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		95.38 227	95.07 224	96.32 274	99.32 112	96.60 156	99.76 186	98.85 63	96.65 72	87.83 391	96.05 361	99.52 1	98.11 313	96.58 213	81.07 405	94.25 358

CHOSEN 280x420		99.01 17	99.03 10	98.95 95	99.38 107	98.87 35	98.46 391	99.42 21	97.03 57	99.02 116	99.09 184	99.35 2	98.21 308	99.73 45	99.78 88	99.77 116

GG-mvs-BLEND				98.54 128	98.21 206	98.01 84	93.87 470	98.52 128		97.92 172	97.92 296	99.02 3	97.94 326	98.17 142	99.58 110	99.67 133

gg-mvs-nofinetune		93.51 293	91.86 320	98.47 135	97.72 243	97.96 89	92.62 476	98.51 131	74.70 473	97.33 195	69.59 492	98.91 4	97.79 330	97.77 169	99.56 111	99.67 133

TestfortrainingZip				99.90 5	99.97 3	99.70 5	99.97 42	98.89 52	96.02 98	99.99 1	99.96 3	97.97 5	100.00 1		99.65 97	100.00 1

test_0728_THIRD									96.48 78	99.83 23	99.91 19	97.87 6	100.00 1	99.92 16	100.00 1	100.00 1

baseline2		96.71 163	96.49 152	97.37 229	95.63 368	95.96 185	99.74 196	98.88 55	92.94 223	91.61 313	98.97 206	97.72 7	98.62 265	94.83 250	98.08 189	97.53 316

BP-MVS1		98.33 59	98.18 56	98.81 101	97.44 269	97.98 86	99.96 56	98.17 222	94.88 130	98.77 129	99.59 125	97.59 8	99.08 210	98.24 139	98.93 155	99.36 203

SteuartSystems-ACMMP		99.02 16	98.97 14	99.18 63	98.72 163	97.71 100	99.98 24	98.44 148	96.85 62	99.80 27	99.91 19	97.57 9	99.85 130	99.44 66	99.99 21	99.99 25
Skip Steuart: Steuart Systems R&D Blog.
thisisatest0515		97.41 122	97.02 128	98.59 121	97.71 245	97.52 109	99.97 42	98.54 123	91.83 283	97.45 190	99.04 191	97.50 10	99.10 209	94.75 253	96.37 247	99.16 235

PC_three_1452									96.96 60	99.80 27	99.79 63	97.49 11	100.00 1	99.99 5	99.98 32	100.00 1

test_one_0601					99.94 17	99.30 13		98.41 173	96.63 73	99.75 41	99.93 12	97.49 11

thisisatest0530		97.10 136	96.72 142	98.22 152	97.60 257	96.70 148	99.92 103	98.54 123	91.11 308	97.07 205	98.97 206	97.47 13	99.03 212	93.73 282	96.09 252	98.92 263

tttt0517		96.85 151	96.49 152	97.92 174	97.48 268	95.89 187	99.85 147	98.54 123	90.72 325	96.63 221	98.93 218	97.47 13	99.02 213	93.03 295	95.76 264	98.85 267

DVP-MVS++		99.26 6	99.09 9	99.77 9	99.91 44	99.31 11	99.95 75	98.43 156	96.48 78	99.80 27	99.93 12	97.44 15	100.00 1	99.92 16	99.98 32	100.00 1

OPU-MVS				99.93 2	99.89 50	99.80 2	99.96 56				99.80 59	97.44 15	100.00 1	100.00 1	99.98 32	100.00 1

MSP-MVS		99.09 10	99.12 5	98.98 92	99.93 28	97.24 122	99.95 75	98.42 168	97.50 38	99.52 75	99.88 29	97.43 17	99.71 160	99.50 61	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		99.15 8	99.00 12	99.60 24	99.96 9	98.79 42	99.97 42	98.88 55	95.89 102	99.07 111	99.93 12	97.36 18	100.00 1	99.98 9	99.96 46	99.99 25

TestfortrainingZip a		99.09 10	98.87 19	99.76 11	99.96 9	99.27 19	99.97 42	98.88 55	96.36 88	99.07 111	99.93 12	97.36 18	100.00 1	98.32 133	99.96 46	100.00 1

NCCC		99.37 2	99.25 2	99.71 17	99.96 9	99.15 24	99.97 42	98.62 98	98.02 22	99.90 7	99.95 4	97.33 20	100.00 1	99.54 58	100.00 1	100.00 1

MVSTER		95.53 223	95.22 217	96.45 268	98.56 174	97.72 99	99.91 111	97.67 280	92.38 263	91.39 315	97.14 316	97.24 21	97.30 351	94.80 251	87.85 346	94.34 353

DVP-MVS		99.30 4	99.16 3	99.73 14	99.93 28	99.29 16	99.95 75	98.32 197	97.28 45	99.83 23	99.91 19	97.22 22	100.00 1	99.99 5	100.00 1	99.89 97
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 28	99.29 16	99.96 56	98.42 168	97.28 45	99.86 16	99.94 5	97.22 22

test_241102_TWO								98.43 156	97.27 47	99.80 27	99.94 5	97.18 24	100.00 1	100.00 1	100.00 1	100.00 1

DPM-MVS		98.83 24	98.46 36	99.97 1	99.33 110	99.92 1	99.96 56	98.44 148	97.96 23	99.55 70	99.94 5	97.18 24	100.00 1	93.81 277	99.94 59	99.98 57

GDP-MVS		97.88 86	97.59 100	98.75 106	97.59 258	97.81 96	99.95 75	97.37 319	94.44 150	99.08 109	99.58 128	97.13 26	99.08 210	94.99 243	98.17 181	99.37 201

CNVR-MVS		99.40 1	99.26 1	99.84 7	99.98 2	99.51 7	99.98 24	98.69 82	98.20 9	99.93 3	99.98 2	96.82 27	100.00 1	99.75 41	100.00 1	99.99 25

WBMVS		94.52 257	94.03 255	95.98 281	98.38 191	96.68 151	99.92 103	97.63 284	90.75 324	89.64 346	95.25 397	96.77 28	96.90 379	94.35 263	83.57 383	94.35 351

UBG		97.84 91	97.69 93	98.29 149	98.38 191	96.59 158	99.90 117	98.53 126	93.91 181	98.52 144	98.42 274	96.77 28	99.17 205	98.54 119	96.20 249	99.11 242

SED-MVS		99.28 5	99.11 7	99.77 9	99.93 28	99.30 13	99.96 56	98.43 156	97.27 47	99.80 27	99.94 5	96.71 30	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 28	99.30 13		98.43 156	97.26 49	99.80 27	99.88 29	96.71 30	100.00 1

DPE-MVS		99.26 6	99.10 8	99.74 13	99.89 50	99.24 21	99.87 133	98.44 148	97.48 39	99.64 57	99.94 5	96.68 32	99.99 40	99.99 5	100.00 1	99.99 25
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
segment_acmp												96.68 32

UWE-MVS		96.79 154	96.72 142	97.00 247	98.51 182	93.70 281	99.71 212	98.60 101	92.96 222	97.09 203	98.34 278	96.67 34	98.85 227	92.11 308	96.50 242	98.44 285

patch_mono-2		98.24 69	99.12 5	95.59 296	99.67 88	86.91 427	99.95 75	98.89 52	97.60 34	99.90 7	99.76 73	96.54 35	99.98 51	99.94 14	99.82 85	99.88 98

PAPM		98.60 37	98.42 38	99.14 73	96.05 345	98.96 28	99.90 117	99.35 24	96.68 71	98.35 156	99.66 116	96.45 36	98.51 274	99.45 65	99.89 74	99.96 75

MCST-MVS		99.32 3	99.14 4	99.86 6	99.97 3	99.59 6	99.97 42	98.64 91	98.47 3	99.13 106	99.92 18	96.38 37	100.00 1	99.74 43	100.00 1	100.00 1

ME-MVS		99.07 12	98.89 17	99.59 27	99.93 28	98.79 42	99.95 75	98.80 72	95.89 102	99.28 98	99.93 12	96.28 38	99.98 51	99.98 9	99.96 46	99.99 25

ET-MVSNet_ETH3D		94.37 264	93.28 285	97.64 198	98.30 198	97.99 85	99.99 8	97.61 290	94.35 156	71.57 478	99.45 141	96.23 39	95.34 443	96.91 200	85.14 370	99.59 154

EPP-MVSNet		96.69 164	96.60 147	96.96 249	97.74 238	93.05 302	99.37 288	98.56 113	88.75 366	95.83 254	99.01 195	96.01 40	98.56 270	96.92 198	97.20 214	99.25 228

test_prior2							99.95 75		95.78 105	99.73 46	99.76 73	96.00 41		99.78 35	100.00 1

train_agg		98.88 23	98.65 27	99.59 27	99.92 36	98.92 31	99.96 56	98.43 156	94.35 156	99.71 48	99.86 34	95.94 42	99.85 130	99.69 50	99.98 32	99.99 25

test_8					99.92 36	98.88 34	99.96 56	98.43 156	94.35 156	99.69 50	99.85 38	95.94 42	99.85 130

MSLP-MVS++		99.13 9	99.01 11	99.49 37	99.94 17	98.46 67	99.98 24	98.86 60	97.10 53	99.80 27	99.94 5	95.92 44	100.00 1	99.51 59	100.00 1	100.00 1

TEST9					99.92 36	98.92 31	99.96 56	98.43 156	93.90 182	99.71 48	99.86 34	95.88 45	99.85 130

test_yl		97.83 92	97.37 111	99.21 60	99.18 119	97.98 86	99.64 233	99.27 27	91.43 297	97.88 176	98.99 202	95.84 46	99.84 138	98.82 101	95.32 280	99.79 112

DCV-MVSNet		97.83 92	97.37 111	99.21 60	99.18 119	97.98 86	99.64 233	99.27 27	91.43 297	97.88 176	98.99 202	95.84 46	99.84 138	98.82 101	95.32 280	99.79 112

DP-MVS Recon		98.41 53	98.02 68	99.56 30	99.97 3	98.70 53	99.92 103	98.44 148	92.06 276	98.40 154	99.84 49	95.68 48	100.00 1	98.19 141	99.71 92	99.97 67

旧先验1					99.76 73	97.52 109		98.64 91			99.85 38	95.63 49			99.94 59	99.99 25

SMA-MVS		98.76 29	98.48 35	99.62 22	99.87 56	98.87 35	99.86 144	98.38 184	93.19 210	99.77 39	99.94 5	95.54 50	100.00 1	99.74 43	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		96.74 161	96.26 162	98.16 155	97.36 279	96.48 160	99.96 56	98.29 203	91.93 279	95.77 255	98.07 289	95.54 50	98.29 300	90.55 335	98.89 156	99.70 125

APDe-MVS		99.06 14	98.91 15	99.51 34	99.94 17	98.76 50	99.91 111	98.39 180	97.20 51	99.46 79	99.85 38	95.53 52	99.79 145	99.86 27	100.00 1	99.99 25
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
testing3-2		97.72 106	97.43 109	98.60 118	98.55 177	97.11 131	100.00 1	99.23 31	93.78 186	97.90 173	98.73 240	95.50 53	99.69 164	98.53 121	94.63 287	98.99 257

testing11		97.48 116	97.27 116	98.10 161	98.36 194	96.02 183	99.92 103	98.45 143	93.45 201	98.15 166	98.70 243	95.48 54	99.22 198	97.85 162	95.05 284	99.07 246

PLC	95.54 3	97.93 83	97.89 82	98.05 165	99.82 65	94.77 242	99.92 103	98.46 142	93.93 179	97.20 199	99.27 163	95.44 55	99.97 64	97.41 177	99.51 118	99.41 197
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 18	99.63 19	99.90 47	99.02 27	99.95 75	98.56 113	97.56 37	99.44 81	99.85 38	95.38 56	100.00 1	99.31 71	99.99 21	99.87 100

PHI-MVS		98.41 53	98.21 53	99.03 85	99.86 58	97.10 132	99.98 24	98.80 72	90.78 323	99.62 61	99.78 67	95.30 57	100.00 1	99.80 32	99.93 65	99.99 25

myMVS_eth3d28		97.86 88	97.59 100	98.68 110	98.50 184	97.26 121	99.92 103	98.55 119	93.79 185	98.26 161	98.75 238	95.20 58	99.48 186	98.93 92	96.40 245	99.29 221

test-mter		96.39 180	95.93 184	97.78 186	97.02 303	95.44 207	99.96 56	98.21 217	91.81 285	95.55 261	96.38 346	95.17 59	98.27 304	90.42 338	98.83 160	99.64 139

patchmatchnet-post											91.70 458	95.12 60	97.95 324

MDTV_nov1_ep13			95.69 194		97.90 226	94.15 267	95.98 460	98.44 148	93.12 216	97.98 170	95.74 366	95.10 61	98.58 267	90.02 344	96.92 230

IB-MVS	92.85 6	94.99 238	93.94 259	98.16 155	97.72 243	95.69 198	99.99 8	98.81 68	94.28 162	92.70 303	96.90 329	95.08 62	99.17 205	96.07 224	73.88 446	99.60 153
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 36	98.57 61		98.52 128	92.34 264	99.31 94	99.83 51	95.06 63	99.80 143	99.70 49	99.97 42

CDS-MVSNet		96.34 184	96.07 169	97.13 242	97.37 277	94.96 232	99.53 260	97.91 255	91.55 291	95.37 266	98.32 279	95.05 64	97.13 361	93.80 278	95.75 265	99.30 219
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Patchmatch-test		92.65 317	91.50 328	96.10 279	96.85 320	90.49 375	91.50 481	97.19 354	82.76 441	90.23 328	95.59 374	95.02 65	98.00 320	77.41 454	96.98 229	99.82 107

CostFormer		96.10 194	95.88 187	96.78 256	97.03 300	92.55 317	97.08 437	97.83 264	90.04 343	98.72 134	94.89 413	95.01 66	98.29 300	96.54 214	95.77 263	99.50 179

TSAR-MVS + GP.		98.60 37	98.51 34	98.86 99	99.73 80	96.63 153	99.97 42	97.92 254	98.07 19	98.76 132	99.55 132	95.00 67	99.94 94	99.91 19	97.68 197	99.99 25

CDPH-MVS		98.65 35	98.36 45	99.49 37	99.94 17	98.73 51	99.87 133	98.33 195	93.97 176	99.76 40	99.87 32	94.99 68	99.75 154	98.55 118	100.00 1	99.98 57

原ACMM1				98.96 94	99.73 80	96.99 136		98.51 131	94.06 172	99.62 61	99.85 38	94.97 69	99.96 76	95.11 240	99.95 54	99.92 93

