This table lists the benchmark results for the low-res many-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 Infoalllow-res
many-view
indooroutdoorlakesidesand boxstorage roomstorage room 2tunnel
sort bysorted bysort bysort bysort bysort bysort bysort bysort by
DeepPCF-MVS93.97 187.63 182.10 191.31 191.80 191.34 177.64 186.56 190.79 1
DeepC-MVS_fast93.89 286.59 280.39 290.73 291.00 390.77 275.90 384.89 390.41 2
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepC-MVS93.07 385.88 379.73 489.98 389.82 690.09 574.93 584.53 490.03 3
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TAPA-MVS90.10 784.80 480.13 387.91 688.22 888.54 975.35 484.91 286.96 14
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PCF-MVS89.48 1084.51 576.96 1089.54 491.30 288.76 773.35 880.56 1288.57 4
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TAPA-MVS(SR)83.88 678.08 787.74 888.99 786.49 1673.17 1082.99 687.76 10
COLMAP(base)83.59 777.50 987.65 986.74 1287.68 1173.30 981.70 988.52 5
PLCcopyleft91.00 683.54 878.38 586.98 1385.38 1687.33 1373.45 683.31 588.23 9
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
GSE83.39 977.82 887.10 1285.70 1587.27 1473.41 782.23 788.34 8
COLMAP(SR)83.28 1076.24 1287.97 587.61 987.90 1072.76 1179.71 1488.39 7
ACMH+87.92 1382.46 1176.63 1186.35 1686.95 1184.52 1971.68 1281.58 1087.56 12
ACMP89.59 982.31 1275.00 1487.18 1184.49 2088.57 868.43 1881.58 1088.49 6
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB88.41 1282.23 1378.11 684.97 1986.24 1382.83 2576.93 279.30 1585.84 16
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
ACMM89.79 882.20 1475.34 1386.76 1484.94 1887.68 1168.85 1781.84 887.67 11
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
3Dnovator91.36 582.19 1574.09 1687.59 1089.83 590.10 471.54 1376.63 1882.84 20
3Dnovator+91.43 481.91 1673.11 1987.78 790.06 490.17 370.40 1575.82 2183.12 18
COLMAP_ROBcopyleft87.81 1481.57 1774.74 1586.13 1783.81 2187.08 1569.46 1680.01 1387.49 13
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH87.59 1580.55 1873.69 1785.11 1886.17 1482.81 2668.19 1979.20 1686.36 15
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OpenMVScopyleft89.19 1180.38 1971.40 2086.37 1587.42 1089.29 667.70 2075.10 2282.40 22
LPCS78.54 2073.62 1881.82 2279.59 2783.19 2371.25 1475.99 2082.69 21
A-TVSNet + Gipumacopyleft77.14 2167.96 2383.26 2080.53 2486.26 1765.25 2170.67 2382.99 19
BP-MVSNet76.76 2268.58 2282.22 2184.51 1977.66 3560.98 2676.18 1984.48 17
Christian Sormann, Patrick Knöbelreiter, Andreas Kuhn, Mattia Rossi, Thomas Pock, Friedrich Fraundorfer: BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo. 3DV 2020
PVSNet_082.17 1774.27 2364.50 2580.78 2381.77 2380.64 2961.11 2467.89 2679.92 23
PVSNet86.66 1673.29 2465.21 2478.67 2780.40 2577.98 3364.04 2366.38 2977.62 24
OpenMVS_ROBcopyleft81.14 1873.28 2563.11 2780.06 2582.70 2281.62 2861.11 2465.12 3175.87 25
CIDER72.92 2662.80 2879.66 2680.16 2683.22 2260.69 2764.90 3275.61 27
Qingshan Xu and Wenbing Tao: Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume. AAAI 2020
test_112671.43 2757.57 3380.67 2485.16 1784.45 2055.16 3159.98 3672.40 29
