论文标题
智能自动对焦
Intelligent Autofocus
论文作者
论文摘要
我们证明，深度学习方法可以从1-2图像样本中确定最佳焦点位置，比传统的基于搜索的方法更快地使5-10倍的焦点。与相位检测方法相反，深度对焦不需要专门的硬件。在采用常规方法（假设静态“最佳焦点”）的进一步约束中，AI方法可以生成基于场景的焦点轨迹，从而优化合成的图像质量，以用于动态和三维场景。
We demonstrate that deep learning methods can determine the best focus position from 1-2 image samples, enabling 5-10x faster focus than traditional search-based methods. In contrast with phase detection methods, deep autofocus does not require specialized hardware. In further constrast with conventional methods, which assume a static "best focus," AI methods can generate scene-based focus trajectories that optimize synthesized image quality for dynamic and three dimensional scenes.
