Sammy Lievens

16K Cinematic VR Streaming

We present an end-to-end system for streaming Cinematic Virtual Reality (VR) content (also called 360 or omnidirectional content). Content is captured and ingested at a resolution of 16K at 25Hz and streamed towards untethered mobile VR devices. Besides the usual navigation interactions such as panning and tilting offered by common VR systems, we also provide a zooming interactivity. This allows the VR client to fetch high quality pixels captured at a spatial resolution of 16K that greatly increase perceived quality compared to a 4K VR streaming solution. Since current client devices are not capable of receiving and decoding a 16K video, several optimizations are provided to only stream the required pixels for the current viewport of the user, while meeting strict latency and bandwidth requirements for a qualitative VR immersive experience.

A Prior-Based Approach to 3D Face Reconstruction Using Depth Images

We present a system for 3D face reconstruction that is based on live depth information combined with face priors. The system includes a stereo matching method that employs prior information for limiting the search space and introduces an offline scanned 3D model that is animated by means of 2D morphing techniques in order to match the live facial expressions. The resulting live- and synthetic depth images are combined and a live 3D mesh is generated. Computational aspects are taken into account for every part of the system, enabling a live face reconstruction system with the potential for real-time execution.

Stereo Matching Optimization by Means of Texture Analysis

The extraction of disparity data by means of stereo matching has well known issues in regions of low texture. This paper proposes a method which employs texture classification metrics in order to make predictions on the quality of the stereo matching output. Such predictions can then be used to alter the way the disparity data is used in further processing, or to even cancel processing of a pixel when the predicted quality is too low. Three metrics (based on laws, entropy and energy) are evaluated to this purpose on two stereo matching algorithms.

A real-time 3D end-to-end augmented reality system (and its representation transformations)

The new generation of HMDs coming to the market is expected to enable many new applications that allow free viewpoint experiences with captured video objects. Current applications usually rely on 3D content that is manually created or captured in an offline manner. In contrast, this paper focuses on augmented reality applications that use live captured 3D objects while maintaining free viewpoint interaction. We present a system that allows live dynamic 3D objects (e.g. a person who is talking) to be captured in real-time. Real-time performance is achieved by traversing a number of representation formats and exploiting their specific benefits. For instance, depth images are maintained for fast neighborhood retrieval and occlusion determination, while implicit surfaces are used to facilitate multi-source aggregation for both geometry and texture. The result is a 3D reconstruction system that outputs multi-textured triangle meshes at real-time rates. An end-to-end system is presented that captures and reconstructs live 3D data and allows for this data to be used on a networked (AR) device. For allocating the different functional blocks onto the available physical devices, a number of alternatives are proposed considering the available computational power and bandwidth for each of the components. As we will show, the representation format can play an important role in this functional allocation and allows for a flexible system that can support a highly heterogeneous infrastructure.