Scene-Space Video Processing
Abstract
The high degree of redundancy in video footage allows compensating for noisy depth estimates and to achieve various high-quality processing effects such as denoising, deblurring, super resolution, object removal, computational shutter functions, and scene-space camera effects.
Publications
Efficient GPU Based Sampling for Scene-Space Video Processing
in Proc. Vision, Modeling and Visualization (VMV), pp. 103-110, October 2015.
Sampling Based Scene-Space Video Processing
in ACM Transactions on Graphics (Proc. of Siggraph), vol. 34, no. 4, pp. 67:1-67:11, August 2015.
ACM Siggraph 2015 paper
Related Projects
The goal of this project is to augment video data with high-quality 3D geometry, while only using a single camera as input. As an application of this project, we want to dress a person in a video with artificial clothing. We reconstruct a 3D human pose from 2D input data. This information can be used to drive a cloth simulation creating a plausible 3D garment for the observed pose. Composing this animated garment into the original video creates the illusion of the person wearing different clothing. We aim at real-time frame rates for this system, allowing for virtual mirror applications.
Scope of "Reality CG" is to pioneer a novel approach to modelling, editing and rendering in computer graphics. Instead of manually creating digital models of virtual worlds, Reality CG will explore new ways to achieve visual realism from the kind of approximate models that can be derived from conventional, real-world imagery as input.