Fast Hierarchical Depth Map Computation from Stereo

TL;DR

This paper introduces a multi-scale hierarchical block-matching method for stereo depth estimation that improves accuracy while maintaining low memory usage, achieving near state-of-the-art results on the Middlebury benchmark.

Contribution

A novel multi-scale hierarchical block-matching approach using pyramidal depth and cost functions that enhances standard block matching stereo techniques.

Findings

Achieves results close to state-of-the-art SGM methods on Middlebury benchmark.

Maintains low memory footprint and reduces computational complexity.

Significantly improves standard block matching accuracy.

Abstract

Disparity by Block Matching stereo is usually used in applications with limited computational power in order to get depth estimates. However, the research on simple stereo methods has been lesser than the energy based counterparts which promise a better quality depth map with more potential for future improvements. Semi-global-matching (SGM) methods offer good performance and easy implementation but suffer from the problem of very high memory footprint because it's working on the full disparity space image. On the other hand, Block matching stereo needs much less memory. In this paper, we introduce a novel multi-scale-hierarchical block-matching approach using a pyramidal variant of depth and cost functions which drastically improves the results of standard block matching stereo techniques while preserving the low memory footprint and further reducing the complexity of standard block matching. We tested our new multi block matching scheme on the Middlebury stereo benchmark. For the Middlebury benchmark we get results that are only slightly worse than state of the art SGM implementations.