TY - GEN
T1 - 3D object representations for fine-grained categorization
AU - Krause, Jonathan
AU - Stark, Michael
AU - Deng, Jia
AU - Fei-Fei, Li
PY - 2013
Y1 - 2013
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84897485170&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84897485170&partnerID=8YFLogxK
U2 - 10.1109/ICCVW.2013.77
DO - 10.1109/ICCVW.2013.77
M3 - Conference contribution
AN - SCOPUS:84897485170
SN - 9781479930227
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 554
EP - 561
BT - Proceedings - 2013 IEEE International Conference on Computer Vision Workshops, ICCVW 2013
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2013 14th IEEE International Conference on Computer Vision Workshops, ICCVW 2013
Y2 - 1 December 2013 through 8 December 2013
ER -