Image quality assessment: from error visibility to structural similarity

By Zhou Wang, A. Bovik, Hamid R. Sheikh, Eero P. Simoncelli. 2004

58,269 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, 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 Computer Vision and Pattern Recognition

In Media Technology

In Evaluation & Benchmarks

Citations in the corpus

Scaling Autoregressive Video Models (2019, background): “Prior work mainly reported results on the peak signal-to-noise ratio (PSNR) and mean-structural similarity (SSIM) metrics (Wang et al., 2004b).”
Do ImageNet Classifiers Generalize to ImageNet? (2019, methodology): “To find near-duplicates, we computed the 30 nearest neighbors for each candidate image in three different metrics: `2-distance on raw pixels, `2-distance on features extracted from a pre-trained VGG [49] model (fc7), and SSIM (structural similarity) [56], which is a popular image similarity metric.”
Evaluating Lossy Compression Rates of Deep Generative Models (2020, methodology): “However, for natural images, one could use more perceptually valid distortion metrics such as SSIM (Wang et al., 2004), MSSIM (Wang et al., 2003), or distances between deep features of a CNN (Johnson et al., 2016).”
Learning Energy-Based Spatial-Temporal Generative ConvNets for Dynamic Patterns (2019, background): “The structural similarity (SSIM) index [68] is designed to provide a perceptual judgment on the similarity between two videos, and ranges from 1 to 1, with a larger score indicating greater similarity.”
Image Super-Resolution via Iterative Refinement (2021, background): “Table 2 shows the PSNR, SSIM [63] and Consistency scores for 16 16 !”
EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning (2019, methodology): “Numerical Metrics We measure the quality of our re-sults using the following metrics: 1) relative (cid:96) 1 ; 2) structural similarity index (SSIM) [47], with a window size of 11 ; and 3) peak signal-to-noise ratio (PSNR).”
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric (2018, methodology): “We show qualitative comparison on traditional distortions, using the SSIM [57] metric and BiGAN network [13].”
Image-to-Image Translation with Conditional Adversarial Networks (2016, methodology): “A large body of literature has considered losses of this kind, with methods including conditional random fields [9], the SSIM metric [53], feature matching [13], nonparametric losses [34], the convolutional pseudo-prior [54], and losses based on matching covariance statistics [27].”
Generating Images with Perceptual Similarity Metrics based on Deep Networks (2016, background): “While psychophysical experiments go out of scope of this paper, we believe that deep learned feature representations have better potential than shallow hand-designed SSIM.”
Diffusion Autoencoders: Toward a Meaningful and Decodable Representation (2021, methodology): “The evaluation metrics are SSIM [53] (↑), LPIPS [61] (↓), and MSE.”
GAN Inversion: A Survey (2021, background): “The most widely used metrics are PSNR and SSIM.”
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (2016, methodology): “For fair quantitative comparison, all reported PSNR [dB] and SSIM [49] measures were calculated on the ychannel using the daala package available at https: //github.”
Semantic Image Inpainting with Deep Generative Models (2016, positive): “Similar results are obtained using SSIM [36] instead of PSNR.”
Deep multi-scale video prediction beyond mean square error (2015, positive): “We also provide the Structural Similarity Index Measure (SSIM) of Wang et al. (2004).”
Combined Scaling for Zero-shot Transfer Learning (2021, methodology): “To avoid such contaminations, we ﬁlter all instances in our training data that has a structural similarity index (SSIM (Wang et al., 2004)) of at least 0.5 with any image from our evaluation benchmarks.”
Meta-Learning Probabilistic Inference for Prediction (2018, background): “Mean squared error (MSE – lower is better) and the structural similarity index (SSIM - higher is better) (Wang et al., 2004) are measured between the generated and ground truth images.”
Generating Images with Sparse Representations (2021, background): “…takes advantage of the statistical structure of natural images (e.g., smooth signals with high frequency noise) and human vision (e.g., low frequencies tend to be more perceptually salient) by dropping high frequency information, to strike favorable efﬁciency/quality trade-offs (Wang et al., 2004).”
Perceptual Losses for Real-Time Style Transfer and Super-Resolution (2016, methodology): “We report PSNR and SSIM [59], computing both only on the Y channel after converting to the YCbCr colorspace, following [1,44].”
Generating Images from Captions with Attention (2015, methodology): “As you can see on Table 1, SSI scores achieved by variational models were higher compared to SSI score achieved by LAPGAN.”