Perceptual image quality assessment using a normalized Laplacian pyramid

By Valero Laparra, Johannes Ballé, Alexander Berardino, Eero P. Simoncelli. 2016

177 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, 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 Cognitive Neuroscience

1. Johannes Ballé
2. Valero Laparra
3. Eero P. Simoncelli
4. Kede Ma
5. Ferenc Huszár
6. Lucas Theis
7. Wenzhe Shi
8. Weisi Lin

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Ming-Hsuan Yang
3. Dacheng Tao
4. Radu Timofte
5. Chen Change Loy
6. Lei Zhang
7. Andrea Vedaldi
8. Xiaogang Wang

In Media Technology

1. Ferenc Huszár
2. Lucas Theis
3. Kede Ma
4. Weisi Lin
5. Wenzhe Shi
6. Radu Timofte
7. Bernhard Schölkopf
8. Michael Hirsch

Citations in the corpus

• End-to-end optimization of nonlinear transform codes for perceptual quality (2016, methodology): “We optimized each of these for two distortion metrics: mean squared error (MSE) and distance in the NLP domain [4].”
• Lossy Image Compression with Compressive Autoencoders (2017, methodology): “While Gregor et al. (2016) used a Gaussian distribution for the encoder, we can link their approach to the work of Ball´e et al. (2016) by assuming it to be uniform, p ( y | x ) = f ( x ) + u .”
• Amortised MAP Inference for Image Super-resolution (2016, methodology): “most widely used loss functions MSE and the related peak-signal-to-noise-ratio (PSNR) metric have been shown to correlate poorly with human perception of image quality (Laparra et al., 2016; Wang et al., 2004).”
• Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Network (2018, background): “Previous studies [46,27] revealed that pixel-wise computed error measures correlate poorly with human perception of image quality.”
• TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment (2023, background): “[10] introduced the structural similarity (SSIM) index to compare structural similarity in local patches, which inspired a lot of followup works [4], [11]–[16].”
• Generative Compression (2017, background): “, 2016) and an area of active research (Laparra et al., 2016)).”
• Image Quality Assessment: Unifying Structure and Texture Similarity (2020, methodology): “Others have used transformations that mimic the early visual system [22], [37]–[39].”
• The Unreasonable Effectiveness of Texture Transfer for Single Image Super-resolution (2018, background): “This was illustrated in [10, 11] and recently mathematically analyzed in [12].”