ClipGStream：面向任意长度与任意运动多视角动态场景重建的片段流高斯泼溅
ClipGStream: Clip-Stream Gaussian Splatting for Any Length and Any Motion Multi-View Dynamic Scene Reconstruction
把动态高斯泼溅的优化粒度从帧级提升到片段级，用片段独立的时空场加残差锚框补偿建模局部运动，并通过跨片段继承锚框与解码器保持长序列一致性——这套「Clip-Stream」思路可直接迁移到长视频新视角合成与流式动态重建，兼顾显存与闪烁抑制。
原文依据 performs stream optimization at the clip level rather than the frame level
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论动态三维场景重建对 VR、MR、XR 等沉浸式媒体至关重要，但对于存在大规模运动的长多视角序列仍然极具挑战。现有的动态高斯方法要么是帧流式，具备可扩展性但时序稳定性差；要么是基于片段，能获得局部一致性，却以高显存开销和有限的序列长度为代价。我们提出 ClipGStream，一种在片段层级而非帧层级进行流式优化的混合重建框架。序列被划分为若干短片段，其中动态运动通过片段独立的时空场与残差锚框补偿来建模，从而高效捕捉局部变化；同时，跨片段继承的锚框与解码器维持片段之间的结构一致性。这种片段流设计使得长动态视频能够以高时序连贯性和更低的显存开销实现可扩展、无闪烁的重建。大量实验表明，ClipGStream 达到了最优的重建质量与效率。
英文原文摘要 1066 字符
Dynamic 3D scene reconstruction is essential for immersive media such as VR, MR, and XR, yet remains challenging for long multi-view sequences with large-scale motion. Existing dynamic Gaussian approaches are either Frame-Stream, offering scalability but poor temporal stability, or Clip, achieving local consistency at the cost of high memory and limited sequence length. We propose ClipGStream, a hybrid reconstruction framework that performs stream optimization at the clip level rather than the frame level. The sequence is divided into short clips, where dynamic motion is modeled using clip-independent spatio-temporal fields and residual anchor compensation to capture local variations efficiently, while inter-clip inherited anchors and decoders maintain structural consistency across clips. This Clip-Stream design enables scalable, flicker-free reconstruction of long dynamic videos with high temporal coherence and reduced memory overhead. Extensive experiments demonstrate that ClipGStream achieves state-of-the-art reconstruction quality and efficiency.