GauMVC：面向以人为中心的多视角视频压缩的生成式解耦高斯表示
GauMVC: Generative Decoupled Gaussian Representation for Human-centric Multi-view Video Compression
将多视角视频压缩转化为语义解耦的生成式建模：背景用 3DGS 单次建模，人体用 SMPL 驱动的个性化高斯化身，仅传输背景、关键视角和逐帧 SMPL 参数，为高保真多视角合成提供极低码率方案。
原文依据 The background is modeled once with 3D Gaussian Splatting, while the human is represented by a personalized Gaussian avatar
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论以人为中心的多视角视频具有清晰的语义结构：静态背景与动态人体运动。我们提出一种生成式压缩框架，显式解耦这些成分。背景用 3D 高斯泼溅单次建模，而人体由个性化高斯化身表示，该化身从仅传输一次的一组稀疏关键视角重建，并由来自蒙皮多人线性（SMPL）模型的紧凑逐帧姿态参数驱动。编码器仅发送三个元素：背景、关键视角和 SMPL 参数，从而以显著降低的码率实现高保真多视角合成。这将压缩从低层冗余去除转变为语义感知的生成式建模。在多个以人为中心的数据集上的实验表明，其率失真性能优越，尤其对于长时且密集采集的序列，并自然支持语义编辑。
英文原文摘要 967 字符
Human-centric multi-view video has a clear semantic structure: a static background and dynamic human motion. We propose a generative compression framework that explicitly decouples these components. The background is modeled once with 3D Gaussian Splatting, while the human is represented by a personalized Gaussian avatar reconstructed from a sparse set of key views that are transmitted only once and driven by compact per-frame pose parameters from the Skinned Multi-Person Linear (SMPL) model. The encoder sends only three elements: the background, the key views, and the SMPL parameters, enabling high-fidelity multi-viewpoint synthesis at dramatically reduced bitrates. This shifts compression from low-level redundancy removal to semantics-aware generative modeling. Experiments across multiple human-centric datasets demonstrate superior rate-distortion performance, particularly for long and densely captured sequences, and naturally enable semantic editing.