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.

CHOSEN 280x420		99.01 13	99.03 10	98.95 74	99.38 95	98.87 32	98.46 301	99.42 22	97.03 40	99.02 87	99.09 143	99.35 1	98.21 232	99.73 30	99.78 79	99.77 99

GG-mvs-BLEND				98.54 101	98.21 165	98.01 68	93.87 370	98.52 99		97.92 132	97.92 221	99.02 2	97.94 248	98.17 104	99.58 95	99.67 111

gg-mvs-nofinetune		93.51 213	91.86 239	98.47 106	97.72 198	97.96 72	92.62 374	98.51 102	74.70 376	97.33 146	69.59 389	98.91 3	97.79 252	97.77 128	99.56 96	99.67 111

iter_conf05		96.07 141	95.95 131	96.44 195	98.43 152	97.52 85	99.91 80	96.85 315	94.16 129	92.49 226	97.98 218	98.20 4	97.34 267	97.26 139	88.29 262	94.45 261

iter_conf_final		96.01 144	95.93 133	96.28 200	98.38 154	97.03 105	99.87 98	97.03 295	94.05 138	92.61 222	97.98 218	98.01 5	97.34 267	97.02 146	88.39 261	94.47 255

test_0728_THIRD									96.48 57	99.83 11	99.91 14	97.87 6	100.00 1	99.92 12	100.00 1	100.00 1

baseline2		96.71 118	96.49 111	97.37 166	95.63 285	95.96 144	99.74 151	98.88 51	92.94 171	91.61 233	98.97 157	97.72 7	98.62 195	94.83 182	98.08 154	97.53 234

SteuartSystems-ACMMP		99.02 12	98.97 13	99.18 48	98.72 137	97.71 77	99.98 14	98.44 117	96.85 44	99.80 15	99.91 14	97.57 8	99.85 106	99.44 44	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
thisisatest0515		97.41 90	97.02 96	98.59 95	97.71 200	97.52 85	99.97 25	98.54 96	91.83 216	97.45 144	99.04 147	97.50 9	99.10 170	94.75 185	96.37 188	99.16 184

PC_three_1452									96.96 42	99.80 15	99.79 55	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

test_one_0601					99.94 13	99.30 12		98.41 140	96.63 54	99.75 27	99.93 11	97.49 10

thisisatest0530		97.10 100	96.72 104	98.22 120	97.60 206	96.70 115	99.92 76	98.54 96	91.11 239	97.07 151	98.97 157	97.47 12	99.03 171	93.73 212	96.09 191	98.92 195

tttt0517		96.85 109	96.49 111	97.92 132	97.48 213	95.89 146	99.85 114	98.54 96	90.72 250	96.63 162	98.93 168	97.47 12	99.02 172	93.03 224	95.76 202	98.85 199

DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 39	99.31 10	99.95 50	98.43 125	96.48 57	99.80 15	99.93 11	97.44 14	100.00 1	99.92 12	99.98 32	100.00 1

OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 32				99.80 51	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 71	99.93 24	97.24 96	99.95 50	98.42 136	97.50 24	99.52 57	99.88 21	97.43 16	99.71 136	99.50 39	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 14	99.96 8	99.15 21	99.97 25	98.62 79	98.02 11	99.90 2	99.95 3	97.33 17	100.00 1	99.54 37	100.00 1	100.00 1

MVSTER		95.53 159	95.22 155	96.45 193	98.56 143	97.72 76	99.91 80	97.67 227	92.38 201	91.39 235	97.14 240	97.24 18	97.30 272	94.80 183	87.85 269	94.34 271

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 50	98.32 164	97.28 30	99.83 11	99.91 14	97.22 19	100.00 1	99.99 5	100.00 1	99.89 82
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 32	98.42 136	97.28 30	99.86 5	99.94 4	97.22 19

test_241102_TWO								98.43 125	97.27 32	99.80 15	99.94 4	97.18 21	100.00 1	100.00 1	100.00 1	100.00 1

DPM-MVS		98.83 19	98.46 27	99.97 1	99.33 97	99.92 1	99.96 32	98.44 117	97.96 12	99.55 52	99.94 4	97.18 21	100.00 1	93.81 207	99.94 54	99.98 48

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 14	98.69 66	98.20 5	99.93 1	99.98 2	96.82 23	100.00 1	99.75 26	100.00 1	99.99 23

SED-MVS		99.28 5	99.11 7	99.77 8	99.93 24	99.30 12	99.96 32	98.43 125	97.27 32	99.80 15	99.94 4	96.71 24	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 125	97.26 34	99.80 15	99.88 21	96.71 24	100.00 1

DPE-MVS		99.26 6	99.10 8	99.74 11	99.89 45	99.24 19	99.87 98	98.44 117	97.48 25	99.64 40	99.94 4	96.68 26	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 26

patch_mono-2		98.24 53	99.12 5	95.59 215	99.67 77	86.91 334	99.95 50	98.89 49	97.60 20	99.90 2	99.76 63	96.54 28	99.98 43	99.94 11	99.82 76	99.88 83

PAPM		98.60 27	98.42 28	99.14 57	96.05 263	98.96 26	99.90 85	99.35 25	96.68 53	98.35 120	99.66 94	96.45 29	98.51 200	99.45 43	99.89 66	99.96 63

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 25	98.64 74	98.47 2	99.13 83	99.92 13	96.38 30	100.00 1	99.74 28	100.00 1	100.00 1

ET-MVSNet_ETH3D		94.37 190	93.28 208	97.64 150	98.30 157	97.99 69	99.99 4	97.61 234	94.35 120	71.57 376	99.45 115	96.23 31	95.34 346	96.91 152	85.14 291	99.59 128

EPP-MVSNet		96.69 119	96.60 107	96.96 178	97.74 193	93.05 229	99.37 215	98.56 87	88.75 284	95.83 183	99.01 150	96.01 32	98.56 197	96.92 151	97.20 171	99.25 179

test_prior2							99.95 50		95.78 77	99.73 30	99.76 63	96.00 33		99.78 25	100.00 1

train_agg		98.88 17	98.65 18	99.59 23	99.92 31	98.92 28	99.96 32	98.43 125	94.35 120	99.71 32	99.86 26	95.94 34	99.85 106	99.69 33	99.98 32	99.99 23

test_8					99.92 31	98.88 31	99.96 32	98.43 125	94.35 120	99.69 34	99.85 30	95.94 34	99.85 106

MSLP-MVS++		99.13 8	99.01 11	99.49 32	99.94 13	98.46 59	99.98 14	98.86 53	97.10 38	99.80 15	99.94 4	95.92 36	100.00 1	99.51 38	100.00 1	100.00 1

TEST9					99.92 31	98.92 28	99.96 32	98.43 125	93.90 146	99.71 32	99.86 26	95.88 37	99.85 106

test_yl		97.83 67	97.37 81	99.21 45	99.18 101	97.98 70	99.64 175	99.27 27	91.43 229	97.88 135	98.99 153	95.84 38	99.84 114	98.82 75	95.32 211	99.79 95

DCV-MVSNet		97.83 67	97.37 81	99.21 45	99.18 101	97.98 70	99.64 175	99.27 27	91.43 229	97.88 135	98.99 153	95.84 38	99.84 114	98.82 75	95.32 211	99.79 95

DP-MVS Recon		98.41 42	98.02 54	99.56 25	99.97 3	98.70 46	99.92 76	98.44 117	92.06 210	98.40 118	99.84 41	95.68 40	100.00 1	98.19 103	99.71 83	99.97 57

旧先验1					99.76 66	97.52 85		98.64 74			99.85 30	95.63 41			99.94 54	99.99 23

SMA-MVS		98.76 21	98.48 26	99.62 20	99.87 51	98.87 32	99.86 111	98.38 151	93.19 166	99.77 25	99.94 4	95.54 42	100.00 1	99.74 28	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		96.74 116	96.26 116	98.16 121	97.36 219	96.48 121	99.96 32	98.29 170	91.93 213	95.77 184	98.07 213	95.54 42	98.29 224	90.55 258	98.89 128	99.70 106

APDe-MVS		99.06 11	98.91 14	99.51 29	99.94 13	98.76 43	99.91 80	98.39 147	97.20 36	99.46 61	99.85 30	95.53 44	99.79 121	99.86 19	100.00 1	99.99 23
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
PLC	95.54 3	97.93 62	97.89 64	98.05 128	99.82 58	94.77 187	99.92 76	98.46 112	93.93 144	97.20 148	99.27 130	95.44 45	99.97 53	97.41 135	99.51 100	99.41 160
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 15	99.63 17	99.90 42	99.02 25	99.95 50	98.56 87	97.56 23	99.44 63	99.85 30	95.38 46	100.00 1	99.31 49	99.99 21	99.87 85

PHI-MVS		98.41 42	98.21 42	99.03 66	99.86 53	97.10 103	99.98 14	98.80 60	90.78 249	99.62 44	99.78 59	95.30 47	100.00 1	99.80 23	99.93 60	99.99 23

test-mter		96.39 131	95.93 133	97.78 140	97.02 233	95.44 162	99.96 32	98.21 178	91.81 218	95.55 186	96.38 267	95.17 48	98.27 228	90.42 261	98.83 132	99.64 117

patchmatchnet-post											91.70 359	95.12 49	97.95 246

MDTV_nov1_ep13			95.69 142		97.90 182	94.15 201	95.98 360	98.44 117	93.12 168	97.98 130	95.74 284	95.10 50	98.58 196	90.02 267	96.92 179

IB-MVS	92.85 6	94.99 170	93.94 187	98.16 121	97.72 198	95.69 155	99.99 4	98.81 58	94.28 125	92.70 221	96.90 250	95.08 51	99.17 167	96.07 161	73.88 360	99.60 127
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 54		98.52 99	92.34 202	99.31 74	99.83 43	95.06 52	99.80 119	99.70 32	99.97 42

CDS-MVSNet		96.34 133	96.07 120	97.13 174	97.37 218	94.96 180	99.53 192	97.91 211	91.55 224	95.37 190	98.32 208	95.05 53	97.13 283	93.80 208	95.75 203	99.30 174
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Patchmatch-test		92.65 235	91.50 245	96.10 205	96.85 243	90.49 288	91.50 379	97.19 276	82.76 351	90.23 248	95.59 291	95.02 54	98.00 242	77.41 356	96.98 178	99.82 90

CostFormer		96.10 140	95.88 137	96.78 183	97.03 232	92.55 243	97.08 340	97.83 219	90.04 262	98.72 103	94.89 324	95.01 55	98.29 224	96.54 156	95.77 201	99.50 149

TSAR-MVS + GP.		98.60 27	98.51 25	98.86 78	99.73 72	96.63 117	99.97 25	97.92 210	98.07 9	98.76 100	99.55 106	95.00 56	99.94 75	99.91 15	97.68 160	99.99 23

CDPH-MVS		98.65 25	98.36 35	99.49 32	99.94 13	98.73 44	99.87 98	98.33 162	93.97 141	99.76 26	99.87 24	94.99 57	99.75 130	98.55 91	100.00 1	99.98 48

原ACMM1				98.96 73	99.73 72	96.99 107		98.51 102	94.06 136	99.62 44	99.85 30	94.97 58	99.96 59	95.11 172	99.95 49	99.92 79

TSAR-MVS + MP.		98.93 14	98.77 16	99.41 38	99.74 69	98.67 47	99.77 140	98.38 151	96.73 51	99.88 4	99.74 74	94.89 59	99.59 147	99.80 23	99.98 32	99.97 57
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test12				99.43 35	99.74 69	98.56 55		98.40 144		99.65 38		94.76 60	99.75 130		99.98 32	99.99 23

sam_mvs1												94.72 61				99.59 128

SF-MVS		98.67 24	98.40 29	99.50 30	99.77 65	98.67 47	99.90 85	98.21 178	93.53 156	99.81 13	99.89 19	94.70 62	99.86 105	99.84 20	99.93 60	99.96 63