TSAR-MVS + MP.		98.93 20	98.77 22	99.41 44	99.74 77	98.67 54	99.77 180	98.38 184	96.73 69	99.88 13	99.74 88	94.89 70	99.59 174	99.80 32	99.98 32	99.97 67
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
testing99		97.17 132	96.91 130	97.95 170	98.35 196	95.70 196	99.91 111	98.43 156	92.94 223	97.36 193	98.72 241	94.83 71	99.21 199	97.00 192	94.64 286	98.95 259

testing91		97.16 133	96.90 131	97.97 168	98.35 196	95.67 199	99.91 111	98.42 168	92.91 225	97.33 195	98.72 241	94.81 72	99.21 199	96.98 194	94.63 287	99.03 254

test12				99.43 41	99.74 77	98.56 62		98.40 177		99.65 54		94.76 73	99.75 154		99.98 32	99.99 25

fmvsm_l_conf0.5_n_a		99.00 18	98.91 15	99.28 53	99.21 117	97.91 91	99.98 24	98.85 63	98.25 5	99.92 5	99.75 81	94.72 74	99.97 64	99.87 25	99.64 98	99.95 83

sam_mvs1												94.72 74				99.59 154

SF-MVS		98.67 33	98.40 39	99.50 35	99.77 72	98.67 54	99.90 117	98.21 217	93.53 194	99.81 25	99.89 27	94.70 76	99.86 129	99.84 29	99.93 65	99.96 75

reproduce-ours		98.78 27	98.67 24	99.09 80	99.70 85	97.30 119	99.74 196	98.25 208	97.10 53	99.10 107	99.90 23	94.59 77	99.99 40	99.77 37	99.91 71	99.99 25

our_new_method		98.78 27	98.67 24	99.09 80	99.70 85	97.30 119	99.74 196	98.25 208	97.10 53	99.10 107	99.90 23	94.59 77	99.99 40	99.77 37	99.91 71	99.99 25

SD-MVS		98.92 21	98.70 23	99.56 30	99.70 85	98.73 51	99.94 93	98.34 194	96.38 84	99.81 25	99.76 73	94.59 77	99.98 51	99.84 29	99.96 46	99.97 67
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 41		99.87 56		99.91 111	98.33 195	93.22 208	99.78 38	99.89 27	94.57 80	99.85 130	99.84 29	99.97 42

reproduce_model		98.75 30	98.66 26	99.03 85	99.71 83	97.10 132	99.73 203	98.23 212	97.02 58	99.18 104	99.90 23	94.54 81	99.99 40	99.77 37	99.90 73	99.99 25

test_post											63.35 497	94.43 82	98.13 312

EPMVS		96.53 173	96.01 172	98.09 162	98.43 189	96.12 182	96.36 451	99.43 20	93.53 194	97.64 184	95.04 404	94.41 83	98.38 291	91.13 321	98.11 186	99.75 118

新几何1				99.42 43	99.75 76	98.27 71		98.63 97	92.69 240	99.55 70	99.82 54	94.40 84	100.00 1	91.21 319	99.94 59	99.99 25

MDTV_nov1_ep13_2view						96.26 170	96.11 457		91.89 280	98.06 168		94.40 84		94.30 264		99.67 133

PAPM_NR		98.12 75	97.93 78	98.70 109	99.94 17	96.13 180	99.82 164	98.43 156	94.56 142	97.52 186	99.70 101	94.40 84	99.98 51	97.00 192	99.98 32	99.99 25

dcpmvs_2		97.42 121	98.09 63	95.42 303	99.58 96	87.24 423	99.23 311	96.95 399	94.28 162	98.93 120	99.73 92	94.39 87	99.16 207	99.89 21	99.82 85	99.86 102

miper_enhance_ethall		94.36 266	93.98 257	95.49 297	98.68 165	95.24 223	99.73 203	97.29 341	93.28 207	89.86 338	95.97 362	94.37 88	97.05 367	92.20 302	84.45 376	94.19 366

XVS		98.70 32	98.55 31	99.15 71	99.94 17	97.50 111	99.94 93	98.42 168	96.22 92	99.41 86	99.78 67	94.34 89	99.96 76	98.92 94	99.95 54	99.99 25

X-MVStestdata		93.83 280	92.06 315	99.15 71	99.94 17	97.50 111	99.94 93	98.42 168	96.22 92	99.41 86	41.37 501	94.34 89	99.96 76	98.92 94	99.95 54	99.99 25

balanced_conf03		98.27 63	97.99 70	99.11 78	98.64 170	98.43 68	99.47 271	97.79 266	94.56 142	99.74 44	98.35 276	94.33 91	99.25 196	99.12 79	99.96 46	99.64 139

CP-MVS		98.45 48	98.32 47	98.87 98	99.96 9	96.62 154	99.97 42	98.39 180	94.43 151	98.90 121	99.87 32	94.30 92	100.00 1	99.04 85	99.99 21	99.99 25

MVSMamba_PlusPlus		97.83 92	97.45 106	98.99 90	98.60 172	98.15 72	99.58 247	97.74 275	90.34 336	99.26 100	98.32 279	94.29 93	99.23 197	99.03 88	99.89 74	99.58 160

sam_mvs												94.25 94

Patchmatch-RL test		86.90 407	85.98 406	89.67 436	84.45 478	75.59 476	89.71 487	92.43 484	86.89 399	77.83 462	90.94 461	94.22 95	93.63 464	87.75 380	69.61 460	99.79 112

HFP-MVS		98.56 39	98.37 43	99.14 73	99.96 9	97.43 115	99.95 75	98.61 99	94.77 134	99.31 94	99.85 38	94.22 95	100.00 1	98.70 109	99.98 32	99.98 57

fmvsm_l_conf0.5_n		98.94 19	98.84 20	99.25 56	99.17 121	97.81 96	99.98 24	98.86 60	98.25 5	99.90 7	99.76 73	94.21 97	99.97 64	99.87 25	99.52 115	99.98 57

PatchmatchNet		95.94 201	95.45 202	97.39 228	97.83 231	94.41 254	96.05 458	98.40 177	92.86 227	97.09 203	95.28 396	94.21 97	98.07 317	89.26 356	98.11 186	99.70 125
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
DeepPCF-MVS	95.94 2	97.71 107	98.98 13	93.92 369	99.63 90	81.76 462	99.96 56	98.56 113	99.47 1	99.19 103	99.99 1	94.16 99	100.00 1	99.92 16	99.93 65	100.00 1

APD-MVS		98.62 36	98.35 46	99.41 44	99.90 47	98.51 64	99.87 133	98.36 188	94.08 169	99.74 44	99.73 92	94.08 100	99.74 156	99.42 67	99.99 21	99.99 25
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
region2R		98.54 41	98.37 43	99.05 83	99.96 9	97.18 125	99.96 56	98.55 119	94.87 131	99.45 80	99.85 38	94.07 101	100.00 1	98.67 111	100.00 1	99.98 57

PAPR		98.52 43	98.16 58	99.58 29	99.97 3	98.77 47	99.95 75	98.43 156	95.35 118	98.03 169	99.75 81	94.03 102	99.98 51	98.11 146	99.83 81	99.99 25

MG-MVS		98.91 22	98.65 27	99.68 18	99.94 17	99.07 26	99.64 233	99.44 19	97.33 44	99.00 117	99.72 95	94.03 102	99.98 51	98.73 108	100.00 1	100.00 1

MVS_111021_HR		98.72 31	98.62 29	99.01 89	99.36 108	97.18 125	99.93 100	99.90 1	96.81 67	98.67 136	99.77 71	93.92 104	99.89 118	99.27 74	99.94 59	99.96 75

tpmrst		96.27 190	95.98 175	97.13 242	97.96 223	93.15 299	96.34 452	98.17 222	92.07 274	98.71 135	95.12 401	93.91 105	98.73 249	94.91 248	96.62 239	99.50 179

test-LLR		96.47 174	96.04 171	97.78 186	97.02 303	95.44 207	99.96 56	98.21 217	94.07 170	95.55 261	96.38 346	93.90 106	98.27 304	90.42 338	98.83 160	99.64 139

test0.0.03 1		93.86 279	93.61 266	94.64 329	95.02 381	92.18 325	99.93 100	98.58 105	94.07 170	87.96 389	98.50 266	93.90 106	94.96 448	81.33 432	93.17 308	96.78 322

ETVMVS		97.03 142	96.64 145	98.20 153	98.67 166	97.12 129	99.89 127	98.57 107	91.10 309	98.17 165	98.59 256	93.86 108	98.19 309	95.64 233	95.24 282	99.28 223

test222					99.55 97	97.41 117	99.34 292	98.55 119	91.86 282	99.27 99	99.83 51	93.84 109			99.95 54	99.99 25

dp		95.05 235	94.43 242	96.91 250	97.99 221	92.73 311	96.29 454	97.98 246	89.70 347	95.93 251	94.67 419	93.83 110	98.45 279	86.91 395	96.53 241	99.54 168

ACMMPR		98.50 44	98.32 47	99.05 83	99.96 9	97.18 125	99.95 75	98.60 101	94.77 134	99.31 94	99.84 49	93.73 111	100.00 1	98.70 109	99.98 32	99.98 57

EPNet		98.49 45	98.40 39	98.77 105	99.62 91	96.80 147	99.90 117	99.51 16	97.60 34	99.20 101	99.36 152	93.71 112	99.91 111	97.99 154	98.71 165	99.61 151
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
alignmvs		97.81 96	97.33 113	99.25 56	98.77 160	98.66 56	99.99 8	98.44 148	94.40 155	98.41 152	99.47 138	93.65 113	99.42 190	98.57 117	94.26 295	99.67 133

testdata				98.42 142	99.47 103	95.33 216		98.56 113	93.78 186	99.79 36	99.85 38	93.64 114	99.94 94	94.97 244	99.94 59	100.00 1

EI-MVSNet-Vis-set		98.27 63	98.11 62	98.75 106	99.83 64	96.59 158	99.40 280	98.51 131	95.29 120	98.51 146	99.76 73	93.60 115	99.71 160	98.53 121	99.52 115	99.95 83

UWE-MVS-28		95.95 200	96.49 152	94.34 347	98.51 182	89.99 386	99.39 284	98.57 107	93.14 214	97.33 195	98.31 281	93.44 116	94.68 453	93.69 284	95.98 255	98.34 290

mPP-MVS		98.39 56	98.20 54	98.97 93	99.97 3	96.92 139	99.95 75	98.38 184	95.04 124	98.61 140	99.80 59	93.39 117	100.00 1	98.64 114	100.00 1	99.98 57

testing222		97.08 141	96.75 140	98.06 164	98.56 174	96.82 142	99.85 147	98.61 99	92.53 255	98.84 123	98.84 233	93.36 118	98.30 299	95.84 229	94.30 294	99.05 249

SR-MVS		98.46 47	98.30 50	98.93 96	99.88 54	97.04 134	99.84 152	98.35 190	94.92 128	99.32 93	99.80 59	93.35 119	99.78 147	99.30 72	99.95 54	99.96 75

WTY-MVS		98.10 76	97.60 98	99.60 24	98.92 146	99.28 18	99.89 127	99.52 14	95.58 112	98.24 163	99.39 149	93.33 120	99.74 156	97.98 156	95.58 274	99.78 115

tpm2		95.47 224	95.18 219	96.35 273	96.91 315	91.70 346	96.96 440	97.93 251	88.04 382	98.44 149	95.40 385	93.32 121	97.97 321	94.00 268	95.61 273	99.38 199

HY-MVS	92.50 7	97.79 99	97.17 122	99.63 19	98.98 138	99.32 10	97.49 425	99.52 14	95.69 109	98.32 157	97.41 309	93.32 121	99.77 150	98.08 149	95.75 265	99.81 109

EI-MVSNet-UG-set		98.14 74	97.99 70	98.60 118	99.80 68	96.27 169	99.36 290	98.50 137	95.21 122	98.30 158	99.75 81	93.29 123	99.73 159	98.37 130	99.30 139	99.81 109

SR-MVS-dyc-post		98.31 60	98.17 57	98.71 108	99.79 69	96.37 167	99.76 186	98.31 199	94.43 151	99.40 88	99.75 81	93.28 124	99.78 147	98.90 97	99.92 68	99.97 67

baseline1		95.78 212	94.86 231	98.54 128	98.47 187	98.07 80	99.06 329	97.99 244	92.68 241	94.13 286	98.62 253	93.28 124	98.69 256	93.79 279	85.76 363	98.84 268

MGCNet		99.06 14	98.84 20	99.72 15	99.76 73	99.21 23	99.99 8	99.34 25	98.70 2	99.44 81	99.75 81	93.24 126	99.99 40	99.94 14	99.41 132	99.95 83

PGM-MVS		98.34 58	98.13 60	98.99 90	99.92 36	97.00 135	99.75 192	99.50 17	93.90 182	99.37 91	99.76 73	93.24 126	100.00 1	97.75 171	99.96 46	99.98 57

test_post1							95.78 463				59.23 500	93.20 128	97.74 333	91.06 323

CSCG		97.10 136	97.04 126	97.27 236	99.89 50	91.92 331	99.90 117	99.07 37	88.67 368	95.26 269	99.82 54	93.17 129	99.98 51	98.15 144	99.47 125	99.90 96

DeepC-MVS_fast	96.59 1	98.81 26	98.54 32	99.62 22	99.90 47	98.85 37	99.24 310	98.47 140	98.14 16	99.08 109	99.91 19	93.09 130	100.00 1	99.04 85	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 60	98.03 67	99.17 66	99.88 54	97.59 106	99.94 93	98.44 148	94.31 159	98.50 147	99.82 54	93.06 131	99.99 40	98.30 135	99.99 21	99.93 88

testing3		93.92 278	94.23 248	92.99 396	97.54 262	90.23 380	99.99 8	99.16 33	90.57 328	91.33 317	98.63 252	92.99 132	92.52 473	82.46 425	95.39 278	96.22 330

GST-MVS		98.27 63	97.97 72	99.17 66	99.92 36	97.57 107	99.93 100	98.39 180	94.04 174	98.80 126	99.74 88	92.98 133	100.00 1	98.16 143	99.76 89	99.93 88

RE-MVS-def			98.13 60		99.79 69	96.37 167	99.76 186	98.31 199	94.43 151	99.40 88	99.75 81	92.95 134		98.90 97	99.92 68	99.97 67

CS-MVS		97.79 99	97.91 79	97.43 223	99.10 125	94.42 253	99.99 8	97.10 373	95.07 123	99.68 51	99.75 81	92.95 134	98.34 295	98.38 128	99.14 146	99.54 168

ACMMP_NAP		98.49 45	98.14 59	99.54 32	99.66 89	98.62 60	99.85 147	98.37 187	94.68 139	99.53 73	99.83 51	92.87 136	100.00 1	98.66 113	99.84 80	99.99 25

APD-MVS_3200maxsize		98.25 68	98.08 64	98.78 103	99.81 67	96.60 156	99.82 164	98.30 202	93.95 178	99.37 91	99.77 71	92.84 137	99.76 153	98.95 90	99.92 68	99.97 67

JIA-IIPM		91.76 338	90.70 339	94.94 318	96.11 343	87.51 420	93.16 475	98.13 232	75.79 469	97.58 185	77.68 489	92.84 137	97.97 321	88.47 367	96.54 240	99.33 210

Test By Simon												92.82 139

MTAPA		98.29 62	97.96 75	99.30 52	99.85 61	97.93 90	99.39 284	98.28 204	95.76 106	97.18 201	99.88 29	92.74 140	100.00 1	98.67 111	99.88 77	99.99 25

0.3-1-1-0.015		94.22 270	93.13 290	97.49 217	95.50 371	94.17 266	100.00 1	98.22 213	88.44 375	97.14 202	97.04 324	92.73 141	98.59 266	96.45 217	72.65 451	99.70 125

