TRIDENT: The Nonlinear Trilogy for Implicit Neural Representations
This work addresses the need for more effective implicit neural representations in machine learning, though it appears incremental as it builds on existing INR methods.
The authors tackled the problem of modeling complex data with implicit neural representations by introducing TRIDENT, a novel function with three nonlinearity properties, and demonstrated it outperforms existing INR functions on various inverse problems.
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.