Follow-Your-Canvas:
Higher-Resolution Video Outpainting with Extensive Content Generation

Qihua Chen1,3* Yue Ma2* Hongfa Wang1,4* Junkun Yuan1*✝
Wenzhe Zhao1 Qi Tian1 Hongmei Wang1 Shaobo Min1 Qifeng Chen2 Wei Liu1✝
1Tencent, Hunyuan      2HKUST      3USTC      4Tsinghua University
Arxiv Preprint.
*Contribute Equally; ✝Corresponding Author
Paper Supplementary Code arXiv

Demo video

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 us to generate higher-resolution outpainting videos with rich content while keeping spatial and temporal consistency. Follow-Your-Canvas excels in large-scale video outpainting, e.g., from 512 X 512 to 1152 X 2048 (9 X ), while producing high-quality and aesthetically pleasing results. It achieves the best quantitative results across various resolution and scale setups.

Method Overview

model_overview

The training phase of Follow-Your-Canvas. An anchor window and a target window are randomly sampled, mimicking the “source video” and “region to perform outpaint” for inference respectively. The anchor window is injected into the model through a layout encoder, as well as a relative region embedding calculated by the positional relation between the anchor window and the target window, helping the model align the generated layout of the target window with the anchor window

BibTeX

 @article{qihuaFollowYourCanvas2024,
        title={Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation},
        author={Qihua Chen, Yue Ma, Hongfa Wang, Junkun Yuan, Wenzhe Zhao, Qi Tian, Hongmei Wang, Shaobo Min, Qifeng Chen, Wei Liu},
        journal={arXiv preprint arXiv:XXXX,XXX0},
        year={2024}
      }