Photorealistic color retouching plays a vital role in visual content creation, yet manual retouching remains inaccessible to non-experts due to its reliance on specialized expertise. Reference-based methods offer a promising alternative by transferring the preset color of a reference image to a source image. However, these approaches often operate as novice learners, performing global color mappings derived from pixel-level statistics, without a true understanding of semantic context or human aesthetics. To address this issue, we propose SemiNFT, a Diffusion Transformer (DiT)-based retouching framework that mirrors the trajectory of human artistic training: beginning with rigid imitation and evolving into intuitive creation. Specifically, SemiNFT is first taught with paired triplets to acquire basic structural preservation and color mapping skills, and then advanced to reinforcement learning (RL) on unpaired data to cultivate nuanced aesthetic perception. Crucially, during the RL stage, to prevent catastrophic forgetting of old skills, we design a hybrid online-offline reward mechanism that anchors aesthetic exploration with structural review. % experiments Extensive experiments show that SemiNFT not only outperforms state-of-the-art methods on standard preset transfer benchmarks but also demonstrates remarkable intelligence in zero-shot tasks, such as black-and-white photo colorization and cross-domain (anime-to-photo) preset transfer. These results confirm that SemiNFT transcends simple statistical matching and achieves a sophisticated level of aesthetic comprehension. Our project can be found at https://melanyyang.github.io/SemiNFT/.

翻译：逼真的色彩润饰在视觉内容创作中扮演着至关重要的角色，然而，由于其依赖专业技巧，手动润饰对于非专业人士而言仍然难以掌握。基于参考的方法提供了一种有前景的替代方案，通过将参考图像的预设色彩迁移到源图像上。然而，这些方法通常如同初学者般运作，执行基于像素级统计的全局色彩映射，而未能真正理解语义语境或人类审美。为了解决这一问题，我们提出了SemiNFT，一个基于扩散Transformer（DiT）的润饰框架，它模拟了人类艺术训练的过程：从刻板模仿开始，逐渐发展为直觉创作。具体而言，SemiNFT首先通过配对的三元组数据进行训练，以掌握基本的结构保持和色彩映射技能，然后进阶到在非配对数据上进行强化学习（RL），以培养细腻的审美感知。关键的是，在RL阶段，为了防止对旧技能的灾难性遗忘，我们设计了一种混合在线-离线奖励机制，通过结构回顾来锚定审美探索。大量实验表明，SemiNFT不仅在标准预设迁移基准测试中超越了最先进的方法，而且在零样本任务（如黑白照片着色和跨域（动漫到照片）预设迁移）中也展现出显著的智能。这些结果证实了SemiNFT超越了简单的统计匹配，达到了复杂的审美理解水平。我们的项目可在 https://melanyyang.github.io/SemiNFT/ 找到。