Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset

2026-04-17

AI Summary

This work addresses the limitations of existing photo color grading style transfer methods, which suffer from the scarcity of high-quality triplet datasets and semantic loss or color distortion caused by independently extracting content and reference features. To overcome these challenges, the authors construct TST100K—the first large-scale tone transfer triplet dataset comprising 100,000 image triplets—and propose ICTone, a diffusion-based framework that enables context-aware joint conditional modeling for synergistic content-reference feature extraction. Furthermore, they introduce a tone-scoring reward feedback mechanism to refine generation quality. Experimental results demonstrate that the proposed method achieves state-of-the-art performance on both quantitative metrics and human evaluations, validating the effectiveness of the new dataset and the superiority of the proposed framework.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Tone style transfer for photo retouching aims to adapt the stylistic tone of the reference image to a given content image. However, the lack of high-quality large-scale triplet datasets with stylized ground truth forces existing methods to rely on self-supervised or proxy objectives, which limits model capability. To mitigate this gap, we design a data construction pipeline to build TST100K, a large-scale dataset of 100,000 content-reference-stylized triplets. At the core of this pipeline, we train a tone style scorer to ensure strict stylistic consistency for each triplet. In addition, existing methods typically extract content and reference features independently and then fuse them in a decoder, which may cause semantic loss and lead to inappropriate color transfer and degraded visual aesthetics. Instead, we propose ICTone, a diffusion-based framework that performs tone transfer in an in-context manner by jointly conditioning on both images, leveraging the semantic priors of generative models for semantic-aware transfer. Reward feedback learning using the tone style scorer is further incorporated to improve stylistic fidelity and visual quality. Experiments demonstrate the effectiveness of TST100K, and ICTone achieves state-of-the-art performance on both quantitative metrics and human evaluations.

Problem

• tone style transfer
• photo retouching
• triplet dataset
• semantic consistency
• color transfer

Innovation

• tone style transfer
• in-context learning
• diffusion model
• triplet dataset
• reward feedback learning