Yebin Liu received the B.E. degree from Beijing University of Posts and Telecommunications, Beijing, China in 2002, and the Ph.D degrees in Automation Department, Tsinghua University, Beijing, China, in 2009. He is currently a postdoctoral researcher at Automation Department, Tsinghua University, Beijing, China. His research interests include light field, image based modeling and rendering, multi-camera array techniques. He has developed the first multi-camera and multi-lighting dome in China and was awarded the national prize of Technological Invention (Second Prize) in 2008.

AG 4, MMCI   Info

AG Audience

English

45 Minutes

Saarbrücken

Images of object filmed under multiple temporal instants, multiple lights, and multiple viewpoints constitute the visual filed of the object. How to fuse the available images for high fidelity 3D reconstruction and other vision enhancement applications is crucial for computer vision and computer graphics researches. This fusion problem covers lots of hot topics in state-of-the-art research, such as multi-view stereo, photometric stereo, image based relighting, performance capture and animation, structure from motion, etc. To help the understanding of the base mechanisms behind this complicate fusion problem, a multi-camera and multi-lighting dome is developed in Tsinghua University, China. The talk begins from this dome and includes the following contents:



* Multi-camera and multi-lighting (MVML) dome
The MVML dome is composed of 40 cameras and 31 light sources. Such a dome can be regarded as a combination of 3D production stereo and light stage. The goals, the design and the future of this dome will be introduced.

* Continuous depth map based multi-view stereo (CMVS)
CMVS is a new multi-view stereo technique for 3D reconstruction under sparse multi-view images. CMVS is robust, and achieves the most accurate reconstruction results for geometry details such as wrinkles on the cloth.

* Multi-view photometric stereo (MPS) for free-viewpoint video
An MPS algorithm is designed aiming at 3D reconstruction for the MVML datasets. Compared with the MVS algorithm using only the multi-view images captured under constant lights, MPS takes advantages of lighting information and improves reconstruction accuracy and robustness.

* Future works
At last, the talk will introduce the basic idea for fusion the images captured under this MVML dome with multiple temporal instants, multiple lights, and multiple viewpoints for high accurate motion, geometry reconstruction and appearance relighting.

Thorsten Thormählen (Christian Theobalt)

+49 681 9325-417

--email hidden

passcode not visible

logged in users only