Showing 2026Show all
3 papers · 1 filter
cs.CV2026
Instruction-Based Video Editing by Repurposing an Image Editing Model
Yunpeng Bai, Yossi Gandelsman, Michaël Gharbi +1
Instruction-based video editing is commonly built on video-pretrained generative backbones: a video diffusion transformer is adapted, at considerable cost, to condition on a source…
cs.CV2026
DuSPiT: Dual-Branch Sub-Patch Pixel Diffusion Transformer
Yunpeng Bai, Yossi Gandelsman, Michaël Gharbi
Diffusion Transformers achieve strong image generation performance, but most operate in compressed latent spaces. Pixel-space diffusion avoids this information loss, yet existing a…
cs.CV2026
PE-Field 4D: Video Generation Models as Canvas
Yunpeng Bai, Haoxiang Li, Qixing Huang
Diffusion Transformers have recently achieved strong performance in video generation, yet controlling scene geometry under viewpoint changes and camera motion remains challenging.…