发表机构
University of Bristol; National Chung Cheng University; National Yang Ming Chiao Tung University（布里斯托大学; 国立中正大学; 国立阳明交通大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对动态3DGS压缩难题，提出SAGA编解码器，利用分层稀疏4D锚点和INR解码器实现紧凑参数共享，并引入固定大小内存槽建模长程依赖，在Neu3D和MPEG MIV上分别实现80.39%和83.94%的BD-rate降低。
AI 中文摘要
沉浸式视频通信需要逼真、渲染高效且紧凑的动态场景表示。3D高斯泼溅（3DGS）提供了一种有前景的表示方法，但动态3DGS由于密集基元和时空冗余而难以压缩。基于锚点的公式通过稀疏支架共享基元间的几何和外观，提高了紧凑性。然而，现有设计通常依赖于变形单个规范支架，并孤立地调节每个基元与其关联锚点，限制了其处理非局部动态和遮挡消除的能力，同时未充分利用锚点间相关性，尤其是在运动或纹理密集区域。为解决这些限制，我们提出了SAGA，一种基于稀疏锚点辅助高斯泼溅表示构建的体积视频编解码器。SAGA使用分层组织的稀疏4D锚点表示动态3D场景，其中基于坐标的INR解码器从锚点间插值生成精细锚点和高斯基元，实现了跨时空结构的紧凑参数共享。对于非结构化锚点间的长程依赖，我们进一步引入了具有正交性更新信息的固定大小内存槽，以实现准确的熵上下文建模。实验表明，与GIFStream相比，SAGA在Neu3D和MPEG MIV上分别实现了PSNR BD-rate降低80.39%和83.94%，展现了强大的率失真性能。
英文摘要
Immersive video communication requires photorealistic, render-efficient, and compact dynamic scene representations. 3D Gaussian Splatting (3DGS) offers a promising representation, but dynamic 3DGS remains difficult to compress due to dense primitives and spatiotemporal redundancy. Anchor-based formulations improve compactness with sparse scaffolds that share geometry and appearance across primitives. However, existing designs often rely on deforming a single canonical scaffold and condition each primitive on its associated anchor in isolation, limiting their ability to handle non-local dynamics and disocclusion while under-exploiting inter-anchor correlations, particularly in motion- or texture-dense regions. To address these limitations, we propose SAGA, a volumetric video codec built upon Sparse Anchor-assisted GAussian splatting representations. SAGA represents dynamic 3D scenes using hierarchically organized sparse 4D anchors, where coordinate-based INR decoders generate fine anchors and Gaussian primitives from inter-anchor interpolations, enabling compact parameter sharing across spatiotemporal structures. For long-range dependencies among unstructured anchors, we further introduce fixed-size memory slots with orthogonality-informed updates for accurate entropy-context modeling. Experiments show that SAGA achieves strong rate-distortion performance against GIFStream, with PSNR BD-rate reductions of 80.39% and 83.94% on Neu3D and MPEG MIV, respectively.