SD-MVS		98.92 15	98.70 17	99.56 25	99.70 76	98.73 44	99.94 66	98.34 161	96.38 63	99.81 13	99.76 63	94.59 63	99.98 43	99.84 20	99.96 46	99.97 57
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 31		99.87 51		99.91 80	98.33 162	93.22 165	99.78 24	99.89 19	94.57 64	99.85 106	99.84 20	99.97 42

test_post											63.35 394	94.43 65	98.13 235

EPMVS		96.53 125	96.01 122	98.09 126	98.43 152	96.12 142	96.36 351	99.43 21	93.53 156	97.64 139	95.04 317	94.41 66	98.38 216	91.13 244	98.11 151	99.75 101

新几何1				99.42 37	99.75 68	98.27 61		98.63 78	92.69 183	99.55 52	99.82 46	94.40 67	100.00 1	91.21 242	99.94 54	99.99 23

MDTV_nov1_ep13_2view						96.26 131	96.11 357		91.89 214	98.06 128		94.40 67		94.30 195		99.67 111

PAPM_NR		98.12 57	97.93 61	98.70 85	99.94 13	96.13 140	99.82 128	98.43 125	94.56 111	97.52 141	99.70 83	94.40 67	99.98 43	97.00 147	99.98 32	99.99 23

dcpmvs_2		97.42 89	98.09 51	95.42 220	99.58 84	87.24 330	99.23 232	96.95 304	94.28 125	98.93 91	99.73 76	94.39 70	99.16 168	99.89 16	99.82 76	99.86 87

miper_enhance_ethall		94.36 192	93.98 185	95.49 216	98.68 139	95.24 172	99.73 156	97.29 269	93.28 164	89.86 256	95.97 280	94.37 71	97.05 289	92.20 231	84.45 296	94.19 280

XVS		98.70 23	98.55 23	99.15 55	99.94 13	97.50 88	99.94 66	98.42 136	96.22 69	99.41 66	99.78 59	94.34 72	99.96 59	98.92 68	99.95 49	99.99 23

X-MVStestdata		93.83 201	92.06 233	99.15 55	99.94 13	97.50 88	99.94 66	98.42 136	96.22 69	99.41 66	41.37 398	94.34 72	99.96 59	98.92 68	99.95 49	99.99 23

CP-MVS		98.45 37	98.32 37	98.87 77	99.96 8	96.62 118	99.97 25	98.39 147	94.43 115	98.90 92	99.87 24	94.30 74	100.00 1	99.04 61	99.99 21	99.99 23

sam_mvs												94.25 75

Patchmatch-RL test		86.90 314	85.98 318	89.67 335	84.45 377	75.59 374	89.71 384	92.43 382	86.89 313	77.83 363	90.94 362	94.22 76	93.63 364	87.75 291	69.61 367	99.79 95

HFP-MVS		98.56 29	98.37 33	99.14 57	99.96 8	97.43 92	99.95 50	98.61 80	94.77 103	99.31 74	99.85 30	94.22 76	100.00 1	98.70 82	99.98 32	99.98 48

PatchmatchNet		95.94 146	95.45 147	97.39 165	97.83 187	94.41 193	96.05 358	98.40 144	92.86 172	97.09 150	95.28 312	94.21 78	98.07 239	89.26 274	98.11 151	99.70 106
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
DeepPCF-MVS	95.94 2	97.71 79	98.98 12	93.92 279	99.63 79	81.76 361	99.96 32	98.56 87	99.47 1	99.19 81	99.99 1	94.16 79	100.00 1	99.92 12	99.93 60	100.00 1

APD-MVS		98.62 26	98.35 36	99.41 38	99.90 42	98.51 57	99.87 98	98.36 155	94.08 133	99.74 29	99.73 76	94.08 80	99.74 132	99.42 45	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 30	98.37 33	99.05 64	99.96 8	97.18 99	99.96 32	98.55 93	94.87 101	99.45 62	99.85 30	94.07 81	100.00 1	98.67 84	100.00 1	99.98 48

PAPR		98.52 32	98.16 46	99.58 24	99.97 3	98.77 40	99.95 50	98.43 125	95.35 89	98.03 129	99.75 68	94.03 82	99.98 43	98.11 108	99.83 72	99.99 23

MG-MVS		98.91 16	98.65 18	99.68 15	99.94 13	99.07 24	99.64 175	99.44 20	97.33 29	99.00 88	99.72 79	94.03 82	99.98 43	98.73 81	100.00 1	100.00 1

MVS_111021_HR		98.72 22	98.62 20	99.01 69	99.36 96	97.18 99	99.93 73	99.90 1	96.81 49	98.67 105	99.77 61	93.92 84	99.89 94	99.27 51	99.94 54	99.96 63

tpmrst		96.27 139	95.98 125	97.13 174	97.96 179	93.15 226	96.34 352	98.17 183	92.07 208	98.71 104	95.12 315	93.91 85	98.73 186	94.91 180	96.62 182	99.50 149

test-LLR		96.47 126	96.04 121	97.78 140	97.02 233	95.44 162	99.96 32	98.21 178	94.07 134	95.55 186	96.38 267	93.90 86	98.27 228	90.42 261	98.83 132	99.64 117

test0.0.03 1		93.86 200	93.61 193	94.64 247	95.02 294	92.18 250	99.93 73	98.58 83	94.07 134	87.96 297	98.50 198	93.90 86	94.96 351	81.33 339	93.17 230	96.78 237

test222					99.55 85	97.41 94	99.34 218	98.55 93	91.86 215	99.27 78	99.83 43	93.84 88			99.95 49	99.99 23

dp		95.05 168	94.43 174	96.91 179	97.99 178	92.73 237	96.29 354	97.98 202	89.70 266	95.93 180	94.67 330	93.83 89	98.45 205	86.91 306	96.53 184	99.54 141

ACMMPR		98.50 33	98.32 37	99.05 64	99.96 8	97.18 99	99.95 50	98.60 81	94.77 103	99.31 74	99.84 41	93.73 90	100.00 1	98.70 82	99.98 32	99.98 48

EPNet		98.49 34	98.40 29	98.77 82	99.62 80	96.80 114	99.90 85	99.51 17	97.60 20	99.20 79	99.36 124	93.71 91	99.91 87	97.99 115	98.71 135	99.61 125
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
alignmvs		97.81 70	97.33 83	99.25 43	98.77 135	98.66 49	99.99 4	98.44 117	94.40 119	98.41 116	99.47 112	93.65 92	99.42 160	98.57 90	94.26 220	99.67 111

testdata				98.42 111	99.47 91	95.33 168		98.56 87	93.78 149	99.79 23	99.85 30	93.64 93	99.94 75	94.97 176	99.94 54	100.00 1

EI-MVSNet-Vis-set		98.27 49	98.11 50	98.75 83	99.83 57	96.59 120	99.40 208	98.51 102	95.29 91	98.51 112	99.76 63	93.60 94	99.71 136	98.53 92	99.52 98	99.95 70

mPP-MVS		98.39 44	98.20 43	98.97 72	99.97 3	96.92 110	99.95 50	98.38 151	95.04 95	98.61 109	99.80 51	93.39 95	100.00 1	98.64 87	100.00 1	99.98 48

SR-MVS		98.46 36	98.30 40	98.93 75	99.88 49	97.04 104	99.84 118	98.35 157	94.92 99	99.32 73	99.80 51	93.35 96	99.78 123	99.30 50	99.95 49	99.96 63

WTY-MVS		98.10 58	97.60 73	99.60 22	98.92 122	99.28 17	99.89 93	99.52 15	95.58 83	98.24 126	99.39 121	93.33 97	99.74 132	97.98 117	95.58 206	99.78 98

tpm2		95.47 160	95.18 157	96.35 199	96.91 238	91.70 265	96.96 343	97.93 207	88.04 297	98.44 115	95.40 301	93.32 98	97.97 243	94.00 199	95.61 205	99.38 162

HY-MVS	92.50 7	97.79 73	97.17 90	99.63 17	98.98 115	99.32 9	97.49 330	99.52 15	95.69 80	98.32 121	97.41 233	93.32 98	99.77 126	98.08 111	95.75 203	99.81 92

EI-MVSNet-UG-set		98.14 56	97.99 55	98.60 93	99.80 61	96.27 130	99.36 217	98.50 107	95.21 93	98.30 122	99.75 68	93.29 100	99.73 135	98.37 97	99.30 114	99.81 92

SR-MVS-dyc-post		98.31 46	98.17 45	98.71 84	99.79 62	96.37 128	99.76 145	98.31 166	94.43 115	99.40 68	99.75 68	93.28 101	99.78 123	98.90 71	99.92 63	99.97 57

baseline1		95.78 150	94.86 166	98.54 101	98.47 151	98.07 65	99.06 249	97.99 200	92.68 184	94.13 205	98.62 190	93.28 101	98.69 191	93.79 209	85.76 284	98.84 200

PGM-MVS		98.34 45	98.13 48	98.99 70	99.92 31	97.00 106	99.75 148	99.50 18	93.90 146	99.37 71	99.76 63	93.24 103	100.00 1	97.75 130	99.96 46	99.98 48

test_post1							95.78 363				59.23 397	93.20 104	97.74 255	91.06 246

CSCG		97.10 100	97.04 94	97.27 172	99.89 45	91.92 256	99.90 85	99.07 34	88.67 286	95.26 192	99.82 46	93.17 105	99.98 43	98.15 106	99.47 102	99.90 81

DeepC-MVS_fast	96.59 1	98.81 20	98.54 24	99.62 20	99.90 42	98.85 34	99.24 231	98.47 110	98.14 8	99.08 84	99.91 14	93.09 106	100.00 1	99.04 61	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 46	98.03 53	99.17 51	99.88 49	97.59 82	99.94 66	98.44 117	94.31 123	98.50 113	99.82 46	93.06 107	99.99 36	98.30 101	99.99 21	99.93 74

testing3		93.92 199	94.23 179	92.99 306	97.54 208	90.23 293	99.99 4	99.16 30	90.57 251	91.33 238	98.63 189	92.99 108	92.52 372	82.46 332	95.39 209	96.22 245

GST-MVS		98.27 49	97.97 56	99.17 51	99.92 31	97.57 83	99.93 73	98.39 147	94.04 139	98.80 96	99.74 74	92.98 109	100.00 1	98.16 105	99.76 80	99.93 74

RE-MVS-def			98.13 48		99.79 62	96.37 128	99.76 145	98.31 166	94.43 115	99.40 68	99.75 68	92.95 110		98.90 71	99.92 63	99.97 57

CS-MVS		97.79 73	97.91 62	97.43 162	99.10 106	94.42 192	99.99 4	97.10 287	95.07 94	99.68 35	99.75 68	92.95 110	98.34 220	98.38 96	99.14 121	99.54 141

ACMMP_NAP		98.49 34	98.14 47	99.54 27	99.66 78	98.62 53	99.85 114	98.37 154	94.68 108	99.53 55	99.83 43	92.87 112	100.00 1	98.66 86	99.84 71	99.99 23

APD-MVS_3200maxsize		98.25 52	98.08 52	98.78 80	99.81 60	96.60 119	99.82 128	98.30 169	93.95 143	99.37 71	99.77 61	92.84 113	99.76 129	98.95 65	99.92 63	99.97 57

JIA-IIPM		91.76 255	90.70 255	94.94 236	96.11 261	87.51 328	93.16 373	98.13 191	75.79 372	97.58 140	77.68 386	92.84 113	97.97 243	88.47 283	96.54 183	99.33 170

Test By Simon												92.82 115

MVS_0304		98.87 18	98.61 21	99.67 16	99.18 101	99.13 22	99.87 98	99.65 12	98.17 6	98.75 102	99.75 68	92.76 116	99.94 75	99.88 18	99.44 106	99.94 72

MTAPA		98.29 48	97.96 59	99.30 42	99.85 54	97.93 73	99.39 212	98.28 171	95.76 78	97.18 149	99.88 21	92.74 117	100.00 1	98.67 84	99.88 68	99.99 23

