This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

(*) 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 Infoallhigh-res
multi-view
indooroutdoorbotani.boulde.bridgedoorexhibi.lectur.living.loungeobserv.old co.statueterrac.
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysorted by
mvs5depth99.30 3399.59 1298.44 27399.65 7095.35 36299.82 399.94 399.83 799.42 11199.94 298.13 12399.96 1399.63 3699.96 28100.00 1
test_fmvsmconf0.01_n99.57 1099.63 1099.36 7499.87 1298.13 14998.08 19599.95 299.45 5099.98 299.75 1699.80 199.97 699.82 1299.99 599.99 2
fmvsm_s_conf0.1_n_a99.17 5299.30 4498.80 19399.75 3496.59 29997.97 22599.86 1798.22 20099.88 2199.71 2298.59 6799.84 17699.73 2899.98 1299.98 3
fmvsm_s_conf0.1_n_299.20 5099.38 2898.65 22699.69 6096.08 32697.49 30099.90 1299.53 4199.88 2199.64 3798.51 7699.90 8199.83 1099.98 1299.97 4
mmtdpeth99.30 3399.42 2598.92 17099.58 9396.89 28499.48 1399.92 899.92 298.26 32899.80 1198.33 9599.91 7499.56 4199.95 3999.97 4
fmvsm_s_conf0.1_n99.16 5699.33 3798.64 22899.71 4896.10 32197.87 23899.85 1998.56 17599.90 1499.68 2598.69 5799.85 15899.72 3099.98 1299.97 4
test_fmvs399.12 6999.41 2698.25 29599.76 3095.07 37799.05 6899.94 397.78 24599.82 3499.84 398.56 7399.71 30699.96 199.96 2899.97 4
test_fmvsmconf0.1_n99.49 1599.54 1499.34 8399.78 2498.11 15197.77 25299.90 1299.33 6599.97 399.66 3299.71 399.96 1399.79 1999.99 599.96 8
test_f98.67 15998.87 11098.05 32199.72 4495.59 34498.51 13599.81 3296.30 36699.78 3999.82 596.14 27198.63 49399.82 1299.93 5799.95 9
test_fmvs298.70 14698.97 9797.89 33499.54 12294.05 41398.55 12699.92 896.78 34299.72 4799.78 1396.60 24899.67 33699.91 299.90 8899.94 10
PS-MVSNAJss99.46 1799.49 1699.35 8099.90 498.15 14699.20 4999.65 7499.48 4499.92 899.71 2298.07 12699.96 1399.53 48100.00 199.93 11
test_vis3_rt99.14 6299.17 6099.07 13599.78 2498.38 12298.92 8399.94 397.80 24299.91 1299.67 3097.15 20898.91 48599.76 2399.56 28399.92 12
fmvsm_s_conf0.5_n_299.14 6299.31 4198.63 23299.49 14696.08 32697.38 31499.81 3299.48 4499.84 3099.57 4998.46 8299.89 9799.82 1299.97 2199.91 13
MVStest195.86 40695.60 39996.63 42895.87 51991.70 46997.93 22798.94 32898.03 22399.56 7499.66 3271.83 50998.26 49899.35 5899.24 35899.91 13
fmvsm_s_conf0.5_n_a99.10 7199.20 5898.78 20099.55 11696.59 29997.79 24899.82 3198.21 20299.81 3699.53 6498.46 8299.84 17699.70 3399.97 2199.90 15
fmvsm_s_conf0.5_n_999.17 5299.38 2898.53 25999.51 13295.82 33897.62 27899.78 3699.72 1499.90 1499.48 7598.66 5999.89 9799.85 699.93 5799.89 16
fmvsm_s_conf0.5_n99.09 7299.26 5098.61 23899.55 11696.09 32497.74 26099.81 3298.55 17699.85 2799.55 5698.60 6699.84 17699.69 3599.98 1299.89 16
test_fmvsmconf_n99.44 1999.48 1899.31 9499.64 7698.10 15497.68 26799.84 2399.29 7199.92 899.57 4999.60 599.96 1399.74 2799.98 1299.89 16
test_djsdf99.52 1399.51 1599.53 3899.86 1498.74 9199.39 2099.56 11599.11 9999.70 5199.73 2099.00 2799.97 699.26 6599.98 1299.89 16
fmvsm_s_conf0.5_n_1199.21 4799.34 3598.80 19399.48 15496.56 30497.97 22599.69 5599.63 2899.84 3099.54 6298.21 11399.94 4199.76 2399.95 3999.88 20
mvs_tets99.63 699.67 699.49 5599.88 998.61 10399.34 2399.71 4799.27 7399.90 1499.74 1899.68 499.97 699.55 4399.99 599.88 20
fmvsm_s_conf0.5_n_899.13 6699.26 5098.74 21399.51 13296.44 31297.65 27399.65 7499.66 2399.78 3999.48 7597.92 14099.93 5399.72 3099.95 3999.87 22
fmvsm_s_conf0.5_n_798.83 12199.04 8698.20 30299.30 20794.83 38697.23 33299.36 20798.64 15999.84 3099.43 8898.10 12599.91 7499.56 4199.96 2899.87 22
fmvsm_l_conf0.5_n_399.45 1899.48 1899.34 8399.59 9198.21 14397.82 24399.84 2399.41 5799.92 899.41 9499.51 899.95 2599.84 999.97 2199.87 22
ttmdpeth97.91 26798.02 25097.58 37198.69 35994.10 41298.13 18598.90 33897.95 22997.32 40499.58 4795.95 28798.75 49096.41 32699.22 36299.87 22
jajsoiax99.58 999.61 1199.48 5799.87 1298.61 10399.28 4099.66 6999.09 10999.89 1899.68 2599.53 799.97 699.50 5099.99 599.87 22
EU-MVSNet97.66 29398.50 17295.13 48299.63 8285.84 51698.35 16198.21 40898.23 19999.54 7999.46 8095.02 31899.68 33298.24 14499.87 10099.87 22
fmvsm_s_conf0.5_n_399.22 4699.37 3198.78 20099.46 16096.58 30297.65 27399.72 4599.47 4799.86 2499.50 6898.94 3199.89 9799.75 2699.97 2199.86 28
UA-Net99.47 1699.40 2799.70 299.49 14699.29 2399.80 499.72 4599.82 899.04 19899.81 898.05 12999.96 1398.85 9899.99 599.86 28
fmvsm_l_conf0.5_n_999.32 3299.43 2498.98 15799.59 9197.18 26297.44 30999.83 2699.56 3999.91 1299.34 11599.36 1399.93 5399.83 1099.98 1299.85 30
MM98.22 23497.99 25398.91 17298.66 36996.97 27697.89 23494.44 49799.54 4098.95 21899.14 17793.50 36599.92 6599.80 1799.96 2899.85 30
LCM-MVSNet99.93 199.92 199.94 199.99 199.97 199.90 199.89 1499.98 199.99 199.96 199.77 2100.00 199.81 16100.00 199.85 30
fmvsm_l_conf0.5_n_a99.19 5199.27 4798.94 16499.65 7097.05 27197.80 24799.76 3998.70 15799.78 3999.11 18498.79 4399.95 2599.85 699.96 2899.83 33
fmvsm_l_conf0.5_n99.21 4799.28 4699.02 14899.64 7697.28 24897.82 24399.76 3998.73 15099.82 3499.09 19398.81 3999.95 2599.86 499.96 2899.83 33
mvsany_test398.87 11198.92 10198.74 21399.38 18396.94 28098.58 12399.10 30096.49 35599.96 499.81 898.18 11699.45 43698.97 8999.79 15899.83 33
PDCNetPlus95.22 42994.73 43696.70 42797.85 44791.14 48593.94 49599.97 193.06 47098.95 21898.89 25674.32 50699.14 47395.63 36899.93 5799.82 36
fmvsm_s_conf0.5_n_1099.15 5799.27 4798.78 20099.47 15796.56 30497.75 25899.71 4799.60 3599.74 4699.44 8597.96 13799.95 2599.86 499.94 5199.82 36
SSC-MVS98.71 14198.74 12798.62 23499.72 4496.08 32698.74 9998.64 38199.74 1299.67 5999.24 14494.57 33499.95 2599.11 7799.24 35899.82 36
anonymousdsp99.51 1499.47 2199.62 999.88 999.08 6999.34 2399.69 5598.93 13199.65 6399.72 2198.93 3399.95 2599.11 77100.00 199.82 36
ANet_high99.57 1099.67 699.28 9699.89 698.09 15599.14 5899.93 699.82 899.93 699.81 899.17 2099.94 4199.31 61100.00 199.82 36
MED-MVS99.01 8998.84 11899.52 4499.58 9398.93 7998.68 10999.60 8998.85 14499.53 8399.16 16897.87 14799.83 19496.67 29899.64 24999.81 41
TestfortrainingZip a99.09 7298.92 10199.61 1399.58 9399.17 4398.68 10999.27 25598.85 14499.61 7099.16 16897.14 20999.86 14498.39 13799.57 27999.81 41
fmvsm_s_conf0.5_n_499.01 8999.22 5498.38 28099.31 20395.48 35397.56 28999.73 4498.87 13999.75 4499.27 13198.80 4199.86 14499.80 1799.90 8899.81 41
PS-CasMVS99.40 2599.33 3799.62 999.71 4899.10 6599.29 3699.53 12999.53 4199.46 10199.41 9498.23 10899.95 2598.89 9699.95 3999.81 41
VortexMVS97.98 26498.31 20997.02 40898.88 31991.45 47498.03 20699.47 15898.65 15899.55 7799.47 7891.49 40499.81 22399.32 6099.91 8099.80 45
FC-MVSNet-test99.27 3799.25 5299.34 8399.77 2798.37 12499.30 3599.57 10699.61 3499.40 11699.50 6897.12 21099.85 15899.02 8699.94 5199.80 45
test_cas_vis1_n_192098.33 21898.68 14097.27 39599.69 6092.29 46398.03 20699.85 1997.62 25799.96 499.62 4093.98 35599.74 28899.52 4999.86 10799.79 47
test_vis1_n_192098.40 20498.92 10196.81 42299.74 3690.76 49298.15 18399.91 1098.33 18899.89 1899.55 5695.07 31799.88 11599.76 2399.93 5799.79 47
CP-MVSNet99.21 4799.09 8199.56 2699.65 7098.96 7799.13 5999.34 21999.42 5599.33 13599.26 13797.01 21899.94 4198.74 10799.93 5799.79 47
fmvsm_s_conf0.5_n_599.07 8199.10 7998.99 15399.47 15797.22 25597.40 31199.83 2697.61 26099.85 2799.30 12598.80 4199.95 2599.71 3299.90 8899.78 50
UniMVSNet_ETH3D99.69 299.69 499.69 399.84 1799.34 1999.69 599.58 9899.90 399.86 2499.78 1399.58 699.95 2599.00 8799.95 3999.78 50
CVMVSNet96.25 38997.21 31693.38 50599.10 26580.56 53597.20 33798.19 41196.94 32899.00 20399.02 20889.50 42699.80 23296.36 33099.59 27099.78 50
reproduce_monomvs95.00 43595.25 41994.22 49297.51 47583.34 52797.86 23998.44 39598.51 17799.29 14699.30 12567.68 51799.56 39598.89 9699.81 14099.77 53
Anonymous2023121199.27 3799.27 4799.26 10199.29 20998.18 14499.49 1299.51 13699.70 1599.80 3799.68 2596.84 22799.83 19499.21 7099.91 8099.77 53
PEN-MVS99.41 2499.34 3599.62 999.73 3799.14 5799.29 3699.54 12599.62 3299.56 7499.42 8998.16 12099.96 1398.78 10299.93 5799.77 53
WR-MVS_H99.33 3099.22 5499.65 899.71 4899.24 2999.32 2699.55 11999.46 4999.50 9399.34 11597.30 19799.93 5398.90 9499.93 5799.77 53
LTVRE_ROB98.40 199.67 399.71 299.56 2699.85 1699.11 6499.90 199.78 3699.63 2899.78 3999.67 3099.48 1099.81 22399.30 6299.97 2199.77 53
Andreas Kuhn, Heiko Hirschmüller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
WB-MVS98.52 19098.55 16398.43 27499.65 7095.59 34498.52 13098.77 36499.65 2599.52 8799.00 22394.34 34399.93 5398.65 11498.83 40899.76 58
patch_mono-298.51 19198.63 15098.17 30599.38 18394.78 38897.36 31999.69 5598.16 21298.49 30599.29 12897.06 21399.97 698.29 14399.91 8099.76 58
nrg03099.40 2599.35 3399.54 3199.58 9399.13 6098.98 7699.48 14999.68 1999.46 10199.26 13798.62 6499.73 29599.17 7499.92 7199.76 58
FIs99.14 6299.09 8199.29 9599.70 5698.28 13399.13 5999.52 13599.48 4499.24 16499.41 9496.79 23499.82 20698.69 11299.88 9599.76 58
