I-INR: Iterative Implicit Neural Representations
This addresses a bottleneck in INR-based signal processing for computer vision applications, offering incremental improvements in reconstruction quality.
The paper tackled the problem of Implicit Neural Representations (INRs) being prone to regression to the mean, which limits detail capture and noise handling, by proposing Iterative Implicit Neural Representations (I-INRs) that enhance signal reconstruction through iterative refinement, achieving superior performance in tasks like image restoration and denoising.
Implicit Neural Representations (INRs) have revolutionized signal processing and computer vision by modeling signals as continuous, differentiable functions parameterized by neural networks. However, their inherent formulation as a regression problem makes them prone to regression to the mean, limiting their ability to capture fine details, retain high-frequency information, and handle noise effectively. To address these challenges, we propose Iterative Implicit Neural Representations (I-INRs) a novel plug-and-play framework that enhances signal reconstruction through an iterative refinement process. I-INRs effectively recover high-frequency details, improve robustness to noise, and achieve superior reconstruction quality. Our framework seamlessly integrates with existing INR architectures, delivering substantial performance gains across various tasks. Extensive experiments show that I-INRs outperform baseline methods, including WIRE, SIREN, and Gauss, in diverse computer vision applications such as image restoration, image denoising, and object occupancy prediction.