English

TRIDENT: The Nonlinear Trilogy for Implicit Neural Representations

Computer Vision and Pattern Recognition 2023-11-27 v1 Image and Video Processing

Abstract

Implicit neural representations (INRs) have garnered significant interest recently for their ability to model complex, high-dimensional data without explicit parameterisation. In this work, we introduce TRIDENT, a novel function for implicit neural representations characterised by a trilogy of nonlinearities. Firstly, it is designed to represent high-order features through order compactness. Secondly, TRIDENT efficiently captures frequency information, a feature called frequency compactness. Thirdly, it has the capability to represent signals or images such that most of its energy is concentrated in a limited spatial region, denoting spatial compactness. We demonstrated through extensive experiments on various inverse problems that our proposed function outperforms existing implicit neural representation functions.

Keywords

Cite

@article{arxiv.2311.13610,
  title  = {TRIDENT: The Nonlinear Trilogy for Implicit Neural Representations},
  author = {Zhenda Shen and Yanqi Cheng and Raymond H. Chan and Pietro Liò and Carola-Bibiane Schönlieb and Angelica I Aviles-Rivero},
  journal= {arXiv preprint arXiv:2311.13610},
  year   = {2023}
}
R2 v1 2026-06-28T13:28:54.419Z