SemiNFT: Learning to Transfer Presets from Imitation to Appreciation via Hybrid-Sample Reinforcement Learning

2026-02-09

AI Summary

Existing color preset transfer methods often neglect semantic context and human aesthetic preferences, relying solely on pixel-level statistics and thus failing to meet the high-quality editing demands of non-professional users. This work proposes SemiNFT, a framework that emulates the human artistic learning process—from imitation to appreciation—by first learning structure-preserving color mappings through paired triplets, then enhancing aesthetic perception via a hybrid online–offline reinforcement learning strategy leveraging unpaired data. To mitigate skill forgetting, the method incorporates a structural consistency constraint. Built upon the Diffusion Transformer architecture, SemiNFT outperforms state-of-the-art approaches on standard benchmarks and demonstrates remarkable generalization and aesthetic understanding in zero-shot cross-domain tasks, such as grayscale-to-color and anime-to-photorealistic image translation.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Semi-Supervised Learning
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

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/.

Problem

• color retouching
• preset transfer
• aesthetic perception
• reference-based image editing
• photorealistic colorization

Innovation

• Hybrid-Sample Reinforcement Learning
• Diffusion Transformer
• Preset Transfer
• Aesthetic Perception
• Catastrophic Forgetting Mitigation