GPI Seminar Series: Manel Baradad (May 31st, 2018)
Manel Baradad, PhD candidate at Computer Science and Artificial Intelligence Laboratory (CSAIL), MIT |
Manel Baradad presents the work resulting from his master MET thesis at MIT, which will be presented at CVPR 2018 next June in Salt Lake City.
Abstract: We present a method for inferring a 4D light field of a hidden scene from 2D shadows cast by a known occluder on a diffuse wall. We do this by determining how light naturally reflected off surfaces in the hidden scene interacts with the occluder. By modeling the light transport as a linear system, and incorporating prior knowledge about
light field structures, we can invert the system to recover the hidden scene. We demonstrate results of our inference method across simulations and experiments with different types of occluders. For instance, using the shadow cast by a real house plant, we are able to recover low resolution light fields with different levels of texture and parallax complexity. We provide two experimental results: a human subject and two planar elements at different depths.
CVPR 2018 authors: Manel Baradad; Vickie Ye; Adam B. Yedidia; Frédo Durand; William T. Freeman; Gregory W. Wornell; Antonio Torralba
Short Bio: Manel Baradad completed his Bachelor's and Master's degrees at TelecomBCN, conducting his Master's thesis at CSAIL (MIT), under the supervision of professor Antonio Torralba. He will join CSAIL as a graduate student this fall.