3 papers
cs.CV2026
TriC-Motion: Tri-Domain Causal Modeling Grounded Text-to-Motion Generation
Yiyang Cao, Yunze Deng, Ziyu Lin +5
Text-to-motion generation, a rapidly evolving field in computer vision, aims to produce realistic and text-aligned motion sequences. Current methods primarily focus on spatial-temp…
cs.CV2026
GO-MLVTON: Garment Occlusion-Aware Multi-Layer Virtual Try-On with Diffusion Models
Yang Yu, Yunze Deng, Yige Zhang +8
Existing image-based virtual try-on (VTON) methods primarily focus on single-layer or multi-garment VTON, neglecting multi-layer VTON (ML-VTON), which involves dressing multiple la…
cs.CV2025
MolSight: Optical Chemical Structure Recognition with SMILES Pretraining, Multi-Granularity Learning and Reinforcement Learning
Wenrui Zhang, Xinggang Wang, Bin Feng +1
Optical Chemical Structure Recognition (OCSR) plays a pivotal role in modern chemical informatics, enabling the automated conversion of chemical structure images from scientific li…