360	99.44 228	99.26 325	93.52 417	96.98 410	99.52 278	88.52 398	99.20 363	92.58 424	97.50 313	97.93 426

ACMP	97.20 11	98.06 242	97.94 246	98.45 308	99.37 257	97.01 327	99.44 228	99.49 169	97.54 256	98.45 355	99.79 146	91.95 345	99.72 250	97.91 255	97.49 316	98.62 363
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
GG-mvs-BLEND				98.45 308	98.55 411	98.16 260	99.43 233	93.68 457		97.23 402	98.46 415	89.30 385	99.22 356	95.43 384	98.22 271	97.98 423

HPM-MVS++		99.39 61	99.23 77	99.87 18	99.75 85	99.84 19	99.43 233	99.51 137	98.68 102	99.27 222	99.53 274	98.64 72	99.96 38	98.44 205	99.80 118	99.79 86

tpm cat1		97.39 340	97.36 319	97.50 385	99.17 317	93.73 420	99.43 233	99.31 310	91.27 431	98.71 322	99.08 374	94.31 278	99.77 231	96.41 362	98.50 254	99.00 287

tpm		97.67 317	97.55 288	98.03 345	99.02 346	95.01 399	99.43 233	98.54 419	96.44 354	99.12 254	99.34 336	91.83 348	99.60 291	97.75 276	96.46 344	99.48 219

GBi-Net		97.68 314	97.48 298	98.29 326	99.51 205	97.26 309	99.43 233	99.48 181	96.49 348	99.07 265	99.32 344	90.26 373	98.98 394	97.10 327	96.65 339	98.62 363

test1		97.68 314	97.48 298	98.29 326	99.51 205	97.26 309	99.43 233	99.48 181	96.49 348	99.07 265	99.32 344	90.26 373	98.98 394	97.10 327	96.65 339	98.62 363

FMVSNet1		96.84 360	96.36 364	98.29 326	99.32 274	97.26 309	99.43 233	99.48 181	95.11 395	98.55 349	99.32 344	83.95 430	98.98 394	95.81 373	96.26 350	98.62 363

fmvsm_s_conf0.5_n_7		99.34 70	99.29 62	99.48 143	99.70 115	98.63 224	99.42 240	99.63 42	99.46 7	99.98 11	99.88 46	95.59 209	99.96 38	99.97 1	99.98 4	99.85 43

fmvsm_s_conf0.5_n_5		99.37 63	99.21 79	99.86 29	99.80 57	99.68 57	99.42 240	99.61 55	99.37 21	99.97 22	99.86 64	94.96 234	99.99 4	99.97 1	99.93 30	99.92 21

mamv4		99.33 72	99.42 28	99.07 211	99.67 127	97.73 287	99.42 240	99.60 62	98.15 162	99.94 25	99.91 24	98.42 88	99.94 86	99.72 29	99.96 15	99.54 195

testgi		97.65 319	97.50 296	98.13 341	99.36 260	96.45 359	99.42 240	99.48 181	97.76 228	97.87 387	99.45 303	91.09 365	98.81 412	94.53 398	98.52 253	99.13 270

F-COLMAP		99.19 95	99.04 104	99.64 94	99.78 63	99.27 136	99.42 240	99.54 100	97.29 283	99.41 183	99.59 250	98.42 88	99.93 104	98.19 228	99.69 146	99.73 113

Anonymous202405211		98.30 219	97.98 240	99.26 191	99.57 180	98.16 260	99.41 245	98.55 418	96.03 383	99.19 243	99.74 176	91.87 346	99.92 116	99.16 101	98.29 267	99.70 133

MSLP-MVS++		99.46 38	99.47 22	99.44 154	99.60 171	99.16 148	99.41 245	99.71 13	98.98 65	99.45 168	99.78 153	99.19 9	99.54 299	99.28 85	99.84 95	99.63 163

VNet		99.11 124	98.90 140	99.73 76	99.52 202	99.56 87	99.41 245	99.39 259	99.01 57	99.74 87	99.78 153	95.56 210	99.92 116	99.52 52	98.18 276	99.72 122

baseline2		97.87 275	97.55 288	98.82 258	99.18 309	98.02 269	99.41 245	96.58 449	96.97 313	96.51 415	99.17 365	93.43 303	99.57 294	97.71 281	99.03 213	98.86 297

DU-MVS		98.08 240	97.79 259	98.96 226	98.87 370	98.98 172	99.41 245	99.45 224	97.87 211	98.71 322	99.50 285	94.82 243	99.22 356	98.57 189	92.87 418	98.68 333

Baseline_NR-MVSNet		97.76 296	97.45 304	98.68 277	99.09 333	98.29 254	99.41 245	98.85 388	95.65 388	98.63 340	99.67 217	94.82 243	99.10 380	98.07 246	92.89 417	98.64 354

XVG-ACMP-BASELINE		97.83 285	97.71 273	98.20 334	99.11 327	96.33 363	99.41 245	99.52 119	98.06 185	99.05 272	99.50 285	89.64 383	99.73 246	97.73 278	97.38 325	98.53 380

DP-MVS		99.16 101	98.95 132	99.78 64	99.77 71	99.53 94	99.41 245	99.50 157	97.03 310	99.04 273	99.88 46	97.39 122	99.92 116	98.66 172	99.90 54	99.87 37

9.14			99.10 93		99.72 104		99.40 253	99.51 137	97.53 257	99.64 126	99.78 153	98.84 44	99.91 128	97.63 286	99.82 110

D2MVS		98.41 208	98.50 198	98.15 340	99.26 288	96.62 353	99.40 253	99.61 55	97.71 233	98.98 283	99.36 329	96.04 185	99.67 270	98.70 165	97.41 323	98.15 410

Anonymous20240529		98.09 238	97.68 276	99.34 169	99.66 138	98.44 248	99.40 253	99.43 244	93.67 415	99.22 234	99.89 37	90.23 376	99.93 104	99.26 90	98.33 262	99.66 146

FMVSNet3		98.03 250	97.76 268	98.84 256	99.39 252	98.98 172	99.40 253	99.38 267	96.67 332	99.07 265	99.28 351	92.93 314	98.98 394	97.10 327	96.65 339	98.56 379

LFMVS		97.90 271	97.35 321	99.54 118	99.52 202	99.01 170	99.39 257	98.24 425	97.10 302	99.65 121	99.79 146	84.79 426	99.91 128	99.28 85	98.38 259	99.69 135

HQP_MVS		98.27 222	98.22 215	98.44 311	99.29 280	96.97 331	99.39 257	99.47 202	98.97 68	99.11 256	99.61 245	92.71 324	99.69 267	97.78 270	97.63 299	98.67 341

plane_prior2							99.39 257		98.97 68

CHOSEN 1792x2688		99.19 95	99.10 93	99.45 150	99.89 8	98.52 238	99.39 257	99.94 1	98.73 95	99.11 256	99.89 37	95.50 212	99.94 86	99.50 54	99.97 8	99.89 26

PAPM_NR		99.04 139	98.84 155	99.66 84	99.74 93	99.44 109	99.39 257	99.38 267	97.70 236	99.28 217	99.28 351	98.34 94	99.85 176	96.96 337	99.45 172	99.69 135

gg-mvs-nofinetune		96.17 374	95.32 386	98.73 269	98.79 380	98.14 262	99.38 262	94.09 456	91.07 434	98.07 378	91.04 454	89.62 384	99.35 332	96.75 347	99.09 208	98.68 333

