SUN RGB-D

RGB-D scene recognition approaches often train two standalone backbones for RGB and depth modalities with the same Places or ImageNet pre-training. However, the pre-trained depth network is still biased by RGB-based models which may result in a suboptimal solution.

Data and Resources

Cite this as

Shuran Song, Samuel P. Lichtenberg, Jianxiong Xiao (2024). Dataset: SUN RGB-D. https://doi.org/10.57702/ppmjecld

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2309.01624
Citation
  • https://doi.org/10.48550/arXiv.2201.08377
  • https://doi.org/10.48550/arXiv.2302.02858
  • https://doi.org/10.48550/arXiv.2105.06461
  • https://doi.org/10.48550/arXiv.2203.10856
  • https://doi.org/10.48550/arXiv.2302.06148
  • https://doi.org/10.48550/arXiv.1609.02948
  • https://doi.org/10.48550/arXiv.2303.17559
  • https://doi.org/10.48550/arXiv.1810.03410
  • https://doi.org/10.48550/arXiv.1701.07122
Author Shuran Song
More Authors
Samuel P. Lichtenberg
Jianxiong Xiao
Homepage http://cs.umiacs.umd.edu/~vlad/rgbd-dataset/