Christian Timmerer

Reza Farahani, Zoha Azimi, Vignesh V Menon et al.

Adaptive streaming of segmented video over HTTP typically relies on a predefined set of bitrate-resolution pairs, known as a bitrate ladder. However, fixed ladders often overlook variations in content and decoding complexities, leading to suboptimal trade-offs between encoding time, decoding efficiency, and video quality. This article introduces DQ-Ladder, a deep reinforcement learning (DRL)-based scheme for constructing time- and quality-aware bitrate ladders for adaptive video streaming applications. DQ-Ladder employs predicted decoding time, quality scores, and bitrate levels per segment as inputs to a Deep Q-Network (DQN) agent, guided by a weighted reward function of decoding time, video quality, and resolution smoothness. We leverage machine learning models to predict decoding time, bitrate level, and objective quality metrics (VMAF, XPSNR), eliminating the need for exhaustive encoding or quality metric computation. We evaluate DQ-Ladder using the Versatile Video Coding (VVC) toolchain (VVenC/VVdeC) on 750 video sequences across six Apple HLS-compliant resolutions and 41 quantization parameters. Experimental results against four baselines show that DQ-Ladder achieves BD-rate reductions of at least 10.3% for XPSNR compared to the HLS ladder, while reducing decoding time by 22%. DQ-Ladder shows significantly lower sensitivity to prediction errors than competing methods, remaining robust even with up to 20% noise.

Emanuele Artioli, Philipp Fößl, Daniele Lorenzi et al.

Recent advancements in 3D Gaussian Splatting (3DGS) have enabled photorealistic rendering of complex scenes, yet widespread adoption on mobile and Extended Reality (XR) devices is hindered by substantial computational and bandwidth requirements. While existing solutions often focus on model compression for client-side rendering, they still demand significant GPU power, limiting applicability on resource-constrained hardware. We propose TIGAS (Thin-client Interactive Gaussian Adaptive Streaming), a remote rendering framework offloading rasterization to a backend. To bypass the prohibitive latencies connected to fluctuating network conditions, TIGAS streams view-dependent 2D projections to a lightweight web client over QUIC, minimizing head-of-line (HoL) blocking. A dedicated ABR algorithm adapts rendering quality to fluctuating network conditions, maintaining motion-to-photon latency within strict 6DoF interactive constraints. Furthermore, we discuss the integration of an experimental WebGPU super-resolution pipeline to analyze the trade-offs between perceptual quality enhancements and thin-client processing bottlenecks. We extensively evaluate TIGAS across multi-continental environments using 14 3DGS models and real 6DoF EyeNavGS movement traces. Powered by a backend rendering frames in under 10 milliseconds, TIGAS maintains latency within interactive thresholds while achieving an average SSIM of 0.88, serving both as a robust testbed for 3DGS streaming research and a capable delivery system. The source code is available at: https://github.com/Rekenar/GaussianAdaptiveStreamer.

Emanuele Artioli, Farzad Tashtarian, Christian Timmerer

The primary challenge of video streaming is to balance high video quality with smooth playback. Traditional codecs are well tuned for this trade-off, yet their inability to use context means they must encode the entire video data and transmit it to the client. This paper introduces ELVIS (End-to-end Learning-based VIdeo Streaming Enhancement Pipeline), an end-to-end architecture that combines server-side encoding optimizations with client-side generative in-painting to remove and reconstruct redundant video data. Its modular design allows ELVIS to integrate different codecs, inpainting models, and quality metrics, making it adaptable to future innovations. Our results show that current technologies achieve improvements of up to 11 VMAF points over baseline benchmarks, though challenges remain for real-time applications due to computational demands. ELVIS represents a foundational step toward incorporating generative AI into video streaming pipelines, enabling higher quality experiences without increased bandwidth requirements.

