Latency in Virtual Reality (VR) applications can have numerous detrimental effects, e.g., a hampered user experience, a reduced user performance, or the occurrence of cybersickness. In VR environments, latency usually is measured as Motion-to-Photon (MTP) latency and reported as a mean value. This mean is taken during some specific intervals of sample runs with the target system, often detached in significant aspects from the final target scenario, to provide the necessary boundary conditions for the measurements. Additionally, the reported mean value is agnostic to dynamic and spiking latency behavior. This paper introduces an apparatus that is capable of determining per-frame MTP latency to capture dynamic MTP latency and latency jitter in addition to the commonly reported mean values of latency. The approach is evaluated by measuring MTP latency of a VR simulation based on the Unreal engine and the HTC Vive as a typical consumer-grade Head-Mounted Display (HMD). In contrast to previous approaches, the system does not rely on the HMD to be fixed to an external apparatus, can be used to assess any simulation setup, and can be extended to continuously measure latency during run-time. We evaluate the accuracy of our apparatus by injecting a controlled artificial latency in a VR simulation. We show that latency jitter artifacts already occur without system load, potentially caused by the tracking of the specific HMD, and how mean latency and jitter increase under system load, leading to dropped frames and an overall degraded system performance. The presented system can be used to monitor latency and latency jitter as critical simulation characteristics necessary to report and control to avoid unwanted effects and detrimental system performance.

This article investigates performance and user experience in Social Virtual Reality (SVR) targeting distributed, embodied, and immersive, face-to-face encounters. We demonstrate the close relationship between scalability, reproduction accuracy, and the resulting performance characteristics, as well as the impact of these characteristics on users co-located with larger groups of embodied virtual others. System scalability provides a variable number of co-located avatars and Al-controlled agents with a variety of different appearances, including realistic-looking virtual humans generated from photogrammetry scans. The article reports on how to meet the requirements of embodied SVR with today's technical off-the-shelf solutions and what to expect regarding features, performance, and potential limitations. Special care has been taken to achieve low latencies and sufficient frame rates necessary for reliable communication of embodied social signals. We propose a hybrid evaluation approach which coherently relates results from technical benchmarks to subjective ratings and which confirms required performance characteristics for the target scenario of larger distributed groups. A user-study reveals positive effects of an increasing number of co-located social companions on the quality of experience of virtual worlds, i.e., on presence, possibility of interaction, and co-presence. It also shows that variety in avatar/agent appearance might increase eeriness but might also stimulate an increased interest of participants about the environment.

Low latency is a fundamental requirement for Virtual Reality (VR) systems to reduce the potential risks of cybersickness and to increase effectiveness, efficiency and user experience. In contrast to the effects of uniform latency degradation, the influence of latency jitter on user experience in VR is not well researched, although today's consumer VR systems are vulnerable in this respect. In this work we report on the impact of latency jitter on cybersickness in HMD-based VR environments. Test subjects are given a search task in Virtual Reality, provoking both head rotation and translation. One group experienced artificially added latency jitter in the tracking data of their head-mounted display. The introduced jitter pattern was a replication of a real-world latency behavior extracted and analyzed from an existing example VR-system. The effects of the introduced latency jitter were measured based on self-reports simulator sickness questionnaire (SSQ) and by taking physiological measurements. We found a significant increase in self-reported simulator sickness. We therefore argue that measure and control of latency based on average values taken at a few time intervals is not enough to assure a required timeliness behavior but that latency jitter needs to be considered when designing experiences for Virtual Reality.

Latency jitter is a pressing problem in Virtual Reality (VR) applications. This paper analyzes latency jitter caused by typical interprocess communication (IPC) techniques commonly found in today's computer systems used for VR. Test programs measure the scalability and latencies for various IPC techniques, where increasing number of threads are performing the same task concurrently. We use four different implementations on a vanilla Linux kernel as well as on a real-time (RT) Linux kernel to further assess if a RT variant of a multiuser multiprocess operating system can prevent latency spikes and how this behavior would apply to different programming languages and IPC techniques. We found that Linux RT can limit the latency jitter at the cost of throughput for certain implementations. Further, coarse grained concurrency should be employed to avoid adding up of scheduler latencies, especially for native system space IPC, while actor systems are found to support a higher degree of concurrency granularity and a higher level of abstraction.

A low latency is a fundamental timeliness requirement to reduce the potential risks of cyber sickness and to increase effectiveness, efficiency, and user experience of Virtual Reality Systems. The effects of uniform latency degradation based on mean or worst-case values are well researched. In contrast, the effects of latency jitter, the distribution pattern of latency changes over time has largely been ignored so far although today's consumer VR systems are extremely vulnerable in this respect. We investigate the applicability of the Walsh, generalized ESD, and the modified z-score test for the detection of outliers as one central latency distribution aspect. The tests are applied to well defined test cases mimicking typical timing behavior expected from concurrent architectures of today. We introduce accompanying graphical visualization methods to inspect, analyze and communicate the latency behavior of VR systems beyond simple mean or worst-case values. As a result, we propose a stacked modified z-score test for more detailed analysis.