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		95.38 194	95.07 193	96.32 230	99.32 104	96.60 140	99.76 165	98.85 57	96.65 68	87.83 333	96.05 312	99.52 1	98.11 269	96.58 183	81.07 357	94.25 309

CHOSEN 280x420		99.01 14	99.03 10	98.95 87	99.38 100	98.87 33	98.46 337	99.42 21	97.03 53	99.02 105	99.09 161	99.35 2	98.21 264	99.73 39	99.78 84	99.77 107

GG-mvs-BLEND				98.54 119	98.21 194	98.01 78	93.87 408	98.52 118		97.92 156	97.92 252	99.02 3	97.94 282	98.17 130	99.58 102	99.67 121

gg-mvs-nofinetune		93.51 247	91.86 273	98.47 125	97.72 230	97.96 83	92.62 412	98.51 121	74.70 414	97.33 175	69.59 428	98.91 4	97.79 286	97.77 156	99.56 103	99.67 121

test_0728_THIRD									96.48 72	99.83 18	99.91 14	97.87 5	100.00 1	99.92 13	100.00 1	100.00 1

baseline2		96.71 149	96.49 141	97.37 196	95.63 323	95.96 168	99.74 172	98.88 52	92.94 196	91.61 267	98.97 175	97.72 6	98.62 226	94.83 212	98.08 175	97.53 267

BP-MVS1		98.33 54	98.18 51	98.81 93	97.44 249	97.98 80	99.96 44	98.17 209	94.88 116	98.77 117	99.59 115	97.59 7	99.08 197	98.24 127	98.93 144	99.36 183

SteuartSystems-ACMMP		99.02 13	98.97 13	99.18 55	98.72 151	97.71 91	99.98 17	98.44 138	96.85 58	99.80 22	99.91 14	97.57 8	99.85 120	99.44 58	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
thisisatest0515		97.41 112	97.02 118	98.59 113	97.71 232	97.52 100	99.97 35	98.54 113	91.83 243	97.45 171	99.04 165	97.50 9	99.10 196	94.75 215	96.37 211	99.16 205

PC_three_1452									96.96 56	99.80 22	99.79 58	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

test_one_0601					99.94 13	99.30 12		98.41 163	96.63 69	99.75 35	99.93 11	97.49 10

thisisatest0530		97.10 125	96.72 132	98.22 141	97.60 240	96.70 135	99.92 90	98.54 113	91.11 267	97.07 184	98.97 175	97.47 12	99.03 199	93.73 242	96.09 215	98.92 222

tttt0517		96.85 139	96.49 141	97.92 159	97.48 248	95.89 170	99.85 133	98.54 113	90.72 280	96.63 195	98.93 186	97.47 12	99.02 200	93.03 255	95.76 227	98.85 226

DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 39	99.31 10	99.95 63	98.43 146	96.48 72	99.80 22	99.93 11	97.44 14	100.00 1	99.92 13	99.98 32	100.00 1

OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 44				99.80 54	97.44 14	100.00 1	100.00 1	99.98 32	100.00 1

MSP-MVS		99.09 9	99.12 5	98.98 84	99.93 24	97.24 113	99.95 63	98.42 158	97.50 34	99.52 69	99.88 24	97.43 16	99.71 150	99.50 53	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
NCCC		99.37 2	99.25 2	99.71 15	99.96 8	99.15 22	99.97 35	98.62 89	98.02 18	99.90 3	99.95 3	97.33 17	100.00 1	99.54 51	100.00 1	100.00 1

MVSTER		95.53 190	95.22 187	96.45 224	98.56 162	97.72 90	99.91 98	97.67 258	92.38 228	91.39 269	97.14 271	97.24 18	97.30 306	94.80 213	87.85 303	94.34 304

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 63	98.32 187	97.28 41	99.83 18	99.91 14	97.22 19	100.00 1	99.99 5	100.00 1	99.89 89
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 24	99.29 15	99.96 44	98.42 158	97.28 41	99.86 11	99.94 4	97.22 19

test_241102_TWO								98.43 146	97.27 43	99.80 22	99.94 4	97.18 21	100.00 1	100.00 1	100.00 1	100.00 1

DPM-MVS		98.83 21	98.46 33	99.97 1	99.33 102	99.92 1	99.96 44	98.44 138	97.96 19	99.55 64	99.94 4	97.18 21	100.00 1	93.81 237	99.94 55	99.98 51

GDP-MVS		97.88 77	97.59 91	98.75 98	97.59 241	97.81 88	99.95 63	97.37 295	94.44 133	99.08 101	99.58 118	97.13 23	99.08 197	94.99 205	98.17 167	99.37 181

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 17	98.69 73	98.20 9	99.93 1	99.98 2	96.82 24	100.00 1	99.75 35	100.00 1	99.99 23

WBMVS		94.52 220	94.03 218	95.98 237	98.38 179	96.68 136	99.92 90	97.63 262	90.75 279	89.64 296	95.25 347	96.77 25	96.90 333	94.35 225	83.57 335	94.35 302

UBG		97.84 82	97.69 84	98.29 138	98.38 179	96.59 142	99.90 104	98.53 116	93.91 164	98.52 130	98.42 231	96.77 25	99.17 191	98.54 111	96.20 212	99.11 211

SED-MVS		99.28 5	99.11 7	99.77 8	99.93 24	99.30 12	99.96 44	98.43 146	97.27 43	99.80 22	99.94 4	96.71 27	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 146	97.26 45	99.80 22	99.88 24	96.71 27	100.00 1

DPE-MVS		99.26 6	99.10 8	99.74 11	99.89 45	99.24 19	99.87 119	98.44 138	97.48 35	99.64 51	99.94 4	96.68 29	99.99 36	99.99 5	100.00 1	99.99 23
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
segment_acmp												96.68 29

UWE-MVS		96.79 142	96.72 132	97.00 207	98.51 170	93.70 243	99.71 186	98.60 92	92.96 195	97.09 182	98.34 235	96.67 31	98.85 208	92.11 264	96.50 206	98.44 241

patch_mono-2		98.24 64	99.12 5	95.59 247	99.67 81	86.91 368	99.95 63	98.89 50	97.60 30	99.90 3	99.76 67	96.54 32	99.98 47	99.94 11	99.82 81	99.88 90

PAPM		98.60 33	98.42 34	99.14 65	96.05 300	98.96 26	99.90 104	99.35 24	96.68 67	98.35 141	99.66 106	96.45 33	98.51 231	99.45 57	99.89 70	99.96 68

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 35	98.64 82	98.47 3	99.13 98	99.92 13	96.38 34	100.00 1	99.74 37	100.00 1	100.00 1

ET-MVSNet_ETH3D		94.37 225	93.28 242	97.64 177	98.30 186	97.99 79	99.99 5	97.61 268	94.35 139	71.57 414	99.45 131	96.23 35	95.34 383	96.91 180	85.14 323	99.59 141

EPP-MVSNet		96.69 150	96.60 137	96.96 209	97.74 225	93.05 259	99.37 247	98.56 103	88.75 318	95.83 217	99.01 168	96.01 36	98.56 228	96.92 179	97.20 192	99.25 200

test_prior2							99.95 63		95.78 92	99.73 40	99.76 67	96.00 37		99.78 29	100.00 1

train_agg		98.88 20	98.65 24	99.59 23	99.92 31	98.92 29	99.96 44	98.43 146	94.35 139	99.71 42	99.86 29	95.94 38	99.85 120	99.69 43	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 44	98.43 146	94.35 139	99.69 44	99.85 33	95.94 38	99.85 120

MSLP-MVS++		99.13 8	99.01 11	99.49 32	99.94 13	98.46 61	99.98 17	98.86 54	97.10 49	99.80 22	99.94 4	95.92 40	100.00 1	99.51 52	100.00 1	100.00 1

TEST9					99.92 31	98.92 29	99.96 44	98.43 146	93.90 165	99.71 42	99.86 29	95.88 41	99.85 120

test_yl		97.83 83	97.37 101	99.21 52	99.18 109	97.98 80	99.64 201	99.27 27	91.43 257	97.88 160	98.99 171	95.84 42	99.84 128	98.82 93	95.32 237	99.79 103

DCV-MVSNet		97.83 83	97.37 101	99.21 52	99.18 109	97.98 80	99.64 201	99.27 27	91.43 257	97.88 160	98.99 171	95.84 42	99.84 128	98.82 93	95.32 237	99.79 103

DP-MVS Recon		98.41 48	98.02 63	99.56 25	99.97 3	98.70 48	99.92 90	98.44 138	92.06 237	98.40 139	99.84 44	95.68 44	100.00 1	98.19 129	99.71 88	99.97 61

旧先验1					99.76 66	97.52 100		98.64 82			99.85 33	95.63 45			99.94 55	99.99 23

SMA-MVS		98.76 26	98.48 32	99.62 20	99.87 51	98.87 33	99.86 130	98.38 174	93.19 187	99.77 33	99.94 4	95.54 46	100.00 1	99.74 37	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		96.74 147	96.26 148	98.16 143	97.36 255	96.48 144	99.96 44	98.29 193	91.93 240	95.77 218	98.07 245	95.54 46	98.29 256	90.55 290	98.89 145	99.70 116

APDe-MVS		99.06 11	98.91 14	99.51 29	99.94 13	98.76 45	99.91 98	98.39 170	97.20 47	99.46 73	99.85 33	95.53 48	99.79 135	99.86 22	100.00 1	99.99 23
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
testing3-2		97.72 97	97.43 99	98.60 110	98.55 165	97.11 121	100.00 1	99.23 29	93.78 169	97.90 157	98.73 202	95.50 49	99.69 154	98.53 113	94.63 244	98.99 220

testing11		97.48 106	97.27 106	98.10 148	98.36 182	96.02 166	99.92 90	98.45 133	93.45 180	98.15 151	98.70 205	95.48 50	99.22 184	97.85 149	95.05 241	99.07 215

PLC	95.54 3	97.93 75	97.89 75	98.05 152	99.82 58	94.77 215	99.92 90	98.46 132	93.93 162	97.20 179	99.27 148	95.44 51	99.97 57	97.41 163	99.51 109	99.41 177
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
HPM-MVS++		99.07 10	98.88 16	99.63 17	99.90 42	99.02 25	99.95 63	98.56 103	97.56 33	99.44 75	99.85 33	95.38 52	100.00 1	99.31 63	99.99 21	99.87 92

PHI-MVS		98.41 48	98.21 48	99.03 77	99.86 53	97.10 122	99.98 17	98.80 66	90.78 278	99.62 55	99.78 62	95.30 53	100.00 1	99.80 26	99.93 61	99.99 23

myMVS_eth3d28		97.86 79	97.59 91	98.68 102	98.50 172	97.26 112	99.92 90	98.55 109	93.79 168	98.26 146	98.75 200	95.20 54	99.48 174	98.93 84	96.40 209	99.29 195

test-mter		96.39 162	95.93 165	97.78 167	97.02 269	95.44 188	99.96 44	98.21 204	91.81 245	95.55 220	96.38 298	95.17 55	98.27 260	90.42 293	98.83 149	99.64 127

patchmatchnet-post											91.70 397	95.12 56	97.95 280

MDTV_nov1_ep13			95.69 173		97.90 214	94.15 231	95.98 398	98.44 138	93.12 192	97.98 154	95.74 317	95.10 57	98.58 227	90.02 299	96.92 200

IB-MVS	92.85 6	94.99 203	93.94 222	98.16 143	97.72 230	95.69 180	99.99 5	98.81 62	94.28 145	92.70 257	96.90 281	95.08 58	99.17 191	96.07 189	73.88 396	99.60 140
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 31	98.57 56		98.52 118	92.34 229	99.31 87	99.83 46	95.06 59	99.80 133	99.70 42	99.97 42

CDS-MVSNet		96.34 164	96.07 153	97.13 204	97.37 254	94.96 207	99.53 220	97.91 239	91.55 251	95.37 224	98.32 236	95.05 60	97.13 316	93.80 238	95.75 228	99.30 193
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Patchmatch-test		92.65 269	91.50 279	96.10 235	96.85 280	90.49 319	91.50 417	97.19 313	82.76 389	90.23 280	95.59 324	95.02 61	98.00 276	77.41 393	96.98 199	99.82 98

CostFormer		96.10 172	95.88 168	96.78 214	97.03 268	92.55 273	97.08 378	97.83 247	90.04 294	98.72 122	94.89 361	95.01 62	98.29 256	96.54 184	95.77 226	99.50 166

TSAR-MVS + GP.		98.60 33	98.51 31	98.86 91	99.73 73	96.63 138	99.97 35	97.92 238	98.07 15	98.76 120	99.55 122	95.00 63	99.94 85	99.91 16	97.68 181	99.99 23

CDPH-MVS		98.65 31	98.36 41	99.49 32	99.94 13	98.73 46	99.87 119	98.33 185	93.97 159	99.76 34	99.87 27	94.99 64	99.75 144	98.55 110	100.00 1	99.98 51

原ACMM1				98.96 86	99.73 73	96.99 126		98.51 121	94.06 155	99.62 55	99.85 33	94.97 65	99.96 68	95.11 202	99.95 50	99.92 85