NormalMVS		97.90 85	97.85 85	98.04 166	99.86 58	95.39 212	99.61 240	97.78 270	96.52 76	98.61 140	99.31 157	92.73 141	99.67 168	96.77 207	99.48 122	99.06 247

SymmetryMVS		97.64 110	97.46 104	98.17 154	98.74 162	95.39 212	99.61 240	99.26 29	96.52 76	98.61 140	99.31 157	92.73 141	99.67 168	96.77 207	95.63 272	99.45 190

EPNet_dtu		95.71 216	95.39 206	96.66 261	98.92 146	93.41 294	99.57 250	98.90 50	96.19 94	97.52 186	98.56 261	92.65 144	97.36 344	77.89 452	98.33 175	99.20 233
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsm_n_1920		98.44 49	98.61 30	97.92 174	99.27 115	95.18 227	100.00 1	98.90 50	98.05 20	99.80 27	99.73 92	92.64 145	99.99 40	99.58 57	99.51 118	98.59 280

MP-MVS-pluss		98.07 78	97.64 96	99.38 49	99.74 77	98.41 69	99.74 196	98.18 221	93.35 203	96.45 231	99.85 38	92.64 145	99.97 64	98.91 96	99.89 74	99.77 116
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
FE-MVS		95.70 218	95.01 227	97.79 184	98.21 206	94.57 246	95.03 465	98.69 82	88.90 362	97.50 188	96.19 353	92.60 147	99.49 185	89.99 345	97.94 192	99.31 216

DELS-MVS		98.54 41	98.22 52	99.50 35	99.15 123	98.65 58	100.00 1	98.58 105	97.70 32	98.21 164	99.24 170	92.58 148	99.94 94	98.63 116	99.94 59	99.92 93
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 84	97.80 88	98.25 151	98.14 213	96.48 160	99.98 24	97.63 284	95.61 111	99.29 97	99.46 140	92.55 149	98.82 231	99.02 89	98.54 170	99.46 185

lecture		98.67 33	98.46 36	99.28 53	99.86 58	97.88 92	99.97 42	99.25 30	96.07 96	99.79 36	99.70 101	92.53 150	99.98 51	99.51 59	99.48 122	99.97 67

test2506		97.53 114	97.19 120	98.58 122	98.66 168	96.90 140	98.81 366	99.77 5	94.93 126	97.95 171	98.96 208	92.51 151	99.20 202	94.93 245	98.15 183	99.64 139

KD-MVS_2432*1600		88.00 398	86.10 402	93.70 378	96.91 315	94.04 270	97.17 434	97.12 366	84.93 422	81.96 439	92.41 448	92.48 152	94.51 455	79.23 443	52.68 491	92.56 439

miper_refine_blended		88.00 398	86.10 402	93.70 378	96.91 315	94.04 270	97.17 434	97.12 366	84.93 422	81.96 439	92.41 448	92.48 152	94.51 455	79.23 443	52.68 491	92.56 439

myMVS_eth3d		94.46 261	94.76 237	93.55 382	97.68 248	90.97 361	99.71 212	98.35 190	90.79 321	92.10 309	98.67 245	92.46 154	93.09 469	87.13 388	95.95 258	96.59 325

EIA-MVS		97.53 114	97.46 104	97.76 190	98.04 219	94.84 237	99.98 24	97.61 290	94.41 154	97.90 173	99.59 125	92.40 155	98.87 225	98.04 151	99.13 147	99.59 154

F-COLMAP		96.93 148	96.95 129	96.87 253	99.71 83	91.74 341	99.85 147	97.95 249	93.11 217	95.72 258	99.16 181	92.35 156	99.94 94	95.32 236	99.35 137	98.92 263

API-MVS		97.86 88	97.66 94	98.47 135	99.52 99	95.41 210	99.47 271	98.87 59	91.68 288	98.84 123	99.85 38	92.34 157	99.99 40	98.44 126	99.96 46	100.00 1

CNLPA		97.76 101	97.38 110	98.92 97	99.53 98	96.84 141	99.87 133	98.14 231	93.78 186	96.55 227	99.69 105	92.28 158	99.98 51	97.13 187	99.44 129	99.93 88

0.4-1-1-0.1		94.07 276	92.95 293	97.42 224	95.24 376	94.00 273	100.00 1	98.22 213	88.27 379	96.81 217	96.93 328	92.27 159	98.56 270	96.21 223	72.63 453	99.70 125

0.4-1-1-0.2		94.14 271	93.02 292	97.51 214	95.45 372	94.25 262	100.00 1	98.22 213	88.53 372	96.83 215	96.95 327	92.25 160	98.57 269	96.34 218	72.65 451	99.70 125

blend_shiyan4		90.13 374	88.79 379	94.17 351	87.12 467	91.83 336	99.75 192	97.08 377	79.27 461	88.69 369	92.53 446	92.25 160	96.50 402	89.35 352	73.04 449	94.18 367

TAMVS		95.85 205	95.58 198	96.65 262	97.07 297	93.50 291	99.17 316	97.82 265	91.39 301	95.02 271	98.01 290	92.20 162	97.30 351	93.75 281	95.83 262	99.14 238

1112_ss		96.01 198	95.20 218	98.42 142	97.80 233	96.41 163	99.65 229	96.66 421	92.71 238	92.88 301	99.40 147	92.16 163	99.30 194	91.92 311	93.66 302	99.55 164

Test_1112_low_res		95.72 214	94.83 232	98.42 142	97.79 234	96.41 163	99.65 229	96.65 422	92.70 239	92.86 302	96.13 357	92.15 164	99.30 194	91.88 312	93.64 303	99.55 164

HyFIR lowres test		96.66 166	96.43 156	97.36 231	99.05 129	93.91 276	99.70 219	99.80 3	90.54 329	96.26 241	98.08 288	92.15 164	98.23 307	96.84 202	95.46 275	99.93 88

SPE-MVS-test		97.88 86	97.94 77	97.70 194	99.28 113	95.20 226	99.98 24	97.15 361	95.53 114	99.62 61	99.79 63	92.08 166	98.38 291	98.75 107	99.28 140	99.52 173

MVS_111021_LR		98.42 52	98.38 41	98.53 130	99.39 106	95.79 190	99.87 133	99.86 2	96.70 70	98.78 127	99.79 63	92.03 167	99.90 113	99.17 78	99.86 79	99.88 98

TAPA-MVS	92.12 8	94.42 262	93.60 268	96.90 252	99.33 110	91.78 340	99.78 175	98.00 243	89.89 345	94.52 275	99.47 138	91.97 168	99.18 204	69.90 471	99.52 115	99.73 120
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PatchT		90.38 364	88.75 381	95.25 310	95.99 347	90.16 382	91.22 483	97.54 299	76.80 465	97.26 198	86.01 483	91.88 169	96.07 429	66.16 479	95.91 260	99.51 177

HPM-MVS		97.96 80	97.72 90	98.68 110	99.84 63	96.39 166	99.90 117	98.17 222	92.61 245	98.62 139	99.57 131	91.87 170	99.67 168	98.87 99	99.99 21	99.99 25
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MP-MVS		98.23 71	97.97 72	99.03 85	99.94 17	97.17 128	99.95 75	98.39 180	94.70 138	98.26 161	99.81 58	91.84 171	100.00 1	98.85 100	99.97 42	99.93 88
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		97.80 97	97.50 103	98.68 110	99.79 69	96.42 162	99.88 130	98.16 227	91.75 287	98.94 119	99.54 134	91.82 172	99.65 172	97.62 174	99.99 21	99.99 25

tpmvs		94.28 268	93.57 270	96.40 270	98.55 177	91.50 356	95.70 464	98.55 119	87.47 388	92.15 308	94.26 429	91.42 173	98.95 220	88.15 375	95.85 261	98.76 272

ACMMP		97.74 103	97.44 107	98.66 113	99.92 36	96.13 180	99.18 315	99.45 18	94.84 132	96.41 238	99.71 98	91.40 174	99.99 40	97.99 154	98.03 190	99.87 100
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)		96.32 185	95.98 175	97.35 233	97.93 225	94.82 239	99.47 271	98.15 230	91.83 283	95.09 270	99.11 183	91.37 175	97.47 342	93.47 286	97.43 201	99.74 119

sss		97.57 113	97.03 127	99.18 63	98.37 193	98.04 83	99.73 203	99.38 22	93.46 199	98.76 132	99.06 189	91.21 176	99.89 118	96.33 219	97.01 228	99.62 147

pcd_1.5k_mvsjas		7.60 469	10.13 472	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 504	91.20 177	0.00 504	0.00 502	0.00 502	0.00 500

PS-MVSNAJss		93.64 290	93.31 284	94.61 330	92.11 437	92.19 324	99.12 318	97.38 316	92.51 257	88.45 375	96.99 326	91.20 177	97.29 354	94.36 261	87.71 348	94.36 348

PS-MVSNAJ		98.44 49	98.20 54	99.16 69	98.80 158	98.92 31	99.54 259	98.17 222	97.34 42	99.85 19	99.85 38	91.20 177	99.89 118	99.41 68	99.67 95	98.69 277

CPTT-MVS		97.64 110	97.32 114	98.58 122	99.97 3	95.77 191	99.96 56	98.35 190	89.90 344	98.36 155	99.79 63	91.18 180	99.99 40	98.37 130	99.99 21	99.99 25

test_fmvsmconf_n		98.43 51	98.32 47	98.78 103	98.12 215	96.41 163	99.99 8	98.83 67	98.22 7	99.67 52	99.64 119	91.11 181	99.94 94	99.67 52	99.62 100	99.98 57

CR-MVSNet		93.45 296	92.62 301	95.94 283	96.29 338	92.66 313	92.01 479	96.23 433	92.62 244	96.94 210	93.31 439	91.04 182	96.03 430	79.23 443	95.96 256	99.13 239

Patchmtry		89.70 381	88.49 385	93.33 386	96.24 341	89.94 390	91.37 482	96.23 433	78.22 463	87.69 392	93.31 439	91.04 182	96.03 430	80.18 441	82.10 393	94.02 391

miper_ehance_all_eth		93.16 301	92.60 302	94.82 324	97.57 259	93.56 289	99.50 265	97.07 385	88.75 366	88.85 366	95.52 378	90.97 184	96.74 389	90.77 331	84.45 376	94.17 368

mvsany_test1		97.82 95	97.90 80	97.55 209	98.77 160	93.04 303	99.80 171	97.93 251	96.95 61	99.61 68	99.68 112	90.92 185	99.83 140	99.18 77	98.29 179	99.80 111

MVSFormer		96.94 146	96.60 147	97.95 170	97.28 287	97.70 102	99.55 257	97.27 343	91.17 304	99.43 83	99.54 134	90.92 185	96.89 380	94.67 256	99.62 100	99.25 228

lupinMVS		97.85 90	97.60 98	98.62 116	97.28 287	97.70 102	99.99 8	97.55 297	95.50 116	99.43 83	99.67 114	90.92 185	98.71 252	98.40 127	99.62 100	99.45 190

h-mvs33		94.92 240	94.36 244	96.59 263	98.85 155	91.29 358	98.93 351	98.94 44	95.90 100	98.77 129	98.42 274	90.89 188	99.77 150	97.80 164	70.76 457	98.72 276

hse-mvs2		94.38 263	94.08 254	95.31 308	98.27 202	90.02 385	99.29 305	98.56 113	95.90 100	98.77 129	98.00 291	90.89 188	98.26 306	97.80 164	69.20 464	97.64 309

xiu_mvs_v2_base		98.23 71	97.97 72	99.02 88	98.69 164	98.66 56	99.52 261	98.08 236	97.05 56	99.86 16	99.86 34	90.65 190	99.71 160	99.39 70	98.63 166	98.69 277

IS-MVSNet		96.29 188	95.90 186	97.45 219	98.13 214	94.80 240	99.08 324	97.61 290	92.02 278	95.54 263	98.96 208	90.64 191	98.08 315	93.73 282	97.41 204	99.47 183

kuosan		93.17 300	92.60 302	94.86 323	98.40 190	89.54 394	98.44 393	98.53 126	84.46 427	88.49 374	97.92 296	90.57 192	97.05 367	83.10 421	93.49 304	97.99 298

FA-MVS(test-final)		95.86 204	95.09 223	98.15 158	97.74 238	95.62 201	96.31 453	98.17 222	91.42 299	96.26 241	96.13 357	90.56 193	99.47 188	92.18 303	97.07 222	99.35 207

cl22		93.77 285	93.25 286	95.33 307	99.49 102	94.43 252	99.61 240	98.09 234	90.38 333	89.16 362	95.61 372	90.56 193	97.34 346	91.93 310	84.45 376	94.21 365

MM		98.83 24	98.53 33	99.76 11	99.59 92	99.33 9	99.99 8	99.76 6	98.39 4	99.39 90	99.80 59	90.49 195	99.96 76	99.89 21	99.43 130	99.98 57

tpm		93.70 289	93.41 278	94.58 333	95.36 375	87.41 421	97.01 438	96.90 406	90.85 315	96.72 220	94.14 430	90.40 196	96.84 384	90.75 332	88.54 338	99.51 177

dongtai		91.55 341	91.13 334	92.82 399	98.16 211	86.35 428	99.47 271	98.51 131	83.24 435	85.07 425	97.56 305	90.33 197	94.94 449	76.09 460	91.73 312	97.18 320

114514_t		97.41 122	96.83 135	99.14 73	99.51 101	97.83 94	99.89 127	98.27 206	88.48 373	99.06 114	99.66 116	90.30 198	99.64 173	96.32 220	99.97 42	99.96 75

ADS-MVSNet2		93.80 284	93.88 261	93.55 382	97.87 228	85.94 432	94.24 466	96.84 410	90.07 341	96.43 236	94.48 424	90.29 199	95.37 442	87.44 382	97.23 212	99.36 203

ADS-MVSNet		94.79 244	94.02 256	97.11 244	97.87 228	93.79 277	94.24 466	98.16 227	90.07 341	96.43 236	94.48 424	90.29 199	98.19 309	87.44 382	97.23 212	99.36 203

miper_lstm_enhance		91.81 332	91.39 331	93.06 395	97.34 280	89.18 398	99.38 286	96.79 415	86.70 401	87.47 397	95.22 398	90.00 201	95.86 434	88.26 371	81.37 399	94.15 374

c3_l		92.53 319	91.87 319	94.52 336	97.40 273	92.99 305	99.40 280	96.93 404	87.86 384	88.69 369	95.44 383	89.95 202	96.44 407	90.45 337	80.69 410	94.14 378

thres200		96.96 145	96.21 166	99.22 59	98.97 139	98.84 38	99.85 147	99.71 7	93.17 212	96.26 241	98.88 220	89.87 203	99.51 178	94.26 265	94.91 285	99.31 216

tpm cat1		93.51 293	92.52 308	96.47 265	97.77 236	91.47 357	96.13 456	98.06 237	80.98 449	92.91 300	93.78 433	89.66 204	98.87 225	87.03 391	96.39 246	99.09 243

test_fmvsmvis_n_1920		97.67 109	97.59 100	97.91 176	97.02 303	95.34 215	99.95 75	98.45 143	97.87 26	97.02 206	99.59 125	89.64 205	99.98 51	99.41 68	99.34 138	98.42 286

