Deep Learning for Geometric Computing
CVPR 2020 Workshop and Challenge
Videos of the keynote speakers:
- Prof. Daniel Cremers: Deep Networks for Camera-Based Reconstruction.
- Prof. Mireille (Mimi) Boutin: The Geometry of High-Dimensional Data.
- Prof. Jitendra Malik: 3D objects and people.
News
- ABC Sharpness Fields Extraction and Geometric Shape Segmentation Challenges are now online!
- Image SkelNetOn challenge is now online!
- Based on CVPR FAQ, physical attendance at the workshop is not mandatory due to COVID-19 and can now be replaced with remote attendance.
- All the accepted papers will be published as usual.
Introduction
Computer vision approaches have made tremendous efforts toward understanding shape from various data formats, especially since entering the deep learning era. Although accurate results have been obtained in detection, recognition, and segmentation, there is less attention and research on extracting topological and geometric information from shapes. These geometric representations provide compact and intuitive abstractions for modeling, synthesis, compression, matching, and analysis. Extracting such representations is significantly different from segmentation and recognition tasks, as they contain both local and global information about the shape.
This workshop aims to bring together researchers from computer vision, computer graphics, and mathematics to advance the state of the art in topological and geometric shape analysis using deep learning.
Topics covered
- Boundary extraction from 2D/3D shapes
- Geometric deep learning on 3D and higher dimensions
- Generative methods for parametric representations
- Novel shape descriptors and embeddings for geometric deep learning
- Deep learning on non-Euclidean geometries
- Transformation invariant shape abstractions
- Shape abstraction in different domains
- Synthetic data generation for data augmentation in geometric deep learning
- Comparison of shape representations for efficient deep learning
- Novel kernels and architectures specifically for 3D generative models
- Eigen-spectra analysis and graph-based approaches for 3D data
- Applications of geometric deep learning in different domains
- Learning-based estimation of shape differential quantities
- Detection of geometric feature lines from 3D data, including 3D point clouds and depth images
- Geometric shape segmentation, including patch decomposition and sharp lines detection
Important dates
Deadlines for paper submissions: see Submission webpage
- Paper submissions are now accepted
Deadlines for challenges submissions: see Challenges webpage
- Challenge submissions are now accepted
- Workshop date: June 14, 2020 (full day)
Acknowledgements
Work performed in the context of this workshop and challenge was in part supported by The Ministry of Education and Science of Russian Federation, grant No. 14.615.21.0004, grant code: RFMEFI61518X0004.