Learning Stereo Matchability in Disparity Regression Networks

Understand

Learning-based stereo matching has recently achieved promising results, yet still suffers difficulties in establishing reliable matches in weakly matchable regions that are textureless, non-Lambertian, or occluded.

• In this paper, we address this challenge by proposing a stereo matching network that considers pixel-wise matchability.
• Specifically, the network jointly regresses disparity and matchability maps from 3D probability volume through expectation and entropy operations.
• Next, a learned attenuation is applied as the robust loss function to alleviate the influence of weakly matchable pixels in the training.