OMC-MVS		97.28 126	97.23 118	97.41 226	99.76 73	93.36 298	99.65 229	97.95 249	96.03 97	97.41 192	99.70 101	89.61 206	99.51 178	96.73 209	98.25 180	99.38 199

DIV-MVS_self_test		92.32 323	91.60 324	94.47 340	97.31 284	92.74 309	99.58 247	96.75 417	86.99 397	87.64 393	95.54 376	89.55 207	96.50 402	88.58 362	82.44 391	94.17 368

cl____		92.31 324	91.58 325	94.52 336	97.33 282	92.77 307	99.57 250	96.78 416	86.97 398	87.56 395	95.51 379	89.43 208	96.62 396	88.60 361	82.44 391	94.16 373

AUN-MVS		93.28 297	92.60 302	95.34 306	98.29 199	90.09 384	99.31 298	98.56 113	91.80 286	96.35 240	98.00 291	89.38 209	98.28 302	92.46 299	69.22 463	97.64 309

tfpn200view9		96.79 154	95.99 173	99.19 62	98.94 141	98.82 39	99.78 175	99.71 7	92.86 227	96.02 249	98.87 227	89.33 210	99.50 180	93.84 274	94.57 289	99.27 225

thres400		96.78 156	95.99 173	99.16 69	98.94 141	98.82 39	99.78 175	99.71 7	92.86 227	96.02 249	98.87 227	89.33 210	99.50 180	93.84 274	94.57 289	99.16 235

thres100view900		96.74 161	95.92 185	99.18 63	98.90 151	98.77 47	99.74 196	99.71 7	92.59 247	95.84 252	98.86 229	89.25 212	99.50 180	93.84 274	94.57 289	99.27 225

thres600view7		96.69 164	95.87 188	99.14 73	98.90 151	98.78 46	99.74 196	99.71 7	92.59 247	95.84 252	98.86 229	89.25 212	99.50 180	93.44 287	94.50 292	99.16 235

eth_miper_zixun_eth		92.41 322	91.93 317	93.84 373	97.28 287	90.68 370	98.83 364	96.97 397	88.57 371	89.19 361	95.73 369	89.24 214	96.69 394	89.97 346	81.55 397	94.15 374

EC-MVSNet		97.38 124	97.24 117	97.80 182	97.41 271	95.64 200	99.99 8	97.06 386	94.59 141	99.63 58	99.32 154	89.20 215	98.14 311	98.76 106	99.23 143	99.62 147

PVSNet_Blended_VisFu		97.27 127	96.81 137	98.66 113	98.81 157	96.67 152	99.92 103	98.64 91	94.51 144	96.38 239	98.49 267	89.05 216	99.88 124	97.10 189	98.34 174	99.43 194

fmvsm_l_conf0.5_n_9		98.55 40	98.23 51	99.49 37	99.10 125	98.50 65	99.99 8	98.70 80	98.14 16	99.94 2	99.68 112	89.02 217	99.98 51	99.89 21	99.61 105	99.99 25

PVSNet_BlendedMVS		96.05 196	95.82 189	96.72 259	99.59 92	96.99 136	99.95 75	99.10 34	94.06 172	98.27 159	95.80 364	89.00 218	99.95 85	99.12 79	87.53 353	93.24 427

PVSNet_Blended		97.94 82	97.64 96	98.83 100	99.59 92	96.99 136	100.00 1	99.10 34	95.38 117	98.27 159	99.08 185	89.00 218	99.95 85	99.12 79	99.25 141	99.57 162

fmvsm_s_conf0.5_n_6		98.27 63	97.96 75	99.23 58	97.66 251	98.11 78	99.98 24	98.64 91	97.85 27	99.87 14	99.72 95	88.86 220	99.93 104	99.64 54	99.36 136	99.63 146

IterMVS-LS		92.69 315	92.11 313	94.43 344	96.80 323	92.74 309	99.45 276	96.89 407	88.98 357	89.65 345	95.38 388	88.77 221	96.34 415	90.98 326	82.04 394	94.22 363
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		93.73 287	93.40 279	94.74 325	96.80 323	92.69 312	99.06 329	97.67 280	88.96 359	91.39 315	99.02 193	88.75 222	97.30 351	91.07 322	87.85 346	94.22 363

UA-Net		96.54 172	95.96 179	98.27 150	98.23 204	95.71 195	98.00 416	98.45 143	93.72 190	98.41 152	99.27 163	88.71 223	99.66 171	91.19 320	97.69 195	99.44 193

MAR-MVS		97.43 117	97.19 120	98.15 158	99.47 103	94.79 241	99.05 333	98.76 74	92.65 243	98.66 137	99.82 54	88.52 224	99.98 51	98.12 145	99.63 99	99.67 133
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		94.82 241	94.43 242	95.98 281	94.54 388	90.73 368	99.03 336	97.06 386	93.16 213	93.15 296	95.47 382	88.29 225	97.57 338	97.85 162	91.33 316	99.62 147

mvs_anonymous		95.65 220	95.03 226	97.53 211	98.19 208	95.74 193	99.33 293	97.49 306	90.87 314	90.47 327	97.10 318	88.23 226	97.16 358	95.92 227	97.66 198	99.68 131

MVS_Test		96.46 175	95.74 192	98.61 117	98.18 209	97.23 123	99.31 298	97.15 361	91.07 310	98.84 123	97.05 322	88.17 227	98.97 217	94.39 260	97.50 200	99.61 151

mvsmamba		96.94 146	96.73 141	97.55 209	97.99 221	94.37 258	99.62 236	97.70 277	93.13 215	98.42 151	97.92 296	88.02 228	98.75 247	98.78 104	99.01 153	99.52 173

fmvsm_l_conf0.5_n_3		98.41 53	98.08 64	99.39 46	99.12 124	98.29 70	99.98 24	98.64 91	98.14 16	99.86 16	99.76 73	87.99 229	99.97 64	99.72 46	99.54 112	99.91 95

CANet		98.27 63	97.82 87	99.63 19	99.72 82	99.10 25	99.98 24	98.51 131	97.00 59	98.52 144	99.71 98	87.80 230	99.95 85	99.75 41	99.38 134	99.83 105

E3new		96.75 159	96.43 156	97.71 193	97.79 234	94.83 238	99.80 171	97.33 325	93.52 197	97.49 189	99.31 157	87.73 231	98.83 228	97.52 175	97.40 205	99.48 182

jason		97.24 129	96.86 133	98.38 145	95.73 359	97.32 118	99.97 42	97.40 315	95.34 119	98.60 143	99.54 134	87.70 232	98.56 270	97.94 157	99.47 125	99.25 228
jason: jason.
test_fmvsmconf0.1_n		97.74 103	97.44 107	98.64 115	95.76 356	96.20 176	99.94 93	98.05 239	98.17 13	98.89 122	99.42 142	87.65 233	99.90 113	99.50 61	99.60 108	99.82 107

FIs		94.10 273	93.43 275	96.11 278	94.70 385	96.82 142	99.58 247	98.93 48	92.54 254	89.34 354	97.31 312	87.62 234	97.10 364	94.22 267	86.58 357	94.40 346

guyue		97.15 134	96.82 136	98.15 158	97.56 260	96.25 174	99.71 212	97.84 263	95.75 107	98.13 167	98.65 248	87.58 235	98.82 231	98.29 136	97.91 193	99.36 203

VortexMVS		94.11 272	93.50 273	95.94 283	97.70 246	96.61 155	99.35 291	97.18 356	93.52 197	89.57 349	95.74 366	87.55 236	96.97 375	95.76 232	85.13 371	94.23 360

LuminaMVS		96.63 167	96.21 166	97.87 179	95.58 370	96.82 142	99.12 318	97.67 280	94.47 145	97.88 176	98.31 281	87.50 237	98.71 252	98.07 150	97.29 211	98.10 296

1314		96.84 152	95.96 179	99.48 40	96.74 328	98.52 63	98.31 400	98.86 60	95.82 104	89.91 336	98.98 204	87.49 238	99.96 76	97.80 164	99.73 91	99.96 75

LS3D		95.84 206	95.11 222	98.02 167	99.85 61	95.10 230	98.74 372	98.50 137	87.22 393	93.66 290	99.86 34	87.45 239	99.95 85	90.94 327	99.81 87	99.02 255

FC-MVSNet-test		93.81 283	93.15 288	95.80 292	94.30 393	96.20 176	99.42 278	98.89 52	92.33 265	89.03 364	97.27 314	87.39 240	96.83 386	93.20 289	86.48 358	94.36 348

fmvsm_s_conf0.5_n_8		98.38 57	98.05 66	99.35 50	99.20 118	98.12 77	99.98 24	98.81 68	98.22 7	99.80 27	99.71 98	87.37 241	99.97 64	99.91 19	99.48 122	99.97 67

fmvsm_s_conf0.5_n		97.80 97	97.85 85	97.67 195	99.06 128	94.41 254	99.98 24	98.97 43	97.34 42	99.63 58	99.69 105	87.27 242	99.97 64	99.62 55	99.06 151	98.62 279

RPMNet		89.76 380	87.28 397	97.19 237	96.29 338	92.66 313	92.01 479	98.31 199	70.19 480	96.94 210	85.87 484	87.25 243	99.78 147	62.69 485	95.96 256	99.13 239

UniMVSNet_NR-MVSNet		92.95 306	92.11 313	95.49 297	94.61 387	95.28 221	99.83 159	99.08 36	91.49 292	89.21 359	96.86 332	87.14 244	96.73 390	93.20 289	77.52 429	94.46 340

UniMVSNet (Re)		93.07 304	92.13 312	95.88 287	94.84 382	96.24 175	99.88 130	98.98 41	92.49 258	89.25 356	95.40 385	87.09 245	97.14 360	93.13 293	78.16 424	94.26 356

fmvsm_s_conf0.5_n_9		98.15 73	98.02 68	98.55 124	99.28 113	95.84 188	99.99 8	98.57 107	98.17 13	99.93 3	99.74 88	87.04 246	99.97 64	99.86 27	99.59 109	99.83 105

DP-MVS		94.54 254	93.42 276	97.91 176	99.46 105	94.04 270	98.93 351	97.48 307	81.15 448	90.04 333	99.55 132	87.02 247	99.95 85	88.97 358	98.11 186	99.73 120

fmvsm_s_conf0.5_n_a		97.73 105	97.72 90	97.77 188	98.63 171	94.26 261	99.96 56	98.92 49	97.18 52	99.75 41	99.69 105	87.00 248	99.97 64	99.46 64	98.89 156	99.08 245

PMMVS		96.76 157	96.76 139	96.76 257	98.28 201	92.10 326	99.91 111	97.98 246	94.12 167	99.53 73	99.39 149	86.93 249	98.73 249	96.95 197	97.73 194	99.45 190

viewcassd2359sk11		96.59 169	96.23 163	97.66 196	97.63 254	94.70 243	99.77 180	97.33 325	93.41 202	97.34 194	99.17 178	86.72 250	98.83 228	97.40 178	97.32 209	99.46 185

sasdasda		97.09 138	96.32 160	99.39 46	98.93 143	98.95 29	99.72 207	97.35 321	94.45 147	97.88 176	99.42 142	86.71 251	99.52 176	98.48 123	93.97 299	99.72 122

canonicalmvs		97.09 138	96.32 160	99.39 46	98.93 143	98.95 29	99.72 207	97.35 321	94.45 147	97.88 176	99.42 142	86.71 251	99.52 176	98.48 123	93.97 299	99.72 122

fmvsm_s_conf0.5_n_4		97.75 102	97.86 84	97.42 224	99.01 131	94.69 244	99.97 42	98.76 74	97.91 25	99.87 14	99.76 73	86.70 253	99.93 104	99.67 52	99.12 149	97.64 309

MVS		96.60 168	95.56 199	99.72 15	96.85 320	99.22 22	98.31 400	98.94 44	91.57 290	90.90 321	99.61 124	86.66 254	99.96 76	97.36 179	99.88 77	99.99 25

Effi-MVS+		96.30 187	95.69 194	98.16 155	97.85 230	96.26 170	97.41 428	97.21 353	90.37 334	98.65 138	98.58 259	86.61 255	98.70 255	97.11 188	97.37 206	99.52 173

diffmvs		97.00 143	96.64 145	98.09 162	97.64 253	96.17 179	99.81 166	97.19 354	94.67 140	98.95 118	99.28 160	86.43 256	98.76 245	98.37 130	97.42 203	99.33 210
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
nrg030		93.51 293	92.53 307	96.45 268	94.36 391	97.20 124	99.81 166	97.16 360	91.60 289	89.86 338	97.46 307	86.37 257	97.68 334	95.88 228	80.31 413	94.46 340

AstraMVS		96.57 171	96.46 155	96.91 250	96.79 326	92.50 318	99.90 117	97.38 316	96.02 98	97.79 181	99.32 154	86.36 258	98.99 214	98.26 138	96.33 248	99.23 231

MGCFI-Net		97.00 143	96.22 165	99.34 51	98.86 154	98.80 41	99.67 227	97.30 333	94.31 159	97.77 182	99.41 146	86.36 258	99.50 180	98.38 128	93.90 301	99.72 122

VNet		97.21 131	96.57 149	99.13 77	98.97 139	97.82 95	99.03 336	99.21 32	94.31 159	99.18 104	98.88 220	86.26 260	99.89 118	98.93 92	94.32 293	99.69 130

fmvsm_s_conf0.5_n_11		98.03 79	97.89 82	98.46 137	99.35 109	97.76 98	99.99 8	98.04 240	98.20 9	99.90 7	99.78 67	86.21 261	99.95 85	99.89 21	99.68 94	97.65 308

fmvsm_s_conf0.5_n_7		97.70 108	97.74 89	97.59 207	98.44 188	95.16 229	99.97 42	98.65 88	97.95 24	99.62 61	99.78 67	86.09 262	99.94 94	99.69 50	99.50 120	97.66 307

AdaColmap		97.23 130	96.80 138	98.51 133	99.99 1	95.60 202	99.09 322	98.84 66	93.32 205	96.74 219	99.72 95	86.04 263	100.00 1	98.01 152	99.43 130	99.94 87

fmvsm_s_conf0.5_n_5		98.08 77	97.71 92	99.17 66	98.67 166	97.69 104	99.99 8	98.57 107	97.40 40	99.89 11	99.69 105	85.99 264	99.96 76	99.80 32	99.40 133	99.85 103

fmvsm_s_conf0.5_n_10		98.24 69	97.90 80	99.26 55	99.24 116	97.88 92	99.99 8	98.76 74	98.20 9	99.92 5	99.74 88	85.97 265	99.94 94	99.72 46	99.53 114	99.96 75

Effi-MVS+-dtu		94.53 256	95.30 214	92.22 407	97.77 236	82.54 455	99.59 245	97.06 386	94.92 128	95.29 267	95.37 389	85.81 266	97.89 327	94.80 251	97.07 222	96.23 329

