Griffiths, D;
Boehm, J;
Ritschel, T;
(2021)
Curiosity-driven 3D Object Detection Without Labels.
In:
2021 International Conference on 3D Vision (3DV).
(pp. pp. 525-534).
IEEE: London, UK.
Preview |
Text
Boehm_2012.01230_1.pdf - Accepted Version Download (23MB) | Preview |
Abstract
Previous work has demonstrated learning isolated 3D objects (voxel grids, point clouds, meshes, etc.) from 2D-only self-supervision. Here we set out to extend this to entire 3D scenes made out of multiple objects, including their location, orientation and type, and the scenes illumination. Once learned, we can map arbitrary 2D images to 3D scene structure. We analyze why analysis-by-synthesis-like losses for supervision of 3D scene structure using differentiable rendering is not practical, as it almost always gets stuck in local minima of visual ambiguities. This can be overcome by a novel form of training: we use an additional network to steer the optimization itself to explore the full gamut of possible solutions \ie to be curious, and hence, to resolve those ambiguities and find workable minima. The resulting system converts 2D images of different virtual or real images into complete 3D scenes, learned only from 2D images of those scenes.
| Type: | Proceedings paper |
|---|---|
| Title: | Curiosity-driven 3D Object Detection Without Labels |
| Event: | 2021 International Conference on 3D Vision (3DV) |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/3DV53792.2021.00062 |
| Publisher version: | https://doi.org/10.1109/3DV53792.2021.00062 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Civil, Environ and Geomatic Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10117845 |
Archive Staff Only
 |
View Item |
