Brightening the Optical Flow through Posit Arithmetic

TL;DR

This paper investigates the use of posit arithmetic in optical flow estimation, demonstrating lower error rates and proposing hardware integration for future platforms, thereby highlighting the potential advantages of posit formats over traditional floating-point.

Contribution

The paper provides the first extensive empirical comparison of posit versus IEEE float arithmetic in optical flow estimation and discusses hardware integration of posit units in RISC-V platforms.

Findings

Posit arithmetic reduces average error in optical flow estimation by an order of magnitude.

Empirical analysis using SoftPosit shows significant accuracy improvements over SoftFloat.

Hardware implementation of posit units in RISC-V is feasible and beneficial for future systems.

Abstract

As new technologies are invented, their commercial viability needs to be carefully examined along with their technical merits and demerits. The posit data format, proposed as a drop-in replacement for IEEE 754 float format, is one such invention that requires extensive theoretical and experimental study to identify products that can benefit from the advantages of posits for specific market segments. In this paper, we present an extensive empirical study of posit-based arithmetic vis-\`a-vis IEEE 754 compliant arithmetic for the optical flow estimation method called Lucas-Kanade (LuKa). First, we use SoftPosit and SoftFloat format emulators to perform an empirical error analysis of the LuKa method. Our study shows that the average error in LuKa with SoftPosit is an order of magnitude lower than LuKa with SoftFloat. We then present the integration of the hardware implementation of a posit adder and multiplier in a RISC-V open-source platform. We make several recommendations, along with the analysis of LuKa in the RISC-V context, for future generation platforms incorporating posit arithmetic units.