IMVS_0403		95.25 230	94.81 234	96.58 264	96.97 308	91.64 348	98.97 346	97.12 366	92.33 265	95.43 264	98.88 220	85.78 267	98.79 240	92.12 304	95.70 268	99.32 212

icg_test_0407_2		95.04 236	94.78 236	95.84 290	96.97 308	91.64 348	98.63 383	97.12 366	92.33 265	95.60 259	98.88 220	85.65 268	96.56 399	92.12 304	95.70 268	99.32 212

IMVS_0407		95.21 231	94.80 235	96.46 267	96.97 308	91.64 348	98.81 366	97.12 366	92.33 265	95.60 259	98.88 220	85.65 268	98.42 281	92.12 304	95.70 268	99.32 212

diffmvs_AUTHOR		96.75 159	96.41 158	97.79 184	97.20 290	95.46 206	99.69 222	97.15 361	94.46 146	98.78 127	99.21 174	85.64 270	98.77 243	98.27 137	97.31 210	99.13 239

CVMVSNet		94.68 251	94.94 230	93.89 372	96.80 323	86.92 426	99.06 329	98.98 41	94.45 147	94.23 285	99.02 193	85.60 271	95.31 444	90.91 328	95.39 278	99.43 194

viewmanbaseed2359cas		96.45 176	96.07 169	97.59 207	97.55 261	94.59 245	99.70 219	97.33 325	93.62 193	97.00 209	99.32 154	85.57 272	98.71 252	97.26 184	97.33 208	99.47 183

xiu_mvs_v1_base_debu		97.43 117	97.06 123	98.55 124	97.74 238	98.14 74	99.31 298	97.86 260	96.43 81	99.62 61	99.69 105	85.56 273	99.68 165	99.05 82	98.31 176	97.83 302

xiu_mvs_v1_base		97.43 117	97.06 123	98.55 124	97.74 238	98.14 74	99.31 298	97.86 260	96.43 81	99.62 61	99.69 105	85.56 273	99.68 165	99.05 82	98.31 176	97.83 302

xiu_mvs_v1_base_debi		97.43 117	97.06 123	98.55 124	97.74 238	98.14 74	99.31 298	97.86 260	96.43 81	99.62 61	99.69 105	85.56 273	99.68 165	99.05 82	98.31 176	97.83 302

E3		96.36 182	95.95 181	97.60 204	97.37 277	94.52 248	99.71 212	97.33 325	93.18 211	97.02 206	99.07 187	85.45 276	98.82 231	97.27 181	97.14 218	99.46 185

casdiffmvs_mvg		96.43 177	95.94 183	97.89 178	97.44 269	95.47 205	99.86 144	97.29 341	93.35 203	96.03 248	99.19 176	85.39 277	98.72 251	97.89 161	97.04 224	99.49 181
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		96.36 182	95.95 181	97.60 204	97.41 271	94.52 248	99.71 212	97.33 325	93.20 209	97.02 206	99.07 187	85.37 278	98.82 231	97.27 181	97.14 218	99.46 185

baseline		96.43 177	95.98 175	97.76 190	97.34 280	95.17 228	99.51 263	97.17 358	93.92 180	96.90 212	99.28 160	85.37 278	98.64 263	97.50 176	96.86 233	99.46 185

PCF-MVS	94.20 5	95.18 232	94.10 251	98.43 140	98.55 177	95.99 184	97.91 418	97.31 332	90.35 335	89.48 351	99.22 171	85.19 280	99.89 118	90.40 340	98.47 172	99.41 197
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs		96.42 179	95.97 178	97.77 188	97.30 285	94.98 231	99.84 152	97.09 376	93.75 189	96.58 224	99.26 167	85.07 281	98.78 242	97.77 169	97.04 224	99.54 168
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
D2MVS		92.76 312	92.59 306	93.27 388	95.13 377	89.54 394	99.69 222	99.38 22	92.26 270	87.59 394	94.61 421	85.05 282	97.79 330	91.59 315	88.01 344	92.47 443

fmvsm_s_conf0.1_n		97.30 125	97.21 119	97.60 204	97.38 275	94.40 256	99.90 117	98.64 91	96.47 80	99.51 77	99.65 118	84.99 283	99.93 104	99.22 76	99.09 150	98.46 283

viewdifsd2359ckpt13		96.19 193	95.77 190	97.45 219	97.62 255	94.40 256	99.70 219	97.23 351	92.76 235	96.63 221	99.05 190	84.96 284	98.64 263	96.65 210	97.35 207	99.31 216

viewdifsd2359ckpt09		96.21 192	95.77 190	97.53 211	97.69 247	94.50 250	99.78 175	97.23 351	92.88 226	96.58 224	99.26 167	84.85 285	98.66 262	96.61 211	97.02 227	99.43 194

viewmambaseed2359dif		95.92 203	95.55 200	97.04 246	97.38 275	93.41 294	99.78 175	96.97 397	91.14 307	96.58 224	99.27 163	84.85 285	98.75 247	96.87 201	97.12 220	98.97 258

usedtu_dtu_shiyan1		92.78 310	91.73 321	95.92 285	93.03 418	96.82 142	99.83 159	97.79 266	90.58 326	90.09 329	95.04 404	84.75 287	96.72 392	88.19 373	86.23 360	94.23 360

FE-MVSNET3		92.78 310	91.73 321	95.92 285	93.03 418	96.82 142	99.83 159	97.79 266	90.58 326	90.09 329	95.04 404	84.75 287	96.72 392	88.20 372	86.23 360	94.23 360

SSM_0407		95.62 221	94.95 229	97.61 203	97.14 291	95.31 217	99.00 339	97.25 346	90.81 317	94.40 278	98.83 234	84.74 289	98.58 267	95.24 238	97.18 215	98.93 260

SSM_0404		95.75 213	95.16 220	97.50 216	97.53 263	95.39 212	99.11 320	97.25 346	90.81 317	95.27 268	98.83 234	84.74 289	98.67 259	95.24 238	97.69 195	98.45 284

fmvsm_s_conf0.1_n_a		97.09 138	96.90 131	97.63 201	95.65 366	94.21 265	99.83 159	98.50 137	96.27 91	99.65 54	99.64 119	84.72 291	99.93 104	99.04 85	98.84 159	98.74 274

BH-w/o		95.71 216	95.38 211	96.68 260	98.49 186	92.28 322	99.84 152	97.50 305	92.12 273	92.06 311	98.79 236	84.69 292	98.67 259	95.29 237	99.66 96	99.09 243

Fast-Effi-MVS+		95.02 237	94.19 249	97.52 213	97.88 227	94.55 247	99.97 42	97.08 377	88.85 364	94.47 277	97.96 295	84.59 293	98.41 283	89.84 347	97.10 221	99.59 154

mamba_0408		94.98 239	94.09 252	97.64 198	97.14 291	95.31 217	93.48 473	97.08 377	90.48 330	94.40 278	98.62 253	84.49 294	98.67 259	93.99 269	97.18 215	98.93 260

SSM_04072		94.77 246	94.09 252	96.82 254	97.14 291	95.31 217	93.48 473	97.08 377	90.48 330	94.40 278	98.62 253	84.49 294	96.21 422	93.99 269	97.18 215	98.93 260

PVSNet	91.05 13	97.13 135	96.69 144	98.45 138	99.52 99	95.81 189	99.95 75	99.65 12	94.73 136	99.04 115	99.21 174	84.48 296	99.95 85	94.92 246	98.74 164	99.58 160

WR-MVS_H		91.30 342	90.35 346	94.15 354	94.17 396	92.62 316	99.17 316	98.94 44	88.87 363	86.48 411	94.46 426	84.36 297	96.61 397	88.19 373	78.51 422	93.21 428

CHOSEN 1792x2688		96.81 153	96.53 150	97.64 198	98.91 150	93.07 300	99.65 229	99.80 3	95.64 110	95.39 265	98.86 229	84.35 298	99.90 113	96.98 194	99.16 145	99.95 83

fmvsm_s_conf0.5_n_3		97.95 81	97.66 94	98.81 101	98.99 136	98.07 80	99.98 24	98.81 68	98.18 12	99.89 11	99.70 101	84.15 299	99.97 64	99.76 40	99.50 120	98.39 287

our_test_3		90.39 363	89.48 368	93.12 392	92.40 433	89.57 393	99.33 293	96.35 432	87.84 385	85.30 422	94.99 410	84.14 300	96.09 428	80.38 438	84.56 375	93.71 417

MSDG		94.37 264	93.36 283	97.40 227	98.88 153	93.95 275	99.37 288	97.38 316	85.75 413	90.80 324	99.17 178	84.11 301	99.88 124	86.35 396	98.43 173	98.36 289

E4		96.01 198	95.53 201	97.44 222	97.05 299	94.23 263	99.57 250	97.30 333	92.72 236	96.47 230	99.03 192	83.98 302	98.83 228	96.92 198	96.77 234	99.27 225

pmmvs4		92.10 328	91.07 336	95.18 311	92.82 426	94.96 232	99.48 270	96.83 411	87.45 389	88.66 371	96.56 344	83.78 303	96.83 386	89.29 354	84.77 374	93.75 412

BH-untuned		95.18 232	94.83 232	96.22 276	98.36 194	91.22 359	99.80 171	97.32 331	90.91 313	91.08 318	98.67 245	83.51 304	98.54 273	94.23 266	99.61 105	98.92 263

LCM-MVSNet-Re		92.31 324	92.60 302	91.43 416	97.53 263	79.27 472	99.02 338	91.83 487	92.07 274	80.31 449	94.38 427	83.50 305	95.48 439	97.22 186	97.58 199	99.54 168

E6new		95.83 207	95.39 206	97.14 240	97.00 306	93.58 286	99.31 298	97.30 333	92.57 251	96.45 231	99.01 195	83.44 306	98.81 235	96.80 205	96.66 235	99.04 250

E6		95.83 207	95.39 206	97.14 240	97.00 306	93.58 286	99.31 298	97.30 333	92.57 251	96.45 231	99.01 195	83.44 306	98.81 235	96.80 205	96.66 235	99.04 250

E5new		95.83 207	95.39 206	97.15 238	97.03 300	93.59 284	99.32 296	97.30 333	92.58 249	96.45 231	99.00 199	83.37 308	98.81 235	96.81 203	96.65 237	99.04 250

E5		95.83 207	95.39 206	97.15 238	97.03 300	93.59 284	99.32 296	97.30 333	92.58 249	96.45 231	99.00 199	83.37 308	98.81 235	96.81 203	96.65 237	99.04 250

cdsmvs_eth3d_5k		23.43 466	31.24 469	0.00 485	0.00 508	0.00 510	0.00 496	98.09 234	0.00 503	0.00 504	99.67 114	83.37 308	0.00 504	0.00 502	0.00 502	0.00 500

balanced_ft_v1		96.88 150	96.52 151	97.96 169	98.60 172	94.94 234	99.41 279	97.56 296	93.53 194	99.42 85	97.89 299	83.33 311	99.31 193	99.29 73	99.62 100	99.64 139

DeepC-MVS	94.51 4	96.92 149	96.40 159	98.45 138	99.16 122	95.90 186	99.66 228	98.06 237	96.37 87	94.37 281	99.49 137	83.29 312	99.90 113	97.63 173	99.61 105	99.55 164
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NR-MVSNet		91.56 340	90.22 350	95.60 295	94.05 397	95.76 192	98.25 403	98.70 80	91.16 306	80.78 448	96.64 340	83.23 313	96.57 398	91.41 317	77.73 428	94.46 340

MVStest1		85.03 419	82.76 428	91.83 412	92.95 422	89.16 399	98.57 385	94.82 464	71.68 478	68.54 483	95.11 402	83.17 314	95.66 437	74.69 463	65.32 473	90.65 460

viewdifsd2359ckpt07		95.83 207	95.42 204	97.07 245	97.40 273	93.04 303	99.60 243	97.24 349	92.39 262	96.09 247	99.14 182	83.07 315	98.93 221	97.02 191	96.87 231	99.23 231

viewmacassd2359aftdt		95.93 202	95.45 202	97.36 231	97.09 295	94.12 269	99.57 250	97.26 345	93.05 220	96.50 228	99.17 178	82.76 316	98.68 257	96.61 211	97.04 224	99.28 223

3Dnovator+	91.53 11	96.31 186	95.24 216	99.52 33	96.88 319	98.64 59	99.72 207	98.24 210	95.27 121	88.42 381	98.98 204	82.76 316	99.94 94	97.10 189	99.83 81	99.96 75

QAPM		95.40 226	94.17 250	99.10 79	96.92 314	97.71 100	99.40 280	98.68 84	89.31 350	88.94 365	98.89 219	82.48 318	99.96 76	93.12 294	99.83 81	99.62 147

PatchMatch-RL		96.04 197	95.40 205	97.95 170	99.59 92	95.22 225	99.52 261	99.07 37	93.96 177	96.49 229	98.35 276	82.28 319	99.82 142	90.15 343	99.22 144	98.81 270

GeoE		94.36 266	93.48 274	96.99 248	97.29 286	93.54 290	99.96 56	96.72 419	88.35 377	93.43 291	98.94 215	82.05 320	98.05 318	88.12 377	96.48 244	99.37 201

SD_0403		92.63 318	93.38 280	90.40 430	97.32 283	77.91 474	97.75 423	98.03 242	91.89 280	90.83 323	98.29 283	82.00 321	93.79 462	88.51 366	95.75 265	99.52 173

3Dnovator	91.47 12	96.28 189	95.34 212	99.08 82	96.82 322	97.47 114	99.45 276	98.81 68	95.52 115	89.39 352	99.00 199	81.97 322	99.95 85	97.27 181	99.83 81	99.84 104

v8		90.54 361	89.17 371	94.66 328	93.43 408	93.40 296	99.20 313	96.94 403	85.76 411	87.56 395	94.51 422	81.96 323	97.19 357	84.94 409	78.25 423	93.38 424

RRT-MVS		96.24 191	95.68 196	97.94 173	97.65 252	94.92 235	99.27 308	97.10 373	92.79 233	97.43 191	97.99 293	81.85 324	99.37 192	98.46 125	98.57 167	99.53 172

fmvsm_s_conf0.5_n_2		97.59 112	97.28 115	98.53 130	99.01 131	98.15 72	99.98 24	98.59 103	98.17 13	99.75 41	99.63 122	81.83 325	99.94 94	99.78 35	98.79 162	97.51 317

v148		90.70 356	89.63 361	93.92 369	92.97 420	90.97 361	99.75 192	96.89 407	87.51 387	88.27 385	95.01 407	81.67 326	97.04 370	87.40 384	77.17 434	93.75 412

DU-MVS		92.46 321	91.45 330	95.49 297	94.05 397	95.28 221	99.81 166	98.74 77	92.25 271	89.21 359	96.64 340	81.66 327	96.73 390	93.20 289	77.52 429	94.46 340

Baseline_NR-MVSNet		90.33 366	89.51 366	92.81 400	92.84 424	89.95 388	99.77 180	93.94 476	84.69 426	89.04 363	95.66 371	81.66 327	96.52 401	90.99 325	76.98 435	91.97 449

FMVSNet3		92.69 315	91.58 325	95.99 280	98.29 199	97.42 116	99.26 309	97.62 287	89.80 346	89.68 342	95.32 391	81.62 329	96.27 419	87.01 392	85.65 364	94.29 355

