Showing cs.CVShow all
3 papers · 1 filter
cs.CV2025
Lagrangian Motion Fields for Long-term Motion Generation
Yifei Yang, Zikai Huang, Chenshu Xu +1
Long-term motion generation is a challenging task that requires producing coherent and realistic sequences over extended durations. Current methods primarily rely on framewise moti…
cs.CV2025
Stable Score Distillation
Haiming Zhu, Yangyang Xu, Chenshu Xu +5
Text-guided image and 3D editing have advanced with diffusion-based models, yet methods like Delta Denoising Score often struggle with stability, spatial control, and editing stren…
cs.CV2024
Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation
Haofeng Liu, Chenshu Xu, Yifei Yang +2
Point-based interactive editing serves as an essential tool to complement the controllability of existing generative models. A concurrent work, DragDiffusion, updates the diffusion…