EPNet_dtu		95.71 153	95.39 149	96.66 188	98.92 122	93.41 222	99.57 185	98.90 47	96.19 71	97.52 141	98.56 195	92.65 118	97.36 265	77.89 354	98.33 142	99.20 182
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsm_n_1920		98.44 38	98.61 21	97.92 132	99.27 100	95.18 176	100.00 1	98.90 47	98.05 10	99.80 15	99.73 76	92.64 119	99.99 36	99.58 36	99.51 100	98.59 212

MP-MVS-pluss		98.07 59	97.64 71	99.38 41	99.74 69	98.41 60	99.74 151	98.18 182	93.35 160	96.45 167	99.85 30	92.64 119	99.97 53	98.91 70	99.89 66	99.77 99
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
FE-MVS		95.70 155	95.01 163	97.79 139	98.21 165	94.57 188	95.03 365	98.69 66	88.90 281	97.50 143	96.19 273	92.60 121	99.49 156	89.99 268	97.94 157	99.31 172

DELS-MVS		98.54 30	98.22 41	99.50 30	99.15 105	98.65 51	100.00 1	98.58 83	97.70 18	98.21 127	99.24 135	92.58 122	99.94 75	98.63 89	99.94 54	99.92 79
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 63	97.80 67	98.25 119	98.14 171	96.48 121	99.98 14	97.63 229	95.61 82	99.29 77	99.46 114	92.55 123	98.82 179	99.02 64	98.54 137	99.46 153

test2506		97.53 83	97.19 88	98.58 96	98.66 140	96.90 111	98.81 279	99.77 5	94.93 97	97.95 131	98.96 159	92.51 124	99.20 164	94.93 177	98.15 148	99.64 117

KD-MVS_2432*1600		88.00 310	86.10 314	93.70 289	96.91 238	94.04 204	97.17 337	97.12 285	84.93 335	81.96 342	92.41 354	92.48 125	94.51 356	79.23 347	52.68 388	92.56 344

miper_refine_blended		88.00 310	86.10 314	93.70 289	96.91 238	94.04 204	97.17 337	97.12 285	84.93 335	81.96 342	92.41 354	92.48 125	94.51 356	79.23 347	52.68 388	92.56 344

myMVS_eth3d		94.46 187	94.76 169	93.55 293	97.68 201	90.97 275	99.71 161	98.35 157	90.79 247	92.10 229	98.67 183	92.46 127	93.09 368	87.13 299	95.95 196	96.59 240

EIA-MVS		97.53 83	97.46 77	97.76 144	98.04 176	94.84 183	99.98 14	97.61 234	94.41 118	97.90 133	99.59 102	92.40 128	98.87 177	98.04 112	99.13 122	99.59 128

F-COLMAP		96.93 107	96.95 97	96.87 181	99.71 75	91.74 261	99.85 114	97.95 205	93.11 169	95.72 185	99.16 141	92.35 129	99.94 75	95.32 170	99.35 112	98.92 195

API-MVS		97.86 65	97.66 70	98.47 106	99.52 87	95.41 165	99.47 202	98.87 52	91.68 221	98.84 94	99.85 30	92.34 130	99.99 36	98.44 94	99.96 46	100.00 1

CNLPA		97.76 75	97.38 80	98.92 76	99.53 86	96.84 112	99.87 98	98.14 190	93.78 149	96.55 165	99.69 85	92.28 131	99.98 43	97.13 142	99.44 106	99.93 74

TAMVS		95.85 148	95.58 145	96.65 189	97.07 230	93.50 218	99.17 237	97.82 220	91.39 233	95.02 194	98.01 214	92.20 132	97.30 272	93.75 211	95.83 200	99.14 187

1112_ss		96.01 144	95.20 156	98.42 111	97.80 189	96.41 124	99.65 171	96.66 327	92.71 181	92.88 219	99.40 119	92.16 133	99.30 161	91.92 235	93.66 225	99.55 137

Test_1112_low_res		95.72 151	94.83 167	98.42 111	97.79 190	96.41 124	99.65 171	96.65 328	92.70 182	92.86 220	96.13 276	92.15 134	99.30 161	91.88 236	93.64 226	99.55 137

HyFIR lowres test		96.66 121	96.43 113	97.36 168	99.05 109	93.91 209	99.70 163	99.80 3	90.54 252	96.26 173	98.08 212	92.15 134	98.23 231	96.84 153	95.46 207	99.93 74

CS-MVS-test		97.88 64	97.94 60	97.70 147	99.28 99	95.20 175	99.98 14	97.15 282	95.53 85	99.62 44	99.79 55	92.08 136	98.38 216	98.75 80	99.28 115	99.52 145

MVS_111021_LR		98.42 41	98.38 31	98.53 103	99.39 94	95.79 148	99.87 98	99.86 2	96.70 52	98.78 97	99.79 55	92.03 137	99.90 89	99.17 55	99.86 70	99.88 83

TAPA-MVS	92.12 8	94.42 188	93.60 195	96.90 180	99.33 97	91.78 260	99.78 137	98.00 199	89.89 264	94.52 198	99.47 112	91.97 138	99.18 166	69.90 371	99.52 98	99.73 103
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PatchT		90.38 280	88.75 296	95.25 227	95.99 265	90.16 295	91.22 381	97.54 242	76.80 368	97.26 147	86.01 380	91.88 139	96.07 335	66.16 379	95.91 198	99.51 147

HPM-MVS		97.96 60	97.72 68	98.68 86	99.84 56	96.39 127	99.90 85	98.17 183	92.61 188	98.62 108	99.57 105	91.87 140	99.67 143	98.87 73	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 54	97.97 56	99.03 66	99.94 13	97.17 102	99.95 50	98.39 147	94.70 107	98.26 125	99.81 50	91.84 141	100.00 1	98.85 74	99.97 42	99.93 74
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		97.80 71	97.50 76	98.68 86	99.79 62	96.42 123	99.88 95	98.16 187	91.75 220	98.94 90	99.54 108	91.82 142	99.65 145	97.62 133	99.99 21	99.99 23

tpmvs		94.28 194	93.57 197	96.40 196	98.55 145	91.50 270	95.70 364	98.55 93	87.47 302	92.15 228	94.26 339	91.42 143	98.95 175	88.15 286	95.85 199	98.76 204

ACMMP		97.74 76	97.44 78	98.66 88	99.92 31	96.13 140	99.18 236	99.45 19	94.84 102	96.41 170	99.71 81	91.40 144	99.99 36	97.99 115	98.03 155	99.87 85
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)		96.32 134	95.98 125	97.35 169	97.93 181	94.82 184	99.47 202	98.15 189	91.83 216	95.09 193	99.11 142	91.37 145	97.47 263	93.47 215	97.43 164	99.74 102

sss		97.57 82	97.03 95	99.18 48	98.37 155	98.04 67	99.73 156	99.38 23	93.46 158	98.76 100	99.06 146	91.21 146	99.89 94	96.33 157	97.01 177	99.62 122

pcd_1.5k_mvsjas		7.60 367	10.13 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 401	91.20 147	0.00 401	0.00 400	0.00 399	0.00 397

PS-MVSNAJss		93.64 210	93.31 207	94.61 248	92.11 345	92.19 249	99.12 239	97.38 259	92.51 196	88.45 288	96.99 249	91.20 147	97.29 275	94.36 193	87.71 272	94.36 267

PS-MVSNAJ		98.44 38	98.20 43	99.16 53	98.80 133	98.92 28	99.54 191	98.17 183	97.34 27	99.85 7	99.85 30	91.20 147	99.89 94	99.41 46	99.67 85	98.69 209

CPTT-MVS		97.64 81	97.32 84	98.58 96	99.97 3	95.77 149	99.96 32	98.35 157	89.90 263	98.36 119	99.79 55	91.18 150	99.99 36	98.37 97	99.99 21	99.99 23

test_fmvsmconf_n		98.43 40	98.32 37	98.78 80	98.12 173	96.41 124	99.99 4	98.83 57	98.22 4	99.67 36	99.64 97	91.11 151	99.94 75	99.67 34	99.62 88	99.98 48

CR-MVSNet		93.45 216	92.62 220	95.94 207	96.29 256	92.66 239	92.01 377	96.23 340	92.62 187	96.94 153	93.31 348	91.04 152	96.03 336	79.23 347	95.96 194	99.13 188

Patchmtry		89.70 296	88.49 299	93.33 297	96.24 259	89.94 303	91.37 380	96.23 340	78.22 366	87.69 299	93.31 348	91.04 152	96.03 336	80.18 346	82.10 311	94.02 298

miper_ehance_all_eth		93.16 220	92.60 221	94.82 242	97.57 207	93.56 216	99.50 197	97.07 291	88.75 284	88.85 283	95.52 295	90.97 154	96.74 308	90.77 254	84.45 296	94.17 281

mvsany_test1		97.82 69	97.90 63	97.55 155	98.77 135	93.04 230	99.80 134	97.93 207	96.95 43	99.61 50	99.68 91	90.92 155	99.83 116	99.18 54	98.29 146	99.80 94

MVSFormer		96.94 106	96.60 107	97.95 130	97.28 226	97.70 79	99.55 189	97.27 271	91.17 236	99.43 64	99.54 108	90.92 155	96.89 301	94.67 188	99.62 88	99.25 179

lupinMVS		97.85 66	97.60 73	98.62 91	97.28 226	97.70 79	99.99 4	97.55 240	95.50 87	99.43 64	99.67 92	90.92 155	98.71 189	98.40 95	99.62 88	99.45 155

h-mvs33		94.92 171	94.36 175	96.59 190	98.85 130	91.29 272	98.93 265	98.94 41	95.90 74	98.77 98	98.42 206	90.89 158	99.77 126	97.80 123	70.76 365	98.72 208

hse-mvs2		94.38 189	94.08 183	95.31 225	98.27 161	90.02 299	99.29 227	98.56 87	95.90 74	98.77 98	98.00 215	90.89 158	98.26 230	97.80 123	69.20 371	97.64 229

xiu_mvs_v2_base		98.23 54	97.97 56	99.02 68	98.69 138	98.66 49	99.52 193	98.08 194	97.05 39	99.86 5	99.86 26	90.65 160	99.71 136	99.39 48	98.63 136	98.69 209

IS-MVSNet		96.29 137	95.90 136	97.45 160	98.13 172	94.80 185	99.08 244	97.61 234	92.02 212	95.54 188	98.96 159	90.64 161	98.08 237	93.73 212	97.41 167	99.47 152

FA-MVS(test-final)		95.86 147	95.09 160	98.15 124	97.74 193	95.62 157	96.31 353	98.17 183	91.42 231	96.26 173	96.13 276	90.56 162	99.47 158	92.18 232	97.07 173	99.35 167

cl22		93.77 205	93.25 209	95.33 224	99.49 90	94.43 191	99.61 179	98.09 192	90.38 254	89.16 278	95.61 289	90.56 162	97.34 267	91.93 234	84.45 296	94.21 279

MM				99.76 10		99.33 8	99.99 4	99.76 6	98.39 3	99.39 70	99.80 51	90.49 164	99.96 59	99.89 16	99.43 108	99.98 48

tpm		93.70 209	93.41 204	94.58 251	95.36 289	87.41 329	97.01 341	96.90 311	90.85 245	96.72 161	94.14 340	90.40 165	96.84 304	90.75 255	88.54 258	99.51 147

114514_t		97.41 90	96.83 100	99.14 57	99.51 89	97.83 74	99.89 93	98.27 173	88.48 290	99.06 85	99.66 94	90.30 166	99.64 146	96.32 158	99.97 42	99.96 63

ADS-MVSNet2		93.80 204	93.88 189	93.55 293	97.87 184	85.94 337	94.24 366	96.84 316	90.07 260	96.43 168	94.48 335	90.29 167	95.37 345	87.44 293	97.23 169	99.36 165

