人工智能
计算机科学
图像缩放
插值(计算机图形学)
棱锥(几何)
特征(语言学)
计算机视觉
图像分辨率
图像(数学)
特征提取
播种
图像处理
模式识别(心理学)
比例(比率)
数学
工程类
哲学
航空航天工程
物理
量子力学
语言学
几何学
作者
Jiahuan Ji,Baojiang Zhong,Kai-Kuang Ma
出处
期刊:IEEE transactions on image processing
[Institute of Electrical and Electronics Engineers]
日期:2020-01-01
卷期号:29: 9413-9428
被引量:9
标识
DOI:10.1109/tip.2020.3026632
摘要
A new multi-scale deep learning (MDL) framework is proposed and exploited for conducting image interpolation in this paper. The core of the framework is a seeding network that needs to be designed for the targeted task. For image interpolation, a novel attention-aware inception network (AIN) is developed as the seeding network; it has two key stages: 1) feature extraction based on the low-resolution input image; and 2) feature-to-image mapping to enlarge image's size or resolution. Note that the designed seeding network, AIN, needs to be trained with a matched training dataset at each scale. For that, multi-scale image patches are generated using our proposed pyramid cut, which outperforms the conventional image pyramid method by completely avoiding aliasing issue. After training, the trained AINs are then combined for processing the input image in the testing stage. Extensive experimental simulation results obtained from seven image datasets (comprising 359 images in total) have clearly shown that the proposed MAIN consistently delivers highly accurate interpolated images.
科研通智能强力驱动
Strongly Powered by AbleSci AI