A Flexible Neural Renderer for Material Visualization

Speaker(s): Aakash KT, International Institute of Information Technology, Hyderabad, India
Parikshit Sakurikar, International Institute of Information Technology, Hyderabad; DreamVu Inc., India
Saurabh Saini, International Institute of Information Technology, Hyderabad, India
P. J. Narayanan, International Institute of Information Technology, Hyderabad, India

I am currently a MS by research student at Computer Vision Lab (CVIT), which is where I completed my BTech in Computer Science Engineering. My research advisor is Dr. PJ Narayanan. My research involves playing around with the light transport equation, in combination with machine learning (in other words, I work on Computer Vision/Computer Graphics).

I am currently a Ph.D. candidate at the Center for Visual Information Technology at IIIT-Hyderabad. I work with Prof. P. J. Narayanan on topics related to Computational Photography and Machine Learning. My main area of research is Epsilon Focus Photography, which deals with capturing and processing multi-focus images, depth from focus, measurement of focus/defocus-blur and post-capture control of depth-of-field. I am also broadly interested in Computer Vision, Computer Graphics and High Performance Computing.

I am a Ph.D. student under the guidance of Prof. P. J. Narayanan in Center for Visual Information Technology (CVIT) lab, a part of Kohli Center on Intelligent Systems (KCIS), at the International Institute of Information Technology-Hyderabad (IIIT-H) India. My general research interest is in the topics related to Computer Vision, Machine Learning and Optimization, especially applied to 2D or 3D reconstruction. Currently I am working on Inverse Rendering and Inverse Light Transport problems. Specifically, I am focusing on Intrinsic Image Decomposition (separating object property based vs. light related components in an image).

I am a Professor and currently the Director of IIIT, Hyderabad. My research interests include Computer Vision, Computer Graphics, and Parallel Computing.

Description: We propose a convolutional neural network which generates high-quality ray-traced material visualizations on a shaderball, to aid material synthesis and editing.

Binary Space Partitioning Visibility Tree for Polygonal Light Rendering

Speaker(s): Hiroki Okuno, Wakayama University, Japan
Kei Iwasaki, Wakayama University, Prometech CG Research, Japan

Hiroki Okuno received his B.S. degree from Wakayama University in 2018. He is currently an M.S. student at Wakayama University.

Kei Iwasaki received his B.S., M.S., and Ph. D. degrees from the University of Tokyo, in 1999, 2001, and 2004, respectively. He is currently an associate professor at Wakayama University.

Description: We propose a method to render shadows for physically-based materials under polygonal area light sources.

Ray Guiding for Production Lightmap Baking

Speaker(s): Ari Silvennoinen, Activision, United States of America

Ari Silvennoinen is a Senior Technical Director at Activision, where he works on graphics technology research and development. Prior to joining Activision, he obtained a master’s degree from the University of Helsinki and worked on graphics technology at Umbra Software and Remedy Entertainment. His main interests are in global illumination, visibility algorithms and real-time rendering and he has contributions in graphics conferences and journals, including SIGGRAPH, I3D, CGF and EGSR.

Description: We present a ray guiding technique for improving the computation times in the context of production lightmap baking. Compared to state-of-the-art, our method has better scalability and lower variance.

Real-time Rendering of Layered Materials with Anisotropic Normal Distributions

Speaker(s): Tomoya Yamaguchi, Waseda University, Japan
Tatsuya Yatagawa, The University of Tokyo, Japan
Yusuke Tokuyoshi, SQUARE ENIX CO., LTD.; Intel Corporation, Japan
Shigeo Morishima, Waseda University, Japan

Tomoya Yamaguchi is a master's student at Graduate School of Advanced Science and Engineering, Waseda University. He received his Bachelor of Engineering from Waseda University in 2018. His research interests include light transport algorithms and real-time rendering.

Tatsuya Yatagawa is an assistant professor at School of Engineering, the University of Tokyo. He received his Bachelor of Science from Kyoto University in 2010 and received his Ph.D. of Science from the University of Tokyo in 2015. His research interests center on computer graphics and computer vision, including efficient rendering, inverse rendering, and image editing techniques.

Yusuke Tokuyoshi is a research scientist at Intel Corporation (from September 2019). Before joining Intel, he engaged in R&D on rendering as a senior researcher at SQUARED ENIX CO., LTD. He received his Ph.D in engineering from Shinshu University in 2007. From 2007 to 2010, he worked at Hitachi, Ltd. for R&D on compiler optimization. His interests include global illumination algorithms and real-time rendering.

Dr. Shigeo Morishima received B.S., M.S. and Ph.D. degrees in Electrical Engineering from University of Tokyo in 1982, 1984, and 1987, respectively. Currently, he is a professor of School of Advanced Science and Engineering, Waseda University. His research interests include Computer Graphics, Computer Vision and Human Computer Interaction. He is a trustee of Japanese Academy of Facial Studies and a fellow of the Institute of Image Electronics Engineers of Japan.　He was a general chair of ACM VRST 2018 and was VR/AR adviser of SIGGRAPH ASIA 2018. His paper was nominated as a best paper award finalist of CVPR 2019.

Description: We propose a light-weight rendering method for layered materials with anisotropic normal distributions defined on tangent vector fields differing from layer to layer.