ADS-MVSNet		94.79 174	94.02 184	97.11 176	97.87 184	93.79 210	94.24 366	98.16 187	90.07 260	96.43 168	94.48 335	90.29 167	98.19 233	87.44 293	97.23 169	99.36 165

miper_lstm_enhance		91.81 249	91.39 248	93.06 305	97.34 220	89.18 310	99.38 213	96.79 321	86.70 315	87.47 304	95.22 313	90.00 169	95.86 340	88.26 284	81.37 317	94.15 287

c3_l		92.53 236	91.87 238	94.52 254	97.40 216	92.99 231	99.40 208	96.93 309	87.86 298	88.69 286	95.44 299	89.95 170	96.44 319	90.45 260	80.69 327	94.14 290

thres200		96.96 105	96.21 118	99.22 44	98.97 116	98.84 35	99.85 114	99.71 7	93.17 167	96.26 173	98.88 170	89.87 171	99.51 150	94.26 196	94.91 214	99.31 172

tpm cat1		93.51 213	92.52 226	96.47 191	97.77 191	91.47 271	96.13 356	98.06 195	80.98 358	92.91 218	93.78 343	89.66 172	98.87 177	87.03 302	96.39 187	99.09 190

test_fmvsmvis_n_1920		97.67 80	97.59 75	97.91 134	97.02 233	95.34 167	99.95 50	98.45 113	97.87 13	97.02 152	99.59 102	89.64 173	99.98 43	99.41 46	99.34 113	98.42 214

OMC-MVS		97.28 94	97.23 86	97.41 163	99.76 66	93.36 225	99.65 171	97.95 205	96.03 73	97.41 145	99.70 83	89.61 174	99.51 150	96.73 154	98.25 147	99.38 162

DIV-MVS_self_test		92.32 240	91.60 241	94.47 258	97.31 223	92.74 235	99.58 183	96.75 323	86.99 311	87.64 300	95.54 293	89.55 175	96.50 317	88.58 280	82.44 309	94.17 281

cl____		92.31 241	91.58 242	94.52 254	97.33 222	92.77 233	99.57 185	96.78 322	86.97 312	87.56 302	95.51 296	89.43 176	96.62 313	88.60 279	82.44 309	94.16 286

AUN-MVS		93.28 217	92.60 221	95.34 223	98.29 158	90.09 297	99.31 222	98.56 87	91.80 219	96.35 172	98.00 215	89.38 177	98.28 226	92.46 228	69.22 370	97.64 229

tfpn200view9		96.79 112	95.99 123	99.19 47	98.94 118	98.82 36	99.78 137	99.71 7	92.86 172	96.02 178	98.87 173	89.33 178	99.50 152	93.84 204	94.57 215	99.27 177

thres400		96.78 113	95.99 123	99.16 53	98.94 118	98.82 36	99.78 137	99.71 7	92.86 172	96.02 178	98.87 173	89.33 178	99.50 152	93.84 204	94.57 215	99.16 184

thres100view900		96.74 116	95.92 135	99.18 48	98.90 127	98.77 40	99.74 151	99.71 7	92.59 190	95.84 181	98.86 175	89.25 180	99.50 152	93.84 204	94.57 215	99.27 177

thres600view7		96.69 119	95.87 138	99.14 57	98.90 127	98.78 39	99.74 151	99.71 7	92.59 190	95.84 181	98.86 175	89.25 180	99.50 152	93.44 216	94.50 218	99.16 184

eth_miper_zixun_eth		92.41 239	91.93 236	93.84 283	97.28 226	90.68 283	98.83 277	96.97 303	88.57 289	89.19 277	95.73 286	89.24 182	96.69 311	89.97 269	81.55 315	94.15 287

EC-MVSNet		97.38 92	97.24 85	97.80 137	97.41 215	95.64 156	99.99 4	97.06 292	94.59 110	99.63 41	99.32 126	89.20 183	98.14 234	98.76 79	99.23 118	99.62 122

PVSNet_Blended_VisFu		97.27 95	96.81 101	98.66 88	98.81 132	96.67 116	99.92 76	98.64 74	94.51 112	96.38 171	98.49 199	89.05 184	99.88 100	97.10 144	98.34 141	99.43 158

PVSNet_BlendedMVS		96.05 142	95.82 139	96.72 186	99.59 81	96.99 107	99.95 50	99.10 31	94.06 136	98.27 123	95.80 282	89.00 185	99.95 67	99.12 56	87.53 275	93.24 334

PVSNet_Blended		97.94 61	97.64 71	98.83 79	99.59 81	96.99 107	100.00 1	99.10 31	95.38 88	98.27 123	99.08 144	89.00 185	99.95 67	99.12 56	99.25 116	99.57 135

IterMVS-LS		92.69 233	92.11 231	94.43 262	96.80 246	92.74 235	99.45 205	96.89 312	88.98 276	89.65 263	95.38 304	88.77 187	96.34 323	90.98 249	82.04 312	94.22 277
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		93.73 207	93.40 205	94.74 243	96.80 246	92.69 238	99.06 249	97.67 227	88.96 278	91.39 235	99.02 148	88.75 188	97.30 272	91.07 245	87.85 269	94.22 277

UA-Net		96.54 124	95.96 129	98.27 118	98.23 163	95.71 153	98.00 323	98.45 113	93.72 152	98.41 116	99.27 130	88.71 189	99.66 144	91.19 243	97.69 159	99.44 157

MAR-MVS		97.43 85	97.19 88	98.15 124	99.47 91	94.79 186	99.05 253	98.76 61	92.65 186	98.66 106	99.82 46	88.52 190	99.98 43	98.12 107	99.63 87	99.67 111
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
mvs_anonymous		95.65 157	95.03 162	97.53 156	98.19 167	95.74 151	99.33 219	97.49 249	90.87 244	90.47 246	97.10 242	88.23 191	97.16 280	95.92 164	97.66 161	99.68 109

MVS_Test		96.46 127	95.74 140	98.61 92	98.18 168	97.23 97	99.31 222	97.15 282	91.07 240	98.84 94	97.05 246	88.17 192	98.97 173	94.39 192	97.50 163	99.61 125

CANet		98.27 49	97.82 66	99.63 17	99.72 74	99.10 23	99.98 14	98.51 102	97.00 41	98.52 111	99.71 81	87.80 193	99.95 67	99.75 26	99.38 110	99.83 89

jason		97.24 96	96.86 99	98.38 114	95.73 277	97.32 95	99.97 25	97.40 258	95.34 90	98.60 110	99.54 108	87.70 194	98.56 197	97.94 118	99.47 102	99.25 179
jason: jason.
test_fmvsmconf0.1_n		97.74 76	97.44 78	98.64 90	95.76 274	96.20 136	99.94 66	98.05 197	98.17 6	98.89 93	99.42 116	87.65 195	99.90 89	99.50 39	99.60 94	99.82 90

FIs		94.10 196	93.43 201	96.11 204	94.70 298	96.82 113	99.58 183	98.93 45	92.54 193	89.34 270	97.31 236	87.62 196	97.10 286	94.22 198	86.58 280	94.40 263

1314		96.84 110	95.96 129	99.48 34	96.74 250	98.52 56	98.31 309	98.86 53	95.82 76	89.91 254	98.98 155	87.49 197	99.96 59	97.80 123	99.73 82	99.96 63

LS3D		95.84 149	95.11 159	98.02 129	99.85 54	95.10 178	98.74 284	98.50 107	87.22 307	93.66 209	99.86 26	87.45 198	99.95 67	90.94 250	99.81 78	99.02 193

FC-MVSNet-test		93.81 203	93.15 210	95.80 212	94.30 305	96.20 136	99.42 207	98.89 49	92.33 203	89.03 280	97.27 238	87.39 199	96.83 305	93.20 218	86.48 281	94.36 267

fmvsm_s_conf0.5_n		97.80 71	97.85 65	97.67 148	99.06 108	94.41 193	99.98 14	98.97 40	97.34 27	99.63 41	99.69 85	87.27 200	99.97 53	99.62 35	99.06 125	98.62 211

RPMNet		89.76 295	87.28 310	97.19 173	96.29 256	92.66 239	92.01 377	98.31 166	70.19 382	96.94 153	85.87 381	87.25 201	99.78 123	62.69 383	95.96 194	99.13 188

UniMVSNet_NR-MVSNet		92.95 226	92.11 231	95.49 216	94.61 300	95.28 170	99.83 125	99.08 33	91.49 225	89.21 275	96.86 253	87.14 202	96.73 309	93.20 218	77.52 346	94.46 256

UniMVSNet (Re)		93.07 224	92.13 230	95.88 208	94.84 295	96.24 135	99.88 95	98.98 38	92.49 197	89.25 272	95.40 301	87.09 203	97.14 282	93.13 222	78.16 341	94.26 274

DP-MVS		94.54 183	93.42 202	97.91 134	99.46 93	94.04 204	98.93 265	97.48 250	81.15 357	90.04 251	99.55 106	87.02 204	99.95 67	88.97 276	98.11 151	99.73 103

fmvsm_s_conf0.5_n_a		97.73 78	97.72 68	97.77 142	98.63 142	94.26 198	99.96 32	98.92 46	97.18 37	99.75 27	99.69 85	87.00 205	99.97 53	99.46 42	98.89 128	99.08 192

PMMVS		96.76 114	96.76 103	96.76 184	98.28 160	92.10 251	99.91 80	97.98 202	94.12 131	99.53 55	99.39 121	86.93 206	98.73 186	96.95 150	97.73 158	99.45 155

canonicalmvs		97.09 102	96.32 115	99.39 40	98.93 120	98.95 27	99.72 159	97.35 261	94.45 113	97.88 135	99.42 116	86.71 207	99.52 149	98.48 93	93.97 224	99.72 105

MVS		96.60 122	95.56 146	99.72 13	96.85 243	99.22 20	98.31 309	98.94 41	91.57 223	90.90 242	99.61 101	86.66 208	99.96 59	97.36 136	99.88 68	99.99 23

Effi-MVS+		96.30 136	95.69 142	98.16 121	97.85 186	96.26 131	97.41 332	97.21 275	90.37 255	98.65 107	98.58 193	86.61 209	98.70 190	97.11 143	97.37 168	99.52 145

diffmvs		97.00 104	96.64 106	98.09 126	97.64 204	96.17 139	99.81 130	97.19 276	94.67 109	98.95 89	99.28 127	86.43 210	98.76 184	98.37 97	97.42 166	99.33 170
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		93.51 213	92.53 225	96.45 193	94.36 303	97.20 98	99.81 130	97.16 281	91.60 222	89.86 256	97.46 231	86.37 211	97.68 256	95.88 165	80.31 330	94.46 256

mvsmamba		94.10 196	93.72 192	95.25 227	93.57 316	94.13 202	99.67 168	96.45 336	93.63 155	91.34 237	97.77 225	86.29 212	97.22 278	96.65 155	88.10 266	94.40 263

VNet		97.21 98	96.57 109	99.13 61	98.97 116	97.82 75	99.03 256	99.21 29	94.31 123	99.18 82	98.88 170	86.26 213	99.89 94	98.93 67	94.32 219	99.69 108

AdaColmap		97.23 97	96.80 102	98.51 104	99.99 1	95.60 158	99.09 242	98.84 56	93.32 162	96.74 160	99.72 79	86.04 214	100.00 1	98.01 113	99.43 108	99.94 72

Effi-MVS+-dtu		94.53 185	95.30 153	92.22 314	97.77 191	82.54 354	99.59 181	97.06 292	94.92 99	95.29 191	95.37 305	85.81 215	97.89 249	94.80 183	97.07 173	96.23 244

