Decomposition of Neural Discrete Representations for Large-Scale 3D Mapping

TL;DR

DNMap introduces a decomposition-based discrete representation for large-scale 3D neural mapping, significantly reducing storage while maintaining high mapping quality through shared component vectors and low-resolution continuous embeddings.

Contribution

It proposes a novel decomposition strategy for discrete embeddings in 3D mapping, enabling efficient storage and improved scalability over existing methods.

Findings

Achieves efficient large-scale 3D mapping with reduced storage.

Successfully approximates signed distance functions.

Maintains high mapping quality with compressed feature volume.

Abstract

Learning efficient representations of local features is a key challenge in feature volume-based 3D neural mapping, especially in large-scale environments. In this paper, we introduce Decomposition-based Neural Mapping (DNMap), a storage-efficient large-scale 3D mapping method that employs a discrete representation based on a decomposition strategy. This decomposition strategy aims to efficiently capture repetitive and representative patterns of shapes by decomposing each discrete embedding into component vectors that are shared across the embedding space. Our DNMap optimizes a set of component vectors, rather than entire discrete embeddings, and learns composition rather than indexing the discrete embeddings. Furthermore, to complement the mapping quality, we additionally learn low-resolution continuous embeddings that require tiny storage space. By combining these representations with a shallow neural network and an efficient octree-based feature volume, our DNMap successfully approximates signed distance functions and compresses the feature volume while preserving mapping quality. Our source code is available at https://github.com/minseong-p/dnmap.