Instant Gaussian Stream：基于高斯泼溅的快速可泛化动态场景重建流式方法
Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting
AI总结：
针对现有动态场景重建流式方法单帧重建慢、误差累积的问题，提出基于高斯泼溅的IGS框架，结合锚点驱动高斯运动网络与关键帧引导策略，实现快速可泛化的流式重建并提升合成质量。
摘要：
以流式方式构建自由视点视频相比离线训练方法具备响应迅速的优势，可极大提升用户体验。但当前流式方法面临单帧重建时间长（10秒以上）和误差累积的挑战，限制了其更广泛的应用。本文提出Instant Gaussian Stream（IGS，即时高斯流）——一种快速且可泛化的流式框架，以解决上述问题。首先，我们提出一种通用的Anchor-driven Gaussian Motion Network（锚点驱动高斯运动网络），将多视角2D运动特征投影到3D空间，通过锚点驱动所有高斯的运动。该通用网络仅需单次推理的时间，即可生成每个目标帧的高斯运动。其次，我们提出Key-frame-guided Streaming Strategy（关键帧引导流式策略），对每个关键帧进行优化，在缓解误差累积的同时实现时间维度复杂场景的精准重建。我们开展了广泛的域内和跨域评估，结果表明，该方法可实现平均单帧重建时间2秒以上的流式处理，同时提升视角合成质量。
英文摘要：
Building Free-Viewpoint Videos in a streaming manner offers the advantage of rapid responsiveness compared to offline training methods, greatly enhancing user experience. However, current streaming approaches face challenges of high per-frame reconstruction time (10s+) and error accumulation, limiting their broader application. In this paper, we propose Instant Gaussian Stream (IGS), a fast and generalizable streaming framework, to address these issues. First, we introduce a generalized Anchor-driven Gaussian Motion Network, which projects multi-view 2D motion features into 3D space, using anchor points to drive the motion of all Gaussians. This generalized Network generates the motion of Gaussians for each target frame in the time required for a single inference. Second, we propose a Key-frame-guided Streaming Strategy that refines each key frame, enabling accurate reconstruction of temporally complex scenes while mitigating error accumulation. We conducted extensive in-domain and cross-domain evaluations, demonstrating that our approach can achieve streaming with a average per-frame reconstruction time of 2s+, alongside a enhancement in view synthesis quality.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