CVMVSNet		94.68 180	94.94 165	93.89 282	96.80 246	86.92 333	99.06 249	98.98 38	94.45 113	94.23 204	99.02 148	85.60 216	95.31 347	90.91 251	95.39 209	99.43 158

xiu_mvs_v1_base_debu		97.43 85	97.06 91	98.55 98	97.74 193	98.14 62	99.31 222	97.86 216	96.43 60	99.62 44	99.69 85	85.56 217	99.68 140	99.05 58	98.31 143	97.83 224

xiu_mvs_v1_base		97.43 85	97.06 91	98.55 98	97.74 193	98.14 62	99.31 222	97.86 216	96.43 60	99.62 44	99.69 85	85.56 217	99.68 140	99.05 58	98.31 143	97.83 224

xiu_mvs_v1_base_debi		97.43 85	97.06 91	98.55 98	97.74 193	98.14 62	99.31 222	97.86 216	96.43 60	99.62 44	99.69 85	85.56 217	99.68 140	99.05 58	98.31 143	97.83 224

casdiffmvs_mvg		96.43 128	95.94 132	97.89 136	97.44 214	95.47 161	99.86 111	97.29 269	93.35 160	96.03 177	99.19 138	85.39 220	98.72 188	97.89 122	97.04 175	99.49 151
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		96.43 128	95.98 125	97.76 144	97.34 220	95.17 177	99.51 195	97.17 279	93.92 145	96.90 155	99.28 127	85.37 221	98.64 194	97.50 134	96.86 181	99.46 153

PCF-MVS	94.20 5	95.18 165	94.10 182	98.43 110	98.55 145	95.99 143	97.91 325	97.31 266	90.35 256	89.48 267	99.22 136	85.19 222	99.89 94	90.40 263	98.47 139	99.41 160
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs		96.42 130	95.97 128	97.77 142	97.30 224	94.98 179	99.84 118	97.09 289	93.75 151	96.58 164	99.26 133	85.07 223	98.78 182	97.77 128	97.04 175	99.54 141
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		92.76 229	92.59 224	93.27 299	95.13 290	89.54 307	99.69 164	99.38 23	92.26 204	87.59 301	94.61 332	85.05 224	97.79 252	91.59 239	88.01 267	92.47 347

fmvsm_s_conf0.1_n		97.30 93	97.21 87	97.60 154	97.38 217	94.40 195	99.90 85	98.64 74	96.47 59	99.51 59	99.65 96	84.99 225	99.93 83	99.22 53	99.09 124	98.46 213

fmvsm_s_conf0.1_n_a		97.09 102	96.90 98	97.63 152	95.65 283	94.21 200	99.83 125	98.50 107	96.27 68	99.65 38	99.64 97	84.72 226	99.93 83	99.04 61	98.84 131	98.74 206

BH-w/o		95.71 153	95.38 150	96.68 187	98.49 150	92.28 247	99.84 118	97.50 248	92.12 207	92.06 231	98.79 179	84.69 227	98.67 193	95.29 171	99.66 86	99.09 190

Fast-Effi-MVS+		95.02 169	94.19 180	97.52 157	97.88 183	94.55 189	99.97 25	97.08 290	88.85 283	94.47 200	97.96 220	84.59 228	98.41 208	89.84 270	97.10 172	99.59 128

PVSNet	91.05 13	97.13 99	96.69 105	98.45 108	99.52 87	95.81 147	99.95 50	99.65 12	94.73 105	99.04 86	99.21 137	84.48 229	99.95 67	94.92 178	98.74 134	99.58 134

RRT_MVS		93.14 221	92.92 214	93.78 284	93.31 323	90.04 298	99.66 169	97.69 225	92.53 194	88.91 282	97.76 226	84.36 230	96.93 299	95.10 173	86.99 278	94.37 266

WR-MVS_H		91.30 258	90.35 262	94.15 268	94.17 307	92.62 242	99.17 237	98.94 41	88.87 282	86.48 318	94.46 337	84.36 230	96.61 314	88.19 285	78.51 339	93.21 335

CHOSEN 1792x2688		96.81 111	96.53 110	97.64 150	98.91 126	93.07 227	99.65 171	99.80 3	95.64 81	95.39 189	98.86 175	84.35 232	99.90 89	96.98 148	99.16 120	99.95 70

our_test_3		90.39 279	89.48 284	93.12 302	92.40 341	89.57 306	99.33 219	96.35 339	87.84 299	85.30 328	94.99 321	84.14 233	96.09 334	80.38 343	84.56 295	93.71 324

MSDG		94.37 190	93.36 206	97.40 164	98.88 129	93.95 208	99.37 215	97.38 259	85.75 327	90.80 243	99.17 140	84.11 234	99.88 100	86.35 307	98.43 140	98.36 216

pmmvs4		92.10 245	91.07 252	95.18 229	92.82 336	94.96 180	99.48 201	96.83 317	87.45 303	88.66 287	96.56 265	83.78 235	96.83 305	89.29 273	84.77 294	93.75 319

BH-untuned		95.18 165	94.83 167	96.22 202	98.36 156	91.22 273	99.80 134	97.32 265	90.91 243	91.08 239	98.67 183	83.51 236	98.54 199	94.23 197	99.61 92	98.92 195

LCM-MVSNet-Re		92.31 241	92.60 221	91.43 321	97.53 209	79.27 371	99.02 257	91.83 385	92.07 208	80.31 351	94.38 338	83.50 237	95.48 343	97.22 141	97.58 162	99.54 141

cdsmvs_eth3d_5k		23.43 364	31.24 367	0.00 382	0.00 404	0.00 407	0.00 393	98.09 192	0.00 400	0.00 401	99.67 92	83.37 238	0.00 401	0.00 400	0.00 399	0.00 397

DeepC-MVS	94.51 4	96.92 108	96.40 114	98.45 108	99.16 104	95.90 145	99.66 169	98.06 195	96.37 66	94.37 201	99.49 111	83.29 239	99.90 89	97.63 132	99.61 92	99.55 137
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NR-MVSNet		91.56 257	90.22 266	95.60 214	94.05 308	95.76 150	98.25 311	98.70 65	91.16 238	80.78 350	96.64 261	83.23 240	96.57 315	91.41 240	77.73 345	94.46 256

3Dnovator+	91.53 11	96.31 135	95.24 154	99.52 28	96.88 242	98.64 52	99.72 159	98.24 175	95.27 92	88.42 293	98.98 155	82.76 241	99.94 75	97.10 144	99.83 72	99.96 63

QAPM		95.40 162	94.17 181	99.10 62	96.92 237	97.71 77	99.40 208	98.68 68	89.31 269	88.94 281	98.89 169	82.48 242	99.96 59	93.12 223	99.83 72	99.62 122

PatchMatch-RL		96.04 143	95.40 148	97.95 130	99.59 81	95.22 174	99.52 193	99.07 34	93.96 142	96.49 166	98.35 207	82.28 243	99.82 118	90.15 266	99.22 119	98.81 202

GeoE		94.36 192	93.48 200	96.99 177	97.29 225	93.54 217	99.96 32	96.72 325	88.35 293	93.43 210	98.94 166	82.05 244	98.05 240	88.12 288	96.48 186	99.37 164

3Dnovator	91.47 12	96.28 138	95.34 151	99.08 63	96.82 245	97.47 91	99.45 205	98.81 58	95.52 86	89.39 268	99.00 152	81.97 245	99.95 67	97.27 138	99.83 72	99.84 88

v8		90.54 277	89.17 287	94.66 246	93.43 320	93.40 223	99.20 234	96.94 308	85.76 325	87.56 302	94.51 333	81.96 246	97.19 279	84.94 318	78.25 340	93.38 331

v148		90.70 272	89.63 277	93.92 279	92.97 332	90.97 275	99.75 148	96.89 312	87.51 301	88.27 294	95.01 318	81.67 247	97.04 291	87.40 295	77.17 351	93.75 319

DU-MVS		92.46 238	91.45 247	95.49 216	94.05 308	95.28 170	99.81 130	98.74 62	92.25 205	89.21 275	96.64 261	81.66 248	96.73 309	93.20 218	77.52 346	94.46 256

Baseline_NR-MVSNet		90.33 282	89.51 282	92.81 309	92.84 334	89.95 301	99.77 140	93.94 376	84.69 339	89.04 279	95.66 288	81.66 248	96.52 316	90.99 248	76.98 352	91.97 353

FMVSNet3		92.69 233	91.58 242	95.99 206	98.29 158	97.42 93	99.26 230	97.62 231	89.80 265	89.68 260	95.32 307	81.62 250	96.27 326	87.01 303	85.65 285	94.29 273

Fast-Effi-MVS+-dtu		93.72 208	93.86 190	93.29 298	97.06 231	86.16 335	99.80 134	96.83 317	92.66 185	92.58 223	97.83 224	81.39 251	97.67 257	89.75 271	96.87 180	96.05 247

CANet_DTU		96.76 114	96.15 119	98.60 93	98.78 134	97.53 84	99.84 118	97.63 229	97.25 35	99.20 79	99.64 97	81.36 252	99.98 43	92.77 227	98.89 128	98.28 217

V42		91.28 260	90.12 271	94.74 243	93.42 321	93.46 219	99.68 166	97.02 296	87.36 304	89.85 258	95.05 316	81.31 253	97.34 267	87.34 296	80.07 332	93.40 329

test_djsdf		92.83 228	92.29 229	94.47 258	91.90 348	92.46 244	99.55 189	97.27 271	91.17 236	89.96 252	96.07 279	81.10 254	96.89 301	94.67 188	88.91 248	94.05 297

ppachtmachnet_test		89.58 298	88.35 301	93.25 300	92.40 341	90.44 290	99.33 219	96.73 324	85.49 330	85.90 326	95.77 283	81.09 255	96.00 338	76.00 362	82.49 308	93.30 332

v1144		91.09 264	89.83 273	94.87 238	93.25 324	93.69 214	99.62 178	96.98 301	86.83 314	89.64 264	94.99 321	80.94 256	97.05 289	85.08 317	81.16 319	93.87 313

v10		90.25 285	88.82 294	94.57 252	93.53 318	93.43 221	99.08 244	96.87 314	85.00 334	87.34 308	94.51 333	80.93 257	97.02 296	82.85 330	79.23 335	93.26 333

EU-MVSNet		90.14 289	90.34 263	89.54 336	92.55 339	81.06 365	98.69 290	98.04 198	91.41 232	86.59 315	96.84 256	80.83 258	93.31 367	86.20 308	81.91 313	94.26 274

v2v482		91.30 258	90.07 272	95.01 233	93.13 325	93.79 210	99.77 140	97.02 296	88.05 296	89.25 272	95.37 305	80.73 259	97.15 281	87.28 297	80.04 333	94.09 294

WR-MVS		92.31 241	91.25 249	95.48 219	94.45 302	95.29 169	99.60 180	98.68 68	90.10 259	88.07 296	96.89 251	80.68 260	96.80 307	93.14 221	79.67 334	94.36 267

HQP2-MVS												80.65 261

HQP-MVS		94.61 182	94.50 173	94.92 237	95.78 270	91.85 257	99.87 98	97.89 212	96.82 46	93.37 211	98.65 186	80.65 261	98.39 212	97.92 119	89.60 239	94.53 250

XVG-OURS		94.82 172	94.74 170	95.06 232	98.00 177	89.19 308	99.08 244	97.55 240	94.10 132	94.71 196	99.62 100	80.51 263	99.74 132	96.04 162	93.06 233	96.25 242

v144192		90.79 271	89.52 281	94.59 250	93.11 328	92.77 233	99.56 187	96.99 299	86.38 318	89.82 259	94.95 323	80.50 264	97.10 286	83.98 323	80.41 328	93.90 310

HQP_MVS		94.49 186	94.36 175	94.87 238	95.71 280	91.74 261	99.84 118	97.87 214	96.38 63	93.01 215	98.59 191	80.47 265	98.37 218	97.79 126	89.55 242	94.52 252

plane_prior6					95.76 274	91.72 264						80.47 265

v7n		89.65 297	88.29 302	93.72 286	92.22 343	90.56 287	99.07 248	97.10 287	85.42 332	86.73 312	94.72 326	80.06 267	97.13 283	81.14 340	78.12 342	93.49 327