Fast-Effi-MVS+-dtu		93.72 288	93.86 262	93.29 387	97.06 298	86.16 429	99.80 171	96.83 411	92.66 242	92.58 304	97.83 302	81.39 330	97.67 335	89.75 348	96.87 231	96.05 332

CANet_DTU		96.76 157	96.15 168	98.60 118	98.78 159	97.53 108	99.84 152	97.63 284	97.25 50	99.20 101	99.64 119	81.36 331	99.98 51	92.77 298	98.89 156	98.28 291

WB-MVSnew		92.90 307	92.77 299	93.26 389	96.95 313	93.63 283	99.71 212	98.16 227	91.49 292	94.28 283	98.14 286	81.33 332	96.48 405	79.47 442	95.46 275	89.68 471

V42		91.28 344	90.12 355	94.74 325	93.42 409	93.46 292	99.68 225	97.02 390	87.36 390	89.85 340	95.05 403	81.31 333	97.34 346	87.34 385	80.07 415	93.40 422

test_djsdf		92.83 309	92.29 311	94.47 340	91.90 440	92.46 319	99.55 257	97.27 343	91.17 304	89.96 334	96.07 360	81.10 334	96.89 380	94.67 256	88.91 328	94.05 390

ppachtmachnet_test		89.58 384	88.35 387	93.25 390	92.40 433	90.44 377	99.33 293	96.73 418	85.49 416	85.90 419	95.77 365	81.09 335	96.00 432	76.00 461	82.49 390	93.30 425

v1144		91.09 348	89.83 357	94.87 320	93.25 411	93.69 282	99.62 236	96.98 395	86.83 400	89.64 346	94.99 410	80.94 336	97.05 367	85.08 408	81.16 401	93.87 406

v10		90.25 369	88.82 378	94.57 334	93.53 406	93.43 293	99.08 324	96.87 409	85.00 421	87.34 401	94.51 422	80.93 337	97.02 374	82.85 423	79.23 418	93.26 426

fmvsm_s_conf0.1_n_2		97.25 128	96.85 134	98.43 140	98.08 216	98.08 79	99.92 103	97.76 274	98.05 20	99.65 54	99.58 128	80.88 338	99.93 104	99.59 56	98.17 181	97.29 318

EU-MVSNet		90.14 373	90.34 347	89.54 437	92.55 430	81.06 466	98.69 378	98.04 240	91.41 300	86.59 408	96.84 335	80.83 339	93.31 467	86.20 398	81.91 395	94.26 356

v2v482		91.30 342	90.07 356	95.01 315	93.13 412	93.79 277	99.77 180	97.02 390	88.05 381	89.25 356	95.37 389	80.73 340	97.15 359	87.28 386	80.04 416	94.09 386

WR-MVS		92.31 324	91.25 332	95.48 300	94.45 390	95.29 220	99.60 243	98.68 84	90.10 340	88.07 388	96.89 330	80.68 341	96.80 388	93.14 292	79.67 417	94.36 348

HQP2-MVS												80.65 342

HQP-MVS		94.61 253	94.50 241	94.92 319	95.78 352	91.85 334	99.87 133	97.89 256	96.82 64	93.37 292	98.65 248	80.65 342	98.39 287	97.92 158	89.60 319	94.53 335

XVG-OURS		94.82 241	94.74 238	95.06 314	98.00 220	89.19 396	99.08 324	97.55 297	94.10 168	94.71 273	99.62 123	80.51 344	99.74 156	96.04 225	93.06 311	96.25 327

v144192		90.79 355	89.52 365	94.59 332	93.11 415	92.77 307	99.56 254	96.99 393	86.38 404	89.82 341	94.95 412	80.50 345	97.10 364	83.98 415	80.41 411	93.90 403

HQP_MVS		94.49 260	94.36 244	94.87 320	95.71 362	91.74 341	99.84 152	97.87 258	96.38 84	93.01 297	98.59 256	80.47 346	98.37 293	97.79 167	89.55 322	94.52 337

plane_prior6					95.76 356	91.72 345						80.47 346

KinetiMVS		96.10 194	95.29 215	98.53 130	97.08 296	97.12 129	99.56 254	98.12 233	94.78 133	98.44 149	98.94 215	80.30 348	99.39 191	91.56 316	98.79 162	99.06 247

v7n		89.65 382	88.29 388	93.72 375	92.22 435	90.56 374	99.07 328	97.10 373	85.42 418	86.73 405	94.72 415	80.06 349	97.13 361	81.14 433	78.12 425	93.49 420

TranMVSNet+NR-MVSNet		91.68 339	90.61 342	94.87 320	93.69 404	93.98 274	99.69 222	98.65 88	91.03 311	88.44 376	96.83 336	80.05 350	96.18 423	90.26 342	76.89 437	94.45 345

FMVSNet5		88.32 394	87.47 396	90.88 419	96.90 318	88.39 412	97.28 431	95.68 447	82.60 442	84.67 427	92.40 450	79.83 351	91.16 478	76.39 459	81.51 398	93.09 430

test_fmvsmconf0.01_n		96.39 180	95.74 192	98.32 147	91.47 446	95.56 203	99.84 152	97.30 333	97.74 30	97.89 175	99.35 153	79.62 352	99.85 130	99.25 75	99.24 142	99.55 164

RPSCF		91.80 335	92.79 298	88.83 442	98.15 212	69.87 482	98.11 412	96.60 424	83.93 430	94.33 282	99.27 163	79.60 353	99.46 189	91.99 309	93.16 309	97.18 320

Vis-MVSNet		95.72 214	95.15 221	97.45 219	97.62 255	94.28 260	99.28 306	98.24 210	94.27 164	96.84 214	98.94 215	79.39 354	98.76 245	93.25 288	98.49 171	99.30 219
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dmvs_testset		83.79 429	86.07 404	76.94 466	92.14 436	48.60 501	96.75 445	90.27 491	89.48 348	78.65 457	98.55 263	79.25 355	86.65 489	66.85 477	82.69 387	95.57 333

v1192		90.62 360	89.25 370	94.72 327	93.13 412	93.07 300	99.50 265	97.02 390	86.33 405	89.56 350	95.01 407	79.22 356	97.09 366	82.34 427	81.16 401	94.01 393

CP-MVSNet		91.23 346	90.22 350	94.26 349	93.96 399	92.39 321	99.09 322	98.57 107	88.95 360	86.42 412	96.57 343	79.19 357	96.37 413	90.29 341	78.95 419	94.02 391

MDA-MVSNet_test_wron		85.51 415	83.32 423	92.10 408	90.96 450	88.58 409	99.20 313	96.52 427	79.70 454	57.12 491	92.69 444	79.11 358	93.86 461	77.10 456	77.46 431	93.86 407

Syy-MVS		90.00 376	90.63 341	88.11 449	97.68 248	74.66 479	99.71 212	98.35 190	90.79 321	92.10 309	98.67 245	79.10 359	93.09 469	63.35 484	95.95 258	96.59 325

YYNet1		85.50 416	83.33 422	92.00 409	90.89 451	88.38 413	99.22 312	96.55 426	79.60 455	57.26 490	92.72 443	79.09 360	93.78 463	77.25 455	77.37 432	93.84 408

XVG-OURS-SEG-HR		94.79 244	94.70 239	95.08 313	98.05 218	89.19 396	99.08 324	97.54 299	93.66 191	94.87 272	99.58 128	78.78 361	99.79 145	97.31 180	93.40 306	96.25 327

GA-MVS		93.83 280	92.84 295	96.80 255	95.73 359	93.57 288	99.88 130	97.24 349	92.57 251	92.92 299	96.66 338	78.73 362	97.67 335	87.75 380	94.06 298	99.17 234

dmvs_re		93.20 299	93.15 288	93.34 385	96.54 334	83.81 444	98.71 375	98.51 131	91.39 301	92.37 307	98.56 261	78.66 363	97.83 329	93.89 272	89.74 318	98.38 288

OpenMVS	90.15 15	94.77 246	93.59 269	98.33 146	96.07 344	97.48 113	99.56 254	98.57 107	90.46 332	86.51 409	98.95 213	78.57 364	99.94 94	93.86 273	99.74 90	97.57 314

v1921920		90.46 362	89.12 372	94.50 338	92.96 421	92.46 319	99.49 267	96.98 395	86.10 407	89.61 348	95.30 392	78.55 365	97.03 372	82.17 428	80.89 409	94.01 393

MVP-Stereo		90.93 350	90.45 345	92.37 406	91.25 449	88.76 403	98.05 415	96.17 435	87.27 392	84.04 429	95.30 392	78.46 366	97.27 356	83.78 417	99.70 93	91.09 454
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
anonymousdsp		91.79 337	90.92 337	94.41 345	90.76 452	92.93 306	98.93 351	97.17 358	89.08 352	87.46 398	95.30 392	78.43 367	96.92 378	92.38 300	88.73 333	93.39 423

wanda-best-256-512		87.82 401	85.71 407	94.15 354	86.66 470	91.88 332	99.76 186	97.08 377	79.46 457	88.37 382	92.36 451	78.01 368	96.43 408	88.39 368	61.26 482	94.14 378

FE-blended-shiyan7		87.82 401	85.71 407	94.15 354	86.66 470	91.88 332	99.76 186	97.08 377	79.46 457	88.37 382	92.36 451	78.01 368	96.43 408	88.39 368	61.26 482	94.14 378

usedtu_blend_shiyan5		86.75 409	84.29 415	94.16 352	86.66 470	91.83 336	97.42 426	95.23 458	69.94 481	88.37 382	92.36 451	78.01 368	96.50 402	89.35 352	61.26 482	94.14 378

v1240		90.20 370	88.79 379	94.44 342	93.05 417	92.27 323	99.38 286	96.92 405	85.89 409	89.36 353	94.87 414	77.89 371	97.03 372	80.66 436	81.08 404	94.01 393

blended_shiyan8		87.82 401	85.71 407	94.16 352	86.54 473	91.79 338	99.72 207	97.08 377	79.32 459	88.44 376	92.35 454	77.88 372	96.56 399	88.53 364	61.51 481	94.15 374

blended_shiyan6		87.74 404	85.62 410	94.09 359	86.53 474	91.73 344	99.72 207	97.08 377	79.32 459	88.22 386	92.31 456	77.82 373	96.43 408	88.31 370	61.26 482	94.13 383

CLD-MVS		94.06 277	93.90 260	94.55 335	96.02 346	90.69 369	99.98 24	97.72 276	96.62 75	91.05 320	98.85 232	77.21 374	98.47 275	98.11 146	89.51 324	94.48 339
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		96.59 169	96.23 163	97.65 197	98.22 205	94.23 263	99.99 8	97.25 346	97.77 29	99.58 69	99.08 185	77.10 375	99.97 64	97.64 172	99.45 128	98.74 274

viewdifsd2359ckpt11		94.09 274	93.63 265	95.46 301	96.68 331	88.92 401	99.62 236	97.12 366	93.07 218	95.73 256	99.22 171	77.05 376	98.88 224	96.52 215	87.69 351	98.58 281

viewmsd2359difaftdt		94.09 274	93.64 264	95.46 301	96.68 331	88.92 401	99.62 236	97.13 365	93.07 218	95.73 256	99.22 171	77.05 376	98.89 223	96.52 215	87.70 350	98.58 281

N_pmnet		80.06 443	80.78 439	77.89 465	91.94 439	45.28 503	98.80 369	56.82 505	78.10 464	80.08 451	93.33 437	77.03 378	95.76 436	68.14 475	82.81 386	92.64 438

WB-MVS		76.28 447	77.28 449	73.29 470	81.18 486	54.68 495	97.87 419	94.19 472	81.30 446	69.43 481	90.70 463	77.02 379	82.06 493	35.71 497	68.11 468	83.13 484

COLMAP_ROB	90.47 14	92.18 327	91.49 329	94.25 350	99.00 135	88.04 416	98.42 397	96.70 420	82.30 443	88.43 379	99.01 195	76.97 380	99.85 130	86.11 400	96.50 242	94.86 334
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
cascas		94.64 252	93.61 266	97.74 192	97.82 232	96.26 170	99.96 56	97.78 270	85.76 411	94.00 287	97.54 306	76.95 381	99.21 199	97.23 185	95.43 277	97.76 306

BH-RMVSNet		95.18 232	94.31 247	97.80 182	98.17 210	95.23 224	99.76 186	97.53 301	92.52 256	94.27 284	99.25 169	76.84 382	98.80 239	90.89 329	99.54 112	99.35 207

IMVS_0404		93.83 280	93.17 287	95.80 292	96.97 308	91.64 348	97.78 422	97.12 366	92.33 265	90.87 322	98.88 220	76.78 383	96.43 408	92.12 304	95.70 268	99.32 212

PEN-MVS		90.19 371	89.06 374	93.57 381	93.06 416	90.90 365	99.06 329	98.47 140	88.11 380	85.91 418	96.30 350	76.67 384	95.94 433	87.07 389	76.91 436	93.89 404

CL-MVSNet_self_test		84.50 425	83.15 425	88.53 446	86.00 475	81.79 461	98.82 365	97.35 321	85.12 420	83.62 434	90.91 462	76.66 385	91.40 477	69.53 472	60.36 487	92.40 444

IterMVS		90.91 351	90.17 353	93.12 392	96.78 327	90.42 378	98.89 355	97.05 389	89.03 354	86.49 410	95.42 384	76.59 386	95.02 446	87.22 387	84.09 379	93.93 401
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SSC-MVS		75.42 449	76.40 451	72.49 474	80.68 488	53.62 496	97.42 426	94.06 474	80.42 451	68.75 482	90.14 465	76.54 387	81.66 494	33.25 498	66.34 472	82.19 485

IterMVS-SCA-FT		90.85 354	90.16 354	92.93 397	96.72 329	89.96 387	98.89 355	96.99 393	88.95 360	86.63 407	95.67 370	76.48 388	95.00 447	87.04 390	84.04 382	93.84 408

SCA		94.69 249	93.81 263	97.33 234	97.10 294	94.44 251	98.86 361	98.32 197	93.30 206	96.17 246	95.59 374	76.48 388	97.95 324	91.06 323	97.43 201	99.59 154

ab-mvs		94.69 249	93.42 276	98.51 133	98.07 217	96.26 170	96.49 449	98.68 84	90.31 337	94.54 274	97.00 325	76.30 390	99.71 160	95.98 226	93.38 307	99.56 163

DTE-MVSNet		89.40 386	88.24 389	92.88 398	92.66 429	89.95 388	99.10 321	98.22 213	87.29 391	85.12 424	96.22 352	76.27 391	95.30 445	83.56 419	75.74 441	93.41 421

ACMM	91.95 10	92.88 308	92.52 308	93.98 368	95.75 358	89.08 400	99.77 180	97.52 303	93.00 221	89.95 335	97.99 293	76.17 392	98.46 278	93.63 285	88.87 330	94.39 347
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DSMNet-mixed		88.28 395	88.24 389	88.42 447	89.64 460	75.38 478	98.06 414	89.86 492	85.59 415	88.20 387	92.14 457	76.15 393	91.95 476	78.46 450	96.05 253	97.92 299

