An information fidelity criterion for image quality assessment using natural scene statistics

By Hamid R. Sheikh, A. Bovik, Gustavo De Veciana. 2005

1,436 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

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

In Media Technology

Citations in the corpus

The Perception-Distortion Tradeoff (2017, methodology): “Figure 9 depicts the outputs of several algorithms lying closest to the perception-distortion bound in the IFC graph.”
Image Super-Resolution Using Deep Convolutional Networks (2014, methodology): “When we take a look at other evaluation metrics, we observe that SC, to our surprise, gets even lower scores than the bicubic interpolation on IFC and NQM.”
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis (2016, neutral): “As shown in the supplementary, SSIM and IFC [46] which have been found to correlate better with human perception [57] also do not capture the perceptual quality of the results, so we provide alternative quantitative evaluations that agree better with human perception in Sec.”
Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution (2017, methodology): “Table 4: Quantitative evaluation of state-of-the-art SR algorithms: average PSNR/SSIM/IFC for scale factors 2×, 4× and 8×.”
Blind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain (2012, background): “However, the introduction of distortions to the images changes the distribution of the coefficients, as shown in [4] and [31].”
Conditioned Regression Models for Non-blind Single Image Super-Resolution (2015, result): “Not only standard bicubic upscaling but also state-of-the-art methods like [28] trained on a wrong kernel yield clearly inferior results (PSNR and IFC [26] are given) compared to our conditioned regression model (SRF-CAB).”
Blind image quality assessment through anisotropy. (2007, methodology): “[5] use an information fidelity crierion (IFC) for image QA using natural scene statistics odels as an alternative to the HVS-based methods.”
2018 PIRM Challenge on Perceptual Image Super-resolution (2018, methodology): “As above, RMSE, SSIM and IFC are anti -correlated with human-opinion-scores, while NIQE and PI are most correlated (especially in the high perceptual quality regime). altogether), where we average only over diﬀerent human raters.”
Modern Image Quality Assessment (2006, methodology): “In fact, it has been shown that a simplified implementation of the IFC Index is functionally equivalent to a standard error visibility algorithm [77, 78].”
A Deep Journey into Super-resolution (2019, methodology): “The challenge evaluation is based on traditional full-reference metrics such as PSNR, SSIM, RMSE, FC [95], LPIPS [96], as well as the no-reference methods by Ma et al. [97], NIQE [98], BRISQUE [99].”
Objective quality assessment of multiply distorted images (2012, methodology): “The performance of existing objective IQA models such as [1, 2, 3, 4] has previously been measured on databases such as [5, 6] containing images corrupted by one of several pos sible distortions.”
Image information and visual quality (2006, methodology): “In [1], we proposed a new approach to the QA problem where we quantified the information that was shared between the test and the reference images, and demonstrated that this quantification relates well with visual quality.”
Image Super-Resolution via Dual-State Recurrent Networks (2018, methodology): “We provide results of evaluation of our model on several public benchmark datasets in Table 1, with three commonly-used evaluation metrics: Peak Signal-to-Noise Ratio (PSNR), Structural SIMilarity (SSIM) [40] and the Information Fidelity Criterion (IFC) [33].”
F Mean Squared Error: Love It or Leave It? (2009, background): “, the transmitter, the channel, and the receiver [43], [44].”
Comparative evaluation of despeckle filtering in ultrasound imaging of the carotid artery (2005, neutral): “[49].”