DeepLabV3+ (F10)

Reported on 4 benchmarks across 2 tasks · 1 paper

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· 2020-01-14
0.575
best: 0.013 (Defocus/DepthNet (Normalized))
Single Image Depth Estimation Trained via Depth from Defocus Cues arXiv:2001.05036
Depth EstimationonKITTI Eigen split
absolute relative error· 2020-01-14
0.11
best: 0.029 (SPIDepth)
Single Image Depth Estimation Trained via Depth from Defocus Cues arXiv:2001.05036

Methodology2 results

3DonNYU-Depth V2
RMSE· 2020-01-14
0.575
best: 0.013 (Defocus/DepthNet (Normalized))
Single Image Depth Estimation Trained via Depth from Defocus Cues arXiv:2001.05036
3DonKITTI Eigen split
absolute relative error· 2020-01-14
0.11
best: 0.029 (SPIDepth)
Single Image Depth Estimation Trained via Depth from Defocus Cues arXiv:2001.05036