DeepC-MVS_fast | | 98.69 1 | 96.77 1 | 95.30 1 | 97.74 1 | 98.24 2 | 97.85 3 | 92.74 2 | 97.86 1 | 97.13 1 |
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020 |
DeepPCF-MVS | | 98.18 3 | 96.68 2 | 95.10 2 | 97.74 1 | 98.30 1 | 97.78 5 | 92.41 3 | 97.79 2 | 97.12 2 |
|
DeepC-MVS | | 98.35 2 | 96.09 3 | 94.20 10 | 97.34 3 | 97.94 4 | 97.39 10 | 90.85 13 | 97.56 3 | 96.71 4 |
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020 |
COLMAP(SR) | | | 96.07 4 | 94.39 7 | 97.19 5 | 96.86 8 | 97.92 2 | 91.54 10 | 97.24 7 | 96.79 3 |
|
TAPA-MVS(SR) | | | 95.82 5 | 94.80 3 | 96.49 9 | 96.19 12 | 97.58 9 | 92.04 4 | 97.56 3 | 95.71 12 |
|
ACMM | | 97.58 5 | 95.68 6 | 94.49 6 | 96.48 10 | 96.12 13 | 97.20 13 | 92.04 4 | 96.94 10 | 96.10 9 |
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019 |
PCF-MVS | | 97.08 13 | 95.68 6 | 93.36 14 | 97.23 4 | 98.16 3 | 96.93 14 | 91.43 11 | 95.29 19 | 96.61 5 |
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019 |
ACMH+ | | 97.24 9 | 95.61 8 | 93.77 13 | 96.83 6 | 96.69 10 | 97.71 6 | 90.70 14 | 96.85 11 | 96.09 10 |
|
TAPA-MVS | | 97.07 14 | 95.48 9 | 94.55 4 | 96.10 12 | 95.68 16 | 97.30 11 | 91.73 8 | 97.37 5 | 95.32 15 |
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019 |
COLMAP(base) | | | 95.42 10 | 94.03 12 | 96.35 11 | 95.96 14 | 96.92 15 | 91.10 12 | 96.97 8 | 96.16 8 |
|
PLC |  | 97.94 4 | 95.35 11 | 94.28 9 | 96.06 13 | 95.26 19 | 96.59 16 | 91.61 9 | 96.96 9 | 96.34 7 |
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019 |
ACMH | | 97.28 7 | 95.29 12 | 93.25 15 | 96.65 7 | 96.32 11 | 97.93 1 | 89.82 16 | 96.68 14 | 95.69 13 |
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019 |
ACMP | | 97.20 10 | 95.11 13 | 93.01 18 | 96.52 8 | 95.68 16 | 97.26 12 | 89.74 17 | 96.27 16 | 96.61 5 |
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020 |
LTVRE_ROB | | 97.16 11 | 95.10 14 | 94.13 11 | 95.75 14 | 95.69 15 | 95.73 20 | 92.87 1 | 95.39 18 | 95.83 11 |
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 |
GSE | | | 95.00 15 | 94.33 8 | 95.45 17 | 94.81 20 | 96.53 18 | 91.98 6 | 96.68 14 | 95.02 17 |
|
A-TVSNet + Gipuma |  | | 94.96 16 | 94.54 5 | 95.24 19 | 95.31 18 | 96.58 17 | 91.82 7 | 97.27 6 | 93.83 18 |
|
BP-MVSNet | | | 94.57 17 | 93.20 16 | 95.49 15 | 96.77 9 | 94.34 28 | 89.67 18 | 96.74 12 | 95.35 14 |
Christian Sormann, Patrick Knöbelreiter, Andreas Kuhn, Mattia Rossi, Thomas Pock, Friedrich Fraundorfer: BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo. 3DV 2020 |
COLMAP_ROB |  | 97.56 6 | 94.43 18 | 93.09 17 | 95.33 18 | 94.55 21 | 96.37 19 | 89.45 19 | 96.72 13 | 95.07 16 |
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016 |
