Joint Recursive Monocular Filtering of Camera Motion and Disparity Map

TL;DR

This paper introduces a novel recursive filtering method for monocular scene reconstruction that jointly estimates camera motion and disparity maps, handling complex non-linearities and outliers effectively.

Contribution

It presents a second order optimal minimum energy filter on a product Lie group for joint estimation, a significant advancement over classical filters for monocular reconstruction.

Findings

Achieves accuracy comparable to state-of-the-art methods.

Robust to outliers due to generalized Charbonnier energy function.

Handles non-Euclidean and high-dimensional state spaces effectively.

Abstract

Monocular scene reconstruction is essential for modern applications such as robotics or autonomous driving. Although stereo methods usually result in better accuracy than monocular methods, they are more expensive and more difficult to calibrate. In this work, we present a novel second order optimal minimum energy filter that jointly estimates the camera motion, the disparity map and also higher order kinematics recursively on a product Lie group containing a novel disparity group. This mathematical framework enables to cope with non-Euclidean state spaces, non-linear observations and high dimensions which is infeasible for most classical filters. To be robust against outliers, we use a generalized Charbonnier energy function in this framework rather than a quadratic energy function as proposed in related work. Experiments confirm that our method enables accurate reconstructions on-par with state-of-the-art.