v7n99.53 1299.57 1399.41 6999.88 998.54 11199.45 1499.61 8799.66 2399.68 5799.66 3298.44 8499.95 2599.73 2899.96 2899.75 62
APDe-MVScopyleft98.99 9398.79 12399.60 1699.21 23499.15 5298.87 8999.48 14997.57 26499.35 12999.24 14497.83 14999.89 9797.88 17999.70 22199.75 62
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DTE-MVSNet99.43 2299.35 3399.66 799.71 4899.30 2199.31 3099.51 13699.64 2699.56 7499.46 8098.23 10899.97 698.78 10299.93 5799.72 64
MSC_two_6792asdad99.32 9198.43 39998.37 12498.86 34999.89 9797.14 25099.60 26699.71 65
No_MVS99.32 9198.43 39998.37 12498.86 34999.89 9797.14 25099.60 26699.71 65
PMMVS298.07 25398.08 24498.04 32299.41 17794.59 39794.59 47599.40 19597.50 27398.82 25298.83 27196.83 22999.84 17697.50 22099.81 14099.71 65
Baseline_NR-MVSNet98.98 9798.86 11499.36 7499.82 1998.55 10897.47 30599.57 10699.37 6099.21 17099.61 4396.76 23799.83 19498.06 16099.83 12699.71 65
XXY-MVS99.14 6299.15 6799.10 12899.76 3097.74 20698.85 9399.62 8498.48 17999.37 12499.49 7498.75 4799.86 14498.20 14999.80 15199.71 65
test_0728_THIRD98.17 20999.08 18699.02 20897.89 14599.88 11597.07 25699.71 21299.70 70
MSP-MVS98.40 20498.00 25299.61 1399.57 10299.25 2898.57 12499.35 21397.55 26899.31 14497.71 41594.61 33399.88 11596.14 34499.19 37099.70 70
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
SSC-MVS3.298.53 18698.79 12397.74 35099.46 16093.62 43996.45 38599.34 21999.33 6598.93 22798.70 30297.90 14199.90 8199.12 7699.92 7199.69 72
NormalMVS98.26 22997.97 25799.15 12199.64 7697.83 19298.28 16699.43 18199.24 7698.80 25698.85 26489.76 42299.94 4198.04 16399.67 23799.68 73
KinetiMVS99.03 8799.02 8999.03 14599.70 5697.48 22898.43 14899.29 24899.70 1599.60 7199.07 19596.13 27299.94 4199.42 5599.87 10099.68 73
dcpmvs_298.78 13299.11 7397.78 34399.56 11093.67 43699.06 6699.86 1799.50 4399.66 6099.26 13797.21 20599.99 298.00 16899.91 8099.68 73
test_0728_SECOND99.60 1699.50 13899.23 3098.02 20999.32 22799.88 11596.99 26399.63 25599.68 73
OurMVSNet-221017-099.37 2899.31 4199.53 3899.91 398.98 7199.63 799.58 9899.44 5299.78 3999.76 1596.39 25899.92 6599.44 5499.92 7199.68 73
fmvsm_s_conf0.5_n_699.08 7899.21 5798.69 22199.36 19096.51 30697.62 27899.68 6298.43 18199.85 2799.10 18799.12 2399.88 11599.77 2299.92 7199.67 78
CHOSEN 1792x268897.49 30597.14 32198.54 25799.68 6396.09 32496.50 38399.62 8491.58 48898.84 24798.97 23292.36 38799.88 11596.76 28699.95 3999.67 78
reproduce_model99.15 5798.97 9799.67 499.33 20199.44 998.15 18399.47 15899.12 9899.52 8799.32 12398.31 9699.90 8197.78 18999.73 19499.66 80
IU-MVS99.49 14699.15 5298.87 34492.97 47199.41 11396.76 28699.62 25999.66 80
test_241102_TWO99.30 24098.03 22399.26 15499.02 20897.51 18299.88 11596.91 26999.60 26699.66 80
DPE-MVScopyleft98.59 17398.26 21999.57 2199.27 21599.15 5297.01 34799.39 19797.67 25399.44 10698.99 22597.53 17999.89 9795.40 37699.68 23199.66 80
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TransMVSNet (Re)99.44 1999.47 2199.36 7499.80 2198.58 10699.27 4299.57 10699.39 5899.75 4499.62 4099.17 2099.83 19499.06 8299.62 25999.66 80
EI-MVSNet-UG-set98.69 15098.71 13498.62 23499.10 26596.37 31497.23 33298.87 34499.20 8399.19 17298.99 22597.30 19799.85 15898.77 10599.79 15899.65 85
Elysia99.15 5799.14 6899.18 11399.63 8297.92 18198.50 13799.43 18199.67 2099.70 5199.13 17996.66 24499.98 499.54 4499.96 2899.64 86
StellarMVS99.15 5799.14 6899.18 11399.63 8297.92 18198.50 13799.43 18199.67 2099.70 5199.13 17996.66 24499.98 499.54 4499.96 2899.64 86
pmmvs699.67 399.70 399.60 1699.90 499.27 2699.53 999.76 3999.64 2699.84 3099.83 499.50 999.87 13599.36 5799.92 7199.64 86
EI-MVSNet-Vis-set98.68 15698.70 13798.63 23299.09 26896.40 31397.23 33298.86 34999.20 8399.18 17798.97 23297.29 19999.85 15898.72 10999.78 16399.64 86
ACMH96.65 799.25 4099.24 5399.26 10199.72 4498.38 12299.07 6599.55 11998.30 19299.65 6399.45 8499.22 1799.76 26998.44 13099.77 17099.64 86
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DP-MVS98.93 10398.81 12299.28 9699.21 23498.45 11798.46 14599.33 22599.63 2899.48 9699.15 17497.23 20399.75 28197.17 24699.66 24599.63 91
reproduce-ours99.09 7298.90 10499.67 499.27 21599.49 598.00 21399.42 18799.05 11699.48 9699.27 13198.29 9899.89 9797.61 20899.71 21299.62 92
our_new_method99.09 7298.90 10499.67 499.27 21599.49 598.00 21399.42 18799.05 11699.48 9699.27 13198.29 9899.89 9797.61 20899.71 21299.62 92
test_fmvs1_n98.09 25198.28 21397.52 38099.68 6393.47 44198.63 11699.93 695.41 41399.68 5799.64 3791.88 39899.48 42699.82 1299.87 10099.62 92
test111196.49 37496.82 34495.52 47399.42 17487.08 51399.22 4687.14 53099.11 9999.46 10199.58 4788.69 43099.86 14498.80 10099.95 3999.62 92
VPA-MVSNet99.30 3399.30 4499.28 9699.49 14698.36 12799.00 7399.45 16799.63 2899.52 8799.44 8598.25 10699.88 11599.09 7999.84 11499.62 92
LPG-MVS_test98.71 14198.46 18299.47 6199.57 10298.97 7398.23 17299.48 14996.60 34999.10 18499.06 19698.71 5199.83 19495.58 37299.78 16399.62 92
LGP-MVS_train99.47 6199.57 10298.97 7399.48 14996.60 34999.10 18499.06 19698.71 5199.83 19495.58 37299.78 16399.62 92
Test_1112_low_res96.99 35296.55 36798.31 28999.35 19595.47 35695.84 43099.53 12991.51 49096.80 43498.48 34391.36 40699.83 19496.58 30799.53 29399.62 92
tt0320-xc99.64 599.68 599.50 5499.72 4498.98 7199.51 1099.85 1999.86 699.88 2199.82 599.02 2699.90 8199.54 4499.95 3999.61 100
v1098.97 9899.11 7398.55 25299.44 16796.21 32098.90 8499.55 11998.73 15099.48 9699.60 4596.63 24799.83 19499.70 3399.99 599.61 100
sc_t199.62 799.66 899.53 3899.82 1999.09 6899.50 1199.63 7899.88 499.86 2499.80 1199.03 2499.89 9799.48 5299.93 5799.60 102
test_vis1_n98.31 22198.50 17297.73 35399.76 3094.17 40898.68 10999.91 1096.31 36499.79 3899.57 4992.85 38199.42 44299.79 1999.84 11499.60 102
v899.01 8999.16 6298.57 24599.47 15796.31 31798.90 8499.47 15899.03 12099.52 8799.57 4996.93 22399.81 22399.60 3799.98 1299.60 102
EI-MVSNet98.40 20498.51 16998.04 32299.10 26594.73 39197.20 33798.87 34498.97 12699.06 18899.02 20896.00 27999.80 23298.58 11999.82 13399.60 102
SixPastTwentyTwo98.75 13798.62 15299.16 11899.83 1897.96 17799.28 4098.20 40999.37 6099.70 5199.65 3692.65 38599.93 5399.04 8499.84 11499.60 102
IterMVS-LS98.55 18198.70 13798.09 31399.48 15494.73 39197.22 33699.39 19798.97 12699.38 12099.31 12496.00 27999.93 5398.58 11999.97 2199.60 102
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test97.19 33596.60 36598.96 16199.62 8697.28 24895.17 45599.50 13994.21 44699.01 20298.32 36486.61 44599.99 297.10 25499.84 11499.60 102
lecture99.25 4099.12 7199.62 999.64 7699.40 1198.89 8899.51 13699.19 8899.37 12499.25 14298.36 8999.88 11598.23 14699.67 23799.59 109
tt032099.61 899.65 999.48 5799.71 4898.94 7899.54 899.83 2699.87 599.89 1899.82 598.75 4799.90 8199.54 4499.95 3999.59 109
ACMMP_NAP98.75 13798.48 17899.57 2199.58 9399.29 2397.82 24399.25 26396.94 32898.78 25899.12 18298.02 13099.84 17697.13 25299.67 23799.59 109
VPNet98.87 11198.83 11999.01 15099.70 5697.62 21898.43 14899.35 21399.47 4799.28 14899.05 20396.72 24199.82 20698.09 15799.36 33299.59 109
WR-MVS98.40 20498.19 23099.03 14599.00 29497.65 21596.85 35998.94 32898.57 17298.89 23498.50 34095.60 29899.85 15897.54 21699.85 10999.59 109
HPM-MVScopyleft98.79 13098.53 16799.59 2099.65 7099.29 2399.16 5599.43 18196.74 34498.61 28598.38 35498.62 6499.87 13596.47 32199.67 23799.59 109
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EG-PatchMatch MVS98.99 9399.01 9198.94 16499.50 13897.47 22998.04 20499.59 9598.15 21799.40 11699.36 11098.58 7299.76 26998.78 10299.68 23199.59 109
Vis-MVSNetpermissive99.34 2999.36 3299.27 9999.73 3798.26 13599.17 5499.78 3699.11 9999.27 15099.48 7598.82 3899.95 2598.94 9199.93 5799.59 109
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MED-MVS test99.45 6499.58 9398.93 7998.68 10999.60 8996.46 35899.53 8398.77 28499.83 19496.67 29899.64 24999.58 117
ME-MVS98.61 16998.33 20799.44 6599.24 22698.93 7997.45 30799.06 30698.14 21899.06 18898.77 28496.97 22199.82 20696.67 29899.64 24999.58 117
MP-MVS-pluss98.57 17698.23 22499.60 1699.69 6099.35 1697.16 34299.38 19994.87 42798.97 21298.99 22598.01 13199.88 11597.29 23899.70 22199.58 117
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
region2R98.69 15098.40 19099.54 3199.53 12699.17 4398.52 13099.31 23297.46 28198.44 31198.51 33697.83 14999.88 11596.46 32299.58 27599.58 117
ACMMPR98.70 14698.42 18899.54 3199.52 12999.14 5798.52 13099.31 23297.47 27698.56 29698.54 33197.75 15799.88 11596.57 30999.59 27099.58 117
PGM-MVS98.66 16098.37 19799.55 2899.53 12699.18 4298.23 17299.49 14797.01 32598.69 27098.88 25898.00 13299.89 9795.87 35799.59 27099.58 117
SteuartSystems-ACMMP98.79 13098.54 16599.54 3199.73 3799.16 4898.23 17299.31 23297.92 23398.90 23198.90 25098.00 13299.88 11596.15 34399.72 20399.58 117
Skip Steuart: Steuart Systems R&D Blog.