VDDNet		97.55 325	97.02 347	99.16 203	99.49 219	98.12 265	99.38 262	99.30 315	95.35 391	99.68 102	99.90 31	82.62 436	99.93 104	99.31 79	98.13 280	99.42 237

MVS_0304		99.15 105	98.96 128	99.73 76	98.92 362	99.37 116	99.37 264	96.92 442	99.51 2	99.66 112	99.78 153	96.69 159	99.97 26	99.84 25	99.97 8	99.84 50

pmmvs6		96.53 366	96.09 371	97.82 368	98.69 398	95.47 386	99.37 264	99.47 202	93.46 419	97.41 396	99.78 153	87.06 412	99.33 335	96.92 342	92.70 420	98.65 352

PM-MVS		92.96 406	92.23 410	95.14 414	95.61 445	89.98 440	99.37 264	98.21 427	94.80 404	95.04 430	97.69 435	65.06 450	97.90 433	94.30 400	89.98 435	97.54 435

WTY-MVS		99.06 135	98.88 147	99.61 102	99.62 157	99.16 148	99.37 264	99.56 83	98.04 194	99.53 155	99.62 241	96.84 152	99.94 86	98.85 145	98.49 255	99.72 122

IterMVS-LS		98.46 203	98.42 202	98.58 286	99.59 173	98.00 270	99.37 264	99.43 244	96.94 318	99.07 265	99.59 250	97.87 111	99.03 387	98.32 219	95.62 369	98.71 319
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
h-mvs33		97.70 310	97.28 333	98.97 225	99.70 115	97.27 307	99.36 269	99.45 224	98.94 71	99.66 112	99.64 230	94.93 237	99.99 4	99.48 59	84.36 444	99.65 151

DPE-MVS		99.46 38	99.32 50	99.91 3	99.78 63	99.88 9	99.36 269	99.51 137	98.73 95	99.88 37	99.84 86	98.72 64	99.96 38	98.16 232	99.87 72	99.88 32
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UnsupCasMVSNet_eth		96.44 368	96.12 369	97.40 388	98.65 401	95.65 379	99.36 269	99.51 137	97.13 296	96.04 422	98.99 386	88.40 399	98.17 426	96.71 349	90.27 433	98.40 395

sss		99.17 99	99.05 102	99.53 126	99.62 157	98.97 175	99.36 269	99.62 46	97.83 219	99.67 107	99.65 224	97.37 125	99.95 73	99.19 94	99.19 196	99.68 139

DeepC-MVS_fast	98.69 1	99.49 29	99.39 36	99.77 67	99.63 151	99.59 81	99.36 269	99.46 213	99.07 51	99.79 68	99.82 100	98.85 42	99.92 116	98.68 170	99.87 72	99.82 66
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 90	99.14 88	99.59 106	99.41 244	99.16 148	99.35 274	99.57 78	98.82 82	99.51 159	99.61 245	96.46 170	99.95 73	99.59 42	99.98 4	99.65 151

pmmvs-eth3d		95.34 389	94.73 392	97.15 392	95.53 447	95.94 374	99.35 274	99.10 349	95.13 393	93.55 435	97.54 436	88.15 403	97.91 432	94.58 397	89.69 436	97.61 432

MDTV_nov1_ep13_2view						95.18 396	99.35 274		96.84 323	99.58 144		95.19 228		97.82 265		99.46 230

VDD-MVS		97.73 304	97.35 321	98.88 245	99.47 227	97.12 315	99.34 277	98.85 388	98.19 157	99.67 107	99.85 71	82.98 434	99.92 116	99.49 58	98.32 266	99.60 171

COLMAP_ROB	97.56 6	98.86 163	98.75 164	99.17 202	99.88 13	98.53 234	99.34 277	99.59 68	97.55 253	98.70 328	99.89 37	95.83 197	99.90 141	98.10 238	99.90 54	99.08 276
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
viewmambaseed2359dif		99.01 146	98.90 140	99.32 175	99.58 175	98.51 240	99.33 279	99.54 100	97.85 215	99.44 173	99.85 71	96.01 187	99.79 223	99.41 65	99.13 202	99.67 142

myMVS_eth3d28		97.69 311	97.34 324	98.73 269	99.27 285	97.52 298	99.33 279	98.78 398	98.03 196	98.82 310	98.49 414	86.64 413	99.46 305	98.44 205	98.24 270	99.23 264

EGC-MVSNET		82.80 419	77.86 425	97.62 378	97.91 422	96.12 371	99.33 279	99.28 321	8.40 462	25.05 463	99.27 354	84.11 429	99.33 335	89.20 435	98.22 271	97.42 436

ETVMVS		97.50 331	96.90 351	99.29 185	99.23 296	98.78 213	99.32 282	98.90 381	97.52 259	98.56 348	98.09 432	84.72 427	99.69 267	97.86 260	97.88 289	99.39 243

FMVSNet5		96.43 369	96.19 368	97.15 392	99.11 327	95.89 375	99.32 282	99.52 119	94.47 410	98.34 361	99.07 375	87.54 409	97.07 442	92.61 423	95.72 366	98.47 386

dp		97.75 300	97.80 258	97.59 382	99.10 330	93.71 421	99.32 282	98.88 384	96.48 351	99.08 264	99.55 265	92.67 327	99.82 207	96.52 357	98.58 247	99.24 263

tpmvs		97.98 259	98.02 237	97.84 365	99.04 344	94.73 404	99.31 285	99.20 337	96.10 382	98.76 318	99.42 308	94.94 236	99.81 212	96.97 336	98.45 256	98.97 291

tpmrst		98.33 216	98.48 199	97.90 359	99.16 319	94.78 403	99.31 285	99.11 348	97.27 284	99.45 168	99.59 250	95.33 220	99.84 185	98.48 199	98.61 244	99.09 275

testing99		97.36 341	96.94 350	98.63 280	99.18 309	96.70 347	99.30 287	98.93 371	97.71 233	98.23 367	98.26 424	84.92 425	99.84 185	98.04 248	97.85 292	99.35 249

MP-MVS-pluss		99.37 63	99.20 81	99.88 12	99.90 4	99.87 16	99.30 287	99.52 119	97.18 292	99.60 140	99.79 146	98.79 50	99.95 73	98.83 151	99.91 43	99.83 60
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
NCCC		99.34 70	99.19 83	99.79 61	99.61 165	99.65 68	99.30 287	99.48 181	98.86 77	99.21 237	99.63 236	98.72 64	99.90 141	98.25 224	99.63 157	99.80 82

JIA-IIPM		97.50 331	97.02 347	98.93 232	98.73 392	97.80 285	99.30 287	98.97 367	91.73 430	98.91 294	94.86 448	95.10 231	99.71 256	97.58 290	97.98 284	99.28 257

BH-RMVSNet		98.41 208	98.08 229	99.40 160	99.41 244	98.83 205	99.30 287	98.77 399	97.70 236	98.94 291	99.65 224	92.91 317	99.74 240	96.52 357	99.55 165	99.64 158

testing11		97.50 331	97.10 344	98.71 274	99.20 303	96.91 339	99.29 292	98.82 391	97.89 209	98.21 370	98.40 418	85.63 420	99.83 198	98.45 204	98.04 283	99.37 247

