Conformer and Blind Noisy Students for Improved Image Quality Assessment

Conde, Marcos V.; Burchi, Maxime; Timofte, Radu

doi:10.1109/cvprw56347.2022.00108

Cited by 13 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We remark that SSL has not been explored much even in the IQA literature. While Conde et al (Conde, Burchi, and Timofte 2022) study SSL methods for full reference IQA, some other methods (Wang, Li, and Ma 2021;Yue et al 2022) train an NR IQA model with a large number of labelled images and generate pseudo-labels on the unlabelled data.…”

Section: Related Workmentioning

confidence: 99%

Knowledge Guided Semi-supervised Learning for Quality Assessment of User Generated Videos

Mitra,

Soundararajan

2024

AAAI

View full text Add to dashboard Cite

Perceptual quality assessment of user generated content (UGC) videos is challenging due to the requirement of large scale human annotated videos for training. In this work, we address this challenge by first designing a self-supervised Spatio-Temporal Visual Quality Representation Learning (ST-VQRL) framework to generate robust quality aware features for videos. Then, we propose a dual-model based Semi Supervised Learning (SSL) method specifically designed for the Video Quality Assessment (SSL-VQA) task, through a novel knowledge transfer of quality predictions between the two models. Our SSL-VQA method uses the ST-VQRL backbone to produce robust performances across various VQA datasets including cross-database settings, despite being learned with limited human annotated videos. Our model improves the state-of-the-art performance when trained only with limited data by around 10%, and by around 15% when unlabelled data is also used in SSL. Source codes and checkpoints are available at https://github.com/Shankhanil006/SSL-VQA.

show abstract

Section: Related Workmentioning

confidence: 99%

Knowledge Guided Semi-supervised Learning for Quality Assessment of User Generated Videos

Mitra,

Soundararajan

2024

AAAI

View full text Add to dashboard Cite

show abstract

“…On the whole, the entire image's perceptual quality is estimated by the predicted feature similarity index [50] scores of the image patches. In contrast, Conde et al [51] took a CNN backbone network and trained it using a loss function [52] which aims to minimize the mean squared error and maximize linear correlation coefficient between the predicted and ground-truth quality scores. Further, the authors applied several data augmentation techniques, such as horizontal flips, vertical flips, rotations, and random cropping.…”

Section: Related Workmentioning

confidence: 99%

A Human Visual System Inspired No-Reference Image Quality Assessment Method Based on Local Feature Descriptors

Varga

2022

Sensors

View full text Add to dashboard Cite

Objective quality assessment of natural images plays a key role in many fields related to imaging and sensor technology. Thus, this paper intends to introduce an innovative quality-aware feature extraction method for no-reference image quality assessment (NR-IQA). To be more specific, a various sequence of HVS inspired filters were applied to the color channels of an input image to enhance those statistical regularities in the image to which the human visual system is sensitive. From the obtained feature maps, the statistics of a wide range of local feature descriptors were extracted to compile quality-aware features since they treat images from the human visual system’s point of view. To prove the efficiency of the proposed method, it was compared to 16 state-of-the-art NR-IQA techniques on five large benchmark databases, i.e., CLIVE, KonIQ-10k, SPAQ, TID2013, and KADID-10k. It was demonstrated that the proposed method is superior to the state-of-the-art in terms of three different performance indices.

show abstract

Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration

Conde

Choi²,

Burchi

et al. 2023

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

In smartphones and compact cameras, the Image Signal Processor (ISP) transforms the RAW sensor image into a human-readable sRGB image. Most popular superresolution methods depart from a sRGB image and upscale it further, improving its quality. However, modeling the degradations in the sRGB domain is complicated because of the non-linear ISP transformations. Despite this known issue, only a few methods work directly with RAW images and tackle real-world sensor degradations.We tackle blind image super-resolution in the RAW domain. We design a realistic degradation pipeline tailored specifically for training models with raw sensor data. Our approach considers sensor noise, defocus, exposure, and other common issues. Our BSRAW models trained with our pipeline can upscale real-scene RAW images and improve their quality. As part of this effort, we also present a new DSLM dataset and benchmark for this task.

show abstract

Conformer and Blind Noisy Students for Improved Image Quality Assessment

Cited by 13 publications

References 48 publications

Knowledge Guided Semi-supervised Learning for Quality Assessment of User Generated Videos

Knowledge Guided Semi-supervised Learning for Quality Assessment of User Generated Videos

A Human Visual System Inspired No-Reference Image Quality Assessment Method Based on Local Feature Descriptors

Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration

Contact Info

Product

Resources

About