Ekrem Çetinkaya, Minh Nguyen, Christian Timmerer

Deep neural network (DNN) based approaches have been intensively studied to improve video quality thanks to their fast advancement in recent years. These approaches are designed mainly for desktop devices due to their high computational cost. However, with the increasing performance of mobile devices in recent years, it became possible to execute DNN based approaches in mobile devices. Despite having the required computational power, utilizing DNNs to improve the video quality for mobile devices is still an active research area. In this paper, we propose an open-source mobile platform, namely MoViDNN, to evaluate DNN based video quality enhancement methods, such as super-resolution, denoising, and deblocking. Our proposed platform can be used to evaluate the DNN based approaches both objectively and subjectively. For objective evaluation, we report common metrics such as execution time, PSNR, and SSIM. For subjective evaluation, Mean Score Opinion (MOS) is reported. The proposed platform is available publicly at https://github.com/cd-athena/MoViDNN

Anatoliy Zabrovskiy, Evgeny Petrov, Evgeny Kuzmin et al.

Adaptive video streaming over HTTP is becoming omnipresent in our daily life. In the past, dozens of research papers have proposed novel approaches to address different aspects of adaptive streaming and a decent amount of player implementations (commercial and open source) are available. However, state of the art evaluations are sometimes superficial as many proposals only investigate a certain aspect of the problem or focus on a specific platform - player implementations used in actual services are rarely considered. HTML5 is now available on many platforms and foster the deployment of adaptive media streaming applications. We propose a common evaluation framework for adaptive HTML5 players and demonstrate its applicability by evaluating eight different players which are actually deployed in real-world services.

Wei Zhou, Hadi Amirpour, Christian Timmerer et al.

As multimedia services such as video streaming, video conferencing, virtual reality (VR), and online gaming continue to expand, ensuring high perceptual visual quality becomes a priority to maintain user satisfaction and competitiveness. However, multimedia content undergoes various distortions during acquisition, compression, transmission, and storage, resulting in the degradation of experienced quality. Thus, perceptual visual quality assessment (PVQA), which focuses on evaluating the quality of multimedia content based on human perception, is essential for optimizing user experiences in advanced communication systems. Several challenges are involved in the PVQA process, including diverse characteristics of multimedia content such as image, video, VR, point cloud, mesh, multimodality, etc., and complex distortion scenarios as well as viewing conditions. In this paper, we first present an overview of PVQA principles and methods. This includes both subjective methods, where users directly rate their experiences, and objective methods, where algorithms predict human perception based on measurable factors such as bitrate, frame rate, and compression levels. Based on the basics of PVQA, quality predictors for different multimedia data are then introduced. In addition to traditional images and videos, immersive multimedia and generative artificial intelligence (GenAI) content are also discussed. Finally, the paper concludes with a discussion on the future directions of PVQA research.

MohammadAli Hamidi, Hadi Amirpour, Luigi Atzori et al.

Face image quality assessment (FIQA) plays a critical role in face recognition and verification systems, especially in uncontrolled, real-world environments. Although several methods have been proposed, general-purpose no-reference image quality assessment techniques often fail to capture face-specific degradations. Meanwhile, state-of-the-art FIQA models tend to be computationally intensive, limiting their practical applicability. We propose a lightweight and efficient method for FIQA, designed for the perceptual evaluation of face images in the wild. Our approach integrates an ensemble of two compact convolutional neural networks, MobileNetV3-Small and ShuffleNetV2, with prediction-level fusion via simple averaging. To enhance alignment with human perceptual judgments, we employ a correlation-aware loss (MSECorrLoss), combining mean squared error (MSE) with a Pearson correlation regularizer. Our method achieves a strong balance between accuracy and computational cost, making it suitable for real-world deployment. Experiments on the VQualA FIQA benchmark demonstrate that our model achieves a Spearman rank correlation coefficient (SRCC) of 0.9829 and a Pearson linear correlation coefficient (PLCC) of 0.9894, remaining within competition efficiency constraints.

Yiying Wei, Hadi Amirpour, Jong Hwan Ko et al.

