Joint depth prediction from dual camera and dual pixel

Example implementations relate to joint depth prediction from dual cameras and dual pixels. An example method may include obtaining a first set of depth information representing a scene from a first source, and obtaining a second set of depth information representing the scene from a second source. The method may also include determining, using a neural network, a joint depth map that conveys respective depths of elements in the scene. The neural network may determine a joint depth map based on a combination of the first set of depth information and the second set of depth information. Further, the method may include modifying the image representing the scene based on the joint depth map. For example, a background portion of an image may be partially blurred based on a joint depth map. 示例实现涉及来自双相机和双像素的联合深度预测。示例方法可以包括从第一源获得表示场景的第一深度信息集，以及从第二源获得表示场景的第二深度信息集。该方法还可以包括使用神经网络来确定传达场景中元素的相应深度的联合深度图。神经网络可以基于第一深度信息集和第二深度信息集的组合来确定联合深度图。此外，该方法可以包括基于联合深度图修改表示场景的图像。例如，图像的背景部分可以基于联合深度图而被部分模糊。