Gradual interaction network for stereo matching
A Chong, H Yin, Q Du, Y Liu, M Han - Pattern Recognition, 2025 - Elsevier
Existing stereo matching network models have achieved unprecedented state-of-the-art
performance by adopting coarse-to-fine strategy. However, most models ignore the potential …
performance by adopting coarse-to-fine strategy. However, most models ignore the potential …
A unified and efficient semi-supervised learning framework for stereo matching
F Xu, L Wang, H Li - Pattern Recognition, 2024 - Elsevier
Recently, stereo matching algorithms have made tremendous progress in terms of both
accuracy and efficiency. However, it remains a great challenge to train a practical model due …
accuracy and efficiency. However, it remains a great challenge to train a practical model due …
SG-RoadSeg: End-to-end collision-free space detection sharing encoder representations jointly learned via unsupervised deep stereo
Collision-free space detection is of utmost importance for autonomous robot perception and
navigation. State-of-the-art (SoTA) approaches generally extract features from RGB images …
navigation. State-of-the-art (SoTA) approaches generally extract features from RGB images …
Improvement on SGM-based stereo matching algorithm and FPGA implementation
M Jin, W Wu, L Zhang - International Conference on Image …, 2024 - spiedigitallibrary.org
This paper presents a low-resource binocular stereo matching algorithm. This algorithm
begins with an optimized design of semi-global stereo matching (SGM) by employing a …
begins with an optimized design of semi-global stereo matching (SGM) by employing a …