3 papers
cs.CV2021
Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans
Ainaz Eftekhar, Alexander Sax, Roman Bachmann +2
This paper introduces a pipeline to parametrically sample and render multi-task vision datasets from comprehensive 3D scans from the real world. Changing the sampling parameters al…
cs.LG2020
Training Binary Neural Networks using the Bayesian Learning Rule
Xiangming Meng, Roman Bachmann, Mohammad Emtiyaz Khan
Neural networks with binary weights are computation-efficient and hardware-friendly, but their training is challenging because it involves a discrete optimization problem. Surprisi…
cs.CV2019
Motion Capture from Pan-Tilt Cameras with Unknown Orientation
Roman Bachmann, Jörg Spörri, Pascal Fua +1
In sports, such as alpine skiing, coaches would like to know the speed and various biomechanical variables of their athletes and competitors. Existing methods use either body-worn…