重现DragDiffusion：基于扩散模型的交互式点编辑
Reproducing DragDiffusion: Interactive Point-Based Editing with Diffusion Models
AI总结：
本文重现了DragDiffusion方法，验证了其在不同超参数下的可重复性，并发现其性能对优化时间步和特征层敏感。
摘要：
DragDiffusion是一种基于扩散的交互式点图像编辑方法，使用户能够通过直接拖动选定的点来操控图像。该方法声称通过在中间时间步优化单一扩散潜在表示，结合保持身份的微调和空间正则化，可以实现精确的空间控制。本文使用作者发布的实现和DragBench基准进行了DragDiffusion的可重复性研究。我们重现了扩散时间步选择、基于LoRA的微调、遮罩正则化强度和UNet特征监督等主要消融研究，并观察到与原始工作报告的定性和定量趋势有接近的一致性。同时，我们的实验表明，性能对少量超参数假设敏感，特别是优化时间步和用于运动监督的特征层，而其他组件则允许更宽的操作范围。我们进一步评估了多时间步潜在优化变体，发现其不提高空间准确性，但显著增加计算成本。总体而言，我们的发现支持DragDiffusion的核心主张，同时澄清了这些主张在何种条件下可以可靠地重现。代码可在https://github.com/AliSubhan5341/DragDiffusion-TMLR-Reproducibility-Challenge获取。
英文摘要：
DragDiffusion is a diffusion-based method for interactive point-based image editing that enables users to manipulate images by directly dragging selected points. The method claims that accurate spatial control can be achieved by optimizing a single diffusion latent at an intermediate timestep, together with identity-preserving fine-tuning and spatial regularization. This work presents a reproducibility study of DragDiffusion using the authors' released implementation and the DragBench benchmark. We reproduce the main ablation studies on diffusion timestep selection, LoRA-based fine-tuning, mask regularization strength, and UNet feature supervision, and observe close agreement with the qualitative and quantitative trends reported in the original work. At the same time, our experiments show that performance is sensitive to a small number of hyperparameter assumptions, particularly the optimized timestep and the feature level used for motion supervision, while other components admit broader operating ranges. We further evaluate a multi-timestep latent optimization variant and find that it does not improve spatial accuracy while substantially increasing computational cost. Overall, our findings support the central claims of DragDiffusion while clarifying the conditions under which they are reliably reproducible. Code is available at https://github.com/AliSubhan5341/DragDiffusion-TMLR-Reproducibility-Challenge.
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。
