NTU Visual Quality Assessment Group
- 100 followers
- Singapore
Maintained by: Teo Wu (Haoning Wu)
🌟New: We have published Q-Bench: a benchmark for multi-modality large language models (MLLMs) on low-level vision and visual quality assessment!
See our 🖥️codebase and 📑paper!
We are a young research team from Nanyang Technological University (NTU) and Sensetime Research, aiming to build efficient and explainable Image and Video Quality Assessment approaches as well as exploring the perceptual mechanisms behind the human quality perception.
Code repositories to our works under the project:
MaxVQA and MaxWell database (ACM MM, 2023) Paper
Zero-shot BVQI (ICME Oral, 2023) Paper Extension
FAST-VQA/FasterVQA (ECCV, 2022; TPAMI, 2023) Paper Extension
TPQI Matlab, Pytorch (ACM MM Oral, 2022) Paper
Video Quality Assessment: End-to-end VQA
Image Quality Assessment: IQA-Pytorch
Supervisor: Prof Weisi Lin
Co-Supervisors from Sensetime: Dr. Wenxiu Sun, Dr. Qiong Yan
PhD Students: Haoning Wu, Jingwen Hou
Research Fellows (alphabetical order): Dr. Chaofeng Chen, Dr. Liang Liao
Pinned Loading
Repositories
- ExplainableVQA Public
[ACMMM Oral, 2023] "Towards Explainable In-the-wild Video Quality Assessment: A Database and a Language-Prompted Approach"
- DOVER Public
[ICCV 2023, Official Code] for paper "Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives". Official Weights and Demos provided.
- Q-Bench Public Forked from Q-Future/Q-Bench
An archived version of Q-Bench. We will make updates in https://github.com/q-future/Q-Bench in the future.
- .github Public
- BVQI Public
[ICME 2023 Oral, Extended to TIP (UR)] The best zero-shot VQA approach that even outperforms several fully-supervised methods.
- DisCoVQA Public
Placeholder repository for ArXiv Preprint paper "DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment". Full code will be released later.
Top languages
Loading…
Most used topics
Loading…