2 papers
cs.CV2026
SEDiT: Mask-Free Video Subtitle Erasure via One-step Diffusion Transformer
Zheng Hui, Yunlong Bai
Recent breakthroughs in video diffusion models have significantly accelerated the development of video editing techniques. However, existing methods often rely on inpainting video…
cs.CV2025
EraserDiT: Fast Video Inpainting with Diffusion Transformer Model
Jie Liu, Zheng Hui
Video object removal and inpainting are critical tasks in the fields of computer vision and multimedia processing, aimed at restoring missing or corrupted regions in video sequence…