Leveraging the overfitting property of deep neural networks (DNNs) is trending in video delivery systems to enhance quality within bandwidth limits. Existing approaches transmit overfitted super-resolution (SR) model streams for low-resolution (LR) bitstreams, which are used to reconstruct high-resolution (HR) videos at the decoder. Although these approaches show promising results, the huge computational costs of training a large number of video frames limit their practical applications. To overcome this challenge, we propose an efficient patch sampling method named EPS for video SR network overfitting, which identifies the most valuable training patches from video frames. To this end, we first present two low-complexity Discrete Cosine Transform (DCT)-based spatial-temporal features to measure the complexity score of each patch directly. By analyzing the histogram distribution of these features, we then categorize all possible patches into different clusters and select training patches from the cluster with the highest spatial-temporal information. The number of sampled patches is adaptive based on the video content, addressing the trade-off between training complexity and efficiency. Our method reduces the number of patches for the training to 4% to 25%, depending on the resolution and number of clusters, while maintaining high video quality and significantly enhancing training efficiency. Compared to the state-of-the-art patch sampling method, EMT, our approach achieves an 83% decrease in overall run time.

Jesús Aguilar-Armijo, Ekrem Çetinkaya, Christian Timmerer et al.

As the video streaming traffic in mobile networks is increasing, improving the content delivery process becomes crucial, e.g., by utilizing edge computing support. At an edge node, we can deploy adaptive bitrate (ABR) algorithms with a better understanding of network behavior and access to radio and player metrics. In this work, we present ECAS-ML, Edge Assisted Adaptation Scheme for HTTP Adaptive Streaming with Machine Learning. ECAS-ML focuses on managing the tradeoff among bitrate, segment switches, and stalls to achieve a higher quality of experience (QoE). For that purpose, we use machine learning techniques to analyze radio throughput traces and predict the best parameters of our algorithm to achieve better performance. The results show that ECAS-ML outperforms other client-based and edge-based ABR algorithms.

Ekrem Cetinkaya, Hadi Amirpour, Mohammad Ghanbari et al.

High-Efficiency Video Coding (HEVC) surpasses its predecessors in encoding efficiency by introducing new coding tools at the cost of an increased encoding time-complexity. The Coding Tree Unit (CTU) is the main building block used in HEVC. In the HEVC standard, frames are divided into CTUs with the predetermined size of up to 64x64 pixels. Each CTU is then divided recursively into a number of equally sized square areas, known as Coding Units (CUs). Although this diversity of frame partitioning increases encoding efficiency, it also causes an increase in the time complexity due to the increased number of ways to find the optimal partitioning. To address this complexity, numerous algorithms have been proposed to eliminate unnecessary searches during partitioning CTUs by exploiting the correlation in the video. In this paper, existing CTU depth decision algorithms for HEVC are surveyed. These algorithms are categorized into two groups, namely statistics and machine learning approaches. Statistics approaches are further subdivided into neighboring and inherent approaches. Neighboring approaches exploit the similarity between adjacent CTUs to limit the depth range of the current CTU, while inherent approaches use only the available information within the current CTU. Machine learning approaches try to extract and exploit similarities implicitly. Traditional methods like support vector machines or random forests use manually selected features, while recently proposed deep learning methods extract features during training. Finally, this paper discusses extending these methods to more recent video coding formats such as Versatile Video Coding (VVC) and AOMedia Video 1(AV1).

Andrew Perkis, Christian Timmerer, Sabina Baraković et al.

With the coming of age of virtual/augmented reality and interactive media, numerous definitions, frameworks, and models of immersion have emerged across different fields ranging from computer graphics to literary works. Immersion is oftentimes used interchangeably with presence as both concepts are closely related. However, there are noticeable interdisciplinary differences regarding definitions, scope, and constituents that are required to be addressed so that a coherent understanding of the concepts can be achieved. Such consensus is vital for paving the directionality of the future of immersive media experiences (IMEx) and all related matters. The aim of this white paper is to provide a survey of definitions of immersion and presence which leads to a definition of immersive media experience (IMEx). The Quality of Experience (QoE) for immersive media is described by establishing a relationship between the concepts of QoE and IMEx followed by application areas of immersive media experience. Influencing factors on immersive media experience are elaborated as well as the assessment of immersive media experience. Finally, standardization activities related to IMEx are highlighted and the white paper is concluded with an outlook related to future developments.

