SPS Webinar, 2 August 2021: Learning a Convolutional Neural Network for Image Compact-Resolution
Upcoming SPS Webinar
Title: Learning a Convolutional Neural Network for Image Compact-Resolution
Date: 2 August 2021
Time: 9:00 AM ET (New York time)
Duration: Approximately 1 Hour
Presenters: Dr. Yue Li
Based on the IEEE Xplore® article: Learning a Convolutional Neural Network for Image Compact-Resolution
Published: IEEE Transactions on Image Processing, September 2018
Download: Original article will be made freely available for download for 48 hours from the day of the webinar, on IEEE Xplore®
About the topic:
We study the dual problem of image super-resolution (SR), which we term image compact-resolution (CR). Opposite to image SR that hallucinates a visually plausible high-resolution image given a low-resolution input, image CR provides a low-resolution version of a high-resolution image, such that the low-resolution version is both visually pleasing and as informative as possible compared to the high-resolution image. We propose a convolutional neural network (CNN) for image CR, namely, CNN-CR, inspired by the great success of CNN for image SR. Specifically, we translate the requirements of image CR into operable optimization targets for training CNN-CR: the visual quality of the compact resolved image is ensured by constraining its difference from a naively downsampled version and the information loss of image CR is measured by upsampling/super-resolving the compact-resolved image and comparing that to the original image. Accordingly, CNN-CR can be trained either separately or jointly with a CNN for image SR.
We explore different training strategies as well as different network structures for CNN-CR. Our experimental results show that the proposed CNN-CR clearly outperforms simple bicubic downsampling and achieves on average 2.25 dB improvement in terms of the reconstruction quality on a large collection of natural images. We further investigate two applications of image CR, i.e., low-bit-rate image compression and image retargeting. Experimental results show that the proposed CNN-CR helps achieve significant bits saving than High Efficiency Video Coding when applied to image compression and produce visually pleasing results when applied to image retargeting.
About the presenter:
Dr. Yue Li received the B.S. and Ph.D. degrees in electronic engineering from the University of Science and Technology of China, Hefei, China, in 2014 and 2019, respectively.
Dr. Yue Li is currently a research scientist with Bytedance Multimedia Lab in San Diego, CA, USA. His research interests include image/video coding and processing.
