Login / Signup

ICCL: Self-Supervised Intra- and Cross-Modal Contrastive Learning with 2D-3D Pairs for 3D Scene Understanding.

Kyota HigaMasahiro YamaguchiToshinori Hosoi
Published in: ICIP (2023)
Keyphrases
  • d scene
  • cross modal
  • learning process
  • visual recognition
  • learning algorithm
  • optical flow
  • single image
  • image processing
  • image data
  • depth map
  • perceptual information