Syy-MVS		97.09 355	97.14 341	96.95 400	99.00 349	92.73 431	99.29 292	99.39 259	97.06 306	97.41 396	98.15 427	93.92 293	98.68 417	91.71 426	98.34 260	99.45 233

myMVS_eth3d		96.89 358	96.37 363	98.43 313	99.00 349	97.16 313	99.29 292	99.39 259	97.06 306	97.41 396	98.15 427	83.46 433	98.68 417	95.27 388	98.34 260	99.45 233

MCST-MVS		99.43 49	99.30 58	99.82 51	99.79 61	99.74 48	99.29 292	99.40 256	98.79 88	99.52 157	99.62 241	98.91 37	99.90 141	98.64 174	99.75 135	99.82 66

LF4IMVS		97.52 328	97.46 303	97.70 375	98.98 355	95.55 382	99.29 292	98.82 391	98.07 181	98.66 331	99.64 230	89.97 378	99.61 290	97.01 332	96.68 338	97.94 425

hse-mvs2		97.50 331	97.14 341	98.59 283	99.49 219	97.05 322	99.28 297	99.22 333	98.94 71	99.66 112	99.42 308	94.93 237	99.65 278	99.48 59	83.80 446	99.08 276

OPM-MVS		98.19 227	98.10 225	98.45 308	98.88 367	97.07 320	99.28 297	99.38 267	98.57 110	99.22 234	99.81 114	92.12 341	99.66 273	98.08 243	97.54 308	98.61 372
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
diffmvs		99.14 109	99.02 113	99.51 137	99.61 165	98.96 179	99.28 297	99.49 169	98.46 120	99.72 94	99.71 189	96.50 168	99.88 161	99.31 79	99.11 204	99.67 142
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		98.86 163	98.80 158	99.03 217	99.76 75	98.79 211	99.28 297	99.91 3	97.42 272	99.67 107	99.37 326	97.53 119	99.88 161	98.98 119	97.29 328	98.42 392

OMC-MVS		99.08 131	99.04 104	99.20 199	99.67 127	98.22 258	99.28 297	99.52 119	98.07 181	99.66 112	99.81 114	97.79 114	99.78 229	97.79 269	99.81 113	99.60 171

testing222		97.16 351	96.50 360	99.16 203	99.16 319	98.47 247	99.27 302	98.66 414	97.71 233	98.23 367	98.15 427	82.28 439	99.84 185	97.36 312	97.66 298	99.18 267

AUN-MVS		96.88 359	96.31 365	98.59 283	99.48 226	97.04 325	99.27 302	99.22 333	97.44 269	98.51 351	99.41 312	91.97 344	99.66 273	97.71 281	83.83 445	99.07 281

pmmvs5		97.52 328	97.30 330	98.16 337	98.57 410	96.73 346	99.27 302	98.90 381	96.14 376	98.37 359	99.53 274	91.54 358	99.14 369	97.51 299	95.87 361	98.63 361

1314		98.68 190	98.54 195	99.11 209	98.89 366	98.65 221	99.27 302	99.49 169	96.89 320	97.99 380	99.56 262	97.72 117	99.83 198	97.74 277	99.27 187	98.84 299

MVS		97.28 346	96.55 359	99.48 143	98.78 383	98.95 183	99.27 302	99.39 259	83.53 448	98.08 375	99.54 270	96.97 145	99.87 167	94.23 403	99.16 197	99.63 163

BH-untuned		98.42 206	98.36 205	98.59 283	99.49 219	96.70 347	99.27 302	99.13 346	97.24 288	98.80 313	99.38 323	95.75 203	99.74 240	97.07 331	99.16 197	99.33 253

MDTV_nov1_ep13			98.32 209		99.11 327	94.44 411	99.27 302	98.74 403	97.51 260	99.40 188	99.62 241	94.78 247	99.76 235	97.59 289	98.81 236

DP-MVS Recon		99.12 118	98.95 132	99.65 88	99.74 93	99.70 54	99.27 302	99.57 78	96.40 358	99.42 179	99.68 211	98.75 58	99.80 219	97.98 251	99.72 141	99.44 235

PatchmatchNet		98.31 217	98.36 205	98.19 335	99.16 319	95.32 392	99.27 302	98.92 374	97.37 276	99.37 194	99.58 254	94.90 240	99.70 262	97.43 308	99.21 194	99.54 195
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thres200		97.61 322	97.28 333	98.62 281	99.64 148	98.03 268	99.26 311	98.74 403	97.68 238	99.09 262	98.32 422	91.66 355	99.81 212	92.88 419	98.22 271	98.03 417

CNVR-MVS		99.42 51	99.30 58	99.78 64	99.62 157	99.71 52	99.26 311	99.52 119	98.82 82	99.39 190	99.71 189	98.96 25	99.85 176	98.59 185	99.80 118	99.77 94

mamba_0408		99.08 131	98.96 128	99.44 154	99.62 157	98.88 193	99.25 313	99.47 202	98.05 187	99.37 194	99.81 114	96.85 148	99.85 176	98.98 119	99.25 190	99.60 171

mamba_test_0407_2		99.06 135	98.96 128	99.35 168	99.62 157	98.88 193	99.25 313	99.47 202	98.05 187	99.37 194	99.81 114	96.85 148	99.58 293	98.98 119	99.25 190	99.60 171

tt0320		95.71 384	95.07 388	97.62 378	99.05 342	95.02 398	99.25 313	99.52 119	86.81 443	97.97 382	99.72 186	83.58 432	99.15 367	96.38 363	93.35 409	98.68 333

1112_ss		98.98 149	98.77 162	99.59 106	99.68 125	99.02 168	99.25 313	99.48 181	97.23 289	99.13 252	99.58 254	96.93 147	99.90 141	98.87 138	98.78 237	99.84 50

TAPA-MVS	97.07 15	97.74 302	97.34 324	98.94 230	99.70 115	97.53 297	99.25 313	99.51 137	91.90 429	99.30 213	99.63 236	98.78 51	99.64 282	88.09 440	99.87 72	99.65 151
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
UWE-MVS-28		97.36 341	97.24 337	97.75 371	98.84 376	94.44 411	99.24 318	97.58 438	97.98 201	99.00 280	99.00 384	91.35 361	99.53 300	93.75 408	98.39 258	99.27 261

UBG		97.85 278	97.48 298	98.95 228	99.25 292	97.64 294	99.24 318	98.74 403	97.90 208	98.64 338	98.20 426	88.65 395	99.81 212	98.27 222	98.40 257	99.42 237

PLC	97.94 4	99.02 142	98.85 153	99.53 126	99.66 138	99.01 170	99.24 318	99.52 119	96.85 322	99.27 222	99.48 294	98.25 98	99.91 128	97.76 274	99.62 158	99.65 151
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test_post1							99.23 321				65.14 460	94.18 283	99.71 256	97.58 290

ADS-MVSNet2		98.02 252	98.07 232	97.87 361	99.33 267	95.19 395	99.23 321	99.08 352	96.24 366	99.10 259	99.67 217	94.11 284	98.93 406	96.81 345	99.05 211	99.48 219

