Jointly Optimizing 3D Model Fitting and Fine-Grained Classification

Yen-Liang Lin¹, Vlad I. Morariu², Winston Hsu¹, and Larry S. Davis²

¹National Taiwan University, Taipei, Taiwan
yenliang@cmlab.csie.ntu.edu.tw
whsu@ntu.edu.tw

²University of Maryland, College Park, MD, USA
morariu@umiacs.umd.edu
lsd@umiacs.umd.edu

Abstract. 3D object modeling and fine-grained classification are often treated as separate tasks. We propose to optimize 3D model fitting and fine-grained classification jointly. Detailed 3D object representations encode more information (e.g., precise part locations and viewpoint) than traditional 2D-based approaches, and can therefore improve fine-grained classification performance. Meanwhile, the predicted class label can also improve 3D model fitting accuracy, e.g., by providing more detailed class-specific shape models. We evaluate our method on a new fine-grained 3D car dataset (FG3DCar), demonstrating our method outperforms several state-of-the-art approaches. Furthermore, we also conduct a series of analyses to explore the dependence between fine-grained classification performance and 3D models.

LNCS 8692, p. 466 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer International Publishing Switzerland 2014