VPA-MVSNet		92.70 314	91.55 327	96.16 277	95.09 378	96.20 176	98.88 357	99.00 39	91.02 312	91.82 312	95.29 395	76.05 394	97.96 323	95.62 234	81.19 400	94.30 354

SDMVSNet		94.80 243	93.96 258	97.33 234	98.92 146	95.42 209	99.59 245	98.99 40	92.41 260	92.55 305	97.85 300	75.81 395	98.93 221	97.90 160	91.62 314	97.64 309

TR-MVS		94.54 254	93.56 271	97.49 217	97.96 223	94.34 259	98.71 375	97.51 304	90.30 338	94.51 276	98.69 244	75.56 396	98.77 243	92.82 297	95.99 254	99.35 207

PS-CasMVS		90.63 359	89.51 366	93.99 366	93.83 401	91.70 346	98.98 341	98.52 128	88.48 373	86.15 416	96.53 345	75.46 397	96.31 418	88.83 359	78.86 421	93.95 399

TransMVSNet (Re)		87.25 406	85.28 413	93.16 391	93.56 405	91.03 360	98.54 388	94.05 475	83.69 433	81.09 446	96.16 354	75.32 398	96.40 412	76.69 458	68.41 466	92.06 447

LPG-MVS_test		92.96 305	92.71 300	93.71 376	95.43 373	88.67 406	99.75 192	97.62 287	92.81 230	90.05 331	98.49 267	75.24 399	98.40 285	95.84 229	89.12 326	94.07 387

LGP-MVS_train				93.71 376	95.43 373	88.67 406		97.62 287	92.81 230	90.05 331	98.49 267	75.24 399	98.40 285	95.84 229	89.12 326	94.07 387

ECVR-MVS		95.66 219	95.05 225	97.51 214	98.66 168	93.71 280	98.85 363	98.45 143	94.93 126	96.86 213	98.96 208	75.22 401	99.20 202	95.34 235	98.15 183	99.64 139

test1111		95.57 222	94.98 228	97.37 229	98.56 174	93.37 297	98.86 361	98.45 143	94.95 125	96.63 221	98.95 213	75.21 402	99.11 208	95.02 242	98.14 185	99.64 139

OPM-MVS		93.21 298	92.80 297	94.44 342	93.12 414	90.85 367	99.77 180	97.61 290	96.19 94	91.56 314	98.65 248	75.16 403	98.47 275	93.78 280	89.39 325	93.99 396
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tfpnnormal		89.29 388	87.61 395	94.34 347	94.35 392	94.13 268	98.95 348	98.94 44	83.94 429	84.47 428	95.51 379	74.84 404	97.39 343	77.05 457	80.41 411	91.48 453

AllTest		92.48 320	91.64 323	95.00 316	99.01 131	88.43 410	98.94 349	96.82 413	86.50 402	88.71 367	98.47 271	74.73 405	99.88 124	85.39 404	96.18 250	96.71 323

TestCases				95.00 316	99.01 131	88.43 410		96.82 413	86.50 402	88.71 367	98.47 271	74.73 405	99.88 124	85.39 404	96.18 250	96.71 323

Anonymous20231206		86.32 410	85.42 412	89.02 441	89.11 462	80.53 470	99.05 333	95.28 456	85.43 417	82.82 436	93.92 431	74.40 407	93.44 466	66.99 476	81.83 396	93.08 431

XXY-MVS		91.82 331	90.46 343	95.88 287	93.91 400	95.40 211	98.87 360	97.69 279	88.63 370	87.87 390	97.08 319	74.38 408	97.89 327	91.66 314	84.07 380	94.35 351

ACMP	92.05 9	92.74 313	92.42 310	93.73 374	95.91 350	88.72 405	99.81 166	97.53 301	94.13 166	87.00 403	98.23 284	74.07 409	98.47 275	96.22 222	88.86 331	93.99 396
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	88.28 18	90.29 368	89.05 375	94.02 363	95.08 379	90.15 383	97.19 433	97.43 310	84.91 424	83.99 431	97.06 321	74.00 410	98.28 302	84.08 413	87.71 348	93.62 418
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		87.63 405	85.51 411	93.99 366	87.22 466	91.56 355	99.81 166	97.36 320	79.54 456	88.60 373	93.29 441	73.76 411	96.34 415	89.27 355	60.78 486	94.06 389

pm-mvs1		89.36 387	87.81 393	94.01 364	93.40 410	91.93 330	98.62 384	96.48 429	86.25 406	83.86 432	96.14 356	73.68 412	97.04 370	86.16 399	75.73 442	93.04 432

Elysia		94.50 258	93.38 280	97.85 180	96.49 335	96.70 148	98.98 341	97.78 270	90.81 317	96.19 244	98.55 263	73.63 413	98.98 215	89.41 349	98.56 168	97.88 300

StellarMVS		94.50 258	93.38 280	97.85 180	96.49 335	96.70 148	98.98 341	97.78 270	90.81 317	96.19 244	98.55 263	73.63 413	98.98 215	89.41 349	98.56 168	97.88 300

pmmvs5		90.17 372	89.09 373	93.40 384	92.10 438	89.77 391	99.74 196	95.58 450	85.88 410	87.24 402	95.74 366	73.41 415	96.48 405	88.54 363	83.56 384	93.95 399

OurMVSNet-221017-0		89.81 379	89.48 368	90.83 422	91.64 443	81.21 464	98.17 410	95.38 455	91.48 294	85.65 420	97.31 312	72.66 416	97.29 354	88.15 375	84.83 373	93.97 398

jajsoiax		91.92 330	91.18 333	94.15 354	91.35 447	90.95 364	99.00 339	97.42 312	92.61 245	87.38 399	97.08 319	72.46 417	97.36 344	94.53 259	88.77 332	94.13 383

UGNet		95.33 229	94.57 240	97.62 202	98.55 177	94.85 236	98.67 380	99.32 26	95.75 107	96.80 218	96.27 351	72.18 418	99.96 76	94.58 258	99.05 152	98.04 297
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		91.81 332	91.08 335	94.00 365	91.63 444	90.58 373	98.67 380	97.43 310	92.43 259	87.37 400	97.05 322	71.76 419	97.32 349	94.75 253	88.68 334	94.11 385

SixPastTwentyTwo		88.73 391	88.01 392	90.88 419	91.85 441	82.24 457	98.22 408	95.18 461	88.97 358	82.26 438	96.89 330	71.75 420	96.67 395	84.00 414	82.98 385	93.72 416

test_fmvs1		95.35 228	95.68 196	94.36 346	98.99 136	84.98 438	99.96 56	96.65 422	97.60 34	99.73 46	98.96 208	71.58 421	99.93 104	98.31 134	99.37 135	98.17 292

GBi-Net		90.88 352	89.82 358	94.08 360	97.53 263	91.97 327	98.43 394	96.95 399	87.05 394	89.68 342	94.72 415	71.34 422	96.11 425	87.01 392	85.65 364	94.17 368

test1		90.88 352	89.82 358	94.08 360	97.53 263	91.97 327	98.43 394	96.95 399	87.05 394	89.68 342	94.72 415	71.34 422	96.11 425	87.01 392	85.65 364	94.17 368

FMVSNet2		91.02 349	89.56 363	95.41 304	97.53 263	95.74 193	98.98 341	97.41 314	87.05 394	88.43 379	95.00 409	71.34 422	96.24 421	85.12 407	85.21 369	94.25 358

PVSNet_0	88.03 19	91.80 335	90.27 349	96.38 272	98.27 202	90.46 376	99.94 93	99.61 13	93.99 175	86.26 415	97.39 311	71.13 425	99.89 118	98.77 105	67.05 470	98.79 271

sd_testset		93.55 292	92.83 296	95.74 294	98.92 146	90.89 366	98.24 404	98.85 63	92.41 260	92.55 305	97.85 300	71.07 426	98.68 257	93.93 271	91.62 314	97.64 309

Anonymous20231211		89.86 378	88.44 386	94.13 358	98.93 143	90.68 370	98.54 388	98.26 207	76.28 466	86.73 405	95.54 376	70.60 427	97.56 339	90.82 330	80.27 414	94.15 374

ITE_SJBPF				92.38 404	95.69 365	85.14 436		95.71 446	92.81 230	89.33 355	98.11 287	70.23 428	98.42 281	85.91 402	88.16 343	93.59 419

ACMH	89.72 17	90.64 358	89.63 361	93.66 380	95.64 367	88.64 408	98.55 386	97.45 308	89.03 354	81.62 442	97.61 304	69.75 429	98.41 283	89.37 351	87.62 352	93.92 402
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVS-HIRNet		86.22 411	83.19 424	95.31 308	96.71 330	90.29 379	92.12 478	97.33 325	62.85 486	86.82 404	70.37 491	69.37 430	97.49 341	75.12 462	97.99 191	98.15 293

Anonymous202405211		93.10 303	91.99 316	96.40 270	99.10 125	89.65 392	98.88 357	97.93 251	83.71 432	94.00 287	98.75 238	68.79 431	99.88 124	95.08 241	91.71 313	99.68 131

test20.03		84.72 424	83.99 416	86.91 452	88.19 465	80.62 469	98.88 357	95.94 440	88.36 376	78.87 455	94.62 420	68.75 432	89.11 484	66.52 478	75.82 440	91.00 456

VPNet		91.81 332	90.46 343	95.85 289	94.74 384	95.54 204	98.98 341	98.59 103	92.14 272	90.77 325	97.44 308	68.73 433	97.54 340	94.89 249	77.89 426	94.46 340

K. test v3		88.05 397	87.24 398	90.47 428	91.82 442	82.23 458	98.96 347	97.42 312	89.05 353	76.93 465	95.60 373	68.49 434	95.42 441	85.87 403	81.01 407	93.75 412

ACMH+	89.98 16	90.35 365	89.54 364	92.78 401	95.99 347	86.12 430	98.81 366	97.18 356	89.38 349	83.14 435	97.76 303	68.42 435	98.43 280	89.11 357	86.05 362	93.78 411

MDA-MVSNet-bldmvs		84.09 427	81.52 434	91.81 413	91.32 448	88.00 417	98.67 380	95.92 441	80.22 452	55.60 492	93.32 438	68.29 436	93.60 465	73.76 464	76.61 438	93.82 410

ttmdpeth		88.23 396	87.06 399	91.75 414	89.91 459	87.35 422	98.92 354	95.73 444	87.92 383	84.02 430	96.31 349	68.23 437	96.84 384	86.33 397	76.12 439	91.06 455

MS-PatchMatch		90.65 357	90.30 348	91.71 415	94.22 395	85.50 435	98.24 404	97.70 277	88.67 368	86.42 412	96.37 348	67.82 438	98.03 319	83.62 418	99.62 100	91.60 451

KD-MVS_self_test		83.59 431	82.06 431	88.20 448	86.93 468	80.70 468	97.21 432	96.38 430	82.87 439	82.49 437	88.97 469	67.63 439	92.32 474	73.75 465	62.30 480	91.58 452

LFMVS		94.75 248	93.56 271	98.30 148	99.03 130	95.70 196	98.74 372	97.98 246	87.81 386	98.47 148	99.39 149	67.43 440	99.53 175	98.01 152	95.20 283	99.67 133

MIMVSNet		90.30 367	88.67 382	95.17 312	96.45 337	91.64 348	92.39 477	97.15 361	85.99 408	90.50 326	93.19 442	66.95 441	94.86 451	82.01 429	93.43 305	99.01 256

test_vis1_n_1920		95.44 225	95.31 213	95.82 291	98.50 184	88.74 404	99.98 24	97.30 333	97.84 28	99.85 19	99.19 176	66.82 442	99.97 64	98.82 101	99.46 127	98.76 272

XVG-ACMP-BASELINE		91.22 347	90.75 338	92.63 403	93.73 403	85.61 433	98.52 390	97.44 309	92.77 234	89.90 337	96.85 333	66.64 443	98.39 287	92.29 301	88.61 335	93.89 404

Anonymous20240529		92.10 328	90.65 340	96.47 265	98.82 156	90.61 372	98.72 374	98.67 87	75.54 470	93.90 289	98.58 259	66.23 444	99.90 113	94.70 255	90.67 317	98.90 266

lessismore_v0				90.53 426	90.58 453	80.90 467		95.80 442		77.01 464	95.84 363	66.15 445	96.95 376	83.03 422	75.05 444	93.74 415

USDC		90.00 376	88.96 376	93.10 394	94.81 383	88.16 414	98.71 375	95.54 451	93.66 191	83.75 433	97.20 315	65.58 446	98.31 298	83.96 416	87.49 354	92.85 436

pmmvs-eth3d		84.03 428	81.97 432	90.20 431	84.15 479	87.09 424	98.10 413	94.73 467	83.05 437	74.10 475	87.77 476	65.56 447	94.01 458	81.08 434	69.24 462	89.49 474

Anonymous20240521		85.15 418	83.81 420	89.16 440	88.32 463	82.69 453	98.80 369	95.74 443	79.72 453	81.53 443	90.99 460	65.38 448	94.16 457	72.69 466	81.11 403	90.63 461

LF4IMVS		89.25 389	88.85 377	90.45 429	92.81 427	81.19 465	98.12 411	94.79 465	91.44 296	86.29 414	97.11 317	65.30 449	98.11 313	88.53 364	85.25 368	92.07 446

new_pmnet		84.49 426	82.92 426	89.21 439	90.03 457	82.60 454	96.89 442	95.62 449	80.59 450	75.77 470	89.17 468	65.04 450	94.79 452	72.12 468	81.02 406	90.23 463

SSC-MVS3.2		89.59 383	88.66 383	92.38 404	94.29 394	86.12 430	99.49 267	97.66 283	90.28 339	88.63 372	95.18 399	64.46 451	96.88 382	85.30 406	82.66 388	94.14 378

CMPMVS	61.59 21	84.75 423	85.14 414	83.57 459	90.32 455	62.54 487	96.98 439	97.59 294	74.33 474	69.95 480	96.66 338	64.17 452	98.32 297	87.88 379	88.41 340	89.84 469
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_0402		85.58 413	83.94 418	90.50 427	93.81 402	85.04 437	98.55 386	95.20 460	76.01 467	79.72 454	95.13 400	64.15 453	96.26 420	66.04 480	86.88 356	90.21 464

TDRefinement		84.76 422	82.56 429	91.38 417	74.58 495	84.80 441	97.36 430	94.56 470	84.73 425	80.21 450	96.12 359	63.56 454	98.39 287	87.92 378	63.97 476	90.95 458

mmtdpeth		88.52 392	87.75 394	90.85 421	95.71 362	83.47 450	98.94 349	94.85 463	88.78 365	97.19 200	89.58 466	63.29 455	98.97 217	98.54 119	62.86 478	90.10 466

UnsupCasMVSNet_eth		85.52 414	83.99 416	90.10 433	89.36 461	83.51 449	96.65 446	97.99 244	89.14 351	75.89 469	93.83 432	63.25 456	93.92 459	81.92 430	67.90 469	92.88 435

tt0805		91.28 344	90.18 352	94.60 331	96.26 340	87.55 419	98.39 398	98.72 78	89.00 356	89.22 358	98.47 271	62.98 457	98.96 219	90.57 334	88.00 345	97.28 319

new-patchmatchnet		81.19 437	79.34 444	86.76 453	82.86 482	80.36 471	97.92 417	95.27 457	82.09 444	72.02 477	86.87 480	62.81 458	90.74 481	71.10 469	63.08 477	89.19 477

mvs5depth		84.87 421	82.90 427	90.77 423	85.59 477	84.84 440	91.10 484	93.29 482	83.14 436	85.07 425	94.33 428	62.17 459	97.32 349	78.83 449	72.59 454	90.14 465