TranMVSNet+NR-MVSNet		91.68 256	90.61 258	94.87 238	93.69 315	93.98 207	99.69 164	98.65 72	91.03 241	88.44 289	96.83 257	80.05 268	96.18 329	90.26 265	76.89 354	94.45 261

FMVSNet5		88.32 307	87.47 309	90.88 324	96.90 241	88.39 321	97.28 334	95.68 351	82.60 352	84.67 331	92.40 356	79.83 269	91.16 377	76.39 361	81.51 316	93.09 336

test_fmvsmconf0.01_n		96.39 131	95.74 140	98.32 116	91.47 354	95.56 159	99.84 118	97.30 267	97.74 16	97.89 134	99.35 125	79.62 270	99.85 106	99.25 52	99.24 117	99.55 137

RPSCF		91.80 252	92.79 218	88.83 341	98.15 170	69.87 379	98.11 319	96.60 330	83.93 342	94.33 202	99.27 130	79.60 271	99.46 159	91.99 233	93.16 231	97.18 236

Vis-MVSNet		95.72 151	95.15 158	97.45 160	97.62 205	94.28 197	99.28 228	98.24 175	94.27 127	96.84 157	98.94 166	79.39 272	98.76 184	93.25 217	98.49 138	99.30 174
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dmvs_testset		83.79 332	86.07 316	76.94 363	92.14 344	48.60 398	96.75 346	90.27 388	89.48 267	78.65 358	98.55 197	79.25 273	86.65 386	66.85 377	82.69 306	95.57 248

v1192		90.62 276	89.25 286	94.72 245	93.13 325	93.07 227	99.50 197	97.02 296	86.33 319	89.56 266	95.01 318	79.22 274	97.09 288	82.34 334	81.16 319	94.01 300

CP-MVSNet		91.23 262	90.22 266	94.26 266	93.96 310	92.39 246	99.09 242	98.57 85	88.95 279	86.42 319	96.57 264	79.19 275	96.37 321	90.29 264	78.95 336	94.02 298

MDA-MVSNet_test_wron		85.51 321	83.32 329	92.10 315	90.96 358	88.58 318	99.20 234	96.52 333	79.70 363	57.12 388	92.69 352	79.11 276	93.86 362	77.10 358	77.46 348	93.86 314

Syy-MVS		90.00 291	90.63 257	88.11 348	97.68 201	74.66 376	99.71 161	98.35 157	90.79 247	92.10 229	98.67 183	79.10 277	93.09 368	63.35 382	95.95 196	96.59 240

YYNet1		85.50 322	83.33 328	92.00 316	90.89 359	88.38 322	99.22 233	96.55 332	79.60 364	57.26 387	92.72 351	79.09 278	93.78 363	77.25 357	77.37 349	93.84 315

XVG-OURS-SEG-HR		94.79 174	94.70 171	95.08 231	98.05 175	89.19 308	99.08 244	97.54 242	93.66 153	94.87 195	99.58 104	78.78 279	99.79 121	97.31 137	93.40 228	96.25 242

GA-MVS		93.83 201	92.84 215	96.80 182	95.73 277	93.57 215	99.88 95	97.24 274	92.57 192	92.92 217	96.66 259	78.73 280	97.67 257	87.75 291	94.06 223	99.17 183

dmvs_re		93.20 219	93.15 210	93.34 296	96.54 254	83.81 348	98.71 287	98.51 102	91.39 233	92.37 227	98.56 195	78.66 281	97.83 251	93.89 202	89.74 238	98.38 215

OpenMVS	90.15 15	94.77 176	93.59 196	98.33 115	96.07 262	97.48 90	99.56 187	98.57 85	90.46 253	86.51 316	98.95 164	78.57 282	99.94 75	93.86 203	99.74 81	97.57 233

v1921920		90.46 278	89.12 288	94.50 256	92.96 333	92.46 244	99.49 199	96.98 301	86.10 321	89.61 265	95.30 308	78.55 283	97.03 294	82.17 335	80.89 326	94.01 300

MVP-Stereo		90.93 266	90.45 261	92.37 313	91.25 357	88.76 312	98.05 322	96.17 342	87.27 306	84.04 333	95.30 308	78.46 284	97.27 277	83.78 325	99.70 84	91.09 358
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
anonymousdsp		91.79 254	90.92 253	94.41 263	90.76 360	92.93 232	98.93 265	97.17 279	89.08 271	87.46 305	95.30 308	78.43 285	96.92 300	92.38 229	88.73 253	93.39 330

bld_raw_dy_0_64		92.74 230	92.03 234	94.87 238	93.09 329	93.46 219	99.12 239	95.41 357	92.84 175	90.44 247	97.54 229	78.08 286	97.04 291	93.94 200	87.77 271	94.11 292

v1240		90.20 286	88.79 295	94.44 260	93.05 331	92.27 248	99.38 213	96.92 310	85.89 323	89.36 269	94.87 325	77.89 287	97.03 294	80.66 342	81.08 322	94.01 300

CLD-MVS		94.06 198	93.90 188	94.55 253	96.02 264	90.69 282	99.98 14	97.72 223	96.62 56	91.05 241	98.85 178	77.21 288	98.47 201	98.11 108	89.51 244	94.48 254
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		96.59 123	96.23 117	97.65 149	98.22 164	94.23 199	99.99 4	97.25 273	97.77 15	99.58 51	99.08 144	77.10 289	99.97 53	97.64 131	99.45 105	98.74 206

N_pmnet		80.06 342	80.78 340	77.89 362	91.94 347	45.28 400	98.80 281	56.82 402	78.10 367	80.08 353	93.33 346	77.03 290	95.76 341	68.14 375	82.81 305	92.64 343

WB-MVS		76.28 346	77.28 348	73.29 367	81.18 383	54.68 392	97.87 326	94.19 372	81.30 356	69.43 379	90.70 364	77.02 291	82.06 390	35.71 395	68.11 374	83.13 381

COLMAP_ROB	90.47 14	92.18 244	91.49 246	94.25 267	99.00 113	88.04 325	98.42 306	96.70 326	82.30 353	88.43 291	99.01 150	76.97 292	99.85 106	86.11 310	96.50 185	94.86 249
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
cascas		94.64 181	93.61 193	97.74 146	97.82 188	96.26 131	99.96 32	97.78 222	85.76 325	94.00 206	97.54 229	76.95 293	99.21 163	97.23 140	95.43 208	97.76 228

BH-RMVSNet		95.18 165	94.31 178	97.80 137	98.17 169	95.23 173	99.76 145	97.53 244	92.52 195	94.27 203	99.25 134	76.84 294	98.80 180	90.89 252	99.54 97	99.35 167

PEN-MVS		90.19 287	89.06 290	93.57 292	93.06 330	90.90 279	99.06 249	98.47 110	88.11 295	85.91 325	96.30 270	76.67 295	95.94 339	87.07 300	76.91 353	93.89 311

CL-MVSNet_self_test		84.50 328	83.15 331	88.53 345	86.00 375	81.79 360	98.82 278	97.35 261	85.12 333	83.62 337	90.91 363	76.66 296	91.40 376	69.53 372	60.36 385	92.40 348

IterMVS		90.91 267	90.17 269	93.12 302	96.78 249	90.42 291	98.89 268	97.05 294	89.03 273	86.49 317	95.42 300	76.59 297	95.02 349	87.22 298	84.09 299	93.93 308
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SSC-MVS		75.42 347	76.40 350	72.49 371	80.68 385	53.62 393	97.42 331	94.06 374	80.42 360	68.75 380	90.14 366	76.54 298	81.66 391	33.25 396	66.34 378	82.19 382

IterMVS-SCA-FT		90.85 270	90.16 270	92.93 307	96.72 251	89.96 300	98.89 268	96.99 299	88.95 279	86.63 314	95.67 287	76.48 299	95.00 350	87.04 301	84.04 302	93.84 315

SCA		94.69 178	93.81 191	97.33 170	97.10 229	94.44 190	98.86 274	98.32 164	93.30 163	96.17 176	95.59 291	76.48 299	97.95 246	91.06 246	97.43 164	99.59 128

ab-mvs		94.69 178	93.42 202	98.51 104	98.07 174	96.26 131	96.49 349	98.68 68	90.31 257	94.54 197	97.00 248	76.30 301	99.71 136	95.98 163	93.38 229	99.56 136

DTE-MVSNet		89.40 300	88.24 303	92.88 308	92.66 338	89.95 301	99.10 241	98.22 177	87.29 305	85.12 330	96.22 272	76.27 302	95.30 348	83.56 327	75.74 357	93.41 328

ACMM	91.95 10	92.88 227	92.52 226	93.98 278	95.75 276	89.08 311	99.77 140	97.52 246	93.00 170	89.95 253	97.99 217	76.17 303	98.46 204	93.63 214	88.87 250	94.39 265
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DSMNet-mixed		88.28 308	88.24 303	88.42 346	89.64 367	75.38 375	98.06 321	89.86 389	85.59 329	88.20 295	92.14 358	76.15 304	91.95 375	78.46 352	96.05 192	97.92 223

VPA-MVSNet		92.70 232	91.55 244	96.16 203	95.09 291	96.20 136	98.88 270	99.00 36	91.02 242	91.82 232	95.29 311	76.05 305	97.96 245	95.62 168	81.19 318	94.30 272

SDMVSNet		94.80 173	93.96 186	97.33 170	98.92 122	95.42 164	99.59 181	98.99 37	92.41 199	92.55 224	97.85 222	75.81 306	98.93 176	97.90 121	91.62 235	97.64 229

TR-MVS		94.54 183	93.56 198	97.49 159	97.96 179	94.34 196	98.71 287	97.51 247	90.30 258	94.51 199	98.69 182	75.56 307	98.77 183	92.82 226	95.99 193	99.35 167

PS-CasMVS		90.63 275	89.51 282	93.99 277	93.83 312	91.70 265	98.98 259	98.52 99	88.48 290	86.15 323	96.53 266	75.46 308	96.31 325	88.83 277	78.86 338	93.95 306

TransMVSNet (Re)		87.25 313	85.28 320	93.16 301	93.56 317	91.03 274	98.54 298	94.05 375	83.69 345	81.09 348	96.16 274	75.32 309	96.40 320	76.69 360	68.41 372	92.06 351

LPG-MVS_test		92.96 225	92.71 219	93.71 287	95.43 287	88.67 315	99.75 148	97.62 231	92.81 176	90.05 249	98.49 199	75.24 310	98.40 210	95.84 166	89.12 246	94.07 295

LGP-MVS_train				93.71 287	95.43 287	88.67 315		97.62 231	92.81 176	90.05 249	98.49 199	75.24 310	98.40 210	95.84 166	89.12 246	94.07 295

ECVR-MVS		95.66 156	95.05 161	97.51 158	98.66 140	93.71 213	98.85 276	98.45 113	94.93 97	96.86 156	98.96 159	75.22 312	99.20 164	95.34 169	98.15 148	99.64 117

test1111		95.57 158	94.98 164	97.37 166	98.56 143	93.37 224	98.86 274	98.45 113	94.95 96	96.63 162	98.95 164	75.21 313	99.11 169	95.02 175	98.14 150	99.64 117

OPM-MVS		93.21 218	92.80 217	94.44 260	93.12 327	90.85 281	99.77 140	97.61 234	96.19 71	91.56 234	98.65 186	75.16 314	98.47 201	93.78 210	89.39 245	93.99 303
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tfpnnormal		89.29 302	87.61 308	94.34 265	94.35 304	94.13 202	98.95 263	98.94 41	83.94 341	84.47 332	95.51 296	74.84 315	97.39 264	77.05 359	80.41 328	91.48 357

AllTest		92.48 237	91.64 240	95.00 234	99.01 111	88.43 319	98.94 264	96.82 319	86.50 316	88.71 284	98.47 203	74.73 316	99.88 100	85.39 314	96.18 189	96.71 238

