Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction
This addresses the challenge of 3D reconstruction from images without labeled data, though it is incremental as it builds on existing multi-view consistency ideas.
The paper tackles the problem of learning single-view shape and pose prediction without direct supervision by using multi-view consistency as a supervisory signal, achieving competitive performance on ShapeNet and demonstrating applicability to online product images.
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.