用真实数据训练，让照片虚化效果可控又逼真。
Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures
- 通过光圈感知注意力机制，直观调节虚化强度。
- 在23,000张真实高分辨率照片上训练，效果更自然。
- 计算量小，零样本泛化强，适合图像编辑与摄影应用。
虚化渲染在专业摄影中能产生视觉吸引力强的柔和背景模糊效果。尽管近年基于学习的方法取得进展，但实现可变强度的真实感虚化仍具挑战。现有方法依赖额外输入且因使用合成数据导致虚化效果不自然。本文提出Bokehlicious，一种高效网络，通过光圈感知注意力机制实现对虚化强度的直观控制，模拟真实镜头光圈行为。为解决高质量真实数据缺乏问题，我们构建了RealBokeh数据集，包含23,000张由专业摄影师拍摄的24兆像素高分辨率图像，覆盖多样场景及不同光圈和焦距设置。在新提出的RealBokeh及现有虚化基准上的评估表明，Bokehlicious持续优于当前最优方法，显著降低计算成本，并展现强大零样本泛化能力。该方法还可拓展至失焦去模糊任务，在RealDOF基准上达到竞争力表现。代码与数据详见https://github.com/TimSeizinger/Bokehlicious。
原文摘要 · Abstract (English)
Bokeh rendering methods play a key role in creating the visually appealing, softly blurred backgrounds seen in professional photography. While recent learning-based approaches show promising results, generating realistic Bokeh with variable strength remains challenging. Existing methods require additional inputs and suffer from unrealistic Bokeh reproduction due to reliance on synthetic data. In this work, we propose Bokehlicious, a highly efficient network that provides intuitive control over Bokeh strength through an Aperture-Aware Attention mechanism, mimicking the physical lens aperture. To further address the lack of high-quality real-world data, we present RealBokeh, a novel dataset featuring 23,000 high-resolution (24-MP) images captured by professional photographers, covering diverse scenes with varied aperture and focal length settings. Evaluations on both our new RealBokeh and established Bokeh rendering benchmarks show that Bokehlicious consistently outperforms SOTA methods while significantly reducing computational cost and exhibiting strong zero-shot generalization. Our method and dataset further extend to defocus deblurring, achieving competitive results on the RealDOF benchmark. Our code and data can be found at https://github.com/TimSeizinger/Bokehlicious
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。