Learning Conditional Knowledge Distillation for Degraded-Reference Image
Quality Assessment
- URL: http://arxiv.org/abs/2108.07948v1
- Date: Wed, 18 Aug 2021 02:35:08 GMT
- Title: Learning Conditional Knowledge Distillation for Degraded-Reference Image
Quality Assessment
- Authors: Heliang Zheng, Huan Yang, Jianlong Fu, Zheng-Jun Zha, Jiebo Luo
- Abstract summary: We propose a practical solution named degraded-reference IQA (DR-IQA)
DR-IQA exploits the inputs of IR models, degraded images, as references.
Our results can even be close to the performance of full-reference settings.
- Score: 157.1292674649519
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: An important scenario for image quality assessment (IQA) is to evaluate image
restoration (IR) algorithms. The state-of-the-art approaches adopt a
full-reference paradigm that compares restored images with their corresponding
pristine-quality images. However, pristine-quality images are usually
unavailable in blind image restoration tasks and real-world scenarios. In this
paper, we propose a practical solution named degraded-reference IQA (DR-IQA),
which exploits the inputs of IR models, degraded images, as references.
Specifically, we extract reference information from degraded images by
distilling knowledge from pristine-quality images. The distillation is achieved
through learning a reference space, where various degraded images are
encouraged to share the same feature statistics with pristine-quality images.
And the reference space is optimized to capture deep image priors that are
useful for quality assessment. Note that pristine-quality images are only used
during training. Our work provides a powerful and differentiable metric for
blind IRs, especially for GAN-based methods. Extensive experiments show that
our results can even be close to the performance of full-reference settings.
Related papers
- DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild [54.139923409101044]
We propose a novel IQA method called diffusion priors-based IQA (DP-IQA)
We use pre-trained stable diffusion as the backbone, extract multi-level features from the denoising U-Net, and decode them to estimate the image quality score.
We distill the knowledge in the above model into a CNN-based student model, significantly reducing the parameter to enhance applicability.
arXiv Detail & Related papers (2024-05-30T12:32:35Z) - Quality-Aware Image-Text Alignment for Real-World Image Quality Assessment [8.431867616409958]
No-Reference Image Quality Assessment (NR-IQA) focuses on designing methods to measure image quality in alignment with human perception when a high-quality reference image is unavailable.
The reliance on annotated Mean Opinion Scores (MOS) in the majority of state-of-the-art NR-IQA approaches limits their scalability and broader applicability to real-world scenarios.
We propose QualiCLIP, a CLIP-based self-supervised opinion-unaware method that does not require labeled MOS.
arXiv Detail & Related papers (2024-03-17T11:32:18Z) - Less is More: Learning Reference Knowledge Using No-Reference Image
Quality Assessment [58.09173822651016]
We argue that it is possible to learn reference knowledge under the No-Reference Image Quality Assessment setting.
We propose a new framework to learn comparative knowledge from non-aligned reference images.
Experiments on eight standard NR-IQA datasets demonstrate the superior performance to the state-of-the-art NR-IQA methods.
arXiv Detail & Related papers (2023-12-01T13:56:01Z) - Conformer and Blind Noisy Students for Improved Image Quality Assessment [80.57006406834466]
Learning-based approaches for perceptual image quality assessment (IQA) usually require both the distorted and reference image for measuring the perceptual quality accurately.
In this work, we explore the performance of transformer-based full-reference IQA models.
We also propose a method for IQA based on semi-supervised knowledge distillation from full-reference teacher models into blind student models.
arXiv Detail & Related papers (2022-04-27T10:21:08Z) - Confusing Image Quality Assessment: Towards Better Augmented Reality
Experience [96.29124666702566]
We consider AR technology as the superimposition of virtual scenes and real scenes, and introduce visual confusion as its basic theory.
A ConFusing Image Quality Assessment (CFIQA) database is established, which includes 600 reference images and 300 distorted images generated by mixing reference images in pairs.
An objective metric termed CFIQA is also proposed to better evaluate the confusing image quality.
arXiv Detail & Related papers (2022-04-11T07:03:06Z) - Can No-reference features help in Full-reference image quality
estimation? [20.491565297561912]
We study utilization of no-reference features in Full-reference IQA task.
Our model achieves higher SRCC and KRCC scores than a number of state-of-the-art algorithms.
arXiv Detail & Related papers (2022-03-02T03:39:28Z) - Image Quality Assessment using Contrastive Learning [50.265638572116984]
We train a deep Convolutional Neural Network (CNN) using a contrastive pairwise objective to solve the auxiliary problem.
We show through extensive experiments that CONTRIQUE achieves competitive performance when compared to state-of-the-art NR image quality models.
Our results suggest that powerful quality representations with perceptual relevance can be obtained without requiring large labeled subjective image quality datasets.
arXiv Detail & Related papers (2021-10-25T21:01:00Z) - A survey on IQA [0.0]
This article will review the concepts and metrics of image quality assessment and also video quality assessment.
It briefly introduce some methods of full-reference and semi-reference image quality assessment, and focus on the non-reference image quality assessment methods based on deep learning.
arXiv Detail & Related papers (2021-08-29T10:52:27Z) - Perceptual Image Restoration with High-Quality Priori and Degradation
Learning [28.93489249639681]
We show that our model performs well in measuring the similarity between restored and degraded images.
Our simultaneous restoration and enhancement framework generalizes well to real-world complicated degradation types.
arXiv Detail & Related papers (2021-03-04T13:19:50Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.