SUN RGB-D

doi:doi:10.57702/ppmjecld

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.

BibTex:

@dataset{Shuran_Song_and_Samuel_P_Lichtenberg_and_Jianxiong_Xiao_2024,
    abstract = {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.},
    author = {Shuran Song and Samuel P. Lichtenberg and Jianxiong Xiao},
    doi = {10.57702/ppmjecld},
    institution = {No Organization},
    keyword = {'3D Data Recognition', '3D Object Detection', '3D Object Recognition', 'Benchmark', 'Benchmark Suite', 'Indoor Scene', 'Object Detection', 'Object Recognition', 'Point Clouds', 'RGB and depth images', 'RGB-D', 'RGB-D Data', 'RGB-D Images', 'RGB-D images', 'RGBD images', 'SUN RGB-D', 'Scene Understanding', 'Semantic Segmentation', 'depth estimation', 'image segmentation', 'indoor scene', 'indoor scenes', 'scene understanding'},
    month = {dec},
    publisher = {TIB},
    title = {SUN RGB-D},
    url = {https://service.tib.eu/ldmservice/dataset/sun-rgb-d},
    year = {2024}
}