DeepPCF-MVS | | 93.97 1 | 87.63 1 | 82.10 1 | 91.31 1 | 91.80 1 | 91.34 1 | 77.64 1 | 86.56 1 | 90.79 1 |
|
DeepC-MVS_fast | | 93.89 2 | 86.59 2 | 80.39 2 | 90.73 2 | 91.00 3 | 90.77 2 | 75.90 3 | 84.89 3 | 90.41 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 | | 93.07 3 | 85.88 3 | 79.73 4 | 89.98 3 | 89.82 6 | 90.09 5 | 74.93 5 | 84.53 4 | 90.03 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 | | 90.10 7 | 84.80 4 | 80.13 3 | 87.91 6 | 88.22 8 | 88.54 9 | 75.35 4 | 84.91 2 | 86.96 14 |
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019 |
PCF-MVS | | 89.48 10 | 84.51 5 | 76.96 10 | 89.54 4 | 91.30 2 | 88.76 7 | 73.35 8 | 80.56 12 | 88.57 4 |
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019 |
TAPA-MVS(SR) | | | 83.88 6 | 78.08 7 | 87.74 8 | 88.99 7 | 86.49 16 | 73.17 10 | 82.99 6 | 87.76 10 |
|
COLMAP(base) | | | 83.59 7 | 77.50 9 | 87.65 9 | 86.74 12 | 87.68 11 | 73.30 9 | 81.70 9 | 88.52 5 |
|
PLC |  | 91.00 6 | 83.54 8 | 78.38 5 | 86.98 13 | 85.38 16 | 87.33 13 | 73.45 6 | 83.31 5 | 88.23 9 |
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019 |
GSE | | | 83.39 9 | 77.82 8 | 87.10 12 | 85.70 15 | 87.27 14 | 73.41 7 | 82.23 7 | 88.34 8 |
|
COLMAP(SR) | | | 83.28 10 | 76.24 12 | 87.97 5 | 87.61 9 | 87.90 10 | 72.76 11 | 79.71 14 | 88.39 7 |
|
ACMH+ | | 87.92 13 | 82.46 11 | 76.63 11 | 86.35 16 | 86.95 11 | 84.52 19 | 71.68 12 | 81.58 10 | 87.56 12 |
|
ACMP | | 89.59 9 | 82.31 12 | 75.00 14 | 87.18 11 | 84.49 20 | 88.57 8 | 68.43 18 | 81.58 10 | 88.49 6 |
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020 |
LTVRE_ROB | | 88.41 12 | 82.23 13 | 78.11 6 | 84.97 19 | 86.24 13 | 82.83 25 | 76.93 2 | 79.30 15 | 85.84 16 |
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 | | 89.79 8 | 82.20 14 | 75.34 13 | 86.76 14 | 84.94 18 | 87.68 11 | 68.85 17 | 81.84 8 | 87.67 11 |
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019 |
3Dnovator | | 91.36 5 | 82.19 15 | 74.09 16 | 87.59 10 | 89.83 5 | 90.10 4 | 71.54 13 | 76.63 18 | 82.84 20 |
|
3Dnovator+ | | 91.43 4 | 81.91 16 | 73.11 19 | 87.78 7 | 90.06 4 | 90.17 3 | 70.40 15 | 75.82 21 | 83.12 18 |
|
COLMAP_ROB |  | 87.81 14 | 81.57 17 | 74.74 15 | 86.13 17 | 83.81 21 | 87.08 15 | 69.46 16 | 80.01 13 | 87.49 13 |
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016 |
ACMH | | 87.59 15 | 80.55 18 | 73.69 17 | 85.11 18 | 86.17 14 | 82.81 26 | 68.19 19 | 79.20 16 | 86.36 15 |
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019 |
OpenMVS |  | 89.19 11 | 80.38 19 | 71.40 20 | 86.37 15 | 87.42 10 | 89.29 6 | 67.70 20 | 75.10 22 | 82.40 22 |
|
LPCS | | | 78.54 20 | 73.62 18 | 81.82 22 | 79.59 27 | 83.19 23 | 71.25 14 | 75.99 20 | 82.69 21 |
|