3Dnovator | | 97.25 8 | 92.47 19 | 87.97 27 | 95.47 16 | 97.93 5 | 97.85 3 | 86.02 23 | 89.92 27 | 90.64 22 |
|
3Dnovator+ | | 97.12 12 | 92.17 20 | 87.57 28 | 95.24 19 | 97.49 6 | 97.68 7 | 85.24 26 | 89.91 28 | 90.54 23 |
|
LPCS | | | 92.07 21 | 92.93 19 | 91.49 26 | 90.32 30 | 93.29 30 | 90.66 15 | 95.20 20 | 90.87 21 |
|
OpenMVS |  | 96.50 15 | 91.77 22 | 86.65 30 | 95.19 21 | 97.38 7 | 97.66 8 | 84.60 29 | 88.69 32 | 90.53 24 |
|
R-MVSNet | | | 90.93 23 | 89.80 21 | 91.68 25 | 90.81 29 | 94.15 29 | 87.67 20 | 91.93 25 | 90.07 25 |
|
PVSNet_0 | | 94.43 17 | 90.46 24 | 85.77 31 | 93.59 22 | 93.82 23 | 95.33 23 | 84.62 28 | 86.92 34 | 91.61 20 |
|
test_1126 | | | 89.66 25 | 88.06 26 | 90.73 28 | 93.40 24 | 95.29 24 | 84.99 27 | 91.13 26 | 83.50 33 |
|
test_1205 | | | 89.53 26 | 89.08 24 | 89.83 31 | 92.63 26 | 95.71 21 | 85.34 25 | 92.82 24 | 81.15 39 |
|
CPR_FA | | | 89.35 27 | 88.37 25 | 90.00 30 | 89.38 32 | 87.69 38 | 87.29 22 | 89.46 30 | 92.93 19 |
|
PVSNet | | 96.02 16 | 89.22 28 | 84.53 35 | 92.35 23 | 93.29 25 | 94.60 27 | 85.85 24 | 83.20 37 | 89.17 26 |
|
CIDER | | | 88.55 29 | 83.13 37 | 92.16 24 | 93.95 22 | 95.61 22 | 83.79 32 | 82.47 38 | 86.92 28 |
Qingshan Xu and Wenbing Tao: Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume. AAAI 2020 |
ANet-0.75 | | | 87.89 30 | 89.58 22 | 86.76 32 | 84.37 44 | 90.29 34 | 84.51 30 | 94.65 21 | 85.61 31 |
|
OpenMVS_ROB |  | 92.34 18 | 87.46 31 | 81.75 38 | 91.27 27 | 92.55 27 | 95.21 25 | 81.21 36 | 82.29 39 | 86.05 29 |
|
P-MVSNet | | | 85.35 32 | 91.57 20 | 81.21 41 | 78.76 51 | 82.87 46 | 87.56 21 | 95.58 17 | 82.00 36 |
|
ANet | | | 85.16 33 | 85.20 33 | 85.14 35 | 84.37 44 | 90.29 34 | 82.00 34 | 88.39 33 | 80.78 41 |
|
unMVSv1 | | | 83.89 34 | 84.37 36 | 83.58 37 | 84.00 48 | 85.63 40 | 83.17 33 | 85.56 35 | 81.11 40 |
|
metmvs_fine | | | 83.50 35 | 84.90 34 | 82.56 39 | 84.72 39 | 81.80 49 | 81.09 37 | 88.72 31 | 81.17 38 |
|
A1Net | | | 82.90 36 | 89.39 23 | 78.57 50 | 85.19 36 | 63.18 63 | 84.36 31 | 94.42 22 | 87.34 27 |
|
RMVSNet | | | 80.62 37 | 86.71 29 | 76.57 52 | 84.14 46 | 78.09 51 | 80.22 38 | 93.20 23 | 67.48 58 |
|
Pnet_fast | | | 80.38 38 | 65.52 55 | 90.29 29 | 90.03 31 | 94.91 26 | 60.54 54 | 70.51 57 | 85.93 30 |
|
AttMVS | | | 80.32 39 | 78.27 39 | 81.68 40 | 78.98 50 | 86.16 39 | 79.76 39 | 76.79 52 | 79.89 42 |
|
Pnet-new- | | | 79.46 40 | 69.54 51 | 86.08 33 | 84.76 38 | 90.31 33 | 65.13 48 | 73.95 54 | 83.16 34 |
|
CasMVSNet(SR_A) | | | 79.00 41 | 69.56 50 | 85.29 34 | 85.95 34 | 92.82 31 | 62.08 51 | 77.05 48 | 77.11 43 |
|
hgnet | | | 78.82 42 | 76.20 41 | 80.57 45 | 84.50 40 | 82.32 47 | 75.56 41 | 76.84 49 | 74.88 47 |
|
DPSNet | | | 78.82 42 | 76.20 41 | 80.57 45 | 84.50 40 | 82.32 47 | 75.56 41 | 76.84 49 | 74.88 47 |
|
