DeepPCF-MVS | | 89.96 1 | 79.79 1 | 72.17 1 | 84.87 1 | 84.94 1 | 85.37 1 | 66.97 1 | 77.38 1 | 84.30 1 |
|
DeepC-MVS_fast | | 89.43 2 | 78.34 2 | 69.56 4 | 84.20 2 | 84.26 2 | 84.39 2 | 64.46 3 | 74.66 4 | 83.95 2 |
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020 |
DeepC-MVS | | 88.79 3 | 77.94 3 | 69.90 3 | 83.31 3 | 82.66 7 | 83.75 3 | 64.27 4 | 75.52 3 | 83.50 3 |
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020 |
TAPA-MVS | | 84.62 6 | 76.12 4 | 70.08 2 | 80.15 7 | 80.96 8 | 80.06 9 | 63.78 5 | 76.37 2 | 79.45 14 |
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019 |
PCF-MVS | | 84.11 10 | 75.39 5 | 66.57 6 | 81.27 5 | 83.29 4 | 80.62 7 | 62.19 6 | 70.95 6 | 79.89 11 |
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019 |
3Dnovator+ | | 87.14 4 | 74.49 6 | 63.75 14 | 81.65 4 | 83.81 3 | 82.92 4 | 60.57 10 | 66.93 17 | 78.22 15 |
|
3Dnovator | | 86.66 5 | 74.48 7 | 64.71 9 | 81.00 6 | 82.81 5 | 82.90 5 | 61.47 8 | 67.94 13 | 77.28 16 |
|
COLMAP(base) | | | 74.23 8 | 65.63 8 | 79.96 9 | 78.64 11 | 79.30 11 | 61.52 7 | 69.74 9 | 81.95 4 |
|
PLC |  | 84.53 7 | 73.65 9 | 66.64 5 | 78.33 15 | 75.81 19 | 78.67 13 | 61.39 9 | 71.89 5 | 80.49 8 |
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019 |
COLMAP(SR) | | | 73.53 10 | 63.77 13 | 80.04 8 | 79.79 9 | 78.44 14 | 60.49 11 | 67.05 16 | 81.87 5 |
|
TAPA-MVS(SR) | | | 73.30 11 | 64.27 10 | 79.32 11 | 82.74 6 | 75.33 19 | 59.44 12 | 69.10 10 | 79.88 12 |
|
GSE | | | 73.02 12 | 64.14 11 | 78.95 12 | 77.59 14 | 78.43 15 | 59.39 13 | 68.88 11 | 80.83 7 |
|
ACMP | | 84.23 8 | 72.76 13 | 62.76 15 | 79.42 10 | 76.30 17 | 80.59 8 | 54.92 18 | 70.60 7 | 81.37 6 |
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020 |
LTVRE_ROB | | 82.13 12 | 72.22 14 | 66.24 7 | 76.21 18 | 77.23 15 | 74.60 23 | 65.16 2 | 67.32 15 | 76.79 18 |
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 |
ACMM | | 84.12 9 | 72.07 15 | 62.37 17 | 78.54 14 | 75.71 20 | 79.93 10 | 54.53 19 | 70.21 8 | 79.97 10 |
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019 |
OpenMVS |  | 83.78 11 | 71.88 16 | 61.70 18 | 78.66 13 | 78.88 10 | 81.24 6 | 56.67 17 | 66.73 18 | 75.86 19 |
|
COLMAP_ROB |  | 80.39 14 | 71.80 17 | 62.64 16 | 77.90 16 | 74.64 21 | 78.97 12 | 57.39 16 | 67.89 14 | 80.10 9 |
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016 |
ACMH+ | | 81.04 13 | 71.42 18 | 63.93 12 | 76.41 17 | 78.38 12 | 71.06 26 | 58.99 14 | 68.87 12 | 79.80 13 |
|
LPCS | | | 68.73 19 | 60.59 19 | 74.16 20 | 72.17 23 | 74.57 24 | 57.78 15 | 63.39 21 | 75.74 20 |
|
ACMH | | 80.38 15 | 68.42 20 | 59.50 20 | 74.37 19 | 77.00 16 | 69.10 31 | 54.34 20 | 64.66 19 | 77.02 17 |
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019 |
