用少量摄像头实现动态场景高质量4D重建，适合真实环境应用。
MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion
- 通过融合多个单目摄像头的独立重建结果，实现时空一致的动态场景还原。
- 在PanopticStudio和Ego-Exo4D数据集上，新视角渲染质量优于已有方法。
- 仅需4个固定摄像头即可覆盖全场景，适用于野外复杂环境重建。
本文研究从稀疏视图视频中重建动态场景的问题。以往工作通常需要数百个校准摄像头组成的密集多视角采集系统（如Panoptic Studio），此类系统成本高昂，难以在真实环境中部署。相比之下，本工作旨在仅用少量稀疏视角摄像头（如4个等距向内安装的静态摄像头）实现完整场景覆盖下的动态人体行为重建，例如修车或跳舞。我们发现，现有密集多视角重建方法在稀疏视角设置下因视角重叠度低而表现不佳。为此，我们通过精细对齐各摄像头的独立单目重建结果，实现时间与视角一致的动态场景重建。在PanopticStudio和Ego-Exo4D上的大量实验表明，该方法在新视角渲染方面显著优于现有技术。代码、数据及处理脚本已开源：https://github.com/Z1hanW/MonoFusion。
原文摘要 · Abstract (English)
We address the problem of dynamic scene reconstruction from sparse-view videos. Prior work often requires dense multi-view captures with hundreds of calibrated cameras (e.g. Panoptic Studio). Such multi-view setups are prohibitively expensive to build and cannot capture diverse scenes in-the-wild. In contrast, we aim to reconstruct dynamic human behaviors, such as repairing a bike or dancing, from a small set of sparse-view cameras with complete scene coverage (e.g. four equidistant inward-facing static cameras). We find that dense multi-view reconstruction methods struggle to adapt to this sparse-view setup due to limited overlap between viewpoints. To address these limitations, we carefully align independent monocular reconstructions of each camera to produce time- and view-consistent dynamic scene reconstructions. Extensive experiments on PanopticStudio and Ego-Exo4D demonstrate that our method achieves higher quality reconstructions than prior art, particularly when rendering novel views. Code, data, and data-processing scripts are available on https://github.com/Z1hanW/MonoFusion.
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。