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 is available at https://github.com/WindVChen/INR-Harmonization.

翻译：高分辨率图像和谐化在图像合成与编辑等实际应用中具有重要意义。然而，受限于高内存消耗，现有密集像素到像素和谐化方法主要聚焦于处理低分辨率图像。部分近期研究尝试结合颜色到颜色变换，但要么受限于特定分辨率，要么严重依赖手工设计的图像滤波器。本研究探索利用隐式神经表征，提出了一种基于隐式神经网络的图像和谐化方法——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高分辨率图像的密集像素到像素方法。受Retinex理论启发，我们将多层感知机解耦为两部分，分别捕获合成图像的内容与环境。同时设计了低分辨率图像先验网络以缓解边界不一致问题，并对训练与推理过程提出新方案。大量实验表明，本方法相比现有最优方法具有显著有效性。此外，我们还探索了该方法若干有趣且实用的应用场景。代码已开源至https://github.com/WindVChen/INR-Harmonization。