2025/12/01 by Yu-Cheng Liao, Liao, Yucheng, Jiajun Liang +13
Computer Science · #Generative Adversarial Networks and Image Synthesis #Multimodal Machine Learning Applications #Advanced Image and Video Retrieval Techniques
paper · pdf · doi:10.48550/arxiv.2512.01755
Instruction-based image editing through natural language has emerged as a powerful paradigm for intuitive visual manipulation. While recent models achieve impressive results on single edits, they suffer from severe quality degradation under multi-turn editing. Through systematic analysis, we identify progressive loss of high-frequency information as the primary cause of this quality degradation. We present FreqEdit, a training-free framework that enables stable editing across 10+ consecutive iterations. Our approach comprises three synergistic components: (1) high-frequency feature injection from reference velocity fields to preserve fine-grained details, (2) an adaptive injection strategy that spatially modulates injection strength for precise region-specific control, and (3) a path compensation mechanism that periodically recalibrates the editing trajectory to prevent over-constraint. Extensive experiments demonstrate that FreqEdit achieves superior performance in both identity preservation and instruction following compared to seven state-of-the-art baselines.