CVSep 9, 2024

Lagrangian Hashing for Compressed Neural Field Representations

arXiv:2409.05334v14 citationsh-index: 45
Originality Incremental advance
AI Analysis

This addresses the storage and computational efficiency problem for neural field applications like 3D reconstruction, though it appears incremental.

The paper tackles the problem of creating compact neural field representations by combining Eulerian grid and point-based approaches, achieving comparable quality with more compact representations.

We present Lagrangian Hashing, a representation for neural fields combining the characteristics of fast training NeRF methods that rely on Eulerian grids (i.e.~InstantNGP), with those that employ points equipped with features as a way to represent information (e.g. 3D Gaussian Splatting or PointNeRF). We achieve this by incorporating a point-based representation into the high-resolution layers of the hierarchical hash tables of an InstantNGP representation. As our points are equipped with a field of influence, our representation can be interpreted as a mixture of Gaussians stored within the hash table. We propose a loss that encourages the movement of our Gaussians towards regions that require more representation budget to be sufficiently well represented. Our main finding is that our representation allows the reconstruction of signals using a more compact representation without compromising quality.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes