DeepPCF-MVS | | 80.84 1 | 63.41 1 | 53.95 1 | 69.71 2 | 69.72 4 | 71.26 1 | 48.73 1 | 59.18 1 | 68.16 2 |
|
DeepC-MVS | | 79.81 2 | 62.37 2 | 52.77 2 | 68.77 3 | 68.65 5 | 70.30 3 | 46.95 2 | 58.59 3 | 67.37 3 |
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020 |
DeepC-MVS_fast | | 79.65 3 | 62.24 3 | 50.96 4 | 69.75 1 | 69.91 3 | 71.08 2 | 46.04 3 | 55.88 4 | 68.27 1 |
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 4 | 59.53 4 | 47.18 7 | 67.76 4 | 70.63 1 | 67.68 4 | 43.34 7 | 51.01 9 | 64.98 6 |
|
3Dnovator | | 76.31 5 | 59.36 5 | 48.19 5 | 66.81 5 | 70.04 2 | 67.59 5 | 44.27 5 | 52.10 7 | 62.80 10 |
|
TAPA-MVS | | 73.13 9 | 58.67 6 | 52.34 3 | 62.89 11 | 63.68 10 | 63.46 11 | 45.85 4 | 58.83 2 | 61.53 11 |
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019 |
PCF-MVS | | 73.52 7 | 57.06 7 | 48.10 6 | 63.03 9 | 66.85 7 | 62.36 13 | 43.32 8 | 52.89 5 | 59.86 14 |
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019 |
ACMP | | 74.13 6 | 56.41 8 | 44.60 12 | 64.28 6 | 61.46 14 | 65.81 7 | 37.07 18 | 52.13 6 | 65.56 5 |
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020 |
COLMAP(SR) | | | 56.21 9 | 44.16 13 | 64.25 7 | 63.87 9 | 62.07 14 | 41.86 10 | 46.45 16 | 66.80 4 |
|
OpenMVS |  | 72.83 10 | 56.18 10 | 45.66 9 | 63.19 8 | 64.67 8 | 65.13 8 | 39.60 14 | 51.71 8 | 59.76 15 |
|
COLMAP(base) | | | 55.51 11 | 44.97 11 | 62.54 13 | 60.85 15 | 62.46 12 | 42.24 9 | 47.71 12 | 64.29 7 |
|
TAPA-MVS(SR) | | | 55.07 12 | 43.33 15 | 62.90 10 | 67.41 6 | 57.81 21 | 39.94 13 | 46.71 15 | 63.49 8 |
|
ACMM | | 73.20 8 | 55.01 13 | 43.19 16 | 62.89 11 | 59.60 17 | 66.07 6 | 35.89 20 | 50.48 10 | 63.01 9 |
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019 |
LTVRE_ROB | | 69.57 12 | 53.52 14 | 45.46 10 | 58.89 15 | 58.76 18 | 60.60 18 | 43.91 6 | 47.01 14 | 57.32 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 |
PLC |  | 70.83 11 | 53.50 15 | 45.79 8 | 58.64 17 | 56.31 24 | 60.76 16 | 41.70 11 | 49.88 11 | 58.86 17 |
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019 |
GSE | | | 52.52 16 | 40.81 18 | 60.34 14 | 61.71 13 | 58.23 20 | 38.13 17 | 43.48 19 | 61.07 13 |
|
COLMAP_ROB |  | 66.92 15 | 52.32 17 | 42.45 17 | 58.89 15 | 56.18 25 | 61.09 15 | 38.61 15 | 46.28 17 | 59.41 16 |
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016 |
ACMH+ | | 68.96 13 | 52.02 18 | 43.83 14 | 57.49 20 | 59.85 16 | 51.27 32 | 40.04 12 | 47.62 13 | 61.35 12 |
|
LPCS | | | 50.60 19 | 40.43 19 | 57.38 21 | 58.37 19 | 56.00 25 | 38.14 16 | 42.71 21 | 57.77 18 |
|
OpenMVS_ROB |  | 64.09 17 | 48.56 20 | 38.68 21 | 55.15 24 | 61.90 12 | 49.65 34 | 36.02 19 | 41.33 23 | 53.89 24 |
|
ACMH | | 67.68 14 | 47.97 21 | 38.24 23 | 54.45 26 | 56.88 21 | 50.08 33 | 34.49 22 | 41.99 22 | 56.40 21 |
