让AI生成图像时能精确控制镜头虚化，像真实相机一样调节光圈。
Fine-grained Defocus Blur Control for Generative Image Models
- 通过模拟物理成像过程，先生成清晰图再预测焦点距离。
- 能根据EXIF数据精准生成对应虚化效果，不改变画面内容。
- 适合需要真实镜头效果的摄影级图像生成场景。
当前文本到图像扩散模型虽能生成高质量图像，但在融入精确相机参数（如光圈值）方面表现不佳。本文提出一种新框架，利用图像文件中嵌入的EXIF数据，重点实现可调控的镜头虚化效果。方法通过先生成全焦图像，估计单目深度，使用新型焦点距离变换器预测合理焦距，再借助现有可微分镜头模糊模型生成虚化图像。整个流程支持反向传播，无需显式标注即可学习基于内容与EXIF数据的虚化生成。推理阶段，用户可精细交互控制虚化程度，同时保持场景内容不变。实验表明，该模型在不改变画面内容的前提下，实现了更精细的虚化控制能力。
原文摘要 · Abstract (English)
Current text-to-image diffusion models excel at generating diverse, high-quality images, yet they struggle to incorporate fine-grained camera metadata such as precise aperture settings. In this work, we introduce a novel text-to-image diffusion framework that leverages camera metadata, or EXIF data, which is often embedded in image files, with an emphasis on generating controllable lens blur. Our method mimics the physical image formation process by first generating an all-in-focus image, estimating its monocular depth, predicting a plausible focus distance with a novel focus distance transformer, and then forming a defocused image with an existing differentiable lens blur model. Gradients flow backwards through this whole process, allowing us to learn without explicit supervision to generate defocus effects based on content elements and the provided EXIF data. At inference time, this enables precise interactive user control over defocus effects while preserving scene contents, which is not achievable with existing diffusion models. Experimental results demonstrate that our model enables superior fine-grained control without altering the depicted scene.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。