Video quality assessment (VQA) plays a critical role in optimizing video delivery systems. Perceived quality strongly depends on viewing conditions and display characteristics — factors such as ambient lighting, display brightness, and resolution significantly influence the visibility of distortions.

We address multi-screen quality assessment on mobile devices, an area that remains largely under-covered. We introduce the first large-scale subjective dataset collected across more than 300 different Android devices, accompanied by metadata on viewing conditions and display properties. We propose a strategy for aggregated score extraction and adaptation of VQA models to device-specific quality estimation.

Our results demonstrate that incorporating device and context information enables more accurate and flexible quality prediction, offering new opportunities for fine-grained optimization in streaming services.

Cite us

@inproceedings{safonov2026mobilevqa,
  author    = {Nickolay Safonov and Dmitriy Vatolin},
  title     = {Learning Flexible Generalization in Video Quality Assessment by Bringing Device and Viewing Condition Distributions},
  booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
  series    = {Proceedings of Machine Learning Research},
  year      = {2026},
  publisher = {PMLR},
  url       = {https://icml.cc/virtual/2026/poster/63617}
}