3 papers
cs.CV2026
CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representation
Jingyu Hu, Weilong Yan, Zhengzhe Liu +6
This paper presents a latent-space 3D shape editing framework built upon a coupled neural shape (CNS) representation and a neural feature volume optimization. This work extends CNS…
cs.CV2026
PEGAsus: 3D Personalization of Geometry and Appearance
Jingyu Hu, Bin Hu, Ka-Hei Hui +4
We present PEGAsus, a new framework capable of generating Personalized 3D shapes by learning shape concepts at both Geometry and Appearance levels. First, we formulate 3D shape per…
cs.CV2025
Not-So-Optimal Transport Flows for 3D Point Cloud Generation
Ka-Hei Hui, Chao Liu, Xiaohui Zeng +2
Learning generative models of 3D point clouds is one of the fundamental problems in 3D generative learning. One of the key properties of point clouds is their permutation invarianc…