无需训练的解耦文本引导图像编辑：通过稀疏潜在约束
Training-Free Disentangled Text-Guided Image Editing via Sparse Latent Constraints
AI总结：
本文提出一种无需训练的解耦文本引导图像编辑方法，通过引入稀疏潜在约束减少属性纠缠问题，提升编辑的可控性与准确性。
摘要：
文本驱动的图像操作常常受到属性纠缠的困扰，其中修改目标属性（例如添加发饰）会无意中改变其他语义属性，如身份或外观。PPE框架通过利用预训练的视觉-语言模型来实现解耦编辑。在本工作中，我们分析了PPE框架，重点在于其架构组件，包括基于BERT的属性预测和基于StyleGAN2的图像生成在CelebA-HQ数据集上。通过实证分析，我们发现原始正则化策略的局限性，其中潜在更新仍保持密集且容易产生语义泄漏。为缓解这一问题，我们引入了基于稀疏性的约束，使用L1正则化对潜在空间操作进行约束。实验结果表明，所提出的方法能够更集中和受控地进行编辑，有效减少非目标属性的意外变化，同时保持面部身份。
英文摘要：
Text-driven image manipulation often suffers from attribute entanglement, where modifying a target attribute (e.g., adding bangs) unintentionally alters other semantic properties such as identity or appearance. The Predict, Prevent, and Evaluate (PPE) framework addresses this issue by leveraging pre-trained vision-language models for disentangled editing. In this work, we analyze the PPE framework, focusing on its architectural components, including BERT-based attribute prediction and StyleGAN2-based image generation on the CelebA-HQ dataset. Through empirical analysis, we identify a limitation in the original regularization strategy, where latent updates remain dense and prone to semantic leakage. To mitigate this issue, we introduce a sparsity-based constraint using L1 regularization on latent space manipulation. Experimental results demonstrate that the proposed approach enforces more focused and controlled edits, effectively reducing unintended changes in non-target attributes while preserving facial identity.
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。
