No-reference image quality assessment based on spatial and spectral entropies

By Lixiong Liu, Bao Liu, Hua Huang, A. Bovik. Signal processing. Image communication, 2014

705 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/1193d61539259cc0a9670e6c1fdf980aac8d43c3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Ming-Hsuan Yang
2. Luc Van Gool
3. Dacheng Tao
4. Radu Timofte
5. Chen Change Loy
6. Jiayi Ma
7. Jia-Bin Huang
8. Zhangyang Wang

In Media Technology

1. Jiayi Ma
2. Radu Timofte
3. Ming-Hsuan Yang
4. Luc Van Gool
5. Han Xu
6. Jia-Bin Huang
7. Yulun Zhang
8. Xiaojie Guo

Citations in the corpus

• An Experiment-Based Review of Low-Light Image Enhancement Methods (2020, methodology): “Eight metrics, namely, STD, IE, AG, BLIINDS-II [290], NIQE [289], BRISQUE [288], the contrast enhancement-based contrast-changed image quality measure (CEIQ) [311], and the spatial–spectral entropy-based quality measure (SSEQ) [312], were employed for NIQA-based evaluation.”
• KonIQ-10k: An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment (2019, methodology): “These methods were BIQI [32], BLIINDS-II [35], BRISQUE [36], CORNIA [7], DI-IVINE [33], HOSA [8], and SSEQ [34].”
• Benchmarking Low-Light Image Enhancement and Beyond (2021, background): “2016), SSEQ (Liu et al. 2014), and BLIINDS-II (Saad et al.”
• FusionDN: A Unified Densely Connected Network for Image Fusion (2020, methodology): “More concretely, we employ the entropy (EN) (Liu et al. 2014), mean gradient (MG) and standard deviation (SD) to evaluate the amount of information, edges and textures, and contrast in the fused image.”
• KADID-10k: A Large-scale Artificially Distorted IQA Database (2019, neutral): “…0.559 0.527 0.375 BRISQUE [26] 0.554 0.519 0.368 CORNIA * [27] 0.580 0.541 0.384 DIIVINE [28] 0.532 0.489 0.341 HOSA * [29] 0.653 0.609 0.438 SSEQ [30] 0.463 0.424 0.295 InceptionResNetV2 (fine-tune) 0.734 0.731 0.546 * To reduce time complexity, CORNIA and HOSA features were restricted to 100…”
• Benchmarking Single-Image Dehazing and Beyond (2017, methodology): “We thus refer to two no-reference IQA models: spatial-spectral entropy-based quality (SSEQ) [45], and blind image integrity notator using DCT statistics (BLIINDS-II) [44], to complement the shortness of PSNR/SSIM.”
• Deep Image Deblurring: A Survey (2022, methodology): “To evaluate the performance of deblurring methods on realworld images, several no-reference metrics have been used, such as BIQI Moorthy and Bovik (2010), BLINDS2 Saad et al. (2012), BRISQUEMittal et al. (2012a), CORNIAYe et al. (2012), DIIVINEMoorthy andBovik (2011), NIQEMittal et al. (2012b), and ”
• Multi-Scale Progressive Fusion Network for Single Image Deraining (2020, methodology): “Moreover, we use another two quantitative indicators, Naturalness Image Quality Evaluator (NIQE) [23] and Spatial-Spectral Entropy-based Quality (SSEQ) [22], to quantitatively evaluate the reference-free restoration performance.”
• A Comparative Study for Single Image Blind Deblurring (2016, background): “While numerous full-reference [36] [37] and no-reference image quality metrics [19] [23] [24] [26] [27] [33] [47] have been proposed, it is unclear whether these metrics can be applied to measure the quality of deblurred images.”
• Single Image Deraining: A Comprehensive Benchmark Analysis (2019, methodology): “Due to the unavailability of ground truth clean images in real world, we evaluate NIQE, SSEQ, and BLIINDS-II on the three real-world sets.”