Search Results for author:
Found 2 papers, 1 papers with code
Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching
However, disparity is just a byproduct of a matching process modeled by cost volume, while indirectly learning cost volume driven by disparity regression is prone to overfitting since the cost volume is under constrained.
HMFlow: Hybrid Matching Optical Flow Network for Small and Fast-Moving Objects
To address this problem, we introduce a lightweight but effective Global Matching Component (GMC) to grab global matching features.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