Mohammad Hosseini, Christian Timmerer

High-quality point clouds have recently gained interest as an emerging form of representing immersive 3D graphics. Unfortunately, these 3D media are bulky and severely bandwidth intensive, which makes it difficult for streaming to resource-limited and mobile devices. This has called researchers to propose efficient and adaptive approaches for streaming of high-quality point clouds. In this paper, we run a pilot study towards dynamic adaptive point cloud streaming, and extend the concept of dynamic adaptive streaming over HTTP (DASH) towards DASH-PC, a dynamic adaptive bandwidth-efficient and view-aware point cloud streaming system. DASH-PC can tackle the huge bandwidth demands of dense point cloud streaming while at the same time can semantically link to human visual acuity to maintain high visual quality when needed. In order to describe the various quality representations, we propose multiple thinning approaches to spatially sub-sample point clouds in the 3D space, and design a DASH Media Presentation Description manifest specific for point cloud streaming. Our initial evaluations show that we can achieve significant bandwidth and performance improvement on dense point cloud streaming with minor negative quality impacts compared to the baseline scenario when no adaptations is applied.

Anatoliy Zabrovskiy, Christian Feldmann, Christian Timmerer

The number of bandwidth-hungry applications and services is constantly growing. HTTP adaptive streaming of audio-visual content accounts for the majority of today's internet traffic. Although the internet bandwidth increases also constantly, audio-visual compression technology is inevitable and we are currently facing the challenge to be confronted with multiple video codecs. This paper proposes a multi-codec DASH dataset comprising AVC, HEVC, VP9, and AV1 in order to enable interoperability testing and streaming experiments for the efficient usage of these codecs under various conditions. We adopt state of the art encoding and packaging options and also provide basic quality metrics along with the DASH segments. Additionally, we briefly introduce a multi-codec DASH scheme and possible usage scenarios. Finally, we provide a preliminary evaluation of the encoding efficiency in the context of HTTP adaptive streaming services and applications.

Christian Timmerer, Matteo Maiero, Benjamin Rainer

Multimedia content delivery over the Internet is predominantly using the Hypertext Transfer Protocol (HTTP) as its primary protocol and multiple proprietary solutions exits. The MPEG standard Dynamic Adaptive Streaming over HTTP (DASH) provides an interoperable solution and in recent years various adaptation logics/algorithms have been proposed. However, to the best of our knowledge, there is no comprehensive evaluation of the various logics/algorithms. Therefore, this paper provides a comprehensive evaluation of ten different adaptation logics/algorithms, which have been proposed in the past years. The evaluation is done both objectively and subjectively. The former is using a predefined bandwidth trajectory within a controlled environment and the latter is done in a real-world environment adopting crowdsourcing. The results shall provide insights about which strategy can be adopted in actual deployment scenarios. Additionally, the evaluation methodology described in this paper can be used to evaluate any other/new adaptation logic and to compare it directly with the results reported here.

Christian Timmerer, Alan Bertoni

Multimedia streaming over HTTP is no longer a niche research topic as it has entered our daily live. The common assumption is that it is deployed on top of the existing infrastructure utilizing application (HTTP) and transport (TCP) layer protocols as is. Interestingly, standards like MPEG's Dynamic Adaptive Streaming over HTTP (DASH) do not mandate the usage of any specific transport protocol allowing for sufficient deployment flexibility which is further supported by emerging developments within both protocol layers. This paper investigates and evaluates the usage of advanced transport options for the dynamic adaptive streaming over HTTP. We utilize a common test setup to evaluate HTTP/2.0 and Google's Quick UDP Internet Connections (QUIC) protocol in the context of DASH-based services.