High-Performance and Tunable Stereo Reconstruction

TL;DR

This paper introduces a fast, tunable stereo disparity estimation method capable of real-time performance at 120Hz on a CPU, suitable for high-speed robotic applications requiring quick environment reconstruction.

Contribution

A novel stereo disparity algorithm that iteratively approximates scene depth using a piece-wise planar mesh, optimized for high-speed, tunable performance on CPU.

Findings

Achieves 120Hz frame-rate at VGA resolution on a single CPU thread.

Provides a tunable trade-off between reconstruction quality and runtime.

Enables rapid environment reconstruction for high-speed robotic maneuvering.

Abstract

Traditional stereo algorithms have focused their efforts on reconstruction quality and have largely avoided prioritizing for run time performance. Robots, on the other hand, require quick maneuverability and effective computation to observe its immediate environment and perform tasks within it. In this work, we propose a high-performance and tunable stereo disparity estimation method, with a peak frame-rate of 120Hz (VGA resolution, on a single CPU-thread), that can potentially enable robots to quickly reconstruct their immediate surroundings and maneuver at high-speeds. Our key contribution is a disparity estimation algorithm that iteratively approximates the scene depth via a piece-wise planar mesh from stereo imagery, with a fast depth validation step for semi-dense reconstruction. The mesh is initially seeded with sparsely matched keypoints, and is recursively tessellated and refined as needed (via a resampling stage), to provide the desired stereo disparity accuracy. The inherent simplicity and speed of our approach, with the ability to tune it to a desired reconstruction quality and runtime performance makes it a compelling solution for applications in high-speed vehicles.