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.

reproduce_monomvs		95.38 239	95.07 236	96.32 287	99.32 113	96.60 160	99.76 197	98.85 62	96.65 75	87.83 406	96.05 376	99.52 1	98.11 328	96.58 224	81.07 421	94.25 372

CHOSEN 280x420		99.01 17	99.03 11	98.95 96	99.38 108	98.87 37	98.46 407	99.42 21	97.03 58	99.02 119	99.09 192	99.35 2	98.21 323	99.73 47	99.78 88	99.77 118

GG-mvs-BLEND				98.54 130	98.21 211	98.01 86	93.87 488	98.52 130		97.92 180	97.92 309	99.02 3	97.94 341	98.17 147	99.58 111	99.67 135

gg-mvs-nofinetune		93.51 307	91.86 334	98.47 137	97.72 248	97.96 91	92.62 499	98.51 133	74.70 492	97.33 204	69.59 528	98.91 4	97.79 345	97.77 176	99.56 112	99.67 135

TestfortrainingZip				99.90 5	99.97 3	99.70 5	99.97 43	98.89 52	96.02 100	99.99 1	99.96 3	97.97 5	100.00 1		99.65 98	100.00 1

test_0728_THIRD									96.48 81	99.83 25	99.91 19	97.87 6	100.00 1	99.92 17	100.00 1	100.00 1

baseline2		96.71 168	96.49 156	97.37 239	95.63 382	95.96 189	99.74 208	98.88 55	92.94 233	91.61 328	98.97 214	97.72 7	98.62 276	94.83 263	98.08 192	97.53 330

BP-MVS1		98.33 60	98.18 57	98.81 103	97.44 277	97.98 88	99.96 57	98.17 225	94.88 132	98.77 133	99.59 126	97.59 8	99.08 212	98.24 144	98.93 157	99.36 209

SteuartSystems-ACMMP		99.02 16	98.97 14	99.18 64	98.72 165	97.71 102	99.98 24	98.44 150	96.85 65	99.80 29	99.91 19	97.57 9	99.85 132	99.44 68	99.99 21	99.99 27
Skip Steuart: Steuart Systems R&D Blog.
thisisatest0515		97.41 125	97.02 131	98.59 123	97.71 250	97.52 112	99.97 43	98.54 125	91.83 293	97.45 199	99.04 199	97.50 10	99.10 211	94.75 266	96.37 257	99.16 246

PC_three_1452									96.96 61	99.80 29	99.79 63	97.49 11	100.00 1	99.99 5	99.98 32	100.00 1

test_one_0601					99.94 18	99.30 15		98.41 176	96.63 76	99.75 43	99.93 12	97.49 11

thisisatest0530		97.10 140	96.72 146	98.22 155	97.60 263	96.70 152	99.92 104	98.54 125	91.11 322	97.07 214	98.97 214	97.47 13	99.03 214	93.73 295	96.09 264	98.92 275

tttt0517		96.85 155	96.49 156	97.92 177	97.48 274	95.89 191	99.85 151	98.54 125	90.72 339	96.63 231	98.93 226	97.47 13	99.02 215	93.03 309	95.76 278	98.85 280

DVP-MVS++		99.26 6	99.09 10	99.77 10	99.91 45	99.31 13	99.95 76	98.43 158	96.48 81	99.80 29	99.93 12	97.44 15	100.00 1	99.92 17	99.98 32	100.00 1

OPU-MVS				99.93 2	99.89 51	99.80 2	99.96 57				99.80 59	97.44 15	100.00 1	100.00 1	99.98 32	100.00 1

MSP-MVS		99.09 11	99.12 5	98.98 93	99.93 29	97.24 125	99.95 76	98.42 170	97.50 39	99.52 78	99.88 29	97.43 17	99.71 162	99.50 63	99.98 32	100.00 1
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
MED-MVS		99.24 8	99.12 5	99.60 25	99.96 9	98.79 44	99.97 43	98.88 55	96.91 63	99.07 114	99.92 16	97.36 18	100.00 1	99.98 9	99.98 32	100.00 1

NCCC		99.37 2	99.25 2	99.71 17	99.96 9	99.15 25	99.97 43	98.62 99	98.02 23	99.90 8	99.95 4	97.33 19	100.00 1	99.54 60	100.00 1	100.00 1

MVSTER		95.53 235	95.22 229	96.45 281	98.56 176	97.72 101	99.91 112	97.67 285	92.38 273	91.39 330	97.14 330	97.24 20	97.30 366	94.80 264	87.85 361	94.34 367

DVP-MVS		99.30 4	99.16 3	99.73 14	99.93 29	99.29 18	99.95 76	98.32 200	97.28 46	99.83 25	99.91 19	97.22 21	100.00 1	99.99 5	100.00 1	99.89 99
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
test0726					99.93 29	99.29 18	99.96 57	98.42 170	97.28 46	99.86 17	99.94 5	97.22 21

test_241102_TWO								98.43 158	97.27 48	99.80 29	99.94 5	97.18 23	100.00 1	100.00 1	100.00 1	100.00 1

DPM-MVS		98.83 25	98.46 37	99.97 1	99.33 111	99.92 1	99.96 57	98.44 150	97.96 24	99.55 73	99.94 5	97.18 23	100.00 1	93.81 290	99.94 59	99.98 58

GDP-MVS		97.88 87	97.59 101	98.75 108	97.59 264	97.81 98	99.95 76	97.37 325	94.44 153	99.08 112	99.58 129	97.13 25	99.08 212	94.99 256	98.17 184	99.37 207

CNVR-MVS		99.40 1	99.26 1	99.84 7	99.98 2	99.51 8	99.98 24	98.69 82	98.20 10	99.93 4	99.98 2	96.82 26	100.00 1	99.75 43	100.00 1	99.99 27

WBMVS		94.52 270	94.03 268	95.98 295	98.38 194	96.68 155	99.92 104	97.63 289	90.75 338	89.64 361	95.25 413	96.77 27	96.90 395	94.35 276	83.57 398	94.35 365

UBG		97.84 92	97.69 94	98.29 152	98.38 194	96.59 162	99.90 118	98.53 128	93.91 186	98.52 150	98.42 286	96.77 27	99.17 207	98.54 123	96.20 261	99.11 253

SED-MVS		99.28 5	99.11 8	99.77 10	99.93 29	99.30 15	99.96 57	98.43 158	97.27 48	99.80 29	99.94 5	96.71 29	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 29	99.30 15		98.43 158	97.26 50	99.80 29	99.88 29	96.71 29	100.00 1

DPE-MVS		99.26 6	99.10 9	99.74 13	99.89 51	99.24 22	99.87 135	98.44 150	97.48 40	99.64 59	99.94 5	96.68 31	99.99 40	99.99 5	100.00 1	99.99 27
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
segment_acmp												96.68 31

UWE-MVS		96.79 158	96.72 146	97.00 258	98.51 184	93.70 292	99.71 224	98.60 103	92.96 232	97.09 212	98.34 291	96.67 33	98.85 232	92.11 322	96.50 252	98.44 298

patch_mono-2		98.24 70	99.12 5	95.59 310	99.67 89	86.91 442	99.95 76	98.89 52	97.60 35	99.90 8	99.76 74	96.54 34	99.98 52	99.94 15	99.82 85	99.88 100

PAPM		98.60 38	98.42 39	99.14 74	96.05 359	98.96 30	99.90 118	99.35 24	96.68 74	98.35 162	99.66 117	96.45 35	98.51 286	99.45 67	99.89 74	99.96 76

test-260524					99.95 17	99.33 10		98.42 170		99.04 117		96.44 36	100.00 1	99.98 9	99.98 32

MCST-MVS		99.32 3	99.14 4	99.86 6	99.97 3	99.59 6	99.97 43	98.64 91	98.47 3	99.13 109	99.92 16	96.38 37	100.00 1	99.74 45	100.00 1	100.00 1

TestfortrainingZip a		99.01 17	98.78 22	99.69 18	99.96 9	99.09 27	99.97 43	98.74 76	96.91 63	99.86 17	99.92 16	96.29 38	99.99 40	98.32 138	99.09 151	100.00 1

aaEdge-Enhanced		99.07 12	98.89 18	99.59 28	99.93 29	98.79 44	99.95 76	98.80 71	95.89 105	99.28 101	99.93 12	96.28 39	99.98 52	99.98 9	99.96 48	99.99 27

ET-MVSNet_ETH3D		94.37 277	93.28 298	97.64 205	98.30 202	97.99 87	99.99 8	97.61 295	94.35 159	71.57 497	99.45 142	96.23 40	95.34 462	96.91 209	85.14 385	99.59 157

EPP-MVSNet		96.69 169	96.60 151	96.96 260	97.74 243	93.05 315	99.37 301	98.56 115	88.75 382	95.83 266	99.01 203	96.01 41	98.56 281	96.92 207	97.20 217	99.25 237

test_prior2							99.95 76		95.78 107	99.73 48	99.76 74	96.00 42		99.78 37	100.00 1

train_agg		98.88 24	98.65 28	99.59 28	99.92 37	98.92 33	99.96 57	98.43 158	94.35 159	99.71 50	99.86 34	95.94 43	99.85 132	99.69 52	99.98 32	99.99 27

test_8					99.92 37	98.88 36	99.96 57	98.43 158	94.35 159	99.69 52	99.85 38	95.94 43	99.85 132

MSLP-MVS++		99.13 10	99.01 12	99.49 38	99.94 18	98.46 69	99.98 24	98.86 59	97.10 54	99.80 29	99.94 5	95.92 45	100.00 1	99.51 61	100.00 1	100.00 1

TEST9					99.92 37	98.92 33	99.96 57	98.43 158	93.90 187	99.71 50	99.86 34	95.88 46	99.85 132

test_yl		97.83 93	97.37 114	99.21 61	99.18 120	97.98 88	99.64 245	99.27 27	91.43 310	97.88 185	98.99 210	95.84 47	99.84 140	98.82 104	95.32 295	99.79 114

DCV-MVSNet		97.83 93	97.37 114	99.21 61	99.18 120	97.98 88	99.64 245	99.27 27	91.43 310	97.88 185	98.99 210	95.84 47	99.84 140	98.82 104	95.32 295	99.79 114

fmvsm_l_mol_unc0.5_1		99.14 9	98.92 15	99.81 9	99.03 131	99.54 7	99.98 24	97.90 260	98.36 5	99.94 2	99.78 67	95.70 49	99.97 65	99.83 33	99.75 90	99.92 94

DP-MVS Recon		98.41 54	98.02 69	99.56 31	99.97 3	98.70 55	99.92 104	98.44 150	92.06 286	98.40 160	99.84 49	95.68 50	100.00 1	98.19 146	99.71 93	99.97 68

旧先验1					99.76 74	97.52 112		98.64 91			99.85 38	95.63 51			99.94 59	99.99 27

SMA-MVS		98.76 30	98.48 36	99.62 23	99.87 57	98.87 37	99.86 148	98.38 187	93.19 219	99.77 41	99.94 5	95.54 52	100.00 1	99.74 45	99.99 21	100.00 1
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
TESTMET0.1,1		96.74 166	96.26 168	98.16 158	97.36 289	96.48 164	99.96 57	98.29 206	91.93 289	95.77 267	98.07 302	95.54 52	98.29 314	90.55 349	98.89 158	99.70 127

APDe-MVS		99.06 14	98.91 16	99.51 35	99.94 18	98.76 52	99.91 112	98.39 183	97.20 52	99.46 82	99.85 38	95.53 54	99.79 147	99.86 28	100.00 1	99.99 27
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
testing3-2		97.72 108	97.43 112	98.60 120	98.55 179	97.11 135	100.00 1	99.23 31	93.78 191	97.90 181	98.73 250	95.50 55	99.69 166	98.53 125	94.63 302	98.99 269

testing11		97.48 119	97.27 119	98.10 164	98.36 197	96.02 187	99.92 104	98.45 145	93.45 206	98.15 173	98.70 254	95.48 56	99.22 200	97.85 168	95.05 299	99.07 258

PLC	95.54 3	97.93 84	97.89 83	98.05 168	99.82 66	94.77 249	99.92 104	98.46 144	93.93 184	97.20 208	99.27 167	95.44 57	99.97 65	97.41 185	99.51 119	99.41 202
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
HPM-MVS++		99.07 12	98.88 19	99.63 20	99.90 48	99.02 29	99.95 76	98.56 115	97.56 38	99.44 84	99.85 38	95.38 58	100.00 1	99.31 73	99.99 21	99.87 102

PHI-MVS		98.41 54	98.21 54	99.03 86	99.86 59	97.10 136	99.98 24	98.80 71	90.78 337	99.62 63	99.78 67	95.30 59	100.00 1	99.80 34	99.93 65	99.99 27

myMVS_eth3d28		97.86 89	97.59 101	98.68 112	98.50 186	97.26 124	99.92 104	98.55 121	93.79 190	98.26 167	98.75 248	95.20 60	99.48 188	98.93 95	96.40 255	99.29 228

test-mter		96.39 188	95.93 193	97.78 190	97.02 316	95.44 211	99.96 57	98.21 220	91.81 295	95.55 273	96.38 361	95.17 61	98.27 319	90.42 352	98.83 163	99.64 141

patchmatchnet-post											91.70 477	95.12 62	97.95 339

MDTV_nov1_ep13			95.69 204		97.90 231	94.15 278	95.98 478	98.44 150	93.12 226	97.98 178	95.74 381	95.10 63	98.58 278	90.02 358	96.92 240

IB-MVS	92.85 6	94.99 251	93.94 272	98.16 158	97.72 248	95.69 202	99.99 8	98.81 67	94.28 165	92.70 318	96.90 343	95.08 64	99.17 207	96.07 236	73.88 464	99.60 156
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
ZD-MVS					99.92 37	98.57 63		98.52 130	92.34 274	99.31 97	99.83 51	95.06 65	99.80 145	99.70 51	99.97 44

CDS-MVSNet		96.34 192	96.07 178	97.13 253	97.37 286	94.96 239	99.53 273	97.91 259	91.55 304	95.37 278	98.32 292	95.05 66	97.13 376	93.80 291	95.75 279	99.30 226
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Patchmatch-test		92.65 331	91.50 342	96.10 292	96.85 334	90.49 390	91.50 505	97.19 362	82.76 459	90.23 343	95.59 390	95.02 67	98.00 335	77.41 473	96.98 239	99.82 109

CostFormer		96.10 204	95.88 197	96.78 268	97.03 313	92.55 330	97.08 455	97.83 269	90.04 358	98.72 138	94.89 429	95.01 68	98.29 314	96.54 225	95.77 277	99.50 183

TSAR-MVS + GP.		98.60 38	98.51 35	98.86 101	99.73 81	96.63 157	99.97 43	97.92 258	98.07 20	98.76 136	99.55 133	95.00 69	99.94 96	99.91 20	97.68 200	99.99 27

CDPH-MVS		98.65 36	98.36 46	99.49 38	99.94 18	98.73 53	99.87 135	98.33 198	93.97 181	99.76 42	99.87 32	94.99 70	99.75 156	98.55 122	100.00 1	99.98 58

原ACMM1				98.96 95	99.73 81	96.99 140		98.51 133	94.06 177	99.62 63	99.85 38	94.97 71	99.96 78	95.11 253	99.95 54	99.92 94

TSAR-MVS + MP.		98.93 21	98.77 23	99.41 45	99.74 78	98.67 56	99.77 191	98.38 187	96.73 72	99.88 14	99.74 89	94.89 72	99.59 176	99.80 34	99.98 32	99.97 68
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
testing99		97.17 135	96.91 134	97.95 173	98.35 199	95.70 200	99.91 112	98.43 158	92.94 233	97.36 202	98.72 251	94.83 73	99.21 201	97.00 201	94.64 301	98.95 271

testing91		97.16 136	96.90 135	97.97 171	98.35 199	95.67 203	99.91 112	98.42 170	92.91 235	97.33 204	98.72 251	94.81 74	99.21 201	96.98 203	94.63 302	99.03 266

test12				99.43 42	99.74 78	98.56 64		98.40 180		99.65 56		94.76 75	99.75 156		99.98 32	99.99 27

fmvsm_l_conf0.5_n_a		99.00 19	98.91 16	99.28 54	99.21 118	97.91 93	99.98 24	98.85 62	98.25 6	99.92 6	99.75 82	94.72 76	99.97 65	99.87 26	99.64 99	99.95 84

sam_mvs1												94.72 76				99.59 157

SF-MVS		98.67 34	98.40 40	99.50 36	99.77 73	98.67 56	99.90 118	98.21 220	93.53 199	99.81 27	99.89 27	94.70 78	99.86 131	99.84 30	99.93 65	99.96 76

testing915		97.83 93	97.48 106	98.88 99	98.41 192	97.68 107	99.87 135	98.64 91	93.35 210	98.82 129	98.62 264	94.60 79	98.97 219	98.72 112	96.25 260	100.00 1

reproduce-ours		98.78 28	98.67 25	99.09 81	99.70 86	97.30 122	99.74 208	98.25 211	97.10 54	99.10 110	99.90 23	94.59 80	99.99 40	99.77 39	99.91 71	99.99 27

our_new_method		98.78 28	98.67 25	99.09 81	99.70 86	97.30 122	99.74 208	98.25 211	97.10 54	99.10 110	99.90 23	94.59 80	99.99 40	99.77 39	99.91 71	99.99 27

