Enhancing Implicit Neural Representations via Symmetric Power Transformation
This work addresses a domain-specific problem for researchers and practitioners using INR in signal processing, offering an incremental improvement through a novel data transformation method.
The paper tackles the problem of enhancing Implicit Neural Representations (INR) by proposing a symmetric power transformation to improve their expressive ability, demonstrating reliable performance improvements in 1D audio, 2D image, and 3D video fitting tasks compared to other data transformations.
We propose symmetric power transformation to enhance the capacity of Implicit Neural Representation~(INR) from the perspective of data transformation. Unlike prior work utilizing random permutation or index rearrangement, our method features a reversible operation that does not require additional storage consumption. Specifically, we first investigate the characteristics of data that can benefit the training of INR, proposing the Range-Defined Symmetric Hypothesis, which posits that specific range and symmetry can improve the expressive ability of INR. Based on this hypothesis, we propose a nonlinear symmetric power transformation to achieve both range-defined and symmetric properties simultaneously. We use the power coefficient to redistribute data to approximate symmetry within the target range. To improve the robustness of the transformation, we further design deviation-aware calibration and adaptive soft boundary to address issues of extreme deviation boosting and continuity breaking. Extensive experiments are conducted to verify the performance of the proposed method, demonstrating that our transformation can reliably improve INR compared with other data transformations. We also conduct 1D audio, 2D image and 3D video fitting tasks to demonstrate the effectiveness and applicability of our method.