TestCases				95.00 234	99.01 111	88.43 319		96.82 319	86.50 316	88.71 284	98.47 203	74.73 316	99.88 100	85.39 314	96.18 189	96.71 238

Anonymous20231206		86.32 316	85.42 319	89.02 340	89.11 369	80.53 369	99.05 253	95.28 360	85.43 331	82.82 339	93.92 341	74.40 318	93.44 366	66.99 376	81.83 314	93.08 337

XXY-MVS		91.82 248	90.46 259	95.88 208	93.91 311	95.40 166	98.87 273	97.69 225	88.63 288	87.87 298	97.08 243	74.38 319	97.89 249	91.66 238	84.07 300	94.35 270

ACMP	92.05 9	92.74 230	92.42 228	93.73 285	95.91 268	88.72 314	99.81 130	97.53 244	94.13 130	87.00 310	98.23 209	74.07 320	98.47 201	96.22 160	88.86 251	93.99 303
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	88.28 18	90.29 284	89.05 291	94.02 274	95.08 292	90.15 296	97.19 336	97.43 253	84.91 337	83.99 334	97.06 245	74.00 321	98.28 226	84.08 321	87.71 272	93.62 325
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		89.36 301	87.81 307	94.01 275	93.40 322	91.93 255	98.62 295	96.48 335	86.25 320	83.86 335	96.14 275	73.68 322	97.04 291	86.16 309	75.73 358	93.04 338

pmmvs5		90.17 288	89.09 289	93.40 295	92.10 346	89.77 304	99.74 151	95.58 354	85.88 324	87.24 309	95.74 284	73.41 323	96.48 318	88.54 281	83.56 303	93.95 306

OurMVSNet-221017-0		89.81 294	89.48 284	90.83 326	91.64 351	81.21 363	98.17 317	95.38 359	91.48 226	85.65 327	97.31 236	72.66 324	97.29 275	88.15 286	84.83 293	93.97 305

jajsoiax		91.92 247	91.18 250	94.15 268	91.35 355	90.95 278	99.00 258	97.42 255	92.61 188	87.38 306	97.08 243	72.46 325	97.36 265	94.53 191	88.77 252	94.13 291

UGNet		95.33 164	94.57 172	97.62 153	98.55 145	94.85 182	98.67 292	99.32 26	95.75 79	96.80 159	96.27 271	72.18 326	99.96 59	94.58 190	99.05 126	98.04 222
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		91.81 249	91.08 251	94.00 276	91.63 352	90.58 286	98.67 292	97.43 253	92.43 198	87.37 307	97.05 246	71.76 327	97.32 271	94.75 185	88.68 254	94.11 292

SixPastTwentyTwo		88.73 305	88.01 306	90.88 324	91.85 349	82.24 356	98.22 315	95.18 364	88.97 277	82.26 341	96.89 251	71.75 328	96.67 312	84.00 322	82.98 304	93.72 323

test_fmvs1		95.35 163	95.68 144	94.36 264	98.99 114	84.98 343	99.96 32	96.65 328	97.60 20	99.73 30	98.96 159	71.58 329	99.93 83	98.31 100	99.37 111	98.17 218

GBi-Net		90.88 268	89.82 274	94.08 271	97.53 209	91.97 252	98.43 303	96.95 304	87.05 308	89.68 260	94.72 326	71.34 330	96.11 331	87.01 303	85.65 285	94.17 281

test1		90.88 268	89.82 274	94.08 271	97.53 209	91.97 252	98.43 303	96.95 304	87.05 308	89.68 260	94.72 326	71.34 330	96.11 331	87.01 303	85.65 285	94.17 281

FMVSNet2		91.02 265	89.56 279	95.41 221	97.53 209	95.74 151	98.98 259	97.41 257	87.05 308	88.43 291	95.00 320	71.34 330	96.24 328	85.12 316	85.21 290	94.25 276

PVSNet_0	88.03 19	91.80 252	90.27 265	96.38 198	98.27 161	90.46 289	99.94 66	99.61 14	93.99 140	86.26 322	97.39 235	71.13 333	99.89 94	98.77 78	67.05 376	98.79 203

sd_testset		93.55 212	92.83 216	95.74 213	98.92 122	90.89 280	98.24 312	98.85 55	92.41 199	92.55 224	97.85 222	71.07 334	98.68 192	93.93 201	91.62 235	97.64 229

Anonymous20231211		89.86 293	88.44 300	94.13 270	98.93 120	90.68 283	98.54 298	98.26 174	76.28 369	86.73 312	95.54 293	70.60 335	97.56 260	90.82 253	80.27 331	94.15 287

ITE_SJBPF				92.38 312	95.69 282	85.14 341		95.71 350	92.81 176	89.33 271	98.11 211	70.23 336	98.42 207	85.91 312	88.16 265	93.59 326

ACMH	89.72 17	90.64 274	89.63 277	93.66 291	95.64 284	88.64 317	98.55 296	97.45 251	89.03 273	81.62 345	97.61 228	69.75 337	98.41 208	89.37 272	87.62 274	93.92 309
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVS-HIRNet		86.22 317	83.19 330	95.31 225	96.71 252	90.29 292	92.12 376	97.33 264	62.85 383	86.82 311	70.37 388	69.37 338	97.49 262	75.12 363	97.99 156	98.15 219

Anonymous202405211		93.10 223	91.99 235	96.40 196	99.10 106	89.65 305	98.88 270	97.93 207	83.71 344	94.00 206	98.75 181	68.79 339	99.88 100	95.08 174	91.71 234	99.68 109

test20.03		84.72 327	83.99 322	86.91 350	88.19 372	80.62 368	98.88 270	95.94 346	88.36 292	78.87 356	94.62 331	68.75 340	89.11 381	66.52 378	75.82 356	91.00 359

VPNet		91.81 249	90.46 259	95.85 210	94.74 297	95.54 160	98.98 259	98.59 82	92.14 206	90.77 244	97.44 232	68.73 341	97.54 261	94.89 181	77.89 343	94.46 256

K. test v3		88.05 309	87.24 311	90.47 329	91.82 350	82.23 357	98.96 262	97.42 255	89.05 272	76.93 366	95.60 290	68.49 342	95.42 344	85.87 313	81.01 324	93.75 319

ACMH+	89.98 16	90.35 281	89.54 280	92.78 310	95.99 265	86.12 336	98.81 279	97.18 278	89.38 268	83.14 338	97.76 226	68.42 343	98.43 206	89.11 275	86.05 283	93.78 318

MDA-MVSNet-bldmvs		84.09 330	81.52 337	91.81 319	91.32 356	88.00 326	98.67 292	95.92 347	80.22 361	55.60 389	93.32 347	68.29 344	93.60 365	73.76 364	76.61 355	93.82 317

MS-PatchMatch		90.65 273	90.30 264	91.71 320	94.22 306	85.50 340	98.24 312	97.70 224	88.67 286	86.42 319	96.37 269	67.82 345	98.03 241	83.62 326	99.62 88	91.60 355

KD-MVS_self_test		83.59 334	82.06 334	88.20 347	86.93 373	80.70 367	97.21 335	96.38 337	82.87 349	82.49 340	88.97 369	67.63 346	92.32 373	73.75 365	62.30 384	91.58 356

LFMVS		94.75 177	93.56 198	98.30 117	99.03 110	95.70 154	98.74 284	97.98 202	87.81 300	98.47 114	99.39 121	67.43 347	99.53 148	98.01 113	95.20 213	99.67 111

MIMVSNet		90.30 283	88.67 297	95.17 230	96.45 255	91.64 267	92.39 375	97.15 282	85.99 322	90.50 245	93.19 350	66.95 348	94.86 353	82.01 336	93.43 227	99.01 194

test_vis1_n_1920		95.44 161	95.31 152	95.82 211	98.50 149	88.74 313	99.98 14	97.30 267	97.84 14	99.85 7	99.19 138	66.82 349	99.97 53	98.82 75	99.46 104	98.76 204

XVG-ACMP-BASELINE		91.22 263	90.75 254	92.63 311	93.73 314	85.61 338	98.52 300	97.44 252	92.77 179	89.90 255	96.85 254	66.64 350	98.39 212	92.29 230	88.61 255	93.89 311

Anonymous20240529		92.10 245	90.65 256	96.47 191	98.82 131	90.61 285	98.72 286	98.67 71	75.54 373	93.90 208	98.58 193	66.23 351	99.90 89	94.70 187	90.67 237	98.90 198

lessismore_v0				90.53 327	90.58 361	80.90 366		95.80 348		77.01 365	95.84 281	66.15 352	96.95 297	83.03 329	75.05 359	93.74 322

USDC		90.00 291	88.96 292	93.10 304	94.81 296	88.16 323	98.71 287	95.54 355	93.66 153	83.75 336	97.20 239	65.58 353	98.31 223	83.96 324	87.49 276	92.85 341

pmmvs-eth3d		84.03 331	81.97 335	90.20 331	84.15 378	87.09 331	98.10 320	94.73 368	83.05 347	74.10 374	87.77 375	65.56 354	94.01 359	81.08 341	69.24 369	89.49 372

Anonymous20240521		85.15 324	83.81 326	89.16 339	88.32 370	82.69 352	98.80 281	95.74 349	79.72 362	81.53 346	90.99 361	65.38 355	94.16 358	72.69 366	81.11 321	90.63 363

LF4IMVS		89.25 303	88.85 293	90.45 330	92.81 337	81.19 364	98.12 318	94.79 366	91.44 228	86.29 321	97.11 241	65.30 356	98.11 236	88.53 282	85.25 289	92.07 350

new_pmnet		84.49 329	82.92 332	89.21 338	90.03 365	82.60 353	96.89 345	95.62 353	80.59 359	75.77 371	89.17 368	65.04 357	94.79 354	72.12 368	81.02 323	90.23 365

CMPMVS	61.59 21	84.75 326	85.14 321	83.57 356	90.32 363	62.54 384	96.98 342	97.59 238	74.33 377	69.95 378	96.66 259	64.17 358	98.32 222	87.88 290	88.41 260	89.84 369
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_0402		85.58 319	83.94 324	90.50 328	93.81 313	85.04 342	98.55 296	95.20 363	76.01 370	79.72 355	95.13 314	64.15 359	96.26 327	66.04 380	86.88 279	90.21 366

TDRefinement		84.76 325	82.56 333	91.38 322	74.58 391	84.80 345	97.36 333	94.56 370	84.73 338	80.21 352	96.12 278	63.56 360	98.39 212	87.92 289	63.97 381	90.95 361

UnsupCasMVSNet_eth		85.52 320	83.99 322	90.10 332	89.36 368	83.51 350	96.65 347	97.99 200	89.14 270	75.89 370	93.83 342	63.25 361	93.92 360	81.92 337	67.90 375	92.88 340

tt0805		91.28 260	90.18 268	94.60 249	96.26 258	87.55 327	98.39 307	98.72 63	89.00 275	89.22 274	98.47 203	62.98 362	98.96 174	90.57 257	88.00 268	97.28 235

new-patchmatchnet		81.19 337	79.34 344	86.76 351	82.86 381	80.36 370	97.92 324	95.27 361	82.09 354	72.02 375	86.87 377	62.81 363	90.74 379	71.10 369	63.08 382	89.19 375

TinyColmap		87.87 312	86.51 313	91.94 317	95.05 293	85.57 339	97.65 329	94.08 373	84.40 340	81.82 344	96.85 254	62.14 364	98.33 221	80.25 345	86.37 282	91.91 354

test_fmvs1_n		94.25 195	94.36 175	93.92 279	97.68 201	83.70 349	99.90 85	96.57 331	97.40 26	99.67 36	98.88 170	61.82 365	99.92 86	98.23 102	99.13 122	98.14 221

