TY - CONF ID - raul2021iccv T1 - LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments A1 - Howard-Jenkins, Henry A1 - Ruiz-Sarmiento, J. R. A1 - Prisacariu, Victor Adrian TI - Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Y1 - 2021 SP - 10107 EP - 10116 UR - https://openaccess.thecvf.com/content/ICCV2021/papers/Howard-Jenkins_LaLaLoc_Latent_Layout_Localisation_in_Dynamic_Unvisited_Environments_ICCV_2021_paper.pdf M2 - doi: https://doi.org/10.48550/arXiv.2104.09169 N2 - 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. M1 - img_url= M1 - rank_indexname= M1 - rank_pos_in_category= M1 - rank_num_in_category= M1 - rank_cat_name= M1 - impact_factor= ER -