Aspects of the present disclosure relate to systems and methods for generating a depth map. An example device may include one or more processors and a memory. The memory may include instructions that, when executed by the one or more processors, cause the device to receive a first intensity measurement for each of a plurality of focal regions for a camera at a first focal length, determine, from the first intensity measurements, a first focus value for each of the plurality of focal regions, generate a depth map of an indication of focal lengths for the plurality of focal regions based on the first focus values for the plurality of focal regions, and use the depth map in determining when to perform or in performing an autofocus operation for the camera.