A-TVSNet + Gipuma |  | | 77.14 21 | 67.96 23 | 83.26 20 | 80.53 24 | 86.26 17 | 65.25 21 | 70.67 23 | 82.99 19 |
|
BP-MVSNet | | | 76.76 22 | 68.58 22 | 82.22 21 | 84.51 19 | 77.66 35 | 60.98 26 | 76.18 19 | 84.48 17 |
Christian Sormann, Patrick Knöbelreiter, Andreas Kuhn, Mattia Rossi, Thomas Pock, Friedrich Fraundorfer: BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo. 3DV 2020 |
PVSNet_0 | | 82.17 17 | 74.27 23 | 64.50 25 | 80.78 23 | 81.77 23 | 80.64 29 | 61.11 24 | 67.89 26 | 79.92 23 |
|
PVSNet | | 86.66 16 | 73.29 24 | 65.21 24 | 78.67 27 | 80.40 25 | 77.98 33 | 64.04 23 | 66.38 29 | 77.62 24 |
|
OpenMVS_ROB |  | 81.14 18 | 73.28 25 | 63.11 27 | 80.06 25 | 82.70 22 | 81.62 28 | 61.11 24 | 65.12 31 | 75.87 25 |
|
CIDER | | | 72.92 26 | 62.80 28 | 79.66 26 | 80.16 26 | 83.22 22 | 60.69 27 | 64.90 32 | 75.61 27 |
Qingshan Xu and Wenbing Tao: Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume. AAAI 2020 |
test_1126 | | | 71.43 27 | 57.57 33 | 80.67 24 | 85.16 17 | 84.45 20 | 55.16 31 | 59.98 36 | 72.40 29 |
|
test_1205 | | | 70.75 28 | 62.35 29 | 76.35 30 | 78.70 28 | 85.03 18 | 55.63 30 | 69.08 24 | 65.34 39 |
|
R-MVSNet | | | 70.54 29 | 63.98 26 | 74.91 32 | 73.85 34 | 77.87 34 | 59.85 28 | 68.11 25 | 73.01 28 |
|
P-MVSNet | | | 70.42 30 | 71.20 21 | 69.90 36 | 66.73 39 | 72.02 37 | 64.84 22 | 77.55 17 | 70.95 31 |
|
ANet-0.75 | | | 67.51 31 | 58.66 32 | 73.41 34 | 70.12 35 | 79.37 30 | 50.72 33 | 66.61 28 | 70.74 32 |
|
AttMVS | | | 65.89 32 | 60.14 30 | 69.73 37 | 64.68 42 | 75.04 36 | 58.80 29 | 61.47 35 | 69.47 34 |
|
ANet | | | 63.85 33 | 52.65 35 | 71.32 35 | 70.12 35 | 79.37 30 | 48.53 35 | 56.77 39 | 64.48 40 |
|
Pnet-new- | | | 63.42 34 | 42.13 45 | 77.61 28 | 77.71 30 | 79.30 32 | 41.06 38 | 43.20 51 | 75.82 26 |
|
CasMVSNet(SR_A) | | | 63.08 35 | 45.33 42 | 74.92 31 | 74.36 31 | 83.73 21 | 37.04 45 | 53.62 42 | 66.66 37 |
|
CasMVSNet(base) | | | 61.88 36 | 43.72 43 | 73.99 33 | 74.03 33 | 81.95 27 | 34.99 48 | 52.45 43 | 65.99 38 |
|
Pnet_fast | | | 59.94 37 | 35.26 57 | 76.39 29 | 74.15 32 | 82.99 24 | 25.02 56 | 45.51 48 | 72.03 30 |
|
CPR_FA | | | 58.26 38 | 56.35 34 | 59.54 45 | 56.43 49 | 55.34 48 | 50.61 34 | 62.09 34 | 66.83 36 |
|
MVSNet | | | 56.22 39 | 46.49 39 | 62.70 41 | 57.79 46 | 67.16 43 | 38.93 41 | 54.05 40 | 63.16 42 |
|
A1Net | | | 54.85 40 | 59.98 31 | 51.43 48 | 47.46 58 | 42.97 57 | 52.72 32 | 67.24 27 | 63.86 41 |
|
MVSNet_plusplus | | | 54.10 41 | 36.12 55 | 66.09 38 | 78.36 29 | 49.55 52 | 20.40 61 | 51.84 44 | 70.36 33 |
|
Pnet-blend | | | 53.68 42 | 37.04 52 | 64.76 39 | 68.91 37 | 70.02 39 | 24.13 57 | 49.96 46 | 55.36 46 |
|
Pnet-blend++ | | | 53.68 42 | 37.04 52 | 64.76 39 | 68.91 37 | 70.02 39 | 24.13 57 | 49.96 46 | 55.36 46 |
