Runz, M;
Li, K;
Tang, M;
Ma, L;
Kong, C;
Schmidt, T;
Reid, I;
... Newcombe, R; + view all
(2020)
FroDO: From Detections to 3D Objects.
In:
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
(pp. pp. 14708-14717).
IEEE: Seattle, WA, USA.
Preview |
Text
Runz_FroDO_From_Detections_to_3D_Objects_CVPR_2020_paper.pdf - Published Version Download (1MB) | Preview |
Abstract
Object-oriented maps are important for scene understanding since they jointly capture geometry and semantics, allow individual instantiation and meaningful reasoning about objects. We introduce FroDO, a method for accurate 3D reconstruction of object instances from RGB video that infers their location, pose and shape in a coarse to fine manner. Key to FroDO is to embed object shapes in a novel learnt shape space that allows seamless switching between sparse point cloud and dense DeepSDF decoding. Given an input sequence of localized RGB frames, FroDO first aggregates 2D detections to instantiate a 3D bounding box per object. A shape code is regressed using an encoder network before optimizing shape and pose further under the learnt shape priors using sparse or dense shape representations. The optimization uses multi-view geometric, photometric and silhouette losses. We evaluate on real-world datasets, including Pix3D, Redwood-OS, and ScanNet, for single-view, multi-view, and multi-object reconstruction.
Type: | Proceedings paper |
---|---|
Title: | FroDO: From Detections to 3D Objects |
Event: | 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
Dates: | 13 June 2020 - 19 June 2020 |
Open access status: | An open access version is available from UCL Discovery |
DOI: | 10.1109/cvpr42600.2020.01473 |
Publisher version: | https://doi.org/10.1109/CVPR42600.2020.01473 |
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 Computer Science |
URI: | https://discovery.ucl.ac.uk/id/eprint/10111218 |
Archive Staff Only
![]() |
View Item |