StereoVAE: A lightweight stereo-matching system using embedded GPUs
This work addresses the problem of efficient stereo matching for embedded systems, representing an incremental improvement through a hybrid approach.
The authors tackled the trade-off between accuracy and processing speed in stereo matching by developing a lightweight system that uses a tiny VAE-based neural network to upsample and refine coarse disparity maps, achieving high robustness and real-time performance on embedded GPUs as demonstrated on the KITTI 2015 benchmark.
We present a lightweight system for stereo matching through embedded GPUs. It breaks the trade-off between accuracy and processing speed in stereo matching, enabling our embedded system to further improve the matching accuracy while ensuring real-time processing. The main idea of our method is to construct a tiny neural network based on variational auto-encoder (VAE) to upsample and refinement a small size of coarse disparity map, which is first generated by a traditional matching method. The proposed hybrid structure cannot only bring the advantage of traditional methods in terms of computational complexity, but also ensure the matching accuracy under the impact of neural network. Extensive experiments on the KITTI 2015 benchmark demonstrate that our tiny system exhibits high robustness in improving the accuracy of the coarse disparity maps generated by different algorithms, while also running in real-time on embedded GPUs.