test_120570.75 2862.35 2976.35 3078.70 2885.03 1855.63 3069.08 2465.34 39
R-MVSNet70.54 2963.98 2674.91 3273.85 3477.87 3459.85 2868.11 2573.01 28
P-MVSNet70.42 3071.20 2169.90 3666.73 3972.02 3764.84 2277.55 1770.95 31
ANet-0.7567.51 3158.66 3273.41 3470.12 3579.37 3050.72 3366.61 2870.74 32
AttMVS65.89 3260.14 3069.73 3764.68 4275.04 3658.80 2961.47 3569.47 34
ANet63.85 3352.65 3571.32 3570.12 3579.37 3048.53 3556.77 3964.48 40
Pnet-new-63.42 3442.13 4577.61 2877.71 3079.30 3241.06 3843.20 5175.82 26
CasMVSNet(SR_A)63.08 3545.33 4274.92 3174.36 3183.73 2137.04 4553.62 4266.66 37
CasMVSNet(base)61.88 3643.72 4373.99 3374.03 3381.95 2734.99 4852.45 4365.99 38
Pnet_fast59.94 3735.26 5776.39 2974.15 3282.99 2425.02 5645.51 4872.03 30
CPR_FA58.26 3856.35 3459.54 4556.43 4955.34 4850.61 3462.09 3466.83 36
MVSNet56.22 3946.49 3962.70 4157.79 4667.16 4338.93 4154.05 4063.16 42
A1Net54.85 4059.98 3151.43 4847.46 5842.97 5752.72 3267.24 2763.86 41
MVSNet_plusplus54.10 4136.12 5566.09 3878.36 2949.55 5220.40 6151.84 4470.36 33
Pnet-blend53.68 4237.04 5264.76 3968.91 3770.02 3924.13 5749.96 4655.36 46
Pnet-blend++53.68 4237.04 5264.76 3968.91 3770.02 3924.13 5749.96 4655.36 46
MVSCRF51.99 4437.64 4961.55 4358.88 4368.35 4134.99 4840.28 5457.43 45
MVSNet_++50.85 4537.40 5059.81 4465.34 4146.28 539.19 6465.60 3067.81 35
test_112450.28 4631.72 5862.65 4258.29 4570.82 3827.23 5536.21 5858.84 43
Snet49.32 4736.02 5658.18 4666.02 4050.24 5027.93 5444.12 4958.27 44
CasMVSNet(SR_B)48.99 4845.75 4051.15 4949.07 5662.78 4437.57 4253.93 4141.61 53
Pnet-eth45.62 4949.15 3743.27 5853.31 5129.96 6535.03 4763.26 3346.53 50
unMVSv145.02 5043.12 4446.29 5547.83 5750.14 5142.67 3643.57 5040.92 54
RMVSNet44.67 5150.67 3640.67 5950.79 5241.21 5942.32 3759.02 3730.02 58
MVEpermissive50.73 2144.67 5145.57 4144.07 5735.90 6152.30 4940.89 3950.26 4544.00 52
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DPSNet44.61 5338.48 4748.69 5057.33 4760.08 4537.17 4339.80 5628.65 60
hgnet44.61 5338.48 4748.69 5057.33 4760.08 4537.17 4339.80 5628.65 60
MVSNet + Gipuma44.11 5538.76 4647.67 5350.05 5545.26 5534.93 5042.60 5247.71 48
F/T MVSNet+Gipuma43.59 5637.31 5147.78 5250.12 5345.64 5434.25 5140.37 5347.60 49
PMVScopyleft53.92 2042.74 5726.50 6053.57 4754.03 5068.05 4236.35 4616.65 6438.64 55
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
firsttry41.11 5836.23 5444.36 5643.82 5943.77 5632.28 5240.18 5545.51 51
example40.49 5930.54 5947.11 5458.75 4458.88 4729.97 5331.12 5923.71 64
metmvs_fine39.41 6048.46 3833.38 6135.53 6231.67 6439.28 4057.64 3832.95 57
unMVSmet32.09 6125.89 6136.22 6036.96 6042.02 5823.79 5927.99 6029.68 59
test_1120copyleft27.94 6222.22 6331.76 6220.92 6537.22 6118.54 6325.90 6237.14 56
confMetMVS26.62 6323.72 6228.55 6428.79 6333.00 6321.33 6026.10 6123.86 63
Cas-MVS_preliminary25.33 6419.98 6428.90 6324.65 6434.26 6218.62 6221.35 6327.78 62
CMPMVSbinary62.92 198.44 650.22 6613.92 654.26 6637.50 600.45 660.00 660.00 66
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FADENet1.48 661.79 651.27 662.11 671.06 662.23 651.34 650.65 65
dnet0.00 670.00 670.00 670.00 680.00 670.00 670.00 660.00 66
UnsupFinetunedMVSNet50.12 53