ADS-MVSNet		98.20 226	98.08 229	98.56 291	99.33 267	96.48 358	99.23 321	99.15 343	96.24 366	99.10 259	99.67 217	94.11 284	99.71 256	96.81 345	99.05 211	99.48 219

EPNet_dtu		98.03 250	97.96 242	98.23 333	98.27 418	95.54 384	99.23 321	98.75 400	99.02 55	97.82 389	99.71 189	96.11 182	99.48 302	93.04 417	99.65 154	99.69 135
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		98.17 230	97.93 247	98.87 249	99.18 309	98.49 243	99.22 325	99.33 296	96.96 314	99.56 148	99.38 323	94.33 276	99.00 392	94.83 396	98.58 247	99.14 268

RPMNet		96.72 362	95.90 375	99.19 200	99.18 309	98.49 243	99.22 325	99.52 119	88.72 441	99.56 148	97.38 438	94.08 286	99.95 73	86.87 446	98.58 247	99.14 268

sc_t1		95.75 382	95.05 389	97.87 361	98.83 377	94.61 408	99.21 327	99.45 224	87.45 442	97.97 382	99.85 71	81.19 442	99.43 316	98.27 222	93.20 413	99.57 189

WBMVS		97.74 302	97.50 296	98.46 306	99.24 294	97.43 301	99.21 327	99.42 246	97.45 266	98.96 287	99.41 312	88.83 390	99.23 352	98.94 126	96.02 354	98.71 319

plane_prior						96.97 331	99.21 327		98.45 122						97.60 302

ICG_test_0404		98.53 199	98.52 197	98.55 293	99.55 188	96.93 334	99.20 330	99.44 233	98.05 187	98.96 287	99.80 130	94.66 260	99.13 372	98.15 234	98.92 222	99.60 171

tt0320-xc		95.31 390	94.59 394	97.45 386	98.92 362	94.73 404	99.20 330	99.31 310	86.74 444	97.23 402	99.72 186	81.14 443	98.95 404	97.08 330	91.98 424	98.67 341

testing91		97.44 338	97.02 347	98.71 274	99.18 309	96.89 341	99.19 332	99.04 359	97.78 226	98.31 362	98.29 423	85.41 422	99.85 176	98.01 249	97.95 285	99.39 243

WR-MVS		98.06 242	97.73 271	99.06 213	98.86 373	99.25 139	99.19 332	99.35 283	97.30 282	98.66 331	99.43 306	93.94 291	99.21 361	98.58 186	94.28 396	98.71 319

new-patchmatchnet		94.48 398	94.08 399	95.67 413	95.08 450	92.41 432	99.18 334	99.28 321	94.55 409	93.49 436	97.37 439	87.86 407	97.01 443	91.57 427	88.36 438	97.61 432

AdaColmap		99.01 146	98.80 158	99.66 84	99.56 184	99.54 91	99.18 334	99.70 15	98.18 160	99.35 203	99.63 236	96.32 176	99.90 141	97.48 302	99.77 130	99.55 193

EG-PatchMatch MVS		95.97 378	95.69 379	96.81 404	97.78 425	92.79 430	99.16 336	98.93 371	96.16 373	94.08 433	99.22 360	82.72 435	99.47 303	95.67 379	97.50 313	98.17 408

PatchT		97.03 356	96.44 362	98.79 264	98.99 352	98.34 253	99.16 336	99.07 355	92.13 428	99.52 157	97.31 441	94.54 268	98.98 394	88.54 438	98.73 239	99.03 284

CNLPA		99.14 109	98.99 120	99.59 106	99.58 175	99.41 113	99.16 336	99.44 233	98.45 122	99.19 243	99.49 288	98.08 106	99.89 156	97.73 278	99.75 135	99.48 219

MDA-MVSNet-bldmvs		94.96 393	93.98 400	97.92 357	98.24 419	97.27 307	99.15 339	99.33 296	93.80 414	80.09 455	99.03 380	88.31 400	97.86 434	93.49 412	94.36 395	98.62 363

CDPH-MVS		99.13 111	98.91 138	99.80 58	99.75 85	99.71 52	99.15 339	99.41 249	96.60 342	99.60 140	99.55 265	98.83 45	99.90 141	97.48 302	99.83 106	99.78 92

save fliter					99.76 75	99.59 81	99.14 341	99.40 256	99.00 60

WB-MVSnew		97.65 319	97.65 279	97.63 377	98.78 383	97.62 295	99.13 342	98.33 422	97.36 277	99.07 265	98.94 392	95.64 208	99.15 367	92.95 418	98.68 242	96.12 446

testf1		90.42 413	90.68 414	89.65 433	97.78 425	73.97 461	99.13 342	98.81 393	89.62 436	91.80 444	98.93 393	62.23 453	98.80 413	86.61 447	91.17 427	96.19 444

APD_test2		90.42 413	90.68 414	89.65 433	97.78 425	73.97 461	99.13 342	98.81 393	89.62 436	91.80 444	98.93 393	62.23 453	98.80 413	86.61 447	91.17 427	96.19 444

xiu_mvs_v1_base_debu		99.29 79	99.27 69	99.34 169	99.63 151	98.97 175	99.12 345	99.51 137	98.86 77	99.84 50	99.47 297	98.18 101	99.99 4	99.50 54	99.31 184	99.08 276

xiu_mvs_v1_base		99.29 79	99.27 69	99.34 169	99.63 151	98.97 175	99.12 345	99.51 137	98.86 77	99.84 50	99.47 297	98.18 101	99.99 4	99.50 54	99.31 184	99.08 276

xiu_mvs_v1_base_debi		99.29 79	99.27 69	99.34 169	99.63 151	98.97 175	99.12 345	99.51 137	98.86 77	99.84 50	99.47 297	98.18 101	99.99 4	99.50 54	99.31 184	99.08 276

XVG-OURS-SEG-HR		98.69 189	98.62 185	98.89 243	99.71 110	97.74 286	99.12 345	99.54 100	98.44 125	99.42 179	99.71 189	94.20 280	99.92 116	98.54 196	98.90 228	99.00 287

jason		99.13 111	99.03 107	99.45 150	99.46 229	98.87 197	99.12 345	99.26 325	98.03 196	99.79 68	99.65 224	97.02 143	99.85 176	99.02 116	99.90 54	99.65 151
jason: jason.
N_pmnet		94.95 394	95.83 377	92.31 424	98.47 414	79.33 456	99.12 345	92.81 462	93.87 413	97.68 392	99.13 370	93.87 295	99.01 391	91.38 428	96.19 351	98.59 376

MDA-MVSNet_test_wron		95.45 386	94.60 393	98.01 348	98.16 420	97.21 312	99.11 351	99.24 330	93.49 418	80.73 454	98.98 388	93.02 312	98.18 425	94.22 404	94.45 393	98.64 354

Patchmtry		97.75 300	97.40 316	98.81 261	99.10 330	98.87 197	99.11 351	99.33 296	94.83 403	98.81 311	99.38 323	94.33 276	99.02 389	96.10 366	95.57 371	98.53 380

YYNet1		95.36 388	94.51 396	97.92 357	97.89 423	97.10 316	99.10 353	99.23 331	93.26 421	80.77 453	99.04 379	92.81 318	98.02 429	94.30 400	94.18 398	98.64 354

