Multi-view Disparity Estimation Using a Novel Gradient Consistency Model

TL;DR

This paper introduces a Gradient Consistency Model for disparity estimation that adaptively weights data terms based on gradient mismatch, improving convergence and accuracy over traditional methods.

Contribution

The novel Gradient Consistency Model self-schedules weights in disparity estimation, outperforming existing coarse-to-fine and view-inclusion strategies.

Findings

Outperforms standard coarse-to-fine schemes

Achieves higher accuracy in disparity estimation

Converges faster than existing methods

Abstract

Variational approaches to disparity estimation typically use a linearised brightness constancy constraint, which only applies in smooth regions and over small distances. Accordingly, current variational approaches rely on a schedule to progressively include image data. This paper proposes the use of Gradient Consistency information to assess the validity of the linearisation; this information is used to determine the weights applied to the data term as part of an analytically inspired Gradient Consistency Model. The Gradient Consistency Model penalises the data term for view pairs that have a mismatch between the spatial gradients in the source view and the spatial gradients in the target view. Instead of relying on a tuned or learned schedule, the Gradient Consistency Model is self-scheduling, since the weights evolve as the algorithm progresses. We show that the Gradient Consistency Model outperforms standard coarse-to-fine schemes and the recently proposed progressive inclusion of views approach in both rate of convergence and accuracy.