Research map / Video / Video generation
ZeroPatcher: Training-free Sampler for Video Inpainting and Editing
Shaoshu Yang, Yingya Zhang, Ran He
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes ZeroPatcher, a training-free sampler that adapts pretrained text-to-video generation models for video inpainting and editing.
Problem
Video inpainting and editing require substantial compute and large datasets to train models; the paper asks whether priors from large pretrained video foundation models can handle these tasks without training.
Approach
Leverages the prior knowledge of large-scale text-to-video foundation models through a training-free sampling procedure to perform video inpainting and editing, rather than training task-specific models.
Closest papers by meaning
- Keyframe-Guided Creative Video Inpainting (CVPR 2025 · similarity 0.88)
- AVID: Any-Length Video Inpainting with Diffusion Model (CVPR 2024 · similarity 0.88)
- Elevating Flow-Guided Video Inpainting with Reference Generation (AAAI 2025 · similarity 0.87)
- MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers (CVPR 2024 · similarity 0.87)
- Video Diffusion Models Are Strong Video Inpainter (AAAI 2025 · similarity 0.87)
- FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
