SSR: A Generic Framework for Text-Aided Map Compression for Localization

2026-03-04

AI Summary

This work addresses the high storage and transmission costs of robotic maps in large-scale deployments by proposing an efficient compression framework that integrates lightweight textual descriptions with compact image feature vectors. Leveraging text as a losslessly compressible auxiliary modality, the method introduces an innovative Similarity Space Replication (SSR) technique that adaptively learns image embeddings retaining only information complementary to the text. This approach significantly enhances compression efficiency, achieving up to twice the compression ratio of existing baselines on benchmark datasets—including TokyoVal, Pittsburgh30k, Replica, and KITTI—while preserving high-accuracy localization performance.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Representation Learning for Vision
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Mapping is crucial in robotics for localization and downstream decision-making. As robots are deployed in ever-broader settings, the maps they rely on continue to increase in size. However, storing these maps indefinitely (cold storage), transferring them across networks, or sending localization queries to cloud-hosted maps imposes prohibitive memory and bandwidth costs. We propose a text-enhanced compression framework that reduces both memory and bandwidth footprints while retaining high-fidelity localization. The key idea is to treat text as an alternative modality: one that can be losslessly compressed with large language models. We propose leveraging lightweight text descriptions combined with very small image feature vectors, which capture "complementary information" as a compact representation for the mapping task. Building on this, our novel technique, Similarity Space Replication (SSR), learns an adaptive image embedding in one shot that captures only the information "complementary" to the text descriptions. We validate our compression framework on multiple downstream localization tasks, including Visual Place Recognition as well as object-centric Monte Carlo localization in both indoor and outdoor settings. SSR achieves 2 times better compression than competing baselines on state-of-the-art datasets, including TokyoVal, Pittsburgh30k, Replica, and KITTI.

Problem

• map compression
• localization
• memory cost
• bandwidth cost
• robotics

Innovation

• text-aided compression
• Similarity Space Replication
• complementary representation
• map compression
• localization