DocumentCode :
3428096
Title :
Parsing IKEA Objects: Fine Pose Estimation
Author :
Lim, Jasmine J. ; Pirsiavash, Hamed ; Torralba, Antonio
Author_Institution :
Compter Sci. & Artificial Intell. Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA
fYear :
2013
fDate :
1-8 Dec. 2013
Firstpage :
2992
Lastpage :
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.
Keywords :
image matching; object detection; pose estimation; solid modelling; IKEA object parsing; candidate pose; exact 3D model matching; fine-aligned objects; global alignment; local keypoint detectors; object detection; object fine-pose estimation; objects fine-pose localization; Computational modeling; Design automation; Estimation; Image edge detection; Shape; Solid modeling; Three-dimensional displays;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision (ICCV), 2013 IEEE International Conference on
Conference_Location :
Sydney, VIC
ISSN :
1550-5499
Type :
conf
DOI :
10.1109/ICCV.2013.372
Filename :
6751483
Link To Document :
بازگشت