The 3rd Geometry Meets Deep Learning Workshop
in association with ECCV 2018
September 14th, Munich, Germany

Welcome to the 3rd edition of the Geometry meets Deep Learning (GMDL) workshop.  This series of workshops was initiated at ECCV 2016, followed by the second edition at ICCV 2017.  The goal of this full-day workshop is to encourage the interplay between geometric vision and deep learning. 

In the past few years deep learning has emerged as a common approach to learning data-driven representations.  While deep learning approaches have attained remarkable performance improvements in many 2D vision tasks, such as image classification and object detection, they cannot be directly applied to geometric vision problems due to the fundamental differences between 2D and 3D vision tasks, such as the non-Euclidean nature of geometric objects, higher dimensionality, and the lack of large-scale annotated 3D datasets.  Designing geometric components and constraints to improve the performance of deep neural networks is a promising direction worth further exploration. The workshop aims to bring together experts from both the geometric vision and deep learning areas to summarize recent advances, exchange ideas, and inspire new directions. 

The workshop will consist of invited talks, spotlight presentations, and a poster session.  We are soliciting original contributions that deploy deep learning, 3D geometry and optimization techniques to solve geometric vision problems including, but not limited to:
  • 3D object detection / classification
  • Object pose estimation and reconstruction
  • Stereo matching and depth / surface normal / layout estimation
  • Human pose / hand pose estimation
  • 3D shape matching / retrieval / recognition
  • 3D scene understanding
  • Place recognition and visual odometry 
  • Semantic localization and SLAM
  • Image / object matching
  • Data mining and signal processing on graphs
  • Deep learning on manifolds and non-Euclidean domains
Please refer to the submission page for the submission guidelines.
For any inquiries regarding the workshop, please contact the organizers at gmdl.workshop@gmail.com