{"ID":6138108,"CreatedAt":"2026-07-09T01:07:32.349475501Z","UpdatedAt":"2026-07-11T06:21:26.878598377Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.07051","arxiv_id":"2607.07051","title":"Making Implicit Preservation Intent Explicit in Conversational Image Editing","abstract":"Conversational image editing requires preserving not only visible content, but also content that temporarily disappears across turns. When newly added or modified content occludes a previously visible region, that region should reappear if it was never semantically changed. However, existing systems often fail to recover such occluded-but-unchanged content, producing inconsistent or hallucinated results. We introduce OCCUR-Bench, a diagnostic benchmark for temporal preservation in conversational image editing. OCCUR-Bench provides diverse occlusion-and-revelation scenarios with historical restoration references, enabling evaluation of faithful restoration rather than plausible regeneration. We also propose ReSpec, a training-free framework that makes implicit preservation explicit by pairing restoration-aware instructions with historical visual references. Given an editing history, ReSpec identifies what should persist, selects the historical image state that provides missing visual evidence, and conditions an in-context editor on the resulting instruction and reference image. Experiments show that ReSpec improves restoration fidelity and temporal consistency on OCCUR-Bench, highlighting the need to ground preservation in editing history rather than only the current image.","short_abstract":"Conversational image editing requires preserving not only visible content, but also content that temporarily disappears across turns. When newly added or modified content occludes a previously visible region, that region should reappear if it was never semantically changed. However, existing systems often fail to recov...","url_abs":"https://arxiv.org/abs/2607.07051","url_pdf":"https://arxiv.org/pdf/2607.07051v1","authors":"[\"Soomin Han\",\"Jihyung Ahn\",\"Bumsoo Kim\",\"Buru Chang\"]","published":"2026-07-08T06:26:28Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false}
