用全局特征引导，让视频扩展更连贯自然。
GlobalPaint: Spatiotemporal Coherent Video Outpainting with Global Feature Guidance
- 分层处理：先扩关键帧，再插值中间帧，减少误差累积。
- 3D窗口注意力+全局特征引导，提升时空一致性。
- 适合需要高质量视频边界扩展的生成任务。
视频外扩通过合成原画面边界外的内容来扩展视频范围。与图像外扩相比，视频外扩不仅要求每帧空间上合理，还需保持长时间序列的运动连贯性，尤其在摄像机或物体运动时，新生成内容跨时间可见。我们提出GlobalPaint，一种基于扩散模型的时空一致视频外扩框架。方法采用分层流程：先外扩关键帧，再通过条件插值模型完成中间帧，降低顺序处理中的误差积累。模型层面，我们在预训练图像修复骨干网络基础上，引入（i）3D窗口注意力的增强时空模块，强化时空交互；（ii）全局特征引导机制，利用专用提取器将所有帧中观测区域的OpenCLIP特征提炼为紧凑全局标记。在基准数据集上的全面评估表明，该方法在重建质量与运动自然度上优于先前方法。演示页：https://yuemingpan.github.io/GlobalPaint/
原文摘要 · Abstract (English)
Video outpainting extends a video beyond its original boundaries by synthesizing missing border content. Compared with image outpainting, it requires not only per-frame spatial plausibility but also long-range temporal coherence, especially when outpainted content becomes visible across time under camera or object motion. We propose GlobalPaint, a diffusion-based framework for spatiotemporal coherent video outpainting. Our approach adopts a hierarchical pipeline that first outpaints key frames and then completes intermediate frames via an interpolation model conditioned on the completed boundaries, reducing error accumulation in sequential processing. At the model level, we augment a pretrained image inpainting backbone with (i) an Enhanced Spatial-Temporal module featuring 3D windowed attention for stronger spatiotemporal interaction, and (ii) global feature guidance that distills OpenCLIP features from observed regions across all frames into compact global tokens using a dedicated extractor. Comprehensive evaluations on benchmark datasets demonstrate improved reconstruction quality and more natural motion compared to prior methods. Our demo page is https://yuemingpan.github.io/GlobalPaint/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。