|
MVSCRF | | | 51.99 44 | 37.64 49 | 61.55 43 | 58.88 43 | 68.35 41 | 34.99 48 | 40.28 54 | 57.43 45 |
|
MVSNet_++ | | | 50.85 45 | 37.40 50 | 59.81 44 | 65.34 41 | 46.28 53 | 9.19 64 | 65.60 30 | 67.81 35 |
|
test_1124 | | | 50.28 46 | 31.72 58 | 62.65 42 | 58.29 45 | 70.82 38 | 27.23 55 | 36.21 58 | 58.84 43 |
|
Snet | | | 49.32 47 | 36.02 56 | 58.18 46 | 66.02 40 | 50.24 50 | 27.93 54 | 44.12 49 | 58.27 44 |
|
CasMVSNet(SR_B) | | | 48.99 48 | 45.75 40 | 51.15 49 | 49.07 56 | 62.78 44 | 37.57 42 | 53.93 41 | 41.61 53 |
|
Pnet-eth | | | 45.62 49 | 49.15 37 | 43.27 58 | 53.31 51 | 29.96 65 | 35.03 47 | 63.26 33 | 46.53 50 |
|
unMVSv1 | | | 45.02 50 | 43.12 44 | 46.29 55 | 47.83 57 | 50.14 51 | 42.67 36 | 43.57 50 | 40.92 54 |
|
RMVSNet | | | 44.67 51 | 50.67 36 | 40.67 59 | 50.79 52 | 41.21 59 | 42.32 37 | 59.02 37 | 30.02 58 |
|
MVE |  | 50.73 21 | 44.67 51 | 45.57 41 | 44.07 57 | 35.90 61 | 52.30 49 | 40.89 39 | 50.26 45 | 44.00 52 |
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014) |
DPSNet | | | 44.61 53 | 38.48 47 | 48.69 50 | 57.33 47 | 60.08 45 | 37.17 43 | 39.80 56 | 28.65 60 |
|
hgnet | | | 44.61 53 | 38.48 47 | 48.69 50 | 57.33 47 | 60.08 45 | 37.17 43 | 39.80 56 | 28.65 60 |
|
MVSNet + Gipuma | | | 44.11 55 | 38.76 46 | 47.67 53 | 50.05 55 | 45.26 55 | 34.93 50 | 42.60 52 | 47.71 48 |
|
F/T MVSNet+Gipuma | | | 43.59 56 | 37.31 51 | 47.78 52 | 50.12 53 | 45.64 54 | 34.25 51 | 40.37 53 | 47.60 49 |
|
PMVS |  | 53.92 20 | 42.74 57 | 26.50 60 | 53.57 47 | 54.03 50 | 68.05 42 | 36.35 46 | 16.65 64 | 38.64 55 |
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010) |
firsttry | | | 41.11 58 | 36.23 54 | 44.36 56 | 43.82 59 | 43.77 56 | 32.28 52 | 40.18 55 | 45.51 51 |
|
example | | | 40.49 59 | 30.54 59 | 47.11 54 | 58.75 44 | 58.88 47 | 29.97 53 | 31.12 59 | 23.71 64 |
|
metmvs_fine | | | 39.41 60 | 48.46 38 | 33.38 61 | 35.53 62 | 31.67 64 | 39.28 40 | 57.64 38 | 32.95 57 |
|
unMVSmet | | | 32.09 61 | 25.89 61 | 36.22 60 | 36.96 60 | 42.02 58 | 23.79 59 | 27.99 60 | 29.68 59 |
|
test_1120 |  | | 27.94 62 | 22.22 63 | 31.76 62 | 20.92 65 | 37.22 61 | 18.54 63 | 25.90 62 | 37.14 56 |
|
confMetMVS | | | 26.62 63 | 23.72 62 | 28.55 64 | 28.79 63 | 33.00 63 | 21.33 60 | 26.10 61 | 23.86 63 |
|
Cas-MVS_preliminary | | | 25.33 64 | 19.98 64 | 28.90 63 | 24.65 64 | 34.26 62 | 18.62 62 | 21.35 63 | 27.78 62 |
|
CMPMVS |  | 62.92 19 | 8.44 65 | 0.22 66 | 13.92 65 | 4.26 66 | 37.50 60 | 0.45 66 | 0.00 66 | 0.00 66 |
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011 |
FADENet | | | 1.48 66 | 1.79 65 | 1.27 66 | 2.11 67 | 1.06 66 | 2.23 65 | 1.34 65 | 0.65 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 | | | | | | 50.12 53 | | | | |
|