The CUDA LATCH Binary Descriptor: Because Sometimes Faster Means Better

Christopher Parker, Matthew Daiter, Kareem Omar, Gil Levi, Tal Hassner
University of Oslo, Norway
arXiv:1609.03986 [cs.CV], (14 Sep 2016)


   title={The CUDA LATCH Binary Descriptor: Because Sometimes Faster Means Better},

   author={Parker, Christopher and Daiter, Matthew and Omar, Kareem and Levi, Gil and Hassner, Tal},






Download Download (PDF)   View View   Source Source   Source codes Source codes




Accuracy, descriptor size, and the time required for extraction and matching are all important factors when selecting local image descriptors. To optimize over all these requirements, this paper presents a CUDA port for the recent Learned Arrangement of Three Patches (LATCH) binary descriptors to the GPU platform. The design of LATCH makes it well suited for GPU processing. Owing to its small size and binary nature, the GPU can further be used to efficiently match LATCH features. Taken together, this leads to breakneck descriptor extraction and matching speeds. We evaluate the trade off between these speeds and the quality of results in a feature matching intensive application. To this end, we use our proposed CUDA LATCH (CLATCH) to recover structure from motion (SfM), comparing 3D reconstructions and speed using different representations. Our results show that CLATCH provides high quality 3D reconstructions at fractions of the time required by other representations, with little, if any, loss of reconstruction quality.
Rating: 2.5/5. From 2 votes.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: