FSIM: A Feature Similarity Index for Image Quality Assessment

By Lin Zhang, Lei Zhang, Xuanqin Mou, David Dapeng Zhang. 2011

4,965 citations recorded by the source corpus.

Subfields: Oncology, Public Health, Environmental and Occupational Health, Evaluation & Benchmarks

How researchers see this paper

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

In Oncology

In Public Health, Environmental and Occupational Health

In Evaluation & Benchmarks

Citations in the corpus

The Unreasonable Effectiveness of Deep Features as a Perceptual Metric (2018, methodology): “In each case, the traditional metrics (L2/PSNR, SSIM, FSIM) disagree with human judgments.”
Perceptual Losses for Real-Time Style Transfer and Super-Resolution (2016, background): “More results (including FSIM [63] and VIF [64] metrics) are shown in the supplementary material.”
The Perception-Distortion Tradeoff (2017, background): “Many alternative, more perceptual, distortion measures have been proposed, including SSIM [40], MS-SSIM [42], IFC [36], VIF [35], VSNR [3] and FSIM [47].”
Learning a No-Reference Quality Metric for Single-Image Super-Resolution (2016, methodology): “Ours BRISQUEBLIINDS CORNIA CNNIQA NSSA DIVINE BIQI IFC SSIM FSIM PSNR [41] [23] [24] [42] [28] [21] [20] [18] [16] [43] Bicubic 0.”
fastMRI: An Open Dataset and Benchmarks for Accelerated MRI (2018, methodology): “t from the validation, test, or challenge sets. 10 5 Metrics The assessment of MRI reconstruction quality is of paramount relevance to develop and compare machine learning and medical imaging systems [51,53,3,58]. The most commonly used evaluation metrics in the MRI reconstruction literature [3] inc”
Domain Fingerprints for No-Reference Image Quality Assessment (2019, background): “Considering that perceptual scores are not available in Waterloo Exploration, we provide a score and weight for every distorted image patch by performing FSIM [36], which is one of the state-of-the-art FR-IQA metrics.”
The 2018 PIRM Challenge on Perceptual Image Super-Resolution (2018, methodology): “ctly evaluating the perceptual quality of perceptually-aware SR algorithms are NIQE and PI (which is a combination of NIQE and Ma). Note that we also tested the full-reference measures VIF [33], FSIM [50] and MS-SSIM [47], and the no-reference measures CORNIA [49] and BLIINDS [31], which all failed ”
No-Reference Image Sharpness Assessment in Autoregressive Parameter Space (2015, methodology): “We further take chrominance information into consideration, as used in the literature [3], [4].”
Blind Image Quality Estimation via Distortion Aggravation (2018, methodology): “GSI [24], FSIM [25], GMSD [26], PSIM [14].”
Nonlocally Centralized Sparse Representation for Image Restoration (2013, methodology): “From left to right and top to bottom: original image, noisy image (σ = 100), and denoised images by SAPCA-BM3D [39] (PSNR = 25.20 dB; FSIM = 0.8065), LSSC [18] (PSNR = 25.63 dB; FSIM = 0.8017), EPLL [33] (PSNR = 25.44 dB; FSIM = 0.8100), and NCSR (PSNR = 25.65 dB; FSIM = 0.8068). achieves highly com”
TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment (2023, neutral): “To address this, Wang et al. [13] introduced the structural similarity (SSIM) index to compare structural similarity in local patches, which inspired a lot of follow-up works [7], [14], [15], [16], [17], [18], [19].”
Text-to-image Synthesis via Symmetrical Distillation Networks (2018, neutral): “Flower-102 is split into 82 training categories and 20 testing categories. 4.2 Quantitative Evaluation For quantitative evaluation, we adopt four kinds of metrics: inception score [33], SSIM[39], FSIM[44] and human rank. Inception score is a numerical assessment approach, which has been widely used ”
Color image database TID2013: Peculiarities and preliminary results (2013, background): “All aforementioned metrics (except FSIM) have been computed using the software [35].”
Deep Learning of Human Visual Sensitivity in Image Quality Assessment Framework (2017, methodology): “DeepQA was compared to eight FR-IQA metrics: PSNR, SSIM [32], MS-SSIM [33], VIF [28], GMSD [34], FSIMc [35], DOG-SSIMc [17], and FR-DCNN [14].”
The Analysis of Image Contrast: From Quality Assessment to Automatic Enhancement (2016, methodology): “, gradient and phase) in the IQA exploration, feature similarity index (FSIM) [11], gradient similarity index (GSIM) [12], internal generative”