Beyond One-Size-Fits-All: Adaptive and Computationally Efficient Video Streaming
Hadi Amirpour
Habilitation
On 25.06.2026, Dr. Hadi Amirpour defended his habilitation “Beyond One-Size-Fits-All: Adaptive and Computationally Efficient Video Streaming” at the University of Klagenfurt, Austria.
Abstract:
Video streaming has become an integral and ever-growing component of daily life, driving increasing demands for efficient, scalable, and high-quality delivery across heterogeneous networks and devices. This habilitation thesis investigates novel methods to improve the compression, computation, and perceptual performance of video streaming systems across the entire delivery pipeline. A central focus is placed on bitrate ladder construction, where the same video content is encoded into multiple representations, typically at different bitrates and resolutions, to enable adaptive streaming. Although a one-size-fits-all approach is widely adopted due to its simplicity and ease of deployment, it is inherently suboptimal, as it neglects content characteristics and network variability, leading to inefficient resource utilization and reduced quality of experience (QoE).
This habilitation thesis first presents advanced bitrate ladder optimization strategies encompassing both content-aware and network-aware approaches to determine the appropriate number of representations and their associated bitrates for video-on-demand and live streaming scenarios. The optimization is further extended to a multi-dimensional representation space, including spatial and temporal resolution, bit depth, encoder presets, and device capabilities, with explicit consideration of compression efficiency, computational cost, and energy consumption. These contributions establish the foundation for deciding what should be encoded and delivered in adaptive streaming systems.
However, determining optimal representations through exhaustive encoding is computationally prohibitive, particularly in live streaming scenarios. To address this limitation, efficient feature extraction and encoding-aware as well as semantic-aware video complexity analysis methods are introduced. These predictive models enable fast and reliable content characterization without requiring brute-force encoding, thereby supporting scalable and real-time bitrate ladder construction and encoder configuration.
Once the bitrate ladder is determined, this habilitation thesis further investigates fast multi-rate encoding approaches, which typically exploit encoding decisions from one representation to accelerate the encoding of other representations, thereby reducing computational redundancy while maintaining rate–distortion performance. Additionally, lightweight transcoding techniques are developed for cloud and edge environments, where metadata generated in the cloud is leveraged to accelerate subsequent transcoding processes. Finally, quality evaluation is addressed as a key cross-cutting aspect, focusing on the measurement and modeling of QoE to ensure that system-level optimizations translate into perceptually meaningful improvements for end users.
This habilitation thesis also includes technical advances in multimedia security and privacy, such as reversible data hiding, selective encryption, and cryptographic analysis, ensuring that efficiency and scalability do not compromise confidentiality, integrity, and trustworthiness in modern streaming ecosystems. It is complemented by survey and tutorial contributions that position the work within the broader research landscape and consolidate the presented methods within a unified scientific context.
Taken together, the research contributions presented in this habilitation thesis establish a coherent progression for adaptive video streaming systems, addressing what to encode and deliver through adaptive and multi-dimensional bitrate ladder construction; how to predict optimal encoding decisions efficiently using encoding-aware and semantic visual complexity modeling; how to produce optimized representations at scale via accelerated multi-rate encoding and lightweight edge transcoding; how to evaluate system decisions perceptually through QoE modeling and real-time quality metrics; and how to protect multimedia content in distributed cloud and edge infrastructures through format-compliant encryption and security mechanisms. This integrated perspective advances video streaming as a cross-layer, end-to-end optimization framework that jointly considers compression efficiency, computational scalability, perceptual quality, and security within modern multimedia delivery ecosystems.
Keywords: Video streaming; bitrate ladder construction; encoding optimization; video complexity analysis; Quality of Experience (QoE); accelerated encoding; multimedia security.
