collaborators

5 papers

cs.CV2026

CANIS: Generation-Assisted 3D Canonicalization via an Image-Semantic Bridge

Kendong Liu, Yuxin Yao, Junhui Hou

Canonicalizing 3D object orientation is fundamental to 3D understanding and analysis. Existing approaches often rely on geometric cues, although 3D canonicalization ultimately requ…

cs.CV2026

G-Skin: Learning to Bind 3D Gaussians with Generative Visual Priors

Yuxin Yao, Kendong Liu, Shiqi Zhou +2

3D Gaussian Splatting has achieved remarkable success in photorealistic and efficient rendering, leading to a rapid increase in 3D assets represented by 3D Gaussian primitives. Dir…

cs.CV2026

GSwap: Realistic Head Swapping with Dynamic Neural Gaussian Field

Jingtao Zhou, Xuan Gao, Dongyu Liu +3

We present GSwap, a novel consistent and realistic video head-swapping system empowered by dynamic neural Gaussian portrait priors, which significantly advances the state of the ar…

cs.CV2025

SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration

Yuxin Yao, Bailin Deng, Junhui Hou +1

Existing optimization-based methods for non-rigid registration typically minimize an alignment error metric based on the point-to-point or point-to-plane distance between correspon…

cs.CV2025

RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videos

Yuxin Yao, Zhi Deng, Junhui Hou

This paper considers the problem of modeling articulated objects captured in 2D videos to enable novel view synthesis, while also being easily editable, drivable, and re-posable. T…