Date & Time: 

2023 / 04 / 21 (Fri) 14:20 - 16:20

Location: 

Delta Building R216, NTHU

Speaker: 

 劉育綸 教授

國立陽明交通大學 資訊工程學系

Topic: 

Dynamic and Local Radiance Fields for Robust View Synthesis

Abstract: 

NeRF is an emerging technique to synthesize novel views. However, current approaches cannot deal with casually-captured videos which lack accurate camera poses and contain dynamic objects. Therefore, we propose dynamic robust radiance fields with sophisticated designs to tackle this challenging task. Additionally, we present local radiance fields and progressive optimization to handle long videos. Thorough experimental results demonstrate the superior performance of our approaches over existing methods.

Biography: 

Dr. Yu-Lun Liu is an Assistant Professor in the Department of Computer Science at National Yang Ming Chiao Tung University. Dr. Liu works on image/video processing, computer vision, and computational photography, particularly on essential problems requiring machine learning with insights from geometry and domain-specific knowledge. From 2014 to 2022, Dr. Liu was an algorithm development engineer at MediaTek Inc. and joined Meta Reality Labs Research as a Research Scientist Intern in 2022. Dr. Liu received his Ph.D. from National Taiwan University, where he was advised by Yung-Yu Chuang. Dr. Liu did his undergrad and master's at National Chiao Tung University, where he worked with Hsueh-Ming Hang.