Physiological inverse tone mapping based on retina response

Huo, Yongqing; Yang, Fan; Dong, Le; Brost, Vincent

doi:10.1007/s00371-013-0875-4

Cited by 109 publications

(76 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among these, the EO of Huo et al [9] expands LDR pixels by inverting the local retina response without the need of segmentation or expand maps. Instead, the EO by Kuo et al [10] inverts a class of parametric tone mapping operators (TMOs), i.e.…”

Section: A Expansion Operators (Eos)mentioning

confidence: 99%

“…The algorithms include (letters denote the abbreviation used in the rest of the paper to refer to each algorithm): (A) simple linear scaling 1 of LDR values to meet the HDR display luminance range [11]; (M) the highlight enhancement method by Meylan et al [5] (with ⇢ = 0.67); (R) the method based on expand map by Rempel et al [2]; and (H) the perceptual algorithm by Huo et al [9].…”

Section: A Source Ldr Content and Considered Eosmentioning

confidence: 99%

“…In a more constrained scenario, where the goal is to render LDR content on an HDR screen, the problem is more tractable, though its solution is not unique. As a result, various expansion operators (EOs) have been proposed [2][3][4][5][6][7][8][9][10]. Evaluating these techniques plays a key role in the design of new EOs and helps to improve the characteristics of HDR displays.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dynamic range expansion of video sequences: A subjective quality assessment study

Simone

Valenzise

Lauga

et al. 2014

2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)

View full text Add to dashboard Cite

The goal of this paper is to assess whether existing solutions to expand low dynamic range (LDR) still images to high dynamic range (HDR) displays can apply to moving pictures. To this end, we conduct a subjective quality assessment test on four state-of-the-art expansion operators, using high-quality input LDR content. Our results show that, perhaps surprisingly, no temporal artifacts, such as flickering due to global illumination changes, are introduced applying frame-based algorithms. In addition, they confirm previous studies in that operators as simple as linear expansion can yield acceptable (or even excellent) quality of the HDR video.Index Terms-High dynamic range, expansion operators, HDR display, subjective quality assessment

show abstract

Section: A Expansion Operators (Eos)mentioning

confidence: 99%

Section: A Source Ldr Content and Considered Eosmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic range expansion of video sequences: A subjective quality assessment study

Simone

Valenzise

Lauga

et al. 2014

2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)

View full text Add to dashboard Cite

show abstract

“…Kovaleski and Oliviera [KO14] extended the work of Rempel et al via the use of a cross bilateral filter. Subsequently, Huo et al [HYDB14] further extended this work to remove the thresholding used by Kovaleski and Oliviera.…”

Section: Related Workmentioning

confidence: 99%

ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content

Marnerides

Bashford-Rogers

Hatchett

et al. 2018

Computer Graphics Forum

227

248

View full text Add to dashboard Cite

High dynamic range (HDR) imaging provides the capability of handling real world lighting as opposed to the traditional low dynamic range (LDR) which struggles to accurately represent images with higher dynamic range. However, most imaging content is still available only in LDR. This paper presents a method for generating HDR content from LDR content based on deep Convolutional Neural Networks (CNNs) termed ExpandNet. ExpandNet accepts LDR images as input and generates images with an expanded range in an end‐to‐end fashion. The model attempts to reconstruct missing information that was lost from the original signal due to quantization, clipping, tone mapping or gamma correction. The added information is reconstructed from learned features, as the network is trained in a supervised fashion using a dataset of HDR images. The approach is fully automatic and data driven; it does not require any heuristics or human expertise. ExpandNet uses a multiscale architecture which avoids the use of upsampling layers to improve image quality. The method performs well compared to expansion/inverse tone mapping operators quantitatively on multiple metrics, even for badly exposed inputs.

show abstract

“…HDR imaging equipments are often expensive [1][2][3] and the captured images often need to be compressed to LDR images due to the limitation of common display equipments. Therefore, software imaging technique is popular, which includes tone mapping [4][5][6][7] and exposure fusion. Compared to the former one, exposure fusion is a simple and direct method because it need not estimate the camera response function and do not produce the intermediate HDR image.…”

Section: Introductionmentioning

confidence: 99%

An improved exposure fusion of image pairs with window constraint

Zhang

2015

2015 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)

View full text Add to dashboard Cite

The real scene often has too High Dynamic Range (HDR) to be captured in a single common digital image. Exposure fusion is a simple, direct and effective method to transform multiple Low Dynamic Range (LDR) images under different exposure settings into a single HDR-like LDR image. A pair of exposure bracketed images often contains insufficient image information of the scene, so the classic methods generate undesirable results especially in the transition regions. In this paper we introduce a novel optimization model for adjusting the weight maps defined by the Mertens' method. Our weightadjustment method is performed on overlapping windows all over the pixels in the image domain. Using this method, the global visual effect and the local detail can be preserved even in challenging pair of images that contains insufficient information. Experimental results demonstrate that our method obtain natural images. Comparisons with the Mertens' method show that our algorithm can generate better quality images.Index Terms-Exposure fusion, weight adjustment, window constraint.

show abstract

Physiological inverse tone mapping based on retina response

Cited by 109 publications

References 11 publications

Dynamic range expansion of video sequences: A subjective quality assessment study

Dynamic range expansion of video sequences: A subjective quality assessment study

ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content

An improved exposure fusion of image pairs with window constraint

Contact Info

Product

Resources

About