English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

Learning a Disentangled Embedding for Monocular 3D Shape Retrieval and Pose Estimation

MPS-Authors
/persons/resource/persons206382

Xu,  Weipeng
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons203020

Sun,  Qianru
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

/persons/resource/persons45610

Theobalt,  Christian
Computer Graphics, MPI for Informatics, Max Planck Society;

External Ressource
No external resources are shared
Fulltext (public)

arXiv:1812.09899.pdf
(Preprint), 3MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Lin, K. Z., Xu, W., Sun, Q., Theobalt, C., & Chua, T.-S. (2018). Learning a Disentangled Embedding for Monocular 3D Shape Retrieval and Pose Estimation. Retrieved from http://arxiv.org/abs/1812.09899.


Cite as: http://hdl.handle.net/21.11116/0000-0002-D519-2
Abstract
We propose a novel approach to jointly perform 3D object retrieval and pose estimation from monocular images.In order to make the method robust to real world scene variations in the images, e.g. texture, lighting and background,we learn an embedding space from 3D data that only includes the relevant information, namely the shape and pose.Our method can then be trained for robustness under real world scene variations without having to render a large training set simulating these variations. Our learned embedding explicitly disentangles a shape vector and a pose vector, which alleviates both pose bias for 3D shape retrieval and categorical bias for pose estimation. Having the learned disentangled embedding, we train a CNN to map the images to the embedding space, and then retrieve the closest 3D shape from the database and estimate the 6D pose of the object using the embedding vectors. Our method achieves 10.8 median error for pose estimation and 0.514 top-1-accuracy for category agnostic 3D object retrieval on the Pascal3D+ dataset. It therefore outperforms the previous state-of-the-art methods on both tasks.