Technical Communications

Q&A for DMCR-GAN: Adversarial Denoising for Monte Carlo Renderings with Residual Attention Networks and Hierarchical Features Modulation of Auxiliary Buffers

Abstract: We propose an adversarial approach for denoising Monte Carlo renderings (DMCR-GAN) with residual attention networks and hierarchical features modulation of auxiliary buffers.

Author(s)/Presenter(s):
YiFan Lu, Center for Future Media, University of Electronic Science and Technology of China, China
Ning Xie, Center for Future Media, University of Electronic Science and Technology of China, China
Heng Tao Shen, Center for Future Media, University of Electronic Science and Technology of China, China

Q&A for Learning Illumination from Diverse Portraits

Abstract: We present a state-of-the-art method to estimate HDR, omnidirectional illumination from a single portrait image, essentially using faces as light probes while resolving the illumination/reflectance ambiguity across diverse skin tones.

Author(s)/Presenter(s):
Chloe LeGendre, Google Research, United States of America
Wan-Chun Ma, Google Inc., United States of America
Rohit Pandey, Google Inc., United States of America
Sean Fanello, Google Inc., United States of America
Christoph Rhemann, Google Inc., United States of America
Jason Dourgarian, Google Inc., United States of America
Jay Busch, Google Inc., United States of America
Paul Debevec, Google Research, United States of America

Q&A for PoseFromGraph: Compact 3-D Pose Estimation using Graphs

Abstract: PoseFromGraph, a light weight pose estimation framework suitable for AR. Our compact graph representations facilitate efficient and category-agnostic pose estimation with reduction in time & memory footprint by 4x.

Author(s)/Presenter(s):
Meghal Dani, TCS Research, India
Additya Popli, IIIT Hyderabad, India
Ramya Hebbalaguppe, TCS Research, India

Back