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-MVS69.38 247.34 138.25 153.40 254.29 456.62 332.95 143.55 249.30 3
DeepPCF-MVS69.58 146.90 237.52 353.15 353.58 557.05 232.83 242.22 348.83 5
DeepC-MVS_fast68.24 346.61 334.94 454.40 155.37 357.55 131.02 438.86 450.28 1
3Dnovator64.47 545.24 434.37 552.48 557.34 153.53 530.63 538.11 646.56 8
3Dnovator+66.72 444.84 533.14 752.63 456.23 253.78 429.20 637.07 947.89 6
ACMP63.53 642.50 631.11 950.08 648.62 1052.78 724.90 1537.33 848.84 4
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OpenMVScopyleft61.03 942.28 732.86 848.56 951.94 750.82 1027.02 938.70 542.92 12
TAPA-MVS59.36 1041.97 837.54 244.93 1346.78 1346.52 1631.44 343.65 141.48 15
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
COLMAP(SR)41.20 929.58 1048.95 748.70 948.18 1228.26 830.89 1649.98 2
ACMM61.98 740.80 1029.05 1248.64 846.87 1153.22 623.47 1834.63 1045.82 9
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TAPA-MVS(SR)40.72 1129.34 1148.31 1052.32 644.77 1926.63 1132.05 1247.84 7
PCF-MVS61.88 840.12 1233.16 644.75 1449.39 846.16 1728.63 737.70 738.70 20
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
COLMAP(base)37.35 1328.09 1743.52 1642.34 1946.68 1526.55 1229.63 1941.53 14
LTVRE_ROB55.42 1436.88 1428.57 1542.42 1740.72 2348.22 1126.97 1030.17 1838.32 21
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
ACMH+57.40 1136.48 1528.86 1341.57 1943.89 1837.61 3026.39 1331.33 1443.20 11
CasMVSNet(SR_A)35.87 1619.38 2946.87 1146.17 1551.96 914.32 3324.45 2642.47 13
OpenMVS_ROBcopyleft52.78 1635.39 1727.98 1840.33 2046.81 1236.10 3524.79 1631.17 1538.08 22
CasMVSNet(base)35.32 1818.44 3146.56 1246.00 1752.64 813.32 3423.57 2941.04 17
GSE34.79 1923.63 2542.23 1846.31 1439.18 2723.20 2024.07 2741.20 16
PLCcopyleft56.13 1234.63 2028.70 1438.59 2636.78 3144.65 2026.03 1431.36 1334.33 28
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
AttMVS34.35 2128.45 1638.28 2740.03 2440.06 2423.67 1733.23 1134.75 27
LPCS33.63 2224.80 2139.52 2242.29 2039.01 2823.44 1926.15 2337.27 24
PVSNet_043.31 1833.35 2323.83 2339.69 2141.22 2138.75 2921.08 2426.59 2139.10 19
COLMAP_ROBcopyleft52.97 1533.06 2425.38 2038.18 2835.81 3345.04 1822.92 2227.84 2033.69 29
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH55.70 1332.91 2523.69 2439.06 2441.22 2136.76 3321.84 2325.54 2439.18 18
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Pnet-new-32.65 2616.09 3543.68 1546.15 1639.98 2518.51 2713.67 4544.91 10
CIDER32.55 2725.75 1937.08 3139.65 2540.58 2320.91 2530.59 1731.00 33
Qingshan Xu and Wenbing Tao: Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume. AAAI 2020
PVSNet50.76 1732.44 2824.74 2237.57 3038.43 2836.66 3423.03 2126.46 2237.62 23
ANet30.02 2916.73 3438.88 2539.32 2644.06 2115.61 3017.85 3533.26 30
BP-MVSNet29.92 3020.53 2736.17 3237.89 2933.68 3917.55 2823.52 3036.95 25
P-MVSNet29.35 3120.98 2634.93 3334.55 3636.99 3220.06 2621.91 3233.25 31
ANet-0.7529.06 3213.44 3839.47 2339.32 2644.06 2110.78 3816.11 3935.02 26
Pnet_fast27.80 3312.25 3938.17 2937.73 3047.91 137.47 4417.03 3628.88 34
MVSNet27.45 3418.54 3033.39 3429.32 3847.13 1413.18 3523.89 2823.72 37
A-TVSNet + Gipumacopyleft26.68 3516.93 3333.18 3531.29 3739.82 2617.28 2916.57 3828.43 35
R-MVSNet23.84 3618.30 3227.54 3827.82 3933.79 3814.57 3222.03 3121.00 40
CasMVSNet(SR_B)23.80 3719.79 2826.47 4024.88 4037.51 3114.94 3124.65 2517.01 42
Pnet-blend21.89 389.21 4530.34 3634.58 3434.44 363.76 5414.67 4222.00 38
Pnet-blend++21.89 389.21 4530.34 3634.58 3434.44 363.76 5414.67 4222.00 38
MVSNet_plusplus19.10 406.64 5227.41 3936.63 3214.19 483.12 5610.15 4731.41 32
MVSCRF18.49 4112.01 4022.81 4120.51 4332.84 409.61 3914.41 4415.08 45
MVSNet_++16.58 4210.34 4320.75 4222.25 4111.60 511.64 5819.05 3328.39 36
Snet16.01 4311.97 4118.70 4322.09 4217.12 468.46 4215.48 4116.90 43
A1Net14.51 4414.40 3714.59 4413.30 4512.51 4911.95 3616.85 3717.96 41
CPR_FA14.43 4514.90 3614.12 4611.38 4614.82 4711.91 3717.89 3416.15 44
PMVScopyleft28.69 2010.60 464.70 5714.53 4510.82 5030.05 426.66 492.74 572.71 54
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
F/T MVSNet+Gipuma9.78 478.13 4710.88 529.23 5211.92 508.81 407.45 5111.49 46
firsttry9.57 487.40 5011.02 5111.05 4710.54 546.97 477.82 5011.49 46
example9.54 495.97 5611.92 4713.40 4420.72 436.89 485.05 561.63 59
MVSNet + Gipuma9.47 507.91 4810.52 538.91 5411.46 528.80 417.01 5211.18 48
hgnet9.31 516.52 5311.17 4910.91 4820.13 447.15 455.89 532.47 56
DPSNet9.31 516.52 5311.17 4910.91 4820.13 447.15 455.89 532.47 56
MVEpermissive17.77 219.03 539.66 448.62 546.03 5611.40 538.30 4311.02 468.42 49
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
Pnet-eth8.45 5410.49 427.10 569.98 512.92 605.14 5215.84 408.40 50
unMVSv16.85 556.06 557.37 557.56 559.33 556.35 505.76 555.22 51
CMPMVSbinary42.80 196.77 560.01 6111.27 481.93 6131.86 410.03 610.00 610.00 61
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
metmvs_fine4.94 577.02 513.56 583.18 593.86 574.62 539.43 493.63 52
RMVSNet4.93 587.73 493.06 593.93 573.22 595.95 519.52 482.04 58
unMVSmet3.60 592.44 584.38 573.82 586.35 562.69 572.18 582.97 53
confMetMVS2.34 601.33 593.02 603.03 603.47 581.14 591.52 592.56 55
FADENet0.06 610.04 600.07 610.12 620.08 610.05 600.03 600.02 60
dnet0.00 620.00 620.00 620.00 630.00 620.00 620.00 610.00 61
UnsupFinetunedMVSNet9.23 52