Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model
Yuming Du, Robin Kips, Albert Pumarola, Sebastian Starke, Ali Thabet, Artsiom Sanakoyeu
This paper explores advancements in the open-source library, Private Computation Framework, that significantly improve the resource usage and application development lifecycle of Multi-Party Compute applications. First we elaborate on the architecture of Private Computation Framework. We then discuss implementation XOR Secret-Sharing-Based MPC protocols and how it improves upon previous usage of Garbled Circuits, to provide the same privacy guarantees while significantly reducing network usage. The paper also explores new standard libraries provided by the framework, additional optimizations in the latest release of Private Computation Framework, and future development opportunities.
Project page available here: https://github.com/facebookresearch/fbpcf.
Yuming Du, Robin Kips, Albert Pumarola, Sebastian Starke, Ali Thabet, Artsiom Sanakoyeu
Lisa Rivalin, Andrew Grier, Tobias Tiecke, Chi Zhou, Doris Gao, Prakriti Choudhury, John Fabian
Shreshth Tuli, Kinga Bojarczuk, Natalija Gucevska, Mark Harman, Xiao-Yu Wang, Graham Wright