Adobe, Inc.

Ideal Power Inc.

Yifan Jiang

Zhe Lin

Jianming Zhang

Kalyan Krishna Sunkavalli

Sohrab Amirghodsi

Yilin Wang

Sarah Kong

He Zhang

Su Chen

Jiankang Bu

Ruiyang Yu

Mudit Khanna

R Daniel Brdar

Unidirectional hybrid switch. At least one example is a method operating a hybrid switch, the method comprising: sensing a voltage across an upper terminal and a lower terminal of the hybrid switch, the hybrid switch is forward biased when the upper terminal has higher voltage, and the hybrid switch is reverse biased when the lower terminal has higher voltage; when the hybrid switch is forward biased, selectively conducting a forward current from the upper terminal to the lower terminal by sharing the forward current between a FET switch and a BJT switch, the selectively conducting when a control terminal is asserted; and when the hybrid switch is reversed biased, non-selectively conducting a reverse current from the lower terminal to the upper terminal.

Unidirectional hybrid switch circuit

The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately, efficiently, and flexibly generating harmonized digital images utilizing a self-supervised image harmonization neural network. In particular, the disclosed systems can implement, and learn parameters for, a self-supervised image harmonization neural network to extract content from one digital image (disentangled from its appearance) and appearance from another from another digital image (disentangled from its content). For example, the disclosed systems can utilize a dual data augmentation method to generate diverse triplets for parameter learning (including input digital images, reference digital images, and pseudo ground truth digital images), via cropping a digital image with perturbations using three-dimensional color lookup tables ('LUTs'). Additionally, the disclosed systems can utilize the self-supervised image harmonization neural network to generate harmonized digital images that depict content from one digital image having the appearance of another digital image.

Learning parameters for an image harmonization neural network to generate deep harmonized digital images

Generating deep harmonized digital images

Growing community of inventors

Austin, TX, United States of America

Yifan Jiang