TT-NF: Tensor Train Neural Fields
METADATA ONLY
Loading...
Author / Producer
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.
Permanent link
Publication status
published
External links
Editor
Book title
Journal / series
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