SDMVSNet99.23 4599.32 3998.96 16199.68 6397.35 23798.84 9599.48 14999.69 1799.63 6699.68 2599.03 2499.96 1397.97 17299.92 7199.57 124
sd_testset99.28 3699.31 4199.19 11299.68 6398.06 16499.41 1799.30 24099.69 1799.63 6699.68 2599.25 1699.96 1397.25 24199.92 7199.57 124
TranMVSNet+NR-MVSNet99.17 5299.07 8499.46 6399.37 18998.87 8498.39 15799.42 18799.42 5599.36 12799.06 19698.38 8899.95 2598.34 14099.90 8899.57 124
mPP-MVS98.64 16398.34 20299.54 3199.54 12299.17 4398.63 11699.24 26897.47 27698.09 34298.68 30697.62 16899.89 9796.22 33899.62 25999.57 124
PVSNet_Blended_VisFu98.17 24598.15 23698.22 30199.73 3795.15 37397.36 31999.68 6294.45 44198.99 20799.27 13196.87 22699.94 4197.13 25299.91 8099.57 124
1112_ss97.29 32696.86 34098.58 24299.34 20096.32 31696.75 36699.58 9893.14 46796.89 42897.48 43292.11 39599.86 14496.91 26999.54 28999.57 124
MTAPA98.88 11098.64 14899.61 1399.67 6799.36 1598.43 14899.20 27498.83 14898.89 23498.90 25096.98 22099.92 6597.16 24799.70 22199.56 130
XVS98.72 14098.45 18399.53 3899.46 16099.21 3298.65 11499.34 21998.62 16497.54 38698.63 31997.50 18399.83 19496.79 28299.53 29399.56 130
pm-mvs199.44 1999.48 1899.33 8999.80 2198.63 10099.29 3699.63 7899.30 7099.65 6399.60 4599.16 2299.82 20699.07 8099.83 12699.56 130
X-MVStestdata94.32 44392.59 46599.53 3899.46 16099.21 3298.65 11499.34 21998.62 16497.54 38645.85 53297.50 18399.83 19496.79 28299.53 29399.56 130
HPM-MVS_fast99.01 8998.82 12099.57 2199.71 4899.35 1699.00 7399.50 13997.33 29498.94 22698.86 26198.75 4799.82 20697.53 21799.71 21299.56 130
K. test v398.00 26097.66 28799.03 14599.79 2397.56 22199.19 5392.47 51399.62 3299.52 8799.66 3289.61 42499.96 1399.25 6799.81 14099.56 130
CP-MVS98.70 14698.42 18899.52 4499.36 19099.12 6298.72 10499.36 20797.54 27098.30 32298.40 35197.86 14899.89 9796.53 31899.72 20399.56 130
viewmacassd2359aftdt98.86 11598.87 11098.83 18699.53 12697.32 24197.70 26599.64 7698.22 20099.25 16299.27 13198.40 8699.61 37497.98 17199.87 10099.55 137
FE-MVSNET98.59 17398.50 17298.87 17699.58 9397.30 24298.08 19599.74 4396.94 32898.97 21299.10 18796.94 22299.74 28897.33 23499.86 10799.55 137
ZNCC-MVS98.68 15698.40 19099.54 3199.57 10299.21 3298.46 14599.29 24897.28 30098.11 34098.39 35298.00 13299.87 13596.86 27999.64 24999.55 137
v119298.60 17198.66 14598.41 27699.27 21595.88 33497.52 29599.36 20797.41 28699.33 13599.20 15596.37 26199.82 20699.57 3999.92 7199.55 137
v124098.55 18198.62 15298.32 28799.22 23295.58 34697.51 29799.45 16797.16 31699.45 10599.24 14496.12 27499.85 15899.60 3799.88 9599.55 137
UGNet98.53 18698.45 18398.79 19797.94 44296.96 27899.08 6298.54 39099.10 10696.82 43399.47 7896.55 25099.84 17698.56 12499.94 5199.55 137
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
usedtu_dtu_shiyan298.99 9398.86 11499.39 7299.73 3798.71 9799.05 6899.47 15899.16 9399.49 9499.12 18296.34 26399.93 5398.05 16299.36 33299.54 143
E5new99.05 8299.11 7398.85 17999.60 8797.30 24298.42 15199.63 7898.73 15099.26 15499.39 10098.71 5199.70 31398.43 13299.84 11499.54 143
E6new99.05 8299.11 7398.85 17999.60 8797.30 24298.42 15199.63 7898.73 15099.26 15499.39 10098.71 5199.70 31398.43 13299.84 11499.54 143
E699.05 8299.11 7398.85 17999.60 8797.30 24298.42 15199.63 7898.73 15099.26 15499.39 10098.71 5199.70 31398.43 13299.84 11499.54 143
E599.05 8299.11 7398.85 17999.60 8797.30 24298.42 15199.63 7898.73 15099.26 15499.39 10098.71 5199.70 31398.43 13299.84 11499.54 143
AstraMVS98.16 24798.07 24698.41 27699.51 13295.86 33598.00 21395.14 49198.97 12699.43 10799.24 14493.25 36899.84 17699.21 7099.87 10099.54 143
WBMVS95.18 43094.78 43296.37 43697.68 46289.74 50195.80 43198.73 37397.54 27098.30 32298.44 34770.06 51199.82 20696.62 30499.87 10099.54 143
test250692.39 47791.89 47993.89 49799.38 18382.28 53199.32 2666.03 53899.08 11398.77 26199.57 4966.26 52199.84 17698.71 11099.95 3999.54 143
ECVR-MVScopyleft96.42 37996.61 36395.85 46299.38 18388.18 50899.22 4686.00 53299.08 11399.36 12799.57 4988.47 43599.82 20698.52 12799.95 3999.54 143
v14419298.54 18498.57 16198.45 27199.21 23495.98 32997.63 27799.36 20797.15 31899.32 14199.18 16295.84 29199.84 17699.50 5099.91 8099.54 143
v192192098.54 18498.60 15798.38 28099.20 23895.76 34297.56 28999.36 20797.23 31099.38 12099.17 16696.02 27799.84 17699.57 3999.90 8899.54 143
MP-MVScopyleft98.46 19698.09 24199.54 3199.57 10299.22 3198.50 13799.19 27897.61 26097.58 38298.66 31197.40 19199.88 11594.72 39299.60 26699.54 143
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MIMVSNet199.38 2799.32 3999.55 2899.86 1499.19 4199.41 1799.59 9599.59 3699.71 4999.57 4997.12 21099.90 8199.21 7099.87 10099.54 143
ACMMPcopyleft98.75 13798.50 17299.52 4499.56 11099.16 4898.87 8999.37 20397.16 31698.82 25299.01 21997.71 15999.87 13596.29 33599.69 22599.54 143
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
SMA-MVScopyleft98.40 20498.03 24999.51 4999.16 25399.21 3298.05 20299.22 27194.16 44898.98 20899.10 18797.52 18199.79 24596.45 32399.64 24999.53 157
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
HFP-MVS98.71 14198.44 18599.51 4999.49 14699.16 4898.52 13099.31 23297.47 27698.58 29298.50 34097.97 13699.85 15896.57 30999.59 27099.53 157
UniMVSNet_NR-MVSNet98.86 11598.68 14099.40 7199.17 25198.74 9197.68 26799.40 19599.14 9799.06 18898.59 32796.71 24299.93 5398.57 12199.77 17099.53 157
E498.87 11198.88 10798.81 19099.52 12997.23 25297.62 27899.61 8798.58 17099.18 17799.33 11898.29 9899.69 32297.99 17099.83 12699.52 160
GST-MVS98.61 16998.30 21099.52 4499.51 13299.20 3898.26 17099.25 26397.44 28498.67 27498.39 35297.68 16099.85 15896.00 34999.51 29999.52 160
MGCNet97.44 31097.01 32998.72 21796.42 51096.74 29497.20 33791.97 52098.46 18098.30 32298.79 28092.74 38399.91 7499.30 6299.94 5199.52 160
TDRefinement99.42 2399.38 2899.55 2899.76 3099.33 2099.68 699.71 4799.38 5999.53 8399.61 4398.64 6199.80 23298.24 14499.84 11499.52 160
FE-MVSNET299.15 5799.22 5498.94 16499.70 5697.49 22598.62 11899.67 6898.85 14499.34 13299.54 6298.47 7799.81 22398.93 9299.91 8099.51 164
v114498.60 17198.66 14598.41 27699.36 19095.90 33397.58 28799.34 21997.51 27299.27 15099.15 17496.34 26399.80 23299.47 5399.93 5799.51 164
v2v48298.56 17798.62 15298.37 28399.42 17495.81 33997.58 28799.16 28997.90 23599.28 14899.01 21995.98 28499.79 24599.33 5999.90 8899.51 164
CPTT-MVS97.84 28197.36 30699.27 9999.31 20398.46 11698.29 16599.27 25594.90 42697.83 36598.37 35594.90 32099.84 17693.85 42099.54 28999.51 164
casdiffseed41469214799.09 7299.12 7199.01 15099.55 11697.91 18398.30 16499.68 6299.04 11899.19 17299.37 10498.98 2899.61 37498.13 15399.83 12699.50 168
viewdifsd2359ckpt1198.84 11899.04 8698.24 29799.56 11095.51 34997.38 31499.70 5299.16 9399.57 7299.40 9798.26 10499.71 30698.55 12599.82 13399.50 168
viewmsd2359difaftdt98.84 11899.04 8698.24 29799.56 11095.51 34997.38 31499.70 5299.16 9399.57 7299.40 9798.26 10499.71 30698.55 12599.82 13399.50 168
LuminaMVS98.39 21098.20 22698.98 15799.50 13897.49 22597.78 24997.69 42498.75 14999.49 9499.25 14292.30 39099.94 4199.14 7599.88 9599.50 168
DU-MVS98.82 12498.63 15099.39 7299.16 25398.74 9197.54 29399.25 26398.84 14799.06 18898.76 28996.76 23799.93 5398.57 12199.77 17099.50 168
NR-MVSNet98.95 10198.82 12099.36 7499.16 25398.72 9699.22 4699.20 27499.10 10699.72 4798.76 28996.38 26099.86 14498.00 16899.82 13399.50 168
casdiffmvs_mvgpermissive99.12 6999.16 6298.99 15399.43 17297.73 20898.00 21399.62 8499.22 7999.55 7799.22 15198.93 3399.75 28198.66 11399.81 14099.50 168
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMH+96.62 999.08 7899.00 9399.33 8999.71 4898.83 8698.60 12199.58 9899.11 9999.53 8399.18 16298.81 3999.67 33696.71 29399.77 17099.50 168
SymmetryMVS98.05 25597.71 28299.09 13299.29 20997.83 19298.28 16697.64 42999.24 7698.80 25698.85 26489.76 42299.94 4198.04 16399.50 30799.49 176
DVP-MVS++98.90 10798.70 13799.51 4998.43 39999.15 5299.43 1599.32 22798.17 20999.26 15499.02 20898.18 11699.88 11597.07 25699.45 31599.49 176
PC_three_145293.27 46499.40 11698.54 33198.22 11197.00 51695.17 38099.45 31599.49 176
GeoE99.05 8298.99 9599.25 10499.44 16798.35 12898.73 10399.56 11598.42 18298.91 23098.81 27798.94 3199.91 7498.35 13999.73 19499.49 176
h-mvs3397.77 28597.33 30999.10 12899.21 23497.84 19198.35 16198.57 38799.11 9998.58 29299.02 20888.65 43399.96 1398.11 15596.34 49899.49 176
IterMVS-SCA-FT97.85 28098.18 23196.87 41899.27 21591.16 48495.53 44099.25 26399.10 10699.41 11399.35 11193.10 37499.96 1398.65 11499.94 5199.49 176
new-patchmatchnet98.35 21398.74 12797.18 39999.24 22692.23 46596.42 38999.48 14998.30 19299.69 5599.53 6497.44 18999.82 20698.84 9999.77 17099.49 176
APD-MVScopyleft98.10 24997.67 28499.42 6799.11 26398.93 7997.76 25599.28 25294.97 42498.72 26798.77 28497.04 21499.85 15893.79 42199.54 28999.49 176
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EPP-MVSNet98.30 22298.04 24899.07 13599.56 11097.83 19299.29 3698.07 41599.03 12098.59 29099.13 17992.16 39299.90 8196.87 27799.68 23199.49 176
DeepC-MVS97.60 498.97 9898.93 10099.10 12899.35 19597.98 17398.01 21299.46 16397.56 26699.54 7999.50 6898.97 2999.84 17698.06 16099.92 7199.49 176
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMM96.08 1298.91 10598.73 12999.48 5799.55 11699.14 5798.07 19999.37 20397.62 25799.04 19898.96 23698.84 3799.79 24597.43 22899.65 24799.49 176
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
guyue98.01 25997.93 26398.26 29399.45 16595.48 35398.08 19596.24 47198.89 13799.34 13299.14 17791.32 40799.82 20699.07 8099.83 12699.48 187
DVP-MVScopyleft98.77 13598.52 16899.52 4499.50 13899.21 3298.02 20998.84 35397.97 22799.08 18699.02 20897.61 17099.88 11596.99 26399.63 25599.48 187
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
SR-MVS98.71 14198.43 18699.57 2199.18 24999.35 1698.36 16099.29 24898.29 19598.88 23898.85 26497.53 17999.87 13596.14 34499.31 34499.48 187
TSAR-MVS + MP.98.63 16598.49 17799.06 14199.64 7697.90 18598.51 13598.94 32896.96 32699.24 16498.89 25697.83 14999.81 22396.88 27699.49 31099.48 187
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
VDDNet98.21 23797.95 25899.01 15099.58 9397.74 20699.01 7197.29 44099.67 2098.97 21299.50 6890.45 41699.80 23297.88 17999.20 36799.48 187
IterMVS97.73 28798.11 24096.57 42999.24 22690.28 49595.52 44299.21 27298.86 14199.33 13599.33 11893.11 37399.94 4198.49 12899.94 5199.48 187
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IS-MVSNet98.19 24097.90 26799.08 13399.57 10297.97 17499.31 3098.32 40299.01 12298.98 20899.03 20791.59 40099.79 24595.49 37499.80 15199.48 187
ACMP95.32 1598.41 20198.09 24199.36 7499.51 13298.79 8997.68 26799.38 19995.76 39698.81 25498.82 27498.36 8999.82 20694.75 38999.77 17099.48 187
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MCST-MVS98.00 26097.63 29099.10 12899.24 22698.17 14596.89 35898.73 37395.66 39897.92 35697.70 41797.17 20799.66 34996.18 34299.23 36199.47 195
3Dnovator+97.89 398.69 15098.51 16999.24 10698.81 33498.40 12099.02 7099.19 27898.99 12398.07 34499.28 12997.11 21299.84 17696.84 28099.32 34299.47 195
hybridcas99.08 7899.13 7098.92 17099.54 12297.61 21998.22 17699.66 6999.27 7399.40 11699.24 14498.47 7799.70 31398.59 11899.80 15199.46 197
diffmvs_AUTHOR98.50 19298.59 15998.23 30099.35 19595.48 35396.61 37599.60 8998.37 18398.90 23199.00 22397.37 19399.76 26998.22 14799.85 10999.46 197
HPM-MVS++copyleft98.10 24997.64 28999.48 5799.09 26899.13 6097.52 29598.75 37097.46 28196.90 42797.83 40896.01 27899.84 17695.82 36199.35 33599.46 197
V4298.78 13298.78 12598.76 20799.44 16797.04 27298.27 16999.19 27897.87 23799.25 16299.16 16896.84 22799.78 25799.21 7099.84 11499.46 197
APD-MVS_3200maxsize98.84 11898.61 15699.53 3899.19 24199.27 2698.49 14099.33 22598.64 15999.03 20198.98 23097.89 14599.85 15896.54 31799.42 32599.46 197
UniMVSNet (Re)98.87 11198.71 13499.35 8099.24 22698.73 9497.73 26299.38 19998.93 13199.12 18098.73 29296.77 23599.86 14498.63 11699.80 15199.46 197
SR-MVS-dyc-post98.81 12698.55 16399.57 2199.20 23899.38 1298.48 14399.30 24098.64 15998.95 21898.96 23697.49 18699.86 14496.56 31399.39 32899.45 203
RE-MVS-def98.58 16099.20 23899.38 1298.48 14399.30 24098.64 15998.95 21898.96 23697.75 15796.56 31399.39 32899.45 203
HQP_MVS97.99 26397.67 28498.93 16799.19 24197.65 21597.77 25299.27 25598.20 20697.79 36897.98 39694.90 32099.70 31394.42 40199.51 29999.45 203
plane_prior599.27 25599.70 31394.42 40199.51 29999.45 203
lessismore_v098.97 15999.73 3797.53 22486.71 53199.37 12499.52 6789.93 41999.92 6598.99 8899.72 20399.44 207
TAMVS98.24 23398.05 24798.80 19399.07 27297.18 26297.88 23598.81 35896.66 34899.17 17999.21 15394.81 32699.77 26396.96 26799.88 9599.44 207
DeepPCF-MVS96.93 598.32 21998.01 25199.23 10898.39 40498.97 7395.03 45999.18 28296.88 33499.33 13598.78 28298.16 12099.28 46396.74 28899.62 25999.44 207
3Dnovator98.27 298.81 12698.73 12999.05 14298.76 34097.81 20099.25 4399.30 24098.57 17298.55 29899.33 11897.95 13899.90 8197.16 24799.67 23799.44 207
E298.70 14698.68 14098.73 21599.40 17997.10 26997.48 30199.57 10698.09 22099.00 20399.20 15597.90 14199.67 33697.73 19999.77 17099.43 211
E398.69 15098.68 14098.73 21599.40 17997.10 26997.48 30199.57 10698.09 22099.00 20399.20 15597.90 14199.67 33697.73 19999.77 17099.43 211
MVSFormer98.26 22998.43 18697.77 34498.88 31993.89 42999.39 2099.56 11599.11 9998.16 33498.13 38193.81 35999.97 699.26 6599.57 27999.43 211
jason97.45 30997.35 30797.76 34799.24 22693.93 42595.86 42798.42 39894.24 44598.50 30498.13 38194.82 32499.91 7497.22 24399.73 19499.43 211
jason: jason.
NCCC97.86 27597.47 30199.05 14298.61 37498.07 16196.98 35098.90 33897.63 25697.04 41797.93 40195.99 28399.66 34995.31 37798.82 41099.43 211
Anonymous2024052198.69 15098.87 11098.16 30799.77 2795.11 37699.08 6299.44 17599.34 6499.33 13599.55 5694.10 35499.94 4199.25 6799.96 2899.42 216
MVS_111021_HR98.25 23298.08 24498.75 20999.09 26897.46 23195.97 41899.27 25597.60 26297.99 35298.25 37098.15 12299.38 44896.87 27799.57 27999.42 216
COLMAP_ROBcopyleft96.50 1098.99 9398.85 11799.41 6999.58 9399.10 6598.74 9999.56 11599.09 10999.33 13599.19 15898.40 8699.72 30595.98 35199.76 18699.42 216
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SED-MVS98.91 10598.72 13199.49 5599.49 14699.17 4398.10 19299.31 23298.03 22399.66 6099.02 20898.36 8999.88 11596.91 26999.62 25999.41 219
OPU-MVS98.82 18898.59 37998.30 13298.10 19298.52 33598.18 11698.75 49094.62 39399.48 31199.41 219
our_test_397.39 31597.73 28096.34 43798.70 35489.78 50094.61 47498.97 32796.50 35499.04 19898.85 26495.98 28499.84 17697.26 24099.67 23799.41 219
casdiffmvspermissive98.95 10199.00 9398.81 19099.38 18397.33 23997.82 24399.57 10699.17 9299.35 12999.17 16698.35 9399.69 32298.46 12999.73 19499.41 219
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
YYNet197.60 29697.67 28497.39 39199.04 28193.04 44895.27 45198.38 40197.25 30498.92 22998.95 24095.48 30499.73 29596.99 26398.74 41399.41 219
MDA-MVSNet_test_wron97.60 29697.66 28797.41 39099.04 28193.09 44495.27 45198.42 39897.26 30398.88 23898.95 24095.43 30699.73 29597.02 25998.72 41599.41 219
GBi-Net98.65 16198.47 18099.17 11598.90 31398.24 13799.20 4999.44 17598.59 16798.95 21899.55 5694.14 35099.86 14497.77 19199.69 22599.41 219
test198.65 16198.47 18099.17 11598.90 31398.24 13799.20 4999.44 17598.59 16798.95 21899.55 5694.14 35099.86 14497.77 19199.69 22599.41 219
FMVSNet199.17 5299.17 6099.17 11599.55 11698.24 13799.20 4999.44 17599.21 8199.43 10799.55 5697.82 15299.86 14498.42 13699.89 9499.41 219
test_fmvs197.72 28897.94 26197.07 40798.66 36992.39 46097.68 26799.81 3295.20 42099.54 7999.44 8591.56 40299.41 44399.78 2199.77 17099.40 228
viewdifsd2359ckpt0798.71 14198.86 11498.26 29399.43 17295.65 34397.20 33799.66 6999.20 8399.29 14699.01 21998.29 9899.73 29597.92 17599.75 19099.39 229
viewmanbaseed2359cas98.58 17598.54 16598.70 21999.28 21297.13 26897.47 30599.55 11997.55 26898.96 21798.92 24497.77 15599.59 38397.59 21199.77 17099.39 229
KD-MVS_self_test99.25 4099.18 5999.44 6599.63 8299.06 7098.69 10899.54 12599.31 6899.62 6999.53 6497.36 19499.86 14499.24 6999.71 21299.39 229
v14898.45 19898.60 15798.00 32599.44 16794.98 37997.44 30999.06 30698.30 19299.32 14198.97 23296.65 24699.62 36798.37 13899.85 10999.39 229
test20.0398.78 13298.77 12698.78 20099.46 16097.20 25897.78 24999.24 26899.04 11899.41 11398.90 25097.65 16399.76 26997.70 20199.79 15899.39 229
CDPH-MVS97.26 32796.66 35899.07 13599.00 29498.15 14696.03 41599.01 32191.21 49497.79 36897.85 40696.89 22599.69 32292.75 45499.38 33199.39 229
EPNet96.14 39395.44 40898.25 29590.76 53595.50 35297.92 23094.65 49498.97 12692.98 51198.85 26489.12 42899.87 13595.99 35099.68 23199.39 229
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNVR-MVS98.17 24597.87 26999.07 13598.67 36498.24 13797.01 34798.93 33197.25 30497.62 37898.34 35997.27 20099.57 39296.42 32599.33 33999.39 229
DeepC-MVS_fast96.85 698.30 22298.15 23698.75 20998.61 37497.23 25297.76 25599.09 30297.31 29798.75 26498.66 31197.56 17499.64 36196.10 34899.55 28799.39 229
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SF-MVS98.53 18698.27 21699.32 9199.31 20398.75 9098.19 17799.41 19196.77 34398.83 24998.90 25097.80 15399.82 20695.68 36799.52 29699.38 238
test9_res93.28 43799.15 37599.38 238
BP-MVS197.40 31496.97 33198.71 21899.07 27296.81 28998.34 16397.18 44498.58 17098.17 33198.61 32484.01 47399.94 4198.97 8999.78 16399.37 240
OPM-MVS98.56 17798.32 20899.25 10499.41 17798.73 9497.13 34499.18 28297.10 31998.75 26498.92 24498.18 11699.65 35696.68 29799.56 28399.37 240
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
agg_prior292.50 46199.16 37399.37 240
AllTest98.44 19998.20 22699.16 11899.50 13898.55 10898.25 17199.58 9896.80 34098.88 23899.06 19697.65 16399.57 39294.45 39999.61 26499.37 240
TestCases99.16 11899.50 13898.55 10899.58 9896.80 34098.88 23899.06 19697.65 16399.57 39294.45 39999.61 26499.37 240
MDA-MVSNet-bldmvs97.94 26697.91 26698.06 31999.44 16794.96 38096.63 37499.15 29498.35 18598.83 24999.11 18494.31 34599.85 15896.60 30698.72 41599.37 240
MVSTER96.86 35796.55 36797.79 34297.91 44494.21 40697.56 28998.87 34497.49 27599.06 18899.05 20380.72 48699.80 23298.44 13099.82 13399.37 240
viewcassd2359sk1198.55 18198.51 16998.67 22499.29 20996.99 27597.39 31299.54 12597.73 24898.81 25499.08 19497.55 17599.66 34997.52 21999.67 23799.36 247
pmmvs597.64 29497.49 29898.08 31699.14 25895.12 37596.70 36999.05 31093.77 45898.62 28398.83 27193.23 36999.75 28198.33 14299.76 18699.36 247
Anonymous2023120698.21 23798.21 22598.20 30299.51 13295.43 35898.13 18599.32 22796.16 37398.93 22798.82 27496.00 27999.83 19497.32 23699.73 19499.36 247
train_agg97.10 34096.45 37499.07 13598.71 35098.08 15995.96 42099.03 31591.64 48695.85 46897.53 42696.47 25399.76 26993.67 42499.16 37399.36 247
PVSNet_BlendedMVS97.55 30197.53 29597.60 36998.92 30993.77 43396.64 37399.43 18194.49 43697.62 37899.18 16296.82 23099.67 33694.73 39099.93 5799.36 247
hybrid98.22 23498.27 21698.08 31699.13 26095.24 36796.61 37599.53 12997.43 28598.46 30898.97 23296.75 24099.65 35697.84 18499.69 22599.35 252
Anonymous2024052998.93 10398.87 11099.12 12499.19 24198.22 14299.01 7198.99 32499.25 7599.54 7999.37 10497.04 21499.80 23297.89 17699.52 29699.35 252
F-COLMAP97.30 32496.68 35499.14 12299.19 24198.39 12197.27 33199.30 24092.93 47296.62 44398.00 39495.73 29499.68 33292.62 45798.46 43599.35 252
viewdifsd2359ckpt1398.39 21098.29 21298.70 21999.26 22497.19 25997.51 29799.48 14996.94 32898.58 29298.82 27497.47 18899.55 39997.21 24499.33 33999.34 255
ppachtmachnet_test97.50 30297.74 27796.78 42498.70 35491.23 48394.55 47699.05 31096.36 36199.21 17098.79 28096.39 25899.78 25796.74 28899.82 13399.34 255
VDD-MVS98.56 17798.39 19399.07 13599.13 26098.07 16198.59 12297.01 44999.59 3699.11 18199.27 13194.82 32499.79 24598.34 14099.63 25599.34 255
testgi98.32 21998.39 19398.13 30999.57 10295.54 34797.78 24999.49 14797.37 29199.19 17297.65 41998.96 3099.49 42296.50 32098.99 39699.34 255
diffmvspermissive98.22 23498.24 22398.17 30599.00 29495.44 35796.38 39199.58 9897.79 24498.53 30198.50 34096.76 23799.74 28897.95 17499.64 24999.34 255
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UnsupCasMVSNet_eth97.89 27097.60 29298.75 20999.31 20397.17 26497.62 27899.35 21398.72 15698.76 26398.68 30692.57 38699.74 28897.76 19595.60 51299.34 255
viewmambaseed2359dif98.19 24098.26 21997.99 32799.02 29195.03 37896.59 37899.53 12996.21 36899.00 20398.99 22597.62 16899.61 37497.62 20799.72 20399.33 261
baseline98.96 10099.02 8998.76 20799.38 18397.26 25098.49 14099.50 13998.86 14199.19 17299.06 19698.23 10899.69 32298.71 11099.76 18699.33 261
MG-MVS96.77 36196.61 36397.26 39698.31 40993.06 44595.93 42398.12 41496.45 35997.92 35698.73 29293.77 36199.39 44691.19 48499.04 38799.33 261
DKM98.18 24297.95 25898.85 17999.35 19598.31 13196.68 37099.69 5596.90 33398.61 28598.77 28494.41 33898.93 48397.32 23699.84 11499.32 264
HQP4-MVS95.56 47499.54 40599.32 264
CDS-MVSNet97.69 29097.35 30798.69 22198.73 34497.02 27496.92 35798.75 37095.89 38698.59 29098.67 30892.08 39699.74 28896.72 29199.81 14099.32 264
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HQP-MVS97.00 35196.49 37098.55 25298.67 36496.79 29096.29 39899.04 31396.05 37695.55 47596.84 45393.84 35799.54 40592.82 45099.26 35699.32 264
RPSCF98.62 16898.36 19899.42 6799.65 7099.42 1098.55 12699.57 10697.72 25098.90 23199.26 13796.12 27499.52 41195.72 36499.71 21299.32 264
E3new98.41 20198.34 20298.62 23499.19 24196.90 28397.32 32299.50 13997.40 28898.63 27998.92 24497.21 20599.65 35697.34 23299.52 29699.31 269
MVP-Stereo98.08 25297.92 26498.57 24598.96 30196.79 29097.90 23399.18 28296.41 36098.46 30898.95 24095.93 28899.60 37896.51 31998.98 39999.31 269
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS98.40 20498.68 14097.54 37898.96 30197.99 17097.88 23599.36 20798.20 20699.63 6699.04 20598.76 4695.33 52796.56 31399.74 19199.31 269
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
VNet98.42 20098.30 21098.79 19798.79 33997.29 24798.23 17298.66 37899.31 6898.85 24598.80 27894.80 32799.78 25798.13 15399.13 37899.31 269
test_prior98.95 16398.69 35997.95 17899.03 31599.59 38399.30 273
USDC97.41 31397.40 30297.44 38898.94 30393.67 43695.17 45599.53 12994.03 45498.97 21299.10 18795.29 30999.34 45395.84 36099.73 19499.30 273
viewdifsd2359ckpt0998.13 24897.92 26498.77 20599.18 24997.35 23797.29 32699.53 12995.81 39398.09 34298.47 34496.34 26399.66 34997.02 25999.51 29999.29 275
test_fmvsm_n_192099.33 3099.45 2398.99 15399.57 10297.73 20897.93 22799.83 2699.22 7999.93 699.30 12599.42 1199.96 1399.85 699.99 599.29 275
FMVSNet298.49 19398.40 19098.75 20998.90 31397.14 26798.61 12099.13 29698.59 16799.19 17299.28 12994.14 35099.82 20697.97 17299.80 15199.29 275
RoMa-SfM98.46 19698.27 21699.02 14899.35 19598.32 13097.56 28999.70 5295.88 38799.38 12098.65 31396.41 25699.46 43397.78 18999.71 21299.28 278
gbinet_0.2-2-1-0.0295.44 42294.55 43798.14 30895.99 51895.34 36494.71 46798.29 40496.00 38196.05 46590.50 52784.99 46299.79 24597.33 23497.07 48999.28 278
XVG-OURS-SEG-HR98.49 19398.28 21399.14 12299.49 14698.83 8696.54 37999.48 14997.32 29699.11 18198.61 32499.33 1599.30 45996.23 33798.38 43799.28 278
mamba_040898.80 12898.88 10798.55 25299.27 21596.50 30798.00 21399.60 8998.93 13199.22 16798.84 26998.59 6799.89 9797.74 19799.72 20399.27 281
SSM_0407298.80 12898.88 10798.56 25099.27 21596.50 30798.00 21399.60 8998.93 13199.22 16798.84 26998.59 6799.90 8197.74 19799.72 20399.27 281
SSM_040798.86 11598.96 9998.55 25299.27 21596.50 30798.04 20499.66 6999.09 10999.22 16799.02 20898.79 4399.87 13597.87 18199.72 20399.27 281