SD-MVS		98.92 22	98.70 24	99.56 31	99.70 86	98.73 53	99.94 94	98.34 197	96.38 87	99.81 27	99.76 74	94.59 80	99.98 52	99.84 30	99.96 48	99.97 68
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
9.14			98.38 42		99.87 57		99.91 112	98.33 198	93.22 217	99.78 40	99.89 27	94.57 83	99.85 132	99.84 30	99.97 44

reproduce_model		98.75 31	98.66 27	99.03 86	99.71 84	97.10 136	99.73 215	98.23 215	97.02 59	99.18 107	99.90 23	94.54 84	99.99 40	99.77 39	99.90 73	99.99 27

test_post											63.35 540	94.43 85	98.13 327

EPMVS		96.53 180	96.01 181	98.09 165	98.43 191	96.12 186	96.36 469	99.43 20	93.53 199	97.64 193	95.04 420	94.41 86	98.38 304	91.13 335	98.11 189	99.75 120

新几何1				99.42 44	99.75 77	98.27 73		98.63 98	92.69 250	99.55 73	99.82 54	94.40 87	100.00 1	91.21 333	99.94 59	99.99 27

MDTV_nov1_ep13_2view						96.26 174	96.11 475		91.89 290	98.06 175		94.40 87		94.30 277		99.67 135

PAPM_NR		98.12 76	97.93 79	98.70 111	99.94 18	96.13 184	99.82 171	98.43 158	94.56 144	97.52 195	99.70 102	94.40 87	99.98 52	97.00 201	99.98 32	99.99 27

dcpmvs_2		97.42 124	98.09 64	95.42 317	99.58 97	87.24 438	99.23 325	96.95 412	94.28 165	98.93 123	99.73 93	94.39 90	99.16 209	99.89 22	99.82 85	99.86 104

miper_enhance_ethall		94.36 279	93.98 270	95.49 311	98.68 167	95.24 228	99.73 215	97.29 347	93.28 215	89.86 353	95.97 377	94.37 91	97.05 382	92.20 316	84.45 391	94.19 380

XVS		98.70 33	98.55 32	99.15 72	99.94 18	97.50 114	99.94 94	98.42 170	96.22 94	99.41 89	99.78 67	94.34 92	99.96 78	98.92 97	99.95 54	99.99 27

X-MVStestdata		93.83 294	92.06 329	99.15 72	99.94 18	97.50 114	99.94 94	98.42 170	96.22 94	99.41 89	41.37 556	94.34 92	99.96 78	98.92 97	99.95 54	99.99 27

BridgeMVS		98.27 64	97.99 71	99.11 79	98.64 172	98.43 70	99.47 284	97.79 271	94.56 144	99.74 46	98.35 289	94.33 94	99.25 198	99.12 81	99.96 48	99.64 141

CP-MVS		98.45 49	98.32 48	98.87 100	99.96 9	96.62 158	99.97 43	98.39 183	94.43 154	98.90 124	99.87 32	94.30 95	100.00 1	99.04 88	99.99 21	99.99 27

MVSMamba_PlusPlus		97.83 93	97.45 109	98.99 91	98.60 174	98.15 74	99.58 259	97.74 280	90.34 351	99.26 103	98.32 292	94.29 96	99.23 199	99.03 91	99.89 74	99.58 163

sam_mvs												94.25 97

Patchmatch-RL test		86.90 421	85.98 420	89.67 450	84.45 508	75.59 495	89.71 513	92.43 503	86.89 415	77.83 481	90.94 480	94.22 98	93.63 484	87.75 394	69.61 480	99.79 114

HFP-MVS		98.56 40	98.37 44	99.14 74	99.96 9	97.43 118	99.95 76	98.61 101	94.77 136	99.31 97	99.85 38	94.22 98	100.00 1	98.70 113	99.98 32	99.98 58

fmvsm_l_conf0.5_n		98.94 20	98.84 20	99.25 57	99.17 122	97.81 98	99.98 24	98.86 59	98.25 6	99.90 8	99.76 74	94.21 100	99.97 65	99.87 26	99.52 116	99.98 58

PatchmatchNet		95.94 212	95.45 213	97.39 238	97.83 236	94.41 264	96.05 476	98.40 180	92.86 237	97.09 212	95.28 412	94.21 100	98.07 332	89.26 370	98.11 189	99.70 127
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
DeepPCF-MVS	95.94 2	97.71 110	98.98 13	93.92 383	99.63 91	81.76 478	99.96 57	98.56 115	99.47 1	99.19 106	99.99 1	94.16 102	100.00 1	99.92 17	99.93 65	100.00 1

APD-MVS		98.62 37	98.35 47	99.41 45	99.90 48	98.51 66	99.87 135	98.36 191	94.08 174	99.74 46	99.73 93	94.08 103	99.74 158	99.42 69	99.99 21	99.99 27
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
region2R		98.54 42	98.37 44	99.05 84	99.96 9	97.18 128	99.96 57	98.55 121	94.87 133	99.45 83	99.85 38	94.07 104	100.00 1	98.67 115	100.00 1	99.98 58

PAPR		98.52 44	98.16 59	99.58 30	99.97 3	98.77 49	99.95 76	98.43 158	95.35 120	98.03 176	99.75 82	94.03 105	99.98 52	98.11 151	99.83 81	99.99 27

MG-MVS		98.91 23	98.65 28	99.68 19	99.94 18	99.07 28	99.64 245	99.44 19	97.33 45	99.00 120	99.72 96	94.03 105	99.98 52	98.73 111	100.00 1	100.00 1

MVS_111021_HR		98.72 32	98.62 30	99.01 90	99.36 109	97.18 128	99.93 101	99.90 1	96.81 70	98.67 140	99.77 72	93.92 107	99.89 120	99.27 76	99.94 59	99.96 76

tpmrst		96.27 198	95.98 184	97.13 253	97.96 228	93.15 312	96.34 470	98.17 225	92.07 284	98.71 139	95.12 417	93.91 108	98.73 256	94.91 261	96.62 249	99.50 183

test-LLR		96.47 182	96.04 180	97.78 190	97.02 316	95.44 211	99.96 57	98.21 220	94.07 175	95.55 273	96.38 361	93.90 109	98.27 319	90.42 352	98.83 163	99.64 141

test0.0.03 1		93.86 293	93.61 279	94.64 343	95.02 395	92.18 339	99.93 101	98.58 107	94.07 175	87.96 404	98.50 278	93.90 109	94.96 467	81.33 448	93.17 323	96.78 336

ETVMVS		97.03 146	96.64 149	98.20 156	98.67 168	97.12 133	99.89 129	98.57 109	91.10 323	98.17 172	98.59 268	93.86 111	98.19 324	95.64 246	95.24 297	99.28 230

test222					99.55 98	97.41 120	99.34 305	98.55 121	91.86 292	99.27 102	99.83 51	93.84 112			99.95 54	99.99 27

dp		95.05 248	94.43 254	96.91 262	97.99 226	92.73 324	96.29 472	97.98 250	89.70 363	95.93 263	94.67 435	93.83 113	98.45 291	86.91 410	96.53 251	99.54 171

ACMMPR		98.50 45	98.32 48	99.05 84	99.96 9	97.18 128	99.95 76	98.60 103	94.77 136	99.31 97	99.84 49	93.73 114	100.00 1	98.70 113	99.98 32	99.98 58

EPNet		98.49 46	98.40 40	98.77 107	99.62 92	96.80 151	99.90 118	99.51 16	97.60 35	99.20 104	99.36 154	93.71 115	99.91 113	97.99 159	98.71 168	99.61 154
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FBQ-MVS		97.12 139	96.92 133	97.72 197	98.35 199	94.55 255	99.87 135	98.62 99	93.23 216	98.60 148	98.39 288	93.66 116	98.96 222	95.76 244	95.82 275	99.64 141

alignmvs		97.81 98	97.33 116	99.25 57	98.77 162	98.66 58	99.99 8	98.44 150	94.40 158	98.41 158	99.47 139	93.65 117	99.42 192	98.57 121	94.26 310	99.67 135

testdata				98.42 144	99.47 104	95.33 220		98.56 115	93.78 191	99.79 38	99.85 38	93.64 118	99.94 96	94.97 257	99.94 59	100.00 1

EI-MVSNet-Vis-set		98.27 64	98.11 63	98.75 108	99.83 65	96.59 162	99.40 293	98.51 133	95.29 122	98.51 152	99.76 74	93.60 119	99.71 162	98.53 125	99.52 116	99.95 84

UWE-MVS-28		95.95 211	96.49 156	94.34 361	98.51 184	89.99 401	99.39 297	98.57 109	93.14 224	97.33 204	98.31 294	93.44 120	94.68 473	93.69 297	95.98 267	98.34 303

mPP-MVS		98.39 57	98.20 55	98.97 94	99.97 3	96.92 143	99.95 76	98.38 187	95.04 126	98.61 145	99.80 59	93.39 121	100.00 1	98.64 118	100.00 1	99.98 58

testing222		97.08 145	96.75 144	98.06 167	98.56 176	96.82 146	99.85 151	98.61 101	92.53 265	98.84 126	98.84 242	93.36 122	98.30 313	95.84 241	94.30 309	99.05 261

SR-MVS		98.46 48	98.30 51	98.93 97	99.88 55	97.04 138	99.84 156	98.35 193	94.92 130	99.32 96	99.80 59	93.35 123	99.78 149	99.30 74	99.95 54	99.96 76

WTY-MVS		98.10 77	97.60 99	99.60 25	98.92 148	99.28 20	99.89 129	99.52 14	95.58 114	98.24 169	99.39 151	93.33 124	99.74 158	97.98 161	95.58 288	99.78 117

tpm2		95.47 236	95.18 231	96.35 286	96.91 329	91.70 360	96.96 458	97.93 255	88.04 398	98.44 155	95.40 401	93.32 125	97.97 336	94.00 281	95.61 287	99.38 205

HY-MVS	92.50 7	97.79 101	97.17 125	99.63 20	98.98 140	99.32 12	97.49 443	99.52 14	95.69 111	98.32 163	97.41 323	93.32 125	99.77 152	98.08 154	95.75 279	99.81 111

nomal-1		96.23 201	96.10 177	96.64 275	97.64 258	92.37 335	99.76 197	98.09 237	91.73 299	94.59 288	97.47 320	93.31 127	98.45 291	96.77 217	95.52 289	99.10 254

EI-MVSNet-UG-set		98.14 75	97.99 71	98.60 120	99.80 69	96.27 173	99.36 303	98.50 139	95.21 124	98.30 164	99.75 82	93.29 128	99.73 161	98.37 135	99.30 140	99.81 111

SR-MVS-dyc-post		98.31 61	98.17 58	98.71 110	99.79 70	96.37 171	99.76 197	98.31 202	94.43 154	99.40 91	99.75 82	93.28 129	99.78 149	98.90 100	99.92 68	99.97 68

baseline1		95.78 224	94.86 243	98.54 130	98.47 189	98.07 82	99.06 344	97.99 248	92.68 251	94.13 301	98.62 264	93.28 129	98.69 265	93.79 292	85.76 378	98.84 281

MGCNet		99.06 14	98.84 20	99.72 15	99.76 74	99.21 24	99.99 8	99.34 25	98.70 2	99.44 84	99.75 82	93.24 131	99.99 40	99.94 15	99.41 133	99.95 84

PGM-MVS		98.34 59	98.13 61	98.99 91	99.92 37	97.00 139	99.75 204	99.50 17	93.90 187	99.37 94	99.76 74	93.24 131	100.00 1	97.75 178	99.96 48	99.98 58

test_post1							95.78 481				59.23 544	93.20 133	97.74 348	91.06 337

CSCG		97.10 140	97.04 129	97.27 247	99.89 51	91.92 345	99.90 118	99.07 37	88.67 384	95.26 281	99.82 54	93.17 134	99.98 52	98.15 149	99.47 126	99.90 98

DeepC-MVS_fast	96.59 1	98.81 27	98.54 33	99.62 23	99.90 48	98.85 39	99.24 324	98.47 142	98.14 17	99.08 112	99.91 19	93.09 135	100.00 1	99.04 88	99.99 21	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ZNCC-MVS		98.31 61	98.03 68	99.17 67	99.88 55	97.59 109	99.94 94	98.44 150	94.31 162	98.50 153	99.82 54	93.06 136	99.99 40	98.30 140	99.99 21	99.93 89

testing3		93.92 291	94.23 261	92.99 410	97.54 268	90.23 395	99.99 8	99.16 33	90.57 342	91.33 332	98.63 263	92.99 137	92.52 493	82.46 441	95.39 293	96.22 344

GST-MVS		98.27 64	97.97 73	99.17 67	99.92 37	97.57 110	99.93 101	98.39 183	94.04 179	98.80 130	99.74 89	92.98 138	100.00 1	98.16 148	99.76 89	99.93 89

RE-MVS-def			98.13 61		99.79 70	96.37 171	99.76 197	98.31 202	94.43 154	99.40 91	99.75 82	92.95 139		98.90 100	99.92 68	99.97 68

CS-MVS		97.79 101	97.91 80	97.43 232	99.10 126	94.42 263	99.99 8	97.10 385	95.07 125	99.68 53	99.75 82	92.95 139	98.34 308	98.38 133	99.14 147	99.54 171

ACMMP_NAP		98.49 46	98.14 60	99.54 33	99.66 90	98.62 62	99.85 151	98.37 190	94.68 141	99.53 76	99.83 51	92.87 141	100.00 1	98.66 117	99.84 80	99.99 27

APD-MVS_3200maxsize		98.25 69	98.08 65	98.78 105	99.81 68	96.60 160	99.82 171	98.30 205	93.95 183	99.37 94	99.77 72	92.84 142	99.76 155	98.95 93	99.92 68	99.97 68

JIA-IIPM		91.76 352	90.70 353	94.94 332	96.11 357	87.51 435	93.16 497	98.13 235	75.79 488	97.58 194	77.68 521	92.84 142	97.97 336	88.47 381	96.54 250	99.33 216

Test By Simon												92.82 144

MTAPA		98.29 63	97.96 76	99.30 53	99.85 62	97.93 92	99.39 297	98.28 207	95.76 108	97.18 210	99.88 29	92.74 145	100.00 1	98.67 115	99.88 77	99.99 27

0.3-1-1-0.015		94.22 283	93.13 304	97.49 226	95.50 385	94.17 277	100.00 1	98.22 216	88.44 391	97.14 211	97.04 338	92.73 146	98.59 277	96.45 229	72.65 470	99.70 127

NormalMVS		97.90 86	97.85 86	98.04 169	99.86 59	95.39 216	99.61 252	97.78 275	96.52 79	98.61 145	99.31 159	92.73 146	99.67 170	96.77 217	99.48 123	99.06 259

SymmetryMVS		97.64 113	97.46 107	98.17 157	98.74 164	95.39 216	99.61 252	99.26 29	96.52 79	98.61 145	99.31 159	92.73 146	99.67 170	96.77 217	95.63 286	99.45 194

EPNet_dtu		95.71 228	95.39 218	96.66 273	98.92 148	93.41 306	99.57 263	98.90 50	96.19 96	97.52 195	98.56 273	92.65 149	97.36 359	77.89 471	98.33 178	99.20 243
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsm_n_1920		98.44 50	98.61 31	97.92 177	99.27 116	95.18 232	100.00 1	98.90 50	98.05 21	99.80 29	99.73 93	92.64 150	99.99 40	99.58 59	99.51 119	98.59 293

MP-MVS-pluss		98.07 79	97.64 97	99.38 50	99.74 78	98.41 71	99.74 208	98.18 224	93.35 210	96.45 241	99.85 38	92.64 150	99.97 65	98.91 99	99.89 74	99.77 118
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
FE-MVS		95.70 230	95.01 239	97.79 188	98.21 211	94.57 254	95.03 483	98.69 82	88.90 378	97.50 197	96.19 368	92.60 152	99.49 187	89.99 359	97.94 195	99.31 223

DELS-MVS		98.54 42	98.22 53	99.50 36	99.15 124	98.65 60	100.00 1	98.58 107	97.70 33	98.21 171	99.24 176	92.58 153	99.94 96	98.63 120	99.94 59	99.92 94
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
ETV-MVS		97.92 85	97.80 89	98.25 154	98.14 218	96.48 164	99.98 24	97.63 289	95.61 113	99.29 100	99.46 141	92.55 154	98.82 236	99.02 92	98.54 173	99.46 189

lecture		98.67 34	98.46 37	99.28 54	99.86 59	97.88 94	99.97 43	99.25 30	96.07 98	99.79 38	99.70 102	92.53 155	99.98 52	99.51 61	99.48 123	99.97 68

test2506		97.53 117	97.19 123	98.58 124	98.66 170	96.90 144	98.81 382	99.77 5	94.93 128	97.95 179	98.96 216	92.51 156	99.20 204	94.93 258	98.15 186	99.64 141

