Exploration of subjective test methodologies for VSR video quality assessment (Bachelor)
In recent years, video super resolution (VSR) has been gaining increasing relevance in different applications such as video streaming, gaming, medical image analysis, etc. However, there is a lack of a systematic evaluation of the the perceived quality of videos of VSR videos. In this thesis, the focus will be on investigating different subjective test methodologies to ascertain suitable method(s) for the benchmarking of different VSR algorithms in terms of perceived video quality. The tasks would include
- Collection and curation of relevant datasets
- Choosing appropriate subjective test methodologies
- Conduction of subjective tests
- Subjective test results analysis and comparison between different methodologies
Relevant literature
- International Telecommunication Union. (2023). Methodologies for the subjective assessment of the quality of television images (ITU-R Recommendation BT.500-15).
- A. Borisov, E. Bogatyrev, K. Abud, I. Molodetskikh and D. Vatolin, "VSRQAD: Video Super-Resolution Quality Assessment Dataset and Benchmark," in IEEE Access, vol. 14, pp. 60229-60251, 2026, doi: 10.1109/ACCESS.2026.3679554.
- Molodetskikh, I., Borisov, A., Vatolin, D., Timofte, R., Liu, J., Zhi, T., ... & Yi, H. (2024, September). AIM 2024 challenge on video super-resolution quality assessment: Methods and results. In European Conference on Computer Vision (pp. 160-177). Cham: Springer Nature Switzerland. https://doi.org/10.48550/arXiv.2410.04225
- B. Herb, S. Göring, A. Raake and R. R. Ramachandra Rao, "How Accurate are Video Quality Models for Diffusion-Based Video Super-Resolution?," 2026 18th International Conference on Quality of Multimedia Experience (QoMEX), Cardiff, United Kingdom, 2026, pp. 1-7, doi: 10.1109/QoMEX69967.2026.11618341.
Suitable for Bachelor theses. Contact person: Dr.-Ing. Rakesh Rao Ramachandra Rao
