Abstract: Visual content captured by an image capture device may be stabilized. A target depicted within visual content of a video may be identified manually by a user or automatically by a computing device. Dolly zoom visual content may be generated by using a viewing window to crop the visual content. The size and/or the position of the viewing window within the visual content may change based on size and/or the position of the target within the visual content. The combination of video stabilization, target tracking, and cropping of the visual content may produce the dolly zoom effect. The dolly zoom effect may compensate for the movement of the image capture device and work on video captured by an image capture device without optical zoom.

Abstract: Tone mapping for image capture may include accessing a first image detected using an image sensor; accessing an exposure parameter (exposure duration, or time, multiplied by ISO or gain) used to detect the first image; scaling pixel values of the first image by a scale factor inversely proportional to the exposure parameter to obtain a scaled image; determining a scene luminance based on an average of pixel values of the scaled image; determining a target luminance based on the scene luminance; determining a target histogram based on the target luminance; determining a first histogram of luminance values of the first image; determining a transfer function based on the first histogram and the target histogram; applying the transfer function to pixel values of the first image to produce a tone mapped image; and storing or transmitting an output image based on the tone mapped image.

Abstract: An image capture device may experience motion while capturing a video. A video clip may be generated from the video. The beginning of the video clip may be identified based on acceleration of the image capture device during capture of the video, while the ending of the video clip may be identified based on speed of the image capture device during capture of the video.

Abstract: A computer accesses a luminance histogram of an image. The computer determines a target histogram for the image based on a mean luminance of the image and based on a high dynamic range or a low dynamic range status of the image. The computer determines a first loss function based on a sum of a second loss function and a third loss function, the second loss function corresponding to a difference between the luminance histogram and the target histogram, the third loss function corresponding to a difference between a mean luminance of the image and a mean luminance target. The computer computes a gradient descent result by applying a gradient descent algorithm to the first loss function using a tuning constant based on image quality constraints and an exposure target. The computer generates a tone curve comprising the computed gradient descent result.

Abstract: Tone mapping for image capture may include accessing a first image detected using an image sensor; accessing an exposure parameter (exposure duration, or time, multiplied by ISO or gain) used to detect the first image; scaling pixel values of the first image by a scale factor inversely proportional to the exposure parameter to obtain a scaled image; determining a scene luminance based on an average of pixel values of the scaled image; determining a target luminance based on the scene luminance; determining a target histogram based on the target luminance; determining a first histogram of luminance values of the first image; determining a transfer function based on the first histogram and the target histogram; applying the transfer function to pixel values of the first image to produce a tone mapped image; and storing or transmitting an output image based on the tone mapped image.