2/4/2025 | 3:30 PM - 5:30 PM | Regency A

Temporal architectures for vision sensor processing

Author(s)

Ryan Hou | University of Michigan
Thomas Twomey
Vasileios Milionis
Georgios Tzimpragos | University of Wisconsin-Madison

Abstract

Binary representation and Boolean logic have long been the standard for general-purpose computing and storage, but it remains unclear if they are always the optimal choice. We posit that digital temporal codes, combined with a new class of temporal logic, present a unique advantage for near- and in-sensor processing. Temporal codes use time as a resource, encoding data values as delays in discrete voltage transitions, while logic is performed by engineering "race" conditions among these transitions. This approach addresses the scalability and noise issues of pure analog systems, as well as the costly analog-to-digital conversions and limited innovation space of traditional digital systems, all while maintaining full compatibility with off-the-shelf CMOS components for enhanced practicality. Building on our previous work, which demonstrated that temporal XGBoost accelerators achieved orders-of-magnitude improvements in energy-delay product over state-of-the-art solutions, in this talk, we will discuss how temporal computing can bring similar benefits to vision sensor interfaces, with extensions to VIO/SLAM pipelines.