5 papers
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…
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…
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…
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…
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…