Possible Bodies

Simulated+Unsupervised (S+U) learning

Item number: 063
Item title: Simulated+Unsupervised (S+U) learning
Entry of the item into the inventory: 22 July 2017
Inventor(s) for this item: Possible Bodies

automatic refinement of depth:

"learning from synthetic images may not achieve the desired performance due to a gap between synthetic and real image distributions. To reduce this gap, we propose Simulated+Unsupervised (S+U) learning, where the task is to learn a model to improve the realism of a simulator's output using unlabeled real data, while preserving the annotation information from the simulator. "

full article: https://arxiv.org/abs/1612.07828

source: http://imgexhaust.tumblr.com/post/155185196894/httpsarxivorgabs161207828

edit