Director's Cut

In this project, we analyse how end-users view 360° video in the presence of directional cues and evaluate if they are able to follow the actual story of narrative 360° films.

QualityVR

360-degree video, also called live-action virtual reality (VR), is one of the latest and most powerful trends in immersive media, with an increasing potential for the next decades. 

Video Coding and Streaming for VR Applications

With technical advances in virtual reality (VR) devices, the media technology field is evolving toward providing immersive VR video experiences. 

Visual Attention in 360-Video

Understanding visual attention has always been a topic of great interest in different research communities. This is particularly important in omnidirectional images (ODIs) viewed with a head-mounted display (HMD), where only a fraction of the captured scene is displayed at a time, namely viewport.

Light Field Imaging Technologies

Light fields capture all light rays passing through a given volume of space.

Compared to traditional 2D imaging systems which capture the spatial intensity of the light rays, 4D light fields also contain the angular direction of light rays.

Deformable Surface Tracking

The AutoPost tracking plugins aim to automate major parts of the daily workload in audio-visual post-production and, with it, to make post-production more efficient by reducing time-consuming and costly manual processing. 

Depth-enabled Post-production Workflows

3FLEX is a new advanced workflow for flexible 2D and multiview video production capable to deal with and take advantage of the Video + Depth content approach and to develop the building blocks to implement it. 

Scribble-based 2D-to-3D Conversion

The user scribbles depth values into objects or areas of a selected key- frame and the software estimates a dense depth map by propagating the depth values between all pixels within this frame and over time using sophisticated and proprietary computer vision algorithms.

Realistic Stereo-view Synthesis using Structure-from-Motion

A new approach for the generation of super-resolution stereoscopic and multi-view video from monocular video which is based on structure from motion techniques and image-based rendering to generate the desired stereoscopic views for each point in time.