KD-MVS_2432*1600		88.00 412	86.10 416	93.70 392	96.91 329	94.04 281	97.17 452	97.12 377	84.93 439	81.96 456	92.41 467	92.48 157	94.51 475	79.23 462	52.68 521	92.56 454

miper_refine_blended		88.00 412	86.10 416	93.70 392	96.91 329	94.04 281	97.17 452	97.12 377	84.93 439	81.96 456	92.41 467	92.48 157	94.51 475	79.23 462	52.68 521	92.56 454

myMVS_eth3d		94.46 274	94.76 249	93.55 396	97.68 253	90.97 376	99.71 224	98.35 193	90.79 335	92.10 324	98.67 256	92.46 159	93.09 489	87.13 403	95.95 270	96.59 339

EIA-MVS		97.53 117	97.46 107	97.76 194	98.04 224	94.84 244	99.98 24	97.61 295	94.41 157	97.90 181	99.59 126	92.40 160	98.87 229	98.04 156	99.13 148	99.59 157

F-COLMAP		96.93 152	96.95 132	96.87 265	99.71 84	91.74 355	99.85 151	97.95 253	93.11 227	95.72 270	99.16 188	92.35 161	99.94 96	95.32 249	99.35 138	98.92 275

API-MVS		97.86 89	97.66 95	98.47 137	99.52 100	95.41 214	99.47 284	98.87 58	91.68 301	98.84 126	99.85 38	92.34 162	99.99 40	98.44 130	99.96 48	100.00 1

CNLPA		97.76 103	97.38 113	98.92 98	99.53 99	96.84 145	99.87 135	98.14 234	93.78 191	96.55 237	99.69 106	92.28 163	99.98 52	97.13 196	99.44 130	99.93 89

0.4-1-1-0.1		94.07 289	92.95 307	97.42 233	95.24 390	94.00 284	100.00 1	98.22 216	88.27 395	96.81 227	96.93 342	92.27 164	98.56 281	96.21 235	72.63 472	99.70 127

0.4-1-1-0.2		94.14 284	93.02 306	97.51 221	95.45 386	94.25 273	100.00 1	98.22 216	88.53 388	96.83 225	96.95 341	92.25 165	98.57 280	96.34 230	72.65 470	99.70 127

blend_shiyan4		90.13 388	88.79 393	94.17 365	87.12 490	91.83 350	99.75 204	97.08 389	79.27 479	88.69 384	92.53 465	92.25 165	96.50 419	89.35 366	73.04 468	94.18 381

TAMVS		95.85 216	95.58 209	96.65 274	97.07 310	93.50 303	99.17 330	97.82 270	91.39 314	95.02 283	98.01 303	92.20 167	97.30 366	93.75 294	95.83 274	99.14 249

1112_ss		96.01 209	95.20 230	98.42 144	97.80 238	96.41 167	99.65 241	96.66 435	92.71 248	92.88 316	99.40 149	92.16 168	99.30 196	91.92 325	93.66 317	99.55 167

Test_1112_low_res		95.72 226	94.83 244	98.42 144	97.79 239	96.41 167	99.65 241	96.65 436	92.70 249	92.86 317	96.13 372	92.15 169	99.30 196	91.88 326	93.64 318	99.55 167

HyFIR lowres test		96.66 171	96.43 161	97.36 241	99.05 130	93.91 287	99.70 231	99.80 3	90.54 343	96.26 251	98.08 301	92.15 169	98.23 322	96.84 211	95.46 290	99.93 89

SPE-MVS-test		97.88 87	97.94 78	97.70 200	99.28 114	95.20 231	99.98 24	97.15 371	95.53 116	99.62 63	99.79 63	92.08 171	98.38 304	98.75 110	99.28 141	99.52 176

MVS_111021_LR		98.42 53	98.38 42	98.53 132	99.39 107	95.79 194	99.87 135	99.86 2	96.70 73	98.78 131	99.79 63	92.03 172	99.90 115	99.17 80	99.86 79	99.88 100

TAPA-MVS	92.12 8	94.42 275	93.60 281	96.90 264	99.33 111	91.78 354	99.78 185	98.00 247	89.89 361	94.52 290	99.47 139	91.97 173	99.18 206	69.90 490	99.52 116	99.73 122
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PatchT		90.38 378	88.75 395	95.25 324	95.99 361	90.16 397	91.22 507	97.54 304	76.80 484	97.26 207	86.01 510	91.88 174	96.07 446	66.16 502	95.91 272	99.51 181

HPM-MVS		97.96 81	97.72 91	98.68 112	99.84 64	96.39 170	99.90 118	98.17 225	92.61 255	98.62 144	99.57 132	91.87 175	99.67 170	98.87 102	99.99 21	99.99 27
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MP-MVS		98.23 72	97.97 73	99.03 86	99.94 18	97.17 132	99.95 76	98.39 183	94.70 140	98.26 167	99.81 58	91.84 176	100.00 1	98.85 103	99.97 44	99.93 89
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		97.80 99	97.50 105	98.68 112	99.79 70	96.42 166	99.88 132	98.16 230	91.75 298	98.94 122	99.54 135	91.82 177	99.65 174	97.62 182	99.99 21	99.99 27

tpmvs		94.28 281	93.57 283	96.40 283	98.55 179	91.50 371	95.70 482	98.55 121	87.47 404	92.15 323	94.26 446	91.42 178	98.95 224	88.15 389	95.85 273	98.76 285

ACMMP		97.74 105	97.44 110	98.66 115	99.92 37	96.13 184	99.18 329	99.45 18	94.84 134	96.41 248	99.71 99	91.40 179	99.99 40	97.99 159	98.03 193	99.87 102
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
Vis-MVSNet (Re-imp)		96.32 193	95.98 184	97.35 243	97.93 230	94.82 246	99.47 284	98.15 233	91.83 293	95.09 282	99.11 191	91.37 180	97.47 357	93.47 299	97.43 204	99.74 121

sss		97.57 116	97.03 130	99.18 64	98.37 196	98.04 85	99.73 215	99.38 22	93.46 204	98.76 136	99.06 197	91.21 181	99.89 120	96.33 231	97.01 238	99.62 150

pcd_1.5k_mvsjas		7.60 527	10.13 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 562	91.20 182	0.00 564	0.00 562	0.00 562	0.00 559

PS-MVSNAJss		93.64 304	93.31 297	94.61 344	92.11 454	92.19 338	99.12 333	97.38 322	92.51 267	88.45 390	96.99 340	91.20 182	97.29 369	94.36 274	87.71 363	94.36 362

PS-MVSNAJ		98.44 50	98.20 55	99.16 70	98.80 160	98.92 33	99.54 272	98.17 225	97.34 43	99.85 21	99.85 38	91.20 182	99.89 120	99.41 70	99.67 96	98.69 290

CPTT-MVS		97.64 113	97.32 117	98.58 124	99.97 3	95.77 195	99.96 57	98.35 193	89.90 360	98.36 161	99.79 63	91.18 185	99.99 40	98.37 135	99.99 21	99.99 27

test_fmvsmconf_n		98.43 52	98.32 48	98.78 105	98.12 220	96.41 167	99.99 8	98.83 66	98.22 8	99.67 54	99.64 120	91.11 186	99.94 96	99.67 54	99.62 101	99.98 58

CR-MVSNet		93.45 310	92.62 315	95.94 297	96.29 352	92.66 326	92.01 502	96.23 448	92.62 254	96.94 219	93.31 457	91.04 187	96.03 447	79.23 462	95.96 268	99.13 250

Patchmtry		89.70 395	88.49 399	93.33 400	96.24 355	89.94 405	91.37 506	96.23 448	78.22 482	87.69 407	93.31 457	91.04 187	96.03 447	80.18 459	82.10 409	94.02 405

miper_ehance_all_eth		93.16 315	92.60 316	94.82 338	97.57 265	93.56 301	99.50 278	97.07 397	88.75 382	88.85 381	95.52 394	90.97 189	96.74 406	90.77 345	84.45 391	94.17 382

mvsany_test1		97.82 97	97.90 81	97.55 216	98.77 162	93.04 316	99.80 179	97.93 255	96.95 62	99.61 71	99.68 113	90.92 190	99.83 142	99.18 79	98.29 182	99.80 113

MVSFormer		96.94 150	96.60 151	97.95 173	97.28 298	97.70 104	99.55 270	97.27 349	91.17 318	99.43 86	99.54 135	90.92 190	96.89 396	94.67 269	99.62 101	99.25 237

lupinMVS		97.85 91	97.60 99	98.62 118	97.28 298	97.70 104	99.99 8	97.55 302	95.50 118	99.43 86	99.67 115	90.92 190	98.71 260	98.40 132	99.62 101	99.45 194

h-mvs33		94.92 253	94.36 256	96.59 276	98.85 157	91.29 373	98.93 367	98.94 44	95.90 103	98.77 133	98.42 286	90.89 193	99.77 152	97.80 171	70.76 476	98.72 289

hse-mvs2		94.38 276	94.08 267	95.31 322	98.27 207	90.02 400	99.29 318	98.56 115	95.90 103	98.77 133	98.00 304	90.89 193	98.26 321	97.80 171	69.20 484	97.64 323

xiu_mvs_v2_base		98.23 72	97.97 73	99.02 89	98.69 166	98.66 58	99.52 274	98.08 240	97.05 57	99.86 17	99.86 34	90.65 195	99.71 162	99.39 72	98.63 169	98.69 290

IS-MVSNet		96.29 196	95.90 195	97.45 228	98.13 219	94.80 247	99.08 339	97.61 295	92.02 288	95.54 275	98.96 216	90.64 196	98.08 330	93.73 295	97.41 207	99.47 187

kuosan		93.17 314	92.60 316	94.86 337	98.40 193	89.54 409	98.44 409	98.53 128	84.46 444	88.49 389	97.92 309	90.57 197	97.05 382	83.10 436	93.49 319	97.99 312

FA-MVS(test-final)		95.86 215	95.09 235	98.15 161	97.74 243	95.62 205	96.31 471	98.17 225	91.42 312	96.26 251	96.13 372	90.56 198	99.47 190	92.18 317	97.07 229	99.35 213

cl22		93.77 299	93.25 299	95.33 321	99.49 103	94.43 262	99.61 252	98.09 237	90.38 348	89.16 377	95.61 388	90.56 198	97.34 361	91.93 324	84.45 391	94.21 379

MM		98.83 25	98.53 34	99.76 12	99.59 93	99.33 10	99.99 8	99.76 6	98.39 4	99.39 93	99.80 59	90.49 200	99.96 78	99.89 22	99.43 131	99.98 58

tpm		93.70 303	93.41 291	94.58 347	95.36 389	87.41 436	97.01 456	96.90 420	90.85 329	96.72 230	94.14 448	90.40 201	96.84 400	90.75 346	88.54 353	99.51 181

dongtai		91.55 355	91.13 348	92.82 413	98.16 216	86.35 443	99.47 284	98.51 133	83.24 452	85.07 441	97.56 318	90.33 202	94.94 468	76.09 479	91.73 327	97.18 334

114514_t		97.41 125	96.83 139	99.14 74	99.51 102	97.83 96	99.89 129	98.27 209	88.48 389	99.06 116	99.66 117	90.30 203	99.64 175	96.32 232	99.97 44	99.96 76

ADS-MVSNet2		93.80 298	93.88 274	93.55 396	97.87 233	85.94 448	94.24 484	96.84 424	90.07 356	96.43 246	94.48 440	90.29 204	95.37 461	87.44 396	97.23 215	99.36 209

ADS-MVSNet		94.79 257	94.02 269	97.11 255	97.87 233	93.79 288	94.24 484	98.16 230	90.07 356	96.43 246	94.48 440	90.29 204	98.19 324	87.44 396	97.23 215	99.36 209

miper_lstm_enhance		91.81 346	91.39 345	93.06 409	97.34 291	89.18 413	99.38 299	96.79 429	86.70 418	87.47 412	95.22 414	90.00 206	95.86 451	88.26 385	81.37 415	94.15 388

c3_l		92.53 333	91.87 333	94.52 350	97.40 281	92.99 318	99.40 293	96.93 417	87.86 400	88.69 384	95.44 399	89.95 207	96.44 424	90.45 351	80.69 426	94.14 392

thres200		96.96 149	96.21 172	99.22 60	98.97 141	98.84 40	99.85 151	99.71 7	93.17 221	96.26 251	98.88 229	89.87 208	99.51 180	94.26 278	94.91 300	99.31 223

tpm cat1		93.51 307	92.52 322	96.47 278	97.77 241	91.47 372	96.13 474	98.06 241	80.98 467	92.91 315	93.78 451	89.66 209	98.87 229	87.03 406	96.39 256	99.09 255

test_fmvsmvis_n_1920		97.67 112	97.59 101	97.91 179	97.02 316	95.34 219	99.95 76	98.45 145	97.87 27	97.02 215	99.59 126	89.64 210	99.98 52	99.41 70	99.34 139	98.42 299

OMC-MVS		97.28 129	97.23 121	97.41 236	99.76 74	93.36 310	99.65 241	97.95 253	96.03 99	97.41 201	99.70 102	89.61 211	99.51 180	96.73 220	98.25 183	99.38 205

DIV-MVS_self_test		92.32 337	91.60 338	94.47 354	97.31 295	92.74 322	99.58 259	96.75 431	86.99 413	87.64 408	95.54 392	89.55 212	96.50 419	88.58 376	82.44 407	94.17 382

cl____		92.31 338	91.58 339	94.52 350	97.33 293	92.77 320	99.57 263	96.78 430	86.97 414	87.56 410	95.51 395	89.43 213	96.62 413	88.60 375	82.44 407	94.16 387

AUN-MVS		93.28 311	92.60 316	95.34 320	98.29 204	90.09 399	99.31 311	98.56 115	91.80 296	96.35 250	98.00 304	89.38 214	98.28 316	92.46 313	69.22 483	97.64 323

tfpn200view9		96.79 158	95.99 182	99.19 63	98.94 143	98.82 41	99.78 185	99.71 7	92.86 237	96.02 261	98.87 236	89.33 215	99.50 182	93.84 287	94.57 304	99.27 233

thres400		96.78 160	95.99 182	99.16 70	98.94 143	98.82 41	99.78 185	99.71 7	92.86 237	96.02 261	98.87 236	89.33 215	99.50 182	93.84 287	94.57 304	99.16 246

thres100view900		96.74 166	95.92 194	99.18 64	98.90 153	98.77 49	99.74 208	99.71 7	92.59 257	95.84 264	98.86 238	89.25 217	99.50 182	93.84 287	94.57 304	99.27 233

thres600view7		96.69 169	95.87 198	99.14 74	98.90 153	98.78 48	99.74 208	99.71 7	92.59 257	95.84 264	98.86 238	89.25 217	99.50 182	93.44 300	94.50 307	99.16 246

eth_miper_zixun_eth		92.41 336	91.93 331	93.84 387	97.28 298	90.68 385	98.83 380	96.97 410	88.57 387	89.19 376	95.73 384	89.24 219	96.69 411	89.97 360	81.55 413	94.15 388

EC-MVSNet		97.38 127	97.24 120	97.80 186	97.41 279	95.64 204	99.99 8	97.06 398	94.59 143	99.63 60	99.32 156	89.20 220	98.14 326	98.76 109	99.23 144	99.62 150

PVSNet_Blended_VisFu		97.27 130	96.81 141	98.66 115	98.81 159	96.67 156	99.92 104	98.64 91	94.51 146	96.38 249	98.49 279	89.05 221	99.88 126	97.10 198	98.34 177	99.43 198

fmvsm_l_conf0.5_n_9		98.55 41	98.23 52	99.49 38	99.10 126	98.50 67	99.99 8	98.70 80	98.14 17	99.94 2	99.68 113	89.02 222	99.98 52	99.89 22	99.61 106	99.99 27

PVSNet_BlendedMVS		96.05 207	95.82 199	96.72 271	99.59 93	96.99 140	99.95 76	99.10 34	94.06 177	98.27 165	95.80 379	89.00 223	99.95 87	99.12 81	87.53 368	93.24 441

PVSNet_Blended		97.94 83	97.64 97	98.83 102	99.59 93	96.99 140	100.00 1	99.10 34	95.38 119	98.27 165	99.08 193	89.00 223	99.95 87	99.12 81	99.25 142	99.57 165

PRO-TEST		97.72 108	97.51 104	98.33 148	98.30 202	97.18 128	99.90 118	97.46 313	95.98 102	99.62 63	99.42 143	88.95 225	98.28 316	99.12 81	98.88 161	99.52 176

fmvsm_s_conf0.5_n_6		98.27 64	97.96 76	99.23 59	97.66 256	98.11 80	99.98 24	98.64 91	97.85 28	99.87 15	99.72 96	88.86 226	99.93 106	99.64 56	99.36 137	99.63 149

