Score: 1

Good Noise Makes Good Edits: A Training-Free Diffusion-Based Video Editing with Image and Text Prompts

Published: June 14, 2025 | arXiv ID: 2506.12520v1

By: Saemee Choi , Sohyun Jeong , Jaegul Choo and more

Potential Business Impact:

Changes videos using pictures and words.

Business Areas:
Video Editing Content and Publishing, Media and Entertainment, Video

We propose ImEdit, the first zero-shot, training-free video editing method conditioned on both images and text. The proposed method introduces $\rho$-start sampling and dilated dual masking to construct well-structured noise maps for coherent and accurate edits. We further present zero image guidance, a controllable negative prompt strategy, for visual fidelity. Both quantitative and qualitative evaluations show that our method outperforms state-of-the-art methods across all metrics.

Country of Origin
🇰🇷 Korea, Republic of

Page Count
22 pages

Category
Computer Science:
CV and Pattern Recognition