Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching

06/05/2018
by   Stepan Tulyakov, et al.
10

End-to-end deep-learning networks recently demonstrated extremely good perfor- mance for stereo matching. However, existing networks are difficult to use for practical applications since (1) they are memory-hungry and unable to process even modest-size images, (2) they have to be trained for a given disparity range. The Practical Deep Stereo (PDS) network that we propose addresses both issues: First, its architecture relies on novel bottleneck modules that drastically reduce the memory footprint in inference, and additional design choices allow to handle greater image size during training. This results in a model that leverages large image context to resolve matching ambiguities. Second, a novel sub-pixel cross- entropy loss combined with a MAP estimator make this network less sensitive to ambiguous matches, and applicable to any disparity range without re-training. We compare PDS to state-of-the-art methods published over the recent months, and demonstrate its superior performance on FlyingThings3D and KITTI sets.

READ FULL TEXT
research
03/05/2019

EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detection

Recently, leveraging on the development of end-to-end convolutional neur...
research
09/04/2017

Self-Supervised Learning for Stereo Matching with Self-Improving Ability

Exiting deep-learning based dense stereo matching methods often rely on ...
research
01/28/2019

Fast Hierarchical Depth Map Computation from Stereo

Disparity by Block Matching stereo is usually used in applications with ...
research
06/27/2023

Rethinking Cross-Entropy Loss for Stereo Matching Networks

Despite the great success of deep learning in stereo matching, recoverin...
research
10/25/2021

Multi-scale Iterative Residuals for Fast and Scalable Stereo Matching

Despite the remarkable progress of deep learning in stereo matching, the...
research
12/13/2019

Hierarchical Deep Stereo Matching on High-resolution Images

We explore the problem of real-time stereo matching on high-res imagery....
research
01/01/2021

Adaptive Deconvolution-based stereo matching Net for Local Stereo Matching

In deep learning-based local stereo matching methods, larger image patch...

Please sign up or login with your details

Forgot password? Click here to reset