DenseDepth

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Depth EstimationonNYU-Depth V2
RMSE· 2018-12-31
0.465
best: 0.013 (Defocus/DepthNet (Normalized))
SOTA
High Quality Monocular Depth Estimation via Transfer Learning arXiv:1812.11941
Depth EstimationonKITTI Eigen split
absolute relative error· 2018-12-31
0.093
best: 0.029 (SPIDepth)
High Quality Monocular Depth Estimation via Transfer Learning arXiv:1812.11941

Methodology2 results

3DonNYU-Depth V2
RMSE· 2018-12-31
0.465
best: 0.013 (Defocus/DepthNet (Normalized))
SOTA
High Quality Monocular Depth Estimation via Transfer Learning arXiv:1812.11941
3DonKITTI Eigen split
absolute relative error· 2018-12-31
0.093
best: 0.029 (SPIDepth)
High Quality Monocular Depth Estimation via Transfer Learning arXiv:1812.11941