Abstract
We propose a multiview model of appearance of objects that explicitly represents their variations of appearance with respect to their 3D pose. This results in a probabilistic, generative model capable of precisely synthesizing novel views of the learned object in arbitrary poses, not limited to the discrete set of trained viewpoints. We show how to use this model on the task of localization and full pose estimation in 2D images, which benefits from its particular capabilities in two ways. First, the generative model is used to improve the precision of the pose estimate much beyond nearest-neighbour matching with training views. Second, the pose/appearance relations stored within the model are used to resolve ambiguous test cases (e.g. an object facing towards/away from the camera). Here, changes of appearance as a function of incremental pose changes are detected in the test scene, using a pair or triple of views, and are then matched with those stored in the model. We demonstrate the effectiveness of this method on several datasets of very different nature, and show results superior to state-of-the-art methods in terms of accuracy. The pose estimation of textureless objects in cluttered scenes also benefits from the proposed contributions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Avidan, S., Shashua, A.: Novel view synthesis in tensor space. In: CVPR (1997)
Chen, S.E., Williams, L.: View interpolation for image synthesis. In: SIGGRAPH (1993)
Chen, S., Li, Y., Kwok, N.M.: Active vision in robotic systems: A survey of recent developments. Int. J. of Rob. Res. 30(11), 1343–1377 (2011)
Johansson, B., Moe, A.: Patch-duplets for object recognition and pose estimation. In: CRV (2005)
Kushal, A., Schmid, C., Ponce, J.: Flexible object models for category-level 3D object recognition. In: CVPR (2007)
Liu, C.: Beyond Pixels: Exploring New Representations and Applications for Motion Analysis. Ph.D. thesis. MIT (2009)
Martinez Torres, M., Collet Romea, A., Srinivasa, S.: MOPED: A scalable and low latency object recognition and pose estimation system. In: ICRA (2010)
Ozuysal, M., Lepetit, V., Fua, P.: Pose estimation for category specific multiview object localization. In: CVPR (2009)
Savarese, S., Fei-Fei, L.: View synthesis for recognizing unseen poses of object classes. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 602–615. Springer, Heidelberg (2008)
Savarese, S., Fei-Fei, L.: 3D generic object categorization, localization and pose estimation. In: IEEE Int. Conf. on Comp. Vis. (2007)
Seitz, S.M., Dyer, C.R.: Toward image-based scene representation using view morphing. In: Int. Conf. on Patt. Rec., pp. 84–89 (1996)
Sipe, M.A., Casasent, D.: Best viewpoints for active vision classification and pose estimation. In: Intelligent Robots and Comp. Vis., pp. 382–393 (1997)
Sun, M., Su, H., Savarese, S., Fei-Fei, L.: A multi-view probabilistic model for 3D object classes. In: CVPR (2009)
Teney, D., Piater, J.: Generalized Exemplar-Based Full Pose Estimation from 2D Images without Correspondences. In: DICTA (2012)
Teney, D., Piater, J.: Continuous pose estimation in 2D images at instance and category levels (submitted, 2013)
Thomas, A., Ferrari, V., Leibe, B., Tuytelaars, T., Schiel, B., Van Gool, L.: Towards multi-view object class detection. In: CVPR (2006)
Torki, M., Elgammal, A.M.: Regression from local features for viewpoint and pose estimation. In: ICCV (2011)
Vikstén, F., Soderberg, R., Nordberg, K., Perwass, C.: Increasing pose estimation performance using multi-cue integration. In: ICRA (2006)
Vikstén, F., Forssén, P.E., Johansson, B., Moe, A.: Comparison of local image descriptors for full 6 degree-of-freedom pose estimation. In: ICRA (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Teney, D., Piater, J. (2013). Modeling Pose/Appearance Relations for Improved Object Localization and Pose Estimation in 2D images. In: Sanches, J.M., Micó, L., Cardoso, J.S. (eds) Pattern Recognition and Image Analysis. IbPRIA 2013. Lecture Notes in Computer Science, vol 7887. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38628-2_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-38628-2_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38627-5
Online ISBN: 978-3-642-38628-2
eBook Packages: Computer ScienceComputer Science (R0)