collaborators

7 papers

cs.CV2026

SkelMo: Universal Skeletal Motion Generation for 3D Rigged Shapes

Ye Tao, Yuxin Yao, Kendong Liu +2

Motion generation for rigged shapes is vital for scalable 4D asset production. However, template-based methods are limited by specific topologies and fail to generalize across dive…

cs.CV2026

From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data

Yuming Zhao, Junhui Hou, Qijian Zhang +2

Geometric analysis fundamentally distinguishes between \textit{extrinsic} and \textit{intrinsic} perspectives. The dominant paradigm in current 3D representation learning relies on…

cs.CV2026

Joint Geometry-Appearance Human Reconstruction in a Unified Latent Space via Bridge Diffusion

Yingzhi Tang, Qijian Zhang, Junhui Hou

Achieving consistent and high-fidelity geometry and appearance reconstruction of 3D digital humans from a single RGB image is inherently a challenging task. Existing studies typica…

cs.CV2025

HuGDiffusion: Generalizable Single-Image Human Rendering via 3D Gaussian Diffusion

Yingzhi Tang, Qijian Zhang, Junhui Hou

We present HuGDiffusion, a generalizable 3D Gaussian splatting (3DGS) learning pipeline to achieve novel view synthesis (NVS) of human characters from single-view input images. Exi…

cs.CV2025

Voronoi-Assisted Diffusion for Computing Unsigned Distance Fields from Unoriented Points

Jiayi Kong, Chen Zong, Junkai Deng +6

Unsigned Distance Fields (UDFs) provide a flexible representation for 3D shapes with arbitrary topology, including open and closed surfaces, orientable and non-orientable geometrie…

cs.CV2025

A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functions

Jiangbei Hu, Yanggeng Li, Fei Hou +5

Unsigned distance fields (UDFs) provide a versatile framework for representing a diverse array of 3D shapes, encompassing both watertight and non-watertight geometries. Traditional…