CANet_DTU		98.97 151	98.87 148	99.25 192	99.33 267	98.42 251	99.08 354	99.30 315	99.16 30	99.43 176	99.75 171	95.27 222	99.97 26	98.56 192	99.95 20	99.36 248

icg_test_0407_2		98.79 180	98.86 150	98.57 287	99.55 188	96.93 334	99.07 355	99.44 233	98.05 187	99.66 112	99.80 130	97.13 135	99.18 364	98.15 234	98.92 222	99.60 171

SCA		98.19 227	98.16 217	98.27 331	99.30 276	95.55 382	99.07 355	98.97 367	97.57 250	99.43 176	99.57 259	92.72 322	99.74 240	97.58 290	99.20 195	99.52 202

TSAR-MVS + GP.		99.36 67	99.36 42	99.36 166	99.67 127	98.61 228	99.07 355	99.33 296	99.00 60	99.82 61	99.81 114	99.06 16	99.84 185	99.09 108	99.42 174	99.65 151

MG-MVS		99.13 111	99.02 113	99.45 150	99.57 180	98.63 224	99.07 355	99.34 288	98.99 62	99.61 137	99.82 100	97.98 110	99.87 167	97.00 333	99.80 118	99.85 43

PatchMatch-RL		98.84 175	98.62 185	99.52 132	99.71 110	99.28 134	99.06 359	99.77 9	97.74 231	99.50 160	99.53 274	95.41 215	99.84 185	97.17 326	99.64 155	99.44 235

OpenMVS_ROB	92.34 20	94.38 399	93.70 405	96.41 409	97.38 431	93.17 428	99.06 359	98.75 400	86.58 445	94.84 431	98.26 424	81.53 440	99.32 337	89.01 436	97.87 290	96.76 439

TEST9					99.67 127	99.65 68	99.05 361	99.41 249	96.22 368	98.95 289	99.49 288	98.77 54	99.91 128

train_agg		99.02 142	98.77 162	99.77 67	99.67 127	99.65 68	99.05 361	99.41 249	96.28 362	98.95 289	99.49 288	98.76 55	99.91 128	97.63 286	99.72 141	99.75 100

lupinMVS		99.13 111	99.01 118	99.46 149	99.51 205	98.94 186	99.05 361	99.16 342	97.86 212	99.80 66	99.56 262	97.39 122	99.86 170	98.94 126	99.85 87	99.58 186

DELS-MVS		99.48 33	99.42 28	99.65 88	99.72 104	99.40 114	99.05 361	99.66 28	99.14 33	99.57 147	99.80 130	98.46 84	99.94 86	99.57 45	99.84 95	99.60 171
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		96.38 370	96.03 372	97.41 387	98.13 421	95.16 397	99.05 361	99.20 337	93.94 412	97.39 399	98.79 404	91.61 357	99.04 385	90.43 431	95.77 363	98.05 416

Patchmatch-test		97.93 265	97.65 279	98.77 267	99.18 309	97.07 320	99.03 366	99.14 345	96.16 373	98.74 319	99.57 259	94.56 265	99.72 250	93.36 413	99.11 204	99.52 202

test_8					99.67 127	99.61 78	99.03 366	99.41 249	96.28 362	98.93 292	99.48 294	98.76 55	99.91 128

Test_1112_low_res		98.89 156	98.66 175	99.57 113	99.69 120	98.95 183	99.03 366	99.47 202	96.98 312	99.15 250	99.23 359	96.77 156	99.89 156	98.83 151	98.78 237	99.86 39

IterMVS-SCA-FT		97.82 288	97.75 269	98.06 344	99.57 180	96.36 362	99.02 369	99.49 169	97.18 292	98.71 322	99.72 186	92.72 322	99.14 369	97.44 307	95.86 362	98.67 341

xiu_mvs_v2_base		99.26 86	99.25 73	99.29 185	99.53 196	98.91 191	99.02 369	99.45 224	98.80 87	99.71 96	99.26 356	98.94 32	99.98 17	99.34 75	99.23 193	98.98 290

MIMVSNet		97.73 304	97.45 304	98.57 287	99.45 235	97.50 299	99.02 369	98.98 366	96.11 378	99.41 183	99.14 369	90.28 372	98.74 415	95.74 375	98.93 220	99.47 225

IterMVS		97.83 285	97.77 264	98.02 347	99.58 175	96.27 366	99.02 369	99.48 181	97.22 290	98.71 322	99.70 193	92.75 319	99.13 372	97.46 305	96.00 356	98.67 341
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		99.11 124	98.92 135	99.65 88	99.90 4	99.37 116	99.02 369	99.91 3	97.67 240	99.59 143	99.75 171	95.90 195	99.73 246	99.53 50	99.02 215	99.86 39

UWE-MVS		97.58 324	97.29 332	98.48 300	99.09 333	96.25 367	99.01 374	96.61 448	97.86 212	99.19 243	99.01 383	88.72 391	99.90 141	97.38 311	98.69 241	99.28 257

新几何2							99.01 374

BH-w/o		98.00 257	97.89 253	98.32 323	99.35 261	96.20 369	99.01 374	98.90 381	96.42 356	98.38 358	99.00 384	95.26 224	99.72 250	96.06 367	98.61 244	99.03 284

test_prior4						99.56 87	98.99 377

无先验							98.99 377	99.51 137	96.89 320				99.93 104	97.53 298		99.72 122

pmmvs4		98.13 234	97.90 249	98.81 261	98.61 406	98.87 197	98.99 377	99.21 336	96.44 354	99.06 270	99.58 254	95.90 195	99.11 378	97.18 325	96.11 353	98.46 389

HQP-NCC					99.19 306		98.98 380		98.24 149	98.66 331

ACMP_Plane					99.19 306		98.98 380		98.24 149	98.66 331

HQP-MVS		98.02 252	97.90 249	98.37 319	99.19 306	96.83 342	98.98 380	99.39 259	98.24 149	98.66 331	99.40 316	92.47 333	99.64 282	97.19 323	97.58 304	98.64 354

PS-MVSNAJ		99.32 74	99.32 50	99.30 182	99.57 180	98.94 186	98.97 383	99.46 213	98.92 74	99.71 96	99.24 358	99.01 18	99.98 17	99.35 70	99.66 152	98.97 291

MVP-Stereo		97.81 290	97.75 269	97.99 351	97.53 429	96.60 355	98.96 384	98.85 388	97.22 290	97.23 402	99.36 329	95.28 221	99.46 305	95.51 381	99.78 127	97.92 427
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test_prior2							98.96 384		98.34 135	99.01 276	99.52 278	98.68 67		97.96 252	99.74 138

旧先验2							98.96 384		96.70 330	99.47 165			99.94 86	98.19 228

原ACMM2							98.95 387

MVS_111021_HR		99.41 55	99.32 50	99.66 84	99.72 104	99.47 106	98.95 387	99.85 6	98.82 82	99.54 153	99.73 182	98.51 81	99.74 240	98.91 132	99.88 69	99.77 94

mvsany_test1		99.50 27	99.46 25	99.62 101	99.61 165	99.09 158	98.94 389	99.48 181	99.10 41	99.96 24	99.91 24	98.85 42	99.96 38	99.72 29	99.58 162	99.82 66

