• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Optimize Vision Transformer Architecture via Efficient Attention Modules: A Study on the Monocular Depth Estimation Task.

Claudio SchiavellaLorenzo CirilloLorenzo PapaPaolo RussoIrene Amerini
Published in: ICIAP Workshops (1) (2023)
Keyphrases
  • real time
  • depth estimation
  • monocular images
  • depth map
  • computer vision
  • three dimensional
  • high quality
  • vision system
  • pose estimation
  • binocular stereo