Reproduce “Codec-Compatible Learned Compression for 3D Gaussian Splatting” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Feiyang Yu, Qi Yang, Wenjie Huang, Yunfeng Guan, Yiling Xu, Zhu Li
CCT-GS compresses 3D Gaussian Splatting scenes for rendering from new viewpoints by targeting directional color values called non-DC spherical-harmonic coefficients (SH-AC). A shared learned transform reduces these 45-channel maps to 15 channels for HEVC, while scene-specific adaptation helps reconstruct details. On MPEG GSC Forward-facing 1F, it achieves an average BD-rate of −51.30% versus GSCodec Studio, not for every scene or quality point.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.