arXiv Analytics

Sign in

arXiv:1801.03910 [cs.CV]AbstractReferencesReviewsResources

Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction

Shubham Tulsiani, Alexei A. Efros, Jitendra Malik

Published 2018-01-11Version 1

We present a framework for learning single-view shape and pose prediction without using direct supervision for either. Our approach allows leveraging multi-view observations from unknown poses as supervisory signal during training. Our proposed training setup enforces geometric consistency between the independently predicted shape and pose from two views of the same instance. We consequently learn to predict shape in an emergent canonical (view-agnostic) frame along with a corresponding pose predictor. We show empirical and qualitative results using the ShapeNet dataset and observe encouragingly competitive performance to previous techniques which rely on stronger forms of supervision. We also demonstrate the applicability of our framework in a realistic setting which is beyond the scope of existing techniques: using a training dataset comprised of online product images where the underlying shape and pose are unknown.

Comments: Project url with code:
Categories: cs.CV
Related articles:
arXiv:1712.01261 [cs.CV] (Published 2017-12-02)
SfSNet : Learning Shape, Reflectance and Illuminance of Faces in the Wild
arXiv:1106.5186 [cs.CV] (Published 2011-06-26)
Learning Shape and Texture Characteristics of CT Tree-in-Bud Opacities for CAD Systems