OpenMVS_ROB |  | 74.94 17 | 63.99 21 | 53.23 23 | 71.15 24 | 75.82 18 | 68.57 32 | 51.19 23 | 55.27 26 | 69.07 26 |
|
A-TVSNet + Gipuma |  | | 63.67 22 | 50.37 28 | 72.54 22 | 69.76 27 | 76.21 18 | 48.72 26 | 52.03 31 | 71.64 23 |
|
PVSNet_0 | | 73.20 18 | 63.55 23 | 51.85 26 | 71.35 23 | 72.10 24 | 69.61 30 | 47.57 27 | 56.13 24 | 72.33 22 |
|
CIDER | | | 63.41 24 | 52.95 24 | 70.39 27 | 71.10 26 | 72.79 25 | 49.19 24 | 56.71 23 | 67.28 27 |
Qingshan Xu and Wenbing Tao: Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume. AAAI 2020 |
BP-MVSNet | | | 63.26 25 | 52.48 25 | 70.45 26 | 73.14 22 | 64.36 36 | 45.07 28 | 59.89 22 | 73.84 21 |
Christian Sormann, Patrick Knöbelreiter, Andreas Kuhn, Mattia Rossi, Thomas Pock, Friedrich Fraundorfer: BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo. 3DV 2020 |
PVSNet | | 78.82 16 | 62.67 26 | 53.41 22 | 68.85 29 | 69.68 28 | 66.37 34 | 51.28 22 | 55.54 25 | 70.50 25 |
|
test_1126 | | | 61.29 27 | 44.16 31 | 72.71 21 | 77.87 13 | 75.17 20 | 40.34 30 | 47.98 34 | 65.09 28 |
|
P-MVSNet | | | 61.04 28 | 58.45 21 | 62.77 34 | 60.78 39 | 63.39 38 | 52.67 21 | 64.23 20 | 64.13 29 |
|
test_1205 | | | 58.34 29 | 47.13 30 | 65.81 32 | 67.31 31 | 74.82 21 | 40.34 30 | 53.91 28 | 55.31 40 |
|
AttMVS | | | 58.26 30 | 51.80 27 | 62.56 36 | 58.33 40 | 65.96 35 | 49.04 25 | 54.55 27 | 63.38 30 |
|
R-MVSNet | | | 56.72 31 | 48.74 29 | 62.04 37 | 61.37 36 | 66.93 33 | 43.74 29 | 53.73 29 | 57.82 37 |
|
CasMVSNet(SR_A) | | | 56.09 32 | 36.56 38 | 69.11 28 | 67.36 29 | 77.93 16 | 28.99 39 | 44.12 39 | 62.05 32 |
|
Pnet-new- | | | 55.36 33 | 32.32 42 | 70.71 25 | 71.82 25 | 69.62 29 | 32.54 36 | 32.10 50 | 70.69 24 |
|
ANet-0.75 | | | 55.32 34 | 41.08 33 | 64.81 33 | 61.58 34 | 70.76 27 | 34.14 35 | 48.01 33 | 62.08 31 |
|
CasMVSNet(base) | | | 55.02 35 | 35.18 39 | 68.25 30 | 67.01 32 | 76.54 17 | 27.28 41 | 43.09 40 | 61.20 34 |
|
ANet | | | 53.16 36 | 38.86 35 | 62.70 35 | 61.58 34 | 70.76 27 | 34.74 33 | 42.99 41 | 55.74 39 |
|
Pnet_fast | | | 50.82 37 | 26.87 48 | 66.78 31 | 64.56 33 | 74.79 22 | 17.08 56 | 36.66 47 | 61.01 35 |
|
MVSNet | | | 49.13 38 | 37.77 36 | 56.70 38 | 50.43 44 | 63.92 37 | 30.66 37 | 44.88 37 | 55.77 38 |
|
Pnet-blend | | | 44.30 39 | 26.07 50 | 56.45 39 | 60.87 37 | 61.19 40 | 14.59 57 | 37.56 44 | 47.29 44 |
|
Pnet-blend++ | | | 44.30 39 | 26.07 50 | 56.45 39 | 60.87 37 | 61.19 40 | 14.59 57 | 37.56 44 | 47.29 44 |
|
MVSNet_plusplus | | | 43.14 41 | 25.17 54 | 55.12 42 | 67.36 29 | 36.20 52 | 12.78 60 | 37.55 46 | 61.80 33 |
|
test_1124 | | | 42.16 42 | 21.84 58 | 55.71 41 | 53.19 41 | 61.81 39 | 20.50 53 | 23.19 58 | 52.14 41 |
|
CasMVSNet(SR_B) | | | 42.10 43 | 37.13 37 | 45.41 45 | 43.33 47 | 57.07 44 | 29.42 38 | 44.85 38 | 35.82 50 |
