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
DeepC-MVS_fast79.65 362.24 350.96 469.75 169.91 371.08 246.04 355.88 468.27 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
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
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
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 1465.81 737.07 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 2139.94 1346.71 1563.49 8
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
ACMM73.20 855.01 1343.19 1662.89 1159.60 1766.07 635.89 2050.48 1063.01 9
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
COLMAP(base)55.51 1144.97 1162.54 1360.85 1562.46 1242.24 947.71 1264.29 7
GSE52.52 1640.81 1860.34 1461.71 1358.23 2038.13 1743.48 1961.07 13
COLMAP_ROBcopyleft66.92 1552.32 1742.45 1758.89 1556.18 2561.09 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
LTVRE_ROB69.57 1253.52 1445.46 1058.89 1558.76 1860.60 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
PLCcopyleft70.83 1153.50 1545.79 858.64 1756.31 2460.76 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 2725.99 3457.89 1856.32 2364.81 919.76 3732.23 3352.54 26
CasMVSNet(base)44.49 2824.93 3557.53 1956.38 2264.76 1018.64 3931.23 3551.43 27
ACMH+68.96 1352.02 1843.83 1457.49 2059.85 1651.27 3240.04 1247.62 1361.35 12
LPCS50.60 1940.43 1957.38 2158.37 1956.00 2538.14 1642.71 2157.77 18
test_112645.72 2628.57 3157.15 2262.33 1159.06 1924.22 3132.91 3250.08 28
Pnet-new-42.61 3122.17 4056.24 2358.21 2053.03 2924.08 3220.25 4757.48 19
OpenMVS_ROBcopyleft64.09 1748.56 2038.68 2155.15 2461.90 1249.65 3436.02 1941.33 2353.89 24
PVSNet_057.27 1846.73 2334.96 2654.57 2555.50 2651.93 3031.22 2638.71 2556.27 22
ACMH67.68 1447.97 2138.24 2354.45 2656.88 2150.08 3334.49 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 2755.37 2755.10 2833.25 2543.46 2048.87 31
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 2852.49 2949.20 3634.18 2438.61 2654.41 23
Pnet_fast37.64 3717.70 4350.93 2949.72 3160.73 1710.59 5424.81 4242.34 36
A-TVSNet + Gipumacopyleft42.12 3229.09 3050.80 3048.28 3656.53 2329.14 2729.04 3647.59 32
ANet-0.7539.47 3522.61 3950.71 3149.43 3255.75 2618.21 4027.01 4046.96 33
BP-MVSNet43.22 3032.08 2750.65 3252.86 2846.16 4227.25 2836.92 2752.94 25
Christian Sormann, Patrick Knöbelreiter, Andreas Kuhn, Mattia Rossi, Thomas Pock, Friedrich Fraundorfer: BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo. 3DV 2020
AttMVS45.85 2439.26 2050.25 3349.36 3451.75 3134.83 2143.70 1849.63 29
ANet39.53 3424.60 3649.48 3449.42 3355.75 2622.08 3327.13 3943.25 35
P-MVSNet44.46 2937.09 2449.37 3549.27 3549.30 3534.35 2339.83 2449.54 30
test_120540.46 3329.35 2947.87 3647.88 3756.48 2424.37 3034.32 2939.23 40
MVSNet38.33 3626.99 3245.89 3740.49 4257.57 2220.52 3533.47 3039.63 39
test_112431.65 4013.28 5343.90 3844.21 4047.60 3714.80 4211.75 5839.88 38
Pnet-blend++31.51 4115.02 4842.51 3947.41 3846.50 406.99 5823.05 4333.62 42
Pnet-blend31.51 4115.02 4842.51 3947.41 3846.50 406.99 5823.05 4333.62 42
R-MVSNet36.87 3829.78 2841.61 4142.00 4146.99 3824.73 2934.83 2835.83 41
MVSNet_plusplus28.64 4312.93 5439.11 4249.80 3021.55 516.17 6019.69 4845.98 34
CasMVSNet(SR_B)32.16 3926.80 3335.73 4334.57 4346.99 3820.55 3433.05 3125.63 48
MVSCRF28.32 4418.18 4235.09 4432.16 4644.37 4414.66 4321.69 4628.73 45
MVSNet_++25.72 4517.38 4531.27 4533.47 4418.28 562.87 6431.90 3442.06 37
Snet23.85 4617.41 4428.15 4632.72 4524.90 4912.22 5022.60 4526.83 46
PMVScopyleft37.38 2021.09 4911.49 5927.48 4724.09 4744.44 4315.98 417.01 6013.92 56
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
A1Net23.74 4723.95 3723.61 4821.43 5219.62 5319.93 3627.96 3729.78 44
CPR_FA23.28 4823.62 3823.05 4919.33 5323.00 5019.34 3827.89 3826.81 47
example15.69 5710.14 6019.39 5023.73 4830.32 4611.10 539.17 594.13 64
F/T MVSNet+Gipuma17.31 5014.39 5019.26 5116.83 5519.67 5214.03 4514.75 5221.27 49
DPSNet16.45 5212.31 5619.21 5221.51 5030.31 4712.80 4711.82 565.81 60
hgnet16.45 5212.31 5619.21 5221.51 5030.31 4712.80 4711.82 565.81 60
MVSNet + Gipuma16.91 5114.12 5218.77 5416.39 5719.13 5513.98 4614.27 5320.78 50
firsttry15.88 5612.57 5518.08 5517.80 5417.14 5711.54 5213.61 5419.31 51
MVEpermissive26.22 2116.26 5416.97 4615.79 5611.75 5919.40 5414.45 4419.48 4916.21 52
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
Pnet-eth16.08 5518.30 4114.59 5721.78 497.07 639.66 5526.95 4114.91 54
unMVSv113.05 5812.03 5813.73 5814.18 5816.18 5812.13 5111.93 5510.84 57
CMPMVSbinary51.72 197.38 630.03 6612.27 592.37 6634.46 450.06 660.00 660.00 66
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_1120copyleft9.53 616.82 6111.33 608.74 619.06 617.57 576.06 6116.20 53
Cas-MVS_preliminary7.24 643.51 639.72 617.03 637.46 624.87 622.16 6414.65 55
unMVSmet7.42 625.82 628.48 627.60 6211.29 595.84 615.81 626.56 59
RMVSNet11.09 5915.49 478.17 639.16 6010.05 6012.57 4918.40 515.29 63
metmvs_fine10.03 6014.31 517.18 646.75 646.98 649.52 5619.10 507.81 58
confMetMVS4.86 653.39 645.85 655.59 656.61 652.94 633.83 635.35 62
FADENet0.17 660.15 650.18 660.31 670.16 660.19 650.10 650.08 65
dnet0.00 670.00 670.00 670.00 680.00 670.00 670.00 660.00 66
UnsupFinetunedMVSNet16.83 55