通过再修复自一致性评估图像修复
Assessing Image Inpainting via Re-Inpainting Self-Consistency Evaluation
AI总结：
针对图像修复评估依赖参考图像导致偏差的问题，提出基于多次再修复自一致性度量的无参考评估方法，实验证明其与人类判断一致。
摘要：
图像修复是利用可用数据重建损坏图像中缺失部分的任务，在确保一致性和保真度方面面临挑战，尤其是在信息稀缺条件下。传统评估方法高度依赖未掩码参考图像的存在，固有地偏向某些修复结果，引入偏差。针对这一问题，我们提出了一种创新的评估范式，利用基于多次再修复过程的自监督度量。该方法不同于传统上在像素或特征空间与原始图像进行直接比较的依赖，强调自一致性原则，以探索各种可行的修复方案，有效减少偏差。我们在众多基准上的广泛实验验证了我们的评估方法与人类判断的一致性。
英文摘要：
Image inpainting, the task of reconstructing missing segments in corrupted images using available data, faces challenges in ensuring consistency and fidelity, especially under information-scarce conditions. Traditional evaluation methods, heavily dependent on the existence of unmasked reference images, inherently favor certain inpainting outcomes, introducing biases. Addressing this issue, we introduce an innovative evaluation paradigm that utilizes a self-supervised metric based on multiple re-inpainting passes. This approach, diverging from conventional reliance on direct comparisons in pixel or feature space with original images, emphasizes the principle of self-consistency to enable the exploration of various viable inpainting solutions, effectively reducing biases. Our extensive experiments across numerous benchmarks validate the alignment of our evaluation method with human judgment.
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。
