DeepPCF-MVS | | 96.37 2 | 92.61 1 | 89.11 1 | 94.94 1 | 95.58 1 | 95.07 1 | 85.62 1 | 92.60 1 | 94.17 1 |
|
DeepC-MVS_fast | | 96.70 1 | 92.27 2 | 88.75 2 | 94.63 2 | 95.15 3 | 94.80 2 | 85.14 3 | 92.35 2 | 93.92 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 | | 95.98 3 | 91.43 3 | 87.48 4 | 94.06 4 | 94.52 5 | 94.15 5 | 83.69 6 | 91.26 3 | 93.50 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 | | 93.98 7 | 90.68 4 | 88.05 3 | 92.44 7 | 92.42 10 | 93.52 8 | 85.24 2 | 90.85 6 | 91.36 14 |
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019 |
TAPA-MVS(SR) | | | 90.57 5 | 87.48 4 | 92.63 6 | 92.64 8 | 93.17 11 | 83.91 5 | 91.04 4 | 92.10 12 |
|
PCF-MVS | | 93.45 10 | 90.50 6 | 85.08 13 | 94.11 3 | 95.54 2 | 93.44 10 | 82.27 11 | 87.88 15 | 93.34 4 |
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019 |
COLMAP(SR) | | | 90.17 7 | 85.79 11 | 93.08 5 | 92.63 9 | 93.87 6 | 82.51 10 | 89.07 13 | 92.74 6 |
|
PLC |  | 95.07 4 | 89.96 8 | 87.00 6 | 91.94 12 | 90.65 18 | 92.68 15 | 83.01 8 | 90.98 5 | 92.48 7 |
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019 |
COLMAP(base) | | | 89.91 9 | 86.37 8 | 92.28 9 | 91.56 14 | 92.95 13 | 82.53 9 | 90.21 7 | 92.33 8 |
|
ACMH+ | | 92.99 13 | 89.84 10 | 85.96 10 | 92.43 8 | 92.28 11 | 92.84 14 | 81.89 12 | 90.03 8 | 92.17 10 |
|
GSE | | | 89.80 11 | 86.71 7 | 91.87 13 | 90.87 17 | 92.62 16 | 83.49 7 | 89.92 9 | 92.11 11 |
|
ACMM | | 93.85 8 | 89.42 12 | 85.42 12 | 92.10 11 | 91.09 16 | 92.98 12 | 81.16 14 | 89.68 10 | 92.23 9 |
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019 |
ACMP | | 93.49 9 | 89.04 13 | 84.30 16 | 92.21 10 | 90.34 19 | 93.47 9 | 79.54 18 | 89.07 13 | 92.81 5 |
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020 |
LTVRE_ROB | | 92.95 14 | 89.00 14 | 86.32 9 | 90.78 19 | 91.67 13 | 89.54 24 | 84.87 4 | 87.77 16 | 91.13 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 |
ACMH | | 92.88 15 | 88.89 15 | 84.55 14 | 91.78 14 | 91.37 15 | 92.41 17 | 79.88 16 | 89.21 11 | 91.56 13 |
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019 |
COLMAP_ROB |  | 93.27 11 | 88.32 16 | 84.41 15 | 90.93 18 | 89.38 21 | 92.11 18 | 79.72 17 | 89.10 12 | 91.28 15 |
Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016 |
3Dnovator | | 94.51 5 | 87.43 17 | 80.90 21 | 91.78 14 | 94.76 4 | 94.22 3 | 78.96 19 | 82.85 21 | 86.35 20 |
|
3Dnovator+ | | 94.38 6 | 87.07 18 | 80.26 22 | 91.61 16 | 94.34 6 | 94.17 4 | 78.01 20 | 82.52 22 | 86.34 21 |
|
A-TVSNet + Gipuma |  | | 86.96 19 | 82.91 18 | 89.65 21 | 88.10 23 | 91.71 19 | 80.23 15 | 85.60 20 | 89.15 18 |
|
BP-MVSNet | | | 86.71 20 | 81.68 19 | 90.06 20 | 91.85 12 | 87.55 29 | 75.75 23 | 87.61 17 | 90.77 17 |