TinyColmap		87.87 400	86.51 401	91.94 410	95.05 380	85.57 434	97.65 424	94.08 473	84.40 428	81.82 441	96.85 333	62.14 460	98.33 296	80.25 440	86.37 359	91.91 450

test_fmvs1_n		94.25 269	94.36 244	93.92 369	97.68 248	83.70 445	99.90 117	96.57 425	97.40 40	99.67 52	98.88 220	61.82 461	99.92 110	98.23 140	99.13 147	98.14 295

VDDNet		93.12 302	91.91 318	96.76 257	96.67 333	92.65 315	98.69 378	98.21 217	82.81 440	97.75 183	99.28 160	61.57 462	99.48 186	98.09 148	94.09 297	98.15 293

pmmvs6		85.69 412	83.84 419	91.26 418	90.00 458	84.41 442	97.82 420	96.15 436	75.86 468	81.29 445	95.39 387	61.21 463	96.87 383	83.52 420	73.29 447	92.50 442

VDD-MVS		93.77 285	92.94 294	96.27 275	98.55 177	90.22 381	98.77 371	97.79 266	90.85 315	96.82 216	99.42 142	61.18 464	99.77 150	98.95 90	94.13 296	98.82 269

FE-MVSNET		81.05 439	78.81 446	87.79 450	81.98 484	83.70 445	98.23 406	91.78 488	81.27 447	74.29 473	87.44 478	60.92 465	90.67 482	64.92 482	68.43 465	89.01 478

testgi		89.01 390	88.04 391	91.90 411	93.49 407	84.89 439	99.73 203	95.66 448	93.89 184	85.14 423	98.17 285	59.68 466	94.66 454	77.73 453	88.88 329	96.16 331

FE-MVSNET2		83.57 432	81.36 435	90.20 431	82.83 483	87.59 418	98.28 402	96.04 438	85.33 419	74.13 474	87.45 477	59.16 467	93.26 468	79.12 447	69.91 458	89.77 470

FMVSNet1		88.50 393	86.64 400	94.08 360	95.62 369	91.97 327	98.43 394	96.95 399	83.00 438	86.08 417	94.72 415	59.09 468	96.11 425	81.82 431	84.07 380	94.17 368

DeepMVS_CX				82.92 461	95.98 349	58.66 492		96.01 439	92.72 236	78.34 459	95.51 379	58.29 469	98.08 315	82.57 424	85.29 367	92.03 448

UniMVSNet_ETH3D		90.06 375	88.58 384	94.49 339	94.67 386	88.09 415	97.81 421	97.57 295	83.91 431	88.44 376	97.41 309	57.44 470	97.62 337	91.41 317	88.59 337	97.77 305

pmmvs3		80.27 442	77.77 447	87.76 451	80.32 489	82.43 456	98.23 406	91.97 486	72.74 477	78.75 456	87.97 475	57.30 471	90.99 480	70.31 470	62.37 479	89.87 468

OpenMVS_ROB	79.82 20	83.77 430	81.68 433	90.03 434	88.30 464	82.82 452	98.46 391	95.22 459	73.92 475	76.00 468	91.29 459	55.00 472	96.94 377	68.40 474	88.51 339	90.34 462

test_fmvs2		89.47 385	89.70 360	88.77 445	94.54 388	75.74 475	99.83 159	94.70 469	94.71 137	91.08 318	96.82 337	54.46 473	97.78 332	92.87 296	88.27 341	92.80 437

tmp_tt		65.23 458	62.94 461	72.13 475	44.90 504	50.03 500	81.05 491	89.42 495	38.45 494	48.51 496	99.90 23	54.09 474	78.70 496	91.84 313	18.26 498	87.64 480

tt0320		83.56 433	81.15 436	90.77 423	92.77 428	83.58 447	96.83 444	95.52 452	63.26 484	81.36 444	92.54 445	53.26 475	95.77 435	80.45 437	74.38 445	92.96 433

EGC-MVSNET		69.38 450	63.76 460	86.26 455	90.32 455	81.66 463	96.24 455	93.85 477	0.99 502	3.22 503	92.33 455	52.44 476	92.92 471	59.53 488	84.90 372	84.21 483

test_vis1_n		93.61 291	93.03 291	95.35 305	95.86 351	86.94 425	99.87 133	96.36 431	96.85 62	99.54 72	98.79 236	52.41 477	99.83 140	98.64 114	98.97 154	99.29 221

MIMVSNet1		82.58 435	80.51 440	88.78 443	86.68 469	84.20 443	96.65 446	95.41 454	78.75 462	78.59 458	92.44 447	51.88 478	89.76 483	65.26 481	78.95 419	92.38 445

EG-PatchMatch MVS		85.35 417	83.81 420	89.99 435	90.39 454	81.89 460	98.21 409	96.09 437	81.78 445	74.73 471	93.72 435	51.56 479	97.12 363	79.16 446	88.61 335	90.96 457

sc_t1		85.01 420	82.46 430	92.67 402	92.44 432	83.09 451	97.39 429	95.72 445	65.06 482	85.64 421	96.16 354	49.50 480	97.34 346	84.86 410	75.39 443	97.57 314

tt0320-xc		82.94 434	80.35 441	90.72 425	92.90 423	83.54 448	96.85 443	94.73 467	63.12 485	79.85 453	93.77 434	49.43 481	95.46 440	80.98 435	71.54 455	93.16 429

UnsupCasMVSNet_bld		79.97 445	77.03 450	88.78 443	85.62 476	81.98 459	93.66 471	97.35 321	75.51 471	70.79 479	83.05 486	48.70 482	94.91 450	78.31 451	60.29 488	89.46 475

test_vis1_rt		86.87 408	86.05 405	89.34 438	96.12 342	78.07 473	99.87 133	83.54 499	92.03 277	78.21 460	89.51 467	45.80 483	99.91 111	96.25 221	93.11 310	90.03 467

test_method		80.79 440	79.70 443	84.08 458	92.83 425	67.06 484	99.51 263	95.42 453	54.34 490	81.07 447	93.53 436	44.48 484	92.22 475	78.90 448	77.23 433	92.94 434

APD_test1		81.15 438	80.92 438	81.86 462	92.45 431	59.76 491	96.04 459	93.61 480	73.29 476	77.06 463	96.64 340	44.28 485	96.16 424	72.35 467	82.52 389	89.67 472

mvsany_test3		82.12 436	81.14 437	85.06 457	81.87 485	70.41 481	97.09 436	92.14 485	91.27 303	77.84 461	88.73 470	39.31 486	95.49 438	90.75 332	71.24 456	89.29 476

usedtu_dtu_shiyan2		75.87 448	72.37 452	86.39 454	76.18 494	75.49 477	96.53 448	93.82 478	64.74 483	72.53 476	88.48 471	37.67 487	91.12 479	64.13 483	57.22 490	92.56 439

PM-MVS		80.47 441	78.88 445	85.26 456	83.79 481	72.22 480	95.89 462	91.08 489	85.71 414	76.56 467	88.30 472	36.64 488	93.90 460	82.39 426	69.57 461	89.66 473

ambc				83.23 460	77.17 492	62.61 486	87.38 489	94.55 471		76.72 466	86.65 481	30.16 489	96.36 414	84.85 411	69.86 459	90.73 459

Gipuma		66.95 457	65.00 457	72.79 471	91.52 445	67.96 483	66.16 494	95.15 462	47.89 492	58.54 489	67.99 494	29.74 490	87.54 488	50.20 492	77.83 427	62.87 494
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EMVS		51.44 463	51.22 465	52.11 481	70.71 497	44.97 504	94.04 468	75.66 503	35.34 498	42.40 498	61.56 499	28.93 491	65.87 500	27.64 500	24.73 496	45.49 497

test_fmvs3		79.99 444	80.17 442	79.45 464	84.02 480	62.83 485	99.05 333	93.49 481	88.29 378	80.06 452	86.65 481	28.09 492	88.00 485	88.63 360	73.27 448	87.54 481

test_f		78.40 446	77.59 448	80.81 463	80.82 487	62.48 488	96.96 440	93.08 483	83.44 434	74.57 472	84.57 485	27.95 493	92.63 472	84.15 412	72.79 450	87.32 482

E-PMN		52.30 461	52.18 463	52.67 480	71.51 496	45.40 502	93.62 472	76.60 502	36.01 496	43.50 497	64.13 496	27.11 494	67.31 499	31.06 499	26.06 495	45.30 498

FPMVS		68.72 452	68.72 453	68.71 476	65.95 499	44.27 505	95.97 461	94.74 466	51.13 491	53.26 493	90.50 464	25.11 495	83.00 492	60.80 486	80.97 408	78.87 489

PMMVS2		67.15 456	64.15 459	76.14 468	70.56 498	62.07 489	93.89 469	87.52 496	58.09 487	60.02 486	78.32 488	22.38 496	84.54 491	59.56 487	47.03 493	81.80 486

testf1		68.38 453	66.92 454	72.78 472	78.80 490	50.36 498	90.95 485	87.35 497	55.47 488	58.95 487	88.14 473	20.64 497	87.60 486	57.28 489	64.69 474	80.39 487

APD_test2		68.38 453	66.92 454	72.78 472	78.80 490	50.36 498	90.95 485	87.35 497	55.47 488	58.95 487	88.14 473	20.64 497	87.60 486	57.28 489	64.69 474	80.39 487

LCM-MVSNet		67.77 455	64.73 458	76.87 467	62.95 501	56.25 494	89.37 488	93.74 479	44.53 493	61.99 485	80.74 487	20.42 499	86.53 490	69.37 473	59.50 489	87.84 479

test123		37.68 465	39.14 468	33.31 482	19.94 506	24.83 508	98.36 399	9.75 507	15.53 500	51.31 494	87.14 479	19.62 500	17.74 502	47.10 493	3.47 501	57.36 495

ANet_high		56.10 459	52.24 462	67.66 477	49.27 503	56.82 493	83.94 490	82.02 500	70.47 479	33.28 500	64.54 495	17.23 501	69.16 498	45.59 494	23.85 497	77.02 490

test_vis3_rt		68.82 451	66.69 456	75.21 469	76.24 493	60.41 490	96.44 450	68.71 504	75.13 472	50.54 495	69.52 493	16.42 502	96.32 417	80.27 439	66.92 471	68.89 491

testmvs		40.60 464	44.45 467	29.05 483	19.49 507	14.11 509	99.68 225	18.47 506	20.74 499	64.59 484	98.48 270	10.95 503	17.09 503	56.66 491	11.01 499	55.94 496

PMVS	49.05 23	53.75 460	51.34 464	60.97 479	40.80 505	34.68 506	74.82 493	89.62 494	37.55 495	28.67 501	72.12 490	7.09 504	81.63 495	43.17 495	68.21 467	66.59 493
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		20.37 467	20.84 470	18.99 484	65.34 500	27.73 507	50.43 495	7.67 508	9.50 501	8.01 502	6.34 502	6.13 505	26.24 501	23.40 501	10.69 500	2.99 499

MVE	53.74 22	51.54 462	47.86 466	62.60 478	59.56 502	50.93 497	79.41 492	77.69 501	35.69 497	36.27 499	61.76 498	5.79 506	69.63 497	37.97 496	36.61 494	67.24 492
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
mmdepth		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 504	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

monomultidepth		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 504	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

test_blank		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.02 503	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

uanet_test		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 504	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

DCPMVS		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 504	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

sosnet-low-res		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 504	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

sosnet		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 504	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

uncertanet		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 504	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

Regformer		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 504	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

ab-mvs-re		8.28 468	11.04 471	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	99.40 147	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

uanet		0.00 470	0.00 473	0.00 485	0.00 508	0.00 510	0.00 496	0.00 509	0.00 503	0.00 504	0.00 504	0.00 507	0.00 504	0.00 502	0.00 502	0.00 500

MED-MVS test				99.60 24	99.96 9	98.79 42	99.97 42	98.88 55	96.36 88	99.07 111	99.93 12		100.00 1	99.98 9	99.96 46	99.99 25

WAC-MVS						90.97 361								86.10 401

FOURS1					99.92 36	97.66 105	99.95 75	98.36 188	95.58 112	99.52 75

MSC_two_6792asdad				99.93 2	99.91 44	99.80 2		98.41 173					100.00 1	99.96 12	100.00 1	100.00 1

No_MVS				99.93 2	99.91 44	99.80 2		98.41 173					100.00 1	99.96 12	100.00 1	100.00 1

eth-test2					0.00 508

eth-test					0.00 508

IU-MVS					99.93 28	99.31 11		98.41 173	97.71 31	99.84 22				100.00 1	100.00 1	100.00 1

save fliter					99.82 65	98.79 42	99.96 56	98.40 177	97.66 33

test_0728_SECOND				99.82 8	99.94 17	99.47 8	99.95 75	98.43 156					100.00 1	99.99 5	100.00 1	100.00 1

GSMVS																99.59 154

test_part2					99.89 50	99.25 20				99.49 78

MTGPA								98.28 204

MTMP							99.87 133	96.49 428

gm-plane-assit					96.97 308	93.76 279			91.47 295		98.96 208		98.79 240	94.92 246

test9_res														99.71 48	99.99 21	100.00 1

agg_prior2														99.48 63	100.00 1	100.00 1

agg_prior					99.93 28	98.77 47		98.43 156		99.63 58			99.85 130

test_prior4						98.05 82	99.94 93

test_prior				99.43 41	99.94 17	98.49 66		98.65 88					99.80 143			99.99 25

旧先验2							99.46 275		94.21 165	99.85 19			99.95 85	96.96 196

新几何2							99.40 280

无先验							99.49 267	98.71 79	93.46 199				100.00 1	94.36 261		99.99 25

原ACMM2							99.90 117

testdata2													99.99 40	90.54 336

testdata1							99.28 306		96.35 90

plane_prior7					95.71 362	91.59 354

plane_prior5								97.87 258					98.37 293	97.79 167	89.55 322	94.52 337

plane_prior4											98.59 256

plane_prior3						91.64 348			96.63 73	93.01 297

plane_prior2							99.84 152		96.38 84

plane_prior1					95.73 359

plane_prior						91.74 341	99.86 144		96.76 68						89.59 321

n2								0.00 509

nn								0.00 509

door-mid								89.69 493

test11								98.44 148

door								90.31 490

HQP5-MVS						91.85 334

HQP-NCC					95.78 352		99.87 133		96.82 64	93.37 292

ACMP_Plane					95.78 352		99.87 133		96.82 64	93.37 292

BP-MVS														97.92 158

HQP4-MVS										93.37 292			98.39 287			94.53 335

HQP3-MVS								97.89 256							89.60 319

NP-MVS					95.77 355	91.79 338					98.65 248

ACMMP++_ref															87.04 355

ACMMP++															88.23 342

High-resolution multi-view benchmark