Deep Generative Video Compression

The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy. Here, we propose an end-to-end, deep generative modeling approach to compress temporal sequences with a focus on video. Our approach builds upon variational autoencoder (VAE) models for sequential data and combines them with recent work on neural image compression.

Learn More




Light Field Video Synthesis Using Inexpensive Surveillance Camera Systems

We present a light field video synthesis technique that can achieve accurate reconstruction given a low-cost, widebaseline camera rig. Our system called, INDiuM, novelly integrates optical flow with methods for rectification, disparity estimation, and feature extraction, which we then feed to a neural network view synthesis solver with widebaseline capability. A new bi-directional warping approach resolves reprojection ambiguities that would result from either backward or forward warping only. The system and method enables the use of off-the-shelf surveillance camera hardware in a simplified and expedited capture workflow. A thorough analysis of the refinement process and resulting view synthesis accuracy over state of the art is provided.

Learn More


Smile Intensity Detection in Multiparty Interaction using Deep Learning

Emotion expression recognition is an important aspect for enabling decision making in autonomous agents and systems designed to interact with humans. In this paper, we present our experience in developing a software component for smile intensity detection for multiparty interaction. First, the deep learning architecture and training process is described in detail. This is followed by analysis of the results obtained from testing the trained network. Finally, we outline the steps taken to implement and visualize this network in a real-time software component.

Learn More