FreqINR: Frequency Consistency for Implicit Neural Representation with Adaptive DCT Frequency Loss
This addresses blurring and artifacts in super-resolution for image processing applications, offering a lightweight solution with incremental improvements over existing methods.
The paper tackles frequency discrepancies causing artifacts in high-resolution images from Implicit Neural Representations by introducing FreqINR, which uses adaptive frequency loss and extended receptive fields to achieve state-of-the-art performance in arbitrary-scale super-resolution with improved computational efficiency.
Recent advancements in local Implicit Neural Representation (INR) demonstrate its exceptional capability in handling images at various resolutions. However, frequency discrepancies between high-resolution (HR) and ground-truth images, especially at larger scales, result in significant artifacts and blurring in HR images. This paper introduces Frequency Consistency for Implicit Neural Representation (FreqINR), an innovative Arbitrary-scale Super-resolution method aimed at enhancing detailed textures by ensuring spectral consistency throughout both training and inference. During training, we employ Adaptive Discrete Cosine Transform Frequency Loss (ADFL) to minimize the frequency gap between HR and ground-truth images, utilizing 2-Dimensional DCT bases and focusing dynamically on challenging frequencies. During inference, we extend the receptive field to preserve spectral coherence between low-resolution (LR) and ground-truth images, which is crucial for the model to generate high-frequency details from LR counterparts. Experimental results show that FreqINR, as a lightweight approach, achieves state-of-the-art performance compared to existing Arbitrary-scale Super-resolution methods and offers notable improvements in computational efficiency. The code for our method will be made publicly available.