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019 |
CIDER | | | 47.21 22 | 38.36 22 | 53.11 27 | 55.37 27 | 55.10 28 | 33.25 25 | 43.46 20 | 48.87 31 |
Qingshan Xu and Wenbing Tao: Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume. AAAI 2020 |
PVSNet_0 | | 57.27 18 | 46.73 23 | 34.96 26 | 54.57 25 | 55.50 26 | 51.93 30 | 31.22 26 | 38.71 25 | 56.27 22 |
|
AttMVS | | | 45.85 24 | 39.26 20 | 50.25 33 | 49.36 34 | 51.75 31 | 34.83 21 | 43.70 18 | 49.63 29 |
|
PVSNet | | 64.34 16 | 45.78 25 | 36.40 25 | 52.03 28 | 52.49 29 | 49.20 36 | 34.18 24 | 38.61 26 | 54.41 23 |
|
test_1126 | | | 45.72 26 | 28.57 31 | 57.15 22 | 62.33 11 | 59.06 19 | 24.22 31 | 32.91 32 | 50.08 28 |
|
CasMVSNet(SR_A) | | | 45.13 27 | 25.99 34 | 57.89 18 | 56.32 23 | 64.81 9 | 19.76 37 | 32.23 33 | 52.54 26 |
|
CasMVSNet(base) | | | 44.49 28 | 24.93 35 | 57.53 19 | 56.38 22 | 64.76 10 | 18.64 39 | 31.23 35 | 51.43 27 |
|
P-MVSNet | | | 44.46 29 | 37.09 24 | 49.37 35 | 49.27 35 | 49.30 35 | 34.35 23 | 39.83 24 | 49.54 30 |
|
BP-MVSNet | | | 43.22 30 | 32.08 27 | 50.65 32 | 52.86 28 | 46.16 42 | 27.25 28 | 36.92 27 | 52.94 25 |
Christian Sormann, Patrick Knöbelreiter, Andreas Kuhn, Mattia Rossi, Thomas Pock, Friedrich Fraundorfer: BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo. 3DV 2020 |
Pnet-new- | | | 42.61 31 | 22.17 40 | 56.24 23 | 58.21 20 | 53.03 29 | 24.08 32 | 20.25 47 | 57.48 19 |
|
A-TVSNet + Gipuma |  | | 42.12 32 | 29.09 30 | 50.80 30 | 48.28 36 | 56.53 23 | 29.14 27 | 29.04 36 | 47.59 32 |
|
test_1205 | | | 40.46 33 | 29.35 29 | 47.87 36 | 47.88 37 | 56.48 24 | 24.37 30 | 34.32 29 | 39.23 40 |
|
ANet | | | 39.53 34 | 24.60 36 | 49.48 34 | 49.42 33 | 55.75 26 | 22.08 33 | 27.13 39 | 43.25 35 |
|
ANet-0.75 | | | 39.47 35 | 22.61 39 | 50.71 31 | 49.43 32 | 55.75 26 | 18.21 40 | 27.01 40 | 46.96 33 |
|
MVSNet | | | 38.33 36 | 26.99 32 | 45.89 37 | 40.49 42 | 57.57 22 | 20.52 35 | 33.47 30 | 39.63 39 |
|
Pnet_fast | | | 37.64 37 | 17.70 43 | 50.93 29 | 49.72 31 | 60.73 17 | 10.59 54 | 24.81 42 | 42.34 36 |
|
R-MVSNet | | | 36.87 38 | 29.78 28 | 41.61 41 | 42.00 41 | 46.99 38 | 24.73 29 | 34.83 28 | 35.83 41 |
|
CasMVSNet(SR_B) | | | 32.16 39 | 26.80 33 | 35.73 43 | 34.57 43 | 46.99 38 | 20.55 34 | 33.05 31 | 25.63 48 |
|
test_1124 | | | 31.65 40 | 13.28 53 | 43.90 38 | 44.21 40 | 47.60 37 | 14.80 42 | 11.75 58 | 39.88 38 |
|
Pnet-blend++ | | | 31.51 41 | 15.02 48 | 42.51 39 | 47.41 38 | 46.50 40 | 6.99 58 | 23.05 43 | 33.62 42 |
|
Pnet-blend | | | 31.51 41 | 15.02 48 | 42.51 39 | 47.41 38 | 46.50 40 | 6.99 58 | 23.05 43 | 33.62 42 |
|
MVSNet_plusplus | | | 28.64 43 | 12.93 54 | 39.11 42 | 49.80 30 | 21.55 51 | 6.17 60 | 19.69 48 | 45.98 34 |
