Preprint
Sep 2026
LEGAU: Learning Semantic Gaussian Priors for Scalable Category-level Pose Estimation
Category-level 6D pose estimation from a single RGB-D observation is inherently under-constrained, since partial visible geometry must be interpreted together with a canonical object structure before a stable pose can be determined. We present LEGAU, a unified framework that jointly predicts NOCS correspondence, object...
Hong-Li Xu, Zhao-Wei Lu, Jun-Wen Huang et al.
· 0 citations