MVS_111021_LR		99.41 55	99.33 48	99.65 88	99.77 71	99.51 100	98.94 389	99.85 6	98.82 82	99.65 121	99.74 176	98.51 81	99.80 219	98.83 151	99.89 65	99.64 158

pmmvs3		94.09 401	93.25 407	96.60 407	94.76 452	94.49 410	98.92 391	98.18 429	89.66 435	96.48 416	98.06 433	86.28 416	97.33 440	89.68 434	87.20 441	97.97 424

XVG-OURS		98.73 187	98.68 171	98.88 245	99.70 115	97.73 287	98.92 391	99.55 91	98.52 115	99.45 168	99.84 86	95.27 222	99.91 128	98.08 243	98.84 232	99.00 287

test222					99.75 85	99.49 102	98.91 393	99.49 169	96.42 356	99.34 206	99.65 224	98.28 97			99.69 146	99.72 122

PMMVS2		86.87 416	85.37 420	91.35 428	90.21 457	83.80 447	98.89 394	97.45 440	83.13 449	91.67 446	95.03 446	48.49 459	94.70 452	85.86 449	77.62 451	95.54 447

miper_lstm_enhance		98.00 257	97.91 248	98.28 330	99.34 266	97.43 301	98.88 395	99.36 276	96.48 351	98.80 313	99.55 265	95.98 188	98.91 407	97.27 316	95.50 374	98.51 382

MVS-HIRNet		95.75 382	95.16 387	97.51 384	99.30 276	93.69 422	98.88 395	95.78 450	85.09 447	98.78 316	92.65 450	91.29 363	99.37 325	94.85 395	99.85 87	99.46 230

TR-MVS		97.76 296	97.41 315	98.82 258	99.06 339	97.87 281	98.87 397	98.56 417	96.63 338	98.68 330	99.22 360	92.49 332	99.65 278	95.40 385	97.79 294	98.95 295

testdata1							98.85 398		98.32 138

ET-MVSNet_ETH3D		96.49 367	95.64 381	99.05 215	99.53 196	98.82 208	98.84 399	97.51 439	97.63 243	84.77 448	99.21 363	92.09 342	98.91 407	98.98 119	92.21 423	99.41 240

our_test_3		97.65 319	97.68 276	97.55 383	98.62 404	94.97 400	98.84 399	99.30 315	96.83 325	98.19 371	99.34 336	97.01 144	99.02 389	95.00 393	96.01 355	98.64 354

MS-PatchMatch		97.24 350	97.32 328	96.99 397	98.45 415	93.51 426	98.82 401	99.32 306	97.41 273	98.13 374	99.30 347	88.99 388	99.56 296	95.68 378	99.80 118	97.90 428

c3_l		98.12 236	98.04 234	98.38 318	99.30 276	97.69 293	98.81 402	99.33 296	96.67 332	98.83 308	99.34 336	97.11 137	98.99 393	97.58 290	95.34 376	98.48 384

ppachtmachnet_test		97.49 336	97.45 304	97.61 381	98.62 404	95.24 393	98.80 403	99.46 213	96.11 378	98.22 369	99.62 241	96.45 171	98.97 401	93.77 407	95.97 360	98.61 372

PAPR		98.63 196	98.34 207	99.51 137	99.40 249	99.03 167	98.80 403	99.36 276	96.33 359	99.00 280	99.12 373	98.46 84	99.84 185	95.23 389	99.37 183	99.66 146

test0.0.03 1		97.71 309	97.42 314	98.56 291	98.41 417	97.82 284	98.78 405	98.63 415	97.34 278	98.05 379	98.98 388	94.45 273	98.98 394	95.04 392	97.15 334	98.89 296

PVSNet_Blended		99.08 131	98.97 124	99.42 158	99.76 75	98.79 211	98.78 405	99.91 3	96.74 327	99.67 107	99.49 288	97.53 119	99.88 161	98.98 119	99.85 87	99.60 171

PMMVS		98.80 179	98.62 185	99.34 169	99.27 285	98.70 217	98.76 407	99.31 310	97.34 278	99.21 237	99.07 375	97.20 133	99.82 207	98.56 192	98.87 229	99.52 202

test123		39.01 428	42.50 430	28.53 443	39.17 466	20.91 468	98.75 408	19.17 468	19.83 461	38.57 460	66.67 458	33.16 463	15.42 462	37.50 462	29.66 460	49.26 457

MSDG		98.98 149	98.80 158	99.53 126	99.76 75	99.19 143	98.75 408	99.55 91	97.25 286	99.47 165	99.77 162	97.82 113	99.87 167	96.93 340	99.90 54	99.54 195

CLD-MVS		98.16 231	98.10 225	98.33 321	99.29 280	96.82 344	98.75 408	99.44 233	97.83 219	99.13 252	99.55 265	92.92 315	99.67 270	98.32 219	97.69 297	98.48 384
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		98.18 229	98.10 225	98.41 314	99.23 296	97.72 289	98.72 411	99.31 310	96.60 342	98.88 299	99.29 349	97.29 129	99.13 372	97.60 288	95.99 357	98.38 397

cl____		98.01 255	97.84 257	98.55 293	99.25 292	97.97 272	98.71 412	99.34 288	96.47 353	98.59 347	99.54 270	95.65 207	99.21 361	97.21 319	95.77 363	98.46 389

DIV-MVS_self_test		98.01 255	97.85 256	98.48 300	99.24 294	97.95 277	98.71 412	99.35 283	96.50 347	98.60 346	99.54 270	95.72 205	99.03 387	97.21 319	95.77 363	98.46 389

test-LLR		98.06 242	97.90 249	98.55 293	98.79 380	97.10 316	98.67 414	97.75 434	97.34 278	98.61 344	98.85 398	94.45 273	99.45 307	97.25 317	99.38 176	99.10 271

TESTMET0.1,1		97.55 325	97.27 336	98.40 316	98.93 360	96.53 356	98.67 414	97.61 437	96.96 314	98.64 338	99.28 351	88.63 397	99.45 307	97.30 315	99.38 176	99.21 266

test-mter		97.49 336	97.13 343	98.55 293	98.79 380	97.10 316	98.67 414	97.75 434	96.65 334	98.61 344	98.85 398	88.23 401	99.45 307	97.25 317	99.38 176	99.10 271

mvs5depth		96.66 363	96.22 367	97.97 352	97.00 440	96.28 365	98.66 417	99.03 361	96.61 339	96.93 412	99.79 146	87.20 411	99.47 303	96.65 355	94.13 399	98.16 409

IB-MVS	95.67 18	96.22 371	95.44 385	98.57 287	99.21 301	96.70 347	98.65 418	97.74 436	96.71 329	97.27 401	98.54 413	86.03 417	99.92 116	98.47 202	86.30 442	99.10 271
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		98.95 152	98.71 168	99.66 84	99.63 151	99.55 89	98.64 419	99.10 349	97.93 205	99.42 179	99.55 265	98.67 69	99.80 219	95.80 374	99.68 149	99.61 168

thisisatest0515		98.14 233	97.79 259	99.19 200	99.50 217	98.50 242	98.61 420	96.82 444	96.95 316	99.54 153	99.43 306	91.66 355	99.86 170	98.08 243	99.51 167	99.22 265

