中法信息、自动化与应用数学联合实验室(LIAMA)是中国科学院自动化研究所与法国国家信息与自动化研究院(INRIA)于1997年1月共同建立的联合实验室，2008年被授予国家级国际合作研究中心，是模式识别国家重点实验室(NLPR)的组成部分。中法实验室现因科研工作需要，目前面向各高校招收访问学生，要求能够稳定工作半年以上，由中法双方研究员共同指导。课题组将按照本所研究生的标准提供实习津贴和奖金，表现优异的同学可获得赴法交流的机会，若在高水平国际会议上发表论文课题组也将提供出国费用。
有意向的同学请将简历发送至wmdong@liama.ia.ac.cn和xmei@nlpr.ia.ac.cn，若曾经发表过学术论文也请选择1-2篇随简历发送。
相关要求和项目信息描述见下方。
Requirements:
1. Major in computer science (not a must).
2. The applicants should have basic knowledge in at least one of the following areas: image & video processing /computer vision/computer graphics.
3. The applicants should be familiar with C or C++. Experience with OpenCV or CUDA would be a big plus.
Project 1: 2D-3D Video Conversion
We aim at developing new tools which converts traditional 2D images and video clips into 3D ready materials. The tools will be tested by artists in film production. So this thing is for real. The problems to be tackled:
(1) Depth maps generation
(2) Depth image based rendering
(3) Temporal coherence for videos
(4) Subjective evaluation
(5) Computation acceleration
Project 2: Multi-view reconstruction
We aim at developing new methods to reconstruct dense depth maps and water-tight 3D mesh models with multiple images or views. Both matching accuracy and computation efficiency are concerns for this project.
Project 3: Content-aware image/video synthesis and analysis
Image synthesis is a hot topic in computer graphics and image processing. It is a very effective way in image acquisition and editing. Image synthesis can be used in graphic design, movie post-processing, realistic rendering and many other applications. In this context, the goal of this project is to develop new image synthesis methods, by analyzing the content of the source image (color, lighting, texture and other necessary features), which should be integrated into energy functions. Optimization algorithm will be constructed by studying the connections between image content analysis and the synthesis process. Different algorithms will be studied according to the specific visual effects. The problem will be studied under different directions:
1) Content-aware image/video compositing;
2) Image/video appearance transfer and enhancement;
3) Painterly stylization of images and videos.
Advisors
Prof. Xiaopeng Zhang
LIAMA-NLPR, CAS Institute of Automation
Dr. Xing Mei
LIAMA-NLPR, CAS Institute of Automation
Dr. Weiming Dong
LIAMA-NLPR, CAS Institute of Automation
Prof. Jean-Claude Paul
INRIA, France
--
FROM 159.226.21.*