VDDNet		93.12 222	91.91 237	96.76 184	96.67 253	92.65 241	98.69 290	98.21 178	82.81 350	97.75 138	99.28 127	61.57 366	99.48 157	98.09 110	94.09 222	98.15 219

pmmvs6		85.69 318	83.84 325	91.26 323	90.00 366	84.41 346	97.82 327	96.15 343	75.86 371	81.29 347	95.39 303	61.21 367	96.87 303	83.52 328	73.29 361	92.50 346

VDD-MVS		93.77 205	92.94 213	96.27 201	98.55 145	90.22 294	98.77 283	97.79 221	90.85 245	96.82 158	99.42 116	61.18 368	99.77 126	98.95 65	94.13 221	98.82 201

testgi		89.01 304	88.04 305	91.90 318	93.49 319	84.89 344	99.73 156	95.66 352	93.89 148	85.14 329	98.17 210	59.68 369	94.66 355	77.73 355	88.88 249	96.16 246

FMVSNet1		88.50 306	86.64 312	94.08 271	95.62 286	91.97 252	98.43 303	96.95 304	83.00 348	86.08 324	94.72 326	59.09 370	96.11 331	81.82 338	84.07 300	94.17 281

DeepMVS_CX				82.92 358	95.98 267	58.66 389		96.01 345	92.72 180	78.34 360	95.51 296	58.29 371	98.08 237	82.57 331	85.29 288	92.03 352

UniMVSNet_ETH3D		90.06 290	88.58 298	94.49 257	94.67 299	88.09 324	97.81 328	97.57 239	83.91 343	88.44 289	97.41 233	57.44 372	97.62 259	91.41 240	88.59 257	97.77 227

pmmvs3		80.27 341	77.77 346	87.76 349	80.32 386	82.43 355	98.23 314	91.97 384	72.74 380	78.75 357	87.97 374	57.30 373	90.99 378	70.31 370	62.37 383	89.87 368

OpenMVS_ROB	79.82 20	83.77 333	81.68 336	90.03 333	88.30 371	82.82 351	98.46 301	95.22 362	73.92 378	76.00 369	91.29 360	55.00 374	96.94 298	68.40 374	88.51 259	90.34 364

test_fmvs2		89.47 299	89.70 276	88.77 344	94.54 301	75.74 373	99.83 125	94.70 369	94.71 106	91.08 239	96.82 258	54.46 375	97.78 254	92.87 225	88.27 263	92.80 342

tmp_tt		65.23 356	62.94 359	72.13 372	44.90 400	50.03 397	81.05 388	89.42 392	38.45 391	48.51 393	99.90 18	54.09 376	78.70 393	91.84 237	18.26 395	87.64 377

EGC-MVSNET		69.38 348	63.76 358	86.26 352	90.32 363	81.66 362	96.24 355	93.85 377	0.99 399	3.22 400	92.33 357	52.44 377	92.92 370	59.53 386	84.90 292	84.21 380

test_vis1_n		93.61 211	93.03 212	95.35 222	95.86 269	86.94 332	99.87 98	96.36 338	96.85 44	99.54 54	98.79 179	52.41 378	99.83 116	98.64 87	98.97 127	99.29 176

MIMVSNet1		82.58 335	80.51 341	88.78 342	86.68 374	84.20 347	96.65 347	95.41 357	78.75 365	78.59 359	92.44 353	51.88 379	89.76 380	65.26 381	78.95 336	92.38 349

EG-PatchMatch MVS		85.35 323	83.81 326	89.99 334	90.39 362	81.89 359	98.21 316	96.09 344	81.78 355	74.73 372	93.72 344	51.56 380	97.12 285	79.16 350	88.61 255	90.96 360

UnsupCasMVSNet_bld		79.97 344	77.03 349	88.78 342	85.62 376	81.98 358	93.66 371	97.35 261	75.51 374	70.79 377	83.05 383	48.70 381	94.91 352	78.31 353	60.29 386	89.46 373

test_vis1_rt		86.87 315	86.05 317	89.34 337	96.12 260	78.07 372	99.87 98	83.54 396	92.03 211	78.21 361	89.51 367	45.80 382	99.91 87	96.25 159	93.11 232	90.03 367

test_method		80.79 339	79.70 343	84.08 355	92.83 335	67.06 381	99.51 195	95.42 356	54.34 387	81.07 349	93.53 345	44.48 383	92.22 374	78.90 351	77.23 350	92.94 339

APD_test1		81.15 338	80.92 339	81.86 359	92.45 340	59.76 388	96.04 359	93.61 379	73.29 379	77.06 364	96.64 261	44.28 384	96.16 330	72.35 367	82.52 307	89.67 370

mvsany_test3		82.12 336	81.14 338	85.06 354	81.87 382	70.41 378	97.09 339	92.14 383	91.27 235	77.84 362	88.73 370	39.31 385	95.49 342	90.75 255	71.24 364	89.29 374

PM-MVS		80.47 340	78.88 345	85.26 353	83.79 380	72.22 377	95.89 362	91.08 386	85.71 328	76.56 368	88.30 371	36.64 386	93.90 361	82.39 333	69.57 368	89.66 371

ambc				83.23 357	77.17 389	62.61 383	87.38 386	94.55 371		76.72 367	86.65 378	30.16 387	96.36 322	84.85 319	69.86 366	90.73 362

Gipuma		66.95 355	65.00 355	72.79 368	91.52 353	67.96 380	66.16 391	95.15 365	47.89 389	58.54 386	67.99 391	29.74 388	87.54 385	50.20 390	77.83 344	62.87 391
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EMVS		51.44 361	51.22 363	52.11 378	70.71 393	44.97 401	94.04 368	75.66 400	35.34 395	42.40 395	61.56 396	28.93 389	65.87 397	27.64 398	24.73 393	45.49 394

test_fmvs3		79.99 343	80.17 342	79.45 361	84.02 379	62.83 382	99.05 253	93.49 380	88.29 294	80.06 354	86.65 378	28.09 390	88.00 382	88.63 278	73.27 362	87.54 378

test_f		78.40 345	77.59 347	80.81 360	80.82 384	62.48 385	96.96 343	93.08 381	83.44 346	74.57 373	84.57 382	27.95 391	92.63 371	84.15 320	72.79 363	87.32 379

E-PMN		52.30 359	52.18 361	52.67 377	71.51 392	45.40 399	93.62 372	76.60 399	36.01 393	43.50 394	64.13 393	27.11 392	67.31 396	31.06 397	26.06 392	45.30 395

FPMVS		68.72 350	68.72 351	68.71 373	65.95 395	44.27 402	95.97 361	94.74 367	51.13 388	53.26 390	90.50 365	25.11 393	83.00 389	60.80 384	80.97 325	78.87 386

PMMVS2		67.15 354	64.15 357	76.14 365	70.56 394	62.07 386	93.89 369	87.52 393	58.09 384	60.02 383	78.32 385	22.38 394	84.54 388	59.56 385	47.03 390	81.80 383

testf1		68.38 351	66.92 352	72.78 369	78.80 387	50.36 395	90.95 382	87.35 394	55.47 385	58.95 384	88.14 372	20.64 395	87.60 383	57.28 387	64.69 379	80.39 384

APD_test2		68.38 351	66.92 352	72.78 369	78.80 387	50.36 395	90.95 382	87.35 394	55.47 385	58.95 384	88.14 372	20.64 395	87.60 383	57.28 387	64.69 379	80.39 384

LCM-MVSNet		67.77 353	64.73 356	76.87 364	62.95 397	56.25 391	89.37 385	93.74 378	44.53 390	61.99 382	80.74 384	20.42 397	86.53 387	69.37 373	59.50 387	87.84 376

test123		37.68 363	39.14 366	33.31 379	19.94 402	24.83 405	98.36 308	9.75 404	15.53 397	51.31 391	87.14 376	19.62 398	17.74 399	47.10 391	3.47 398	57.36 392

ANet_high		56.10 357	52.24 360	67.66 374	49.27 399	56.82 390	83.94 387	82.02 397	70.47 381	33.28 397	64.54 392	17.23 399	69.16 395	45.59 392	23.85 394	77.02 387

test_vis3_rt		68.82 349	66.69 354	75.21 366	76.24 390	60.41 387	96.44 350	68.71 401	75.13 375	50.54 392	69.52 390	16.42 400	96.32 324	80.27 344	66.92 377	68.89 388

testmvs		40.60 362	44.45 365	29.05 380	19.49 403	14.11 406	99.68 166	18.47 403	20.74 396	64.59 381	98.48 202	10.95 401	17.09 400	56.66 389	11.01 396	55.94 393

PMVS	49.05 23	53.75 358	51.34 362	60.97 376	40.80 401	34.68 403	74.82 390	89.62 391	37.55 392	28.67 398	72.12 387	7.09 402	81.63 392	43.17 393	68.21 373	66.59 390
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		20.37 365	20.84 368	18.99 381	65.34 396	27.73 404	50.43 392	7.67 405	9.50 398	8.01 399	6.34 399	6.13 403	26.24 398	23.40 399	10.69 397	2.99 396

MVE	53.74 22	51.54 360	47.86 364	62.60 375	59.56 398	50.93 394	79.41 389	77.69 398	35.69 394	36.27 396	61.76 395	5.79 404	69.63 394	37.97 394	36.61 391	67.24 389
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_blank		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.02 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet_test		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 401	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

DCPMVS		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 401	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

sosnet-low-res		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 401	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

sosnet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 401	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uncertanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 401	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

Regformer		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 401	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

ab-mvs-re		8.28 366	11.04 369	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	99.40 119	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 401	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

WAC-MVS						90.97 275								86.10 311

FOURS1					99.92 31	97.66 81	99.95 50	98.36 155	95.58 83	99.52 57

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 140					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 140					100.00 1	99.96 9	100.00 1	100.00 1

eth-test2					0.00 404

eth-test					0.00 404

IU-MVS					99.93 24	99.31 10		98.41 140	97.71 17	99.84 10				100.00 1	100.00 1	100.00 1

save fliter					99.82 58	98.79 38	99.96 32	98.40 144	97.66 19

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 50	98.43 125					100.00 1	99.99 5	100.00 1	100.00 1

GSMVS																99.59 128

test_part2					99.89 45	99.25 18				99.49 60

MTGPA								98.28 171

MTMP							99.87 98	96.49 334

gm-plane-assit					96.97 236	93.76 212			91.47 227		98.96 159		98.79 181	94.92 178

test9_res														99.71 31	99.99 21	100.00 1

agg_prior2														99.48 41	100.00 1	100.00 1

agg_prior					99.93 24	98.77 40		98.43 125		99.63 41			99.85 106

test_prior4						98.05 66	99.94 66

test_prior				99.43 35	99.94 13	98.49 58		98.65 72					99.80 119			99.99 23

旧先验2							99.46 204		94.21 128	99.85 7			99.95 67	96.96 149

新几何2							99.40 208

无先验							99.49 199	98.71 64	93.46 158				100.00 1	94.36 193		99.99 23

原ACMM2							99.90 85

testdata2													99.99 36	90.54 259

testdata1							99.28 228		96.35 67

plane_prior7					95.71 280	91.59 269

plane_prior5								97.87 214					98.37 218	97.79 126	89.55 242	94.52 252

plane_prior4											98.59 191

plane_prior3						91.64 267			96.63 54	93.01 215

plane_prior2							99.84 118		96.38 63

plane_prior1					95.73 277

plane_prior						91.74 261	99.86 111		96.76 50						89.59 241

n2								0.00 406

nn								0.00 406

door-mid								89.69 390

test11								98.44 117

door								90.31 387

HQP5-MVS						91.85 257

HQP-NCC					95.78 270		99.87 98		96.82 46	93.37 211

ACMP_Plane					95.78 270		99.87 98		96.82 46	93.37 211

BP-MVS														97.92 119

HQP4-MVS										93.37 211			98.39 212			94.53 250

HQP3-MVS								97.89 212							89.60 239

NP-MVS					95.77 273	91.79 259					98.65 186

ACMMP++_ref															87.04 277

ACMMP++															88.23 264

High-resolution multi-view benchmark