Connectionists: ShapeNet Challenge on Segmentation and Reconstruction - Call for participation

[Hao Su]

----------------------------------------------------------
ShapeNet Challenge - Call for Participation
----------------------------------------------------------

We invite you to participate in the ShapeNet challenge, (https://shapenet.cs.stanford.edu/iccv17/ <https://shapenet.cs.stanford.edu/iccv17/>), whose results will be presented at ICCV 2017 Workshop on Learning to See from 3D Data.

In recent years we have witnessed an explosion in the amount of 3D data that we can generate and store. On the one hand, better 3D modeling tools have enabled designers to build 3D models easily, resulting in an expansion in the size of 3D CAD model repositories. On the other hand, commodity depth sensors have allowed ordinary people to capture their own 3D scans conveniently. We need good techniques to design algorithms that successfully understand our 3D world.

However, due to fundamental challenges in dealing with 3D representations and processing, there are still many open research issues. Two key research problems are (1) 3D shape reconstruction based on a single image, and (2) shape part level segmentation. Existing algorithms are usually evaluated on small datasets with a few hundreds of models, even though millions of 3D models are now available on the Internet. Thanks to the efforts of the ShapeNet team, we can now use a much larger and varied repository of 3D models to develop and evaluate new algorithms in computer vision and computer graphics.

In this challenge, we aim to evaluate the performance of 3D reconstruction based on single image and shape part level segmentation on a subset of the ShapeNet dataset.

Task 1 -- 3D reconstruction from a single image: reconstructing a 3D shape, given a single image as input.

Task 2 -- 3D part segmentation: predicting a per point part label, given 3D shape point clouds and their category labels as input.

The participants will have a chance to submit a report describing their system, which will be summarized and published. Furthermore, the groups of the best-performing systems will be invited to give an oral presentation at the workshop, Learning to See from 3D Data, at ICCV 2017 and others will be given the option of presenting a poster.

Schedule:
Aug. 8: Dataset released
Sep. 15: Deadline for registering as participants. Please send email to shapenetchallenge.iccv17 at gmail.com <mailto:shapenetchallenge.iccv17 at gmail.com> to register.
Sep. 30 11:59PM UTC: Deadline for sending results. Each participant should also submits a one-page method description with at most two figures. Submission is by email containing MD5 checksum and download link to results. Please submit results to shapenetchallenge.iccv17 at gmail.com <mailto:shapenetchallenge.iccv17 at gmail.com>.
Oct. 7: Organizers carry out automatic evaluation and release evaluation results for all participants.
Oct. 7: Organizers write a contest report with result details including method description from each participant.
Oct. 22-29: Results are presented at ICCV 2017 Workshop on Learning to See from 3D Data.

For more details on the task and data, please visit https://shapenet.cs.stanford.edu/iccv17/ <https://shapenet.cs.stanford.edu/iccv17/>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20170818/206b6392/attachment.html>