Abstract Recurrent All-Pairs Field Transforms (RAFT) has shown great potentials in
matching tasks. However, all-pairs correlations lack non-local geometry knowledge and …

Deep learning-based stereo matching methods have made remarkable progress in recent
years. However, it is still a challenging task to achieve high accuracy in real time. In …

Correlation based stereo matching has achieved outstanding performance, which pursues
cost volume between two feature maps. Unfortunately, current methods with a fixed trained …

We introduce a novel approach for adapting deep stereo networks in a collaborative
manner. By building over principles of federated learning we develop a distributed …

Stereo matching is a fundamental building block for many vision and robotics applications.
An informative and concise cost volume representation is vital for stereo matching of high …

In this paper, we propose CGI-Stereo, a novel neural network architecture that can
concurrently achieve real-time performance, competitive accuracy, and strong …

Stereo matching aims to estimate the disparity between matching pixels in a stereo image
pair, which is important to robotics, autonomous driving, and other computer vision tasks …

Self-supervised multi-frame depth estimation achieves high accuracy by computing
matching costs of pixel correspondences between adjacent frames, injecting geometric …

Stereo matching is close to hitting a half-century of history, yet witnessed a rapid evolution in
the last decade thanks to deep learning. While previous surveys in the late 2010s covered …

We present LightStereo, a cutting-edge stereo-matching network crafted to accelerate the
matching process. Departing from conventional methodologies that rely on aggregating …