公开(公告)号：US20230093734A1

公开(公告)日：2023-03-23

申请号：US17802775

申请日：2021-02-21

Applicant: Microsoft Technology Licensing, LLC

Inventor： Shuxin Zheng ,  Chang Liu ,  Di He ,  Guolin Ke ,  Yatao Li ,  Jiang Bian ,  Tie-Yan Liu

IPC: G06T3/40

Abstract: According to implementations of the subject matter described herein, a solution for image rescaling is proposed. According to the solution, an input image of a first resolution is obtained. An output image of a second resolution and high-frequency information following a predetermined distribution are generated based on the input image by using a trained invertible neural network, where the first resolution exceeds the second resolution. Besides, a further input image of the second resolution is obtained. A further output image of the first resolution is generated based on the further input image and high-frequency information following the predetermined distribution by using an inverse network of the invertible neural network. This solution can downscale an original image into a visually-pleasing low-resolution image with the same semantics and also can reconstruct a high-resolution image of high quality from a low-resolution image.

公开(公告)号：US20230206396A1

公开(公告)日：2023-06-29

申请号：US17927863

申请日：2021-05-10

Applicant: Microsoft Technology Licensing, LLC

Inventor： Shuxin Zheng ,  Chang Liu ,  Di He ,  Guolin Ke ,  Jiang Bian ,  Tie-Yan Liu

IPC: G06T3/40

CPC classification number: G06T3/4053 ,  G06T3/4046

Abstract: According to implementations of the subject matter described herein, a solution is proposed for super-resolution image reconstructing. According to the solution, an input image with first resolution is obtained. An invertible neural network is trained using the input image, wherein the invertible neural network is configured to generate an intermediate image with second resolution and first high-frequency information based on the input image, the second resolution being lower than the first resolution. Subsequently, an output image with third resolution is generated based on the input image and second high-frequency information by using an inverse network of the trained invertible neural network, the second high-frequency information conforming to a predetermined distribution, and the third resolution being higher than the first resolution. The solution can effectively process a low-resolution image obtained by an unknown downsampling method, thereby obtaining a high-quality and high-resolution image.

公开(公告)号：US11544561B2

公开(公告)日：2023-01-03

申请号：US16875782

申请日：2020-05-15

Applicant: Microsoft Technology Licensing, LLC

Inventor： Gaurav Mittal ,  Victor Manuel Fragoso Rojas ,  Nikolaos Karianakis ,  Mei Chen ,  Chang Liu

IPC: G06N3/08 ,  G06K9/62

Abstract: Providing a task-aware recommendation of hyperparameter configurations for a neural network architecture. First, a joint space of tasks and hyperparameter configurations are constructed using a plurality of tasks (each of which corresponds to a dataset) and a plurality of hyperparameter configurations. The joint space is used as training data to train and optimize a performance prediction network, such that for a given unseen task corresponding to one of the plurality of tasks and a given hyperparameter configuration corresponding to one of the plurality of hyperparameter configurations, the performance prediction network is configured to predict performance that is to be achieved for the unseen task using the hyperparameter configuration.