An Eigenshapes Approach to Compressed Signed Distance Fields and Their Utility in Robot Mapping

TL;DR

This paper introduces a novel eigenshapes approach for high-ratio compression of 3D signed distance fields, demonstrating improved robot mapping and ego-motion estimation performance through various compression techniques.

Contribution

It presents a new eigenshapes-based compression method for signed distance fields, combining PCA and auto-encoder architectures, with application-specific evaluation in robotic mapping tasks.

Findings

Compressed maps retain essential features for ego-motion estimation.

Lossy compression can outperform uncompressed maps in challenging scenarios.

Different compression methods impact reconstruction fidelity and task performance.

Abstract

In order to deal with the scaling problem of volumetric map representations we propose spatially local methods for high-ratio compression of 3D maps, represented as truncated signed distance fields. We show that these compressed maps can be used as meaningful descriptors for selective decompression in scenarios relevant to robotic applications. As compression methods, we compare using PCA-derived low-dimensional bases to non-linear auto-encoder networks and novel mixed architectures that combine both. Selecting two application-oriented performance metrics, we evaluate the impact of different compression rates on reconstruction fidelity as well as to the task of map-aided ego-motion estimation. It is demonstrated that lossily compressed distance fields used as cost functions for ego-motion estimation, can outperform their uncompressed counterparts in challenging scenarios from standard RGB-D data-sets.