Deep Learning for Panoramic Vision on Mobile Devices
In the last few years, remarkable progress was made with mobile consumer devices. Modern smartphones and tablet computers offer multi-core processors and graphics processing cores which open up new application possibilities such as deep learning-based computer vision tasks.
Deep learning has received much attention from the communities of computer vision and computer graphics due to its excellent representativeness for images. With the development of deep learning theory and technology, the performance of computer vision algorithms including object detection and tracking, face recognition, and 3D reconstruction have made tremendous progress. However, computer vision technology relies on the valid information from the input image and video, and the performance of the algorithm is essentially constrained by the quality of source image/video.
Panorama plays important role in capturing large-scale dynamic scenes for both macro and micro domains. Benefited from the recent progress of panoramic cameras, the capture of panoramic image/video becomes more and more convenient. In particular, along with the emergence of panoramic image/video, the corresponding computer vision tasks remain unsolved, due to the extremely high-resolution, large-scale, huge-data that induced by the panoramic camera. Moreover, with development of mobile devices (mobile phones with GPU), their computing power become more and more powerful. However, the research computer vision technology on mobile devices is relatively backward, especially panorama-based computer vision technology.
As a result, the recent diffusion of deep learning and the development of modern mobile devices have encouraged computer vision community to explore new solutions for panorama-based computer vision tasks on mobile devices. This special session aims to bring the latest results over advanced deep learning techniques for panoramic vision on mobile devices. It can help technicians to exchange the latest technical progresses.
Topics include, but are not limited to:
Deep learning on mobile devices
Feature tracking for panoramic image
Panorama-based visual tracking on mobile devices
Depth-map estimation on mobile devices
Real-time object detection for panorama on mobile devices
Deep learning-based surface reconstruction on mobile devices
Panorama-based virtual reality for mobile devices
Panorama construction on mobile devices
Submission deadline: August 1, 2020
First notification: October 20, 2020
Revised Manuscript: December 20, 2020
Final notification: February 10, 2021
Dr. Zhihan Lv
Professor, Qingdao University, China
Professor, Polytechnic University of Valencia, Spain.
Assistant Professor, Embry-Riddle Aeronautical University, USA.