Call for Papers

Important Dates

Topics of the papers include but are not limited to:

3D Reconstruction from Images. We accept submissions in which 3D models are created from single or multiple images.
3D Generation. We are also interested in works that contain latent 3D representations somewhere in the model and with the capability to render this back into an image or generate volumetric shapes. We would like to see an exploration of what modifications of the latent variable lead to in the rendered scene or volumes.
3D Unsupervised Learning. We are interested in works where the model does not get trained on ground truth 3D models, or where only few 3D models are available for training.
3D-Aware Modelling and Manipulations. We are interested in works where the model captures the graphic code or 3D scene/object representation which can be used for rotations, translation and manipulating other geometric features freely while maintaining consistent shape and texture.

All accepted papers will be presented as posters. The guidelines for the posters are the same as at the main conference.

We solicit short papers on 3D reconstruction, 3D generation, 3D unsupervised learning and 3D-aware modelling and manipulations
Submitted manuscript should follow the CVPR 2019 paper template
The page limit is less than 6 pages (excluding references).
Submitted work can be extended abstract of recent publications:
- Including full papers presented at the main conference
- Work in progress which may be submitted to a different conference at a later date
The accepted papers will be linked at the workshop webpage and also in the main conference proceedings if the authors agree
Papers will be peer reviewed under double-blind policy, and must be submitted online through the CMT submission system at: https://cmt3.research.microsoft.com/3DWiDGET2019

There will be awards for the best papers of the workshop