ATHENA Christian Doppler (CD) Laboratory

IEEE International Conference on Image Processing (ICIP 2024)

27-30 October 2024, Abu Dhabi, UAE

[PDF]

Ahmed Telili (TII, UAE), Ibrahim Farhat (TII, UAE), Wassim Hamidouche (TII, UAE), Hadi Amirpour (AAU, Austria)

Abstract: Omnidirectional or 360-degree video is being increasingly deployed, largely due to the latest advancements in immersive virtual reality (VR) and extended reality (XR) technology. However, the adoption of these videos in streaming encounters challenges related to bandwidth and latency, particularly in mobility conditions such as with unmanned aerial vehicles (UAVs). Adaptive resolution and compression aim to preserve quality while maintaining low latency under these constraints, yet downscaling and encoding can still degrade quality and introduce artifacts. Machine learning (ML)-based super-resolution (SR) and quality enhancement techniques offer a promising solution by enhancing detail recovery and reducing compression artifacts. However, current publicly available 360-degree video SR datasets lack compression artifacts, which limit research in this field. To bridge this gap, this paper introduces omnidirectional video streaming dataset (ODVista), which comprises 200 high-resolution and high-quality videos downscaled and encoded at four bitrate ranges using the high-efficiency video coding (HEVC)/H.265 standard. Evaluations show that the dataset not only features a wide variety of scenes but also spans different levels of content complexity, which is crucial for robust solutions that perform well in real-world scenarios and generalize across diverse visual environments. Additionally, we evaluate the performance, considering both quality enhancement and runtime, of two handcrafted and two ML-based SR models on the validation and testing sets of ODVista.
Dataset URL: https://github.com/Omnidirectional-video-group/ODVista

ACM Transactions on Multimedia Computing Communications and Applications (ACM TOMM)

[PDF]

Chen Chen (Tsinghua University, China),  Lingfeng Qu (Guangzhou University, China), Hadi Amirpour (Alpen-Adria-Universität Klagenfurt), Xingjun Wang (Tsinghua University, China),  Christian Timmerer (Alpen-Adria-Universität Klagenfurt), and Zhihong Tian (Guangzhou University, China)

Abstract:

With the growing applications of video, ensuring its security has become of utmost importance. Selective encryption (SE) has gained significant attention in the field of video content protection due to its compatibility with video codecs, favorable visual distortion, and low time complexity. However, few studies consider SE security under cryptographic attacks. To fill this gap, we analyze the security concerns of encrypted bitstreams by SE schemes and propose two known plaintext attacks (KPAs). Then, the corresponding defense is presented against the KPAs.To validate the effectiveness of the KPA, it is applied to attack two existing SE schemes with superior visual degradation in HEVC videos.

Firstly, the encrypted bitstreams are generated using the HEVC encoder with SE (HESE).
Secondly, the video sequences are encoded using H.265/HEVC. During encoding, the selected syntax elements are recorded. Then, the recorded syntax elements are imported into the HEVC decoder using decryption (HDD). By utilizing the encryption parameters and the imported data in the HDD, it becomes possible to reconstruct a significant portion of the original syntax elements before encryption. Finally, the reconstructed syntax elements are compared with the encrypted syntax elements in the HDD, allowing the design of a pseudo-key stream (PKS) through the inverse of the encryption operations. The PKS is used to decrypt the existing SE scheme, and the experimental results provide evidence that the two existing SE schemes are vulnerable to the proposed KPAs.
In the case of single bitstream estimation (SBE), the average correct rate of key stream estimation exceeds 93%. Moreover, with multi-bitstream complementation (MBC), the average estimation accuracy can be further improved to 99%.

Das Original befindet sich hier.

Am 5. Juni 2024 findet an der Universität Klagenfurt die Antrittsvorlesung von Christian Timmerer vom Institut für Informationstechnologie zum Thema „Video Streaming: Then, Now, and in the Future“ statt.   

Das Rektorat der Universität Klagenfurt und der Dekan der Fakultät für Technische Wissenschaften laden herzlich am 5. Juni 2024 zur Antrittsvorlesung von Christian Timmerer ein. Christian Timmerer ist seit Dezember 2022 Universitätsprofessor für Multimedia Systems am Institut für Informationstechnologie der Fakultät für Technische Wissenschaften. Seine Antrittsvorlesung hält er zum Thema:

„Video Streaming: Then, Now, and in the Future“   [Slides]

5. Juni 2024
17.00 Uhr
Universität Klagenfurt
Hörsaal 2 (Zentraltrakt der Universität)

In seinem öffentlichen Vortrag gibt Christian Timmerer Einblicke in die faszinierende Geschichte des Videostreamings, beginnend bei den bescheidenen Anfängen vor YouTube bis hin zu den bahnbrechenden Technologien, die heutzutage Plattformen wie Netflix und ORF ON dominieren. Timmerer präsentiert dabei auch provokante eigene Beiträge, die die Branche maßgeblich beeinflusst haben. Zum Abschluss wirft er einen Blick auf die zukünftigen Herausforderungen und lädt das Publikum zu einer Diskussion ein.

Die Antrittsvorlesung findet in englischer Sprache statt.

European Signal Processing Conference (EUSIPCO)

26-30 August 2024, Lyon, France

[PDF]

Mohammad Ghasempour (AAU, Austria), Yiying Wei (AAU, Austria), Hadi Amirpour (AAU, Austria),  and Christian Timmerer (AAU, Austria)

Abstract: Video coding relies heavily on reducing spatial and temporal redundancy to enable efficient transmission. To tackle the temporal redundancy, each video frame is predicted from the previously encoded frames, known as reference frames. The quality of this prediction is highly dependent on the quality of the reference frames. Recent advancements in machine learning are motivating the exploration of frame synthesis to generate high-quality reference frames. However, the efficacy of such models depends on training with content similar to that encountered during usage, which is challenging due to the diverse nature of video data. This paper introduces a content-aware reference frame synthesis to enhance inter-prediction efficiency. Unlike conventional approaches that rely on pre-trained models, our proposed framework optimizes a deep learning model for each content by fine-tuning only the last layer of the model, requiring the transmission of only a few kilobytes of additional information to the decoder. Experimental results show that the proposed framework yields significant bitrate savings of 12.76%, outperforming its counterpart in the pre-trained framework, which only achieves 5.13% savings in bitrate.