Timezone: »

Direct LiDAR-based object detector training from automated 2D detections
Robert McCraith · Eldar Insafutdinov · Lukas Neumann · Andrea Vedaldi

3D Object detection (3DOD) is an important component of many applications, however existing methods rely heavily on datasets of depth and image data which require expensive annotation in 3D thus limiting the ability of a diverse dataset being collected which truly represents the long tail of potential scenes in the wild.In this work we propose to utilise a readily available robust 2D Object Detector and to transfer information about objects from 2D to 3D, allowing us to train a 3D Object Detector without the need for any human annotation in 3D. We demonstrate that our method significantly outperforms previous 3DOD methods supervised by only 2D annotations, and that our method narrows the accuracy gap between methods that use 3D supervision and those that do not.

Author Information

Robert McCraith (University of Oxford)
Eldar Insafutdinov (University of Oxford)
Lukas Neumann (University of Oxford)
Andrea Vedaldi (Facebook AI Research and University of Oxford)

More from the Same Authors