RenderGAN: Generating Realistic Labeled Data

RenderGAN: Generating Realistic Labeled Data

Deep Convolutional Neuronal Networks (DCNN) are showing remarkable performance on many computer vision tasks. Due to their large parameter space, they require many labeled samples when trained in a supervised setting. The costs of annotating data manually can render the usage of DCNNs infeasible. We present a novel framework called RenderGAN that can generate large amounts of realistic, labeled...

Generating Realistic Data Sets for Combinatorial Auctions

Generating Realistic TCP Workloads

The workload of a network is usually a heterogeneous aggregate of services and applications, driven by a large number of users. This complexity makes it challenging to evaluate the performance of network mechanisms and configurations under realistic conditions. We propose a new methodology for transforming anonymized traces of packet headers into application-neutral models of network traffic. T...

Generating Visemes for Realistic Animation

Efficient, realistic face animation is still a challenge. A system is proposed that yields realistic visemes for speech animation. This paper discusses the extraction of these visemes. It starts from real 3D face dynamics, observed at frame rate for thousands of points on the faces of speaking actors. A generic 3D mesh is fitted to the data throughout 3D time sequences. This is based on a combi...

Generating realistic scaled complex networks

Research on generative models plays a central role in the emerging field of network science, studying how statistical patterns found in real networks could be generated by formal rules. Output from these generative models is then the basis for designing and evaluating computational methods on networks including verification and simulation studies. During the last two decades, a variety of model...