TSAR-MVS + MP.		98.93 17	98.77 19	99.41 38	99.74 70	98.67 49	99.77 160	98.38 174	96.73 65	99.88 8	99.74 82	94.89 66	99.59 162	99.80 26	99.98 32	99.97 61
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
testing99		97.17 122	96.91 120	97.95 155	98.35 184	95.70 178	99.91 98	98.43 146	92.94 196	97.36 174	98.72 203	94.83 67	99.21 185	97.00 173	94.64 243	98.95 221

testing91		97.16 123	96.90 121	97.97 154	98.35 184	95.67 181	99.91 98	98.42 158	92.91 198	97.33 175	98.72 203	94.81 68	99.21 185	96.98 175	94.63 244	99.03 217

test12				99.43 35	99.74 70	98.56 57		98.40 167		99.65 48		94.76 69	99.75 144		99.98 32	99.99 23

mamv4		95.24 197	96.90 121	90.25 369	98.65 158	72.11 416	98.28 348	97.64 261	89.99 295	95.93 213	98.25 239	94.74 70	99.11 194	99.01 81	99.64 92	99.53 159

fmvsm_l_conf0.5_n_a		99.00 15	98.91 14	99.28 47	99.21 107	97.91 85	99.98 17	98.85 57	98.25 5	99.92 2	99.75 75	94.72 71	99.97 57	99.87 20	99.64 92	99.95 75

sam_mvs1												94.72 71				99.59 141

SF-MVS		98.67 30	98.40 35	99.50 30	99.77 65	98.67 49	99.90 104	98.21 204	93.53 176	99.81 20	99.89 22	94.70 73	99.86 119	99.84 23	99.93 61	99.96 68

reproduce-ours		98.78 24	98.67 21	99.09 72	99.70 78	97.30 110	99.74 172	98.25 198	97.10 49	99.10 99	99.90 18	94.59 74	99.99 36	99.77 31	99.91 67	99.99 23

our_new_method		98.78 24	98.67 21	99.09 72	99.70 78	97.30 110	99.74 172	98.25 198	97.10 49	99.10 99	99.90 18	94.59 74	99.99 36	99.77 31	99.91 67	99.99 23

SD-MVS		98.92 18	98.70 20	99.56 25	99.70 78	98.73 46	99.94 80	98.34 184	96.38 78	99.81 20	99.76 67	94.59 74	99.98 47	99.84 23	99.96 46	99.97 61
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 37		99.87 51		99.91 98	98.33 185	93.22 186	99.78 32	99.89 22	94.57 77	99.85 120	99.84 23	99.97 42

reproduce_model		98.75 27	98.66 23	99.03 77	99.71 76	97.10 122	99.73 179	98.23 202	97.02 54	99.18 96	99.90 18	94.54 78	99.99 36	99.77 31	99.90 69	99.99 23

test_post											63.35 433	94.43 79	98.13 268

EPMVS		96.53 156	96.01 155	98.09 149	98.43 177	96.12 165	96.36 389	99.43 20	93.53 176	97.64 166	95.04 354	94.41 80	98.38 247	91.13 276	98.11 172	99.75 109

新几何1				99.42 37	99.75 69	98.27 65		98.63 88	92.69 210	99.55 64	99.82 49	94.40 81	100.00 1	91.21 274	99.94 55	99.99 23

MDTV_nov1_ep13_2view						96.26 154	96.11 395		91.89 241	98.06 152		94.40 81		94.30 226		99.67 121

PAPM_NR		98.12 68	97.93 72	98.70 101	99.94 13	96.13 163	99.82 148	98.43 146	94.56 127	97.52 168	99.70 93	94.40 81	99.98 47	97.00 173	99.98 32	99.99 23

dcpmvs_2		97.42 111	98.09 58	95.42 252	99.58 89	87.24 364	99.23 265	96.95 342	94.28 145	98.93 109	99.73 84	94.39 84	99.16 193	99.89 18	99.82 81	99.86 94

miper_enhance_ethall		94.36 227	93.98 220	95.49 248	98.68 153	95.24 198	99.73 179	97.29 306	93.28 185	89.86 288	95.97 313	94.37 85	97.05 322	92.20 262	84.45 328	94.19 314

XVS		98.70 29	98.55 28	99.15 63	99.94 13	97.50 102	99.94 80	98.42 158	96.22 84	99.41 79	99.78 62	94.34 86	99.96 68	98.92 86	99.95 50	99.99 23

X-MVStestdata		93.83 235	92.06 268	99.15 63	99.94 13	97.50 102	99.94 80	98.42 158	96.22 84	99.41 79	41.37 437	94.34 86	99.96 68	98.92 86	99.95 50	99.99 23

balanced_conf03		98.27 58	97.99 64	99.11 70	98.64 159	98.43 62	99.47 231	97.79 249	94.56 127	99.74 38	98.35 233	94.33 88	99.25 182	99.12 70	99.96 46	99.64 127

CP-MVS		98.45 43	98.32 43	98.87 90	99.96 8	96.62 139	99.97 35	98.39 170	94.43 134	98.90 110	99.87 27	94.30 89	100.00 1	99.04 76	99.99 21	99.99 23

MVSMamba_PlusPlus		97.83 83	97.45 96	98.99 82	98.60 161	98.15 66	99.58 210	97.74 253	90.34 287	99.26 92	98.32 236	94.29 90	99.23 183	99.03 79	99.89 70	99.58 147

sam_mvs												94.25 91

Patchmatch-RL test		86.90 352	85.98 356	89.67 374	84.45 417	75.59 412	89.71 423	92.43 421	86.89 348	77.83 401	90.94 400	94.22 92	93.63 403	87.75 323	69.61 404	99.79 103

HFP-MVS		98.56 35	98.37 39	99.14 65	99.96 8	97.43 106	99.95 63	98.61 90	94.77 119	99.31 87	99.85 33	94.22 92	100.00 1	98.70 101	99.98 32	99.98 51

fmvsm_l_conf0.5_n		98.94 16	98.84 17	99.25 48	99.17 111	97.81 88	99.98 17	98.86 54	98.25 5	99.90 3	99.76 67	94.21 94	99.97 57	99.87 20	99.52 106	99.98 51

PatchmatchNet		95.94 177	95.45 179	97.39 195	97.83 219	94.41 222	96.05 396	98.40 167	92.86 199	97.09 182	95.28 346	94.21 94	98.07 273	89.26 306	98.11 172	99.70 116
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
DeepPCF-MVS	95.94 2	97.71 98	98.98 12	93.92 311	99.63 83	81.76 399	99.96 44	98.56 103	99.47 1	99.19 95	99.99 1	94.16 96	100.00 1	99.92 13	99.93 61	100.00 1

APD-MVS		98.62 32	98.35 42	99.41 38	99.90 42	98.51 59	99.87 119	98.36 178	94.08 152	99.74 38	99.73 84	94.08 97	99.74 146	99.42 59	99.99 21	99.99 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
region2R		98.54 36	98.37 39	99.05 75	99.96 8	97.18 116	99.96 44	98.55 109	94.87 117	99.45 74	99.85 33	94.07 98	100.00 1	98.67 103	100.00 1	99.98 51

PAPR		98.52 38	98.16 53	99.58 24	99.97 3	98.77 42	99.95 63	98.43 146	95.35 104	98.03 153	99.75 75	94.03 99	99.98 47	98.11 134	99.83 77	99.99 23

MG-MVS		98.91 19	98.65 24	99.68 16	99.94 13	99.07 24	99.64 201	99.44 19	97.33 40	99.00 106	99.72 87	94.03 99	99.98 47	98.73 100	100.00 1	100.00 1

MVS_111021_HR		98.72 28	98.62 26	99.01 81	99.36 101	97.18 116	99.93 87	99.90 1	96.81 63	98.67 124	99.77 65	93.92 101	99.89 108	99.27 65	99.94 55	99.96 68

tpmrst		96.27 170	95.98 158	97.13 204	97.96 211	93.15 256	96.34 390	98.17 209	92.07 235	98.71 123	95.12 351	93.91 102	98.73 217	94.91 210	96.62 203	99.50 166

test-LLR		96.47 157	96.04 154	97.78 167	97.02 269	95.44 188	99.96 44	98.21 204	94.07 153	95.55 220	96.38 298	93.90 103	98.27 260	90.42 293	98.83 149	99.64 127

test0.0.03 1		93.86 234	93.61 227	94.64 278	95.02 332	92.18 280	99.93 87	98.58 96	94.07 153	87.96 331	98.50 223	93.90 103	94.96 388	81.33 374	93.17 265	96.78 273

ETVMVS		97.03 131	96.64 135	98.20 142	98.67 154	97.12 120	99.89 113	98.57 98	91.10 268	98.17 150	98.59 215	93.86 105	98.19 265	95.64 197	95.24 239	99.28 197

test222					99.55 90	97.41 108	99.34 250	98.55 109	91.86 242	99.27 91	99.83 46	93.84 106			99.95 50	99.99 23

dp		95.05 201	94.43 207	96.91 210	97.99 209	92.73 267	96.29 392	97.98 230	89.70 299	95.93 213	94.67 367	93.83 107	98.45 236	86.91 338	96.53 205	99.54 155

ACMMPR		98.50 39	98.32 43	99.05 75	99.96 8	97.18 116	99.95 63	98.60 92	94.77 119	99.31 87	99.84 44	93.73 108	100.00 1	98.70 101	99.98 32	99.98 51

EPNet		98.49 40	98.40 35	98.77 97	99.62 84	96.80 134	99.90 104	99.51 16	97.60 30	99.20 93	99.36 142	93.71 109	99.91 101	97.99 141	98.71 153	99.61 138
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
alignmvs		97.81 87	97.33 103	99.25 48	98.77 149	98.66 51	99.99 5	98.44 138	94.40 138	98.41 137	99.47 128	93.65 110	99.42 178	98.57 109	94.26 252	99.67 121

testdata				98.42 131	99.47 96	95.33 194		98.56 103	93.78 169	99.79 31	99.85 33	93.64 111	99.94 85	94.97 206	99.94 55	100.00 1

EI-MVSNet-Vis-set		98.27 58	98.11 57	98.75 98	99.83 57	96.59 142	99.40 239	98.51 121	95.29 106	98.51 132	99.76 67	93.60 112	99.71 150	98.53 113	99.52 106	99.95 75

UWE-MVS-28		95.95 176	96.49 141	94.34 296	98.51 170	89.99 330	99.39 243	98.57 98	93.14 190	97.33 175	98.31 238	93.44 113	94.68 393	93.69 244	95.98 218	98.34 246

mPP-MVS		98.39 51	98.20 49	98.97 85	99.97 3	96.92 129	99.95 63	98.38 174	95.04 110	98.61 128	99.80 54	93.39 114	100.00 1	98.64 106	100.00 1	99.98 51

testing222		97.08 130	96.75 130	98.06 151	98.56 162	96.82 132	99.85 133	98.61 90	92.53 221	98.84 112	98.84 197	93.36 115	98.30 255	95.84 194	94.30 251	99.05 216

SR-MVS		98.46 42	98.30 46	98.93 88	99.88 49	97.04 124	99.84 138	98.35 180	94.92 114	99.32 86	99.80 54	93.35 116	99.78 137	99.30 64	99.95 50	99.96 68

WTY-MVS		98.10 69	97.60 89	99.60 22	98.92 135	99.28 17	99.89 113	99.52 14	95.58 98	98.24 148	99.39 139	93.33 117	99.74 146	97.98 143	95.58 231	99.78 106

tpm2		95.47 191	95.18 189	96.35 229	96.91 275	91.70 295	96.96 381	97.93 235	88.04 331	98.44 135	95.40 335	93.32 118	97.97 277	94.00 230	95.61 230	99.38 179

HY-MVS	92.50 7	97.79 90	97.17 112	99.63 17	98.98 127	99.32 9	97.49 368	99.52 14	95.69 95	98.32 142	97.41 264	93.32 118	99.77 140	98.08 137	95.75 228	99.81 100

EI-MVSNet-UG-set		98.14 67	97.99 64	98.60 110	99.80 61	96.27 153	99.36 249	98.50 127	95.21 108	98.30 143	99.75 75	93.29 120	99.73 149	98.37 122	99.30 128	99.81 100

SR-MVS-dyc-post		98.31 55	98.17 52	98.71 100	99.79 62	96.37 151	99.76 165	98.31 189	94.43 134	99.40 81	99.75 75	93.28 121	99.78 137	98.90 89	99.92 64	99.97 61

baseline1		95.78 181	94.86 199	98.54 119	98.47 175	98.07 74	99.06 281	97.99 228	92.68 211	94.13 240	98.62 214	93.28 121	98.69 222	93.79 239	85.76 316	98.84 227

MVS_0304		99.06 11	98.84 17	99.72 13	99.76 66	99.21 21	99.99 5	99.34 25	98.70 2	99.44 75	99.75 75	93.24 123	99.99 36	99.94 11	99.41 121	99.95 75

