Improved Stereo Matching with Constant Highway Networks and Reflective Confidence Learning
This work addresses stereo matching for computer vision applications, offering incremental improvements with novel components.
The paper tackles stereo matching by introducing a three-step pipeline with a new highway network for matching cost, a post-processing CNN for disparity and confidence, and a refinement step using learned confidence, achieving state-of-the-art accuracy on major benchmarks.
We present an improved three-step pipeline for the stereo matching problem and introduce multiple novelties at each stage. We propose a new highway network architecture for computing the matching cost at each possible disparity, based on multilevel weighted residual shortcuts, trained with a hybrid loss that supports multilevel comparison of image patches. A novel post-processing step is then introduced, which employs a second deep convolutional neural network for pooling global information from multiple disparities. This network outputs both the image disparity map, which replaces the conventional "winner takes all" strategy, and a confidence in the prediction. The confidence score is achieved by training the network with a new technique that we call the reflective loss. Lastly, the learned confidence is employed in order to better detect outliers in the refinement step. The proposed pipeline achieves state of the art accuracy on the largest and most competitive stereo benchmarks, and the learned confidence is shown to outperform all existing alternatives.