Style-transfer GANs for bridging the domain gap in synthetic pose estimator training
Abstract
Given the dependency of current CNN architectures on a large training set, the possibility of using synthetic data is alluring as it allows generating a virtually infinite amount of labeled training data. However, producing such data is a non-trivial task as current CNN architectures are sensitive to the domain gap between real and synthetic data. We propose to adopt general-purpose GAN models for pixel-level image translation, allowing to formulate the domain gap itself as a learning problem. The obtained models are then used either during training or inference to bridge the domain gap. Here, we focus on training the single-stage YOLO6D object pose estimator on synthetic CAD geometry only, where not even approximate surface information is available. When employing paired GAN models, we use an edge-based intermediate domain and introduce different mappings to represent the unknown surface properties. Our evaluation shows a considerable improvement in model performance when compared to a model trained with the same degree of domain randomization, while requiring only very little additional effort.
- Publication:
-
arXiv e-prints
- Pub Date:
- April 2020
- arXiv:
- arXiv:2004.13681
- Bibcode:
- 2020arXiv200413681R
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition
- E-Print:
- doi:10.1109/AIVR50618.2020.00039