IterMVS-LS		92.69 329	92.11 327	94.43 358	96.80 337	92.74 322	99.45 289	96.89 421	88.98 373	89.65 360	95.38 404	88.77 227	96.34 432	90.98 340	82.04 410	94.22 377
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		93.73 301	93.40 292	94.74 339	96.80 337	92.69 325	99.06 344	97.67 285	88.96 375	91.39 330	99.02 201	88.75 228	97.30 366	91.07 336	87.85 361	94.22 377

UA-Net		96.54 179	95.96 188	98.27 153	98.23 209	95.71 199	98.00 433	98.45 145	93.72 195	98.41 158	99.27 167	88.71 229	99.66 173	91.19 334	97.69 198	99.44 197

MAR-MVS		97.43 120	97.19 123	98.15 161	99.47 104	94.79 248	99.05 348	98.76 73	92.65 253	98.66 141	99.82 54	88.52 230	99.98 52	98.12 150	99.63 100	99.67 135
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
MonoMVSNet		94.82 254	94.43 254	95.98 295	94.54 402	90.73 383	99.03 351	97.06 398	93.16 222	93.15 311	95.47 398	88.29 231	97.57 353	97.85 168	91.33 331	99.62 150

mvs_anonymous		95.65 232	95.03 238	97.53 218	98.19 213	95.74 197	99.33 306	97.49 311	90.87 328	90.47 342	97.10 332	88.23 232	97.16 373	95.92 239	97.66 201	99.68 133

MVS_Test		96.46 183	95.74 202	98.61 119	98.18 214	97.23 126	99.31 311	97.15 371	91.07 324	98.84 126	97.05 336	88.17 233	98.97 219	94.39 273	97.50 203	99.61 154

mvsmamba		96.94 150	96.73 145	97.55 216	97.99 226	94.37 268	99.62 248	97.70 282	93.13 225	98.42 157	97.92 309	88.02 234	98.75 254	98.78 107	99.01 155	99.52 176

fmvsm_l_conf0.5_n_3		98.41 54	98.08 65	99.39 47	99.12 125	98.29 72	99.98 24	98.64 91	98.14 17	99.86 17	99.76 74	87.99 235	99.97 65	99.72 48	99.54 113	99.91 97

CANet		98.27 64	97.82 88	99.63 20	99.72 83	99.10 26	99.98 24	98.51 133	97.00 60	98.52 150	99.71 99	87.80 236	99.95 87	99.75 43	99.38 135	99.83 107

E3new		96.75 163	96.43 161	97.71 198	97.79 239	94.83 245	99.80 179	97.33 331	93.52 202	97.49 198	99.31 159	87.73 237	98.83 233	97.52 183	97.40 208	99.48 186

jason		97.24 132	96.86 137	98.38 147	95.73 373	97.32 121	99.97 43	97.40 321	95.34 121	98.60 148	99.54 135	87.70 238	98.56 281	97.94 162	99.47 126	99.25 237
jason: jason.
test_fmvsmconf0.1_n		97.74 105	97.44 110	98.64 117	95.76 370	96.20 180	99.94 94	98.05 243	98.17 14	98.89 125	99.42 143	87.65 239	99.90 115	99.50 63	99.60 109	99.82 109

FIs		94.10 286	93.43 288	96.11 291	94.70 399	96.82 146	99.58 259	98.93 48	92.54 264	89.34 369	97.31 326	87.62 240	97.10 379	94.22 280	86.58 372	94.40 360

guyue		97.15 137	96.82 140	98.15 161	97.56 266	96.25 178	99.71 224	97.84 268	95.75 109	98.13 174	98.65 259	87.58 241	98.82 236	98.29 141	97.91 196	99.36 209

VortexMVS		94.11 285	93.50 286	95.94 297	97.70 251	96.61 159	99.35 304	97.18 364	93.52 202	89.57 364	95.74 381	87.55 242	96.97 390	95.76 244	85.13 386	94.23 374

LuminaMVS		96.63 172	96.21 172	97.87 182	95.58 384	96.82 146	99.12 333	97.67 285	94.47 148	97.88 185	98.31 294	87.50 243	98.71 260	98.07 155	97.29 214	98.10 310

1314		96.84 156	95.96 188	99.48 41	96.74 342	98.52 65	98.31 417	98.86 59	95.82 106	89.91 351	98.98 212	87.49 244	99.96 78	97.80 171	99.73 92	99.96 76

LS3D		95.84 217	95.11 234	98.02 170	99.85 62	95.10 236	98.74 388	98.50 139	87.22 409	93.66 305	99.86 34	87.45 245	99.95 87	90.94 341	99.81 87	99.02 267

FC-MVSNet-test		93.81 297	93.15 302	95.80 306	94.30 408	96.20 180	99.42 291	98.89 52	92.33 275	89.03 379	97.27 328	87.39 246	96.83 402	93.20 303	86.48 373	94.36 362

fmvsm_s_conf0.5_n_8		98.38 58	98.05 67	99.35 51	99.20 119	98.12 79	99.98 24	98.81 67	98.22 8	99.80 29	99.71 99	87.37 247	99.97 65	99.91 20	99.48 123	99.97 68

fmvsm_s_conf0.5_n		97.80 99	97.85 86	97.67 201	99.06 129	94.41 264	99.98 24	98.97 43	97.34 43	99.63 60	99.69 106	87.27 248	99.97 65	99.62 57	99.06 153	98.62 292

RPMNet		89.76 394	87.28 411	97.19 248	96.29 352	92.66 326	92.01 502	98.31 202	70.19 500	96.94 219	85.87 511	87.25 249	99.78 149	62.69 511	95.96 268	99.13 250

UniMVSNet_NR-MVSNet		92.95 320	92.11 327	95.49 311	94.61 401	95.28 226	99.83 164	99.08 36	91.49 305	89.21 374	96.86 346	87.14 250	96.73 407	93.20 303	77.52 446	94.46 354

UniMVSNet (Re)		93.07 318	92.13 326	95.88 301	94.84 396	96.24 179	99.88 132	98.98 41	92.49 268	89.25 371	95.40 401	87.09 251	97.14 375	93.13 307	78.16 441	94.26 370

fmvsm_s_conf0.5_n_9		98.15 74	98.02 69	98.55 126	99.28 114	95.84 192	99.99 8	98.57 109	98.17 14	99.93 4	99.74 89	87.04 252	99.97 65	99.86 28	99.59 110	99.83 107

DP-MVS		94.54 267	93.42 289	97.91 179	99.46 106	94.04 281	98.93 367	97.48 312	81.15 466	90.04 348	99.55 133	87.02 253	99.95 87	88.97 372	98.11 189	99.73 122

fmvsm_s_conf0.5_n_a		97.73 107	97.72 91	97.77 192	98.63 173	94.26 272	99.96 57	98.92 49	97.18 53	99.75 43	99.69 106	87.00 254	99.97 65	99.46 66	98.89 158	99.08 257

PMMVS		96.76 161	96.76 143	96.76 269	98.28 206	92.10 340	99.91 112	97.98 250	94.12 172	99.53 76	99.39 151	86.93 255	98.73 256	96.95 206	97.73 197	99.45 194

viewcassd2359sk11		96.59 175	96.23 169	97.66 203	97.63 260	94.70 250	99.77 191	97.33 331	93.41 207	97.34 203	99.17 185	86.72 256	98.83 233	97.40 186	97.32 212	99.46 189

sasdasda		97.09 142	96.32 166	99.39 47	98.93 145	98.95 31	99.72 219	97.35 327	94.45 150	97.88 185	99.42 143	86.71 257	99.52 178	98.48 127	93.97 314	99.72 124

canonicalmvs		97.09 142	96.32 166	99.39 47	98.93 145	98.95 31	99.72 219	97.35 327	94.45 150	97.88 185	99.42 143	86.71 257	99.52 178	98.48 127	93.97 314	99.72 124

fmvsm_s_conf0.5_n_4		97.75 104	97.86 85	97.42 233	99.01 133	94.69 252	99.97 43	98.76 73	97.91 26	99.87 15	99.76 74	86.70 259	99.93 106	99.67 54	99.12 150	97.64 323

MVS		96.60 174	95.56 210	99.72 15	96.85 334	99.22 23	98.31 417	98.94 44	91.57 303	90.90 336	99.61 125	86.66 260	99.96 78	97.36 187	99.88 77	99.99 27

Effi-MVS+		96.30 195	95.69 204	98.16 158	97.85 235	96.26 174	97.41 446	97.21 361	90.37 349	98.65 143	98.58 271	86.61 261	98.70 263	97.11 197	97.37 209	99.52 176

diffmvs		97.00 147	96.64 149	98.09 165	97.64 258	96.17 183	99.81 173	97.19 362	94.67 142	98.95 121	99.28 163	86.43 262	98.76 252	98.37 135	97.42 206	99.33 216
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmamba		96.61 173	96.34 165	97.42 233	97.26 301	94.37 268	99.83 164	97.16 368	94.51 146	97.89 183	99.26 171	86.38 263	98.66 271	97.70 179	97.06 232	99.23 240

nrg030		93.51 307	92.53 321	96.45 281	94.36 406	97.20 127	99.81 173	97.16 368	91.60 302	89.86 353	97.46 321	86.37 264	97.68 349	95.88 240	80.31 429	94.46 354

AstraMVS		96.57 177	96.46 159	96.91 262	96.79 340	92.50 331	99.90 118	97.38 322	96.02 100	97.79 190	99.32 156	86.36 265	98.99 216	98.26 143	96.33 258	99.23 240

MGCFI-Net		97.00 147	96.22 171	99.34 52	98.86 156	98.80 43	99.67 239	97.30 339	94.31 162	97.77 191	99.41 148	86.36 265	99.50 182	98.38 133	93.90 316	99.72 124

VNet		97.21 134	96.57 153	99.13 78	98.97 141	97.82 97	99.03 351	99.21 32	94.31 162	99.18 107	98.88 229	86.26 267	99.89 120	98.93 95	94.32 308	99.69 132

fmvsm_s_conf0.5_n_11		98.03 80	97.89 83	98.46 139	99.35 110	97.76 100	99.99 8	98.04 244	98.20 10	99.90 8	99.78 67	86.21 268	99.95 87	99.89 22	99.68 95	97.65 322

fmvsm_s_conf0.5_n_7		97.70 111	97.74 90	97.59 214	98.44 190	95.16 234	99.97 43	98.65 88	97.95 25	99.62 63	99.78 67	86.09 269	99.94 96	99.69 52	99.50 121	97.66 321

AdaColmap		97.23 133	96.80 142	98.51 135	99.99 1	95.60 206	99.09 337	98.84 65	93.32 213	96.74 229	99.72 96	86.04 270	100.00 1	98.01 157	99.43 131	99.94 88

fmvsm_s_conf0.5_n_5		98.08 78	97.71 93	99.17 67	98.67 168	97.69 106	99.99 8	98.57 109	97.40 41	99.89 12	99.69 106	85.99 271	99.96 78	99.80 34	99.40 134	99.85 105

fmvsm_s_conf0.5_n_10		98.24 70	97.90 81	99.26 56	99.24 117	97.88 94	99.99 8	98.76 73	98.20 10	99.92 6	99.74 89	85.97 272	99.94 96	99.72 48	99.53 115	99.96 76

Effi-MVS+-dtu		94.53 269	95.30 226	92.22 421	97.77 241	82.54 471	99.59 257	97.06 398	94.92 130	95.29 279	95.37 405	85.81 273	97.89 342	94.80 264	97.07 229	96.23 343

IMVS_0403		95.25 242	94.81 246	96.58 277	96.97 322	91.64 363	98.97 361	97.12 377	92.33 275	95.43 276	98.88 229	85.78 274	98.79 247	92.12 318	95.70 282	99.32 218

onestephybrid01		96.75 163	96.44 160	97.71 198	97.47 275	95.03 237	99.83 164	97.27 349	94.15 170	98.66 141	99.25 174	85.72 275	98.81 240	98.42 131	97.17 223	99.28 230

icg_test_0407_2		95.04 249	94.78 248	95.84 304	96.97 322	91.64 363	98.63 399	97.12 377	92.33 275	95.60 271	98.88 229	85.65 276	96.56 416	92.12 318	95.70 282	99.32 218

IMVS_0407		95.21 243	94.80 247	96.46 280	96.97 322	91.64 363	98.81 382	97.12 377	92.33 275	95.60 271	98.88 229	85.65 276	98.42 294	92.12 318	95.70 282	99.32 218

diffmvs_AUTHOR		96.75 163	96.41 163	97.79 188	97.20 303	95.46 210	99.69 234	97.15 371	94.46 149	98.78 131	99.21 180	85.64 278	98.77 250	98.27 142	97.31 213	99.13 250

CVMVSNet		94.68 264	94.94 242	93.89 386	96.80 337	86.92 441	99.06 344	98.98 41	94.45 150	94.23 300	99.02 201	85.60 279	95.31 463	90.91 342	95.39 293	99.43 198

viewmanbaseed2359cas		96.45 184	96.07 178	97.59 214	97.55 267	94.59 253	99.70 231	97.33 331	93.62 198	97.00 218	99.32 156	85.57 280	98.71 260	97.26 192	97.33 211	99.47 187

xiu_mvs_v1_base_debu		97.43 120	97.06 126	98.55 126	97.74 243	98.14 76	99.31 311	97.86 265	96.43 84	99.62 63	99.69 106	85.56 281	99.68 167	99.05 85	98.31 179	97.83 316

xiu_mvs_v1_base		97.43 120	97.06 126	98.55 126	97.74 243	98.14 76	99.31 311	97.86 265	96.43 84	99.62 63	99.69 106	85.56 281	99.68 167	99.05 85	98.31 179	97.83 316

xiu_mvs_v1_base_debi		97.43 120	97.06 126	98.55 126	97.74 243	98.14 76	99.31 311	97.86 265	96.43 84	99.62 63	99.69 106	85.56 281	99.68 167	99.05 85	98.31 179	97.83 316

E3		96.36 190	95.95 190	97.60 211	97.37 286	94.52 257	99.71 224	97.33 331	93.18 220	97.02 215	99.07 195	85.45 284	98.82 236	97.27 189	97.14 225	99.46 189

casdiffmvs_mvg		96.43 185	95.94 192	97.89 181	97.44 277	95.47 209	99.86 148	97.29 347	93.35 210	96.03 259	99.19 183	85.39 285	98.72 259	97.89 167	97.04 233	99.49 185
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E2		96.36 190	95.95 190	97.60 211	97.41 279	94.52 257	99.71 224	97.33 331	93.20 218	97.02 215	99.07 195	85.37 286	98.82 236	97.27 189	97.14 225	99.46 189

baseline		96.43 185	95.98 184	97.76 194	97.34 291	95.17 233	99.51 276	97.17 366	93.92 185	96.90 221	99.28 163	85.37 286	98.64 274	97.50 184	96.86 243	99.46 189

hybrid		96.53 180	96.15 175	97.67 201	97.39 283	95.12 235	99.80 179	97.15 371	93.38 208	98.23 170	99.16 188	85.20 288	98.70 263	97.92 163	97.15 224	99.20 243

PCF-MVS	94.20 5	95.18 244	94.10 264	98.43 142	98.55 179	95.99 188	97.91 436	97.31 338	90.35 350	89.48 366	99.22 177	85.19 289	99.89 120	90.40 354	98.47 175	99.41 202
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs		96.42 187	95.97 187	97.77 192	97.30 296	94.98 238	99.84 156	97.09 388	93.75 194	96.58 234	99.26 171	85.07 290	98.78 249	97.77 176	97.04 233	99.54 171
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
hybridnocas07		96.57 177	96.16 174	97.81 185	97.36 289	95.32 221	99.81 173	97.12 377	94.17 169	98.02 177	98.90 227	85.05 291	98.80 245	97.85 168	97.18 219	99.32 218

D2MVS		92.76 326	92.59 320	93.27 402	95.13 391	89.54 409	99.69 234	99.38 22	92.26 280	87.59 409	94.61 437	85.05 291	97.79 345	91.59 329	88.01 359	92.47 458

fmvsm_s_conf0.1_n		97.30 128	97.21 122	97.60 211	97.38 284	94.40 266	99.90 118	98.64 91	96.47 83	99.51 80	99.65 119	84.99 293	99.93 106	99.22 78	99.09 151	98.46 296

viewdifsd2359ckpt13		96.19 203	95.77 200	97.45 228	97.62 261	94.40 266	99.70 231	97.23 358	92.76 245	96.63 231	99.05 198	84.96 294	98.64 274	96.65 221	97.35 210	99.31 223

viewdifsd2359ckpt09		96.21 202	95.77 200	97.53 218	97.69 252	94.50 259	99.78 185	97.23 358	92.88 236	96.58 234	99.26 171	84.85 295	98.66 271	96.61 222	97.02 236	99.43 198

viewmambaseed2359dif		95.92 214	95.55 211	97.04 257	97.38 284	93.41 306	99.78 185	96.97 410	91.14 321	96.58 234	99.27 167	84.85 295	98.75 254	96.87 210	97.12 227	98.97 270

usedtu_dtu_shiyan1		92.78 324	91.73 335	95.92 299	93.03 433	96.82 146	99.83 164	97.79 271	90.58 340	90.09 344	95.04 420	84.75 297	96.72 409	88.19 387	86.23 375	94.23 374

