Hardware-efficient debanding and visual enhancement filter for inverse tone mapped high dynamic range images and videos

Song, Qingyang; Su, Guan‐Ming; Cosman, Pamela C.

doi:10.1109/icip.2016.7532970

Cited by 13 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…contouring or banding artifacts) in regions with smooth gradient changes. Previous works on bit-depth expansion smooth image by applying the spatially adaptive filter [8] or selective average filter [47], or even directly adding noise to alleviate the artifacts [7]. Learning-based methods [22,32,55,43] have been proposed recently and they usually focus on restoration from lower bit-depth input to the 8-bit image.…”

Section: Dequantizationmentioning

confidence: 99%

HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization

Chen¹,

Liu²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Figure 1. HDR reconstruction with denoising and dequantization from a single LDR image. We propose a novel learning based method for single image HDR reconstruction with denoising and dequantization. The proposed method consists of a spatially dynamic encoder-decoder network and a new T anh L1 loss function. The visual comparison shows that our method reconstructs information in over-exposed regions and also reduces the noise and quantization loss in well-exposed regions. All the images have been µ-law tone-mapped for display. We slightly increase the contrast of patches in the bottom row for clearer visualization. Please zoom in for best view.

show abstract

Section: Dequantizationmentioning

confidence: 99%

HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization

Chen¹,

Liu²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…These methods are intended to conceal false contours at the same bit-depth as the input image. In order to actually increase the bit-depth, there are a number of filtering based methods [56,150,159,229]. For example, the method proposed by Daly and Feng [56] filters the image followed by quantization at the input bit-depth.…”

Section: Single-exposure Techniquesmentioning

confidence: 99%

The high dynamic range imaging pipeline : Tone-mapping, distribution, and single-exposure reconstruction

Eilertsen¹

2018

Linköping Studies in Science and Technology. Dissertations

View full text Add to dashboard Cite

“…Banding is another visual artifact, generally noticeable is poorly-compressed HDR content. In [49], a hardware-friendly implementation of the selective sparse filter is presented. The filter combines a smooth region detection and banding reduction to remove banding artifacts while additionally reducing other compression-related artifacts such as blocking.…”

Section: The Future Of Hdr Technologymentioning

confidence: 99%

The technology behind the exceptional visual experience via high dynamic range

Gadgil

Song

et al. 2018

SIP

Self Cite

View full text Add to dashboard Cite

High dynamic range (HDR) technology is rapidly changing today's video landscape by offering spectacular visual experiences. The development in display technology to support higher luminance levels for commercial and consumer electronic devices such as TVs, smartphones, projectors etc., has created an exponential demand for delivering HDR content to viewers. The essential component of the HDR technology is “expanded contrast,” which allows richer black levels and enhanced brightness, providing dramatic contrast that reveals finer details. The use of “wide color gamut” allows wider color spectrum and richer colors providing aesthetically pleasing true-to-life feel. Such visual enhancements clearly establish HDR as one of the most significant upcoming video technologies.In this paper, we review major technical advances in this exciting field of study. Quantization of HDR signals is reviewed in the context of transfer functions that convert optical signals to electrical signals and vice versa. They mainly consist of Perceptual Quantization and Hybrid-Log-Gamma approaches. Compression of HDR content is another broad area of study involving several coding approaches, often categorized in terms of backward-compatibility and single/dual layer methods. Some key industry applications of HDR processing systems are also discussed, followed by some future directions of HDR technology.

show abstract

Hardware-efficient debanding and visual enhancement filter for inverse tone mapped high dynamic range images and videos

Cited by 13 publications

References 10 publications

HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization

HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization

The high dynamic range imaging pipeline : Tone-mapping, distribution, and single-exposure reconstruction

The technology behind the exceptional visual experience via high dynamic range

Contact Info

Product

Resources

About