Parsing IKEA Objects: Fine Pose Estimation

Joseph J. Lim, Hamed Pirsiavash, Antonio Torralba; The IEEE International Conference on Computer Vision (ICCV), 2013, pp. 2992-2999

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Lim_2013_ICCV,
author = {Lim, Joseph J. and Pirsiavash, Hamed and Torralba, Antonio},
title = {Parsing IKEA Objects: Fine Pose Estimation},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2013}
}