Revisiting Implicit Neural Representations in Low-Level Vision
This work addresses image restoration challenges for computer vision practitioners, but it is incremental as it extends an existing method to new tasks.
The paper tackles the under-exploration of Implicit Neural Representations (INR) in 2D low-level vision tasks, showing that applying INR to image restoration problems like denoising and super-resolution achieves superior performance, outperforming counterparts by over 2dB in some cases.
Implicit Neural Representation (INR) has been emerging in computer vision in recent years. It has been shown to be effective in parameterising continuous signals such as dense 3D models from discrete image data, e.g. the neural radius field (NeRF). However, INR is under-explored in 2D image processing tasks. Considering the basic definition and the structure of INR, we are interested in its effectiveness in low-level vision problems such as image restoration. In this work, we revisit INR and investigate its application in low-level image restoration tasks including image denoising, super-resolution, inpainting, and deblurring. Extensive experimental evaluations suggest the superior performance of INR in several low-level vision tasks with limited resources, outperforming its counterparts by over 2dB. Code and models are available at https://github.com/WenTXuL/LINR