Christian Sormann, Patrick Knöbelreiter, Andreas Kuhn, Mattia Rossi, Thomas Pock, Friedrich Fraundorfer: BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo. 3DV 2020 |
OpenMVS |  | 93.04 12 | 86.34 21 | 79.08 23 | 91.18 17 | 93.50 7 | 93.77 7 | 76.56 21 | 81.60 25 | 86.26 22 |
|
LPCS | | | 85.52 22 | 83.61 17 | 86.79 23 | 84.99 29 | 88.49 26 | 81.34 13 | 85.87 19 | 86.89 19 |
|
PVSNet_0 | | 88.72 17 | 82.59 23 | 75.14 27 | 87.55 22 | 88.79 22 | 88.38 27 | 73.35 26 | 76.93 29 | 85.48 23 |
|
PVSNet | | 91.96 16 | 81.42 24 | 74.82 28 | 85.83 26 | 87.90 24 | 86.77 30 | 74.82 24 | 74.81 33 | 82.83 24 |
|
R-MVSNet | | | 81.26 25 | 77.44 24 | 83.81 28 | 82.82 30 | 86.25 31 | 74.52 25 | 80.36 27 | 82.37 25 |
|
CIDER | | | 80.48 26 | 72.14 30 | 86.05 24 | 87.66 25 | 89.77 22 | 71.75 27 | 72.53 37 | 80.72 27 |
Qingshan Xu and Wenbing Tao: Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume. AAAI 2020 |
test_1205 | | | 80.31 27 | 75.46 26 | 83.55 29 | 86.48 27 | 90.90 20 | 70.38 29 | 80.54 26 | 73.26 38 |
|
test_1126 | | | 80.30 28 | 71.93 32 | 85.88 25 | 89.75 20 | 90.41 21 | 70.18 30 | 73.68 35 | 77.50 31 |
|
OpenMVS_ROB |  | 86.42 18 | 80.25 29 | 71.88 33 | 85.82 27 | 87.52 26 | 89.56 23 | 70.53 28 | 73.24 36 | 80.39 28 |
|
ANet-0.75 | | | 77.73 30 | 74.78 29 | 79.70 32 | 77.01 36 | 84.71 34 | 67.34 34 | 82.21 24 | 77.39 32 |
|
P-MVSNet | | | 77.69 31 | 81.61 20 | 75.07 38 | 71.91 42 | 77.33 40 | 76.51 22 | 86.71 18 | 75.98 35 |
|
CPR_FA | | | 74.23 32 | 72.06 31 | 75.68 36 | 74.30 40 | 70.69 46 | 68.60 32 | 75.52 31 | 82.05 26 |
|
ANet | | | 74.07 33 | 68.26 35 | 77.94 35 | 77.01 36 | 84.71 34 | 64.75 35 | 71.76 38 | 72.09 39 |
|
AttMVS | | | 72.35 34 | 68.13 36 | 75.16 37 | 70.98 46 | 80.63 36 | 68.09 33 | 68.16 39 | 73.87 37 |
|
Pnet-new- | | | 70.55 35 | 53.66 47 | 81.81 31 | 81.27 32 | 85.23 33 | 51.15 44 | 56.17 53 | 78.92 30 |
|
CasMVSNet(SR_A) | | | 69.66 36 | 55.07 43 | 79.38 33 | 80.08 33 | 87.62 28 | 46.56 49 | 63.58 46 | 70.44 40 |
|
Pnet_fast | | | 68.89 37 | 47.01 56 | 83.47 30 | 81.84 31 | 89.30 25 | 38.61 57 | 55.42 54 | 79.28 29 |
|
CasMVSNet(base) | | | 68.63 38 | 53.70 46 | 78.58 34 | 79.92 34 | 85.96 32 | 44.83 51 | 62.57 48 | 69.87 41 |
|
A1Net | | | 68.49 39 | 75.64 25 | 63.72 48 | 63.53 53 | 51.39 61 | 68.88 31 | 82.41 23 | 76.23 34 |
|
MVSNet_plusplus | | | 64.09 40 | 48.06 54 | 74.77 39 | 85.29 28 | 62.00 51 | 31.11 61 | 65.01 40 | 77.03 33 |
|
Pnet-blend | | | 64.02 41 | 52.13 51 | 71.95 40 | 75.81 38 | 78.00 38 | 40.66 54 | 63.61 44 | 62.05 46 |
|
Pnet-blend++ | | | 64.02 41 | 52.13 51 | 71.95 40 | 75.81 38 | 78.00 38 | 40.66 54 | 63.61 44 | 62.05 46 |
|
unMVSv1 | | | 63.91 43 | 62.59 39 | 64.80 47 | 66.39 49 | 68.00 49 | 61.62 36 | 63.55 47 | 60.01 49 |
