Title： Deep View Morphing

Speaker：Dinghuang Ji, UNC Chapel Hill

Time： 15:00, October 9, 2017

Venue：Middle Meeting Room, Floor 4, Building 5, Institute of Software, Chinese Academy of Sciences

(中科院軟件研究所5號樓4層中會議室)

 

Abstract

Recently, convolutional neural networks (CNN) have been successfully applied to view synthesis problems. However, such CNN-based methods can suffer from lack of texture details, shape distortions, or high computational complexity. In this paper, we propose a novel CNN architecture for view synthesis called "Deep View Morphing" that does not suffer from these issues. To synthesize a middle view of two input images, a rectification network first rectifies the two input images. An encoder-decoder network then generates dense correspondences between the rectified images and blending masks to predict the visibility of pixels of the rectified images in the middle view. A view morphing network finally synthesizes the middle view using the dense correspondences and blending masks. We experimentally show the proposed method significantly outperforms the state-of-the-art CNN-based view synthesis method.

 

Bio

Dinghuang Ji received the BE degree in computer science from the University of Science and Technology of China in 2009, and the MS degree in computer science from the Institute of Computing Technology CAS in 2013. He defended his PhD thesis in 2017 summer with Department of Computer Science at UNC Chapel Hill. His research interests include 3D computer vision, image processing and machine learning.

 

All are welcome!