3D Object Representations for Fine-Grained Categorization
Citations Over TimeTop 1% of 2013 papers
Abstract
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.
Related Papers
- → Object recognition and 3D reconstruction of occluded objects using binocular stereo(2017)24 cited
- → Object Recognition Method for Industrial Intelligent Robot(2013)7 cited
- → A feature matching method for simultaneous localization and mapping(2017)3 cited
- → Towards Object Detection from Motion(2019)1 cited
- An object recognition and localization system designed for robots based on image processing(2008)