Section: New Software and Platforms

LCR-Net

Localization-Classification-Regression Network for Human Pose

Keywords: Object detection - Recognition of human movement

Functional Description: We propose an end-to-end architecture for joint 2D and 3D human pose estimation in natural images. Key to our approach is the generation and scoring of a number of pose proposals per image, which allows us to predict 2D and 3D pose of multiple people simultaneously. Our architecture contains 3 main components: 1) the pose proposal generator that suggests potential poses at different locations in the image, 2) a classifier that scores the different pose proposals , and 3) a regressor that refines pose proposals both in 2D and 3D.

• Participants: Grégory Rogez, Philippe Weinzaepfel and Cordelia Schmid

• Partner: Naver Labs Europe

• Contact: Nicolas Jourdan

• Publication: LCR-Net: Localization-Classification-Regression for Human Pose

• URL: https://thoth.inrialpes.fr/src/LCR-Net/