Deep Stereo Matching with Dense CRF Priors

Understand

Stereo reconstruction from rectified images has recently been revisited within the context of deep learning.

• Using a deep Convolutional Neural Network to obtain patch-wise matching cost volumes has resulted in state of the art stereo reconstruction on classic datasets like Middlebury and Kitti.
• By introducing this cost into a classical stereo pipeline, the final results are improved dramatically over non-learning based cost models.
• However these pipelines typically include hand engineered post processing steps to effectively regularize and clean the result.