The 2nd Workshop on Geometry Meets Deep Learning
in association with ICCV 2017
October 28th, Venice, Italy

Welcome to the 2nd edition of the GMDL workshop. This series of workshop was initiated at ECCV 2016 and the goal 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 obtained remarkable performance improvements in most 2D vision problems, 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 problems, such as the non-Euclidean nature of geometric objects, higher dimensionality, and the lack of large-scale annotated 3D datasets. Designing geometric components or constraints to improve the performances of deep neural networks is also a promising direction worth further exploration. The workshop aims to bring together experts from both 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 sessionWe 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