Parsing IKEA Objects: Fine Pose Estimation

• Main Authors: Pirsiavash, Hamed (Contributor), Torralba, Antonio (Contributor), Lim, Joseph Jaewhan (Contributor)
• Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
• Format: Article
• Language: English
• Published: Institute of Electrical and Electronics Engineers (IEEE), 2014-10-20T14:55:48Z.
• Subjects: Article
• Online Access: Get fulltext

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.
United States. Office of Naval Research. Multidisciplinary University Research Initiative (N000141010933)