FE-MVSNET3		92.78 324	91.73 335	95.92 299	93.03 433	96.82 146	99.83 164	97.79 271	90.58 340	90.09 344	95.04 420	84.75 297	96.72 409	88.20 386	86.23 375	94.23 374

SSM_0407		95.62 233	94.95 241	97.61 210	97.14 304	95.31 222	99.00 354	97.25 353	90.81 331	94.40 293	98.83 243	84.74 299	98.58 278	95.24 251	97.18 219	98.93 272

SSM_0404		95.75 225	95.16 232	97.50 223	97.53 269	95.39 216	99.11 335	97.25 353	90.81 331	95.27 280	98.83 243	84.74 299	98.67 268	95.24 251	97.69 198	98.45 297

fmvsm_s_conf0.1_n_a		97.09 142	96.90 135	97.63 208	95.65 380	94.21 276	99.83 164	98.50 139	96.27 93	99.65 56	99.64 120	84.72 301	99.93 106	99.04 88	98.84 162	98.74 287

BH-w/o		95.71 228	95.38 223	96.68 272	98.49 188	92.28 336	99.84 156	97.50 310	92.12 283	92.06 326	98.79 246	84.69 302	98.67 268	95.29 250	99.66 97	99.09 255

Casviewmamba		96.25 199	95.89 196	97.32 246	97.45 276	93.68 294	99.80 179	97.22 360	93.38 208	96.86 222	99.28 163	84.64 303	98.87 229	97.18 195	97.19 218	99.41 202

Fast-Effi-MVS+		95.02 250	94.19 262	97.52 220	97.88 232	94.55 255	99.97 43	97.08 389	88.85 380	94.47 292	97.96 308	84.59 304	98.41 296	89.84 361	97.10 228	99.59 157

mamba_0408		94.98 252	94.09 265	97.64 205	97.14 304	95.31 222	93.48 494	97.08 389	90.48 345	94.40 293	98.62 264	84.49 305	98.67 268	93.99 282	97.18 219	98.93 272

SSM_04072		94.77 259	94.09 265	96.82 266	97.14 304	95.31 222	93.48 494	97.08 389	90.48 345	94.40 293	98.62 264	84.49 305	96.21 439	93.99 282	97.18 219	98.93 272

PVSNet	91.05 13	97.13 138	96.69 148	98.45 140	99.52 100	95.81 193	99.95 76	99.65 12	94.73 138	99.04 117	99.21 180	84.48 307	99.95 87	94.92 259	98.74 167	99.58 163

WR-MVS_H		91.30 356	90.35 360	94.15 368	94.17 411	92.62 329	99.17 330	98.94 44	88.87 379	86.48 426	94.46 442	84.36 308	96.61 414	88.19 387	78.51 438	93.21 442

CHOSEN 1792x2688		96.81 157	96.53 154	97.64 205	98.91 152	93.07 313	99.65 241	99.80 3	95.64 112	95.39 277	98.86 238	84.35 309	99.90 115	96.98 203	99.16 146	99.95 84

hybridcas		96.09 206	95.62 208	97.50 223	97.37 286	94.44 260	99.84 156	97.16 368	93.16 222	96.03 259	99.21 180	84.19 310	98.65 273	96.53 226	97.07 229	99.42 201

fmvsm_s_conf0.5_n_3		97.95 82	97.66 95	98.81 103	98.99 138	98.07 82	99.98 24	98.81 67	98.18 13	99.89 12	99.70 102	84.15 311	99.97 65	99.76 42	99.50 121	98.39 300

our_test_3		90.39 377	89.48 382	93.12 406	92.40 450	89.57 408	99.33 306	96.35 447	87.84 401	85.30 437	94.99 426	84.14 312	96.09 445	80.38 456	84.56 390	93.71 431

MSDG		94.37 277	93.36 296	97.40 237	98.88 155	93.95 286	99.37 301	97.38 322	85.75 430	90.80 339	99.17 185	84.11 313	99.88 126	86.35 411	98.43 176	98.36 302

E4		96.01 209	95.53 212	97.44 231	97.05 312	94.23 274	99.57 263	97.30 339	92.72 246	96.47 240	99.03 200	83.98 314	98.83 233	96.92 207	96.77 244	99.27 233

dtuplus		95.79 223	95.42 215	96.93 261	97.24 302	93.16 311	99.78 185	96.93 417	91.69 300	96.18 256	99.29 162	83.80 315	98.73 256	96.83 212	97.02 236	98.89 279

pmmvs4		92.10 342	91.07 350	95.18 325	92.82 443	94.96 239	99.48 283	96.83 425	87.45 405	88.66 386	96.56 359	83.78 316	96.83 402	89.29 368	84.77 389	93.75 426

BH-untuned		95.18 244	94.83 244	96.22 289	98.36 197	91.22 374	99.80 179	97.32 337	90.91 327	91.08 333	98.67 256	83.51 317	98.54 285	94.23 279	99.61 106	98.92 275

LCM-MVSNet-Re		92.31 338	92.60 316	91.43 430	97.53 269	79.27 489	99.02 353	91.83 507	92.07 284	80.31 467	94.38 444	83.50 318	95.48 458	97.22 194	97.58 202	99.54 171

E6new		95.83 218	95.39 218	97.14 251	97.00 320	93.58 298	99.31 311	97.30 339	92.57 261	96.45 241	99.01 203	83.44 319	98.81 240	96.80 215	96.66 245	99.04 262

E6		95.83 218	95.39 218	97.14 251	97.00 320	93.58 298	99.31 311	97.30 339	92.57 261	96.45 241	99.01 203	83.44 319	98.81 240	96.80 215	96.66 245	99.04 262

E5new		95.83 218	95.39 218	97.15 249	97.03 313	93.59 296	99.32 309	97.30 339	92.58 259	96.45 241	99.00 207	83.37 321	98.81 240	96.81 213	96.65 247	99.04 262

E5		95.83 218	95.39 218	97.15 249	97.03 313	93.59 296	99.32 309	97.30 339	92.58 259	96.45 241	99.00 207	83.37 321	98.81 240	96.81 213	96.65 247	99.04 262

cdsmvs_eth3d_5k		23.43 522	31.24 517	0.00 543	0.00 567	0.00 570	0.00 555	98.09 237	0.00 562	0.00 563	99.67 115	83.37 321	0.00 564	0.00 562	0.00 562	0.00 559

balanced_ft_v1		96.88 154	96.52 155	97.96 172	98.60 174	94.94 241	99.41 292	97.56 301	93.53 199	99.42 88	97.89 312	83.33 324	99.31 195	99.29 75	99.62 101	99.64 141

DeepC-MVS	94.51 4	96.92 153	96.40 164	98.45 140	99.16 123	95.90 190	99.66 240	98.06 241	96.37 90	94.37 296	99.49 138	83.29 325	99.90 115	97.63 181	99.61 106	99.55 167
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NR-MVSNet		91.56 354	90.22 364	95.60 309	94.05 412	95.76 196	98.25 420	98.70 80	91.16 320	80.78 466	96.64 355	83.23 326	96.57 415	91.41 331	77.73 445	94.46 354

MVStest1		85.03 436	82.76 445	91.83 426	92.95 438	89.16 414	98.57 401	94.82 481	71.68 497	68.54 502	95.11 418	83.17 327	95.66 456	74.69 482	65.32 493	90.65 477

viewdifsd2359ckpt07		95.83 218	95.42 215	97.07 256	97.40 281	93.04 316	99.60 255	97.24 356	92.39 272	96.09 258	99.14 190	83.07 328	98.93 225	97.02 200	96.87 241	99.23 240

viewmacassd2359aftdt		95.93 213	95.45 213	97.36 241	97.09 308	94.12 280	99.57 263	97.26 352	93.05 230	96.50 238	99.17 185	82.76 329	98.68 266	96.61 222	97.04 233	99.28 230

3Dnovator+	91.53 11	96.31 194	95.24 228	99.52 34	96.88 333	98.64 61	99.72 219	98.24 213	95.27 123	88.42 396	98.98 212	82.76 329	99.94 96	97.10 198	99.83 81	99.96 76

QAPM		95.40 238	94.17 263	99.10 80	96.92 328	97.71 102	99.40 293	98.68 84	89.31 366	88.94 380	98.89 228	82.48 331	99.96 78	93.12 308	99.83 81	99.62 150

PatchMatch-RL		96.04 208	95.40 217	97.95 173	99.59 93	95.22 230	99.52 274	99.07 37	93.96 182	96.49 239	98.35 289	82.28 332	99.82 144	90.15 357	99.22 145	98.81 283

GeoE		94.36 279	93.48 287	96.99 259	97.29 297	93.54 302	99.96 57	96.72 433	88.35 393	93.43 306	98.94 223	82.05 333	98.05 333	88.12 391	96.48 254	99.37 207

SD_0403		92.63 332	93.38 293	90.40 444	97.32 294	77.91 491	97.75 441	98.03 246	91.89 290	90.83 338	98.29 296	82.00 334	93.79 482	88.51 380	95.75 279	99.52 176

3Dnovator	91.47 12	96.28 197	95.34 224	99.08 83	96.82 336	97.47 117	99.45 289	98.81 67	95.52 117	89.39 367	99.00 207	81.97 335	99.95 87	97.27 189	99.83 81	99.84 106

v8		90.54 375	89.17 385	94.66 342	93.43 423	93.40 308	99.20 327	96.94 416	85.76 428	87.56 410	94.51 438	81.96 336	97.19 372	84.94 424	78.25 440	93.38 438

RRT-MVS		96.24 200	95.68 206	97.94 176	97.65 257	94.92 242	99.27 321	97.10 385	92.79 243	97.43 200	97.99 306	81.85 337	99.37 194	98.46 129	98.57 170	99.53 175

fmvsm_s_conf0.5_n_2		97.59 115	97.28 118	98.53 132	99.01 133	98.15 74	99.98 24	98.59 105	98.17 14	99.75 43	99.63 123	81.83 338	99.94 96	99.78 37	98.79 165	97.51 331

v148		90.70 370	89.63 375	93.92 383	92.97 436	90.97 376	99.75 204	96.89 421	87.51 403	88.27 400	95.01 423	81.67 339	97.04 385	87.40 398	77.17 451	93.75 426

DU-MVS		92.46 335	91.45 344	95.49 311	94.05 412	95.28 226	99.81 173	98.74 76	92.25 281	89.21 374	96.64 355	81.66 340	96.73 407	93.20 303	77.52 446	94.46 354

Baseline_NR-MVSNet		90.33 380	89.51 380	92.81 414	92.84 440	89.95 403	99.77 191	93.94 495	84.69 443	89.04 378	95.66 386	81.66 340	96.52 418	90.99 339	76.98 452	91.97 466

FMVSNet3		92.69 329	91.58 339	95.99 294	98.29 204	97.42 119	99.26 323	97.62 292	89.80 362	89.68 357	95.32 407	81.62 342	96.27 436	87.01 407	85.65 379	94.29 369

Fast-Effi-MVS+-dtu		93.72 302	93.86 275	93.29 401	97.06 311	86.16 445	99.80 179	96.83 425	92.66 252	92.58 319	97.83 315	81.39 343	97.67 350	89.75 362	96.87 241	96.05 346

CANet_DTU		96.76 161	96.15 175	98.60 120	98.78 161	97.53 111	99.84 156	97.63 289	97.25 51	99.20 104	99.64 120	81.36 344	99.98 52	92.77 312	98.89 158	98.28 304

WB-MVSnew		92.90 321	92.77 313	93.26 403	96.95 327	93.63 295	99.71 224	98.16 230	91.49 305	94.28 298	98.14 299	81.33 345	96.48 422	79.47 460	95.46 290	89.68 490

V42		91.28 358	90.12 369	94.74 339	93.42 424	93.46 304	99.68 237	97.02 402	87.36 406	89.85 355	95.05 419	81.31 346	97.34 361	87.34 399	80.07 431	93.40 436

test_djsdf		92.83 323	92.29 325	94.47 354	91.90 457	92.46 332	99.55 270	97.27 349	91.17 318	89.96 349	96.07 375	81.10 347	96.89 396	94.67 269	88.91 343	94.05 404

ppachtmachnet_test		89.58 398	88.35 401	93.25 404	92.40 450	90.44 392	99.33 306	96.73 432	85.49 433	85.90 434	95.77 380	81.09 348	96.00 449	76.00 480	82.49 406	93.30 439

dtuonly		93.89 292	93.16 301	96.08 293	94.37 405	91.67 362	99.15 332	95.04 478	91.79 297	94.74 285	98.72 251	81.01 349	98.31 311	87.29 400	96.33 258	98.27 305

v1144		91.09 362	89.83 371	94.87 334	93.25 426	93.69 293	99.62 248	96.98 408	86.83 416	89.64 361	94.99 426	80.94 350	97.05 382	85.08 423	81.16 417	93.87 420

v10		90.25 383	88.82 392	94.57 348	93.53 421	93.43 305	99.08 339	96.87 423	85.00 438	87.34 416	94.51 438	80.93 351	97.02 389	82.85 438	79.23 434	93.26 440

fmvsm_s_conf0.1_n_2		97.25 131	96.85 138	98.43 142	98.08 221	98.08 81	99.92 104	97.76 279	98.05 21	99.65 56	99.58 129	80.88 352	99.93 106	99.59 58	98.17 184	97.29 332

EU-MVSNet		90.14 387	90.34 361	89.54 451	92.55 447	81.06 482	98.69 394	98.04 244	91.41 313	86.59 423	96.84 349	80.83 353	93.31 487	86.20 413	81.91 411	94.26 370

casdiffseed414692147		95.07 247	94.26 260	97.50 223	97.01 319	94.70 250	99.58 259	97.02 402	91.27 316	94.66 287	98.82 245	80.79 354	98.55 284	93.39 301	95.79 276	99.27 233

v2v482		91.30 356	90.07 370	95.01 329	93.13 427	93.79 288	99.77 191	97.02 402	88.05 397	89.25 371	95.37 405	80.73 355	97.15 374	87.28 401	80.04 432	94.09 400

WR-MVS		92.31 338	91.25 346	95.48 314	94.45 404	95.29 225	99.60 255	98.68 84	90.10 355	88.07 403	96.89 344	80.68 356	96.80 404	93.14 306	79.67 433	94.36 362

HQP2-MVS												80.65 357

HQP-MVS		94.61 266	94.50 253	94.92 333	95.78 366	91.85 348	99.87 135	97.89 261	96.82 67	93.37 307	98.65 259	80.65 357	98.39 300	97.92 163	89.60 334	94.53 349

XVG-OURS		94.82 254	94.74 250	95.06 328	98.00 225	89.19 411	99.08 339	97.55 302	94.10 173	94.71 286	99.62 124	80.51 359	99.74 158	96.04 237	93.06 326	96.25 341

v144192		90.79 369	89.52 379	94.59 346	93.11 430	92.77 320	99.56 267	96.99 406	86.38 421	89.82 356	94.95 428	80.50 360	97.10 379	83.98 430	80.41 427	93.90 417

HQP_MVS		94.49 273	94.36 256	94.87 334	95.71 376	91.74 355	99.84 156	97.87 263	96.38 87	93.01 312	98.59 268	80.47 361	98.37 306	97.79 174	89.55 337	94.52 351

plane_prior6					95.76 370	91.72 359						80.47 361

KinetiMVS		96.10 204	95.29 227	98.53 132	97.08 309	97.12 133	99.56 267	98.12 236	94.78 135	98.44 155	98.94 223	80.30 363	99.39 193	91.56 330	98.79 165	99.06 259

v7n		89.65 396	88.29 402	93.72 389	92.22 452	90.56 389	99.07 343	97.10 385	85.42 435	86.73 420	94.72 431	80.06 364	97.13 376	81.14 449	78.12 442	93.49 434

TranMVSNet+NR-MVSNet		91.68 353	90.61 356	94.87 334	93.69 419	93.98 285	99.69 234	98.65 88	91.03 325	88.44 391	96.83 350	80.05 365	96.18 440	90.26 356	76.89 454	94.45 359

FMVSNet5		88.32 408	87.47 410	90.88 433	96.90 332	88.39 427	97.28 449	95.68 462	82.60 460	84.67 443	92.40 469	79.83 366	91.16 499	76.39 478	81.51 414	93.09 444

test_fmvsmconf0.01_n		96.39 188	95.74 202	98.32 150	91.47 464	95.56 207	99.84 156	97.30 339	97.74 31	97.89 183	99.35 155	79.62 367	99.85 132	99.25 77	99.24 143	99.55 167

RPSCF		91.80 349	92.79 312	88.83 456	98.15 217	69.87 502	98.11 429	96.60 438	83.93 447	94.33 297	99.27 167	79.60 368	99.46 191	91.99 323	93.16 324	97.18 334