DeepPCF-MVS	98.18 3	98.81 176	99.37 40	97.12 395	99.60 171	91.75 435	98.61 420	99.44 233	99.35 22	99.83 58	99.85 71	98.70 66	99.81 212	99.02 116	99.91 43	99.81 73

cl22		97.85 278	97.64 282	98.48 300	99.09 333	97.87 281	98.60 422	99.33 296	97.11 301	98.87 302	99.22 360	92.38 338	99.17 366	98.21 226	95.99 357	98.42 392

GA-MVS		97.85 278	97.47 301	99.00 221	99.38 254	97.99 271	98.57 423	99.15 343	97.04 309	98.90 296	99.30 347	89.83 380	99.38 322	96.70 350	98.33 262	99.62 166

TinyColmap		97.12 353	96.89 352	97.83 366	99.07 337	95.52 385	98.57 423	98.74 403	97.58 249	97.81 390	99.79 146	88.16 402	99.56 296	95.10 390	97.21 331	98.39 396

eth_miper_zixun_eth		98.05 247	97.96 242	98.33 321	99.26 288	97.38 303	98.56 425	99.31 310	96.65 334	98.88 299	99.52 278	96.58 164	99.12 377	97.39 310	95.53 373	98.47 386

CMPMVS	69.68 23	94.13 400	94.90 391	91.84 425	97.24 435	80.01 455	98.52 426	99.48 181	89.01 439	91.99 442	99.67 217	85.67 419	99.13 372	95.44 383	97.03 336	96.39 443
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
USDC		97.34 343	97.20 338	97.75 371	99.07 337	95.20 394	98.51 427	99.04 359	97.99 200	98.31 362	99.86 64	89.02 387	99.55 298	95.67 379	97.36 326	98.49 383

ambc				93.06 423	92.68 454	82.36 448	98.47 428	98.73 409		95.09 429	97.41 437	55.55 455	99.10 380	96.42 360	91.32 426	97.71 429

miper_enhance_ethall		98.16 231	98.08 229	98.41 314	98.96 358	97.72 289	98.45 429	99.32 306	96.95 316	98.97 285	99.17 365	97.06 141	99.22 356	97.86 260	95.99 357	98.29 401

CHOSEN 280x420		99.12 118	99.13 89	99.08 210	99.66 138	97.89 280	98.43 430	99.71 13	98.88 76	99.62 133	99.76 166	96.63 161	99.70 262	99.46 62	99.99 1	99.66 146

testmvs		39.17 427	43.78 429	25.37 444	36.04 467	16.84 469	98.36 431	26.56 466	20.06 460	38.51 461	67.32 457	29.64 464	15.30 463	37.59 461	39.90 459	43.98 458

FPMVS		84.93 418	85.65 419	82.75 439	86.77 460	63.39 465	98.35 432	98.92 374	74.11 451	83.39 450	98.98 388	50.85 458	92.40 454	84.54 450	94.97 384	92.46 449

KD-MVS_2432*1600		94.62 395	93.72 403	97.31 389	97.19 437	95.82 376	98.34 433	99.20 337	95.00 399	97.57 393	98.35 420	87.95 404	98.10 427	92.87 420	77.00 452	98.01 418

miper_refine_blended		94.62 395	93.72 403	97.31 389	97.19 437	95.82 376	98.34 433	99.20 337	95.00 399	97.57 393	98.35 420	87.95 404	98.10 427	92.87 420	77.00 452	98.01 418

CL-MVSNet_self_test		94.49 397	93.97 401	96.08 411	96.16 442	93.67 423	98.33 435	99.38 267	95.13 393	97.33 400	98.15 427	92.69 326	96.57 445	88.67 437	79.87 450	97.99 422

PVSNet	96.02 17	98.85 172	98.84 155	98.89 243	99.73 100	97.28 306	98.32 436	99.60 62	97.86 212	99.50 160	99.57 259	96.75 157	99.86 170	98.56 192	99.70 145	99.54 195

PAPM		97.59 323	97.09 345	99.07 211	99.06 339	98.26 256	98.30 437	99.10 349	94.88 401	98.08 375	99.34 336	96.27 178	99.64 282	89.87 433	98.92 222	99.31 255

Patchmatch-RL test		95.84 380	95.81 378	95.95 412	95.61 445	90.57 438	98.24 438	98.39 421	95.10 397	95.20 427	98.67 408	94.78 247	97.77 435	96.28 365	90.02 434	99.51 211

UnsupCasMVSNet_bld		93.53 403	92.51 409	96.58 408	97.38 431	93.82 418	98.24 438	99.48 181	91.10 433	93.10 437	96.66 443	74.89 447	98.37 422	94.03 406	87.71 440	97.56 434

LCM-MVSNet		86.80 417	85.22 421	91.53 427	87.81 459	80.96 453	98.23 440	98.99 365	71.05 452	90.13 447	96.51 444	48.45 460	96.88 444	90.51 430	85.30 443	96.76 439

cascas		97.69 311	97.43 313	98.48 300	98.60 407	97.30 305	98.18 441	99.39 259	92.96 423	98.41 356	98.78 405	93.77 299	99.27 345	98.16 232	98.61 244	98.86 297

kuosan		90.92 412	90.11 417	93.34 420	98.78 383	85.59 445	98.15 442	93.16 460	89.37 438	92.07 441	98.38 419	81.48 441	95.19 450	62.54 459	97.04 335	99.25 262

Effi-MVS+		98.81 176	98.59 191	99.48 143	99.46 229	99.12 156	98.08 443	99.50 157	97.50 261	99.38 192	99.41 312	96.37 175	99.81 212	99.11 104	98.54 252	99.51 211

PCF-MVS	97.08 14	97.66 318	97.06 346	99.47 147	99.61 165	99.09 158	98.04 444	99.25 327	91.24 432	98.51 351	99.70 193	94.55 267	99.91 128	92.76 422	99.85 87	99.42 237
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet_0	94.43 19	96.09 376	95.47 383	97.94 355	99.31 275	94.34 415	97.81 445	99.70 15	97.12 298	97.46 395	98.75 406	89.71 381	99.79 223	97.69 284	81.69 448	99.68 139

E-PMN		80.61 421	79.88 423	82.81 438	90.75 456	76.38 459	97.69 446	95.76 451	66.44 456	83.52 449	92.25 451	62.54 452	87.16 458	68.53 457	61.40 455	84.89 456

dongtai		93.26 404	92.93 408	94.25 416	99.39 252	85.68 444	97.68 447	93.27 458	92.87 424	96.85 413	99.39 320	82.33 438	97.48 439	76.78 452	97.80 293	99.58 186

ANet_high		77.30 423	74.86 427	84.62 437	75.88 463	77.61 457	97.63 448	93.15 461	88.81 440	64.27 458	89.29 455	36.51 462	83.93 460	75.89 454	52.31 457	92.33 451

EMVS		80.02 422	79.22 424	82.43 440	91.19 455	76.40 458	97.55 449	92.49 463	66.36 457	83.01 451	91.27 453	64.63 451	85.79 459	65.82 458	60.65 456	85.08 455

