3D Reconstruction meets Semantics – Reconstruction Challenge

Description

Part of the workshop is a challenge on combining 3D and semantic information in complex scenes. To this end, a challenging outdoor dataset, captured by a robot driving through a semantically-rich garden that contains fine geometric details, will be released. A multi-camera rig is mounted on top of the robot, enabling the use of both stereo and motion stereo information. Precise ground truth for the 3D structure of the garden has been obtained with a laser scanner and accurate pose estimates for the robot are available as well. Ground truth semantic labels and ground truth depth from a laser scan will be used for benchmarking the quality of the 3D reconstructions, the quality of semantic segmentation, and the quality of semantically annotated 3D models.

Data

Please check back at the end of May for more information and data

Submission

Please check back at the end of May for more information and data

Twitter
Today it was the March for Science! For the future of scientists, the progress of our World. https://t.co/Zcb5Wb8Pby5 days
The sharp spinning blade is an interesting idea! But better to have a BBQ first :) @dashdashbang https://t.co/pGJ4wxSxR56 days
Robotics research in @EU_H2020 is also sub-marine! https://t.co/VP5Djl4lN33 weeks
Our #test #garden becomes nicer and nicer! https://t.co/lk4yfiFyyy4 weeks