PGM-MVS		98.34 53	98.13 55	98.99 82	99.92 31	97.00 125	99.75 169	99.50 17	93.90 165	99.37 84	99.76 67	93.24 123	100.00 1	97.75 158	99.96 46	99.98 51

test_post1							95.78 401				59.23 436	93.20 125	97.74 289	91.06 278

CSCG		97.10 125	97.04 116	97.27 202	99.89 45	91.92 286	99.90 104	99.07 35	88.67 320	95.26 226	99.82 49	93.17 126	99.98 47	98.15 132	99.47 114	99.90 88

DeepC-MVS_fast	96.59 1	98.81 23	98.54 29	99.62 20	99.90 42	98.85 35	99.24 264	98.47 130	98.14 13	99.08 101	99.91 14	93.09 127	100.00 1	99.04 76	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 55	98.03 62	99.17 58	99.88 49	97.59 97	99.94 80	98.44 138	94.31 142	98.50 133	99.82 49	93.06 128	99.99 36	98.30 126	99.99 21	99.93 80

testing3		93.92 233	94.23 213	92.99 338	97.54 243	90.23 324	99.99 5	99.16 31	90.57 281	91.33 271	98.63 213	92.99 129	92.52 411	82.46 367	95.39 235	96.22 281

GST-MVS		98.27 58	97.97 66	99.17 58	99.92 31	97.57 98	99.93 87	98.39 170	94.04 157	98.80 115	99.74 82	92.98 130	100.00 1	98.16 131	99.76 85	99.93 80

RE-MVS-def			98.13 55		99.79 62	96.37 151	99.76 165	98.31 189	94.43 134	99.40 81	99.75 75	92.95 131		98.90 89	99.92 64	99.97 61

CS-MVS		97.79 90	97.91 73	97.43 191	99.10 115	94.42 221	99.99 5	97.10 324	95.07 109	99.68 45	99.75 75	92.95 131	98.34 251	98.38 120	99.14 135	99.54 155

ACMMP_NAP		98.49 40	98.14 54	99.54 27	99.66 82	98.62 55	99.85 133	98.37 177	94.68 124	99.53 67	99.83 46	92.87 133	100.00 1	98.66 105	99.84 76	99.99 23

APD-MVS_3200maxsize		98.25 63	98.08 59	98.78 95	99.81 60	96.60 140	99.82 148	98.30 192	93.95 161	99.37 84	99.77 65	92.84 134	99.76 143	98.95 82	99.92 64	99.97 61

JIA-IIPM		91.76 289	90.70 290	94.94 267	96.11 298	87.51 361	93.16 411	98.13 219	75.79 410	97.58 167	77.68 425	92.84 134	97.97 277	88.47 315	96.54 204	99.33 189

Test By Simon												92.82 136

MTAPA		98.29 57	97.96 69	99.30 46	99.85 54	97.93 84	99.39 243	98.28 194	95.76 93	97.18 181	99.88 24	92.74 137	100.00 1	98.67 103	99.88 73	99.99 23

EPNet_dtu		95.71 184	95.39 181	96.66 219	98.92 135	93.41 252	99.57 213	98.90 48	96.19 86	97.52 168	98.56 220	92.65 138	97.36 300	77.89 391	98.33 161	99.20 203
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsm_n_1920		98.44 44	98.61 27	97.92 159	99.27 106	95.18 202	100.00 1	98.90 48	98.05 16	99.80 22	99.73 84	92.64 139	99.99 36	99.58 50	99.51 109	98.59 239

MP-MVS-pluss		98.07 71	97.64 87	99.38 43	99.74 70	98.41 63	99.74 172	98.18 208	93.35 181	96.45 200	99.85 33	92.64 139	99.97 57	98.91 88	99.89 70	99.77 107
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
FE-MVS		95.70 186	95.01 196	97.79 166	98.21 194	94.57 217	95.03 403	98.69 73	88.90 314	97.50 170	96.19 305	92.60 141	99.49 173	89.99 300	97.94 178	99.31 191

DELS-MVS		98.54 36	98.22 47	99.50 30	99.15 113	98.65 53	100.00 1	98.58 96	97.70 28	98.21 149	99.24 153	92.58 142	99.94 85	98.63 108	99.94 55	99.92 85
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 76	97.80 79	98.25 140	98.14 201	96.48 144	99.98 17	97.63 262	95.61 97	99.29 90	99.46 130	92.55 143	98.82 209	99.02 80	98.54 156	99.46 170

test2506		97.53 104	97.19 110	98.58 114	98.66 156	96.90 130	98.81 314	99.77 5	94.93 112	97.95 155	98.96 177	92.51 144	99.20 188	94.93 207	98.15 169	99.64 127

KD-MVS_2432*1600		88.00 348	86.10 352	93.70 320	96.91 275	94.04 233	97.17 375	97.12 322	84.93 370	81.96 380	92.41 392	92.48 145	94.51 395	79.23 383	52.68 427	92.56 378

miper_refine_blended		88.00 348	86.10 352	93.70 320	96.91 275	94.04 233	97.17 375	97.12 322	84.93 370	81.96 380	92.41 392	92.48 145	94.51 395	79.23 383	52.68 427	92.56 378

myMVS_eth3d		94.46 222	94.76 202	93.55 324	97.68 233	90.97 305	99.71 186	98.35 180	90.79 276	92.10 263	98.67 207	92.46 147	93.09 407	87.13 331	95.95 221	96.59 276

EIA-MVS		97.53 104	97.46 95	97.76 171	98.04 207	94.84 211	99.98 17	97.61 268	94.41 137	97.90 157	99.59 115	92.40 148	98.87 206	98.04 138	99.13 136	99.59 141

F-COLMAP		96.93 137	96.95 119	96.87 212	99.71 76	91.74 291	99.85 133	97.95 233	93.11 193	95.72 219	99.16 159	92.35 149	99.94 85	95.32 200	99.35 126	98.92 222

API-MVS		97.86 79	97.66 85	98.47 125	99.52 92	95.41 191	99.47 231	98.87 53	91.68 248	98.84 112	99.85 33	92.34 150	99.99 36	98.44 118	99.96 46	100.00 1

CNLPA		97.76 92	97.38 100	98.92 89	99.53 91	96.84 131	99.87 119	98.14 218	93.78 169	96.55 198	99.69 96	92.28 151	99.98 47	97.13 169	99.44 118	99.93 80

TAMVS		95.85 179	95.58 177	96.65 220	97.07 266	93.50 249	99.17 270	97.82 248	91.39 261	95.02 228	98.01 246	92.20 152	97.30 306	93.75 241	95.83 225	99.14 208

1112_ss		96.01 175	95.20 188	98.42 131	97.80 221	96.41 147	99.65 197	96.66 364	92.71 208	92.88 255	99.40 137	92.16 153	99.30 180	91.92 267	93.66 259	99.55 151

Test_1112_low_res		95.72 182	94.83 200	98.42 131	97.79 222	96.41 147	99.65 197	96.65 365	92.70 209	92.86 256	96.13 308	92.15 154	99.30 180	91.88 268	93.64 260	99.55 151

HyFIR lowres test		96.66 152	96.43 144	97.36 198	99.05 118	93.91 238	99.70 190	99.80 3	90.54 282	96.26 206	98.08 244	92.15 154	98.23 263	96.84 181	95.46 232	99.93 80

SPE-MVS-test		97.88 77	97.94 71	97.70 174	99.28 105	95.20 201	99.98 17	97.15 319	95.53 100	99.62 55	99.79 58	92.08 156	98.38 247	98.75 99	99.28 129	99.52 161

MVS_111021_LR		98.42 47	98.38 37	98.53 121	99.39 99	95.79 172	99.87 119	99.86 2	96.70 66	98.78 116	99.79 58	92.03 157	99.90 103	99.17 69	99.86 75	99.88 90

TAPA-MVS	92.12 8	94.42 223	93.60 229	96.90 211	99.33 102	91.78 290	99.78 157	98.00 227	89.89 297	94.52 232	99.47 128	91.97 158	99.18 190	69.90 410	99.52 106	99.73 111
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PatchT		90.38 315	88.75 331	95.25 259	95.99 302	90.16 326	91.22 419	97.54 276	76.80 406	97.26 178	86.01 419	91.88 159	96.07 371	66.16 418	95.91 223	99.51 164

HPM-MVS		97.96 72	97.72 81	98.68 102	99.84 56	96.39 150	99.90 104	98.17 209	92.61 215	98.62 127	99.57 121	91.87 160	99.67 158	98.87 91	99.99 21	99.99 23
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MP-MVS		98.23 65	97.97 66	99.03 77	99.94 13	97.17 119	99.95 63	98.39 170	94.70 123	98.26 146	99.81 53	91.84 161	100.00 1	98.85 92	99.97 42	99.93 80
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		97.80 88	97.50 94	98.68 102	99.79 62	96.42 146	99.88 116	98.16 214	91.75 247	98.94 108	99.54 124	91.82 162	99.65 160	97.62 161	99.99 21	99.99 23

tpmvs		94.28 229	93.57 231	96.40 226	98.55 165	91.50 300	95.70 402	98.55 109	87.47 337	92.15 262	94.26 377	91.42 163	98.95 204	88.15 318	95.85 224	98.76 231

ACMMP		97.74 94	97.44 97	98.66 105	99.92 31	96.13 163	99.18 269	99.45 18	94.84 118	96.41 203	99.71 90	91.40 164	99.99 36	97.99 141	98.03 176	99.87 92
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)		96.32 165	95.98 158	97.35 199	97.93 213	94.82 212	99.47 231	98.15 217	91.83 243	95.09 227	99.11 160	91.37 165	97.47 298	93.47 246	97.43 185	99.74 110

sss		97.57 103	97.03 117	99.18 55	98.37 181	98.04 77	99.73 179	99.38 22	93.46 178	98.76 120	99.06 164	91.21 166	99.89 108	96.33 185	97.01 198	99.62 134

pcd_1.5k_mvsjas		7.60 407	10.13 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 440	91.20 167	0.00 440	0.00 439	0.00 438	0.00 436

PS-MVSNAJss		93.64 244	93.31 241	94.61 279	92.11 383	92.19 279	99.12 272	97.38 293	92.51 223	88.45 322	96.99 280	91.20 167	97.29 309	94.36 223	87.71 305	94.36 299

PS-MVSNAJ		98.44 44	98.20 49	99.16 61	98.80 147	98.92 29	99.54 219	98.17 209	97.34 38	99.85 14	99.85 33	91.20 167	99.89 108	99.41 60	99.67 90	98.69 236

CPTT-MVS		97.64 101	97.32 104	98.58 114	99.97 3	95.77 173	99.96 44	98.35 180	89.90 296	98.36 140	99.79 58	91.18 170	99.99 36	98.37 122	99.99 21	99.99 23

test_fmvsmconf_n		98.43 46	98.32 43	98.78 95	98.12 203	96.41 147	99.99 5	98.83 61	98.22 7	99.67 46	99.64 109	91.11 171	99.94 85	99.67 45	99.62 95	99.98 51

CR-MVSNet		93.45 250	92.62 254	95.94 239	96.29 293	92.66 269	92.01 415	96.23 376	92.62 214	96.94 186	93.31 386	91.04 172	96.03 372	79.23 383	95.96 219	99.13 209

Patchmtry		89.70 331	88.49 335	93.33 328	96.24 296	89.94 334	91.37 418	96.23 376	78.22 404	87.69 334	93.31 386	91.04 172	96.03 372	80.18 381	82.10 345	94.02 332

miper_ehance_all_eth		93.16 255	92.60 255	94.82 273	97.57 242	93.56 247	99.50 225	97.07 329	88.75 318	88.85 315	95.52 328	90.97 174	96.74 343	90.77 286	84.45 328	94.17 315

mvsany_test1		97.82 86	97.90 74	97.55 183	98.77 149	93.04 260	99.80 154	97.93 235	96.95 57	99.61 62	99.68 103	90.92 175	99.83 130	99.18 68	98.29 165	99.80 102

MVSFormer		96.94 135	96.60 137	97.95 155	97.28 262	97.70 93	99.55 217	97.27 308	91.17 264	99.43 77	99.54 124	90.92 175	96.89 334	94.67 218	99.62 95	99.25 200

lupinMVS		97.85 81	97.60 89	98.62 108	97.28 262	97.70 93	99.99 5	97.55 274	95.50 102	99.43 77	99.67 104	90.92 175	98.71 220	98.40 119	99.62 95	99.45 172

h-mvs33		94.92 204	94.36 209	96.59 221	98.85 144	91.29 302	98.93 299	98.94 42	95.90 89	98.77 117	98.42 231	90.89 178	99.77 140	97.80 151	70.76 402	98.72 235

hse-mvs2		94.38 224	94.08 217	95.31 257	98.27 190	90.02 329	99.29 259	98.56 103	95.90 89	98.77 117	98.00 247	90.89 178	98.26 262	97.80 151	69.20 408	97.64 261

xiu_mvs_v2_base		98.23 65	97.97 66	99.02 80	98.69 152	98.66 51	99.52 221	98.08 222	97.05 52	99.86 11	99.86 29	90.65 180	99.71 150	99.39 62	98.63 154	98.69 236

