The Surprisal Autoencoder: A Distortion-Constrained Stochastic Autoencoder for Estimating Shannon Information of an Image
William R. Mark, Ryan Ehrlich, Andrey Zhmoginov, David Minnen
Google internal technical report, April 2024
Dislosed to public on March 12, 2026 via US Patent Application 19/186,201 and US Provisional Patent Application 63/637,328.
To obtain a copy, click here, login to uspto.gov, and download APPENDIX.SUPP (You may need to create an account on uspto.gov)
This report describes a neural compression autoencoder for images
that targets a particular distortion for each image,
via constrained
optimization. The technique can also serve as a density estimation
technique.
Combining Single and Packet Ray Tracing for Arbitrary Ray Distributions on the Intel MIC Architecture
(preprint, differently formatted)
Carsten Benthin, Ingo Wald, Sven Woop, Manfred Ernst, William R. Mark
IEEE Transactions on Visualization and Computer Graphics, 2012
State of the Art in Ray Tracing Animated Scenes
Ingo Wald, William R. Mark, Johannes Gunther, Solomon Boulos, Thiago
Ize, Warren Hunt, Steven G. Parker, and Peter Shirley
Eurographics 2007 State of the Art Report, Sept. 2007
Universal Mechanisms for Data-Parallel Architectures
Karthikeyan Sankaralingam, Stephen W. Keckler, William R. Mark and Doug Burger
Proceedings of the 36th Annual International Symposium on Microarchitecture (MICRO 2003).
Razor: An Architecture for Dynamic Multiresolution Ray Tracing
Peter Djeu, Warren Hunt, Rui Wang, Ikrima Elhassan, Gordon Stoll, William R. Mark
The University of Texas at Austin, Department of Computer Sciences.
Technical Report TR-07-52, January 24, 2007.
Real-Time Rendering Systems in 2010
William R. Mark and Donald Fussell,
The University of Texas at Austin, Department of Computer Sciences.
Technical Report TR-05-18, May 2, 2005.
UNC-CH Force Feedback Library, Revision C,
William R. Mark, Scott C. Randolph, Mark Finch, and James M. Van Verth,
UNC-CH Computer Science Technical Report TR96-012, January 30, 1996.