V. S. R. Veeravasarapu

Learn More
The use of simulated virtual environments to train deep convolutional neural networks (CNN) is a currently active practice to reduce the (real)data-hungriness of the deep CNN models, especially in application domains in which large scale real data and/or groundtruth acquisition is difficult or laborious. Recent approaches have attempted to harness the(More)
As the computer vision matures into a systems science<lb>and engineering discipline, there is a trend in leveraging<lb>latest advances in computer graphics simulations for per-<lb>formance evaluation, learning, and inference. However,<lb>there is an open question on the utility of graphics sim-<lb>ulations for vision with apparently contradicting views(More)
Rapid advances in computation, combined with latest advances in computer graphics simulations have facilitated the development of vision systems and training them in virtual environments. One major stumbling block is in certification of the designs and tuned parameters of these systems to work in real world. In this paper, we begin to explore the(More)
There is a growing interest to utilize Computer Graphics (CG) renderings to generate large scale annotated data in order to train machine learning systems, such as Deep convolutional neural networks, for Computer Vision (CV). However, there has been a long debate on the usefulness of CG generated data for tuning CV systems (even from the 1980's).(More)
Generalization performance of trained computer vision (CV) systems that use computer graphics (CG) generated data is not yet effective due to the concept of ’domainshift’ between virtual and real data. Although simulated data augmented with a few real-world samples has been shown to mitigate domain shift and improve transferability of trained models,(More)
  • 1