发表机构
Wangxuan Institute of Computer Technology, Peking University; VGI Labs Co., Ltd.; University of California, Merced（北京大学王选计算机研究所; VGI实验室有限公司; 加州大学默塞德分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
DynStream提出一种从长无位姿视频流在线重建动态4D场景的框架，通过局部窗口重建与跨窗口融合实现无需优化的高保真渲染，在室内外场景中达到最先进性能。
AI 中文摘要
从长视频流中在线重建动态4D场景需要同时具备连续处理和照片级真实感渲染能力，现有方法难以同时满足这两点。现有的前馈式高斯方法仅限于离线处理，而在线点云方法则难以维持稠密几何和高保真渲染。我们提出DynStream，一个用于从长无位姿视频进行流式4D高斯重建的框架。给定连续视频流，DynStream在局部时间窗口内重建场景，并逐步将这些局部重建对齐和融合为全局一致的场景，从而实现无需逐场景优化的在线4D重建。通过联合强制执行跨窗口几何一致性并建模时变场景内容，DynStream支持在扩展视频流上进行高效重建和照片级真实感渲染。实验表明，DynStream能够从长视频流实现高保真在线动态重建与渲染，在多种动态室内和室外场景中达到最先进性能。
英文摘要
Online reconstruction of dynamic 4D scenes from long, unposed streaming videos requires both continuous processing and photorealistic rendering, which existing methods struggle to achieve simultaneously. Existing feed-forward Gaussian methods are restricted to offline processing, whereas online point-cloud approaches struggle to maintain dense geometry and high-fidelity rendering. We present DynStream, a framework for streaming 4D Gaussian reconstruction from long, unposed videos. Given a continuous video stream, DynStream reconstructs the scene within local temporal windows and incrementally aligns and fuses these local reconstructions into a globally consistent scene, enabling online 4D reconstruction without per-scene optimization. By jointly enforcing cross-window geometric consistency and modeling time-varying scene content, DynStream supports efficient reconstruction and photorealistic rendering over extended video streams. Experiments demonstrate that DynStream enables high-fidelity online dynamic reconstruction and rendering from long video streams, achieving state-of-the-art performance across diverse dynamic indoor and outdoor scenes.
