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 bysort bysort bysorted bysort bysort bysort bysort bysort by
DeepPCF-MVS80.84 163.41 153.95 169.71 169.72 371.26 148.73 159.18 168.16 1
DeepC-MVS_fast79.62 262.35 251.75 469.41 269.38 470.78 246.85 256.66 468.08 2
DeepC-MVS79.50 361.99 352.12 368.57 367.79 570.58 345.96 358.27 367.34 3
3Dnovator+77.84 459.53 447.18 767.76 470.63 167.68 443.34 751.01 964.98 6
3Dnovator76.31 559.36 548.19 566.81 570.04 267.59 544.27 552.10 762.80 10
ACMP74.13 656.41 844.60 1264.28 661.46 1365.81 737.07 1852.13 665.56 5
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
COLMAP(SR)56.21 944.16 1364.25 763.87 962.07 1441.86 1046.45 1666.80 4
OpenMVScopyleft72.83 1056.18 1045.66 963.19 864.67 865.13 839.60 1451.71 859.76 15
PCF-MVS73.52 757.06 748.10 663.03 966.85 762.36 1343.32 852.89 559.86 14
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TAPA-MVS(SR)55.07 1243.33 1562.90 1067.41 657.81 2039.94 1346.71 1563.49 8
ACMM73.20 855.01 1343.19 1662.89 1159.60 1666.07 635.89 2050.48 1063.01 9
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TAPA-MVS73.13 958.67 652.34 262.89 1163.68 1063.46 1145.85 458.83 261.53 11
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
COLMAP(base)55.51 1144.97 1162.54 1360.85 1462.46 1242.24 947.71 1264.29 7
GSE52.52 1640.81 1860.34 1461.71 1258.23 1938.13 1743.48 1961.07 13
LTVRE_ROB69.57 1253.52 1445.46 1058.89 1558.76 1760.60 1843.91 647.01 1457.32 20
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
COLMAP_ROBcopyleft66.92 1552.32 1742.45 1758.89 1556.18 2461.09 1538.61 1546.28 1759.41 16
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PLCcopyleft70.83 1153.50 1545.79 858.64 1756.31 2360.76 1641.70 1149.88 1158.86 17
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CasMVSNet(SR_A)45.13 2625.99 3157.89 1856.32 2264.81 919.76 3432.23 3052.54 25
CasMVSNet(base)44.49 2724.93 3257.53 1956.38 2164.76 1018.64 3631.23 3251.43 26
ACMH+68.96 1352.02 1843.83 1457.49 2059.85 1551.27 3040.04 1247.62 1361.35 12
LPCS50.60 1940.43 1957.38 2158.37 1856.00 2338.14 1642.71 2157.77 18
Pnet-new-42.61 2922.17 3756.24 2258.21 1953.03 2724.08 2920.25 4457.48 19
OpenMVS_ROBcopyleft64.09 1748.56 2038.68 2155.15 2361.90 1149.65 3236.02 1941.33 2353.89 24
PVSNet_057.27 1846.73 2334.96 2654.57 2455.50 2551.93 2831.22 2638.71 2556.27 22
ACMH67.68 1447.97 2138.24 2354.45 2556.88 2050.08 3134.49 2241.99 2256.40 21
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CIDER47.21 2238.36 2253.11 2655.37 2655.10 2633.25 2543.46 2048.87 29
Qingshan Xu and Wenbing Tao: Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume. AAAI 2020
PVSNet64.34 1645.78 2536.40 2552.03 2752.49 2749.20 3434.18 2438.61 2654.41 23
Pnet_fast37.64 3417.70 4050.93 2849.72 2960.73 1710.59 5024.81 3942.34 34
A-TVSNet + Gipumacopyleft42.12 3029.09 2850.80 2948.28 3456.53 2229.14 2729.04 3347.59 30
ANet-0.7539.47 3222.61 3650.71 3049.43 3055.75 2418.21 3727.01 3746.96 31
AttMVS45.85 2439.26 2050.25 3149.36 3251.75 2934.83 2143.70 1849.63 27
ANet39.53 3124.60 3349.48 3249.42 3155.75 2422.08 3027.13 3643.25 33
P-MVSNet44.46 2837.09 2449.37 3349.27 3349.30 3334.35 2339.83 2449.54 28
MVSNet38.33 3326.99 2945.89 3440.49 3857.57 2120.52 3233.47 2839.63 36
Pnet-blend++31.51 3715.02 4542.51 3547.41 3546.50 376.99 5323.05 4033.62 38
Pnet-blend31.51 3715.02 4542.51 3547.41 3546.50 376.99 5323.05 4033.62 38
R-MVSNet36.87 3529.78 2741.61 3742.00 3746.99 3524.73 2834.83 2735.83 37
MVSNet_plusplus28.64 3912.93 5039.11 3849.80 2821.55 476.17 5519.69 4545.98 32
CasMVSNet(SR_B)32.16 3626.80 3035.73 3934.57 3946.99 3520.55 3133.05 2925.63 44
MVSCRF28.32 4018.18 3935.09 4032.16 4244.37 4014.66 3921.69 4328.73 41
MVSNet_++25.72 4117.38 4231.27 4133.47 4018.28 522.87 5831.90 3142.06 35
Snet23.85 4217.41 4128.15 4232.72 4124.90 4512.22 4622.60 4226.83 42
PMVScopyleft37.38 2021.09 4511.49 5527.48 4324.09 4344.44 3915.98 387.01 5613.92 50
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
A1Net23.74 4323.95 3423.61 4421.43 4819.62 4919.93 3327.96 3429.78 40
CPR_FA23.28 4423.62 3523.05 4519.33 4923.00 4619.34 3527.89 3526.81 43
example15.69 5310.14 5619.39 4623.73 4430.32 4211.10 499.17 554.13 58
F/T MVSNet+Gipuma17.31 4614.39 4719.26 4716.83 5119.67 4814.03 4114.75 4921.27 45
hgnet16.45 4812.31 5219.21 4821.51 4630.31 4312.80 4311.82 535.81 54
DPSNet16.45 4812.31 5219.21 4821.51 4630.31 4312.80 4311.82 535.81 54
MVSNet + Gipuma16.91 4714.12 4918.77 5016.39 5319.13 5113.98 4214.27 5020.78 46
firsttry15.88 5212.57 5118.08 5117.80 5017.14 5311.54 4813.61 5119.31 47
MVEpermissive26.22 2116.26 5016.97 4315.79 5211.75 5519.40 5014.45 4019.48 4616.21 48
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
Pnet-eth16.08 5118.30 3814.59 5321.78 457.07 579.66 5126.95 3814.91 49
unMVSv113.05 5412.03 5413.73 5414.18 5416.18 5412.13 4711.93 5210.84 51
CMPMVSbinary51.72 197.38 580.03 6012.27 552.37 6034.46 410.06 600.00 600.00 60
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
unMVSmet7.42 575.82 578.48 567.60 5711.29 555.84 565.81 576.56 53
RMVSNet11.09 5515.49 448.17 579.16 5610.05 5612.57 4518.40 485.29 57
metmvs_fine10.03 5614.31 487.18 586.75 586.98 589.52 5219.10 477.81 52
confMetMVS4.86 593.39 585.85 595.59 596.61 592.94 573.83 585.35 56
FADENet0.17 600.15 590.18 600.31 610.16 600.19 590.10 590.08 59
dnet0.00 610.00 610.00 610.00 620.00 610.00 610.00 600.00 60
UnsupFinetunedMVSNet16.83 51