DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch
This work addresses the need for efficient stereo matching in applications like autonomous driving by providing a real-time solution, though it is incremental as it builds on existing PatchMatch and deep learning methods.
The paper tackled the problem of speeding up stereo matching algorithms for real-time inference by developing a differentiable PatchMatch module that prunes disparities without full cost volume evaluation, achieving competitive results on KITTI and SceneFlow datasets with a runtime of 62ms.
Our goal is to significantly speed up the runtime of current state-of-the-art stereo algorithms to enable real-time inference. Towards this goal, we developed a differentiable PatchMatch module that allows us to discard most disparities without requiring full cost volume evaluation. We then exploit this representation to learn which range to prune for each pixel. By progressively reducing the search space and effectively propagating such information, we are able to efficiently compute the cost volume for high likelihood hypotheses and achieve savings in both memory and computation. Finally, an image guided refinement module is exploited to further improve the performance. Since all our components are differentiable, the full network can be trained end-to-end. Our experiments show that our method achieves competitive results on KITTI and SceneFlow datasets while running in real-time at 62ms.