test1298.93 16798.58 38197.83 19298.66 37896.53 44895.51 30299.69 32299.13 37899.27 281
DSMNet-mixed97.42 31297.60 29296.87 41899.15 25791.46 47398.54 12899.12 29792.87 47597.58 38299.63 3996.21 26999.90 8195.74 36399.54 28999.27 281
N_pmnet97.63 29597.17 31798.99 15399.27 21597.86 18995.98 41793.41 51095.25 41799.47 10098.90 25095.63 29799.85 15896.91 26999.73 19499.27 281
ambc98.24 29798.82 33195.97 33198.62 11899.00 32399.27 15099.21 15396.99 21999.50 41896.55 31699.50 30799.26 287
LFMVS97.20 33496.72 35198.64 22898.72 34696.95 27998.93 8294.14 50599.74 1298.78 25899.01 21984.45 46899.73 29597.44 22799.27 35299.25 288
FMVSNet596.01 39795.20 42398.41 27697.53 47096.10 32198.74 9999.50 13997.22 31398.03 34999.04 20569.80 51299.88 11597.27 23999.71 21299.25 288
BH-RMVSNet96.83 35896.58 36697.58 37198.47 39294.05 41396.67 37197.36 43496.70 34797.87 36197.98 39695.14 31599.44 43890.47 49498.58 43099.25 288
testf199.25 4099.16 6299.51 4999.89 699.63 398.71 10699.69 5598.90 13599.43 10799.35 11198.86 3599.67 33697.81 18699.81 14099.24 291
APD_test299.25 4099.16 6299.51 4999.89 699.63 398.71 10699.69 5598.90 13599.43 10799.35 11198.86 3599.67 33697.81 18699.81 14099.24 291
SSM_040498.90 10799.01 9198.57 24599.42 17496.59 29998.13 18599.66 6999.09 10999.30 14599.02 20898.79 4399.89 9797.87 18199.80 15199.23 293
旧先验198.82 33197.45 23298.76 36698.34 35995.50 30399.01 39399.23 293
test22298.92 30996.93 28195.54 43998.78 36385.72 52096.86 43198.11 38494.43 33799.10 38399.23 293
XVG-ACMP-BASELINE98.56 17798.34 20299.22 10999.54 12298.59 10597.71 26399.46 16397.25 30498.98 20898.99 22597.54 17799.84 17695.88 35499.74 19199.23 293
FMVSNet397.50 30297.24 31398.29 29198.08 43595.83 33797.86 23998.91 33797.89 23698.95 21898.95 24087.06 44299.81 22397.77 19199.69 22599.23 293
icg_test_0407_298.20 23998.38 19597.65 36299.03 28494.03 41695.78 43299.45 16798.16 21299.06 18898.71 29598.27 10299.68 33297.50 22099.45 31599.22 298
IMVS_040798.39 21098.64 14897.66 36099.03 28494.03 41698.10 19299.45 16798.16 21299.06 18898.71 29598.27 10299.71 30697.50 22099.45 31599.22 298
IMVS_040498.07 25398.20 22697.69 35599.03 28494.03 41696.67 37199.45 16798.16 21298.03 34998.71 29596.80 23399.82 20697.50 22099.45 31599.22 298
IMVS_040398.34 21498.56 16297.66 36099.03 28494.03 41697.98 22199.45 16798.16 21298.89 23498.71 29597.90 14199.74 28897.50 22099.45 31599.22 298
无先验95.74 43498.74 37289.38 50799.73 29592.38 46499.22 298
blended_shiyan895.98 40095.33 41497.94 33097.05 49194.87 38595.34 44998.59 38496.17 36997.09 41392.39 51887.62 44199.76 26997.65 20496.05 50999.20 303
tttt051795.64 41494.98 42797.64 36599.36 19093.81 43198.72 10490.47 52498.08 22298.67 27498.34 35973.88 50799.92 6597.77 19199.51 29999.20 303
pmmvs-eth3d98.47 19598.34 20298.86 17899.30 20797.76 20497.16 34299.28 25295.54 40599.42 11199.19 15897.27 20099.63 36497.89 17699.97 2199.20 303
MS-PatchMatch97.68 29197.75 27697.45 38798.23 42193.78 43297.29 32698.84 35396.10 37598.64 27898.65 31396.04 27699.36 44996.84 28099.14 37699.20 303
新几何198.91 17298.94 30397.76 20498.76 36687.58 51796.75 43698.10 38594.80 32799.78 25792.73 45599.00 39499.20 303
PHI-MVS98.29 22597.95 25899.34 8398.44 39799.16 4898.12 18999.38 19996.01 38098.06 34598.43 34897.80 15399.67 33695.69 36699.58 27599.20 303
blended_shiyan695.99 39995.33 41497.95 32997.06 48994.89 38395.34 44998.58 38596.17 36997.06 41592.41 51787.64 44099.76 26997.64 20596.09 50399.19 309
GDP-MVS97.50 30297.11 32498.67 22499.02 29196.85 28798.16 18299.71 4798.32 19098.52 30398.54 33183.39 47799.95 2598.79 10199.56 28399.19 309
Anonymous20240521197.90 26897.50 29799.08 13398.90 31398.25 13698.53 12996.16 47298.87 13999.11 18198.86 26190.40 41799.78 25797.36 23199.31 34499.19 309
CANet97.87 27497.76 27598.19 30497.75 45395.51 34996.76 36599.05 31097.74 24796.93 42198.21 37595.59 29999.89 9797.86 18399.93 5799.19 309
XVG-OURS98.53 18698.34 20299.11 12699.50 13898.82 8895.97 41899.50 13997.30 29899.05 19698.98 23099.35 1499.32 45695.72 36499.68 23199.18 313
WTY-MVS96.67 36496.27 38297.87 33798.81 33494.61 39696.77 36497.92 41994.94 42597.12 41097.74 41491.11 40999.82 20693.89 41798.15 45199.18 313
Vis-MVSNet (Re-imp)97.46 30797.16 31898.34 28699.55 11696.10 32198.94 8198.44 39598.32 19098.16 33498.62 32288.76 42999.73 29593.88 41899.79 15899.18 313
TinyColmap97.89 27097.98 25497.60 36998.86 32294.35 40296.21 40399.44 17597.45 28399.06 18898.88 25897.99 13599.28 46394.38 40599.58 27599.18 313
wanda-best-256-51295.48 42094.74 43497.68 35696.53 50494.12 41094.17 48798.57 38795.84 38996.71 43791.16 52386.05 45299.76 26997.57 21296.09 50399.17 317
FE-blended-shiyan795.48 42094.74 43497.68 35696.53 50494.12 41094.17 48798.57 38795.84 38996.71 43791.16 52386.05 45299.76 26997.57 21296.09 50399.17 317
usedtu_blend_shiyan596.20 39295.62 39797.94 33096.53 50494.93 38198.83 9699.59 9598.89 13796.71 43791.16 52386.05 45299.73 29596.70 29496.09 50399.17 317
testdata98.09 31398.93 30595.40 35998.80 36090.08 50397.45 39698.37 35595.26 31099.70 31393.58 42898.95 40299.17 317
lupinMVS97.06 34596.86 34097.65 36298.88 31993.89 42995.48 44397.97 41793.53 46198.16 33497.58 42393.81 35999.91 7496.77 28599.57 27999.17 317
Patchmtry97.35 31996.97 33198.50 26697.31 48296.47 31098.18 17898.92 33598.95 13098.78 25899.37 10485.44 46099.85 15895.96 35299.83 12699.17 317
usedtu_dtu_shiyan197.37 31697.13 32298.11 31099.03 28495.40 35994.47 47898.99 32496.87 33597.97 35397.81 40992.12 39399.75 28197.49 22599.43 32399.16 323
FE-MVSNET397.37 31697.13 32298.11 31099.03 28495.40 35994.47 47898.99 32496.87 33597.97 35397.81 40992.12 39399.75 28197.49 22599.43 32399.16 323
SD_040396.28 38695.83 39097.64 36598.72 34694.30 40398.87 8998.77 36497.80 24296.53 44898.02 39397.34 19599.47 42976.93 52799.48 31199.16 323
RRT-MVS97.88 27297.98 25497.61 36898.15 42893.77 43398.97 7799.64 7699.16 9398.69 27099.42 8991.60 39999.89 9797.63 20698.52 43499.16 323
sss97.21 33396.93 33398.06 31998.83 32895.22 37196.75 36698.48 39494.49 43697.27 40597.90 40292.77 38299.80 23296.57 30999.32 34299.16 323
CSCG98.68 15698.50 17299.20 11099.45 16598.63 10098.56 12599.57 10697.87 23798.85 24598.04 39197.66 16299.84 17696.72 29199.81 14099.13 328
MVS_111021_LR98.30 22298.12 23998.83 18699.16 25398.03 16696.09 41399.30 24097.58 26398.10 34198.24 37298.25 10699.34 45396.69 29699.65 24799.12 329
miper_lstm_enhance97.18 33697.16 31897.25 39798.16 42792.85 45195.15 45799.31 23297.25 30498.74 26698.78 28290.07 41899.78 25797.19 24599.80 15199.11 330
testing393.51 45992.09 47297.75 34898.60 37694.40 40097.32 32295.26 49097.56 26696.79 43595.50 48453.57 53699.77 26395.26 37898.97 40099.08 331
原ACMM198.35 28598.90 31396.25 31898.83 35792.48 47996.07 46398.10 38595.39 30799.71 30692.61 45898.99 39699.08 331
QAPM97.31 32296.81 34698.82 18898.80 33797.49 22599.06 6699.19 27890.22 50197.69 37499.16 16896.91 22499.90 8190.89 49099.41 32699.07 333
PAPM_NR96.82 36096.32 37898.30 29099.07 27296.69 29797.48 30198.76 36695.81 39396.61 44496.47 46394.12 35399.17 47090.82 49297.78 46599.06 334
eth_miper_zixun_eth97.23 33197.25 31297.17 40198.00 43992.77 45394.71 46799.18 28297.27 30298.56 29698.74 29191.89 39799.69 32297.06 25899.81 14099.05 335
D2MVS97.84 28197.84 27197.83 33999.14 25894.74 39096.94 35398.88 34295.84 38998.89 23498.96 23694.40 34099.69 32297.55 21499.95 3999.05 335
c3_l97.36 31897.37 30597.31 39298.09 43493.25 44395.01 46099.16 28997.05 32198.77 26198.72 29492.88 37999.64 36196.93 26899.76 18699.05 335
PLCcopyleft94.65 1696.51 37195.73 39398.85 17998.75 34297.91 18396.42 38999.06 30690.94 49895.59 47297.38 43994.41 33899.59 38390.93 48898.04 46099.05 335
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tfpnnormal98.90 10798.90 10498.91 17299.67 6797.82 19799.00 7399.44 17599.45 5099.51 9299.24 14498.20 11599.86 14495.92 35399.69 22599.04 339
CANet_DTU97.26 32797.06 32697.84 33897.57 46594.65 39596.19 40598.79 36197.23 31095.14 48598.24 37293.22 37099.84 17697.34 23299.84 11499.04 339
PM-MVS98.82 12498.72 13199.12 12499.64 7698.54 11197.98 22199.68 6297.62 25799.34 13299.18 16297.54 17799.77 26397.79 18899.74 19199.04 339
TestfortrainingZip98.97 15998.30 41098.43 11998.68 10998.26 40597.76 24698.86 24498.16 38095.15 31499.47 42997.55 47099.02 342
TSAR-MVS + GP.98.18 24297.98 25498.77 20598.71 35097.88 18796.32 39698.66 37896.33 36299.23 16698.51 33697.48 18799.40 44497.16 24799.46 31399.02 342
DIV-MVS_self_test97.02 34896.84 34297.58 37197.82 45094.03 41694.66 47199.16 28997.04 32298.63 27998.71 29588.69 43099.69 32297.00 26199.81 14099.01 344
GA-MVS95.86 40695.32 41697.49 38398.60 37694.15 40993.83 49897.93 41895.49 40796.68 44097.42 43783.21 47899.30 45996.22 33898.55 43299.01 344
OMC-MVS97.88 27297.49 29899.04 14498.89 31898.63 10096.94 35399.25 26395.02 42298.53 30198.51 33697.27 20099.47 42993.50 43299.51 29999.01 344
cl____97.02 34896.83 34397.58 37197.82 45094.04 41594.66 47199.16 28997.04 32298.63 27998.71 29588.68 43299.69 32297.00 26199.81 14099.00 347
pmmvs497.58 29997.28 31098.51 26298.84 32696.93 28195.40 44798.52 39293.60 46098.61 28598.65 31395.10 31699.60 37896.97 26699.79 15898.99 348
blend_shiyan492.09 48390.16 49097.88 33596.78 49894.93 38195.24 45398.58 38596.22 36796.07 46391.42 52263.46 53199.73 29596.70 29476.98 53198.98 349
EPNet_dtu94.93 43694.78 43295.38 47893.58 52687.68 51096.78 36395.69 48697.35 29389.14 52698.09 38788.15 43899.49 42294.95 38699.30 34898.98 349
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t96.50 37395.77 39198.69 22199.48 15497.43 23497.84 24299.55 11981.42 52696.51 45298.58 32895.53 30099.67 33693.41 43599.58 27598.98 349
PVSNet_Blended96.88 35596.68 35497.47 38698.92 30993.77 43394.71 46799.43 18190.98 49797.62 37897.36 44196.82 23099.67 33694.73 39099.56 28398.98 349
APD_test198.83 12198.66 14599.34 8399.78 2499.47 898.42 15199.45 16798.28 19798.98 20899.19 15897.76 15699.58 39096.57 30999.55 28798.97 353
PAPR95.29 42694.47 43897.75 34897.50 47695.14 37494.89 46498.71 37591.39 49295.35 48295.48 48694.57 33499.14 47384.95 51497.37 48098.97 353
EGC-MVSNET85.24 49480.54 49799.34 8399.77 2799.20 3899.08 6299.29 24812.08 53420.84 53599.42 8997.55 17599.85 15897.08 25599.72 20398.96 355
thisisatest053095.27 42794.45 43997.74 35099.19 24194.37 40197.86 23990.20 52597.17 31598.22 32997.65 41973.53 50899.90 8196.90 27499.35 33598.95 356
mvs_anonymous97.83 28398.16 23596.87 41898.18 42491.89 46797.31 32498.90 33897.37 29198.83 24999.46 8096.28 26699.79 24598.90 9498.16 45098.95 356
baseline195.96 40395.44 40897.52 38098.51 39093.99 42398.39 15796.09 47698.21 20298.40 31897.76 41386.88 44399.63 36495.42 37589.27 52598.95 356
CLD-MVS97.49 30597.16 31898.48 26899.07 27297.03 27394.71 46799.21 27294.46 43898.06 34597.16 44797.57 17399.48 42694.46 39899.78 16398.95 356
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MSLP-MVS++98.02 25798.14 23897.64 36598.58 38195.19 37297.48 30199.23 27097.47 27697.90 35898.62 32297.04 21498.81 48897.55 21499.41 32698.94 360
DELS-MVS98.27 22798.20 22698.48 26898.86 32296.70 29695.60 43899.20 27497.73 24898.45 31098.71 29597.50 18399.82 20698.21 14899.59 27098.93 361
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
cl2295.79 40995.39 41196.98 41196.77 49992.79 45294.40 48198.53 39194.59 43597.89 35998.17 37882.82 48299.24 46596.37 32899.03 38898.92 362
LS3D98.63 16598.38 19599.36 7497.25 48399.38 1299.12 6199.32 22799.21 8198.44 31198.88 25897.31 19699.80 23296.58 30799.34 33798.92 362
CMPMVSbinary75.91 2396.29 38595.44 40898.84 18596.25 51398.69 9897.02 34699.12 29788.90 51097.83 36598.86 26189.51 42598.90 48691.92 46899.51 29998.92 362
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LCM-MVSNet-Re98.64 16398.48 17899.11 12698.85 32598.51 11398.49 14099.83 2698.37 18399.69 5599.46 8098.21 11399.92 6594.13 41199.30 34898.91 365
mvsmamba97.57 30097.26 31198.51 26298.69 35996.73 29598.74 9997.25 44197.03 32497.88 36099.23 15090.95 41099.87 13596.61 30599.00 39498.91 365
DPM-MVS96.32 38395.59 40198.51 26298.76 34097.21 25794.54 47798.26 40591.94 48596.37 45697.25 44593.06 37699.43 44091.42 47998.74 41398.89 367
test_yl96.69 36296.29 38097.90 33298.28 41395.24 36797.29 32697.36 43498.21 20298.17 33197.86 40486.27 44799.55 39994.87 38798.32 43998.89 367
DCV-MVSNet96.69 36296.29 38097.90 33298.28 41395.24 36797.29 32697.36 43498.21 20298.17 33197.86 40486.27 44799.55 39994.87 38798.32 43998.89 367
SPE-MVS-test99.13 6699.09 8199.26 10199.13 26098.97 7399.31 3099.88 1599.44 5298.16 33498.51 33698.64 6199.93 5398.91 9399.85 10998.88 370
UnsupCasMVSNet_bld97.30 32496.92 33598.45 27199.28 21296.78 29396.20 40499.27 25595.42 41098.28 32698.30 36693.16 37199.71 30694.99 38397.37 48098.87 371
Effi-MVS+98.02 25797.82 27298.62 23498.53 38897.19 25997.33 32199.68 6297.30 29896.68 44097.46 43598.56 7399.80 23296.63 30398.20 44698.86 372
test_040298.76 13698.71 13498.93 16799.56 11098.14 14898.45 14799.34 21999.28 7298.95 21898.91 24798.34 9499.79 24595.63 36899.91 8098.86 372
PatchmatchNetpermissive95.58 41695.67 39695.30 48197.34 48087.32 51297.65 27396.65 46395.30 41497.07 41498.69 30484.77 46599.75 28194.97 38598.64 42498.83 374
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
testing3-293.78 45593.91 44693.39 50498.82 33181.72 53397.76 25595.28 48998.60 16696.54 44796.66 45865.85 52499.62 36796.65 30298.99 39698.82 375
test_vis1_rt97.75 28697.72 28197.83 33998.81 33496.35 31597.30 32599.69 5594.61 43497.87 36198.05 39096.26 26798.32 49798.74 10798.18 44798.82 375
CL-MVSNet_self_test97.44 31097.22 31598.08 31698.57 38395.78 34194.30 48498.79 36196.58 35198.60 28898.19 37794.74 33099.64 36196.41 32698.84 40798.82 375
miper_ehance_all_eth97.06 34597.03 32797.16 40397.83 44993.06 44594.66 47199.09 30295.99 38298.69 27098.45 34692.73 38499.61 37496.79 28299.03 38898.82 375
MIMVSNet96.62 36796.25 38397.71 35499.04 28194.66 39499.16 5596.92 45797.23 31097.87 36199.10 18786.11 45199.65 35691.65 47499.21 36598.82 375
hse-mvs297.46 30797.07 32598.64 22898.73 34497.33 23997.45 30797.64 42999.11 9998.58 29297.98 39688.65 43399.79 24598.11 15597.39 47998.81 380
GSMVS98.81 380
sam_mvs184.74 46698.81 380
SCA96.41 38096.66 35895.67 46898.24 41888.35 50695.85 42996.88 45896.11 37497.67 37598.67 30893.10 37499.85 15894.16 40799.22 36298.81 380
Patchmatch-RL test97.26 32797.02 32897.99 32799.52 12995.53 34896.13 41099.71 4797.47 27699.27 15099.16 16884.30 47199.62 36797.89 17699.77 17098.81 380
AUN-MVS96.24 39195.45 40798.60 24098.70 35497.22 25597.38 31497.65 42795.95 38495.53 47997.96 40082.11 48599.79 24596.31 33297.44 47698.80 385
ITE_SJBPF98.87 17699.22 23298.48 11599.35 21397.50 27398.28 32698.60 32697.64 16699.35 45293.86 41999.27 35298.79 386
tpm94.67 43894.34 44395.66 46997.68 46288.42 50597.88 23594.90 49294.46 43896.03 46798.56 33078.66 49799.79 24595.88 35495.01 51598.78 387
Patchmatch-test96.55 37096.34 37797.17 40198.35 40693.06 44598.40 15697.79 42097.33 29498.41 31498.67 30883.68 47699.69 32295.16 38199.31 34498.77 388
EC-MVSNet99.09 7299.05 8599.20 11099.28 21298.93 7999.24 4499.84 2399.08 11398.12 33998.37 35598.72 5099.90 8199.05 8399.77 17098.77 388
PMMVS96.51 37195.98 38698.09 31397.53 47095.84 33694.92 46298.84 35391.58 48896.05 46595.58 48195.68 29699.66 34995.59 37198.09 45498.76 390
test_method79.78 49579.50 49880.62 51380.21 53845.76 54170.82 52998.41 40031.08 53380.89 53397.71 41584.85 46497.37 51291.51 47880.03 52998.75 391
ab-mvs98.41 20198.36 19898.59 24199.19 24197.23 25299.32 2698.81 35897.66 25498.62 28399.40 9796.82 23099.80 23295.88 35499.51 29998.75 391
ELoFTR97.81 28497.74 27798.04 32299.39 18195.79 34097.28 33099.58 9894.13 44999.38 12099.37 10493.31 36799.60 37897.23 24299.96 2898.74 393
CHOSEN 280x42095.51 41995.47 40595.65 47098.25 41688.27 50793.25 50898.88 34293.53 46194.65 49497.15 44886.17 44999.93 5397.41 22999.93 5798.73 394
test_fmvsmvis_n_192099.26 3999.49 1698.54 25799.66 6996.97 27698.00 21399.85 1999.24 7699.92 899.50 6899.39 1299.95 2599.89 399.98 1298.71 395
MVS_Test98.18 24298.36 19897.67 35898.48 39194.73 39198.18 17899.02 31897.69 25198.04 34899.11 18497.22 20499.56 39598.57 12198.90 40698.71 395
PVSNet93.40 1795.67 41295.70 39495.57 47198.83 32888.57 50492.50 51397.72 42292.69 47796.49 45596.44 46493.72 36299.43 44093.61 42599.28 35198.71 395
alignmvs97.35 31996.88 33998.78 20098.54 38698.09 15597.71 26397.69 42499.20 8397.59 38195.90 47588.12 43999.55 39998.18 15098.96 40198.70 398
ADS-MVSNet295.43 42394.98 42796.76 42598.14 42991.74 46897.92 23097.76 42190.23 49996.51 45298.91 24785.61 45799.85 15892.88 44896.90 49098.69 399
ADS-MVSNet95.24 42894.93 43096.18 44698.14 42990.10 49797.92 23097.32 43990.23 49996.51 45298.91 24785.61 45799.74 28892.88 44896.90 49098.69 399
MDTV_nov1_ep13_2view74.92 53797.69 26690.06 50497.75 37185.78 45693.52 43098.69 399
LoFTR97.97 26597.79 27398.53 25998.80 33797.47 22997.01 34799.55 11995.55 40399.46 10199.22 15194.22 34899.44 43896.45 32399.82 13398.68 402
MSDG97.71 28997.52 29698.28 29298.91 31296.82 28894.42 48099.37 20397.65 25598.37 31998.29 36897.40 19199.33 45594.09 41299.22 36298.68 402
mvsany_test197.60 29697.54 29497.77 34497.72 45495.35 36295.36 44897.13 44794.13 44999.71 4999.33 11897.93 13999.30 45997.60 21098.94 40398.67 404
CS-MVS99.13 6699.10 7999.24 10699.06 27799.15 5299.36 2299.88 1599.36 6398.21 33098.46 34598.68 5899.93 5399.03 8599.85 10998.64 405
Syy-MVS96.04 39695.56 40397.49 38397.10 48794.48 39896.18 40796.58 46595.65 39994.77 49192.29 52091.27 40899.36 44998.17 15298.05 45898.63 406
myMVS_eth3d91.92 48590.45 48696.30 43897.10 48790.90 48896.18 40796.58 46595.65 39994.77 49192.29 52053.88 53599.36 44989.59 50098.05 45898.63 406
BridgeMVS98.63 16598.72 13198.38 28098.66 36996.68 29898.90 8499.42 18798.99 12398.97 21299.19 15895.81 29299.85 15898.77 10599.77 17098.60 408
miper_enhance_ethall96.01 39795.74 39296.81 42296.41 51192.27 46493.69 50098.89 34191.14 49598.30 32297.35 44290.58 41599.58 39096.31 33299.03 38898.60 408
Effi-MVS+-dtu98.26 22997.90 26799.35 8098.02 43899.49 598.02 20999.16 28998.29 19597.64 37697.99 39596.44 25599.95 2596.66 30198.93 40498.60 408
new_pmnet96.99 35296.76 34897.67 35898.72 34694.89 38395.95 42298.20 40992.62 47898.55 29898.54 33194.88 32399.52 41193.96 41599.44 32298.59 411
MVSMamba_PlusPlus98.83 12198.98 9698.36 28499.32 20296.58 30298.90 8499.41 19199.75 1098.72 26799.50 6896.17 27099.94 4199.27 6499.78 16398.57 412
testing9193.32 46392.27 46996.47 43297.54 46891.25 48196.17 40996.76 46197.18 31493.65 50993.50 50965.11 52699.63 36493.04 44397.45 47598.53 413
EIA-MVS98.00 26097.74 27798.80 19398.72 34698.09 15598.05 20299.60 8997.39 28996.63 44295.55 48297.68 16099.80 23296.73 29099.27 35298.52 414
PatchMatch-RL97.24 33096.78 34798.61 23899.03 28497.83 19296.36 39399.06 30693.49 46397.36 40397.78 41195.75 29399.49 42293.44 43498.77 41198.52 414
sasdasda98.34 21498.26 21998.58 24298.46 39497.82 19798.96 7899.46 16399.19 8897.46 39395.46 48798.59 6799.46 43398.08 15898.71 41798.46 416
ET-MVSNet_ETH3D94.30 44593.21 45797.58 37198.14 42994.47 39994.78 46693.24 51294.72 43189.56 52495.87 47678.57 49999.81 22396.91 26997.11 48898.46 416
canonicalmvs98.34 21498.26 21998.58 24298.46 39497.82 19798.96 7899.46 16399.19 8897.46 39395.46 48798.59 6799.46 43398.08 15898.71 41798.46 416
UBG93.25 46592.32 46796.04 45497.72 45490.16 49695.92 42595.91 48096.03 37993.95 50693.04 51469.60 51399.52 41190.72 49397.98 46298.45 419
tt080598.69 15098.62 15298.90 17599.75 3499.30 2199.15 5796.97 45298.86 14198.87 24397.62 42298.63 6398.96 48199.41 5698.29 44398.45 419
TAPA-MVS96.21 1196.63 36695.95 38898.65 22698.93 30598.09 15596.93 35599.28 25283.58 52398.13 33897.78 41196.13 27299.40 44493.52 43099.29 35098.45 419
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MGCFI-Net98.34 21498.28 21398.51 26298.47 39297.59 22098.96 7899.48 14999.18 9197.40 39995.50 48498.66 5999.50 41898.18 15098.71 41798.44 422
BH-untuned96.83 35896.75 35097.08 40598.74 34393.33 44296.71 36898.26 40596.72 34598.44 31197.37 44095.20 31199.47 42991.89 46997.43 47798.44 422
WB-MVSnew95.73 41195.57 40296.23 44396.70 50190.70 49396.07 41493.86 50795.60 40197.04 41795.45 49196.00 27999.55 39991.04 48598.31 44198.43 424
pmmvs395.03 43394.40 44196.93 41497.70 45992.53 45795.08 45897.71 42388.57 51397.71 37298.08 38879.39 49399.82 20696.19 34099.11 38298.43 424
DP-MVS Recon97.33 32196.92 33598.57 24599.09 26897.99 17096.79 36199.35 21393.18 46697.71 37298.07 38995.00 31999.31 45793.97 41499.13 37898.42 426
testing9993.04 46991.98 47796.23 44397.53 47090.70 49396.35 39495.94 47996.87 33593.41 51093.43 51163.84 52899.59 38393.24 43997.19 48598.40 427
ETVMVS92.60 47591.08 48497.18 39997.70 45993.65 43896.54 37995.70 48496.51 35294.68 49392.39 51861.80 53299.50 41886.97 50797.41 47898.40 427
Fast-Effi-MVS+-dtu98.27 22798.09 24198.81 19098.43 39998.11 15197.61 28399.50 13998.64 15997.39 40197.52 42998.12 12499.95 2596.90 27498.71 41798.38 429
LF4IMVS97.90 26897.69 28398.52 26199.17 25197.66 21397.19 34199.47 15896.31 36497.85 36498.20 37696.71 24299.52 41194.62 39399.72 20398.38 429
testing1193.08 46892.02 47496.26 44197.56 46690.83 49096.32 39695.70 48496.47 35792.66 51493.73 50664.36 52799.59 38393.77 42297.57 46998.37 431
Fast-Effi-MVS+97.67 29297.38 30498.57 24598.71 35097.43 23497.23 33299.45 16794.82 42996.13 46096.51 46098.52 7599.91 7496.19 34098.83 40898.37 431
test0.0.03 194.51 44093.69 45096.99 41096.05 51593.61 44094.97 46193.49 50996.17 36997.57 38494.88 49882.30 48399.01 48093.60 42794.17 51998.37 431
UWE-MVS92.38 47891.76 48194.21 49397.16 48584.65 52195.42 44688.45 52895.96 38396.17 45995.84 47866.36 52099.71 30691.87 47098.64 42498.28 434
FE-MVS95.66 41394.95 42997.77 34498.53 38895.28 36699.40 1996.09 47693.11 46897.96 35599.26 13779.10 49599.77 26392.40 46398.71 41798.27 435
baseline293.73 45692.83 46396.42 43497.70 45991.28 48096.84 36089.77 52693.96 45792.44 51695.93 47479.14 49499.77 26392.94 44596.76 49498.21 436
thisisatest051594.12 45093.16 45896.97 41298.60 37692.90 45093.77 49990.61 52394.10 45196.91 42495.87 47674.99 50599.80 23294.52 39699.12 38198.20 437
EPMVS93.72 45793.27 45695.09 48496.04 51687.76 50998.13 18585.01 53394.69 43296.92 42298.64 31778.47 50199.31 45795.04 38296.46 49798.20 437
balanced_ft_v198.28 22698.35 20198.10 31298.08 43596.23 31999.23 4599.26 26198.34 18697.46 39399.42 8995.38 30899.88 11598.60 11799.34 33798.17 439
dp93.47 46093.59 45293.13 50796.64 50281.62 53497.66 27196.42 46992.80 47696.11 46198.64 31778.55 50099.59 38393.31 43692.18 52498.16 440
CNLPA97.17 33796.71 35298.55 25298.56 38498.05 16596.33 39598.93 33196.91 33297.06 41597.39 43894.38 34199.45 43691.66 47399.18 37298.14 441
dmvs_re95.98 40095.39 41197.74 35098.86 32297.45 23298.37 15995.69 48697.95 22996.56 44695.95 47390.70 41497.68 50888.32 50396.13 50298.11 442
HY-MVS95.94 1395.90 40595.35 41397.55 37797.95 44194.79 38798.81 9896.94 45592.28 48295.17 48498.57 32989.90 42099.75 28191.20 48397.33 48498.10 443
CostFormer93.97 45293.78 44994.51 48997.53 47085.83 51797.98 22195.96 47889.29 50894.99 48898.63 31978.63 49899.62 36794.54 39596.50 49698.09 444
FA-MVS(test-final)96.99 35296.82 34497.50 38298.70 35494.78 38899.34 2396.99 45095.07 42198.48 30799.33 11888.41 43699.65 35696.13 34698.92 40598.07 445
AdaColmapbinary97.14 33996.71 35298.46 27098.34 40797.80 20196.95 35298.93 33195.58 40296.92 42297.66 41895.87 29099.53 40790.97 48799.14 37698.04 446
KD-MVS_2432*160092.87 47391.99 47595.51 47491.37 53189.27 50294.07 49098.14 41295.42 41097.25 40696.44 46467.86 51599.24 46591.28 48196.08 50798.02 447
miper_refine_blended92.87 47391.99 47595.51 47491.37 53189.27 50294.07 49098.14 41295.42 41097.25 40696.44 46467.86 51599.24 46591.28 48196.08 50798.02 447
TESTMET0.1,192.19 48291.77 48093.46 50196.48 50982.80 53094.05 49291.52 52294.45 44194.00 50494.88 49866.65 51999.56 39595.78 36298.11 45398.02 447
testing22291.96 48490.37 48796.72 42697.47 47792.59 45596.11 41294.76 49396.83 33992.90 51292.87 51557.92 53499.55 39986.93 50897.52 47198.00 450
PCF-MVS92.86 1894.36 44293.00 46198.42 27598.70 35497.56 22193.16 51099.11 29979.59 52797.55 38597.43 43692.19 39199.73 29579.85 52499.45 31597.97 451
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS-2890.22 48889.28 49193.02 50894.50 52582.87 52996.52 38287.51 52995.21 41992.36 51796.04 47071.57 51098.25 49972.04 52997.77 46697.94 452
myMVS_eth3d2892.92 47292.31 46894.77 48597.84 44887.59 51196.19 40596.11 47497.08 32094.27 49793.49 51066.07 52398.78 48991.78 47197.93 46497.92 453
OpenMVScopyleft96.65 797.09 34296.68 35498.32 28798.32 40897.16 26598.86 9299.37 20389.48 50696.29 45899.15 17496.56 24999.90 8192.90 44799.20 36797.89 454
Gipumacopyleft99.03 8799.16 6298.64 22899.94 298.51 11399.32 2699.75 4299.58 3898.60 28899.62 4098.22 11199.51 41797.70 20199.73 19497.89 454
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PVSNet_089.98 2191.15 48790.30 48993.70 49997.72 45484.34 52590.24 52097.42 43290.20 50293.79 50793.09 51390.90 41298.89 48786.57 51172.76 53297.87 456
test-LLR93.90 45393.85 44794.04 49496.53 50484.62 52294.05 49292.39 51496.17 36994.12 50095.07 49282.30 48399.67 33695.87 35798.18 44797.82 457
test-mter92.33 48091.76 48194.04 49496.53 50484.62 52294.05 49292.39 51494.00 45694.12 50095.07 49265.63 52599.67 33695.87 35798.18 44797.82 457
tpm293.09 46792.58 46694.62 48897.56 46686.53 51497.66 27195.79 48386.15 51994.07 50298.23 37475.95 50399.53 40790.91 48996.86 49397.81 459
CR-MVSNet96.28 38695.95 38897.28 39497.71 45794.22 40498.11 19098.92 33592.31 48196.91 42499.37 10485.44 46099.81 22397.39 23097.36 48297.81 459
RPMNet97.02 34896.93 33397.30 39397.71 45794.22 40498.11 19099.30 24099.37 6096.91 42499.34 11586.72 44499.87 13597.53 21797.36 48297.81 459
tpmrst95.07 43295.46 40693.91 49697.11 48684.36 52497.62 27896.96 45394.98 42396.35 45798.80 27885.46 45999.59 38395.60 37096.23 50097.79 462
ALIKED-LG97.10 34096.63 36098.50 26697.96 44098.68 9997.75 25899.68 6295.86 38898.36 32198.33 36391.58 40199.04 47590.87 49199.31 34497.77 463
PAPM91.88 48690.34 48896.51 43098.06 43792.56 45692.44 51497.17 44586.35 51890.38 52396.01 47186.61 44599.21 46870.65 53095.43 51397.75 464
SP-LightGlue97.22 33297.01 32997.88 33597.33 48197.19 25996.38 39199.08 30497.28 30096.53 44897.50 43092.36 38798.70 49297.84 18498.76 41297.74 465
FPMVS93.44 46192.23 47097.08 40599.25 22597.86 18995.61 43797.16 44692.90 47493.76 50898.65 31375.94 50495.66 52579.30 52597.49 47397.73 466
MAR-MVS96.47 37695.70 39498.79 19797.92 44399.12 6298.28 16698.60 38392.16 48395.54 47896.17 46994.77 32999.52 41189.62 49898.23 44497.72 467
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
ETV-MVS98.03 25697.86 27098.56 25098.69 35998.07 16197.51 29799.50 13998.10 21997.50 39095.51 48398.41 8599.88 11596.27 33699.24 35897.71 468
thres600view794.45 44193.83 44896.29 43999.06 27791.53 47297.99 22094.24 50398.34 18697.44 39795.01 49479.84 48999.67 33684.33 51598.23 44497.66 469
thres40094.14 44993.44 45396.24 44298.93 30591.44 47597.60 28494.29 50097.94 23197.10 41194.31 50479.67 49199.62 36783.05 51898.08 45597.66 469
IB-MVS91.63 1992.24 48190.90 48596.27 44097.22 48491.24 48294.36 48393.33 51192.37 48092.24 51894.58 50366.20 52299.89 9793.16 44194.63 51797.66 469
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
tpmvs95.02 43495.25 41994.33 49096.39 51285.87 51598.08 19596.83 46095.46 40995.51 48098.69 30485.91 45599.53 40794.16 40796.23 50097.58 472
cascas94.79 43794.33 44496.15 45196.02 51792.36 46292.34 51599.26 26185.34 52195.08 48794.96 49792.96 37898.53 49594.41 40498.59 42997.56 473
MatchFormer97.07 34496.92 33597.49 38398.44 39795.92 33296.79 36199.14 29593.08 46999.32 14199.10 18793.89 35699.03 47692.78 45399.78 16397.52 474
PatchT96.65 36596.35 37697.54 37897.40 47895.32 36597.98 22196.64 46499.33 6596.89 42899.42 8984.32 47099.81 22397.69 20397.49 47397.48 475
TR-MVS95.55 41795.12 42596.86 42197.54 46893.94 42496.49 38496.53 46794.36 44497.03 41996.61 45994.26 34799.16 47186.91 50996.31 49997.47 476
SP-SuperGlue97.31 32297.23 31497.57 37696.96 49297.24 25196.26 40298.76 36697.68 25296.88 43097.85 40694.32 34498.01 50297.76 19598.57 43197.45 477
dmvs_testset92.94 47192.21 47195.13 48298.59 37990.99 48797.65 27392.09 51696.95 32794.00 50493.55 50892.34 38996.97 51772.20 52892.52 52297.43 478
MonoMVSNet96.25 38996.53 36995.39 47796.57 50391.01 48698.82 9797.68 42698.57 17298.03 34999.37 10490.92 41197.78 50794.99 38393.88 52097.38 479
JIA-IIPM95.52 41895.03 42697.00 40996.85 49694.03 41696.93 35595.82 48199.20 8394.63 49599.71 2283.09 47999.60 37894.42 40194.64 51697.36 480
SP-MNN96.46 37796.24 38497.10 40496.71 50095.98 32996.00 41697.33 43895.82 39294.93 48997.10 45293.70 36398.01 50296.30 33498.30 44297.30 481
ALIKED-MNN95.97 40295.30 41798.00 32597.66 46498.12 15096.98 35099.41 19191.11 49694.04 50397.30 44391.56 40298.61 49489.99 49699.63 25597.28 482
BH-w/o95.13 43194.89 43195.86 46198.20 42291.31 47895.65 43697.37 43393.64 45996.52 45195.70 48093.04 37799.02 47888.10 50495.82 51097.24 483
tpm cat193.29 46493.13 46093.75 49897.39 47984.74 52097.39 31297.65 42783.39 52494.16 49998.41 35082.86 48199.39 44691.56 47795.35 51497.14 484
SP-NN94.67 43894.44 44095.36 47995.12 52295.23 37094.27 48596.10 47594.46 43890.91 52195.76 47991.47 40593.87 52995.23 37996.62 49597.00 485
SP-DiffGlue96.87 35696.76 34897.21 39895.17 52196.88 28696.12 41198.93 33196.51 35298.37 31997.55 42593.65 36497.83 50596.11 34798.45 43696.92 486
xiu_mvs_v1_base_debu97.86 27598.17 23296.92 41598.98 29893.91 42696.45 38599.17 28697.85 23998.41 31497.14 44998.47 7799.92 6598.02 16599.05 38496.92 486
xiu_mvs_v1_base97.86 27598.17 23296.92 41598.98 29893.91 42696.45 38599.17 28697.85 23998.41 31497.14 44998.47 7799.92 6598.02 16599.05 38496.92 486
xiu_mvs_v1_base_debi97.86 27598.17 23296.92 41598.98 29893.91 42696.45 38599.17 28697.85 23998.41 31497.14 44998.47 7799.92 6598.02 16599.05 38496.92 486
PMVScopyleft91.26 2097.86 27597.94 26197.65 36299.71 4897.94 18098.52 13098.68 37698.99 12397.52 38899.35 11197.41 19098.18 50091.59 47699.67 23796.82 490
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
0.4-1-1-0.188.42 49085.91 49395.94 45793.08 52791.54 47190.99 51992.04 51889.96 50584.83 53083.25 52963.75 52999.52 41193.25 43882.07 52696.75 491
