Left-Right Comparative Recurrent Model for Stereo Matching

Abstract

Leveraging the disparity information from both left and right views is crucial for stereo disparity estimation. Left-right consistency check is an effective way to enhance the disparity estimation by referring to the information from the opposite view. However, the conventional left-right consistency check is an isolated post-processing step and heavily hand-crafted. This paper proposes a novel left-right comparative recurrent model to perform left-right consistency checking jointly with disparity estimation. At each recurrent step, the model produces disparity results for both views, and then performs online left-right comparison to identify the mismatched regions which may probably contain erroneously labeled pixels. A soft attention mechanism is introduced, which employs the learned error maps for better guiding the model to selectively focus on refining the unreliable regions at the next recurrent step. In this way, the generated disparity maps are progressively improved by the proposed recurrent model. Extensive evaluations on KITTI 2015, Scene Flow and Middlebury benchmarks validate the effectiveness of our model, demonstrating that state-of-the-art stereo disparity estimation results can be achieved by this new model.

arXiv commentAccepted by CVPR 2018

References in corpus (9)

• Computing the Stereo Matching Cost with a Convolutional Neural Network
• End-to-End Learning of Geometry and Context for Deep Stereo Regression
• Learning to Compare Image Patches via Convolutional Neural Networks
• Self-Supervised Learning for Stereo Matching with Self-Improving Ability
• Continuous 3D Label Stereo Matching using Local Expansion Moves
• Semi-Supervised Deep Learning for Monocular Depth Map Prediction
• Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching
• Improved Stereo Matching with Constant Highway Networks and Reflective Confidence Learning
• Detect, Replace, Refine: Deep Structured Prediction For Pixel Wise Labeling

Cited by in corpus (3)

• A Novel Monocular Disparity Estimation Network with Domain Transformation and Ambiguity Learning
• Monocular Depth Estimation with Directional Consistency by Deep Networks
• Learning Parallax Attention for Stereo Image Super-Resolution