SDC - Stacked Dilated Convolutions

René Schuster; Oliver Wasenmüller; Christian Unger; Didier Stricker

In: Computer Science in Cars Sympoisum. ACM Computer Science in Cars Symposium (CSCS-2019), October 8, Kaiserslautern, Germany, ACM, 10/2019.


Dense matching is a fundamental problem in many tasks and applications of Computer Vision. Of utmost importance for robust matching algorithms is a powerful representation of image points. With SDC (Stacked Dilated Convolution), we have presented a universal design element that was successfully used in a deep neural network for dense feature description of images. Using these descriptors, we could improve matching in wide variety of problems and domains.

schuster2019sdc.pdf (pdf, 2 MB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence