Fusion of Range and Stereo Data for High-Resolution Scene-Modeling

TL;DR

This paper presents a novel method for high-resolution scene modeling by fusing low-resolution depth data with high-resolution stereo images using a hierarchical local energy minimization approach, improving accuracy and efficiency.

Contribution

It introduces a hierarchical disparity inference method that fuses depth and stereo data with adaptive correlation and scene-aware fusion, avoiding common propagation errors.

Findings

Runs at 3FPS on 2.0MP images on standard hardware

Outperforms state-of-the-art methods in accuracy

Provides high-resolution, reliable depth maps

Abstract

This paper addresses the problem of range-stereo fusion, for the construction of high-resolution depth maps. In particular, we combine low-resolution depth data with high-resolution stereo data, in a maximum a posteriori (MAP) formulation. Unlike existing schemes that build on MRF optimizers, we infer the disparity map from a series of local energy minimization problems that are solved hierarchically, by growing sparse initial disparities obtained from the depth data. The accuracy of the method is not compromised, owing to three properties of the data-term in the energy function. Firstly, it incorporates a new correlation function that is capable of providing refined correlations and disparities, via subpixel correction. Secondly, the correlation scores rely on an adaptive cost aggregation step, based on the depth data. Thirdly, the stereo and depth likelihoods are adaptively fused, based on the scene texture and camera geometry. These properties lead to a more selective growing process which, unlike previous seed-growing methods, avoids the tendency to propagate incorrect disparities. The proposed method gives rise to an intrinsically efficient algorithm, which runs at 3FPS on 2.0MP images on a standard desktop computer. The strong performance of the new method is established both by quantitative comparisons with state-of-the-art methods, and by qualitative comparisons using real depth-stereo data-sets.