Adaptive Disparity Candidates Prediction Network for Efficient Real-Time Stereo Matching
- 3 August 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (5) , 3099-3110
Abstract
Efficient real-time disparity estimation is critical for the application of stereo vision systems in various areas. Recently, stereo network based on coarse-to-fine method has largely relieved the memory constraints and speed limitations of large-scale network models. Nevertheless, all of the previous coarse-to-fine designs employ constant offsets and three or more stages to progressively refine the coarse disparity map, still resulting in unsatisfactory computation accuracy and inference time when deployed on mobile devices. This paper claims that the coarse matching errors can be corrected efficiently with fewer stages as long as more accurate disparity candidates can be provided. Therefore, we propose a dynamic offset prediction module to meet different correction requirements of diverse objects and design an efficient two-stage framework. In addition, a disparity-independent convolution is proposed to regularize the compact cost volume efficiently and further improve the overall performance. The disparity quality and efficiency of various stereo networks are evaluated on multiple datasets and platforms. Evaluation results demonstrate that, the disparity error rate of the proposed network achieves 2.66% and 2.71% on KITTI 2012 and 2015 test sets respectively, where the computation speed is $2\times $ faster than the state-of-the-art lightweight models on high-end and source-constrained GPUs.Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2017YFA0700800)
- National Natural Science Foundation of China (61790563, 62004157)
- China Postdoctoral Science Foundation (2020M673402)
- Key Research and Development Program of Shaanxi (2021GXLH-Z-039)
This publication has 33 references indexed in Scilit:
- Cross-scale cost aggregation for stereo matchingIEEE Transactions on Circuits and Systems for Video Technology, 2015
- Object scene flow for autonomous vehicles2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- 3-Dimensional Object Perception for Manipulation Tasks Using the Atlas Robot2014
- Making Bertha See2013
- High Performance Stereo System for Dense 3-D ReconstructionIEEE Transactions on Circuits and Systems for Video Technology, 2013
- PMBP: PatchMatch Belief Propagation for Correspondence Field EstimationInternational Journal of Computer Vision, 2013
- Stereo matching using belief propagationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- A taxonomy and evaluation of dense two-frame stereo correspondence algorithms2002
- Fast approximate energy minimization via graph cutsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001