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 bysort bysorted bysort bysort bysort bysort by
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
DeepC-MVS_fast79.65 362.24 350.96 469.75 169.91 371.08 246.04 355.88 468.27 1
DeepPCF-MVS80.84 163.41 153.95 169.71 269.72 471.26 148.73 159.18 168.16 2
DeepC-MVS79.81 262.37 252.77 268.77 368.65 570.30 346.95 258.59 367.37 3
TAPA-MVS(SR)55.07 1243.33 1562.90 1067.41 657.81 2039.94 1346.71 1563.49 8
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
OpenMVScopyleft72.83 1056.18 1045.66 963.19 864.67 865.13 839.60 1451.71 859.76 15
COLMAP(SR)56.21 944.16 1364.25 763.87 962.07 1441.86 1046.45 1666.80 4
TAPA-MVS73.13 958.67 652.34 362.89 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
OpenMVS_ROBcopyleft64.09 1748.56 2038.68 2155.15 2361.90 1149.65 3236.02 1941.33 2353.89 24
GSE52.52 1640.81 1860.34 1461.71 1258.23 1938.13 1743.48 1961.07 13
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(base)55.51 1144.97 1162.54 1360.85 1462.46 1242.24 947.71 1264.29 7
ACMH+68.96 1352.02 1843.83 1457.49 2059.85 1551.27 3040.04 1247.62 1361.35 12
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
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
LPCS50.60 1940.43 1957.38 2158.37 1856.00 2338.14 1642.71 2157.77 18
Pnet-new-42.61 3022.17 3856.24 2258.21 1953.03 2724.08 3020.25 4557.48 19
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
CasMVSNet(base)44.49 2724.93 3357.53 1956.38 2164.76 1018.64 3731.23 3351.43 27
CasMVSNet(SR_A)45.13 2625.99 3257.89 1856.32 2264.81 919.76 3532.23 3152.54 26
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
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
PVSNet_057.27 1846.73 2334.96 2654.57 2455.50 2551.93 2831.22 2638.71 2556.27 22
CIDER47.21 2238.36 2253.11 2655.37 2655.10 2633.25 2543.46 2048.87 30
Qingshan Xu and Wenbing Tao: Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume. AAAI 2020
BP-MVSNet43.22 2932.08 2750.65 3152.86 2746.16 3927.25 2836.92 2752.94 25
PVSNet64.34 1645.78 2536.40 2552.03 2752.49 2849.20 3434.18 2438.61 2654.41 23
MVSNet_plusplus28.64 4012.93 5139.11 3949.80 2921.55 486.17 5619.69 4645.98 33
Pnet_fast37.64 3517.70 4150.93 2849.72 3060.73 1710.59 5124.81 4042.34 35
ANet-0.7539.47 3322.61 3750.71 3049.43 3155.75 2418.21 3827.01 3846.96 32
ANet39.53 3224.60 3449.48 3349.42 3255.75 2422.08 3127.13 3743.25 34
AttMVS45.85 2439.26 2050.25 3249.36 3351.75 2934.83 2143.70 1849.63 28
P-MVSNet44.46 2837.09 2449.37 3449.27 3449.30 3334.35 2339.83 2449.54 29
A-TVSNet + Gipumacopyleft42.12 3129.09 2950.80 2948.28 3556.53 2229.14 2729.04 3447.59 31
Pnet-blend31.51 3815.02 4642.51 3647.41 3646.50 376.99 5423.05 4133.62 39
Pnet-blend++31.51 3815.02 4642.51 3647.41 3646.50 376.99 5423.05 4133.62 39
R-MVSNet36.87 3629.78 2841.61 3842.00 3846.99 3524.73 2934.83 2835.83 38
MVSNet38.33 3426.99 3045.89 3540.49 3957.57 2120.52 3333.47 2939.63 37
CasMVSNet(SR_B)32.16 3726.80 3135.73 4034.57 4046.99 3520.55 3233.05 3025.63 45
MVSNet_++25.72 4217.38 4331.27 4233.47 4118.28 532.87 5931.90 3242.06 36
Snet23.85 4317.41 4228.15 4332.72 4224.90 4612.22 4722.60 4326.83 43
MVSCRF28.32 4118.18 4035.09 4132.16 4344.37 4114.66 4021.69 4428.73 42
PMVScopyleft37.38 2021.09 4611.49 5627.48 4424.09 4444.44 4015.98 397.01 5713.92 51
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
example15.69 5410.14 5719.39 4723.73 4530.32 4311.10 509.17 564.13 59
Pnet-eth16.08 5218.30 3914.59 5421.78 467.07 589.66 5226.95 3914.91 50
hgnet16.45 4912.31 5319.21 4921.51 4730.31 4412.80 4411.82 545.81 55
DPSNet16.45 4912.31 5319.21 4921.51 4730.31 4412.80 4411.82 545.81 55
A1Net23.74 4423.95 3523.61 4521.43 4919.62 5019.93 3427.96 3529.78 41
CPR_FA23.28 4523.62 3623.05 4619.33 5023.00 4719.34 3627.89 3626.81 44
firsttry15.88 5312.57 5218.08 5217.80 5117.14 5411.54 4913.61 5219.31 48
UnsupFinetunedMVSNet16.83 52
F/T MVSNet+Gipuma17.31 4714.39 4819.26 4816.83 5219.67 4914.03 4214.75 5021.27 46
MVSNet + Gipuma16.91 4814.12 5018.77 5116.39 5419.13 5213.98 4314.27 5120.78 47
unMVSv113.05 5512.03 5513.73 5514.18 5516.18 5512.13 4811.93 5310.84 52
MVEpermissive26.22 2116.26 5116.97 4415.79 5311.75 5619.40 5114.45 4119.48 4716.21 49
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
RMVSNet11.09 5615.49 458.17 589.16 5710.05 5712.57 4618.40 495.29 58
unMVSmet7.42 585.82 588.48 577.60 5811.29 565.84 575.81 586.56 54
metmvs_fine10.03 5714.31 497.18 596.75 596.98 599.52 5319.10 487.81 53
confMetMVS4.86 603.39 595.85 605.59 606.61 602.94 583.83 595.35 57
CMPMVSbinary51.72 197.38 590.03 6112.27 562.37 6134.46 420.06 610.00 610.00 61
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FADENet0.17 610.15 600.18 610.31 620.16 610.19 600.10 600.08 60
dnet0.00 620.00 620.00 620.00 630.00 620.00 620.00 610.00 61