CCT-GS learns a codec-friendly transform for spherical-harmonic coefficient maps

arXivarXivPapers

CCT-GS learns a codec-friendly transform for spherical-harmonic coefficient maps
arXiv / Feiyang Yu, Qi Yang and colleagues

Feiyang Yu, Qi Yang, Wenjie Huang, Yunfeng Guan, Yiling Xu and Zhu Li present CCT-GS, a codec-compatible learned transform for video-based 3D Gaussian Splatting compression, accepted at VCIP 2026. High-dimensional non-DC spherical harmonic maps account for a dominant portion of the bitstream but have statistics unlike natural images; CCT-GS first learns a generalized transform that converts those maps into compact, codec-friendly bottlenecks, then uses LoRA-based scene adaptation to recover scene-specific appearance with lightweight side information.

On MPEG GSC sequences, CCT-GS consistently outperforms representative video-based baselines, with an average BD-rate reduction of 51.30% over the video-based anchor.