Vis-MVSNet		95.72 226	95.15 233	97.45 228	97.62 261	94.28 271	99.28 319	98.24 213	94.27 167	96.84 224	98.94 223	79.39 369	98.76 252	93.25 302	98.49 174	99.30 226
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dmvs_testset		83.79 446	86.07 418	76.94 489	92.14 453	48.60 531	96.75 463	90.27 511	89.48 364	78.65 476	98.55 275	79.25 370	86.65 514	66.85 500	82.69 403	95.57 347

v1192		90.62 374	89.25 384	94.72 341	93.13 427	93.07 313	99.50 278	97.02 402	86.33 422	89.56 365	95.01 423	79.22 371	97.09 381	82.34 443	81.16 417	94.01 407

CP-MVSNet		91.23 360	90.22 364	94.26 363	93.96 414	92.39 334	99.09 337	98.57 109	88.95 376	86.42 427	96.57 358	79.19 372	96.37 430	90.29 355	78.95 435	94.02 405

MDA-MVSNet_test_wron		85.51 431	83.32 440	92.10 422	90.96 468	88.58 424	99.20 327	96.52 441	79.70 472	57.12 517	92.69 463	79.11 373	93.86 481	77.10 475	77.46 448	93.86 421

Syy-MVS		90.00 390	90.63 355	88.11 465	97.68 253	74.66 498	99.71 224	98.35 193	90.79 335	92.10 324	98.67 256	79.10 374	93.09 489	63.35 508	95.95 270	96.59 339

YYNet1		85.50 432	83.33 439	92.00 423	90.89 469	88.38 428	99.22 326	96.55 440	79.60 473	57.26 516	92.72 462	79.09 375	93.78 483	77.25 474	77.37 449	93.84 422

XVG-OURS-SEG-HR		94.79 257	94.70 251	95.08 327	98.05 223	89.19 411	99.08 339	97.54 304	93.66 196	94.87 284	99.58 129	78.78 376	99.79 147	97.31 188	93.40 321	96.25 341

GA-MVS		93.83 294	92.84 309	96.80 267	95.73 373	93.57 300	99.88 132	97.24 356	92.57 261	92.92 314	96.66 353	78.73 377	97.67 350	87.75 394	94.06 313	99.17 245

dmvs_re		93.20 313	93.15 302	93.34 399	96.54 348	83.81 460	98.71 391	98.51 133	91.39 314	92.37 322	98.56 273	78.66 378	97.83 344	93.89 285	89.74 333	98.38 301

OpenMVS	90.15 15	94.77 259	93.59 282	98.33 148	96.07 358	97.48 116	99.56 267	98.57 109	90.46 347	86.51 424	98.95 221	78.57 379	99.94 96	93.86 286	99.74 91	97.57 328

v1921920		90.46 376	89.12 386	94.50 352	92.96 437	92.46 332	99.49 280	96.98 408	86.10 424	89.61 363	95.30 408	78.55 380	97.03 387	82.17 444	80.89 425	94.01 407

MVP-Stereo		90.93 364	90.45 359	92.37 420	91.25 467	88.76 418	98.05 432	96.17 450	87.27 408	84.04 446	95.30 408	78.46 381	97.27 371	83.78 432	99.70 94	91.09 471
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
anonymousdsp		91.79 351	90.92 351	94.41 359	90.76 471	92.93 319	98.93 367	97.17 366	89.08 368	87.46 413	95.30 408	78.43 382	96.92 393	92.38 314	88.73 348	93.39 437

wanda-best-256-512		87.82 415	85.71 422	94.15 368	86.66 494	91.88 346	99.76 197	97.08 389	79.46 475	88.37 397	92.36 470	78.01 383	96.43 425	88.39 382	61.26 504	94.14 392

FE-blended-shiyan7		87.82 415	85.71 422	94.15 368	86.66 494	91.88 346	99.76 197	97.08 389	79.46 475	88.37 397	92.36 470	78.01 383	96.43 425	88.39 382	61.26 504	94.14 392

usedtu_blend_shiyan5		86.75 423	84.29 431	94.16 366	86.66 494	91.83 350	97.42 444	95.23 473	69.94 501	88.37 397	92.36 470	78.01 383	96.50 419	89.35 366	61.26 504	94.14 392

v1240		90.20 384	88.79 393	94.44 356	93.05 432	92.27 337	99.38 299	96.92 419	85.89 426	89.36 368	94.87 430	77.89 386	97.03 387	80.66 453	81.08 420	94.01 407

blended_shiyan8		87.82 415	85.71 422	94.16 366	86.54 499	91.79 352	99.72 219	97.08 389	79.32 477	88.44 391	92.35 473	77.88 387	96.56 416	88.53 378	61.51 503	94.15 388

blended_shiyan6		87.74 418	85.62 425	94.09 373	86.53 500	91.73 358	99.72 219	97.08 389	79.32 477	88.22 401	92.31 475	77.82 388	96.43 425	88.31 384	61.26 504	94.13 397

CLD-MVS		94.06 290	93.90 273	94.55 349	96.02 360	90.69 384	99.98 24	97.72 281	96.62 78	91.05 335	98.85 241	77.21 389	98.47 287	98.11 151	89.51 339	94.48 353
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_cas_vis1_n_1920		96.59 175	96.23 169	97.65 204	98.22 210	94.23 274	99.99 8	97.25 353	97.77 30	99.58 72	99.08 193	77.10 390	99.97 65	97.64 180	99.45 129	98.74 287

viewdifsd2359ckpt11		94.09 287	93.63 278	95.46 315	96.68 345	88.92 416	99.62 248	97.12 377	93.07 228	95.73 268	99.22 177	77.05 391	98.88 228	96.52 227	87.69 366	98.58 294

viewmsd2359difaftdt		94.09 287	93.64 277	95.46 315	96.68 345	88.92 416	99.62 248	97.13 376	93.07 228	95.73 268	99.22 177	77.05 391	98.89 227	96.52 227	87.70 365	98.58 294

N_pmnet		80.06 460	80.78 456	77.89 487	91.94 456	45.28 536	98.80 385	56.82 539	78.10 483	80.08 469	93.33 455	77.03 393	95.76 455	68.14 496	82.81 402	92.64 453

WB-MVS		76.28 465	77.28 467	73.29 496	81.18 519	54.68 522	97.87 437	94.19 491	81.30 464	69.43 500	90.70 482	77.02 394	82.06 521	35.71 533	68.11 488	83.13 513

COLMAP_ROB	90.47 14	92.18 341	91.49 343	94.25 364	99.00 137	88.04 431	98.42 413	96.70 434	82.30 461	88.43 394	99.01 203	76.97 395	99.85 132	86.11 415	96.50 252	94.86 348
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
cascas		94.64 265	93.61 279	97.74 196	97.82 237	96.26 174	99.96 57	97.78 275	85.76 428	94.00 302	97.54 319	76.95 396	99.21 201	97.23 193	95.43 292	97.76 320

BH-RMVSNet		95.18 244	94.31 259	97.80 186	98.17 215	95.23 229	99.76 197	97.53 306	92.52 266	94.27 299	99.25 174	76.84 397	98.80 245	90.89 343	99.54 113	99.35 213

IMVS_0404		93.83 294	93.17 300	95.80 306	96.97 322	91.64 363	97.78 440	97.12 377	92.33 275	90.87 337	98.88 229	76.78 398	96.43 425	92.12 318	95.70 282	99.32 218

PEN-MVS		90.19 385	89.06 388	93.57 395	93.06 431	90.90 380	99.06 344	98.47 142	88.11 396	85.91 433	96.30 365	76.67 399	95.94 450	87.07 404	76.91 453	93.89 418

CL-MVSNet_self_test		84.50 442	83.15 442	88.53 460	86.00 501	81.79 477	98.82 381	97.35 327	85.12 437	83.62 451	90.91 481	76.66 400	91.40 498	69.53 491	60.36 510	92.40 459

IterMVS		90.91 365	90.17 367	93.12 406	96.78 341	90.42 393	98.89 371	97.05 401	89.03 370	86.49 425	95.42 400	76.59 401	95.02 465	87.22 402	84.09 394	93.93 415
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SSC-MVS		75.42 468	76.40 469	72.49 501	80.68 521	53.62 523	97.42 444	94.06 493	80.42 469	68.75 501	90.14 486	76.54 402	81.66 522	33.25 534	66.34 492	82.19 514

IterMVS-SCA-FT		90.85 368	90.16 368	92.93 411	96.72 343	89.96 402	98.89 371	96.99 406	88.95 376	86.63 422	95.67 385	76.48 403	95.00 466	87.04 405	84.04 397	93.84 422

SCA		94.69 262	93.81 276	97.33 244	97.10 307	94.44 260	98.86 377	98.32 200	93.30 214	96.17 257	95.59 390	76.48 403	97.95 339	91.06 337	97.43 204	99.59 157

ab-mvs		94.69 262	93.42 289	98.51 135	98.07 222	96.26 174	96.49 467	98.68 84	90.31 352	94.54 289	97.00 339	76.30 405	99.71 162	95.98 238	93.38 322	99.56 166

DTE-MVSNet		89.40 400	88.24 403	92.88 412	92.66 446	89.95 403	99.10 336	98.22 216	87.29 407	85.12 439	96.22 367	76.27 406	95.30 464	83.56 434	75.74 458	93.41 435

ACMM	91.95 10	92.88 322	92.52 322	93.98 382	95.75 372	89.08 415	99.77 191	97.52 308	93.00 231	89.95 350	97.99 306	76.17 407	98.46 290	93.63 298	88.87 345	94.39 361
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DSMNet-mixed		88.28 409	88.24 403	88.42 462	89.64 480	75.38 497	98.06 431	89.86 512	85.59 432	88.20 402	92.14 476	76.15 408	91.95 497	78.46 469	96.05 265	97.92 313

VPA-MVSNet		92.70 328	91.55 341	96.16 290	95.09 392	96.20 180	98.88 373	99.00 39	91.02 326	91.82 327	95.29 411	76.05 409	97.96 338	95.62 247	81.19 416	94.30 368

SDMVSNet		94.80 256	93.96 271	97.33 244	98.92 148	95.42 213	99.59 257	98.99 40	92.41 270	92.55 320	97.85 313	75.81 410	98.93 225	97.90 166	91.62 329	97.64 323

TR-MVS		94.54 267	93.56 284	97.49 226	97.96 228	94.34 270	98.71 391	97.51 309	90.30 353	94.51 291	98.69 255	75.56 411	98.77 250	92.82 311	95.99 266	99.35 213

PS-CasMVS		90.63 373	89.51 380	93.99 380	93.83 416	91.70 360	98.98 356	98.52 130	88.48 389	86.15 431	96.53 360	75.46 412	96.31 435	88.83 373	78.86 437	93.95 413

TransMVSNet (Re)		87.25 420	85.28 428	93.16 405	93.56 420	91.03 375	98.54 404	94.05 494	83.69 450	81.09 463	96.16 369	75.32 413	96.40 429	76.69 477	68.41 486	92.06 464

LPG-MVS_test		92.96 319	92.71 314	93.71 390	95.43 387	88.67 421	99.75 204	97.62 292	92.81 240	90.05 346	98.49 279	75.24 414	98.40 298	95.84 241	89.12 341	94.07 401

LGP-MVS_train				93.71 390	95.43 387	88.67 421		97.62 292	92.81 240	90.05 346	98.49 279	75.24 414	98.40 298	95.84 241	89.12 341	94.07 401

ECVR-MVS		95.66 231	95.05 237	97.51 221	98.66 170	93.71 291	98.85 379	98.45 145	94.93 128	96.86 222	98.96 216	75.22 416	99.20 204	95.34 248	98.15 186	99.64 141

test1111		95.57 234	94.98 240	97.37 239	98.56 176	93.37 309	98.86 377	98.45 145	94.95 127	96.63 231	98.95 221	75.21 417	99.11 210	95.02 255	98.14 188	99.64 141

OPM-MVS		93.21 312	92.80 311	94.44 356	93.12 429	90.85 382	99.77 191	97.61 295	96.19 96	91.56 329	98.65 259	75.16 418	98.47 287	93.78 293	89.39 340	93.99 410
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tfpnnormal		89.29 402	87.61 409	94.34 361	94.35 407	94.13 279	98.95 363	98.94 44	83.94 446	84.47 444	95.51 395	74.84 419	97.39 358	77.05 476	80.41 427	91.48 470

AllTest		92.48 334	91.64 337	95.00 330	99.01 133	88.43 425	98.94 364	96.82 427	86.50 419	88.71 382	98.47 283	74.73 420	99.88 126	85.39 419	96.18 262	96.71 337

TestCases				95.00 330	99.01 133	88.43 425		96.82 427	86.50 419	88.71 382	98.47 283	74.73 420	99.88 126	85.39 419	96.18 262	96.71 337

Anonymous20231206		86.32 424	85.42 427	89.02 455	89.11 483	80.53 486	99.05 348	95.28 471	85.43 434	82.82 453	93.92 449	74.40 422	93.44 486	66.99 498	81.83 412	93.08 445

XXY-MVS		91.82 345	90.46 357	95.88 301	93.91 415	95.40 215	98.87 376	97.69 284	88.63 386	87.87 405	97.08 333	74.38 423	97.89 342	91.66 328	84.07 395	94.35 365

ACMP	92.05 9	92.74 327	92.42 324	93.73 388	95.91 364	88.72 420	99.81 173	97.53 306	94.13 171	87.00 418	98.23 297	74.07 424	98.47 287	96.22 234	88.86 346	93.99 410
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	88.28 18	90.29 382	89.05 389	94.02 377	95.08 393	90.15 398	97.19 451	97.43 316	84.91 441	83.99 448	97.06 335	74.00 425	98.28 316	84.08 428	87.71 363	93.62 432
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
gbinet_0.2-2-1-0.02		87.63 419	85.51 426	93.99 380	87.22 489	91.56 370	99.81 173	97.36 326	79.54 474	88.60 388	93.29 459	73.76 426	96.34 432	89.27 369	60.78 509	94.06 403

pm-mvs1		89.36 401	87.81 407	94.01 378	93.40 425	91.93 344	98.62 400	96.48 444	86.25 423	83.86 449	96.14 371	73.68 427	97.04 385	86.16 414	75.73 459	93.04 446

Elysia		94.50 271	93.38 293	97.85 183	96.49 349	96.70 152	98.98 356	97.78 275	90.81 331	96.19 254	98.55 275	73.63 428	98.98 217	89.41 363	98.56 171	97.88 314

StellarMVS		94.50 271	93.38 293	97.85 183	96.49 349	96.70 152	98.98 356	97.78 275	90.81 331	96.19 254	98.55 275	73.63 428	98.98 217	89.41 363	98.56 171	97.88 314

pmmvs5		90.17 386	89.09 387	93.40 398	92.10 455	89.77 406	99.74 208	95.58 465	85.88 427	87.24 417	95.74 381	73.41 430	96.48 422	88.54 377	83.56 399	93.95 413

OurMVSNet-221017-0		89.81 393	89.48 382	90.83 436	91.64 461	81.21 480	98.17 427	95.38 470	91.48 307	85.65 435	97.31 326	72.66 431	97.29 369	88.15 389	84.83 388	93.97 412

jajsoiax		91.92 344	91.18 347	94.15 368	91.35 465	90.95 379	99.00 354	97.42 318	92.61 255	87.38 414	97.08 333	72.46 432	97.36 359	94.53 272	88.77 347	94.13 397

UGNet		95.33 241	94.57 252	97.62 209	98.55 179	94.85 243	98.67 396	99.32 26	95.75 109	96.80 228	96.27 366	72.18 433	99.96 78	94.58 271	99.05 154	98.04 311
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
mvs_tets		91.81 346	91.08 349	94.00 379	91.63 462	90.58 388	98.67 396	97.43 316	92.43 269	87.37 415	97.05 336	71.76 434	97.32 364	94.75 266	88.68 349	94.11 399

SixPastTwentyTwo		88.73 405	88.01 406	90.88 433	91.85 458	82.24 473	98.22 425	95.18 476	88.97 374	82.26 455	96.89 344	71.75 435	96.67 412	84.00 429	82.98 400	93.72 430

test_fmvs1		95.35 240	95.68 206	94.36 360	98.99 138	84.98 454	99.96 57	96.65 436	97.60 35	99.73 48	98.96 216	71.58 436	99.93 106	98.31 139	99.37 136	98.17 306

GBi-Net		90.88 366	89.82 372	94.08 374	97.53 269	91.97 341	98.43 410	96.95 412	87.05 410	89.68 357	94.72 431	71.34 437	96.11 442	87.01 407	85.65 379	94.17 382

test1		90.88 366	89.82 372	94.08 374	97.53 269	91.97 341	98.43 410	96.95 412	87.05 410	89.68 357	94.72 431	71.34 437	96.11 442	87.01 407	85.65 379	94.17 382

FMVSNet2		91.02 363	89.56 377	95.41 318	97.53 269	95.74 197	98.98 356	97.41 320	87.05 410	88.43 394	95.00 425	71.34 437	96.24 438	85.12 422	85.21 384	94.25 372

