在对话式图像编辑中明确隐式保留意图
Making Implicit Preservation Intent Explicit in Conversational Image Editing
AI总结：
研究对话式图像编辑中隐式保留意图的问题，提出无需训练的ReSpec框架，通过配对恢复感知指令与历史视觉参考使隐式保留明确化，实验显示该框架提升了恢复保真度和时间一致性。
摘要：
对话式图像编辑不仅需要保留可见内容，还需保留跨轮次暂时消失的内容。当新添加或修改的内容遮挡先前可见区域时，若该区域未发生语义变化则应重新出现。然而，现有系统常无法恢复此类被遮挡但未改变的内容，导致结果不一致或产生幻觉。我们引入了OCCUR - Bench，一个用于对话式图像编辑中时间保留的诊断基准。它提供多样的遮挡和揭示场景及历史恢复参考，能评估忠实恢复而非合理生成。我们还提出了ReSpec，一个无需训练的框架，通过将恢复感知指令与历史视觉参考配对来使隐式保留明确化。实验表明ReSpec提高了在OCCUR - Bench上的恢复保真度和时间一致性，强调了在编辑历史而非仅当前图像中进行保留的必要性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
