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

翻译：隐式神经表示（INR）近年来在计算机视觉领域中崭露头角。已经证明它在对离散图像数据进行参数化的连续信号（例如来自神经元半径场（NeRF）的密集3D模型）方面是有效的。但是，在二维图像处理任务中，INR尚未得到充分的探索。考虑到INR的基本定义和结构，我们对其在低级别图像处理问题中（如图像恢复）的有效性很感兴趣。在这项工作中，我们重新审视INR，并调查其在低级别图像恢复任务中的应用，包括图像去噪，超分辨率，修复和去模糊。广泛的实验评估表明，INR在几个低级别视觉任务中具有卓越的性能，并且在资源有限的情况下胜过其同行超过2dB。代码和模型可在https://github.com/WenTXuL/LINR上获得。