从一张模糊照片生成任意焦点和光圈效果的逼真图像。
Generative Refocusing: Flexible Defocus Control from a Single Image
- 先用DeblurNet恢复全焦清晰图，再用BokehNet生成可控虚化背景。
- 在多个基准测试中达到顶尖性能，支持自定义光圈形状。
- 无需专用设备，真实感强，适合摄影与视觉编辑应用。
景深控制对摄影至关重要，但实现完美对焦通常需多次尝试或特殊设备。单图重聚焦仍具挑战性，需恢复清晰内容并生成真实虚化背景。现有方法存在诸多缺陷：依赖全焦输入、依赖模拟生成数据、无法灵活控制光圈。我们提出生成式重聚焦（Generative Refocusing），采用两步流程：首先通过DeblurNet从多样输入中恢复全焦图像；再由BokehNet生成可调控的虚化效果。该方法融合合成与真实虚化图像，在保持真实光学特性的同时实现精准控制。实验表明，该方法在去模糊、虚化合成及重聚焦任务上均表现领先。此外，其支持自定义光圈形状。项目页面：https://generative-refocusing.github.io/
原文摘要 · Abstract (English)
Depth-of-field control is essential in photography, but achieving perfect focus often requires multiple attempts or specialized equipment. Single-image refocusing is still difficult. It involves recovering sharp content and creating realistic bokeh. Current methods have significant drawbacks. They require all-in-focus inputs, rely on synthetic data from simulators, and have limited control over the aperture. We introduce Generative Refocusing, a two-step process that uses DeblurNet to recover all-in-focus images from diverse inputs and BokehNet to create controllable bokeh. This method combines synthetic and real bokeh images to achieve precise control while preserving authentic optical characteristics. Our experiments show we achieve top performance in defocus deblurring, bokeh synthesis, and refocusing benchmarks. Additionally, our Generative Refocusing allows custom aperture shapes. Project page: https://generative-refocusing.github.io/
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。