Revisiting Implicit Neural Representations in Low-Level Vision

04/20/2023

∙

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

READ FULL TEXT

Revisiting Implicit Neural Representations in Low-Level Vision

Rethinking Implicit Neural Representations for Vision Learners

Learning Dual Convolutional Neural Networks for Low-Level Vision

Procedural Kernel Networks

Tiny and Efficient Model for the Edge Detection Generalization

Lightweight Modules for Efficient Deep Learning based Image Restoration

Signal Processing for Implicit Neural Representations

On Considering Uncertainty and Alternatives in Low-Level Vision

Revisiting Implicit Neural Representations in Low-Level Vision

Related Research

Rethinking Implicit Neural Representations for Vision Learners

Learning Dual Convolutional Neural Networks for Low-Level Vision

Procedural Kernel Networks

Tiny and Efficient Model for the Edge Detection Generalization

Lightweight Modules for Efficient Deep Learning based Image Restoration

Signal Processing for Implicit Neural Representations

On Considering Uncertainty and Alternatives in Low-Level Vision