Semi-dense Stereo Matching using Dual CNNs
This work addresses stereo matching for computer vision applications, offering an incremental improvement over existing CNN-based approaches.
The paper tackles semi-dense stereo matching by using dual CNNs for cost computation and filtering, incorporating global information to handle lighting changes and textureless areas, and outperforms state-of-the-art methods on the Middlebury Stereo dataset.
A robust solution for semi-dense stereo matching is presented. It utilizes two CNN models for computing stereo matching cost and performing confidence-based filtering, respectively. Compared to existing CNNs-based matching cost generation approaches, our method feeds additional global information into the network so that the learned model can better handle challenging cases, such as lighting changes and lack of textures. Through utilizing non-parametric transforms, our method is also more self-reliant than most existing semi-dense stereo approaches, which rely highly on the adjustment of parameters. The experimental results based on Middlebury Stereo dataset demonstrate that the proposed approach outperforms the state-of-the-art semi-dense stereo approaches.