A Practical Stereo Depth System for Smart Glasses

TL;DR

This paper introduces a practical, on-device stereo depth sensing system for smart glasses that combines pre-processing, rectification, and depth estimation with fallback mechanisms, enabling real-time 3D effects on mobile hardware.

Contribution

It presents a comprehensive, production-ready stereo depth system optimized for mobile devices, with robustness to calibration changes and input variability, suitable for smart glasses applications.

Findings

Runs in under 1 second on a six-year-old smartphone CPU

Generalizes well to unseen data and real-world images

Achieves good accuracy on Middlebury and in-the-wild images

Abstract

We present the design of a productionized end-to-end stereo depth sensing system that does pre-processing, online stereo rectification, and stereo depth estimation with a fallback to monocular depth estimation when rectification is unreliable. The output of our depth sensing system is then used in a novel view generation pipeline to create 3D computational photography effects using point-of-view images captured by smart glasses. All these steps are executed on-device on the stringent compute budget of a mobile phone, and because we expect the users can use a wide range of smartphones, our design needs to be general and cannot be dependent on a particular hardware or ML accelerator such as a smartphone GPU. Although each of these steps is well studied, a description of a practical system is still lacking. For such a system, all these steps need to work in tandem with one another and fallback gracefully on failures within the system or less than ideal input data. We show how we handle unforeseen changes to calibration, e.g., due to heat, robustly support depth estimation in the wild, and still abide by the memory and latency constraints required for a smooth user experience. We show that our trained models are fast, and run in less than 1s on a six-year-old Samsung Galaxy S8 phone's CPU. Our models generalize well to unseen data and achieve good results on Middlebury and in-the-wild images captured from the smart glasses.