|
MVSCRF | | | 28.32 44 | 18.18 42 | 35.09 44 | 32.16 46 | 44.37 44 | 14.66 43 | 21.69 46 | 28.73 45 |
|
MVSNet_++ | | | 25.72 45 | 17.38 45 | 31.27 45 | 33.47 44 | 18.28 56 | 2.87 64 | 31.90 34 | 42.06 37 |
|
Snet | | | 23.85 46 | 17.41 44 | 28.15 46 | 32.72 45 | 24.90 49 | 12.22 50 | 22.60 45 | 26.83 46 |
|
A1Net | | | 23.74 47 | 23.95 37 | 23.61 48 | 21.43 52 | 19.62 53 | 19.93 36 | 27.96 37 | 29.78 44 |
|
CPR_FA | | | 23.28 48 | 23.62 38 | 23.05 49 | 19.33 53 | 23.00 50 | 19.34 38 | 27.89 38 | 26.81 47 |
|
PMVS |  | 37.38 20 | 21.09 49 | 11.49 59 | 27.48 47 | 24.09 47 | 44.44 43 | 15.98 41 | 7.01 60 | 13.92 56 |
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010) |
F/T MVSNet+Gipuma | | | 17.31 50 | 14.39 50 | 19.26 51 | 16.83 55 | 19.67 52 | 14.03 45 | 14.75 52 | 21.27 49 |
|
MVSNet + Gipuma | | | 16.91 51 | 14.12 52 | 18.77 54 | 16.39 57 | 19.13 55 | 13.98 46 | 14.27 53 | 20.78 50 |
|
hgnet | | | 16.45 52 | 12.31 56 | 19.21 52 | 21.51 50 | 30.31 47 | 12.80 47 | 11.82 56 | 5.81 60 |
|
DPSNet | | | 16.45 52 | 12.31 56 | 19.21 52 | 21.51 50 | 30.31 47 | 12.80 47 | 11.82 56 | 5.81 60 |
|
MVE |  | 26.22 21 | 16.26 54 | 16.97 46 | 15.79 56 | 11.75 59 | 19.40 54 | 14.45 44 | 19.48 49 | 16.21 52 |
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014) |
Pnet-eth | | | 16.08 55 | 18.30 41 | 14.59 57 | 21.78 49 | 7.07 63 | 9.66 55 | 26.95 41 | 14.91 54 |
|
firsttry | | | 15.88 56 | 12.57 55 | 18.08 55 | 17.80 54 | 17.14 57 | 11.54 52 | 13.61 54 | 19.31 51 |
|
example | | | 15.69 57 | 10.14 60 | 19.39 50 | 23.73 48 | 30.32 46 | 11.10 53 | 9.17 59 | 4.13 64 |
|
unMVSv1 | | | 13.05 58 | 12.03 58 | 13.73 58 | 14.18 58 | 16.18 58 | 12.13 51 | 11.93 55 | 10.84 57 |
|
RMVSNet | | | 11.09 59 | 15.49 47 | 8.17 63 | 9.16 60 | 10.05 60 | 12.57 49 | 18.40 51 | 5.29 63 |
|
metmvs_fine | | | 10.03 60 | 14.31 51 | 7.18 64 | 6.75 64 | 6.98 64 | 9.52 56 | 19.10 50 | 7.81 58 |
|
test_1120 |  | | 9.53 61 | 6.82 61 | 11.33 60 | 8.74 61 | 9.06 61 | 7.57 57 | 6.06 61 | 16.20 53 |
|
unMVSmet | | | 7.42 62 | 5.82 62 | 8.48 62 | 7.60 62 | 11.29 59 | 5.84 61 | 5.81 62 | 6.56 59 |
|
CMPMVS |  | 51.72 19 | 7.38 63 | 0.03 66 | 12.27 59 | 2.37 66 | 34.46 45 | 0.06 66 | 0.00 66 | 0.00 66 |
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011 |
Cas-MVS_preliminary | | | 7.24 64 | 3.51 63 | 9.72 61 | 7.03 63 | 7.46 62 | 4.87 62 | 2.16 64 | 14.65 55 |
|
confMetMVS | | | 4.86 65 | 3.39 64 | 5.85 65 | 5.59 65 | 6.61 65 | 2.94 63 | 3.83 63 | 5.35 62 |
|
FADENet | | | 0.17 66 | 0.15 65 | 0.18 66 | 0.31 67 | 0.16 66 | 0.19 65 | 0.10 65 | 0.08 65 |
|
dnet | | | 0.00 67 | 0.00 67 | 0.00 67 | 0.00 68 | 0.00 67 | 0.00 67 | 0.00 66 | 0.00 66 |
|
UnsupFinetunedMVSNet | | | | | | 16.83 55 | | | | |
|