|
MVSNet | | | 63.58 44 | 56.25 41 | 68.47 46 | 66.00 50 | 71.12 43 | 48.36 46 | 64.13 41 | 68.29 43 |
|
MVSCRF | | | 63.13 45 | 52.16 50 | 70.45 42 | 70.18 47 | 75.83 42 | 51.17 43 | 53.16 57 | 65.33 44 |
|
RMVSNet | | | 62.69 46 | 69.01 34 | 58.48 56 | 69.15 48 | 58.56 55 | 59.72 37 | 78.30 28 | 47.75 59 |
|
metmvs_fine | | | 60.95 47 | 66.50 37 | 57.25 58 | 64.00 51 | 51.92 59 | 59.04 38 | 73.97 34 | 55.84 54 |
|
Snet | | | 60.77 48 | 47.18 55 | 69.82 43 | 77.90 35 | 61.73 52 | 39.61 56 | 54.76 55 | 69.82 42 |
|
Pnet-eth | | | 60.43 49 | 65.87 38 | 56.80 59 | 63.59 52 | 45.39 64 | 55.58 40 | 76.16 30 | 61.43 48 |
|
MVSNet_++ | | | 59.91 50 | 45.04 57 | 69.82 43 | 74.28 41 | 60.08 53 | 14.97 64 | 75.11 32 | 75.10 36 |
|
hgnet | | | 59.89 51 | 54.16 44 | 63.70 49 | 71.39 43 | 70.87 44 | 52.09 41 | 56.24 51 | 48.85 56 |
|
DPSNet | | | 59.89 51 | 54.16 44 | 63.70 49 | 71.39 43 | 70.87 44 | 52.09 41 | 56.24 51 | 48.85 56 |
|
MVE |  | 62.14 20 | 59.41 53 | 60.38 40 | 58.77 55 | 50.39 62 | 69.00 48 | 56.98 39 | 63.78 43 | 56.91 53 |
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014) |
test_1124 | | | 58.90 54 | 44.17 59 | 68.72 45 | 62.60 58 | 78.44 37 | 38.12 58 | 50.22 58 | 65.10 45 |
|
MVSNet + Gipuma | | | 57.07 55 | 53.08 48 | 59.73 54 | 62.91 56 | 57.42 57 | 48.41 45 | 57.74 49 | 58.88 50 |
|
CasMVSNet(SR_B) | | | 56.87 56 | 55.95 42 | 57.48 57 | 56.06 59 | 67.85 50 | 47.86 48 | 64.05 42 | 48.53 58 |
|
F/T MVSNet+Gipuma | | | 55.78 57 | 49.83 53 | 59.76 53 | 63.10 54 | 57.51 56 | 46.34 50 | 53.31 56 | 58.66 51 |
|
example | | | 55.06 58 | 44.75 58 | 61.93 51 | 71.21 45 | 69.85 47 | 42.82 53 | 46.68 59 | 44.73 61 |
|
firsttry | | | 54.62 59 | 52.74 49 | 55.88 60 | 54.90 60 | 55.69 58 | 48.02 47 | 57.46 50 | 57.06 52 |
|
PMVS |  | 61.03 21 | 49.24 60 | 32.69 64 | 60.27 52 | 62.70 57 | 76.26 41 | 42.99 52 | 22.38 64 | 41.86 62 |
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010) |
unMVSmet | | | 48.01 61 | 40.73 61 | 52.86 61 | 53.90 61 | 58.72 54 | 36.72 60 | 44.74 61 | 45.96 60 |
|
confMetMVS | | | 44.56 62 | 41.82 60 | 46.39 62 | 46.63 63 | 51.78 60 | 37.38 59 | 46.25 60 | 40.77 63 |
|
test_1120 |  | | 40.25 63 | 35.81 63 | 43.21 63 | 30.29 65 | 50.38 62 | 29.89 63 | 41.72 63 | 48.95 55 |
|
Cas-MVS_preliminary | | | 38.91 64 | 36.73 62 | 40.37 64 | 37.57 64 | 48.76 63 | 30.59 62 | 42.87 62 | 34.76 64 |
|
CMPMVS |  | 66.06 19 | 9.32 65 | 0.44 66 | 15.23 65 | 6.17 66 | 39.51 65 | 0.89 66 | 0.00 66 | 0.00 66 |
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011 |
FADENet | | | 4.02 66 | 4.30 65 | 3.83 66 | 6.03 67 | 3.71 66 | 5.02 65 | 3.58 65 | 1.74 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 | | | | | | 63.10 54 | | | | |
|