MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusion

@article{Wang2022MSTRIQNR,
  title={MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusion},
  author={Jing Wang and Haotian Fa and Xiao Hou and Yitian Xu and Tao Li and X. Lu and Lean Fu},
  journal={2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2022},
  pages={1268-1277}
}
  • Jing WangHaotian Fa L. Fu
  • Published 20 May 2022
  • Computer Science
  • 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Measuring the perceptual quality of images automatically is an essential task in the area of computer vision, as degradations on image quality can exist in many processes from image acquisition, transmission to enhancing. Many Image Quality Assessment(IQA) algorithms have been designed to tackle this problem. However, it still remains unsettled due to the various types of image distortions and the lack of large-scale human-rated datasets. In this paper, we propose a novel algorithm based on the… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 66 REFERENCES

MUSIQ: Multi-scale Image Quality Transformer

A novel hash-based 2D spatial embedding and a scale embedding is proposed to support the positional embedding in the multi-scale representation of IQA, which can achieve state-of-the-art performance on multiple large scale IQA datasets.

Perceptual Image Quality Assessment with Transformers

An image quality transformer (IQT) is proposed that successfully applies a transformer architecture to a perceptual full-reference image quality assessment (IQA) task and uses extra learnable quality embedding and position embedding.

PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration

It is indicated that existing IQA methods cannot fairly evaluate GAN-based IR algorithms, and a large-scale IQA dataset, called Perceptual Image Processing Algorithms (PIPAL) is contributed, which includes the results of GAn-based methods, which are missing in previous datasets.

Deep Learning-based Distortion Sensitivity Prediction for Full-Reference Image Quality Assessment

This work uses the DeepQA as a baseline model on a challenge database that includes various distortions and improves the baseline model by dividing it into three parts and modifying each: distortion encoding network, sensitivity generation network, and score regression.

VTAMIQ: Transformers for Attention Modulated Image Quality Assessment

This work proposes a novel full-reference IQA method, Vision Transformer for Attention Modulated Image Quality (VTAMIQ), which achieves competitive or state-of-the-art performance on the existing IQA datasets and significantly outperforms previous metrics in cross-database evaluations.

NTIRE 2021 Challenge on Perceptual Image Quality Assessment

  • Jinjin GuHaoming Cai K. Aizawa
  • Computer Science
    2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2021
The NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021, achieved much better results than existing IQA methods, while the winning method can demonstrate state-of-the-art performance.

SwinIR: Image Restoration Using Swin Transformer

A strong baseline model SwinIR is proposed for image restoration based on the Swin Transformer that outperforms state-of-the-art methods on different tasks by up to 0.14∼0.45dB, while the total number of parameters can be reduced byUp to 67%.

Saliency-Guided Transformer Network combined with Local Embedding for No-Reference Image Quality Assessment

A novel Saliency-Guided Transformer Network combined with Local Embedding (TranSLA) for No-Reference Image Quality Assessment (NR-IQA) and introduces a Boosting Interaction Module (BIM) to enhance feature aggregation.

NTIRE 2022 Challenge on Perceptual Image Quality Assessment

This paper reports on the NTIRE 2022 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at

Transformer For Image Quality Assessment

This paper proposes an architecture of using a shallow Transformer encoder on the top of a feature map extracted by convolution neural networks (CNN), and finds that the proposed TRIQ architecture achieves outstanding performance.
...