SACHA: Semantic-Aware Compression for 3D Gaussian Head Avatars
2026-08-24 • Multimedia
Multimedia
AI summaryⓘ
The authors developed SACHA, a way to make 3D animated head models that look good but use less space and data. They do this by focusing more on important parts of the face and using smart methods to reduce extra information during motions. This helps in making the models easier to send or store without losing much detail. Their tests show SACHA performs better than older methods in keeping image quality while saving space.
3D Gaussian head avatarssemantic-aware density controlappearance-motion decompositionnovel-view renderingcompressionrate-distortionGaussian primitivesdynamic avatar sequencesvisual saliency
Authors
Zihan Zhang, Shanzhi Yin, Xinju Wu, Bolin Chen, Ru-Ling Liao, Jie Chen, Shiqi Wang, Yan Ye
Abstract
Animatable 3D Gaussian head avatars offer high-fidelity and flexible facial rendering, but typically require substantial storage and transmission costs for numerous Gaussian primitives. Existing Gaussian head avatar methods overlook the visual saliency of different head semantic regions for more appropriate Gaussian primitive allocation, as well as the efficient compression of trained head avatar sequences. To tackle this obstacle, we propose SACHA, a dynamic head avatar compression framework that leverages both semantic-aware density control and appearance-motion decomposition to achieve compact representation and high-quality novel-view rendering of head avatar sequences. Specifically, the semantic-aware density control guides the adaptive allocation of Gaussian primitives across different head regions with region-adaptive densification and pruning. In addition, the appearance-motion decomposed compression further reduces the temporal redundancy of the avatar sequence by transmitting only head-prior parameters for avatar movements. Together, these designs enable a compact representation for efficient transmission of dynamic Gaussian head avatars while preserving visual fidelity. Experiments demonstrate that SACHA achieves a superior rate-distortion performance over existing Gaussian head avatar representation and compression methods while maintaining high-quality novel-view and novel-expression rendering.