Data-Driven Variable-Length Compression of 3D Representations
Lists
Only you see this
Abstract
Compressing 3D shapes is important for the efficiency of many applications, yet existing methods either cannot leverage dataset-level statistics or use a fixed compression ratio for all shapes. We propose a learned variable-length compression method that exploits structure across a training dataset while adapting compressed representation size to individual shape complexity using only fast feed-forward inference. Our method operates on general latent representations and improves rate-distortion for both meshes and signed distance fields. Code is available at https://github.com/voilalab/varlen-3D.
BibTeX
@misc{lin2026data,
author = {Yvette Y. Lin and Sai Karthikey Pentapati and Sarvesh Sundaram and Guandao Yang and Sara Fridovich-Keil},
title = {{Data-Driven Variable-Length Compression of 3D Representations}},
year = {2026},
eprint = {2611.21802},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.21802},
}Loading related content...