Perspectively Equivariant Keypoint Learning for Omnidirectional Images
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Image Processing"
DOI: 10.1109/tip.2023.3270032
Abstract: Robust keypoint detection on omnidirectional images against large perspective variations, is a key problem in many computer vision tasks. In this paper, we propose a perspectively equivariant keypoint learning framework named OmniKL for addressing this… read more here.
Keywords: perspectively equivariant; equivariant keypoint; keypoint; omnidirectional images ... See more keywords