Robust Uncalibrated Stereo Rectification with Constrained Geometric Distortions (USR-CGD)

TL;DR

This paper introduces USR-CGD, a new uncalibrated stereo rectification algorithm that minimizes geometric distortions while keeping rectification errors low, outperforming existing methods through constrained optimization.

Contribution

The paper proposes a novel homography parameterization and a constrained adaptive optimization scheme to reduce geometric distortions in uncalibrated stereo rectification.

Findings

USRCGD significantly reduces geometric distortions compared to existing algorithms.

The method maintains low rectification errors while optimizing for geometric fidelity.

Experimental results demonstrate superior performance of USR-CGD across various datasets.

Abstract

A novel algorithm for uncalibrated stereo image-pair rectification under the constraint of geometric distortion, called USR-CGD, is presented in this work. Although it is straightforward to define a rectifying transformation (or homography) given the epipolar geometry, many existing algorithms have unwanted geometric distortions as a side effect. To obtain rectified images with reduced geometric distortions while maintaining a small rectification error, we parameterize the homography by considering the influence of various kinds of geometric distortions. Next, we define several geometric measures and incorporate them into a new cost function for parameter optimization. Finally, we propose a constrained adaptive optimization scheme to allow a balanced performance between the rectification error and the geometric error. Extensive experimental results are provided to demonstrate the superb performance of the proposed USR-CGD method, which outperforms existing algorithms by a significant margin.