Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Reconstruct locally, localize globally: A model free method for object pose estimation
Author: Cai, M.
Reid, I.
Citation: Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2020, pp.3150-3160
Publisher: IEEE
Publisher Place: online
Issue Date: 2020
Series/Report no.: IEEE Conference on Computer Vision and Pattern Recognition
ISBN: 9781728171685
ISSN: 1063-6919
Conference Name: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (13 Jun 2020 - 19 Jun 2020 : virtual online)
Statement of
Ming Cai, Ian Reid
Abstract: Six degree-of-freedom pose estimation of a known object in a single image is a long-standing computer vision objective. It is classically posed as a correspondence problem between a known geometric model, such as a CAD model, and image locations. If a CAD model is not available, it is possible to use multi-view visual reconstruction methods to create a geometric model, and use this in the same manner. Instead, we propose a learning-based method whose input is a collection of images of a target object, and whose output is the pose of the object in a novel view. At inference time, our method maps from the RoI features of the input image to a dense collection of object-centric 3D coordinates, one per pixel. This dense 2D-3D mapping is then used to determine 6dof pose using standard PnP plus RANSAC. The model that maps 2D to object 3D coordinates is established at training time by automatically discovering and matching image landmarks that are consistent across multiple views. We show that this method eliminates the requirement for a 3D CAD model (needed by classical geometry-based methods and state-of-the-art learning based methods alike) but still achieves performance on a par with the prior art.
Rights: © 2020 IEEE.
DOI: 10.1109/CVPR42600.2020.00322
Grant ID:
Published version:
Appears in Collections:Aurora harvest 8
Computer Science publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.