3D Object Representations for Fine-Grained Categorization
Jonathan Krause, Michael M. Stark, Jia Hao Deng et al. · IEEE International Conference on Computer Vision Workshops · 2013
While 3D object representations are being revived in the context of multi-view object class detection and scene understanding, they have not yet attained wide-spread use in fine-grained categorization. State-of-the-art approaches achieve remarkable performance when training data is plentiful, but they are typically tied to flat, 2D representations that model objects as a collection of unconnected views, limiting their ability to generalize across viewpoints. In this paper, we therefore lift two state-of-the-art 2D object representations to 3D, on the level of both local feature appearance and location. In extensive experiments on existing and newly proposed datasets, we show our 3D object representations outperform their state-of-the-art 2D counterparts for fine-grained categorization and demonstrate their efficacy for estimating 3D geometry from images via ultra-wide baseline matching and 3D reconstruction.
Cited by 3,496 works. doi:10.1109/iccvw.2013.77
Authors
References
- Distinctive Image Features from Scale-Invariant Keypoints
- Histograms of Oriented Gradients for Human Detection
- Object Detection with Discriminatively Trained Part-Based Models
- Multiple View Geometry in Computer Vision
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
- Visual categorization with bags of keypoints
- Poselets: Body part detectors trained using 3D human pose annotations
- Locality-constrained Linear Coding for image classification
- Putting Objects in Perspective
- Automated Flower Classification over a Large Number of Classes