Proceedings of the 2nd International Workshop on Robust Understanding of Low-quality Multimedia Data: Unitive Enhancement, Analysis and Evaluation最新文献

Visual Signal Assessment, Analysis and Enhancement for Low-resolution or Varying-illumination Environment 低分辨率或变照度环境下的视觉信号评估、分析与增强

Proceedings of the 2nd International Workshop on Robust Understanding of Low-quality Multimedia Data: Unitive Enhancement, Analysis and Evaluation Pub Date : 2022-10-14 DOI: 10.1145/3552456.3559437

Weisi Lin

引用次数: 0

In-training Restoration Models Matter: Data Augmentation for Degraded-reference Image Quality Assessment 训练中的恢复模型很重要:退化参考图像质量评估的数据增强

Proceedings of the 2nd International Workshop on Robust Understanding of Low-quality Multimedia Data: Unitive Enhancement, Analysis and Evaluation Pub Date : 2022-10-14 DOI: 10.1145/3552456.3555667

Jiazhi Du, Dongwei Ren, Yue Cao, W. Zuo

{"title":"In-training Restoration Models Matter: Data Augmentation for Degraded-reference Image Quality Assessment","authors":"Jiazhi Du, Dongwei Ren, Yue Cao, W. Zuo","doi":"10.1145/3552456.3555667","DOIUrl":"https://doi.org/10.1145/3552456.3555667","url":null,"abstract":"Full-Reference Image Quality Assessment (FR-IQA) metrics such as PSNR, SSIM, and LPIPS have been widely adopted for evaluating image restoration (IR) methods. However, pristine-quality images are usually not available, making inferior No-Reference Image Quality Assessment (NR-IQA) metrics seem to be the only solutions in practical applications. Fortunately, when evaluating image restoration methods, paired degraded and restoration images are generally available. Thus, this paper takes a step forward to develop a Degraded-Reference IQA (DR-IQA) model while respecting its correspondence with FR-IQA metrics. To this end, we adopt a simple encoder-decoder as DR-IQA model, and take paired degraded and restoration images as the input to predict distortion maps guided by FR-IQA metrics. More importantly, due to the diversity and continuous development of image restoration models, it is difficult to make the DR-IQA model learned based on a specific restoration model generalize well to other ones. To address this issue, we augment the DR-IQA training samples by adding the results produced by in-training restoration models. Benefiting from the diversity of training samples, our learned DR-IQA model generalizes well to unseen restoration models. We respectively test our DR-IQA models on various image restoration tasks,e.g., denoising, super-resolution, JPEG deblocking, and complicated degradations, where our method can further close the performance gap between FR-IQA metrics and the state-of-the-art NR-IQA methods. Moreover, experiments also show the effectiveness of our method in performance comparison and model selection of image restoration models without ground-truth clean images. Source code will be made publicly available.","PeriodicalId":398586,"journal":{"name":"Proceedings of the 2nd International Workshop on Robust Understanding of Low-quality Multimedia Data: Unitive Enhancement, Analysis and Evaluation","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114246963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unlocking the Potential of Disentangled Representation for Robust Media Understanding 为稳健的媒体理解释放解纠缠表示的潜力

Proceedings of the 2nd International Workshop on Robust Understanding of Low-quality Multimedia Data: Unitive Enhancement, Analysis and Evaluation Pub Date : 2022-10-14 DOI: 10.1145/3552456.3554363

Wenjun Zeng

引用次数: 0

Advances of Computational Imaging on Mobile Phones 手机计算成像技术进展

Proceedings of the 2nd International Workshop on Robust Understanding of Low-quality Multimedia Data: Unitive Enhancement, Analysis and Evaluation Pub Date : 2022-10-14 DOI: 10.1145/3552456.3559438

Jinwei Gu

引用次数: 0

Proceedings of the 2nd International Workshop on Robust Understanding of Low-quality Multimedia Data: Unitive Enhancement, Analysis and Evaluation 第二届对低质量多媒体数据的稳健理解国际研讨会论文集:统一增强、分析和评估

Proceedings of the 2nd International Workshop on Robust Understanding of Low-quality Multimedia Data: Unitive Enhancement, Analysis and Evaluation Pub Date : 1900-01-01 DOI: 10.1145/3552456

引用次数: 0