|
MVSCRF | | | 41.80 44 | 27.23 46 | 51.52 43 | 48.62 45 | 58.89 42 | 23.51 49 | 30.95 51 | 47.03 46 |
|
CPR_FA | | | 41.50 45 | 40.70 34 | 42.03 48 | 37.78 52 | 40.09 48 | 34.69 34 | 46.72 36 | 48.23 43 |
|
A1Net | | | 40.64 46 | 42.66 32 | 39.29 49 | 35.99 53 | 32.67 55 | 36.23 32 | 49.09 32 | 49.23 42 |
|
MVSNet_++ | | | 40.21 47 | 29.12 45 | 47.60 44 | 52.26 42 | 32.34 57 | 5.74 64 | 52.50 30 | 58.20 36 |
|
Snet | | | 37.53 48 | 26.97 47 | 44.56 47 | 51.19 43 | 38.17 49 | 19.63 55 | 34.31 49 | 44.33 47 |
|
PMVS |  | 47.18 20 | 35.10 49 | 20.52 59 | 44.82 46 | 43.36 46 | 58.67 43 | 28.88 40 | 12.16 62 | 32.42 52 |
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010) |
Pnet-eth | | | 31.53 50 | 34.06 40 | 29.85 57 | 41.28 49 | 17.75 63 | 20.71 52 | 47.41 35 | 30.53 54 |
|
F/T MVSNet+Gipuma | | | 31.25 51 | 25.73 53 | 34.93 50 | 34.16 54 | 33.91 53 | 23.61 48 | 27.84 53 | 36.73 48 |
|
MVSNet + Gipuma | | | 31.15 52 | 26.01 52 | 34.58 51 | 33.87 56 | 33.39 54 | 23.75 47 | 28.26 52 | 36.47 49 |
|
hgnet | | | 30.74 53 | 25.12 55 | 34.49 52 | 40.98 50 | 47.29 45 | 24.56 45 | 25.68 56 | 15.18 61 |
|
DPSNet | | | 30.74 53 | 25.12 55 | 34.49 52 | 40.98 50 | 47.29 45 | 24.56 45 | 25.68 56 | 15.18 61 |
|
MVE |  | 39.65 21 | 30.69 55 | 31.26 43 | 30.31 56 | 23.68 60 | 36.67 50 | 26.92 42 | 35.60 48 | 30.60 53 |
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014) |
firsttry | | | 28.73 56 | 23.72 57 | 32.06 55 | 31.74 57 | 30.80 58 | 21.15 51 | 26.30 55 | 33.65 51 |
|
unMVSv1 | | | 28.02 57 | 26.35 49 | 29.13 58 | 30.17 58 | 32.63 56 | 26.14 44 | 26.55 54 | 24.58 56 |
|
example | | | 27.92 58 | 19.45 60 | 33.56 54 | 42.92 48 | 46.29 47 | 19.84 54 | 19.07 59 | 11.46 64 |
|
RMVSNet | | | 26.78 59 | 32.62 41 | 22.89 59 | 27.05 59 | 26.01 59 | 26.90 43 | 38.35 43 | 15.62 60 |
|
metmvs_fine | | | 22.70 60 | 30.59 44 | 17.43 63 | 17.52 62 | 16.63 65 | 22.55 50 | 38.64 42 | 18.14 58 |
|
unMVSmet | | | 17.94 61 | 14.89 61 | 19.98 61 | 19.45 61 | 24.72 60 | 13.90 59 | 15.87 60 | 15.75 59 |
|
test_1120 |  | | 17.74 62 | 12.97 62 | 20.92 60 | 13.88 64 | 22.05 61 | 12.33 61 | 13.61 61 | 26.82 55 |
|
Cas-MVS_preliminary | | | 14.58 63 | 9.47 64 | 17.99 62 | 13.62 65 | 18.53 62 | 10.67 62 | 8.27 64 | 21.82 57 |
|
confMetMVS | | | 13.05 64 | 10.92 63 | 14.47 64 | 14.73 63 | 17.12 64 | 10.20 63 | 11.64 63 | 11.56 63 |
|
CMPMVS |  | 59.16 19 | 7.91 65 | 0.09 66 | 13.12 65 | 3.14 66 | 36.21 51 | 0.19 66 | 0.00 66 | 0.00 66 |
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011 |
FADENet | | | 0.56 66 | 0.62 65 | 0.51 66 | 0.86 67 | 0.42 66 | 0.78 65 | 0.45 65 | 0.27 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 | | | | | | 34.16 54 | | | | |
|