EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matching

Abstract

Recent convolutional neural networks, especially end-to-end disparity estimation models, achieve remarkable performance on stereo matching task. However, existed methods, even with the complicated cascade structure, may fail in the regions of non-textures, boundaries and tiny details. Focus on these problems, we propose a multi-task network EdgeStereo that is composed of a backbone disparity network and an edge sub-network. Given a binocular image pair, our model enables end-to-end prediction of both disparity map and edge map. Basically, we design a context pyramid to encode multi-scale context information in disparity branch, followed by a compact residual pyramid for cascaded refinement. To further preserve subtle details, our EdgeStereo model integrates edge cues by feature embedding and edge-aware smoothness loss regularization. Comparative results demonstrates that stereo matching and edge detection can help each other in the unified model. Furthermore, our method achieves state-of-art performance on both KITTI Stereo and Scene Flow benchmarks, which proves the effectiveness of our design.

arXiv commentAccepted by Asian Conference on Computer Vision (ACCV) 2018

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Richer Convolutional Features for Edge Detection
• Holistically-Nested Edge Detection
• Self-Supervised Learning for Stereo Matching with Self-Improving Ability
• Learning for Disparity Estimation through Feature Constancy

Cited by in corpus (5)

• Efficient Attention: Attention with Linear Complexities
• BMN: Boundary-Matching Network for Temporal Action Proposal Generation
• Learning Depth with Convolutional Spatial Propagation Network
• Hierarchical Discrete Distribution Decomposition for Match Density Estimation
• EdgeNet: A novel approach for Arabic numeral classification