DeQA-Score-Mix3

DeQA-Score ( project page / codes / paper ) model weights fully fine-tuned on KonIQ, SPAQ, and KADID datasets.

This work is under our DepictQA project.

Quick Start with AutoModel

[2025.12] Thanks to @lyf1212's and @0x3f3f3f3fun's suggestions, we add support on transformers==4.46.3 and transformers==4.57.6 with minor code modifications. See details.

Note: If you are using transformers==4.36.1, no code modifications are needed.

For the above image, we could start an AutoModel scorer with transformers==4.36.1 using the following code.

import requests
import torch
from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained(
  "zhiyuanyou/DeQA-Score-Mix3",
  trust_remote_code=True,
  attn_implementation="eager", 
  torch_dtype=torch.float16,
  device_map="auto", 
)

from PIL import Image

# The inputs should be a list of multiple PIL images
score = model.score(
  [Image.open(requests.get(
    "https://raw.githubusercontent.com/zhiyuanyou/DeQA-Score/main/fig/singapore_flyer.jpg", stream=True
    ).raw)]
)

The "score" result should be 1.9404 (in range [1,5], higher is better).

Non-reference IQA Results (PLCC / SRCC)

If you find our work useful for your research and applications, please cite using the BibTeX:

@inproceedings{deqa_score,
    title={Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution},
    author={You, Zhiyuan and Cai, Xin and Gu, Jinjin and Xue, Tianfan and Dong, Chao},
    booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={14483--14494},
    year={2025}
}