Jump to Content

Deep Implicit Volume Compression

Danhang "Danny" Tang
Phil Chou
Christian Haene
Mingsong Dou
Jonathan Taylor
Yinda Zhang
Shahram Izadi
Sofien Bouaziz
Cem Keskin
CVPR (2020)
Google Scholar

Abstract

We describe a novel approach for compressing truncated signed distance fields (TSDF) stored in voxel grids and their corresponding textures. To compress the TSDF our method relies on a block-based neural architecture trained end-to-end achieving state-of-the-art compression rates. To prevent topological errors we losslessly compress the signs of the TSDF which also as a side effect bounds the maximum reconstruction error by the voxel size. To compress the affiliated texture we designed a fast block-base charting and Morton packing technique generating a coherent image that can be efficiently compressed using existing image-based compression algorithms. We demonstrate the performance of our algorithms on a large set of 4D performance sequences captured using multi-camera RGBD setups.