FreqEdit: Preserving High-Frequency Features for Robust Multi-Turn Image Editing
By: Yucheng Liao , Jiajun Liang , Kaiqian Cui and more
Potential Business Impact:
Fixes pictures perfectly with many changes.
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.
Similar Papers
Adaptive High-Frequency Preprocessing for Video Coding
CV and Pattern Recognition
Makes videos look better and use less space.
SpotEdit: Evaluating Visually-Guided Image Editing Methods
CV and Pattern Recognition
Tests AI that edits pictures using words and eyes.
AutoEdit: Automatic Hyperparameter Tuning for Image Editing
CV and Pattern Recognition
Makes editing pictures with words much faster.