Invention Grant
- Patent Title: Techniques to use a neural network to expand an image
-
Application No.: US16813589Application Date: 2020-03-09
-
Publication No.: US12340484B2Publication Date: 2025-06-24
- Inventor: Guilin Liu , Andrew Tao , Bryan Christopher Catanzaro , Ting-Chun Wang , Zhiding Yu , Shiqiu Liu , Fitsum Reda , Karan Sapra , Brandon Rowlett
- Applicant: NVIDIA Corporation
- Applicant Address: US CA Santa Clara
- Assignee: NVIDIA Corporation
- Current Assignee: NVIDIA Corporation
- Current Assignee Address: US CA Santa Clara
- Agency: Davis Wright Tremaine LLP
- Main IPC: G06T3/00
- IPC: G06T3/00 ; G06N3/08 ; G06T3/4038 ; G06T3/4046 ; G06T7/40 ; G06V10/44 ; G06V10/54 ; G06V10/776 ; G06V10/82

Abstract:
Apparatuses, systems, and techniques for texture synthesis from small input textures in images using convolutional neural networks. In at least one embodiment, one or more convolutional layers are used in conjunction with one or more transposed convolution operations to generate a large textured output image from a small input textured image while preserving global features and texture, according to various novel techniques described herein.
Public/Granted literature
- US20210279841A1 TECHNIQUES TO USE A NEURAL NETWORK TO EXPAND AN IMAGE Public/Granted day:2021-09-09
Information query
IPC分类:
G | 物理 |
G06 | 计算;推算或计数 |
G06T | 一般的图像数据处理或产生 |
G06T3/00 | 在图像平面内的图形图像转换 |