Goals |
We design prediction algorithms for the visual quality of images and videos, with respect to technical and perceptual aspects e.g. quality of experience (QoE).
The tools of our trade include crowdsourcing, machine learning i.e. deep networks, eye-tracking. Consequently, we are creating massive multimedia databases that are suitable for training generic and accurate VQA models. |
- Home
-
VQA Databases
- KonViD-150k Database
- KonViD-1k Database
- VQA@Country Database
- KonIQ++ Database
- KADID-10k Database
- UHD-IQA Benchmark Database
- IQA-Experts-300
- KonPatch-30k Database
- KonX Cross-Resolution Database
- KoSMo-1k Database
- StudyMB 2.0 Database
- Picturewise JND Data
- CogVQA Database
- KonJND-1k database
- KonFiG-IQA Database
- GFIQA-20k Database
- Feedback study dataset
- About
- Contact
- KonIQ-10k Database