MINER: Multiscale Implicit Neural Representations

02/07/2022
by   Vishwanath Saragadam, et al.
5

We introduce a new neural signal representation designed for the efficient high-resolution representation of large-scale signals. The key innovation in our multiscale implicit neural representation (MINER) is an internal representation via a Laplacian pyramid, which provides a sparse multiscale representation of the signal that captures orthogonal parts of the signal across scales. We leverage the advantages of the Laplacian pyramid by representing small disjoint patches of the pyramid at each scale with a tiny MLP. This enables the capacity of the network to adaptively increase from coarse to fine scales, and only represent parts of the signal with strong signal energy. The parameters of each MLP are optimized from coarse-to-fine scale which results in faster approximations at coarser scales, thereby ultimately an extremely fast training process. We apply MINER to a range of large-scale signal representation tasks, including gigapixel images and very large point clouds, and demonstrate that it requires fewer than 25 parameters, 33 competing techniques such as ACORN to reach the same representation error.

READ FULL TEXT

page 2

page 5

page 6

page 7

page 9

page 10

page 11

page 12

research
10/06/2020

ASDN: A Deep Convolutional Network for Arbitrary Scale Image Super-Resolution

Deep convolutional neural networks have significantly improved the peak ...
research
05/06/2021

ACORN: Adaptive Coordinate Networks for Neural Scene Representation

Neural representations have emerged as a new paradigm for applications i...
research
03/27/2023

Regularize implicit neural representation by itself

This paper proposes a regularizer called Implicit Neural Representation ...
research
06/01/2022

Residual Multiplicative Filter Networks for Multiscale Reconstruction

Coordinate networks like Multiplicative Filter Networks (MFNs) and BACON...
research
12/09/2021

BACON: Band-limited Coordinate Networks for Multiscale Scene Representation

Coordinate-based networks have emerged as a powerful tool for 3D represe...
research
04/29/2021

Fast Multiscale Diffusion on Graphs

Diffusing a graph signal at multiple scales requires computing the actio...
research
04/22/2012

A Unified Multiscale Framework for Discrete Energy Minimization

Discrete energy minimization is a ubiquitous task in computer vision, ye...

Please sign up or login with your details

Forgot password? Click here to reset