IS-MVSNet		96.29 168	95.90 167	97.45 189	98.13 202	94.80 213	99.08 276	97.61 268	92.02 239	95.54 222	98.96 177	90.64 181	98.08 271	93.73 242	97.41 188	99.47 169

kuosan		93.17 254	92.60 255	94.86 272	98.40 178	89.54 338	98.44 339	98.53 116	84.46 375	88.49 321	97.92 252	90.57 182	97.05 322	83.10 363	93.49 261	97.99 253

FA-MVS(test-final)		95.86 178	95.09 192	98.15 146	97.74 225	95.62 183	96.31 391	98.17 209	91.42 259	96.26 206	96.13 308	90.56 183	99.47 176	92.18 263	97.07 194	99.35 186

cl22		93.77 239	93.25 243	95.33 256	99.49 95	94.43 220	99.61 206	98.09 220	90.38 284	89.16 311	95.61 322	90.56 183	97.34 302	91.93 266	84.45 328	94.21 313

MM		98.83 21	98.53 30	99.76 10	99.59 85	99.33 8	99.99 5	99.76 6	98.39 4	99.39 83	99.80 54	90.49 185	99.96 68	99.89 18	99.43 119	99.98 51

tpm		93.70 243	93.41 238	94.58 282	95.36 327	87.41 362	97.01 379	96.90 349	90.85 274	96.72 194	94.14 378	90.40 186	96.84 338	90.75 287	88.54 295	99.51 164

dongtai		91.55 292	91.13 285	92.82 341	98.16 199	86.35 369	99.47 231	98.51 121	83.24 383	85.07 366	97.56 260	90.33 187	94.94 389	76.09 399	91.73 269	97.18 271

114514_t		97.41 112	96.83 126	99.14 65	99.51 94	97.83 86	99.89 113	98.27 196	88.48 324	99.06 103	99.66 106	90.30 188	99.64 161	96.32 186	99.97 42	99.96 68

ADS-MVSNet2		93.80 238	93.88 224	93.55 324	97.87 216	85.94 373	94.24 404	96.84 353	90.07 292	96.43 201	94.48 372	90.29 189	95.37 382	87.44 325	97.23 190	99.36 183

ADS-MVSNet		94.79 208	94.02 219	97.11 206	97.87 216	93.79 239	94.24 404	98.16 214	90.07 292	96.43 201	94.48 372	90.29 189	98.19 265	87.44 325	97.23 190	99.36 183

miper_lstm_enhance		91.81 283	91.39 282	93.06 337	97.34 256	89.18 342	99.38 245	96.79 358	86.70 350	87.47 339	95.22 348	90.00 191	95.86 376	88.26 316	81.37 351	94.15 321

c3_l		92.53 270	91.87 272	94.52 285	97.40 252	92.99 261	99.40 239	96.93 347	87.86 333	88.69 318	95.44 333	89.95 192	96.44 355	90.45 292	80.69 362	94.14 324

thres200		96.96 134	96.21 151	99.22 51	98.97 128	98.84 36	99.85 133	99.71 7	93.17 188	96.26 206	98.88 188	89.87 193	99.51 166	94.26 227	94.91 242	99.31 191

tpm cat1		93.51 247	92.52 261	96.47 222	97.77 223	91.47 301	96.13 394	98.06 223	80.98 396	92.91 254	93.78 381	89.66 194	98.87 206	87.03 334	96.39 210	99.09 212

test_fmvsmvis_n_1920		97.67 100	97.59 91	97.91 161	97.02 269	95.34 193	99.95 63	98.45 133	97.87 22	97.02 185	99.59 115	89.64 195	99.98 47	99.41 60	99.34 127	98.42 242

OMC-MVS		97.28 116	97.23 108	97.41 193	99.76 66	93.36 255	99.65 197	97.95 233	96.03 88	97.41 173	99.70 93	89.61 196	99.51 166	96.73 182	98.25 166	99.38 179

DIV-MVS_self_test		92.32 274	91.60 275	94.47 289	97.31 259	92.74 265	99.58 210	96.75 360	86.99 346	87.64 335	95.54 326	89.55 197	96.50 352	88.58 312	82.44 343	94.17 315

cl____		92.31 275	91.58 276	94.52 285	97.33 258	92.77 263	99.57 213	96.78 359	86.97 347	87.56 337	95.51 329	89.43 198	96.62 348	88.60 311	82.44 343	94.16 320

AUN-MVS		93.28 251	92.60 255	95.34 255	98.29 187	90.09 328	99.31 254	98.56 103	91.80 246	96.35 205	98.00 247	89.38 199	98.28 258	92.46 259	69.22 407	97.64 261

tfpn200view9		96.79 142	95.99 156	99.19 54	98.94 130	98.82 37	99.78 157	99.71 7	92.86 199	96.02 211	98.87 191	89.33 200	99.50 168	93.84 234	94.57 246	99.27 198

thres400		96.78 144	95.99 156	99.16 61	98.94 130	98.82 37	99.78 157	99.71 7	92.86 199	96.02 211	98.87 191	89.33 200	99.50 168	93.84 234	94.57 246	99.16 205

thres100view900		96.74 147	95.92 166	99.18 55	98.90 140	98.77 42	99.74 172	99.71 7	92.59 217	95.84 215	98.86 193	89.25 202	99.50 168	93.84 234	94.57 246	99.27 198

thres600view7		96.69 150	95.87 169	99.14 65	98.90 140	98.78 41	99.74 172	99.71 7	92.59 217	95.84 215	98.86 193	89.25 202	99.50 168	93.44 247	94.50 249	99.16 205

eth_miper_zixun_eth		92.41 273	91.93 270	93.84 315	97.28 262	90.68 314	98.83 312	96.97 341	88.57 323	89.19 310	95.73 319	89.24 204	96.69 346	89.97 301	81.55 349	94.15 321

EC-MVSNet		97.38 114	97.24 107	97.80 164	97.41 251	95.64 182	99.99 5	97.06 330	94.59 126	99.63 52	99.32 144	89.20 205	98.14 267	98.76 98	99.23 132	99.62 134

PVSNet_Blended_VisFu		97.27 117	96.81 127	98.66 105	98.81 146	96.67 137	99.92 90	98.64 82	94.51 129	96.38 204	98.49 224	89.05 206	99.88 114	97.10 171	98.34 160	99.43 175

PVSNet_BlendedMVS		96.05 173	95.82 170	96.72 217	99.59 85	96.99 126	99.95 63	99.10 32	94.06 155	98.27 144	95.80 315	89.00 207	99.95 77	99.12 70	87.53 308	93.24 368

PVSNet_Blended		97.94 74	97.64 87	98.83 92	99.59 85	96.99 126	100.00 1	99.10 32	95.38 103	98.27 144	99.08 162	89.00 207	99.95 77	99.12 70	99.25 130	99.57 149

fmvsm_s_conf0.5_n_6		98.27 58	97.96 69	99.23 50	97.66 236	98.11 72	99.98 17	98.64 82	97.85 23	99.87 9	99.72 87	88.86 209	99.93 94	99.64 47	99.36 125	99.63 133

IterMVS-LS		92.69 267	92.11 266	94.43 293	96.80 283	92.74 265	99.45 236	96.89 350	88.98 309	89.65 295	95.38 338	88.77 210	96.34 359	90.98 281	82.04 346	94.22 311
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		93.73 241	93.40 239	94.74 274	96.80 283	92.69 268	99.06 281	97.67 258	88.96 311	91.39 269	99.02 166	88.75 211	97.30 306	91.07 277	87.85 303	94.22 311

UA-Net		96.54 155	95.96 162	98.27 139	98.23 192	95.71 177	98.00 361	98.45 133	93.72 173	98.41 137	99.27 148	88.71 212	99.66 159	91.19 275	97.69 180	99.44 174

MAR-MVS		97.43 107	97.19 110	98.15 146	99.47 96	94.79 214	99.05 285	98.76 67	92.65 213	98.66 125	99.82 49	88.52 213	99.98 47	98.12 133	99.63 94	99.67 121
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		94.82 205	94.43 207	95.98 237	94.54 339	90.73 312	99.03 288	97.06 330	93.16 189	93.15 250	95.47 332	88.29 214	97.57 294	97.85 149	91.33 273	99.62 134

mvs_anonymous		95.65 188	95.03 195	97.53 185	98.19 196	95.74 175	99.33 251	97.49 283	90.87 273	90.47 279	97.10 273	88.23 215	97.16 313	95.92 192	97.66 182	99.68 119

MVS_Test		96.46 158	95.74 171	98.61 109	98.18 197	97.23 114	99.31 254	97.15 319	91.07 269	98.84 112	97.05 277	88.17 216	98.97 201	94.39 222	97.50 184	99.61 138

mvsmamba		96.94 135	96.73 131	97.55 183	97.99 209	94.37 225	99.62 204	97.70 255	93.13 191	98.42 136	97.92 252	88.02 217	98.75 216	98.78 96	99.01 142	99.52 161

fmvsm_l_conf0.5_n_3		98.41 48	98.08 59	99.39 40	99.12 114	98.29 64	99.98 17	98.64 82	98.14 13	99.86 11	99.76 67	87.99 218	99.97 57	99.72 40	99.54 104	99.91 87

CANet		98.27 58	97.82 78	99.63 17	99.72 75	99.10 23	99.98 17	98.51 121	97.00 55	98.52 130	99.71 90	87.80 219	99.95 77	99.75 35	99.38 123	99.83 97

jason		97.24 119	96.86 124	98.38 134	95.73 314	97.32 109	99.97 35	97.40 292	95.34 105	98.60 129	99.54 124	87.70 220	98.56 228	97.94 144	99.47 114	99.25 200
jason: jason.
test_fmvsmconf0.1_n		97.74 94	97.44 97	98.64 107	95.76 311	96.20 159	99.94 80	98.05 225	98.17 11	98.89 111	99.42 132	87.65 221	99.90 103	99.50 53	99.60 101	99.82 98

FIs		94.10 231	93.43 235	96.11 234	94.70 336	96.82 132	99.58 210	98.93 46	92.54 220	89.34 303	97.31 267	87.62 222	97.10 319	94.22 229	86.58 312	94.40 297

1314		96.84 140	95.96 162	99.48 34	96.74 287	98.52 58	98.31 346	98.86 54	95.82 91	89.91 286	98.98 173	87.49 223	99.96 68	97.80 151	99.73 87	99.96 68

LS3D		95.84 180	95.11 191	98.02 153	99.85 54	95.10 205	98.74 319	98.50 127	87.22 342	93.66 244	99.86 29	87.45 224	99.95 77	90.94 282	99.81 83	99.02 218

FC-MVSNet-test		93.81 237	93.15 244	95.80 244	94.30 344	96.20 159	99.42 238	98.89 50	92.33 230	89.03 313	97.27 269	87.39 225	96.83 340	93.20 249	86.48 313	94.36 299

fmvsm_s_conf0.5_n_8		98.38 52	98.05 61	99.35 44	99.20 108	98.12 71	99.98 17	98.81 62	98.22 7	99.80 22	99.71 90	87.37 226	99.97 57	99.91 16	99.48 113	99.97 61

fmvsm_s_conf0.5_n		97.80 88	97.85 77	97.67 175	99.06 117	94.41 222	99.98 17	98.97 41	97.34 38	99.63 52	99.69 96	87.27 227	99.97 57	99.62 48	99.06 140	98.62 238

RPMNet		89.76 330	87.28 347	97.19 203	96.29 293	92.66 269	92.01 415	98.31 189	70.19 421	96.94 186	85.87 420	87.25 228	99.78 137	62.69 422	95.96 219	99.13 209

UniMVSNet_NR-MVSNet		92.95 260	92.11 266	95.49 248	94.61 338	95.28 196	99.83 145	99.08 34	91.49 252	89.21 308	96.86 284	87.14 229	96.73 344	93.20 249	77.52 381	94.46 291

UniMVSNet (Re)		93.07 258	92.13 265	95.88 240	94.84 333	96.24 158	99.88 116	98.98 39	92.49 224	89.25 305	95.40 335	87.09 230	97.14 315	93.13 253	78.16 376	94.26 307

DP-MVS		94.54 217	93.42 236	97.91 161	99.46 98	94.04 233	98.93 299	97.48 284	81.15 395	90.04 283	99.55 122	87.02 231	99.95 77	88.97 308	98.11 172	99.73 111

fmvsm_s_conf0.5_n_a		97.73 96	97.72 81	97.77 169	98.63 160	94.26 228	99.96 44	98.92 47	97.18 48	99.75 35	99.69 96	87.00 232	99.97 57	99.46 56	98.89 145	99.08 214

PMMVS		96.76 145	96.76 129	96.76 215	98.28 189	92.10 281	99.91 98	97.98 230	94.12 150	99.53 67	99.39 139	86.93 233	98.73 217	96.95 178	97.73 179	99.45 172

sasdasda		97.09 127	96.32 146	99.39 40	98.93 132	98.95 27	99.72 183	97.35 296	94.45 130	97.88 160	99.42 132	86.71 234	99.52 164	98.48 115	93.97 256	99.72 113

canonicalmvs		97.09 127	96.32 146	99.39 40	98.93 132	98.95 27	99.72 183	97.35 296	94.45 130	97.88 160	99.42 132	86.71 234	99.52 164	98.48 115	93.97 256	99.72 113

fmvsm_s_conf0.5_n_4		97.75 93	97.86 76	97.42 192	99.01 120	94.69 216	99.97 35	98.76 67	97.91 21	99.87 9	99.76 67	86.70 236	99.93 94	99.67 45	99.12 138	97.64 261

MVS		96.60 153	95.56 178	99.72 13	96.85 280	99.22 20	98.31 346	98.94 42	91.57 250	90.90 275	99.61 114	86.66 237	99.96 68	97.36 164	99.88 73	99.99 23

Effi-MVS+		96.30 167	95.69 173	98.16 143	97.85 218	96.26 154	97.41 370	97.21 312	90.37 285	98.65 126	98.58 218	86.61 238	98.70 221	97.11 170	97.37 189	99.52 161

diffmvs		97.00 132	96.64 135	98.09 149	97.64 238	96.17 162	99.81 150	97.19 313	94.67 125	98.95 107	99.28 145	86.43 239	98.76 214	98.37 122	97.42 187	99.33 189
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		93.51 247	92.53 260	96.45 224	94.36 342	97.20 115	99.81 150	97.16 318	91.60 249	89.86 288	97.46 262	86.37 240	97.68 290	95.88 193	80.31 365	94.46 291

MGCFI-Net		97.00 132	96.22 150	99.34 45	98.86 143	98.80 39	99.67 195	97.30 303	94.31 142	97.77 164	99.41 136	86.36 241	99.50 168	98.38 120	93.90 258	99.72 113

VNet		97.21 121	96.57 139	99.13 69	98.97 128	97.82 87	99.03 288	99.21 30	94.31 142	99.18 96	98.88 188	86.26 242	99.89 108	98.93 84	94.32 250	99.69 118

fmvsm_s_conf0.5_n_7		97.70 99	97.74 80	97.59 182	98.44 176	95.16 204	99.97 35	98.65 79	97.95 20	99.62 55	99.78 62	86.09 243	99.94 85	99.69 43	99.50 111	97.66 260

AdaColmap		97.23 120	96.80 128	98.51 123	99.99 1	95.60 184	99.09 274	98.84 60	93.32 183	96.74 193	99.72 87	86.04 244	100.00 1	98.01 139	99.43 119	99.94 79

fmvsm_s_conf0.5_n_5		98.08 70	97.71 83	99.17 58	98.67 154	97.69 95	99.99 5	98.57 98	97.40 36	99.89 6	99.69 96	85.99 245	99.96 68	99.80 26	99.40 122	99.85 95

Effi-MVS+-dtu		94.53 219	95.30 185	92.22 348	97.77 223	82.54 392	99.59 208	97.06 330	94.92 114	95.29 225	95.37 339	85.81 246	97.89 283	94.80 213	97.07 194	96.23 280

CVMVSNet		94.68 214	94.94 198	93.89 314	96.80 283	86.92 367	99.06 281	98.98 39	94.45 130	94.23 239	99.02 166	85.60 247	95.31 384	90.91 283	95.39 235	99.43 175

xiu_mvs_v1_base_debu		97.43 107	97.06 113	98.55 116	97.74 225	98.14 68	99.31 254	97.86 244	96.43 75	99.62 55	99.69 96	85.56 248	99.68 155	99.05 73	98.31 162	97.83 255

xiu_mvs_v1_base		97.43 107	97.06 113	98.55 116	97.74 225	98.14 68	99.31 254	97.86 244	96.43 75	99.62 55	99.69 96	85.56 248	99.68 155	99.05 73	98.31 162	97.83 255

xiu_mvs_v1_base_debi		97.43 107	97.06 113	98.55 116	97.74 225	98.14 68	99.31 254	97.86 244	96.43 75	99.62 55	99.69 96	85.56 248	99.68 155	99.05 73	98.31 162	97.83 255

casdiffmvs_mvg		96.43 159	95.94 164	97.89 163	97.44 249	95.47 187	99.86 130	97.29 306	93.35 181	96.03 210	99.19 156	85.39 251	98.72 219	97.89 148	97.04 196	99.49 168
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		96.43 159	95.98 158	97.76 171	97.34 256	95.17 203	99.51 223	97.17 316	93.92 163	96.90 188	99.28 145	85.37 252	98.64 225	97.50 162	96.86 202	99.46 170

PCF-MVS	94.20 5	95.18 198	94.10 216	98.43 129	98.55 165	95.99 167	97.91 363	97.31 302	90.35 286	89.48 300	99.22 154	85.19 253	99.89 108	90.40 295	98.47 158	99.41 177
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs		96.42 161	95.97 161	97.77 169	97.30 260	94.98 206	99.84 138	97.09 327	93.75 172	96.58 197	99.26 151	85.07 254	98.78 212	97.77 156	97.04 196	99.54 155
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		92.76 264	92.59 259	93.27 330	95.13 328	89.54 338	99.69 191	99.38 22	92.26 231	87.59 336	94.61 369	85.05 255	97.79 286	91.59 271	88.01 301	92.47 381

fmvsm_s_conf0.1_n		97.30 115	97.21 109	97.60 181	97.38 253	94.40 224	99.90 104	98.64 82	96.47 74	99.51 71	99.65 108	84.99 256	99.93 94	99.22 67	99.09 139	98.46 240

fmvsm_s_conf0.1_n_a		97.09 127	96.90 121	97.63 179	95.65 321	94.21 230	99.83 145	98.50 127	96.27 83	99.65 48	99.64 109	84.72 257	99.93 94	99.04 76	98.84 148	98.74 233

BH-w/o		95.71 184	95.38 182	96.68 218	98.49 174	92.28 277	99.84 138	97.50 282	92.12 234	92.06 265	98.79 198	84.69 258	98.67 224	95.29 201	99.66 91	99.09 212

Fast-Effi-MVS+		95.02 202	94.19 214	97.52 186	97.88 215	94.55 218	99.97 35	97.08 328	88.85 316	94.47 234	97.96 251	84.59 259	98.41 239	89.84 302	97.10 193	99.59 141

PVSNet	91.05 13	97.13 124	96.69 134	98.45 127	99.52 92	95.81 171	99.95 63	99.65 12	94.73 121	99.04 104	99.21 155	84.48 260	99.95 77	94.92 208	98.74 152	99.58 147

WR-MVS_H		91.30 293	90.35 297	94.15 300	94.17 347	92.62 272	99.17 270	98.94 42	88.87 315	86.48 353	94.46 374	84.36 261	96.61 349	88.19 317	78.51 374	93.21 369

CHOSEN 1792x2688		96.81 141	96.53 140	97.64 177	98.91 139	93.07 257	99.65 197	99.80 3	95.64 96	95.39 223	98.86 193	84.35 262	99.90 103	96.98 175	99.16 134	99.95 75

fmvsm_s_conf0.5_n_3		97.95 73	97.66 85	98.81 93	98.99 125	98.07 74	99.98 17	98.81 62	98.18 10	99.89 6	99.70 93	84.15 263	99.97 57	99.76 34	99.50 111	98.39 243

our_test_3		90.39 314	89.48 319	93.12 334	92.40 379	89.57 337	99.33 251	96.35 375	87.84 334	85.30 363	94.99 358	84.14 264	96.09 370	80.38 378	84.56 327	93.71 358

MSDG		94.37 225	93.36 240	97.40 194	98.88 142	93.95 237	99.37 247	97.38 293	85.75 362	90.80 276	99.17 158	84.11 265	99.88 114	86.35 339	98.43 159	98.36 245

pmmvs4		92.10 279	91.07 287	95.18 260	92.82 374	94.96 207	99.48 230	96.83 354	87.45 338	88.66 319	96.56 296	83.78 266	96.83 340	89.29 305	84.77 326	93.75 353

BH-untuned		95.18 198	94.83 200	96.22 232	98.36 182	91.22 303	99.80 154	97.32 301	90.91 272	91.08 272	98.67 207	83.51 267	98.54 230	94.23 228	99.61 99	98.92 222

LCM-MVSNet-Re		92.31 275	92.60 255	91.43 357	97.53 244	79.27 409	99.02 290	91.83 424	92.07 235	80.31 389	94.38 375	83.50 268	95.48 380	97.22 168	97.58 183	99.54 155

cdsmvs_eth3d_5k		23.43 404	31.24 407	0.00 421	0.00 444	0.00 446	0.00 432	98.09 220	0.00 439	0.00 440	99.67 104	83.37 269	0.00 440	0.00 439	0.00 438	0.00 436

DeepC-MVS	94.51 4	96.92 138	96.40 145	98.45 127	99.16 112	95.90 169	99.66 196	98.06 223	96.37 81	94.37 235	99.49 127	83.29 270	99.90 103	97.63 160	99.61 99	99.55 151
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NR-MVSNet		91.56 291	90.22 301	95.60 246	94.05 348	95.76 174	98.25 349	98.70 72	91.16 266	80.78 388	96.64 292	83.23 271	96.57 350	91.41 272	77.73 380	94.46 291

MVStest1		85.03 363	82.76 372	91.83 353	92.95 371	89.16 343	98.57 331	94.82 403	71.68 419	68.54 419	95.11 352	83.17 272	95.66 378	74.69 402	65.32 416	90.65 398

3Dnovator+	91.53 11	96.31 166	95.24 186	99.52 28	96.88 279	98.64 54	99.72 183	98.24 200	95.27 107	88.42 327	98.98 173	82.76 273	99.94 85	97.10 171	99.83 77	99.96 68

QAPM		95.40 193	94.17 215	99.10 71	96.92 274	97.71 91	99.40 239	98.68 75	89.31 302	88.94 314	98.89 187	82.48 274	99.96 68	93.12 254	99.83 77	99.62 134

PatchMatch-RL		96.04 174	95.40 180	97.95 155	99.59 85	95.22 200	99.52 221	99.07 35	93.96 160	96.49 199	98.35 233	82.28 275	99.82 132	90.15 298	99.22 133	98.81 229

GeoE		94.36 227	93.48 234	96.99 208	97.29 261	93.54 248	99.96 44	96.72 362	88.35 327	93.43 245	98.94 184	82.05 276	98.05 274	88.12 320	96.48 208	99.37 181

3Dnovator	91.47 12	96.28 169	95.34 183	99.08 74	96.82 282	97.47 105	99.45 236	98.81 62	95.52 101	89.39 301	99.00 170	81.97 277	99.95 77	97.27 166	99.83 77	99.84 96

v8		90.54 312	89.17 322	94.66 277	93.43 359	93.40 253	99.20 267	96.94 346	85.76 360	87.56 337	94.51 370	81.96 278	97.19 312	84.94 352	78.25 375	93.38 365

RRT-MVS		96.24 171	95.68 175	97.94 158	97.65 237	94.92 209	99.27 262	97.10 324	92.79 205	97.43 172	97.99 249	81.85 279	99.37 179	98.46 117	98.57 155	99.53 159

fmvsm_s_conf0.5_n_2		97.59 102	97.28 105	98.53 121	99.01 120	98.15 66	99.98 17	98.59 94	98.17 11	99.75 35	99.63 112	81.83 280	99.94 85	99.78 29	98.79 151	97.51 268

v148		90.70 307	89.63 312	93.92 311	92.97 369	90.97 305	99.75 169	96.89 350	87.51 336	88.27 328	95.01 355	81.67 281	97.04 325	87.40 327	77.17 386	93.75 353

DU-MVS		92.46 272	91.45 281	95.49 248	94.05 348	95.28 196	99.81 150	98.74 69	92.25 232	89.21 308	96.64 292	81.66 282	96.73 344	93.20 249	77.52 381	94.46 291

Baseline_NR-MVSNet		90.33 317	89.51 317	92.81 342	92.84 372	89.95 332	99.77 160	93.94 414	84.69 374	89.04 312	95.66 321	81.66 282	96.52 351	90.99 280	76.98 387	91.97 387

FMVSNet3		92.69 267	91.58 276	95.99 236	98.29 187	97.42 107	99.26 263	97.62 265	89.80 298	89.68 292	95.32 341	81.62 284	96.27 362	87.01 335	85.65 317	94.29 306

Fast-Effi-MVS+-dtu		93.72 242	93.86 225	93.29 329	97.06 267	86.16 370	99.80 154	96.83 354	92.66 212	92.58 258	97.83 257	81.39 285	97.67 291	89.75 303	96.87 201	96.05 283

CANet_DTU		96.76 145	96.15 152	98.60 110	98.78 148	97.53 99	99.84 138	97.63 262	97.25 46	99.20 93	99.64 109	81.36 286	99.98 47	92.77 258	98.89 145	98.28 247

WB-MVSnew		92.90 261	92.77 252	93.26 331	96.95 273	93.63 245	99.71 186	98.16 214	91.49 252	94.28 237	98.14 242	81.33 287	96.48 353	79.47 382	95.46 232	89.68 408

