Multi-Scale Cost Volumes Cascade Network for Stereo Matching
Not on the map. Why?
Abstract (arXiv)
Stereo matching is essential for robot navigation. However, the accuracy of current widely used traditional methods is low, while methods based on CNN need expensive computational cost and running time. This is because different cost volumes play a crucial role in balancing speed and accuracy. Thus we propose MSCVNet, which combines traditional methods and neural networks to improve the quality of cost volume. Concretely, our network first generates multiple 3D cost volumes with different resolutions and then uses 2D convolutions to construct a novel cascade hourglass network for cost aggregation. Meanwhile, we design an algorithm to distinguish and calculate the loss for discontinuous areas of disparity result. According to the KITTI official website, our network is much faster than most top-performing methods (24 times than CSPN, 44 times than GANet, etc.). Meanwhile, compared to traditional methods (SPS-St, SGM) and other real-time stereo matching networks (Fast DS-CS, DispNetC, and RTSNet, etc.), our network achieves a big improvement in accuracy, demonstrating the feasibility and capability of the proposed method.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 34 references that are in the map. First posted on arXiv 3 Feb 2021.
Builds on
16 of 34 references.
References · 16
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
- 2018Pyramid Stereo Matching Networkcited by 486
- 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
- 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
- 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 242
- 2020AANet: Adaptive Aggregation Network for Efficient Stereo Matchingcited by 202
- 2015Stereo Matching by Training a Convolutional Neural Network to Compare Image Patchescited by 151
- 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 135
- 2019Hierarchical Deep Stereo Matching on High-resolution Imagescited by 126
- 2019Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identificationcited by 83
4 more
- 2020FADNet: A Fast and Accurate Network for Disparity Estimationcited by 31
- 2019Fast Deep Stereo with 2D Convolutional Processing of Cost Signaturescited by 12
- 2018Fusion of stereo and still monocular depth estimates in a self-supervised learning contextcited by 10
- 2019Energy Clustering for Unsupervised Person Re-identificationcited by 5
Built on by
Not cited yet.