Abstract
Depth-of-field control is essential in photography, but getting the perfect focus often takes several tries or special equipment. Single-image refocusing is still difficult. It involves recovering sharp content and creating realistic bokeh. Current methods have significant drawbacks. They need all-in-focus inputs, depend on synthetic data from simulators, and have limited control over aperture. We introduce Generative Refocusing, a two-step process that uses DeblurNet to recover all-in-focus images from various inputs and BokehNet for creating controllable bokeh. Our main innovation is semi-supervised training. This method combines synthetic paired data with unpaired real bokeh images, using EXIF metadata to capture real optical characteristics beyond what simulators can provide. Our experiments show we achieve top performance in defocus deblurring, bokeh synthesis, and refocusing benchmarks. Additionally, our Generative Refocusing allows text-guided adjustments and custom aperture shapes.
Abstract (translated)
景深控制在摄影中至关重要，但要获得完美的焦点通常需要多次尝试或特殊设备。单图像重新对焦仍然具有挑战性，因为它涉及到恢复清晰的内容并生成逼真的背景虚化效果（bokeh）。目前的方法存在一些显著的缺点：它们依赖于所有内容都聚焦的照片输入、需要来自模拟器的合成数据，并且对于光圈控制有限。 我们引入了一种名为“生成式重新对焦”的两步过程，该方法使用DeblurNet从各种输入中恢复出全部清晰度的图像，并通过BokehNet创建可调节的背景虚化效果。我们的主要创新在于半监督训练方式：这种方法结合了合成配对数据与未配对的真实背景虚化图像，并利用EXIF元数据来捕捉模拟器无法提供的真实光学特性。 实验结果显示，我们在脱焦模糊校正、背景虚化生成以及重新对焦基准测试中取得了最佳性能。此外，我们的“生成式重新对焦”方法还支持基于文本的调整和自定义光圈形状。
URL
https://arxiv.org/abs/2512.16923