131495.74 41095.60 39996.17 44797.53 47092.75 45498.07 19998.31 40391.22 49394.25 49896.68 45795.53 30099.03 47691.64 47597.18 48696.74 492
MVS-HIRNet94.32 44395.62 39790.42 51298.46 39475.36 53696.29 39889.13 52795.25 41795.38 48199.75 1692.88 37999.19 46994.07 41399.39 32896.72 493
OpenMVS_ROBcopyleft95.38 1495.84 40895.18 42497.81 34198.41 40397.15 26697.37 31898.62 38283.86 52298.65 27798.37 35594.29 34699.68 33288.41 50298.62 42896.60 494
ALIKED-NN94.29 44693.41 45596.94 41396.18 51497.66 21394.90 46398.68 37688.85 51190.43 52296.81 45589.82 42196.59 52286.67 51098.33 43896.58 495
0.3-1-1-0.01587.27 49284.50 49695.57 47191.70 53090.77 49189.41 52592.04 51888.98 50982.46 53281.35 53060.36 53399.50 41892.96 44481.23 52896.45 496
0.4-1-1-0.287.49 49184.89 49495.31 48091.33 53390.08 49888.47 52692.07 51788.70 51284.06 53181.08 53163.62 53099.49 42292.93 44681.71 52796.37 497
thres100view90094.19 44793.67 45195.75 46599.06 27791.35 47798.03 20694.24 50398.33 18897.40 39994.98 49679.84 48999.62 36783.05 51898.08 45596.29 498
tfpn200view994.03 45193.44 45395.78 46498.93 30591.44 47597.60 28494.29 50097.94 23197.10 41194.31 50479.67 49199.62 36783.05 51898.08 45596.29 498
MVS93.19 46692.09 47296.50 43196.91 49494.03 41698.07 19998.06 41668.01 53094.56 49696.48 46295.96 28699.30 45983.84 51696.89 49296.17 500
gg-mvs-nofinetune92.37 47991.20 48395.85 46295.80 52092.38 46199.31 3081.84 53599.75 1091.83 51999.74 1868.29 51499.02 47887.15 50697.12 48796.16 501
xiu_mvs_v2_base97.16 33897.49 29896.17 44798.54 38692.46 45895.45 44498.84 35397.25 30497.48 39296.49 46198.31 9699.90 8196.34 33198.68 42296.15 502
PS-MVSNAJ97.08 34397.39 30396.16 44998.56 38492.46 45895.24 45398.85 35297.25 30497.49 39195.99 47298.07 12699.90 8196.37 32898.67 42396.12 503
E-PMN94.17 44894.37 44293.58 50096.86 49585.71 51890.11 52297.07 44898.17 20997.82 36797.19 44684.62 46798.94 48289.77 49797.68 46896.09 504
EMVS93.83 45494.02 44593.23 50696.83 49784.96 51989.77 52396.32 47097.92 23397.43 39896.36 46786.17 44998.93 48387.68 50597.73 46795.81 505
MVEpermissive83.40 2292.50 47691.92 47894.25 49198.83 32891.64 47092.71 51183.52 53495.92 38586.46 52995.46 48795.20 31195.40 52680.51 52398.64 42495.73 506
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
thres20093.72 45793.14 45995.46 47698.66 36991.29 47996.61 37594.63 49597.39 28996.83 43293.71 50779.88 48899.56 39582.40 52198.13 45295.54 507
GLUNet-SfM86.26 49384.68 49591.01 51180.58 53783.56 52678.04 52893.59 50876.70 52895.29 48394.72 50177.51 50294.26 52866.39 53199.33 33995.20 508
API-MVS97.04 34796.91 33897.42 38997.88 44598.23 14198.18 17898.50 39397.57 26497.39 40196.75 45696.77 23599.15 47290.16 49599.02 39194.88 509
GG-mvs-BLEND94.76 48694.54 52492.13 46699.31 3080.47 53688.73 52791.01 52667.59 51898.16 50182.30 52294.53 51893.98 510
SIFT-PointCN96.45 37896.47 37196.39 43598.13 43297.54 22393.31 50797.23 44394.67 43398.68 27398.32 36494.64 33297.81 50693.50 43299.77 17093.83 511
XFeat-MNN93.41 46292.98 46294.68 48792.63 52892.92 44989.72 52495.81 48292.10 48497.23 40896.29 46884.95 46397.31 51489.60 49998.54 43393.81 512
SIFT-ConvMatch96.57 36896.62 36196.43 43398.20 42298.27 13493.88 49696.88 45895.29 41598.88 23898.25 37095.18 31397.43 51193.22 44099.83 12693.59 513
SIFT-NCM-Cal96.56 36996.68 35496.20 44598.27 41598.44 11894.40 48196.67 46295.29 41597.63 37798.17 37896.40 25796.59 52293.61 42599.66 24593.57 514
SIFT-MNN95.92 40495.97 38795.74 46798.18 42498.00 16894.17 48796.99 45095.74 39797.16 40997.90 40290.71 41395.79 52493.71 42399.21 36593.44 515
SIFT-NN-PointCN96.06 39496.11 38595.91 45997.88 44597.73 20893.49 50397.51 43193.22 46596.57 44598.26 36996.23 26896.60 52192.54 46099.27 35293.40 516
DeepMVS_CXcopyleft93.44 50398.24 41894.21 40694.34 49964.28 53191.34 52094.87 50089.45 42792.77 53077.54 52693.14 52193.35 517
SIFT-NN-CMatch95.63 41595.48 40496.08 45398.24 41898.00 16892.71 51194.29 50094.20 44795.85 46897.26 44495.72 29597.01 51591.99 46799.02 39193.23 518
SIFT-NN92.96 47092.79 46493.46 50196.92 49396.45 31191.89 51794.39 49892.91 47392.54 51595.46 48788.26 43790.71 53285.22 51397.52 47193.22 519
SIFT-PCN-Cal96.34 38196.46 37396.01 45698.17 42696.89 28493.48 50497.35 43794.84 42899.35 12998.30 36694.70 33197.92 50492.03 46699.88 9593.21 520
SIFT-UM-Cal96.49 37496.62 36196.12 45298.13 43297.89 18693.35 50698.44 39595.48 40898.63 27998.34 35995.45 30597.45 51092.22 46599.50 30793.02 521
SIFT-CM-Cal96.28 38696.31 37996.16 44998.39 40498.11 15193.46 50596.47 46894.81 43098.49 30598.43 34894.48 33697.34 51392.60 45999.70 22193.02 521
SIFT-UMatch96.33 38296.47 37195.89 46098.29 41197.95 17893.84 49797.24 44295.78 39598.72 26798.04 39193.45 36696.81 51893.14 44299.73 19492.91 523
SIFT-NN-NCMNet95.39 42495.22 42195.92 45898.29 41198.34 12993.58 50294.60 49694.07 45394.84 49097.53 42694.37 34296.62 52091.01 48698.64 42492.80 524
SIFT-NCMNet96.30 38496.40 37596.03 45597.80 45297.68 21292.34 51596.94 45595.55 40398.84 24798.63 31994.17 34997.63 50993.57 42999.71 21292.77 525
SIFT-NN-UMatch95.38 42595.26 41895.75 46598.25 41697.78 20293.24 50995.66 48894.01 45595.10 48697.47 43493.12 37296.78 51992.42 46298.04 46092.69 526
XFeat-NN89.63 48989.13 49291.14 51090.93 53490.02 49984.90 52794.05 50688.10 51592.89 51393.33 51278.74 49690.89 53183.46 51795.72 51192.52 527
tmp_tt78.77 49678.73 49978.90 51458.45 53974.76 53894.20 48678.26 53739.16 53286.71 52892.82 51680.50 48775.19 53486.16 51292.29 52386.74 528
dongtai76.24 49775.95 50077.12 51592.39 52967.91 53990.16 52159.44 54082.04 52589.42 52594.67 50249.68 53781.74 53348.06 53277.66 53081.72 529
kuosan69.30 49868.95 50170.34 51687.68 53665.00 54091.11 51859.90 53969.02 52974.46 53488.89 52848.58 53868.03 53528.61 53372.33 53377.99 530
wuyk23d96.06 39497.62 29191.38 50998.65 37398.57 10798.85 9396.95 45496.86 33899.90 1499.16 16899.18 1998.40 49689.23 50199.77 17077.18 531
test12317.04 50120.11 5047.82 51710.25 5414.91 54294.80 4654.47 5424.93 53510.00 53724.28 5349.69 5393.64 53610.14 53412.43 53514.92 532
testmvs17.12 50020.53 5036.87 51812.05 5404.20 54393.62 5016.73 5414.62 53610.41 53624.33 5338.28 5403.56 5379.69 53515.07 53412.86 533
mmdepth0.00 5040.00 5070.00 5190.00 5420.00 5440.00 5300.00 5430.00 5370.00 5380.00 5370.00 5410.00 5380.00 5360.00 5360.00 534
monomultidepth0.00 5040.00 5070.00 5190.00 5420.00 5440.00 5300.00 5430.00 5370.00 5380.00 5370.00 5410.00 5380.00 5360.00 5360.00 534
test_blank0.00 5040.00 5070.00 5190.00 5420.00 5440.00 5300.00 5430.00 5370.00 5380.00 5370.00 5410.00 5380.00 5360.00 5360.00 534
uanet_test0.00 5040.00 5070.00 5190.00 5420.00 5440.00 5300.00 5430.00 5370.00 5380.00 5370.00 5410.00 5380.00 5360.00 5360.00 534
DCPMVS0.00 5040.00 5070.00 5190.00 5420.00 5440.00 5300.00 5430.00 5370.00 5380.00 5370.00 5410.00 5380.00 5360.00 5360.00 534
cdsmvs_eth3d_5k24.66 49932.88 5020.00 5190.00 5420.00 5440.00 53099.10 3000.00 5370.00 53897.58 42399.21 180.00 5380.00 5360.00 5360.00 534
pcd_1.5k_mvsjas8.17 50210.90 5050.00 5190.00 5420.00 5440.00 5300.00 5430.00 5370.00 5380.00 53798.07 1260.00 5380.00 5360.00 5360.00 534
sosnet-low-res0.00 5040.00 5070.00 5190.00 5420.00 5440.00 5300.00 5430.00 5370.00 5380.00 5370.00 5410.00 5380.00 5360.00 5360.00 534
sosnet0.00 5040.00 5070.00 5190.00 5420.00 5440.00 5300.00 5430.00 5370.00 5380.00 5370.00 5410.00 5380.00 5360.00 5360.00 534
uncertanet0.00 5040.00 5070.00 5190.00 5420.00 5440.00 5300.00 5430.00 5370.00 5380.00 5370.00 5410.00 5380.00 5360.00 5360.00 534
Regformer0.00 5040.00 5070.00 5190.00 5420.00 5440.00 5300.00 5430.00 5370.00 5380.00 5370.00 5410.00 5380.00 5360.00 5360.00 534
ab-mvs-re8.12 50310.83 5060.00 5190.00 5420.00 5440.00 5300.00 5430.00 5370.00 53897.48 4320.00 5410.00 5380.00 5360.00 5360.00 534
uanet0.00 5040.00 5070.00 5190.00 5420.00 5440.00 5300.00 5430.00 5370.00 5380.00 5370.00 5410.00 5380.00 5360.00 5360.00 534
WAC-MVS90.90 48891.37 480
FOURS199.73 3799.67 299.43 1599.54 12599.43 5499.26 154
test_one_060199.39 18199.20 3899.31 23298.49 17898.66 27699.02 20897.64 166
eth-test20.00 542
eth-test0.00 542
ZD-MVS99.01 29398.84 8599.07 30594.10 45198.05 34798.12 38396.36 26299.86 14492.70 45699.19 370
test_241102_ONE99.49 14699.17 4399.31 23297.98 22699.66 6098.90 25098.36 8999.48 426
9.1497.78 27499.07 27297.53 29499.32 22795.53 40698.54 30098.70 30297.58 17299.76 26994.32 40699.46 313
save fliter99.11 26397.97 17496.53 38199.02 31898.24 198
test072699.50 13899.21 3298.17 18199.35 21397.97 22799.26 15499.06 19697.61 170
test_part299.36 19099.10 6599.05 196
sam_mvs84.29 472
MTGPAbinary99.20 274
test_post197.59 28620.48 53683.07 48099.66 34994.16 407
test_post21.25 53583.86 47599.70 313
patchmatchnet-post98.77 28484.37 46999.85 158
MTMP97.93 22791.91 521
gm-plane-assit94.83 52381.97 53288.07 51694.99 49599.60 37891.76 472
TEST998.71 35098.08 15995.96 42099.03 31591.40 49195.85 46897.53 42696.52 25199.76 269
test_898.67 36498.01 16795.91 42699.02 31891.64 48695.79 47197.50 43096.47 25399.76 269
agg_prior98.68 36397.99 17099.01 32195.59 47299.77 263
test_prior497.97 17495.86 427
test_prior295.74 43496.48 35696.11 46197.63 42195.92 28994.16 40799.20 367
旧先验295.76 43388.56 51497.52 38899.66 34994.48 397
新几何295.93 423
原ACMM295.53 440
testdata299.79 24592.80 452
segment_acmp97.02 217
testdata195.44 44596.32 363
plane_prior799.19 24197.87 188
plane_prior698.99 29797.70 21194.90 320
plane_prior497.98 396
plane_prior397.78 20297.41 28697.79 368
plane_prior297.77 25298.20 206
plane_prior199.05 280
plane_prior97.65 21597.07 34596.72 34599.36 332
n20.00 543
nn0.00 543
door-mid99.57 106
test1198.87 344
door99.41 191
HQP5-MVS96.79 290
HQP-NCC98.67 36496.29 39896.05 37695.55 475
ACMP_Plane98.67 36496.29 39896.05 37695.55 475
BP-MVS92.82 450
HQP3-MVS99.04 31399.26 356
HQP2-MVS93.84 357
NP-MVS98.84 32697.39 23696.84 453
MDTV_nov1_ep1395.22 42197.06 48983.20 52897.74 26096.16 47294.37 44396.99 42098.83 27183.95 47499.53 40793.90 41697.95 463
ACMMP++_ref99.77 170
ACMMP++99.68 231
Test By Simon96.52 251