安排你的编辑：一种简单而有效的图像编辑扩散噪声调度
Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing
AI总结：
针对 DDIM 反演误差累积问题，本文提出无需重训且兼容多种方法的 Logistic Schedule，以消除传统噪声调度奇异性并提升图像编辑的内容保持与保真度。
摘要：
文本引导的扩散模型显著推动了图像编辑的发展，能够根据文本提示实现高质量且多样化的修改。然而，有效的编辑需要将源图像反演到潜空间中，这一过程常常受到 DDIM 反演所固有的预测误差的阻碍。这些误差在扩散过程中不断累积，导致内容保持和编辑保真度较差，尤其是在条件输入情况下。我们通过研究 DDIM 反演中导致误差累积的主要因素来应对这些挑战，并指认出传统噪声调度中的奇异性问题是关键症结。为解决这一问题，我们提出了 Logistic Schedule（逻辑斯蒂调度），这是一种新型噪声调度，旨在消除奇异性、提升反演稳定性，并为图像编辑提供更优的噪声空间。该调度降低了噪声预测误差，从而实现更忠实的编辑，保留源图像的原始内容。我们的方法无需额外重新训练，并且与各种现有编辑方法兼容。在八项编辑任务上的实验表明，与传统噪声调度相比，Logistic Schedule 在内容保持和编辑保真度方面表现更优，凸显了其适应性和有效性。
英文摘要：
Text-guided diffusion models have significantly advanced image editing, enabling high-quality and diverse modifications driven by text prompts. However, effective editing requires inverting the source image into a latent space, a process often hindered by prediction errors inherent in DDIM inversion. These errors accumulate during the diffusion process, resulting in inferior content preservation and edit fidelity, especially with conditional inputs. We address these challenges by investigating the primary contributors to error accumulation in DDIM inversion and identify the singularity problem in traditional noise schedules as a key issue. To resolve this, we introduce the Logistic Schedule, a novel noise schedule designed to eliminate singularities, improve inversion stability, and provide a better noise space for image editing. This schedule reduces noise prediction errors, enabling more faithful editing that preserves the original content of the source image. Our approach requires no additional retraining and is compatible with various existing editing methods. Experiments across eight editing tasks demonstrate the Logistic Schedule's superior performance in content preservation and edit fidelity compared to traditional noise schedules, highlighting its adaptability and effectiveness.
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。
