Parsing IKEA Objects: Fine Pose Estimation

Thumbnail Image

Files

ikea_iccv2013.pdf (1.52 MB)

Links to Files

https://ieeexplore.ieee.org/abstract/document/6751483

Permanent Link

https://doi.org/10.1109/ICCV.2013.372
 http://hdl.handle.net/11603/14317

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection

Author/Creator

Author/Creator ORCID

Date

2013-12-03

Type of Work

conference papers and proceedings preprints
Text

Department

Program

Citation of Original Publication

Joseph J. Lim, et.al, Parsing IKEA Objects: Fine Pose Estimation, 2013 IEEE International Conference on Computer Vision, DOI: 10.1109/ICCV.2013.372

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
© 2013 IEEE

Subjects

Three-dimensional displays
Solid modeling
Image edge detection
Estimation
Design automation
Computational modeling
image matching
IKEA object parsing

Abstract

We address the problem of localizing and estimating the fine-pose of objects in the image with exact 3D models. Our main focus is to unify contributions from the 1970s with recent advances in object detection: use local keypoint detectors to find candidate poses and score global alignment of each candidate pose to the image. Moreover, we also provide a new dataset containing fine-aligned objects with their exactly matched 3D models, and a set of models for widely used objects. We also evaluate our algorithm both on object detection and fine pose estimation, and show that our method outperforms state-of-the art algorithms.