Abstract: Natural images exhibit high information correlation across pixels. Bilateral filtering provides a simple yet powerful framework for information propagation across pixels. The common use-case is to manually choose a parametric filter type, usually a Gaussian filter. We generalize the parameterization using a high-dimensional linear approximation and derive a gradient descent algorithm so the filter parameters can be learned from data. We demonstrate the use of learned bilateral filters in several applications where Gaussian bilateral filters are traditionally employed where we consistently observed improvements with filter learning. In addition, the ability to learn generic high-dimensional sparse filters allows us to stack several parallel and sequential filters like in convolutional neural networks (CNN) resulting in a new breed of neural networks which we call ‘Bilateral Neural Networks’ (BNN). We demonstrate the use of BNNs on several 2D, video and 3D vision tasks. Experiments on diverse datasets and tasks demonstrate the use BNNs for a range of vision problems.
Bio: Varun Jampani works as a research scientist at Nvidia Research in Westford, US. He obtained his PhD at Max Planck Institute for Intelligent Systems (MPI) in Tübingen, Germany under the supervision of Prof. Peter V. Gehler. He works in the areas of machine learning and computer vision and his main research interests include probabilistic inference and neural networks. He obtained his BTech and MS from International Institute of Information Technology, Hyderabad (IIIT-H), India, where he was a gold medalist. During his studies, he did internships at Microsoft research institutes in Redmond (US), Cambridge (UK) and Cairo (Egypt); MPI, Tübingen (Germany) and; GE global research, Bangalore (India). He also worked as a volunteer teacher in Tibetan Children’s Village, Dharamsala, India.