V42		91.28 295	90.12 306	94.74 274	93.42 360	93.46 250	99.68 193	97.02 334	87.36 339	89.85 290	95.05 353	81.31 288	97.34 302	87.34 328	80.07 367	93.40 363

test_djsdf		92.83 263	92.29 264	94.47 289	91.90 386	92.46 274	99.55 217	97.27 308	91.17 264	89.96 284	96.07 311	81.10 289	96.89 334	94.67 218	88.91 285	94.05 331

ppachtmachnet_test		89.58 334	88.35 337	93.25 332	92.40 379	90.44 321	99.33 251	96.73 361	85.49 365	85.90 361	95.77 316	81.09 290	96.00 374	76.00 400	82.49 342	93.30 366

v1144		91.09 299	89.83 308	94.87 269	93.25 362	93.69 244	99.62 204	96.98 339	86.83 349	89.64 296	94.99 358	80.94 291	97.05 322	85.08 351	81.16 353	93.87 347

v10		90.25 320	88.82 329	94.57 283	93.53 357	93.43 251	99.08 276	96.87 352	85.00 369	87.34 343	94.51 370	80.93 292	97.02 329	82.85 365	79.23 370	93.26 367

fmvsm_s_conf0.1_n_2		97.25 118	96.85 125	98.43 129	98.08 204	98.08 73	99.92 90	97.76 252	98.05 16	99.65 48	99.58 118	80.88 293	99.93 94	99.59 49	98.17 167	97.29 269

EU-MVSNet		90.14 324	90.34 298	89.54 375	92.55 377	81.06 403	98.69 325	98.04 226	91.41 260	86.59 350	96.84 287	80.83 294	93.31 406	86.20 341	81.91 347	94.26 307

v2v482		91.30 293	90.07 307	95.01 264	93.13 363	93.79 239	99.77 160	97.02 334	88.05 330	89.25 305	95.37 339	80.73 295	97.15 314	87.28 329	80.04 368	94.09 328

WR-MVS		92.31 275	91.25 283	95.48 251	94.45 341	95.29 195	99.60 207	98.68 75	90.10 291	88.07 330	96.89 282	80.68 296	96.80 342	93.14 252	79.67 369	94.36 299

HQP2-MVS												80.65 297

HQP-MVS		94.61 216	94.50 206	94.92 268	95.78 307	91.85 287	99.87 119	97.89 240	96.82 60	93.37 246	98.65 210	80.65 297	98.39 243	97.92 145	89.60 276	94.53 286

XVG-OURS		94.82 205	94.74 203	95.06 263	98.00 208	89.19 340	99.08 276	97.55 274	94.10 151	94.71 230	99.62 113	80.51 299	99.74 146	96.04 190	93.06 268	96.25 278

v144192		90.79 306	89.52 316	94.59 281	93.11 366	92.77 263	99.56 215	96.99 337	86.38 353	89.82 291	94.95 360	80.50 300	97.10 319	83.98 357	80.41 363	93.90 344

HQP_MVS		94.49 221	94.36 209	94.87 269	95.71 317	91.74 291	99.84 138	97.87 242	96.38 78	93.01 251	98.59 215	80.47 301	98.37 249	97.79 154	89.55 279	94.52 288

plane_prior6					95.76 311	91.72 294						80.47 301

v7n		89.65 332	88.29 338	93.72 317	92.22 381	90.56 318	99.07 280	97.10 324	85.42 367	86.73 347	94.72 363	80.06 303	97.13 316	81.14 375	78.12 377	93.49 361

TranMVSNet+NR-MVSNet		91.68 290	90.61 293	94.87 269	93.69 355	93.98 236	99.69 191	98.65 79	91.03 270	88.44 323	96.83 288	80.05 304	96.18 365	90.26 297	76.89 389	94.45 296

FMVSNet5		88.32 344	87.47 346	90.88 360	96.90 278	88.39 354	97.28 372	95.68 388	82.60 390	84.67 368	92.40 394	79.83 305	91.16 416	76.39 398	81.51 350	93.09 370

test_fmvsmconf0.01_n		96.39 162	95.74 171	98.32 136	91.47 392	95.56 185	99.84 138	97.30 303	97.74 26	97.89 159	99.35 143	79.62 306	99.85 120	99.25 66	99.24 131	99.55 151

RPSCF		91.80 286	92.79 251	88.83 380	98.15 200	69.87 418	98.11 357	96.60 367	83.93 378	94.33 236	99.27 148	79.60 307	99.46 177	91.99 265	93.16 266	97.18 271

Vis-MVSNet		95.72 182	95.15 190	97.45 189	97.62 239	94.28 227	99.28 260	98.24 200	94.27 147	96.84 190	98.94 184	79.39 308	98.76 214	93.25 248	98.49 157	99.30 193
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dmvs_testset		83.79 372	86.07 354	76.94 402	92.14 382	48.60 437	96.75 384	90.27 427	89.48 300	78.65 396	98.55 222	79.25 309	86.65 425	66.85 416	82.69 339	95.57 284

v1192		90.62 311	89.25 321	94.72 276	93.13 363	93.07 257	99.50 225	97.02 334	86.33 354	89.56 299	95.01 355	79.22 310	97.09 321	82.34 369	81.16 353	94.01 334

CP-MVSNet		91.23 297	90.22 301	94.26 298	93.96 350	92.39 276	99.09 274	98.57 98	88.95 312	86.42 354	96.57 295	79.19 311	96.37 357	90.29 296	78.95 371	94.02 332

MDA-MVSNet_test_wron		85.51 359	83.32 367	92.10 349	90.96 396	88.58 351	99.20 267	96.52 370	79.70 401	57.12 427	92.69 390	79.11 312	93.86 401	77.10 395	77.46 383	93.86 348

Syy-MVS		90.00 326	90.63 292	88.11 387	97.68 233	74.66 414	99.71 186	98.35 180	90.79 276	92.10 263	98.67 207	79.10 313	93.09 407	63.35 421	95.95 221	96.59 276

YYNet1		85.50 360	83.33 366	92.00 350	90.89 397	88.38 355	99.22 266	96.55 369	79.60 402	57.26 426	92.72 389	79.09 314	93.78 402	77.25 394	77.37 384	93.84 349

XVG-OURS-SEG-HR		94.79 208	94.70 204	95.08 262	98.05 206	89.19 340	99.08 276	97.54 276	93.66 174	94.87 229	99.58 118	78.78 315	99.79 135	97.31 165	93.40 263	96.25 278

GA-MVS		93.83 235	92.84 248	96.80 213	95.73 314	93.57 246	99.88 116	97.24 311	92.57 219	92.92 253	96.66 290	78.73 316	97.67 291	87.75 323	94.06 255	99.17 204

dmvs_re		93.20 253	93.15 244	93.34 327	96.54 291	83.81 385	98.71 322	98.51 121	91.39 261	92.37 261	98.56 220	78.66 317	97.83 285	93.89 232	89.74 275	98.38 244

OpenMVS	90.15 15	94.77 210	93.59 230	98.33 135	96.07 299	97.48 104	99.56 215	98.57 98	90.46 283	86.51 351	98.95 182	78.57 318	99.94 85	93.86 233	99.74 86	97.57 266

v1921920		90.46 313	89.12 323	94.50 287	92.96 370	92.46 274	99.49 227	96.98 339	86.10 356	89.61 298	95.30 342	78.55 319	97.03 327	82.17 370	80.89 361	94.01 334

MVP-Stereo		90.93 301	90.45 296	92.37 347	91.25 395	88.76 345	98.05 360	96.17 378	87.27 341	84.04 370	95.30 342	78.46 320	97.27 311	83.78 359	99.70 89	91.09 392
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
anonymousdsp		91.79 288	90.92 288	94.41 294	90.76 398	92.93 262	98.93 299	97.17 316	89.08 304	87.46 340	95.30 342	78.43 321	96.92 332	92.38 260	88.73 290	93.39 364

v1240		90.20 321	88.79 330	94.44 291	93.05 368	92.27 278	99.38 245	96.92 348	85.89 358	89.36 302	94.87 362	77.89 322	97.03 327	80.66 377	81.08 356	94.01 334

CLD-MVS		94.06 232	93.90 223	94.55 284	96.02 301	90.69 313	99.98 17	97.72 254	96.62 71	91.05 274	98.85 196	77.21 323	98.47 232	98.11 134	89.51 281	94.48 290
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		96.59 154	96.23 149	97.65 176	98.22 193	94.23 229	99.99 5	97.25 310	97.77 25	99.58 63	99.08 162	77.10 324	99.97 57	97.64 159	99.45 117	98.74 233

N_pmnet		80.06 382	80.78 380	77.89 401	91.94 385	45.28 439	98.80 316	56.82 441	78.10 405	80.08 391	93.33 384	77.03 325	95.76 377	68.14 414	82.81 338	92.64 377

WB-MVS		76.28 386	77.28 388	73.29 406	81.18 423	54.68 431	97.87 364	94.19 410	81.30 394	69.43 417	90.70 402	77.02 326	82.06 429	35.71 434	68.11 411	83.13 420

COLMAP_ROB	90.47 14	92.18 278	91.49 280	94.25 299	99.00 124	88.04 358	98.42 343	96.70 363	82.30 391	88.43 325	99.01 168	76.97 327	99.85 120	86.11 343	96.50 206	94.86 285
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
cascas		94.64 215	93.61 227	97.74 173	97.82 220	96.26 154	99.96 44	97.78 251	85.76 360	94.00 241	97.54 261	76.95 328	99.21 185	97.23 167	95.43 234	97.76 259

BH-RMVSNet		95.18 198	94.31 212	97.80 164	98.17 198	95.23 199	99.76 165	97.53 278	92.52 222	94.27 238	99.25 152	76.84 329	98.80 210	90.89 284	99.54 104	99.35 186

PEN-MVS		90.19 322	89.06 325	93.57 323	93.06 367	90.90 309	99.06 281	98.47 130	88.11 329	85.91 360	96.30 302	76.67 330	95.94 375	87.07 332	76.91 388	93.89 345

CL-MVSNet_self_test		84.50 368	83.15 369	88.53 384	86.00 414	81.79 398	98.82 313	97.35 296	85.12 368	83.62 375	90.91 401	76.66 331	91.40 415	69.53 411	60.36 424	92.40 382

IterMVS		90.91 302	90.17 304	93.12 334	96.78 286	90.42 322	98.89 303	97.05 333	89.03 306	86.49 352	95.42 334	76.59 332	95.02 386	87.22 330	84.09 331	93.93 342
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SSC-MVS		75.42 387	76.40 390	72.49 410	80.68 425	53.62 432	97.42 369	94.06 412	80.42 398	68.75 418	90.14 404	76.54 333	81.66 430	33.25 435	66.34 415	82.19 421

IterMVS-SCA-FT		90.85 305	90.16 305	92.93 339	96.72 288	89.96 331	98.89 303	96.99 337	88.95 312	86.63 349	95.67 320	76.48 334	95.00 387	87.04 333	84.04 334	93.84 349

SCA		94.69 212	93.81 226	97.33 200	97.10 265	94.44 219	98.86 309	98.32 187	93.30 184	96.17 209	95.59 324	76.48 334	97.95 280	91.06 278	97.43 185	99.59 141

ab-mvs		94.69 212	93.42 236	98.51 123	98.07 205	96.26 154	96.49 387	98.68 75	90.31 288	94.54 231	97.00 279	76.30 336	99.71 150	95.98 191	93.38 264	99.56 150

DTE-MVSNet		89.40 336	88.24 339	92.88 340	92.66 376	89.95 332	99.10 273	98.22 203	87.29 340	85.12 365	96.22 304	76.27 337	95.30 385	83.56 361	75.74 393	93.41 362

ACMM	91.95 10	92.88 262	92.52 261	93.98 310	95.75 313	89.08 344	99.77 160	97.52 280	93.00 194	89.95 285	97.99 249	76.17 338	98.46 235	93.63 245	88.87 287	94.39 298
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DSMNet-mixed		88.28 345	88.24 339	88.42 385	89.64 406	75.38 413	98.06 359	89.86 428	85.59 364	88.20 329	92.14 396	76.15 339	91.95 414	78.46 389	96.05 216	97.92 254

VPA-MVSNet		92.70 266	91.55 278	96.16 233	95.09 329	96.20 159	98.88 305	99.00 37	91.02 271	91.82 266	95.29 345	76.05 340	97.96 279	95.62 198	81.19 352	94.30 305

SDMVSNet		94.80 207	93.96 221	97.33 200	98.92 135	95.42 190	99.59 208	98.99 38	92.41 226	92.55 259	97.85 255	75.81 341	98.93 205	97.90 147	91.62 271	97.64 261

TR-MVS		94.54 217	93.56 232	97.49 188	97.96 211	94.34 226	98.71 322	97.51 281	90.30 289	94.51 233	98.69 206	75.56 342	98.77 213	92.82 257	95.99 217	99.35 186

PS-CasMVS		90.63 310	89.51 317	93.99 309	93.83 352	91.70 295	98.98 292	98.52 118	88.48 324	86.15 358	96.53 297	75.46 343	96.31 361	88.83 309	78.86 373	93.95 340

TransMVSNet (Re)		87.25 351	85.28 358	93.16 333	93.56 356	91.03 304	98.54 334	94.05 413	83.69 381	81.09 386	96.16 306	75.32 344	96.40 356	76.69 397	68.41 409	92.06 385

