TT-NF: Tensor Train Neural Fields


METADATA ONLY
Loading...

Date

2024-09

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Learning neural fields has been an active topic in deep learning research, focusing, among other issues, on finding more compact and easy-to-fit representations. In this paper, we introduce a novel low-rank representation termed Tensor Train Neural Fields (TT-NF) for learning neural fields on dense regular grids and efficient methods for sampling from them. Our representation is a TT parameterization of the neural field, trained with backpropagation to minimize a non-convex objective. We analyze the effect of low-rank compression on the downstream task quality metrics in two settings. First, we demonstrate the efficiency of our method in a sandbox task of tensor denoising, which admits comparison with SVD-based schemes designed to minimize reconstruction error. Furthermore, we apply the proposed approach to Neural Radiance Fields, where the low-rank structure of the field corresponding to the best quality can be discovered only through learning.

Publication status

published

Editor

Book title

Volume

18 (6)

Pages / Article No.

1024 - 1035

Publisher

IEEE

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Deep learning; neural fields; radiance fields; sampling; tensor decompositions; tensor train; voxels

Organisational unit

Notes

Funding

Related publications and datasets