3 datasets found

Groups: Scene Understanding Organizations: No Organization Formats: JSON

Filter Results

  • InLoc

    Establishing both accurate and robust correspondences across images is an underpinning step to many computer vision algorithms.

  • NYUDv2

    The NYUDv2 dataset contains 1,449 labeled indoor-scene RGB images with both parsing annotations and Kinect depths.

  • 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...