LPG-MVS_test		92.96 259	92.71 253	93.71 318	95.43 325	88.67 348	99.75 169	97.62 265	92.81 202	90.05 281	98.49 224	75.24 345	98.40 241	95.84 194	89.12 283	94.07 329

LGP-MVS_train				93.71 318	95.43 325	88.67 348		97.62 265	92.81 202	90.05 281	98.49 224	75.24 345	98.40 241	95.84 194	89.12 283	94.07 329

ECVR-MVS		95.66 187	95.05 194	97.51 187	98.66 156	93.71 242	98.85 311	98.45 133	94.93 112	96.86 189	98.96 177	75.22 347	99.20 188	95.34 199	98.15 169	99.64 127

test1111		95.57 189	94.98 197	97.37 196	98.56 162	93.37 254	98.86 309	98.45 133	94.95 111	96.63 195	98.95 182	75.21 348	99.11 194	95.02 204	98.14 171	99.64 127

OPM-MVS		93.21 252	92.80 250	94.44 291	93.12 365	90.85 311	99.77 160	97.61 268	96.19 86	91.56 268	98.65 210	75.16 349	98.47 232	93.78 240	89.39 282	93.99 337
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tfpnnormal		89.29 338	87.61 345	94.34 296	94.35 343	94.13 232	98.95 296	98.94 42	83.94 377	84.47 369	95.51 329	74.84 350	97.39 299	77.05 396	80.41 363	91.48 391

AllTest		92.48 271	91.64 274	95.00 265	99.01 120	88.43 352	98.94 297	96.82 356	86.50 351	88.71 316	98.47 228	74.73 351	99.88 114	85.39 347	96.18 213	96.71 274

TestCases				95.00 265	99.01 120	88.43 352		96.82 356	86.50 351	88.71 316	98.47 228	74.73 351	99.88 114	85.39 347	96.18 213	96.71 274

Anonymous20231206		86.32 354	85.42 357	89.02 379	89.11 408	80.53 407	99.05 285	95.28 396	85.43 366	82.82 377	93.92 379	74.40 353	93.44 405	66.99 415	81.83 348	93.08 371

XXY-MVS		91.82 282	90.46 294	95.88 240	93.91 351	95.40 192	98.87 308	97.69 257	88.63 322	87.87 332	97.08 274	74.38 354	97.89 283	91.66 270	84.07 332	94.35 302

ACMP	92.05 9	92.74 265	92.42 263	93.73 316	95.91 305	88.72 347	99.81 150	97.53 278	94.13 149	87.00 345	98.23 240	74.07 355	98.47 232	96.22 188	88.86 288	93.99 337
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	88.28 18	90.29 319	89.05 326	94.02 306	95.08 330	90.15 327	97.19 374	97.43 287	84.91 372	83.99 372	97.06 276	74.00 356	98.28 258	84.08 355	87.71 305	93.62 359
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
pm-mvs1		89.36 337	87.81 343	94.01 307	93.40 361	91.93 285	98.62 330	96.48 372	86.25 355	83.86 373	96.14 307	73.68 357	97.04 325	86.16 342	75.73 394	93.04 372

pmmvs5		90.17 323	89.09 324	93.40 326	92.10 384	89.77 335	99.74 172	95.58 391	85.88 359	87.24 344	95.74 317	73.41 358	96.48 353	88.54 313	83.56 336	93.95 340

OurMVSNet-221017-0		89.81 329	89.48 319	90.83 363	91.64 389	81.21 401	98.17 355	95.38 395	91.48 254	85.65 362	97.31 267	72.66 359	97.29 309	88.15 318	84.83 325	93.97 339

jajsoiax		91.92 281	91.18 284	94.15 300	91.35 393	90.95 308	99.00 291	97.42 289	92.61 215	87.38 341	97.08 274	72.46 360	97.36 300	94.53 221	88.77 289	94.13 326

UGNet		95.33 196	94.57 205	97.62 180	98.55 165	94.85 210	98.67 327	99.32 26	95.75 94	96.80 192	96.27 303	72.18 361	99.96 68	94.58 220	99.05 141	98.04 252
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		91.81 283	91.08 286	94.00 308	91.63 390	90.58 317	98.67 327	97.43 287	92.43 225	87.37 342	97.05 277	71.76 362	97.32 304	94.75 215	88.68 291	94.11 327

SixPastTwentyTwo		88.73 341	88.01 342	90.88 360	91.85 387	82.24 394	98.22 353	95.18 400	88.97 310	82.26 379	96.89 282	71.75 363	96.67 347	84.00 356	82.98 337	93.72 357

test_fmvs1		95.35 195	95.68 175	94.36 295	98.99 125	84.98 379	99.96 44	96.65 365	97.60 30	99.73 40	98.96 177	71.58 364	99.93 94	98.31 125	99.37 124	98.17 248

GBi-Net		90.88 303	89.82 309	94.08 303	97.53 244	91.97 282	98.43 340	96.95 342	87.05 343	89.68 292	94.72 363	71.34 365	96.11 367	87.01 335	85.65 317	94.17 315

test1		90.88 303	89.82 309	94.08 303	97.53 244	91.97 282	98.43 340	96.95 342	87.05 343	89.68 292	94.72 363	71.34 365	96.11 367	87.01 335	85.65 317	94.17 315

FMVSNet2		91.02 300	89.56 314	95.41 253	97.53 244	95.74 175	98.98 292	97.41 291	87.05 343	88.43 325	95.00 357	71.34 365	96.24 364	85.12 350	85.21 322	94.25 309

PVSNet_0	88.03 19	91.80 286	90.27 300	96.38 228	98.27 190	90.46 320	99.94 80	99.61 13	93.99 158	86.26 357	97.39 266	71.13 368	99.89 108	98.77 97	67.05 413	98.79 230

sd_testset		93.55 246	92.83 249	95.74 245	98.92 135	90.89 310	98.24 350	98.85 57	92.41 226	92.55 259	97.85 255	71.07 369	98.68 223	93.93 231	91.62 271	97.64 261

Anonymous20231211		89.86 328	88.44 336	94.13 302	98.93 132	90.68 314	98.54 334	98.26 197	76.28 407	86.73 347	95.54 326	70.60 370	97.56 295	90.82 285	80.27 366	94.15 321

ITE_SJBPF				92.38 345	95.69 320	85.14 377		95.71 387	92.81 202	89.33 304	98.11 243	70.23 371	98.42 238	85.91 345	88.16 300	93.59 360

ACMH	89.72 17	90.64 309	89.63 312	93.66 322	95.64 322	88.64 350	98.55 332	97.45 285	89.03 306	81.62 383	97.61 259	69.75 372	98.41 239	89.37 304	87.62 307	93.92 343
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVS-HIRNet		86.22 355	83.19 368	95.31 257	96.71 289	90.29 323	92.12 414	97.33 300	62.85 422	86.82 346	70.37 427	69.37 373	97.49 297	75.12 401	97.99 177	98.15 249

Anonymous202405211		93.10 257	91.99 269	96.40 226	99.10 115	89.65 336	98.88 305	97.93 235	83.71 380	94.00 241	98.75 200	68.79 374	99.88 114	95.08 203	91.71 270	99.68 119

test20.03		84.72 367	83.99 360	86.91 389	88.19 411	80.62 406	98.88 305	95.94 382	88.36 326	78.87 394	94.62 368	68.75 375	89.11 420	66.52 417	75.82 392	91.00 394

VPNet		91.81 283	90.46 294	95.85 242	94.74 335	95.54 186	98.98 292	98.59 94	92.14 233	90.77 277	97.44 263	68.73 376	97.54 296	94.89 211	77.89 378	94.46 291

K. test v3		88.05 347	87.24 348	90.47 367	91.82 388	82.23 395	98.96 295	97.42 289	89.05 305	76.93 404	95.60 323	68.49 377	95.42 381	85.87 346	81.01 359	93.75 353

ACMH+	89.98 16	90.35 316	89.54 315	92.78 343	95.99 302	86.12 371	98.81 314	97.18 315	89.38 301	83.14 376	97.76 258	68.42 378	98.43 237	89.11 307	86.05 315	93.78 352

MDA-MVSNet-bldmvs		84.09 370	81.52 377	91.81 354	91.32 394	88.00 359	98.67 327	95.92 383	80.22 399	55.60 428	93.32 385	68.29 379	93.60 404	73.76 403	76.61 390	93.82 351

ttmdpeth		88.23 346	87.06 349	91.75 355	89.91 405	87.35 363	98.92 302	95.73 386	87.92 332	84.02 371	96.31 301	68.23 380	96.84 338	86.33 340	76.12 391	91.06 393

MS-PatchMatch		90.65 308	90.30 299	91.71 356	94.22 346	85.50 376	98.24 350	97.70 255	88.67 320	86.42 354	96.37 300	67.82 381	98.03 275	83.62 360	99.62 95	91.60 389

KD-MVS_self_test		83.59 374	82.06 374	88.20 386	86.93 412	80.70 405	97.21 373	96.38 373	82.87 387	82.49 378	88.97 408	67.63 382	92.32 412	73.75 404	62.30 423	91.58 390

LFMVS		94.75 211	93.56 232	98.30 137	99.03 119	95.70 178	98.74 319	97.98 230	87.81 335	98.47 134	99.39 139	67.43 383	99.53 163	98.01 139	95.20 240	99.67 121

MIMVSNet		90.30 318	88.67 332	95.17 261	96.45 292	91.64 297	92.39 413	97.15 319	85.99 357	90.50 278	93.19 388	66.95 384	94.86 391	82.01 371	93.43 262	99.01 219

test_vis1_n_1920		95.44 192	95.31 184	95.82 243	98.50 172	88.74 346	99.98 17	97.30 303	97.84 24	99.85 14	99.19 156	66.82 385	99.97 57	98.82 93	99.46 116	98.76 231

XVG-ACMP-BASELINE		91.22 298	90.75 289	92.63 344	93.73 354	85.61 374	98.52 336	97.44 286	92.77 206	89.90 287	96.85 285	66.64 386	98.39 243	92.29 261	88.61 292	93.89 345

Anonymous20240529		92.10 279	90.65 291	96.47 222	98.82 145	90.61 316	98.72 321	98.67 78	75.54 411	93.90 243	98.58 218	66.23 387	99.90 103	94.70 217	90.67 274	98.90 225

lessismore_v0				90.53 365	90.58 399	80.90 404		95.80 384		77.01 403	95.84 314	66.15 388	96.95 330	83.03 364	75.05 395	93.74 356

USDC		90.00 326	88.96 327	93.10 336	94.81 334	88.16 356	98.71 322	95.54 392	93.66 174	83.75 374	97.20 270	65.58 389	98.31 254	83.96 358	87.49 309	92.85 375

pmmvs-eth3d		84.03 371	81.97 375	90.20 370	84.15 418	87.09 365	98.10 358	94.73 406	83.05 385	74.10 412	87.77 414	65.56 390	94.01 398	81.08 376	69.24 406	89.49 411

Anonymous20240521		85.15 362	83.81 364	89.16 378	88.32 409	82.69 390	98.80 316	95.74 385	79.72 400	81.53 384	90.99 399	65.38 391	94.16 397	72.69 405	81.11 355	90.63 399

LF4IMVS		89.25 339	88.85 328	90.45 368	92.81 375	81.19 402	98.12 356	94.79 404	91.44 256	86.29 356	97.11 272	65.30 392	98.11 269	88.53 314	85.25 321	92.07 384

new_pmnet		84.49 369	82.92 370	89.21 377	90.03 403	82.60 391	96.89 383	95.62 390	80.59 397	75.77 409	89.17 407	65.04 393	94.79 392	72.12 407	81.02 358	90.23 401

SSC-MVS3.2		89.59 333	88.66 333	92.38 345	94.29 345	86.12 371	99.49 227	97.66 260	90.28 290	88.63 320	95.18 349	64.46 394	96.88 336	85.30 349	82.66 340	94.14 324

CMPMVS	61.59 21	84.75 366	85.14 359	83.57 395	90.32 401	62.54 423	96.98 380	97.59 272	74.33 415	69.95 416	96.66 290	64.17 395	98.32 253	87.88 322	88.41 297	89.84 407
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_0402		85.58 357	83.94 362	90.50 366	93.81 353	85.04 378	98.55 332	95.20 399	76.01 408	79.72 393	95.13 350	64.15 396	96.26 363	66.04 419	86.88 311	90.21 402

TDRefinement		84.76 365	82.56 373	91.38 358	74.58 431	84.80 382	97.36 371	94.56 408	84.73 373	80.21 390	96.12 310	63.56 397	98.39 243	87.92 321	63.97 419	90.95 396

mmtdpeth		88.52 342	87.75 344	90.85 362	95.71 317	83.47 388	98.94 297	94.85 402	88.78 317	97.19 180	89.58 405	63.29 398	98.97 201	98.54 111	62.86 421	90.10 404

