Reproduce “CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression” 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
Yu-Ting Zhan, Cheng-Yuan Ho, Hebi Yang, Yi-Hsin Chen, Jui Chiu Chiang, Yu-Lun Liu, Wen-Hsiao Peng
CAT-3DGS compresses 3D Gaussian Splatting scenes into bitstreams while preserving view quality. It projects ScaffoldGS anchors onto multi-scale triplanes, then uses spatial and channel-wise autoregressive coding plus view-frequency-aware masking to represent redundancy. On Mip-NeRF 360 at the second-highest rate point, it reports 78× and 26× rate reductions versus 3DGS and ScaffoldGS, with PSNR 0.16 dB above ScaffoldGS; decoding takes longer than HAC.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.