Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation
Qihua Chen, Yue Ma, Hongfa Wang, Junkun Yuan, Wenzhe Zhao, Qi Tian,, Hongmei Wang, Shaobo Min, Qifeng Chen, Wei Liu

TL;DR
This paper introduces Follow-Your-Canvas, a diffusion-based method for high-resolution video outpainting that overcomes GPU memory limitations and generates consistent, high-quality large-scale videos by dividing the task into spatial windows and maintaining source video relations.
Contribution
The method distributes outpainting across spatial windows and injects source video relations, enabling high-resolution, large-scale video outpainting without GPU memory constraints.
Findings
Achieves up to 9X resolution increase from 512x512 to 1152x2048.
Produces high-quality, spatially and temporally consistent videos.
Outperforms existing methods in quantitative metrics.
Abstract
This paper explores higher-resolution video outpainting with extensive content generation. We point out common issues faced by existing methods when attempting to largely outpaint videos: the generation of low-quality content and limitations imposed by GPU memory. To address these challenges, we propose a diffusion-based method called \textit{Follow-Your-Canvas}. It builds upon two core designs. First, instead of employing the common practice of "single-shot" outpainting, we distribute the task across spatial windows and seamlessly merge them. It allows us to outpaint videos of any size and resolution without being constrained by GPU memory. Second, the source video and its relative positional relation are injected into the generation process of each window. It makes the generated spatial layout within each window harmonize with the source video. Coupling with these two designs enables…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Advanced Image Processing Techniques · Video Analysis and Summarization
