Geometry Meets Deep Learning
in association with ECCV 2016
October 9th, Grand Hotel Krasnapolsky, Amsterdam, Netherlands
Recovering 3D geometry of the world from 2D and 3D visual data is a central task in computer vision. The traditional approaches for geometric vision problems are mostly based on handcrafted geometric representations and image features. With the explosive growth of data and computational power, deep learning has recently emerged as a common approach to learning data-driven representations and features for most of the 2D vision tasks. We believe that the interaction between 3D geometry and deep learning has not been fully explored.
The goal of this workshop is to encourage the interplay between 3D vision and deep learning. The workshop aims to bring together experts from both 3D vision and deep learning areas to summarize the 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 3D 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
The best contribution will be awarded a RealSense camera, sponsored by Intel.
Please refer to the submission page for the submission guidelines.
For any inquiries regarding the workshop, please contact the organizers at email@example.com