Decomposition of Neural Discrete Representations for Large-Scale 3D Mapping
This work addresses storage efficiency in 3D neural mapping for robotics or AR/VR applications, presenting an incremental improvement over existing methods.
The paper tackles the challenge of storage-efficient large-scale 3D mapping by introducing DNMap, which uses a decomposition strategy to compress feature volumes while preserving mapping quality, achieving significant storage reduction without compromising accuracy.
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.