SDC-Depth

Reported on 4 benchmarks across 2 tasks

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

Computer Vision2 results

Depth EstimationonCityscapes test
RMSE
6.917
best: 6.352 (SwinMTL)
Depth EstimationonNYU-Depth V2
RMSE
0.497
best: 0.013 (Defocus/DepthNet (Normalized))

Methodology2 results

3DonCityscapes test
RMSE
6.917
best: 6.352 (SwinMTL)
3DonNYU-Depth V2
RMSE
0.497
best: 0.013 (Defocus/DepthNet (Normalized))