PVSNet_0	88.03 19	91.80 349	90.27 363	96.38 285	98.27 207	90.46 391	99.94 94	99.61 13	93.99 180	86.26 430	97.39 325	71.13 440	99.89 120	98.77 108	67.05 490	98.79 284

sd_testset		93.55 306	92.83 310	95.74 308	98.92 148	90.89 381	98.24 421	98.85 62	92.41 270	92.55 320	97.85 313	71.07 441	98.68 266	93.93 284	91.62 329	97.64 323

Anonymous20231211		89.86 392	88.44 400	94.13 372	98.93 145	90.68 385	98.54 404	98.26 210	76.28 485	86.73 420	95.54 392	70.60 442	97.56 354	90.82 344	80.27 430	94.15 388

ITE_SJBPF				92.38 418	95.69 379	85.14 452		95.71 461	92.81 240	89.33 370	98.11 300	70.23 443	98.42 294	85.91 417	88.16 358	93.59 433

ACMH	89.72 17	90.64 372	89.63 375	93.66 394	95.64 381	88.64 423	98.55 402	97.45 314	89.03 370	81.62 459	97.61 317	69.75 444	98.41 296	89.37 365	87.62 367	93.92 416
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVS-HIRNet		86.22 425	83.19 441	95.31 322	96.71 344	90.29 394	92.12 501	97.33 331	62.85 509	86.82 419	70.37 526	69.37 445	97.49 356	75.12 481	97.99 194	98.15 307

Anonymous202405211		93.10 317	91.99 330	96.40 283	99.10 126	89.65 407	98.88 373	97.93 255	83.71 449	94.00 302	98.75 248	68.79 446	99.88 126	95.08 254	91.71 328	99.68 133

test20.03		84.72 441	83.99 433	86.91 469	88.19 487	80.62 485	98.88 373	95.94 455	88.36 392	78.87 474	94.62 436	68.75 447	89.11 508	66.52 501	75.82 457	91.00 473

VPNet		91.81 346	90.46 357	95.85 303	94.74 398	95.54 208	98.98 356	98.59 105	92.14 282	90.77 340	97.44 322	68.73 448	97.54 355	94.89 262	77.89 443	94.46 354

K. test v3		88.05 411	87.24 412	90.47 442	91.82 460	82.23 474	98.96 362	97.42 318	89.05 369	76.93 484	95.60 389	68.49 449	95.42 460	85.87 418	81.01 423	93.75 426

ACMH+	89.98 16	90.35 379	89.54 378	92.78 415	95.99 361	86.12 446	98.81 382	97.18 364	89.38 365	83.14 452	97.76 316	68.42 450	98.43 293	89.11 371	86.05 377	93.78 425

MDA-MVSNet-bldmvs		84.09 444	81.52 451	91.81 427	91.32 466	88.00 432	98.67 396	95.92 456	80.22 470	55.60 519	93.32 456	68.29 451	93.60 485	73.76 483	76.61 455	93.82 424

ttmdpeth		88.23 410	87.06 413	91.75 428	89.91 479	87.35 437	98.92 370	95.73 459	87.92 399	84.02 447	96.31 364	68.23 452	96.84 400	86.33 412	76.12 456	91.06 472

MS-PatchMatch		90.65 371	90.30 362	91.71 429	94.22 410	85.50 451	98.24 421	97.70 282	88.67 384	86.42 427	96.37 363	67.82 453	98.03 334	83.62 433	99.62 101	91.60 468

KD-MVS_self_test		83.59 448	82.06 448	88.20 464	86.93 491	80.70 484	97.21 450	96.38 445	82.87 457	82.49 454	88.97 492	67.63 454	92.32 494	73.75 484	62.30 502	91.58 469

LFMVS		94.75 261	93.56 284	98.30 151	99.03 131	95.70 200	98.74 388	97.98 250	87.81 402	98.47 154	99.39 151	67.43 455	99.53 177	98.01 157	95.20 298	99.67 135

MIMVSNet		90.30 381	88.67 396	95.17 326	96.45 351	91.64 363	92.39 500	97.15 371	85.99 425	90.50 341	93.19 460	66.95 456	94.86 471	82.01 445	93.43 320	99.01 268

dtuonlycased		86.10 426	85.82 421	86.95 468	91.84 459	79.57 488	99.27 321	94.89 479	86.79 417	79.46 473	94.46 442	66.85 457	90.93 502	80.41 455	78.44 439	90.34 479

test_vis1_n_1920		95.44 237	95.31 225	95.82 305	98.50 186	88.74 419	99.98 24	97.30 339	97.84 29	99.85 21	99.19 183	66.82 458	99.97 65	98.82 104	99.46 128	98.76 285

XVG-ACMP-BASELINE		91.22 361	90.75 352	92.63 417	93.73 418	85.61 449	98.52 406	97.44 315	92.77 244	89.90 352	96.85 347	66.64 459	98.39 300	92.29 315	88.61 350	93.89 418

Anonymous20240529		92.10 342	90.65 354	96.47 278	98.82 158	90.61 387	98.72 390	98.67 87	75.54 489	93.90 304	98.58 271	66.23 460	99.90 115	94.70 268	90.67 332	98.90 278

lessismore_v0				90.53 440	90.58 472	80.90 483		95.80 457		77.01 483	95.84 378	66.15 461	96.95 391	83.03 437	75.05 461	93.74 429

USDC		90.00 390	88.96 390	93.10 408	94.81 397	88.16 429	98.71 391	95.54 466	93.66 196	83.75 450	97.20 329	65.58 462	98.31 311	83.96 431	87.49 369	92.85 450

pmmvs-eth3d		84.03 445	81.97 449	90.20 445	84.15 510	87.09 439	98.10 430	94.73 484	83.05 455	74.10 494	87.77 499	65.56 463	94.01 478	81.08 450	69.24 482	89.49 493

Anonymous20240521		85.15 435	83.81 437	89.16 454	88.32 485	82.69 469	98.80 385	95.74 458	79.72 471	81.53 460	90.99 479	65.38 464	94.16 477	72.69 485	81.11 419	90.63 478

LF4IMVS		89.25 403	88.85 391	90.45 443	92.81 444	81.19 481	98.12 428	94.79 482	91.44 309	86.29 429	97.11 331	65.30 465	98.11 328	88.53 378	85.25 383	92.07 463

new_pmnet		84.49 443	82.92 443	89.21 453	90.03 477	82.60 470	96.89 460	95.62 464	80.59 468	75.77 489	89.17 491	65.04 466	94.79 472	72.12 487	81.02 422	90.23 481

SSC-MVS3.2		89.59 397	88.66 397	92.38 418	94.29 409	86.12 446	99.49 280	97.66 288	90.28 354	88.63 387	95.18 415	64.46 467	96.88 398	85.30 421	82.66 404	94.14 392

CMPMVS	61.59 21	84.75 440	85.14 429	83.57 477	90.32 474	62.54 511	96.98 457	97.59 299	74.33 493	69.95 499	96.66 353	64.17 468	98.32 310	87.88 393	88.41 355	89.84 488
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_0402		85.58 429	83.94 435	90.50 441	93.81 417	85.04 453	98.55 402	95.20 475	76.01 486	79.72 472	95.13 416	64.15 469	96.26 437	66.04 504	86.88 371	90.21 482

TDRefinement		84.76 439	82.56 446	91.38 431	74.58 529	84.80 457	97.36 448	94.56 488	84.73 442	80.21 468	96.12 374	63.56 470	98.39 300	87.92 392	63.97 497	90.95 475

mmtdpeth		88.52 406	87.75 408	90.85 435	95.71 376	83.47 466	98.94 364	94.85 480	88.78 381	97.19 209	89.58 488	63.29 471	98.97 219	98.54 123	62.86 499	90.10 485

UnsupCasMVSNet_eth		85.52 430	83.99 433	90.10 447	89.36 482	83.51 465	96.65 464	97.99 248	89.14 367	75.89 488	93.83 450	63.25 472	93.92 479	81.92 446	67.90 489	92.88 449

tt0805		91.28 358	90.18 366	94.60 345	96.26 354	87.55 434	98.39 415	98.72 78	89.00 372	89.22 373	98.47 283	62.98 473	98.96 222	90.57 348	88.00 360	97.28 333

new-patchmatchnet		81.19 454	79.34 462	86.76 470	82.86 515	80.36 487	97.92 434	95.27 472	82.09 462	72.02 496	86.87 506	62.81 474	90.74 503	71.10 488	63.08 498	89.19 496

mvs5depth		84.87 438	82.90 444	90.77 437	85.59 504	84.84 456	91.10 508	93.29 501	83.14 454	85.07 441	94.33 445	62.17 475	97.32 364	78.83 468	72.59 473	90.14 484

TinyColmap		87.87 414	86.51 415	91.94 424	95.05 394	85.57 450	97.65 442	94.08 492	84.40 445	81.82 458	96.85 347	62.14 476	98.33 309	80.25 458	86.37 374	91.91 467

test_fmvs1_n		94.25 282	94.36 256	93.92 383	97.68 253	83.70 461	99.90 118	96.57 439	97.40 41	99.67 54	98.88 229	61.82 477	99.92 112	98.23 145	99.13 148	98.14 309

VDDNet		93.12 316	91.91 332	96.76 269	96.67 347	92.65 328	98.69 394	98.21 220	82.81 458	97.75 192	99.28 163	61.57 478	99.48 188	98.09 153	94.09 312	98.15 307

pmmvs6		85.69 428	83.84 436	91.26 432	90.00 478	84.41 458	97.82 438	96.15 451	75.86 487	81.29 462	95.39 403	61.21 479	96.87 399	83.52 435	73.29 466	92.50 457

VDD-MVS		93.77 299	92.94 308	96.27 288	98.55 179	90.22 396	98.77 387	97.79 271	90.85 329	96.82 226	99.42 143	61.18 480	99.77 152	98.95 93	94.13 311	98.82 282

FE-MVSNET		81.05 456	78.81 464	87.79 466	81.98 517	83.70 461	98.23 423	91.78 508	81.27 465	74.29 492	87.44 502	60.92 481	90.67 504	64.92 506	68.43 485	89.01 498

testgi		89.01 404	88.04 405	91.90 425	93.49 422	84.89 455	99.73 215	95.66 463	93.89 189	85.14 438	98.17 298	59.68 482	94.66 474	77.73 472	88.88 344	96.16 345

FE-MVSNET2		83.57 449	81.36 452	90.20 445	82.83 516	87.59 433	98.28 419	96.04 453	85.33 436	74.13 493	87.45 501	59.16 483	93.26 488	79.12 466	69.91 478	89.77 489

FMVSNet1		88.50 407	86.64 414	94.08 374	95.62 383	91.97 341	98.43 410	96.95 412	83.00 456	86.08 432	94.72 431	59.09 484	96.11 442	81.82 447	84.07 395	94.17 382

DeepMVS_CX				82.92 481	95.98 363	58.66 518		96.01 454	92.72 246	78.34 478	95.51 395	58.29 485	98.08 330	82.57 439	85.29 382	92.03 465

UniMVSNet_ETH3D		90.06 389	88.58 398	94.49 353	94.67 400	88.09 430	97.81 439	97.57 300	83.91 448	88.44 391	97.41 323	57.44 486	97.62 352	91.41 331	88.59 352	97.77 319

pmmvs3		80.27 459	77.77 465	87.76 467	80.32 522	82.43 472	98.23 423	91.97 506	72.74 496	78.75 475	87.97 498	57.30 487	90.99 501	70.31 489	62.37 501	89.87 487

OpenMVS_ROB	79.82 20	83.77 447	81.68 450	90.03 448	88.30 486	82.82 468	98.46 407	95.22 474	73.92 494	76.00 487	91.29 478	55.00 488	96.94 392	68.40 493	88.51 354	90.34 479

test_fmvs2		89.47 399	89.70 374	88.77 459	94.54 402	75.74 494	99.83 164	94.70 486	94.71 139	91.08 333	96.82 351	54.46 489	97.78 347	92.87 310	88.27 356	92.80 451

tmp_tt		65.23 483	62.94 486	72.13 502	44.90 561	50.03 530	81.05 529	89.42 516	38.45 525	48.51 527	99.90 23	54.09 490	78.70 526	91.84 327	18.26 551	87.64 504

tt0320		83.56 450	81.15 453	90.77 437	92.77 445	83.58 463	96.83 462	95.52 467	63.26 507	81.36 461	92.54 464	53.26 491	95.77 454	80.45 454	74.38 463	92.96 447

EGC-MVSNET		69.38 473	63.76 485	86.26 472	90.32 474	81.66 479	96.24 473	93.85 496	0.99 561	3.22 562	92.33 474	52.44 492	92.92 491	59.53 519	84.90 387	84.21 511

test_vis1_n		93.61 305	93.03 305	95.35 319	95.86 365	86.94 440	99.87 135	96.36 446	96.85 65	99.54 75	98.79 246	52.41 493	99.83 142	98.64 118	98.97 156	99.29 228

MIMVSNet1		82.58 452	80.51 457	88.78 457	86.68 493	84.20 459	96.65 464	95.41 469	78.75 480	78.59 477	92.44 466	51.88 494	89.76 505	65.26 505	78.95 435	92.38 461

EG-PatchMatch MVS		85.35 433	83.81 437	89.99 449	90.39 473	81.89 476	98.21 426	96.09 452	81.78 463	74.73 490	93.72 453	51.56 495	97.12 378	79.16 465	88.61 350	90.96 474

ArgMatch-Sym		85.85 427	85.07 430	88.21 463	92.84 440	77.63 492	98.42 413	94.70 486	89.91 359	84.33 445	96.72 352	51.42 496	94.89 470	82.48 440	74.80 462	92.10 462

ArgMatch-SfM		85.25 434	84.17 432	88.48 461	92.99 435	77.23 493	97.92 434	94.24 490	90.50 344	85.08 440	95.65 387	49.84 497	95.83 452	81.06 451	70.22 477	92.39 460

sc_t1		85.01 437	82.46 447	92.67 416	92.44 449	83.09 467	97.39 447	95.72 460	65.06 505	85.64 436	96.16 369	49.50 498	97.34 361	84.86 425	75.39 460	97.57 328

tt0320-xc		82.94 451	80.35 458	90.72 439	92.90 439	83.54 464	96.85 461	94.73 484	63.12 508	79.85 471	93.77 452	49.43 499	95.46 459	80.98 452	71.54 474	93.16 443

UnsupCasMVSNet_bld		79.97 462	77.03 468	88.78 457	85.62 503	81.98 475	93.66 490	97.35 327	75.51 490	70.79 498	83.05 514	48.70 500	94.91 469	78.31 470	60.29 511	89.46 494

test_vis1_rt		86.87 422	86.05 419	89.34 452	96.12 356	78.07 490	99.87 135	83.54 524	92.03 287	78.21 479	89.51 490	45.80 501	99.91 113	96.25 233	93.11 325	90.03 486

test_method		80.79 457	79.70 460	84.08 476	92.83 442	67.06 506	99.51 276	95.42 468	54.34 519	81.07 464	93.53 454	44.48 502	92.22 496	78.90 467	77.23 450	92.94 448

APD_test1		81.15 455	80.92 455	81.86 482	92.45 448	59.76 517	96.04 477	93.61 499	73.29 495	77.06 482	96.64 355	44.28 503	96.16 441	72.35 486	82.52 405	89.67 491

mvsany_test3		82.12 453	81.14 454	85.06 474	81.87 518	70.41 501	97.09 454	92.14 505	91.27 316	77.84 480	88.73 493	39.31 504	95.49 457	90.75 346	71.24 475	89.29 495

usedtu_dtu_shiyan2		75.87 467	72.37 472	86.39 471	76.18 527	75.49 496	96.53 466	93.82 497	64.74 506	72.53 495	88.48 494	37.67 505	91.12 500	64.13 507	57.22 514	92.56 454

MASt3R-SfM		78.94 463	79.57 461	77.07 488	84.15 510	50.74 527	91.56 504	92.34 504	83.22 453	80.84 465	94.16 447	36.67 506	92.30 495	79.45 461	73.71 465	88.16 501

PM-MVS		80.47 458	78.88 463	85.26 473	83.79 513	72.22 499	95.89 480	91.08 509	85.71 431	76.56 486	88.30 495	36.64 507	93.90 480	82.39 442	69.57 481	89.66 492

LoFTR		74.41 470	70.88 473	84.99 475	86.56 498	67.85 504	93.74 489	89.63 514	69.46 502	54.95 520	87.39 503	30.76 508	96.92 393	61.37 514	64.06 496	90.19 483

DenseAffine		75.91 466	73.39 470	83.47 478	89.52 481	71.86 500	93.39 496	89.29 517	71.44 498	66.83 503	90.32 485	30.65 509	89.67 506	68.20 495	60.88 508	88.88 499

