XClose

Robotics

Menu

Curiosity-driven 3D Object Detection without Labels

To recover the position, orientation, colour, and illumination for every relevant object in the scene given only the 3D geometric representation and unlabelled 2D images.

curiosity-driven_3d_object_detection_without_labels

15 October 2021

Research Team

David Griffiths | Jan Boehm | Tobias Ritschel

Technology Areas

A.I., Machine Learning and Deep Learning

Abstract

We present a novel method for self-supervised scene parameterisation from a single image and geometric representation. We achieve this by employing analysis-by-synthesis using a differentiable renderer. We show that a simple L2 loss is not sufficient for such a task. Instead, we introduce a GAN-like critic to constrain the network to propose realistic outputs. By adding such a constraint, we observe the L2 loss is now sufficient to solve a number of tasks on both synthetic and real data.

Publication: PDF