UIP2P：基于编辑可逆性约束的无监督指令图像编辑
UIP2P: Unsupervised Instruction-based Image Editing via Edit Reversibility Constraint
AI总结：
本文提出UIP2P，一种无需真实编辑图像的无监督指令图像编辑方法，通过编辑可逆性约束（ERC）实现前向与反向编辑对齐，在真实数据上训练，提升编辑保真度与泛化能力。
摘要：
我们提出了一种无监督的基于指令的图像编辑方法，该方法在训练过程中无需真实编辑图像。现有方法依赖于使用输入图像、真实编辑图像和编辑指令三元组的监督学习。这些三元组通常由现有编辑方法生成，这会引入偏差，或通过人工标注获得，这既昂贵又限制了泛化能力。我们的方法通过引入一种名为编辑可逆性约束（ERC）的新颖编辑机制来解决这些挑战，该机制在一个训练步骤中应用前向和反向编辑，并在图像、文本和注意力空间中强制对齐。这使我们能够绕过对真实编辑图像的需求，并首次在由真实图像-标题对或图像-标题-指令三元组组成的数据集上解锁训练。我们通过实验证明，我们的方法在更广泛的编辑范围内表现更好，具有高保真度和精确性。通过消除对预先存在的三元组数据集的需求，减少与当前方法相关的偏差，并提出ERC，我们的工作在解锁基于指令的图像编辑的规模化方面代表了重大进展。
英文摘要：
We propose an unsupervised instruction-based image editing approach that removes the need for ground-truth edited images during training. Existing methods rely on supervised learning with triplets of input images, ground-truth edited images, and edit instructions. These triplets are typically generated either by existing editing methods, introducing biases, or through human annotations, which are costly and limit generalization. Our approach addresses these challenges by introducing a novel editing mechanism called Edit Reversibility Constraint (ERC), which applies forward and reverse edits in one training step and enforces alignment in image, text, and attention spaces. This allows us to bypass the need for ground-truth edited images and unlock training for the first time on datasets comprising either real image-caption pairs or image-caption-instruction triplets. We empirically show that our approach performs better across a broader range of edits with high-fidelity and precision. By eliminating the need for pre-existing datasets of triplets, reducing biases associated with current methods, and proposing ERC, our work represents a significant advancement in unblocking scaling of instruction-based image editing.
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。
