0

Grids Often Outperform Implicit Neural Representations

Research investigates the performance of Implicit Neural Representations (INRs) and grid representations across various tasks, revealing that grids often outperform INRs except for signals with lower-dimensional structure.

Year
2025
Venue
arXiv 2025
Authors
2
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2506.11139ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Implicit Neural Representations (INRs) have recently shown impressive results, but their fundamental capacity, implicit biases, and scaling behavior remain poorly understood. We investigate the performance of diverse INRs across a suite of 2D and 3D real and synthetic signals with varying effective bandwidth, as well as both overfitting and generalization tasks including tomography, super-resolution, and denoising. By stratifying performance according to model size as well as signal type and bandwidth, our results shed light on how different INR and grid representations allocate their capacity. We find that, for most tasks and signals, a simple regularized grid with interpolation trains faster and to higher quality than any INR with the same number of parameters. We also find limited settings where INRs outperform grids -- namely fitting signals with underlying lower-dimensional structure such as shape contours -- to guide future use of INRs towards the most advantageous applications. Code and synthetic signals used in our analysis are available at https://github.com/voilalab/INR-benchmark.

Authors

2