Adobe, Inc.

Chetan Nanda

Elya Shechtman

Oliver Wang

Kalyan Krishna Sunkavalli

Tharun Mohandoss

Pulkit Gera

Kartik Sethi

Ramesh P B

Sweta Agrawal

Systems and techniques for automatic digital parameter adjustment are described that leverage insights learned from an image set to automatically predict parameter values for an input item of digital visual content. To do so, the automatic digital parameter adjustment techniques described herein captures visual and contextual features of digital visual content to determine balanced visual output in a range of visual scenes and settings. The visual and contextual features of digital visual content are used to train a parameter adjustment model through machine learning techniques that captures feature patterns and interactions. The parameter adjustment model exploits these feature interactions to determine visually pleasing parameter values for an input item of digital visual content. The predicted parameter values are output, allowing further adjustment to the parameter values.

Automated digital parameter adjustment for digital images

In implementations of skin tone assisted digital image color matching, a device implements a color editing system, which includes a facial detection module to detect faces in an input image and in a reference image, and includes a skin tone model to determine a skin tone value reflective of a skin tone of each of the faces. A color matching module can be implemented to group the faces into one or more face groups based on the skin tone value of each of the faces, match a face group pair as an input image face group paired with a reference image face group, and generate a modified image from the input image based on color features of the reference image, the color features including face skin tones of the respective faces in the face group pair as part of the color features applied to modify the input image.

Skin tone assisted digital image color matching

Automatic digital parameter adjustment including tone and color correction

This disclosure involves training generative adversarial networks to shot-match two unmatched images in a context-sensitive manner. For example, aspects of the present disclosure include accessing a trained generative adversarial network including a trained generator model and a trained discriminator model. A source image and a reference image may be inputted into the generator model to generate a modified source image. The modified source image and the reference image may be inputted into the discriminator model to determine a likelihood that the modified source image is color-matched with the reference image. The modified source image may be outputted as a shot-match with the reference image in response to determining, using the discriminator model, that the modified source image and the reference image are color-matched.

Enhanced video shot matching using generative adversarial networks

Disclosed systems and methods use machine-learning techniques to determine a set of parameters that if applied to a target video, apply a color characteristic of a reference video to the target video. For example, a color consistency application executing on a computing device computes a feature vector including a representation of a reference video and a target video. The application determines a set of color parameters (e.g., exposure, color temperature, tint, etc.) by applying the feature vector to one or more predictive models trained to determine color consistency. The application generates a preview image by applying the parameters to the target video. The applying causes an adjustment of exposure, color temperature, or tint in the target video such that a color consistency of the adjusted target video is consistent with a color consistency of the reference video. The color consistency application provides settings to further adjust the parameters.

Growing community of inventors

New Delhi, India

Chetan Nanda