RoMa-SfM		74.91 469	72.77 471	81.35 483	88.00 488	67.35 505	93.55 493	86.23 522	68.27 503	66.79 504	92.92 461	30.40 510	87.68 510	66.14 503	62.62 500	89.02 497

ambc				83.23 479	77.17 525	62.61 510	87.38 515	94.55 489		76.72 485	86.65 507	30.16 511	96.36 431	84.85 426	69.86 479	90.73 476

Gipuma		66.95 482	65.00 482	72.79 497	91.52 463	67.96 503	66.16 537	95.15 477	47.89 522	58.54 515	67.99 534	29.74 512	87.54 513	50.20 526	77.83 444	62.87 533
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EMVS		51.44 502	51.22 503	52.11 519	70.71 534	44.97 537	94.04 486	75.66 531	35.34 530	42.40 537	61.56 543	28.93 513	65.87 535	27.64 541	24.73 544	45.49 540

test_fmvs3		79.99 461	80.17 459	79.45 485	84.02 512	62.83 509	99.05 348	93.49 500	88.29 394	80.06 470	86.65 507	28.09 514	88.00 509	88.63 374	73.27 467	87.54 505

MatchFormer		70.84 472	66.72 479	83.19 480	85.99 502	64.61 508	93.58 492	88.62 518	59.32 514	50.64 523	82.31 518	28.00 515	96.79 405	52.52 525	59.50 512	88.18 500

test_f		78.40 464	77.59 466	80.81 484	80.82 520	62.48 512	96.96 458	93.08 502	83.44 451	74.57 491	84.57 513	27.95 516	92.63 492	84.15 427	72.79 469	87.32 506

E-PMN		52.30 499	52.18 500	52.67 518	71.51 533	45.40 535	93.62 491	76.60 530	36.01 528	43.50 534	64.13 539	27.11 517	67.31 534	31.06 535	26.06 543	45.30 543

PDCNetPlus		59.83 486	57.26 489	67.55 506	76.18 527	56.71 520	87.01 516	45.27 549	59.54 513	48.80 526	83.01 515	26.63 518	76.54 528	62.12 513	26.78 542	69.40 529

SP-DiffGlue		56.84 488	55.72 490	60.19 513	65.70 541	40.86 540	81.89 524	60.28 536	34.62 532	50.39 525	76.88 522	26.61 519	58.81 540	48.21 527	56.94 515	80.90 521

MVS_clip		48.84 504	50.24 504	44.65 522	64.05 544	23.54 562	58.84 541	20.46 563	18.73 548	60.84 510	89.57 489	25.96 520	29.22 559	62.25 512	51.44 524	81.19 519

ALIKED-NN		54.48 493	52.67 497	59.89 515	90.79 470	45.45 534	81.25 528	55.75 543	34.99 531	44.87 530	71.98 524	25.50 521	74.36 531	21.88 544	47.04 528	59.85 535

FPMVS		68.72 477	68.72 475	68.71 504	65.95 540	44.27 539	95.97 479	94.74 483	51.13 521	53.26 521	90.50 483	25.11 522	83.00 519	60.80 515	80.97 424	78.87 524

ALIKED-LG		54.29 494	52.28 498	60.32 511	88.90 484	45.51 533	81.66 525	56.33 540	38.60 524	42.62 536	70.81 525	25.00 523	75.20 530	19.87 546	46.76 530	60.24 534

RoMa-HiRes		69.18 474	67.02 476	75.65 493	83.52 514	60.31 516	90.80 511	76.82 529	62.46 510	62.85 507	90.44 484	24.75 524	83.07 518	60.58 516	50.97 526	83.58 512

SP-LightGlue		55.29 490	53.65 493	60.20 512	85.58 505	39.12 542	86.36 521	57.52 538	32.34 535	44.34 532	67.75 535	24.36 525	59.32 539	29.62 537	54.98 517	82.17 515

SP-SuperGlue		55.29 490	53.71 492	60.00 514	85.11 506	38.86 544	86.96 517	57.95 537	32.77 533	44.54 531	68.00 533	23.90 526	59.51 538	29.61 538	54.59 518	81.63 518

DKM		72.18 471	69.80 474	79.34 486	86.79 492	65.15 507	92.70 498	84.00 523	67.67 504	61.97 509	89.63 487	23.69 527	85.17 516	67.39 497	54.35 519	87.70 503

SP-NN		55.28 492	53.59 494	60.34 510	86.63 497	39.01 543	86.70 518	56.31 541	31.08 536	43.77 533	68.45 532	23.39 528	60.24 536	29.19 539	56.76 516	81.77 517

PMMVS2		67.15 481	64.15 484	76.14 492	70.56 535	62.07 513	93.89 487	87.52 519	58.09 515	60.02 511	78.32 520	22.38 529	84.54 517	59.56 518	47.03 529	81.80 516

SP-MNN		53.97 495	52.04 501	59.73 516	84.72 507	38.63 545	86.51 519	55.94 542	29.25 537	40.20 539	67.48 536	22.18 530	59.59 537	27.79 540	54.33 520	80.98 520

DKM-HiRes		68.91 475	66.34 481	76.62 491	84.17 509	60.69 514	90.78 512	78.55 527	62.17 511	58.82 514	87.54 500	20.94 531	82.56 520	63.05 509	51.00 525	86.61 507

ALIKED-MNN		52.51 498	50.15 505	59.60 517	90.05 476	44.33 538	81.60 526	54.93 546	32.36 534	40.96 538	68.77 530	20.90 532	75.30 529	20.00 545	41.78 533	59.18 536

XFeat-NN		42.54 505	42.87 509	41.54 524	59.73 552	27.86 551	69.53 535	45.34 548	24.36 538	37.16 540	64.79 537	20.84 533	51.40 543	30.01 536	34.12 538	45.36 542

testf1		68.38 478	66.92 477	72.78 498	78.80 523	50.36 528	90.95 509	87.35 520	55.47 517	58.95 512	88.14 496	20.64 534	87.60 511	57.28 520	64.69 494	80.39 522

APD_test2		68.38 478	66.92 477	72.78 498	78.80 523	50.36 528	90.95 509	87.35 520	55.47 517	58.95 512	88.14 496	20.64 534	87.60 511	57.28 520	64.69 494	80.39 522

LCM-MVSNet		67.77 480	64.73 483	76.87 490	62.95 546	56.25 521	89.37 514	93.74 498	44.53 523	61.99 508	80.74 519	20.42 536	86.53 515	69.37 492	59.50 512	87.84 502

XFeat-MNN		41.51 506	41.24 510	42.32 523	55.40 557	28.19 550	69.39 536	46.53 547	23.57 539	34.47 542	63.21 541	20.04 537	52.41 542	27.43 542	31.08 541	46.37 539

test123		37.68 508	39.14 511	33.31 526	19.94 565	24.83 559	98.36 416	9.75 566	15.53 558	51.31 522	87.14 505	19.62 538	17.74 561	47.10 528	3.47 561	57.36 537

VLMVS		51.63 500	52.90 496	47.80 521	47.64 560	20.83 563	69.98 533	55.61 544	20.15 542	63.34 506	87.24 504	19.48 539	43.90 547	62.94 510	49.76 527	78.65 525

ANet_high		56.10 489	52.24 499	67.66 505	49.27 559	56.82 519	83.94 523	82.02 525	70.47 499	33.28 544	64.54 538	17.23 540	69.16 533	45.59 529	23.85 546	77.02 526

test_vis3_rt		68.82 476	66.69 480	75.21 495	76.24 526	60.41 515	96.44 468	68.71 533	75.13 491	50.54 524	69.52 529	16.42 541	96.32 434	80.27 457	66.92 491	68.89 530

ELoFTR		64.32 484	60.56 487	75.60 494	73.46 532	53.20 524	86.50 520	80.09 526	60.74 512	45.95 529	82.48 517	16.05 542	89.20 507	56.48 524	43.34 531	84.38 510

VLMVS_CLIP		52.57 497	53.54 495	49.65 520	41.84 562	19.27 564	69.54 534	70.45 532	22.22 540	56.57 518	86.16 509	15.89 543	54.77 541	66.88 499	52.29 523	74.91 528

GLUNet-SfM		51.10 503	46.61 507	64.56 507	61.54 550	39.88 541	79.38 531	65.13 535	36.09 527	33.36 543	69.94 527	14.50 544	78.76 525	42.46 531	17.10 552	75.02 527

SIFT-NN		35.94 509	36.54 512	34.16 525	73.93 531	29.52 547	62.74 538	37.28 550	19.65 543	27.91 546	49.19 545	11.66 545	46.35 544	9.19 548	37.30 534	26.61 544

testmvs		40.60 507	44.45 508	29.05 536	19.49 566	14.11 568	99.68 237	18.47 564	20.74 541	64.59 505	98.48 282	10.95 546	17.09 562	56.66 523	11.01 558	55.94 538

SIFT-NN-NCMNet		33.88 511	34.14 514	33.10 528	66.88 539	28.42 549	60.42 539	36.72 552	19.15 544	24.06 548	47.14 549	10.24 547	44.77 546	8.72 549	33.94 539	26.10 546

SIFT-NN-UMatch		31.23 514	31.05 518	31.79 531	60.08 551	27.23 556	58.49 542	33.65 553	19.14 545	17.30 553	47.31 547	10.12 548	42.88 549	8.67 552	24.67 545	25.27 548

SIFT-MNN		34.10 510	34.41 513	33.17 527	68.99 537	28.51 548	60.22 540	36.81 551	19.08 546	24.04 549	47.28 548	10.06 549	45.04 545	8.72 549	34.47 537	25.97 547

SIFT-NN-CMatch		31.71 513	31.56 516	32.16 529	62.58 547	27.53 555	56.45 544	33.28 554	19.00 547	23.65 550	47.34 546	10.05 550	42.72 550	8.71 551	22.96 547	26.24 545

SIFT-NN-PointCN		29.63 516	29.72 520	29.36 535	57.55 554	23.55 561	56.07 546	30.57 557	17.99 554	20.99 551	45.21 553	9.94 551	39.33 555	8.40 553	20.81 548	25.20 549

PMatch-SfM		62.12 485	58.57 488	72.76 500	74.34 530	52.97 525	84.95 522	65.57 534	56.89 516	46.61 528	85.70 512	9.51 552	80.54 524	60.53 517	43.03 532	84.77 508

SIFT-NCM-Cal		31.73 512	31.67 515	31.91 530	67.18 538	27.55 554	58.36 543	33.09 555	18.38 550	14.93 556	45.16 554	8.60 553	43.82 548	7.62 558	31.68 540	24.36 550

SIFT-ConvMatch		30.09 515	29.76 519	31.09 532	65.16 543	27.56 553	54.13 547	31.17 556	18.55 549	17.88 552	45.89 551	8.40 554	42.26 552	8.11 554	18.51 550	23.46 552

SIFT-UMatch		29.40 517	28.87 521	30.98 533	62.08 549	26.57 557	56.09 545	29.45 558	18.31 551	15.86 555	46.00 550	8.23 555	42.54 551	7.99 555	15.81 553	23.85 551

SIFT-CM-Cal		28.34 518	27.90 522	29.63 534	63.75 545	25.98 558	50.66 550	26.18 560	18.12 553	16.88 554	44.64 555	8.08 556	39.70 553	7.65 557	15.19 555	23.22 553

PMatch-Up-SfM		57.92 487	53.93 491	69.90 503	69.97 536	46.69 532	81.36 527	55.29 545	51.90 520	43.17 535	82.54 516	7.86 557	78.44 527	57.13 522	36.17 536	84.58 509

SIFT-UM-Cal		27.47 519	27.02 523	28.83 537	62.12 548	24.58 560	53.60 548	23.46 561	18.14 552	12.85 558	45.56 552	7.49 558	39.45 554	7.68 556	12.30 556	22.45 554

PMVS	49.05 23	53.75 496	51.34 502	60.97 509	40.80 563	34.68 546	74.82 532	89.62 515	37.55 526	28.67 545	72.12 523	7.09 559	81.63 523	43.17 530	68.21 487	66.59 532
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SIFT-PCN-Cal		24.67 521	24.81 525	24.24 539	56.13 556	18.04 566	49.05 552	23.39 562	16.07 556	12.99 557	40.17 557	6.97 560	34.68 556	6.71 559	11.81 557	19.99 556

SIFT-PointCN		25.49 520	25.71 524	24.84 538	56.17 555	18.65 565	51.37 549	26.53 559	16.31 555	12.78 559	39.87 558	6.41 561	34.09 557	6.51 560	15.42 554	21.77 555

wuyk23d		20.37 524	20.84 527	18.99 541	65.34 542	27.73 552	50.43 551	7.67 567	9.50 559	8.01 561	6.34 560	6.13 562	26.24 560	23.40 543	10.69 559	2.99 558

MVE	53.74 22	51.54 501	47.86 506	62.60 508	59.56 553	50.93 526	79.41 530	77.69 528	35.69 529	36.27 541	61.76 542	5.79 563	69.63 532	37.97 532	36.61 535	67.24 531
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SIFT-NCMNet		21.21 523	21.22 526	21.17 540	52.99 558	16.41 567	42.12 553	14.05 565	15.89 557	10.70 560	35.85 559	5.14 564	29.82 558	5.80 561	8.44 560	17.28 557

MVS_baseline		18.28 525	19.10 528	15.85 542	22.71 564	1.80 569	10.32 554	3.08 568	1.00 560	27.16 547	68.73 531	2.83 565	0.36 563	17.05 547	18.98 549	45.38 541

mmdepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

monomultidepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

test_blank		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.02 561	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

uanet_test		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

DCPMVS		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

sosnet-low-res		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

sosnet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

uncertanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

Regformer		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

ab-mvs-re		8.28 526	11.04 529	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	99.40 149	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

uanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 562	0.00 566	0.00 564	0.00 562	0.00 562	0.00 559

Meshroom													0.00 564
: In preparation.
AliceVision / Meshro													0.00 564
: In preparation.
AliceVision_Meshroom													0.00 564
: In preparation.
PatchmatchNet2					0.00 567	86.19 444	98.94 364	96.51 442	78.40 481
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														68.29 494	82.87 401	92.70 452
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													95.80 453
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
aaatest				99.60 25	99.96 9	98.79 44	99.97 43	98.88 55	96.36 91	99.07 114	99.93 12		100.00 1	99.98 9	99.96 48	99.99 27

WAC-MVS						90.97 376								86.10 416

FOURS1					99.92 37	97.66 108	99.95 76	98.36 191	95.58 114	99.52 78

MSC_two_6792asdad				99.93 2	99.91 45	99.80 2		98.41 176					100.00 1	99.96 13	100.00 1	100.00 1

No_MVS				99.93 2	99.91 45	99.80 2		98.41 176					100.00 1	99.96 13	100.00 1	100.00 1

eth-test2					0.00 567

eth-test					0.00 567

IU-MVS					99.93 29	99.31 13		98.41 176	97.71 32	99.84 24				100.00 1	100.00 1	100.00 1

save fliter					99.82 66	98.79 44	99.96 57	98.40 180	97.66 34

test_0728_SECOND				99.82 8	99.94 18	99.47 9	99.95 76	98.43 158					100.00 1	99.99 5	100.00 1	100.00 1

GSMVS																99.59 157

test_part2					99.89 51	99.25 21				99.49 81

MTGPA								98.28 207

MTMP							99.87 135	96.49 443

gm-plane-assit					96.97 322	93.76 290			91.47 308		98.96 216		98.79 247	94.92 259

test9_res														99.71 50	99.99 21	100.00 1

agg_prior2														99.48 65	100.00 1	100.00 1

agg_prior					99.93 29	98.77 49		98.43 158		99.63 60			99.85 132

test_prior4						98.05 84	99.94 94

test_prior				99.43 42	99.94 18	98.49 68		98.65 88					99.80 145			99.99 27

旧先验2							99.46 288		94.21 168	99.85 21			99.95 87	96.96 205

新几何2							99.40 293

无先验							99.49 280	98.71 79	93.46 204				100.00 1	94.36 274		99.99 27

原ACMM2							99.90 118

testdata2													99.99 40	90.54 350

testdata1							99.28 319		96.35 92

plane_prior7					95.71 376	91.59 369

plane_prior5								97.87 263					98.37 306	97.79 174	89.55 337	94.52 351

plane_prior4											98.59 268

plane_prior3						91.64 363			96.63 76	93.01 312

plane_prior2							99.84 156		96.38 87

plane_prior1					95.73 373

plane_prior						91.74 355	99.86 148		96.76 71						89.59 336

n2								0.00 569

nn								0.00 569

door-mid								89.69 513

test11								98.44 150

door								90.31 510

HQP5-MVS						91.85 348

HQP-NCC					95.78 366		99.87 135		96.82 67	93.37 307

ACMP_Plane					95.78 366		99.87 135		96.82 67	93.37 307

BP-MVS														97.92 163

HQP4-MVS										93.37 307			98.39 300			94.53 349

HQP3-MVS								97.89 261							89.60 334

NP-MVS					95.77 369	91.79 352					98.65 259

ACMMP++_ref															87.04 370

ACMMP++															88.23 357

High-resolution multi-view benchmark