MVE	76.82 21	76.91 424	74.31 428	84.70 436	85.38 462	76.05 460	96.88 450	93.17 459	67.39 455	71.28 457	89.01 456	21.66 467	87.69 457	71.74 456	72.29 454	90.35 453
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		91.10 410	91.36 412	90.31 430	95.85 443	73.72 463	94.89 451	99.25 327	68.39 454	95.82 423	99.02 382	80.50 444	98.95 404	93.64 410	94.89 388	98.25 404

Gipuma		90.99 411	90.15 416	93.51 419	98.73 392	90.12 439	93.98 452	99.45 224	79.32 450	92.28 440	94.91 447	69.61 448	97.98 431	87.42 443	95.67 367	92.45 450
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	70.75 22	75.98 425	74.97 426	79.01 441	70.98 464	55.18 466	93.37 453	98.21 427	65.08 458	61.78 459	93.83 449	21.74 466	92.53 453	78.59 451	91.12 429	89.34 454
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		82.80 419	81.52 422	86.66 435	66.61 465	68.44 464	92.79 454	97.92 431	68.96 453	80.04 456	99.85 71	85.77 418	96.15 448	97.86 260	43.89 458	95.39 448

wuyk23d		40.18 426	41.29 431	36.84 442	86.18 461	49.12 467	79.73 455	22.81 467	27.64 459	25.46 462	28.45 462	21.98 465	48.89 461	55.80 460	23.56 461	12.51 459

mmdepth		0.02 433	0.03 436	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.27 464	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

monomultidepth		0.02 433	0.03 436	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.27 464	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

test_blank		0.13 432	0.17 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	1.57 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

uanet_test		0.02 433	0.03 436	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.27 464	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

DCPMVS		0.02 433	0.03 436	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.27 464	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

cdsmvs_eth3d_5k		24.64 429	32.85 432	0.00 445	0.00 468	0.00 470	0.00 456	99.51 137	0.00 463	0.00 464	99.56 262	96.58 164	0.00 464	0.00 463	0.00 462	0.00 460

pcd_1.5k_mvsjas		8.27 431	11.03 434	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.27 464	99.01 18	0.00 464	0.00 463	0.00 462	0.00 460

sosnet-low-res		0.02 433	0.03 436	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.27 464	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

sosnet		0.02 433	0.03 436	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.27 464	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

uncertanet		0.02 433	0.03 436	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.27 464	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

Regformer		0.02 433	0.03 436	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.27 464	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

ab-mvs-re		8.30 430	11.06 433	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	99.58 254	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

uanet		0.02 433	0.03 436	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.27 464	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

WAC-MVS						97.16 313								95.47 382

MSC_two_6792asdad				99.87 18	99.51 205	99.76 43		99.33 296					99.96 38	98.87 138	99.84 95	99.89 26

PC_three_1452									98.18 160	99.84 50	99.70 193	99.31 3	98.52 420	98.30 221	99.80 118	99.81 73

No_MVS				99.87 18	99.51 205	99.76 43		99.33 296					99.96 38	98.87 138	99.84 95	99.89 26

test_one_0601					99.81 51	99.88 9		99.49 169	98.97 68	99.65 121	99.81 114	99.09 14

eth-test2					0.00 468

eth-test					0.00 468

ZD-MVS					99.71 110	99.79 35		99.61 55	96.84 323	99.56 148	99.54 270	98.58 75	99.96 38	96.93 340	99.75 135

IU-MVS					99.84 34	99.88 9		99.32 306	98.30 140	99.84 50				98.86 143	99.85 87	99.89 26

test_241102_TWO								99.48 181	99.08 49	99.88 37	99.81 114	98.94 32	99.96 38	98.91 132	99.84 95	99.88 32

test_241102_ONE					99.84 34	99.90 2		99.48 181	99.07 51	99.91 28	99.74 176	99.20 7	99.76 235

test_0728_THIRD									98.99 62	99.81 62	99.80 130	99.09 14	99.96 38	98.85 145	99.90 54	99.88 32

GSMVS																99.52 202

test_part2					99.81 51	99.83 20				99.77 77

sam_mvs1												94.86 242				99.52 202

sam_mvs												94.72 254

MTGPA								99.47 202

test_post											65.99 459	94.65 261	99.73 246

patchmatchnet-post											98.70 407	94.79 246	99.74 240

gm-plane-assit					98.54 412	92.96 429			94.65 407		99.15 368		99.64 282	97.56 295

test9_res														97.49 301	99.72 141	99.75 100

agg_prior2														97.21 319	99.73 140	99.75 100

agg_prior					99.67 127	99.62 76		99.40 256		98.87 302			99.91 128

TestCases				99.31 177	99.86 22	98.48 245		99.61 55	97.85 215	99.36 200	99.85 71	95.95 190	99.85 176	96.66 353	99.83 106	99.59 182

test_prior				99.68 82	99.67 127	99.48 104		99.56 83					99.83 198			99.74 104

新几何1				99.75 70	99.75 85	99.59 81		99.54 100	96.76 326	99.29 216	99.64 230	98.43 86	99.94 86	96.92 342	99.66 152	99.72 122

旧先验1					99.74 93	99.59 81		99.54 100			99.69 204	98.47 83			99.68 149	99.73 113

原ACMM1				99.65 88	99.73 100	99.33 123		99.47 202	97.46 263	99.12 254	99.66 222	98.67 69	99.91 128	97.70 283	99.69 146	99.71 131

testdata2													99.95 73	96.67 352

segment_acmp												98.96 25

testdata				99.54 118	99.75 85	98.95 183		99.51 137	97.07 304	99.43 176	99.70 193	98.87 40	99.94 86	97.76 274	99.64 155	99.72 122

test12				99.75 70	99.64 148	99.61 78		99.29 319		99.21 237		98.38 92	99.89 156		99.74 138	99.74 104

plane_prior7					99.29 280	97.03 326

plane_prior6					99.27 285	96.98 330						92.71 324

plane_prior5								99.47 202					99.69 267	97.78 270	97.63 299	98.67 341

plane_prior4											99.61 245

plane_prior3						97.00 328			98.69 100	99.11 256

plane_prior1					99.26 288

n2								0.00 469

nn								0.00 469

door-mid								98.05 430

lessismore_v0				97.79 370	98.69 398	95.44 389		94.75 454		95.71 424	99.87 57	88.69 393	99.32 337	95.89 371	94.93 386	98.62 363

LGP-MVS_train				98.49 298	99.33 267	97.05 322		99.55 91	97.46 263	99.24 229	99.83 91	92.58 329	99.72 250	98.09 239	97.51 311	98.68 333

test11								99.35 283

door								97.92 431

HQP5-MVS						96.83 342

BP-MVS														97.19 323

HQP4-MVS										98.66 331			99.64 282			98.64 354

HQP3-MVS								99.39 259							97.58 304

HQP2-MVS												92.47 333

NP-MVS					99.23 296	96.92 338					99.40 316

ACMMP++_ref															97.19 332

ACMMP++															97.43 322

Test By Simon												98.75 58

ITE_SJBPF				98.08 343	99.29 280	96.37 361		98.92 374	98.34 135	98.83 308	99.75 171	91.09 365	99.62 289	95.82 372	97.40 324	98.25 404

DeepMVS_CX				93.34 420	99.29 280	82.27 449		99.22 333	85.15 446	96.33 417	99.05 378	90.97 367	99.73 246	93.57 411	97.77 295	98.01 418

High-resolution multi-view benchmark