UnsupCasMVSNet_eth		85.52 358	83.99 360	90.10 371	89.36 407	83.51 387	96.65 385	97.99 228	89.14 303	75.89 408	93.83 380	63.25 399	93.92 399	81.92 372	67.90 412	92.88 374

tt0805		91.28 295	90.18 303	94.60 280	96.26 295	87.55 360	98.39 344	98.72 70	89.00 308	89.22 307	98.47 228	62.98 400	98.96 203	90.57 289	88.00 302	97.28 270

new-patchmatchnet		81.19 377	79.34 384	86.76 390	82.86 421	80.36 408	97.92 362	95.27 397	82.09 392	72.02 413	86.87 416	62.81 401	90.74 418	71.10 408	63.08 420	89.19 414

mvs5depth		84.87 364	82.90 371	90.77 364	85.59 416	84.84 381	91.10 420	93.29 419	83.14 384	85.07 366	94.33 376	62.17 402	97.32 304	78.83 388	72.59 400	90.14 403

TinyColmap		87.87 350	86.51 351	91.94 351	95.05 331	85.57 375	97.65 367	94.08 411	84.40 376	81.82 382	96.85 285	62.14 403	98.33 252	80.25 380	86.37 314	91.91 388

test_fmvs1_n		94.25 230	94.36 209	93.92 311	97.68 233	83.70 386	99.90 104	96.57 368	97.40 36	99.67 46	98.88 188	61.82 404	99.92 100	98.23 128	99.13 136	98.14 251

VDDNet		93.12 256	91.91 271	96.76 215	96.67 290	92.65 271	98.69 325	98.21 204	82.81 388	97.75 165	99.28 145	61.57 405	99.48 174	98.09 136	94.09 254	98.15 249

pmmvs6		85.69 356	83.84 363	91.26 359	90.00 404	84.41 383	97.82 365	96.15 379	75.86 409	81.29 385	95.39 337	61.21 406	96.87 337	83.52 362	73.29 397	92.50 380

VDD-MVS		93.77 239	92.94 247	96.27 231	98.55 165	90.22 325	98.77 318	97.79 249	90.85 274	96.82 191	99.42 132	61.18 407	99.77 140	98.95 82	94.13 253	98.82 228

testgi		89.01 340	88.04 341	91.90 352	93.49 358	84.89 380	99.73 179	95.66 389	93.89 167	85.14 364	98.17 241	59.68 408	94.66 394	77.73 392	88.88 286	96.16 282

FMVSNet1		88.50 343	86.64 350	94.08 303	95.62 324	91.97 282	98.43 340	96.95 342	83.00 386	86.08 359	94.72 363	59.09 409	96.11 367	81.82 373	84.07 332	94.17 315

DeepMVS_CX				82.92 397	95.98 304	58.66 428		96.01 381	92.72 207	78.34 398	95.51 329	58.29 410	98.08 271	82.57 366	85.29 320	92.03 386

UniMVSNet_ETH3D		90.06 325	88.58 334	94.49 288	94.67 337	88.09 357	97.81 366	97.57 273	83.91 379	88.44 323	97.41 264	57.44 411	97.62 293	91.41 272	88.59 294	97.77 258

pmmvs3		80.27 381	77.77 386	87.76 388	80.32 426	82.43 393	98.23 352	91.97 423	72.74 418	78.75 395	87.97 413	57.30 412	90.99 417	70.31 409	62.37 422	89.87 406

OpenMVS_ROB	79.82 20	83.77 373	81.68 376	90.03 372	88.30 410	82.82 389	98.46 337	95.22 398	73.92 416	76.00 407	91.29 398	55.00 413	96.94 331	68.40 413	88.51 296	90.34 400

test_fmvs2		89.47 335	89.70 311	88.77 383	94.54 339	75.74 411	99.83 145	94.70 407	94.71 122	91.08 272	96.82 289	54.46 414	97.78 288	92.87 256	88.27 298	92.80 376

tmp_tt		65.23 396	62.94 399	72.13 411	44.90 440	50.03 436	81.05 427	89.42 431	38.45 430	48.51 432	99.90 18	54.09 415	78.70 432	91.84 269	18.26 434	87.64 416

EGC-MVSNET		69.38 388	63.76 398	86.26 391	90.32 401	81.66 400	96.24 393	93.85 415	0.99 438	3.22 439	92.33 395	52.44 416	92.92 409	59.53 425	84.90 324	84.21 419

test_vis1_n		93.61 245	93.03 246	95.35 254	95.86 306	86.94 366	99.87 119	96.36 374	96.85 58	99.54 66	98.79 198	52.41 417	99.83 130	98.64 106	98.97 143	99.29 195

MIMVSNet1		82.58 375	80.51 381	88.78 381	86.68 413	84.20 384	96.65 385	95.41 394	78.75 403	78.59 397	92.44 391	51.88 418	89.76 419	65.26 420	78.95 371	92.38 383

EG-PatchMatch MVS		85.35 361	83.81 364	89.99 373	90.39 400	81.89 397	98.21 354	96.09 380	81.78 393	74.73 410	93.72 382	51.56 419	97.12 318	79.16 386	88.61 292	90.96 395

UnsupCasMVSNet_bld		79.97 384	77.03 389	88.78 381	85.62 415	81.98 396	93.66 409	97.35 296	75.51 412	70.79 415	83.05 422	48.70 420	94.91 390	78.31 390	60.29 425	89.46 412

test_vis1_rt		86.87 353	86.05 355	89.34 376	96.12 297	78.07 410	99.87 119	83.54 435	92.03 238	78.21 399	89.51 406	45.80 421	99.91 101	96.25 187	93.11 267	90.03 405

test_method		80.79 379	79.70 383	84.08 394	92.83 373	67.06 420	99.51 223	95.42 393	54.34 426	81.07 387	93.53 383	44.48 422	92.22 413	78.90 387	77.23 385	92.94 373

APD_test1		81.15 378	80.92 379	81.86 398	92.45 378	59.76 427	96.04 397	93.61 417	73.29 417	77.06 402	96.64 292	44.28 423	96.16 366	72.35 406	82.52 341	89.67 409

mvsany_test3		82.12 376	81.14 378	85.06 393	81.87 422	70.41 417	97.09 377	92.14 422	91.27 263	77.84 400	88.73 409	39.31 424	95.49 379	90.75 287	71.24 401	89.29 413

PM-MVS		80.47 380	78.88 385	85.26 392	83.79 420	72.22 415	95.89 400	91.08 425	85.71 363	76.56 406	88.30 410	36.64 425	93.90 400	82.39 368	69.57 405	89.66 410

ambc				83.23 396	77.17 429	62.61 422	87.38 425	94.55 409		76.72 405	86.65 417	30.16 426	96.36 358	84.85 353	69.86 403	90.73 397

Gipuma		66.95 395	65.00 395	72.79 407	91.52 391	67.96 419	66.16 430	95.15 401	47.89 428	58.54 425	67.99 430	29.74 427	87.54 424	50.20 429	77.83 379	62.87 430
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EMVS		51.44 401	51.22 403	52.11 417	70.71 433	44.97 440	94.04 406	75.66 439	35.34 434	42.40 434	61.56 435	28.93 428	65.87 436	27.64 437	24.73 432	45.49 433

test_fmvs3		79.99 383	80.17 382	79.45 400	84.02 419	62.83 421	99.05 285	93.49 418	88.29 328	80.06 392	86.65 417	28.09 429	88.00 421	88.63 310	73.27 398	87.54 417

test_f		78.40 385	77.59 387	80.81 399	80.82 424	62.48 424	96.96 381	93.08 420	83.44 382	74.57 411	84.57 421	27.95 430	92.63 410	84.15 354	72.79 399	87.32 418

E-PMN		52.30 399	52.18 401	52.67 416	71.51 432	45.40 438	93.62 410	76.60 438	36.01 432	43.50 433	64.13 432	27.11 431	67.31 435	31.06 436	26.06 431	45.30 434

FPMVS		68.72 390	68.72 391	68.71 412	65.95 435	44.27 441	95.97 399	94.74 405	51.13 427	53.26 429	90.50 403	25.11 432	83.00 428	60.80 423	80.97 360	78.87 425

PMMVS2		67.15 394	64.15 397	76.14 404	70.56 434	62.07 425	93.89 407	87.52 432	58.09 423	60.02 422	78.32 424	22.38 433	84.54 427	59.56 424	47.03 429	81.80 422

testf1		68.38 391	66.92 392	72.78 408	78.80 427	50.36 434	90.95 421	87.35 433	55.47 424	58.95 423	88.14 411	20.64 434	87.60 422	57.28 426	64.69 417	80.39 423

APD_test2		68.38 391	66.92 392	72.78 408	78.80 427	50.36 434	90.95 421	87.35 433	55.47 424	58.95 423	88.14 411	20.64 434	87.60 422	57.28 426	64.69 417	80.39 423

LCM-MVSNet		67.77 393	64.73 396	76.87 403	62.95 437	56.25 430	89.37 424	93.74 416	44.53 429	61.99 421	80.74 423	20.42 436	86.53 426	69.37 412	59.50 426	87.84 415

test123		37.68 403	39.14 406	33.31 418	19.94 442	24.83 444	98.36 345	9.75 443	15.53 436	51.31 430	87.14 415	19.62 437	17.74 438	47.10 430	3.47 437	57.36 431

ANet_high		56.10 397	52.24 400	67.66 413	49.27 439	56.82 429	83.94 426	82.02 436	70.47 420	33.28 436	64.54 431	17.23 438	69.16 434	45.59 431	23.85 433	77.02 426

test_vis3_rt		68.82 389	66.69 394	75.21 405	76.24 430	60.41 426	96.44 388	68.71 440	75.13 413	50.54 431	69.52 429	16.42 439	96.32 360	80.27 379	66.92 414	68.89 427

testmvs		40.60 402	44.45 405	29.05 419	19.49 443	14.11 445	99.68 193	18.47 442	20.74 435	64.59 420	98.48 227	10.95 440	17.09 439	56.66 428	11.01 435	55.94 432

PMVS	49.05 23	53.75 398	51.34 402	60.97 415	40.80 441	34.68 442	74.82 429	89.62 430	37.55 431	28.67 437	72.12 426	7.09 441	81.63 431	43.17 432	68.21 410	66.59 429
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		20.37 405	20.84 408	18.99 420	65.34 436	27.73 443	50.43 431	7.67 444	9.50 437	8.01 438	6.34 438	6.13 442	26.24 437	23.40 438	10.69 436	2.99 435

MVE	53.74 22	51.54 400	47.86 404	62.60 414	59.56 438	50.93 433	79.41 428	77.69 437	35.69 433	36.27 435	61.76 434	5.79 443	69.63 433	37.97 433	36.61 430	67.24 428
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
mmdepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

monomultidepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

test_blank		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.02 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet_test		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

DCPMVS		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet-low-res		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uncertanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

Regformer		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

ab-mvs-re		8.28 406	11.04 409	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	99.40 137	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

WAC-MVS						90.97 305								86.10 344

FOURS1					99.92 31	97.66 96	99.95 63	98.36 178	95.58 98	99.52 69

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 163					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 163					100.00 1	99.96 9	100.00 1	100.00 1

eth-test2					0.00 444

eth-test					0.00 444

IU-MVS					99.93 24	99.31 10		98.41 163	97.71 27	99.84 17				100.00 1	100.00 1	100.00 1

save fliter					99.82 58	98.79 40	99.96 44	98.40 167	97.66 29

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 63	98.43 146					100.00 1	99.99 5	100.00 1	100.00 1

GSMVS																99.59 141

test_part2					99.89 45	99.25 18				99.49 72

MTGPA								98.28 194

MTMP							99.87 119	96.49 371

gm-plane-assit					96.97 272	93.76 241			91.47 255		98.96 177		98.79 211	94.92 208

test9_res														99.71 41	99.99 21	100.00 1

agg_prior2														99.48 55	100.00 1	100.00 1

agg_prior					99.93 24	98.77 42		98.43 146		99.63 52			99.85 120

test_prior4						98.05 76	99.94 80

test_prior				99.43 35	99.94 13	98.49 60		98.65 79					99.80 133			99.99 23

旧先验2							99.46 235		94.21 148	99.85 14			99.95 77	96.96 177

新几何2							99.40 239

无先验							99.49 227	98.71 71	93.46 178				100.00 1	94.36 223		99.99 23

原ACMM2							99.90 104

testdata2													99.99 36	90.54 291

testdata1							99.28 260		96.35 82

plane_prior7					95.71 317	91.59 299

plane_prior5								97.87 242					98.37 249	97.79 154	89.55 279	94.52 288

plane_prior4											98.59 215

plane_prior3						91.64 297			96.63 69	93.01 251

plane_prior2							99.84 138		96.38 78

plane_prior1					95.73 314

plane_prior						91.74 291	99.86 130		96.76 64						89.59 278

n2								0.00 445

nn								0.00 445

door-mid								89.69 429

test11								98.44 138

door								90.31 426

HQP5-MVS						91.85 287

HQP-NCC					95.78 307		99.87 119		96.82 60	93.37 246

ACMP_Plane					95.78 307		99.87 119		96.82 60	93.37 246

BP-MVS														97.92 145

HQP4-MVS										93.37 246			98.39 243			94.53 286

HQP3-MVS								97.89 240							89.60 276

NP-MVS					95.77 310	91.79 289					98.65 210

ACMMP++_ref															87.04 310

ACMMP++															88.23 299

High-resolution multi-view benchmark