{"ID":2834545,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.01755","arxiv_id":"2512.01755","title":"FreqEdit: Preserving High-Frequency Features for Robust Multi-Turn Image Editing","abstract":"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.","short_abstract":"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 o...","url_abs":"https://arxiv.org/abs/2512.01755","url_pdf":"https://arxiv.org/pdf/2512.01755v2","authors":"[\"Yucheng Liao\",\"Jiajun Liang\",\"Kaiqian Cui\",\"Baoquan Zhao\",\"Haoran Xie\",\"Wei Liu\",\"Qing Li\",\"Xudong Mao\"]","published":"2025-12-01T15:00:47Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}