用分层高斯压缩实现流畅动态3D虚拟人传输，画质更佳、效率更高。
HGC-Avatar: Hierarchical Gaussian Compression for Streamable Dynamic 3D Avatars
- 分结构与运动两层建模，支持逐层压缩与渐进解码
- 在低码率下仍保持面部细节，视觉质量显著优于已有方法
- 适合需要实时传输的虚拟人应用，如直播、元宇宙社交
近期3D高斯溅射（3DGS）技术实现了动态3D场景的快速、逼真渲染，在沉浸式通信中展现出巨大潜力。然而，现有基于通用3DGS表示的压缩方法缺乏对人类先验知识的利用，导致在数字人编码与传输中比特率效率和解码重建质量不佳，制约了其在流式3D虚拟人系统中的应用。本文提出HGC-Avatar，一种面向高效传输与高质量渲染的动态虚拟人分层高斯压缩框架。该方法将高斯表示解耦为结构层（通过基于StyleUNet的生成器将姿态映射为高斯点）与运动层（利用SMPL-X模型紧凑且语义化地表达时序姿态变化）。这种分层设计支持逐层压缩、渐进解码，并可从视频序列或文本等多样化输入中可控渲染。鉴于人脸真实感最为关键，我们在StyleUNet训练中引入面部注意力机制，在低码率约束下仍能保留身份与表情细节。实验表明，HGC-Avatar在保证快速3D虚拟人渲染的同时，在视觉质量和压缩效率上均显著优于现有方法。
原文摘要 · Abstract (English)
Recent advances in 3D Gaussian Splatting (3DGS) have enabled fast, photorealistic rendering of dynamic 3D scenes, showing strong potential in immersive communication. However, in digital human encoding and transmission, the compression methods based on general 3DGS representations are limited by the lack of human priors, resulting in suboptimal bitrate efficiency and reconstruction quality at the decoder side, which hinders their application in streamable 3D avatar systems. We propose HGC-Avatar, a novel Hierarchical Gaussian Compression framework designed for efficient transmission and high-quality rendering of dynamic avatars. Our method disentangles the Gaussian representation into a structural layer, which maps poses to Gaussians via a StyleUNet-based generator, and a motion layer, which leverages the SMPL-X model to represent temporal pose variations compactly and semantically. This hierarchical design supports layer-wise compression, progressive decoding, and controllable rendering from diverse pose inputs such as video sequences or text. Since people are most concerned with facial realism, we incorporate a facial attention mechanism during StyleUNet training to preserve identity and expression details under low-bitrate constraints. Experimental results demonstrate that HGC-Avatar provides a streamable solution for rapid 3D avatar rendering, while significantly outperforming prior methods in both visual quality and compression efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。