Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussavertaisarvioitu



  • IIT Delhi


We propose a new deep learning based approach for camera relocalization. Our approach localizes a given query image by using a convolutional neural network (CNN) for first retrieving similar database images and then predicting the relative pose between the query and the database images, whose poses are known. The camera location for the query image is obtained via triangulation from two relative translation estimates using a RANSAC based approach. Each relative pose estimate provides a hypothesis for the camera orientation and they are fused in a second RANSAC scheme. The neural network is trained for relative pose estimation in an end-to-end manner using training image pairs. In contrast to previous work, our approach does not require scene-specific training of the network, which improves scalability, and it can also be applied to scenes which are not available during the training of the network. As another main contribution, we release a challenging indoor localisation dataset covering 5 different scenes registered to a common coordinate frame. We evaluate our approach using both our own dataset and the standard 7 Scenes benchmark. The results show that the proposed approach generalizes
well to previously unseen scenes and compares favourably to other recent CNN-based


Otsikko2017 IEEE International Conference on Computer Vision Workshops (ICCVW)
TilaJulkaistu - 2017
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaIEEE International Conference on Computer Vision Workshops - Venice, Italia
Kesto: 22 lokakuuta 201729 lokakuuta 2017
Konferenssinumero: ICCVW


NimiIEEE International Conference on Computer Vision Workshops (ICCVW)
ISSN (elektroninen)2473-9944


WorkshopIEEE International Conference on Computer Vision Workshops

ID: 16829714