Visual Evaluation with Foundation Models

icon location We are working towards a future that one foundation model can be a multi-purpose expert for low-level visual perception and visual evaluation.

Results 5 repositories owned by Visual Evaluation with Foundation Models

Q-Align

212
Stars
16
Forks
Watchers

③[ICML2024] [IQA, IAA, VQA] All-in-one Foundation Model for visual scoring. Can efficiently fine-tune to downstream datasets.

verified publisher icon Q-Future

Q-Bench

242
Stars
12
Forks
Watchers

①[ICLR2024 Spotlight] (GPT-4V/Gemini-Pro/Qwen-VL-Plus+16 OS MLLMs) A benchmark for multi-modality LLMs (MLLMs) on low-level vision and visual quality assessment.

verified publisher icon Q-Future

Q-Instruct

197
Stars
8
Forks
Watchers

②[CVPR 2024] Low-level visual instruction tuning, with a 200K dataset and a model zoo for fine-tuned checkpoints.

verified publisher icon Q-Future

Co-Instruct

45
Stars
3
Forks
Watchers

④[Comparison among Multiple Images!] A study on open-ended multi-image quality comparison: a dataset, a model and a benchmark.

verified publisher icon Q-Future

A-Bench

115
Stars
3
Forks
Watchers

[LMM + AIGC] What do we expect from LMMs as AIGI evaluators and how do they perform?

verified publisher icon Q-Future