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
DeepC-MVS_fast98.69 196.77 195.30 197.74 198.24 297.85 392.74 297.86 197.13 1
DeepPCF-MVS98.18 396.68 295.10 297.74 198.30 197.78 592.41 397.79 297.12 2
DeepC-MVS98.35 296.09 394.20 1097.34 397.94 497.39 1090.85 1397.56 396.71 4
COLMAP(SR)96.07 494.39 797.19 596.86 897.92 291.54 1097.24 796.79 3
TAPA-MVS(SR)95.82 594.80 396.49 996.19 1297.58 992.04 497.56 395.71 12
ACMM97.58 595.68 694.49 696.48 1096.12 1397.20 1392.04 496.94 1096.10 9
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PCF-MVS97.08 1395.68 693.36 1497.23 498.16 396.93 1491.43 1195.29 1996.61 5
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMH+97.24 995.61 893.77 1396.83 696.69 1097.71 690.70 1496.85 1196.09 10
TAPA-MVS97.07 1495.48 994.55 496.10 1295.68 1697.30 1191.73 897.37 595.32 15
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
COLMAP(base)95.42 1094.03 1296.35 1195.96 1496.92 1591.10 1296.97 896.16 8
PLCcopyleft97.94 495.35 1194.28 996.06 1395.26 1996.59 1691.61 996.96 996.34 7
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ACMH97.28 795.29 1293.25 1596.65 796.32 1197.93 189.82 1696.68 1495.69 13
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP97.20 1095.11 1393.01 1896.52 895.68 1697.26 1289.74 1796.27 1696.61 5
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB97.16 1195.10 1494.13 1195.75 1495.69 1595.73 2092.87 195.39 1895.83 11
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
GSE95.00 1594.33 895.45 1794.81 2096.53 1891.98 696.68 1495.02 17
A-TVSNet + Gipumacopyleft94.96 1694.54 595.24 1995.31 1896.58 1791.82 797.27 693.83 18
BP-MVSNet94.57 1793.20 1695.49 1596.77 994.34 2689.67 1896.74 1295.35 14
COLMAP_ROBcopyleft97.56 694.43 1893.09 1795.33 1894.55 2196.37 1989.45 1996.72 1395.07 16
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
3Dnovator97.25 892.47 1987.97 2595.47 1697.93 597.85 386.02 2389.92 2590.64 22
3Dnovator+97.12 1292.17 2087.57 2695.24 1997.49 697.68 785.24 2589.91 2690.54 23
LPCS92.07 2192.93 1991.49 2690.32 2893.29 2890.66 1595.20 2090.87 21
OpenMVScopyleft96.50 1591.77 2286.65 2895.19 2197.38 797.66 884.60 2788.69 3090.53 24
R-MVSNet90.93 2389.80 2191.68 2590.81 2794.15 2787.67 2091.93 2490.07 25
PVSNet_094.43 1790.46 2485.77 2993.59 2293.82 2395.33 2284.62 2686.92 3291.61 20
CPR_FA89.35 2588.37 2490.00 2989.38 3087.69 3687.29 2289.46 2892.93 19
PVSNet96.02 1689.22 2684.53 3392.35 2393.29 2494.60 2585.85 2483.20 3589.17 26
CIDER88.55 2783.13 3592.16 2493.95 2295.61 2183.79 3082.47 3686.92 28
Qingshan Xu and Wenbing Tao: Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume. AAAI 2020
ANet-0.7587.89 2889.58 2286.76 3084.37 4290.29 3284.51 2894.65 2185.61 31
OpenMVS_ROBcopyleft92.34 1887.46 2981.75 3691.27 2792.55 2595.21 2381.21 3482.29 3786.05 29
P-MVSNet85.35 3091.57 2081.21 3978.76 4982.87 4387.56 2195.58 1782.00 35
ANet85.16 3185.20 3185.14 3384.37 4290.29 3282.00 3288.39 3180.78 39
unMVSv183.89 3284.37 3483.58 3584.00 4685.63 3883.17 3185.56 3381.11 38
metmvs_fine83.50 3384.90 3282.56 3784.72 3781.80 4681.09 3588.72 2981.17 37
A1Net82.90 3489.39 2378.57 4885.19 3463.18 5984.36 2994.42 2287.34 27
RMVSNet80.62 3586.71 2776.57 4984.14 4478.09 4880.22 3693.20 2367.48 55
Pnet_fast80.38 3665.52 5390.29 2890.03 2994.91 2460.54 5270.51 5385.93 30
AttMVS80.32 3778.27 3781.68 3878.98 4886.16 3779.76 3776.79 5079.89 40
Pnet-new-79.46 3869.54 4986.08 3184.76 3690.31 3165.13 4673.95 5283.16 33
CasMVSNet(SR_A)79.00 3969.56 4885.29 3285.95 3292.82 2962.08 4977.05 4677.11 41
DPSNet78.82 4076.20 3980.57 4384.50 3882.32 4475.56 3976.84 4774.88 44
hgnet78.82 4076.20 3980.57 4384.50 3882.32 4475.56 3976.84 4774.88 44
Pnet-blend++78.13 4273.62 4381.13 4084.46 4088.20 3466.50 4380.74 3970.74 53
Pnet-blend78.13 4273.62 4381.13 4084.46 4088.20 3466.50 4380.74 3970.74 53
CasMVSNet(base)78.10 4468.51 5084.50 3485.47 3391.56 3059.79 5477.22 4576.47 42
Pnet-eth77.75 4585.52 3072.57 5475.57 5165.89 5881.44 3389.61 2776.26 43
MVSCRF77.21 4674.57 4278.98 4779.29 4783.87 4175.01 4174.12 5173.78 48
MVEpermissive76.82 1976.63 4777.52 3876.03 5170.40 5785.49 3975.68 3879.36 4172.20 50
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
MVSNet_plusplus76.50 4866.38 5183.25 3691.25 2673.79 5353.62 5879.14 4284.70 32
example74.48 4965.59 5280.41 4584.10 4583.16 4262.82 4868.36 5573.98 47
Snet74.39 5064.28 5581.13 4088.04 3173.18 5660.15 5368.41 5482.18 34
MVSNet73.65 5170.01 4776.07 5076.39 5077.59 4961.93 5078.09 4474.23 46
MVSNet + Gipuma72.61 5271.20 4573.54 5275.39 5273.46 5565.60 4576.81 4971.78 51
firsttry72.49 5375.56 4170.44 5668.80 5970.25 5769.31 4281.82 3872.28 49
MVSNet_++71.81 5459.04 5880.33 4684.86 3574.23 5233.06 5985.02 3481.88 36
CasMVSNet(SR_B)70.07 5571.18 4669.33 5769.73 5877.06 5064.06 4778.31 4361.20 57
F/T MVSNet+Gipuma69.80 5664.46 5473.36 5375.05 5373.57 5460.74 5168.18 5671.46 52
unMVSmet66.94 5760.67 5771.11 5571.91 5679.70 4754.62 5666.73 5761.74 56
confMetMVS63.51 5860.95 5665.21 5960.95 6076.48 5155.53 5566.38 5858.21 58
PMVScopyleft70.75 2058.19 5943.22 5968.18 5873.06 5584.09 4054.23 5732.21 5947.37 59
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FADENet18.58 6015.51 6020.63 6021.45 6132.74 6115.09 6015.93 607.68 60
CMPMVSbinary69.68 2111.01 610.97 6117.70 6110.09 6243.01 601.93 610.00 610.00 61
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dnet0.00 620.00 620.00 620.00 630.00 620.00 620.00 610.00 61
UnsupFinetunedMVSNet75.05 53