Pnet-blend++ | | | 78.13 44 | 73.62 45 | 81.13 42 | 84.46 42 | 88.20 36 | 66.50 45 | 80.74 41 | 70.74 56 |
|
Pnet-blend | | | 78.13 44 | 73.62 45 | 81.13 42 | 84.46 42 | 88.20 36 | 66.50 45 | 80.74 41 | 70.74 56 |
|
CasMVSNet(base) | | | 78.10 46 | 68.51 52 | 84.50 36 | 85.47 35 | 91.56 32 | 59.79 56 | 77.22 47 | 76.47 44 |
|
Pnet-eth | | | 77.75 47 | 85.52 32 | 72.57 57 | 75.57 53 | 65.89 61 | 81.44 35 | 89.61 29 | 76.26 45 |
|
MVSCRF | | | 77.21 48 | 74.57 44 | 78.98 49 | 79.29 49 | 83.87 44 | 75.01 43 | 74.12 53 | 73.78 51 |
|
MVE |  | 76.82 19 | 76.63 49 | 77.52 40 | 76.03 54 | 70.40 59 | 85.49 42 | 75.68 40 | 79.36 43 | 72.20 53 |
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014) |
MVSNet_plusplus | | | 76.50 50 | 66.38 53 | 83.25 38 | 91.25 28 | 73.79 56 | 53.62 62 | 79.14 44 | 84.70 32 |
|
example | | | 74.48 51 | 65.59 54 | 80.41 47 | 84.10 47 | 83.16 45 | 62.82 50 | 68.36 59 | 73.98 50 |
|
Snet | | | 74.39 52 | 64.28 57 | 81.13 42 | 88.04 33 | 73.18 59 | 60.15 55 | 68.41 58 | 82.18 35 |
|
MVSNet | | | 73.65 53 | 70.01 49 | 76.07 53 | 76.39 52 | 77.59 52 | 61.93 52 | 78.09 46 | 74.23 49 |
|
MVSNet + Gipuma | | | 72.61 54 | 71.20 47 | 73.54 55 | 75.39 54 | 73.46 58 | 65.60 47 | 76.81 51 | 71.78 54 |
|
firsttry | | | 72.49 55 | 75.56 43 | 70.44 59 | 68.80 62 | 70.25 60 | 69.31 44 | 81.82 40 | 72.28 52 |
|
MVSNet_++ | | | 71.81 56 | 59.04 62 | 80.33 48 | 84.86 37 | 74.23 55 | 33.06 64 | 85.02 36 | 81.88 37 |
|
test_1124 | | | 71.63 57 | 63.97 58 | 76.73 51 | 69.39 61 | 85.55 41 | 56.73 57 | 71.21 55 | 75.26 46 |
|
CasMVSNet(SR_B) | | | 70.07 58 | 71.18 48 | 69.33 60 | 69.73 60 | 77.06 53 | 64.06 49 | 78.31 45 | 61.20 61 |
|
F/T MVSNet+Gipuma | | | 69.80 59 | 64.46 56 | 73.36 56 | 75.05 55 | 73.57 57 | 60.74 53 | 68.18 60 | 71.46 55 |
|
unMVSmet | | | 66.94 60 | 60.67 61 | 71.11 58 | 71.91 58 | 79.70 50 | 54.62 59 | 66.73 61 | 61.74 60 |
|
confMetMVS | | | 63.51 61 | 60.95 60 | 65.21 62 | 60.95 63 | 76.48 54 | 55.53 58 | 66.38 62 | 58.21 62 |
|
test_1120 |  | | 58.74 62 | 57.03 63 | 59.88 63 | 49.42 65 | 64.79 62 | 49.65 63 | 64.41 63 | 65.45 59 |
|
PMVS |  | 70.75 20 | 58.19 63 | 43.22 64 | 68.18 61 | 73.06 57 | 84.09 43 | 54.23 60 | 32.21 64 | 47.37 63 |
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010) |
Cas-MVS_preliminary | | | 56.71 64 | 62.57 59 | 52.80 64 | 50.07 64 | 61.96 64 | 54.15 61 | 71.00 56 | 46.38 64 |
|
FADENet | | | 18.58 65 | 15.51 65 | 20.63 65 | 21.45 66 | 32.74 66 | 15.09 65 | 15.93 65 | 7.68 65 |
|
CMPMVS |  | 69.68 21 | 11.01 66 | 0.97 66 | 17.70 66 | 10.09 67 | 43.01 65 | 1.93 66 | 0.00 66 | 0.00 66 |
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011 |
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 | | | | | | 75.05 55 | | | | |
|