Oral
Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
Supasorn Suwajanakorn · Noah Snavely · Jonathan Tompson · Mohammad Norouzi

Thu Dec 6th 03:50 -- 04:05 PM @ Room 220 E
in Thu Track 2 -- Session 2 »

This paper presents KeypointNet, an end-to-end geometric reasoning framework to learn an optimal set of category-specific keypoints, along with their detectors to predict 3D keypoints in a single 2D input image. We demonstrate this framework on 3D pose estimation task by proposing a differentiable pose objective that seeks the optimal set of keypoints for recovering the relative pose between two views of an object. Our network automatically discovers a consistent set of keypoints across viewpoints of a single object as well as across all object instances of a given object class. Importantly, we find that our end-to-end approach using no ground-truth keypoint annotations outperforms a fully supervised baseline using the same neural network architecture for the pose estimation task. The discovered 3D keypoints across the car, chair, and plane categories of ShapeNet are visualized at https://keypoints.github.io/

Author Information

Supasorn Suwajanakorn (VISTEC)
Noah Snavely (Google)
Jonathan Tompson (Google Brain)
Mohammad Norouzi (Google Brain)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors