Decomposing Subject-Driven Image Generation via Intermediate Structural Prediction
摘要
Subject-driven text-to-image generation still struggles to preserve high-frequency identity details such as logos, patterns, and text. Existing methods typically operate directly in RGB space, which often leads to detail degradation under substantial edits. We propose a two-stage framework that decouples structure from appearance by first predicting a Canny map and then rendering the final image conditioned on both the source appearance and the predicted structure. To improve text handling, we further introduce a fully automatic pipeline that constructs a 100k-pair text-aware dataset with cross-view textual consistency. Experiments, including GPT-4.1-based evaluation and a knowledge distillation study, show clear gains over selected baselines and suggest that intermediate structural prediction is an effective route for high-fidelity subject-driven generation. Our dataset and code will be made publicly available.
引用
@article{arxiv.2605.20807,
title = {Decomposing Subject-Driven Image Generation via Intermediate Structural Prediction},
author = {Hanzhong Guo and Yizhou Yu},
journal= {arXiv preprint arXiv:2605.20807},
year = {2026}
}