{"ID":2877564,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.21090","arxiv_id":"2508.21090","title":"Q-Align: Alleviating Attention Leakage in Zero-Shot Appearance Transfer via Query-Query Alignment","abstract":"We observe that zero-shot appearance transfer with large-scale image generation models faces a significant challenge: Attention Leakage. This challenge arises when the semantic mapping between two images is captured by the Query-Key alignment. To tackle this issue, we introduce Q-Align, utilizing Query-Query alignment to mitigate attention leakage and improve the semantic alignment in zero-shot appearance transfer. Q-Align incorporates three core contributions: (1) Query-Query alignment, facilitating the sophisticated spatial semantic mapping between two images; (2) Key-Value rearrangement, enhancing feature correspondence through realignment; and (3) Attention refinement using rearranged keys and values to maintain semantic consistency. We validate the effectiveness of Q-Align through extensive experiments and analysis, and Q-Align outperforms state-of-the-art methods in appearance fidelity while maintaining competitive structure preservation.","short_abstract":"We observe that zero-shot appearance transfer with large-scale image generation models faces a significant challenge: Attention Leakage. This challenge arises when the semantic mapping between two images is captured by the Query-Key alignment. To tackle this issue, we introduce Q-Align, utilizing Query-Query alignment...","url_abs":"https://arxiv.org/abs/2508.21090","url_pdf":"https://arxiv.org/pdf/2508.21090v1","authors":"[\"Namu Kim\",\"Wonbin Kweon\",\"Minsoo Kim\",\"Hwanjo Yu\"]","published":"2025-08-27T09:54:23Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}