Seminar Series:  3D Face Modeling From A Single RGB Image
Speaker: Tran Tuan Anh - Research Scientist, VinAI Research
Date: Saturday, September 21st, 2019
Location: COGO Co-Working Space, 4th Floor, Sun Grand City Ancora Residence, No.3 Luong Yen Street, Hai Ba Trung District, Hanoi

---
About the Speaker:

Anh Tran is a Research Scientist in VinAI. Prior to VinAI, he was an Applied Scientist at Amazon Rekognition, working on facial image processing APIs. He received Bachelor of Engineering from the Hanoi University of Science and Technology in 2010 and a Ph.D. in Computer Science from University of Southern California in 2017, working with Professor Gerard Medioni. His research interests are in computer vision, particularly in facial image analysis. He has received several honors including Vietnam Talents 2010, Imagine Cup Vietnam 2009, and Vietnam Education Foundation fellowship 2012.  

Abstract:

Estimating 3D face shapes from single images is a problem with a history now spanning two decades. Despite many efforts, classical methods could successfully recover 3D face only under limited conditions. Rebuilding face structure in-the-wild, with a wide range of head orientations, facial expressions, lighting conditions, and the appearance of occlusion, is a challenging problem. Similar to other topics, this research is experiencing rapid growth thanks to deep learning. In this seminar, we will review recent techniques in solving this problem from coarse to fine-grain reconstruction.