TT-NF: Tensor Train Neural Fields

09/30/2022
by   Anton Obukhov, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/07/2021

Spectral Tensor Train Parameterization of Deep Learning Layers

We study low-rank parameterizations of weight matrices with embedded spe...
research
06/02/2022

Dynamic MRI using Learned Transform-based Deep Tensor Low-Rank Network (DTLR-Net)

While low-rank matrix prior has been exploited in dynamic MR image recon...
research
12/03/2018

Tensor N-tubal rank and its convex relaxation for low-rank tensor recovery

As low-rank modeling has achieved great success in tensor recovery, many...
research
03/01/2023

Transformed Low-Rank Parameterization Can Help Robust Generalization for Tensor Neural Networks

Achieving efficient and robust multi-channel data learning is a challeng...
research
03/17/2022

TensoRF: Tensorial Radiance Fields

We present TensoRF, a novel approach to model and reconstruct radiance f...
research
08/14/2018

A Comprehensive Survey for Low Rank Regularization

Low rank regularization, in essence, involves introducing a low rank or ...
research
03/27/2021

Tensor Networks for Multi-Modal Non-Euclidean Data

Modern data sources are typically of large scale and multi-modal natures...

Please sign up or login with your details

Forgot password? Click here to reset