LimeCross：基于结构一致性的上下文条件分层图像编辑
LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency
AI总结：
LimeCross通过上下文条件分层图像编辑框架，实现基于文本的可控编辑，保持结构一致性，提升图像合成的真实性和透明度稳定性。
摘要：
分层图像资产广泛用于现实中的创意工作流程，使非破坏性迭代和灵活重组成为可能。最近的分层图像生成和分解技术能够合成或恢复分层表示，但可控的分层图像编辑仍具挑战性。手动编辑需要在各层之间精心协调以保持一致的光照和接触，而基于AI的流程将各层折叠成扁平图像进行编辑，然后再分解，导致背景到前景的泄漏和不稳定的透明度。为了解决这些限制，我们提出了LimeCross，一种无需训练的上下文条件分层图像编辑框架，能够根据文本编辑用户选择的RGBA层，同时保持其他层不变。它利用双流注意力机制从其他层中获取上下文线索，以保持跨层一致性，同时显式地保持层完整性，以防止编辑层的污染。为了评估我们的方法，我们引入了LayerEditBench，一个包含1500个分层场景的基准测试集，配有配对的源/目标提示，以及评估协议，评估编辑保真度和alpha通道稳定性。广泛的实验表明，LimeCross在强编辑基线上提高了层纯度和复合真实感，确立了基于上下文条件的分层编辑作为可控生成创作的原理性框架。
英文摘要：
Layered image assets are widely used in real-world creative workflows, enabling non-destructive iteration and flexible re-composition. Recent advances in layered image generation and decomposition synthesize or recover layered representations, yet controllable editing of layered images remains challenging. Manual editing requires careful coordination across layers to maintain consistent illumination and contact, while AI-based pipelines collapse layers into a flattened image for editing, then decompose them again, introducing background-to-foreground leakage and unstable transparency. To address these limitations, we propose LimeCross, a training-free context-conditioned layered image editing framework that edits user-selected RGBA layers according to text while keeping the remaining layers unchanged. It leverages contextual cues from other layers using a bi-stream attention mechanism to preserve cross-layer consistency, while explicitly maintaining layer integrity to prevent the contamination of edited layers. To evaluate our approach, we introduce LayerEditBench, a benchmark of 1500 layered scenes with paired source/target prompts, along with evaluation protocols that assess both edit fidelity and alpha channel stability. Extensive experiments demonstrate that LimeCross improves layer purity and composite realism over strong editing baselines, establishing context-conditioned layered editing as a principled framework for controllable generative creation.
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。
