Bilateral Grid Learning for Stereo Matching Networks
arXiv:2101.01601
Abstract
Real-time performance of stereo matching networks is important for many applications, such as automatic driving, robot navigation and augmented reality (AR). Although significant progress has been made in stereo matching networks in recent years, it is still challenging to balance real-time performance and accuracy. In this paper, we present a novel edge-preserving cost volume upsampling module based on the slicing operation in the learned bilateral grid. The slicing layer is parameter-free, which allows us to obtain a high quality cost volume of high resolution from a low-resolution cost volume under the guide of the learned guidance map efficiently. The proposed cost volume upsampling module can be seamlessly embedded into many existing stereo matching networks, such as GCNet, PSMNet, and GANet. The resulting networks are accelerated several times while maintaining comparable accuracy. Furthermore, we design a real-time network (named BGNet) based on this module, which outperforms existing published real-time deep stereo matching networks, as well as some complex networks on the KITTI stereo datasets. The code is available at https://github.com/YuhuaXu/BGNet.
arXiv commentCVPR 2021
References in corpus (5)
- Computing the Stereo Matching Cost with a Convolutional Neural Network
- End-to-End Learning of Geometry and Context for Deep Stereo Regression
- Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
- IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation
- Domain-invariant Stereo Matching Networks