PTM-VQA: efficient video quality assessment leveraging diverse pretrained models from the wild

K Yuan, H Liu, M Li, M Sun, M Sun… - Proceedings of the …, 2024 - openaccess.thecvf.com
Video quality assessment (VQA) is a challenging problem due to the numerous factors that
can affect the perceptual quality of a video eg content attractiveness distortion type motion …

Adaptive image quality assessment via teaching large multimodal model to compare

H Zhu, H Wu, Y Li, Z Zhang, B Chen, L Zhu… - arxiv preprint arxiv …, 2024 - arxiv.org
While recent advancements in large multimodal models (LMMs) have significantly improved
their abilities in image quality assessment (IQA) relying on absolute quality rating, how to …

Mstriq: No reference image quality assessment based on swin transformer with multi-stage fusion

J Wang, H Fan, X Hou, Y Xu, T Li… - Proceedings of the …, 2022 - openaccess.thecvf.com
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 …

Comparing the robustness of modern no-reference image-and video-quality metrics to adversarial attacks

A Antsiferova, K Abud, A Gushchin… - Proceedings of the …, 2024 - ojs.aaai.org
Nowadays neural-network-based image-and video-quality metrics show better performance
compared to traditional methods. However, they also became more vulnerable to …

Non-local geometry and color gradient aggregation graph model for no-reference point cloud quality assessment

S Wang, X Wang, H Gao, J **ong - Proceedings of the 31st ACM …, 2023 - dl.acm.org
No-Reference point cloud quality assessment (NR-PCQA) is a challenging task in computer
vision due to the irregularity of point cloud structures and the unavailability of reference …

Perception-Driven Similarity-Clarity Tradeoff for Image Super-Resolution Quality Assessment

K Zhang, T Zhao, W Chen, Y Niu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Super-Resolution (SR) algorithms aim to enhance the resolutions of images. Massive deep-
learning-based SR techniques have emerged in recent years. In such case, a visually …

SGIQA: semantic-guided no-reference image quality assessment

L Pan, X Zhang, F **e, H Zhang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Existing no reference image quality assessment (NR-IQA) methods have not incorporated
image semantics explicitly in the assessment process, thus overlooking the significant …

Unsupervised blind image quality assessment via joint spatial and transform features

C Yang, Q He, P An - Scientific Reports, 2023 - nature.com
A novel unsupervised blind image quality assessment (BIQA) method, which requires no
mean opinion scores for model training is presented in this paper. The method employs joint …

No‐Reference Image Quality Assessment: Past, Present, and Future

Q Mao, S Liu, Q Li, G Jeon, H Kim… - Expert Systems, 2025 - Wiley Online Library
No‐reference image quality assessment (NR‐IQA) has garnered significant attention due to
its critical role in various image processing applications. This survey provides a …

Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics

A Gushchin, K Abud, G Bychkov, E Shumitskaya… - arxiv preprint arxiv …, 2024 - arxiv.org
In the field of Image Quality Assessment (IQA), the adversarial robustness of the metrics
poses a critical concern. This paper presents a comprehensive benchmarking study of …