用低秩适配动态建模，实现高效4D场景实时渲染。
Efficient 4D Gaussian Stream with Low Rank Adaptation
- 用3D高斯表示场景，低秩适配建模动态变化。
- 流式处理视频帧，带宽降低90%仍保持高质量渲染。
- 适合需要持续学习的长视频动态场景重建任务。
近期方法在生成长视频序列的新视角方面取得显著进展。本文提出一种高度可扩展的动态新视角合成方法，支持持续学习。我们采用3D高斯表示场景，并使用基于低秩适配的变形模型捕捉动态变化。方法通过分块连续重构动态内容，在保持与离线最先进方法相当的渲染质量的同时，将流式传输带宽降低了90%。
原文摘要 · Abstract (English)
Recent methods have made significant progress in synthesizing novel views with long video sequences. This paper proposes a highly scalable method for dynamic novel view synthesis with continual learning. We leverage the 3D Gaussians to represent the scene and a low-rank adaptation-based deformation model to capture the dynamic scene changes. Our method continuously reconstructs the dynamics with chunks of video frames, reduces the streaming bandwidth by $90\%$ while maintaining high rendering quality comparable to the off-line SOTA methods.
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。