• Corpus ID: 239016003

Deep Image Debanding

  title={Deep Image Debanding},
  author={Raymond Zhou and Shahrukh Athar and Zhongling Wang and Zhou Wang},
Banding or false contour is an annoying visual artifact whose impact is even more pronounced in ultra high definition, high dynamic range, and wide colour gamut visual content, which is becoming increasingly popular. Since users associate a heightened expectation of quality with such content and banding leads to deteriorated visual quality-of-experience, the area of banding removal or debanding has taken paramount importance. Existing debanding approaches are mostly knowledge-driven. Despite… 

Figures and Tables from this paper


Capturing Banding in Images: Database Construction and Objective Assessment
A deep neural net-work based no-reference deep banding index (DBI) is developed, which not only produces an overall banding assessment of a given image, but also creates a banding map that indicates the variation of banding across the image space.
An efficient deep convolutional neural networks model for compressed image deblocking
  • Ke Li, Bahetiyaer Bare, Bo Yan
  • Computer Science
    2017 IEEE International Conference on Multimedia and Expo (ICME)
  • 2017
This paper presents an efficient deep C-NNs model that can well alleviate the conflict between bit reduction and quality preservation by taking local small patches into consideration and outperforms the state-of-the-art methods in both the objective quality and the perceptual quality.
Understanding and Removal of False Contour in HEVC Compressed Images
This work identifies the cause of false contours by explaining the human perceptual experiences on them with specific experiments, and proposes a precise pixel-based false contour detection method based on the evolution of afalse contour candidate (FCC) map.
Enhanced Pix2pix Dehazing Network
The proposed Enhanced Pix2pix Dehazing Network (EPDN), which generates a haze-free image without relying on the physical scattering model, is embedded by a generative adversarial network, which is followed by a well-designed enhancer.
dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs
This paper shows that a vast amount of reliable training data in the form of quality-discriminable image pairs (DIPs) can be obtained automatically at low cost by exploiting large-scale databases with diverse image content, and learns an opinion-unaware BIQA (OU-BIQA, meaning that no subjective opinions are used for training) model from millions of DIPs, leading to a DIP inferred quality (dipIQ) index.
A new distortion-specific no-reference video quality model for predicting banding artifacts, called the Blind BANding Detector (BBAND index), which is inspired by human visual models.
Perceptually motivated model for predicting banding artefacts in high-dynamic range images
A model that relies on the contrast sensitivity function (CSF) of the visual system, and hence, predicts the visibility of banding artefacts in a perceptually accurate way is developed and validated.
A Feature-Enriched Completely Blind Image Quality Evaluator
The proposed opinion-unaware BIQA method does not need any distorted sample images nor subjective quality scores for training, yet extensive experiments demonstrate its superior quality-prediction performance to the state-of-the-art opinion-aware BIZA methods.
DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
DeblurGAN achieves state-of-the art performance both in the structural similarity measure and visual appearance and is 5 times faster than the closest competitor - Deep-Deblur.
Blind Image Quality Assessment Based on High Order Statistics Aggregation
A novel general purpose BIQA method based on high order statistics aggregation (HOSA), requiring only a small codebook, which has been extensively evaluated on ten image databases with both simulated and realistic image distortions, and shows highly competitive performance to the state-of-the-art BIZA methods.