Dear guest, welcome to this publication database. As an anonymous user, you will probably not have edit rights. Also, the collapse status of the topic tree will not be persistent. If you like to have these and other options enabled, you might ask Admin for a login account.
| This site is powered by Aigaion - A PHP/Web based management system for shared and annotated bibliographies. For more information visit www.aigaion.nl. |
|
LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments
| Type of publication: | Inproceedings |
| Citation: | raul2021iccv |
| Booktitle: | Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) |
| Year: | 2021 |
| Month: | {oct} |
| Pages: | 10107-10116 |
| URL: | http://https://openaccess.thec... |
| DOI: | https://doi.org/10.48550/arXiv.2104.09169 |
| Abstract: | We present LaLaLoc to localise in environments without the need for prior visitation, and in a manner that is robust to large changes in scene appearance, such as a full rearrangement of furniture. Specifically, LaLaLoc performs localisation through latent representations of room layout. LaLaLoc learns a rich embedding space shared between RGB panoramas and layouts inferred from a known floor plan that encodes the structural similarity between locations. Further, LaLaLoc introduces direct, cross-modal pose optimisation in its latent space. Thus, LaLaLoc enables fine-grained pose estimation in a scene without the need for prior visitation, as well as being robust to dynamics, such as a change in furniture configuration. We show that in a domestic environment LaLaLoc is able to accurately localise a single RGB panorama image to within 8.3cm, given only a floor plan as a prior. |
| Userfields: | img_url=,rank_indexname=,rank_pos_in_category=,rank_num_in_category=,rank_cat_name=,impact_factor= |
| Keywords: | |
| Authors | |
| Added by: | [] |
| Total mark: | 0 |
|
Attachments
|
|
|
Notes
|
|
|
|
|
|
Topics
|
|
|
|
|