collaborators

5 papers

cs.CV2026

NECromancer: Breathing Life into Skeletons via BVH Animation

Mingxi Xu, Qi Wang, Zhengyu Wen +7

Motion tokenization is a key component of generalizable motion models, yet most existing approaches are restricted to species-specific skeletons, limiting their applicability acros…

cs.CV2026

DiMo: Discrete Diffusion Modeling for Motion Generation and Understanding

Ning Zhang, Zhengyu Li, Kwong Weng Loh +7

Prior masked modeling motion generation methods predominantly study text-to-motion. We present DiMo, a discrete diffusion-style framework, which extends masked modeling to bidirect…

cs.CV2025

SWiT-4D: Sliding-Window Transformer for Lossless and Parameter-Free Temporal 4D Generation

Kehong Gong, Zhengyu Wen, Mingxi Xu +9

Despite significant progress in 4D content generation, the conversion of monocular videos into high-quality animated 3D assets with explicit 4D meshes remains considerably challeng…

cs.CV2025

HF-VTON: High-Fidelity Virtual Try-On via Consistent Geometric and Semantic Alignment

Ming Meng, Qi Dong, Jiajie Li +5

Virtual try-on technology has become increasingly important in the fashion and retail industries, enabling the generation of high-fidelity garment images that adapt seamlessly to t…

math.NA2025

Convergence Guarantees for Gradient-Based Training of Neural PDE Solvers: From Linear to Nonlinear PDEs

Wei Zhao, Tao Luo

We present a unified convergence theory for gradient-based training of neural network methods for partial differential equations (PDEs), covering both physics-informed neural netwo…