High-resolution (HR) image harmonization is of great significance in real-world applications such as image synthesis and image editing. However, due to the high memory costs, existing dense pixel-to-pixel harmonization methods are mainly focusing on processing low-resolution (LR) images. Some recent works resort to combining with color-to-color transformations but are either limited to certain resolutions or heavily depend on hand-crafted image filters. In this work, we explore leveraging the implicit neural representation (INR) and propose a novel image Harmonization method based on Implicit neural Networks (HINet), which to the best of our knowledge, is the first dense pixel-to-pixel method applicable to HR images without any hand-crafted filter design. Inspired by the Retinex theory, we decouple the MLPs into two parts to respectively capture the content and environment of composite images. A Low-Resolution Image Prior (LRIP) network is designed to alleviate the Boundary Inconsistency problem, and we also propose new designs for the training and inference process. Extensive experiments have demonstrated the effectiveness of our method compared with state-of-the-art methods. Furthermore, some interesting and practical applications of the proposed method are explored. Our code will be available at https://github.com/WindVChen/INR-Harmonization.

翻译：高分辨率（HR）图像和谐化在图像合成和图像编辑等实际应用中具有重要意义。然而，由于高内存成本，现有的密集像素到像素和谐化方法主要专注于处理低分辨率（LR）图像。近期一些工作尝试与颜色到颜色变换相结合，但要么局限于特定分辨率，要么严重依赖手工设计的图像滤波器。本文探索利用隐式神经表示（INR），提出一种基于隐式神经网络的新型图像和谐化方法HINet，据我们所知，这是首个无需任何手工滤波器设计即可适用于HR图像的密集像素到像素方法。受Retinex理论启发，我们将多层感知机（MLPs）解耦为两部分，分别捕获合成图像的内容和环境。设计低分辨率图像先验（LRIP）网络以缓解边界不一致问题，并提出新的训练与推理流程设计。大量实验证明了我们的方法相较于现有最优方法的有效性。此外，本文还探索了该方法的一些有趣且实用的应用。我们的代码将在https://github.com/WindVChen/INR-Harmonization 公开。