Gradient-Based Tone Mapping for Rate-Distortion Optimized Backward-Compatible High Dynamic Range Compression

Gommelet, David; Roumy, Aline; Guillemot, Christine; Ropert, Michael; Tanou, Julien Le

doi:10.1109/tip.2017.2740159

Cited by 14 publications

(14 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The purpose of the weights in (1) is to exclude saturated intensities from the weighted average. Beyond that, post-processing for the radiance map is necessary, such as white balance, gamma correction, and tone mapping [19,20]. Figure 2 shows the general steps of HDR image reconstruction.…”

Section: Figurementioning

confidence: 99%

“…Specifically, the radiance map can be (1) method has its own weighting . The purpose of the weights in (1) is to exclude saturated and noisy pixel processing for the radiance map is necessary, such as white balance, gamma correction, and tone mapping [19,20]. Figure nal complexities arise when objects of the scene or camera move between shots, and thus images with different The traditional HDR image reconstruction approach.…”

Section: Figurementioning

confidence: 99%

See 1 more Smart Citation

Joint Up-sampling High Dynamic Range Images with a Guidance Image

Siqi¹

2019

JMI

View full text Add to dashboard Cite

In this paper, we address the problem of acquiring guidance images for use in joint up-sampling of high dynamic range (HDR) images. A guidance image is usually an unprocessed high-resolution image that is indispensable to joint up-sampling, which is aimed at accelerating a large class of image processing operators. However, the guidance image is blank-posed in joint up-sampling of the HDR image, which involves the process where multiple low dynamic range (LDR) images with various exposure times in the same scene are synthesized into one image with a greater dynamic range; Such many-toone operations limit joint up-sampling in being applied to this field. To this end, we propose an HDR guidance image (HGI), which is an image type generated by weighted averaging LDR images into a single with rich contour information. The huge advantage of joint up-sampling is that the cost of running the original algorithm is at a greatly reduced resolution. Since HGI synthesis takes about 3-70ms, and joint up-sampling of an HDR image takes about 20-300ms, most operations can be done with GPU shaders. Compared with the conventional methods of HDR image reconstruction, using joint upsampling can achieve 3-10 times the performance acceleration. We demonstrate that joint up-sampling using our guidance images can produce high-resolution HDR images with no visible degradation compared to the image produced by the conventional method.

show abstract

Section: Figurementioning

confidence: 99%

Section: Figurementioning

confidence: 99%

Joint Up-sampling High Dynamic Range Images with a Guidance Image

Siqi¹

2019

JMI

View full text Add to dashboard Cite

show abstract

“…Tone mapping is a prerequisite in the high dynamic range (HDR) imaging [1], [2], [3], [4] pipeline to print or render HDR content for low dynamic range displays. With the unprecedented demands of capturing/reproducing scenes in highresolution and superior quality, HDR technology is growing rapidly [5], [6], [7].…”

Section: Introductionmentioning

confidence: 99%

Deep Tone Mapping Operator for High Dynamic Range Images

Rana

Singh

Valenzise

et al. 2020

IEEE Trans. on Image Process.

111

View full text Add to dashboard Cite

A computationally fast tone mapping operator (TMO) that can quickly adapt to a wide spectrum of high dynamic range (HDR) content is quintessential for visualization on varied low dynamic range (LDR) output devices such as movie screens or standard displays. Existing TMOs can successfully tone-map only a limited number of HDR content and require an extensive parameter tuning to yield the best subjective-quality tone-mapped output. In this paper, we address this problem by proposing a fast, parameter-free and scene-adaptable deep tone mapping operator (DeepTMO) that yields a high-resolution and high-subjective quality tone mapped output. Based on conditional generative adversarial network (cGAN), DeepTMO not only learns to adapt to vast scenic-content (e.g., outdoor, indoor, human, structures, etc.) but also tackles the HDR related scenespecific challenges such as contrast and brightness, while preserving the fine-grained details. We explore 4 possible combinations of Generator-Discriminator architectural designs to specifically address some prominent issues in HDR related deep-learning frameworks like blurring, tiling patterns and saturation artifacts. By exploring different influences of scales, loss-functions and normalization layers under a cGAN setting, we conclude with adopting a multi-scale model for our task. To further leverage on the large-scale availability of unlabeled HDR data, we train our network by generating targets using an objective HDR quality metric, namely Tone Mapping Image Quality Index (TMQI). We demonstrate results both quantitatively and qualitatively, and showcase that our DeepTMO generates high-resolution, high-quality output images over a large spectrum of real-world scenes. Finally, we evaluate the perceived quality of our results by conducting a pair-wise subjective study which confirms the versatility of our method.

show abstract

“…Compression schemes using an enhancement layer are referred to as two layer (or scalable) schemes. We showed in a previous contribution [1], that a two layer scheme can be optimally separated into a TMO optimization in a single layer scheme followed by a rate allocation step.…”

Section: Introductionmentioning

confidence: 99%

Optical-Flow Based Nonlinear Weighted Prediction for SDR and Backward Compatible HDR Video Coding

Gommelet

Tanou²,

Roumy

et al. 2020

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Tone Mapping Operators (TMO) designed for videos can be classified into two categories. In a first approach, TMOs are temporal filtered to reduce temporal artifacts and provide a Standard Dynamic Range (SDR) content with improved temporal consistency. This however does not improve the SDR coding Rate Distortion (RD) performances. A second approach is to design the TMO with the goal of optimizing the SDR coding ratedistortion performances. This second category of methods may lead to SDR videos altering the artistic intent compared with the produced HDR content. In this paper, we combine the benefits of the two approaches by introducing new Weighted Prediction (WP) methods inside the HEVC SDR codec. As a first step, we demonstrate the interest of the WP methods compared to TMO optimized for RD performances. Then we present the newly introduced WP algorithm and WP modes. The WP algorithm consists in performing a global motion compensation between frames using an optical flow, and the new modes are based on non linear functions in contrast with the literature using only linear functions. The contribution of each novelty is studied independently and in a second time they are all put in competition to maximize the RD performances. Tests were made for HDR backward compatible compression but also for SDR compression only. In both cases, the proposed WP methods improve the RD performances while maintaining the SDR temporal coherency.

show abstract

Gradient-Based Tone Mapping for Rate-Distortion Optimized Backward-Compatible High Dynamic Range Compression

Cited by 14 publications

References 32 publications

Joint Up-sampling High Dynamic Range Images with a Guidance Image

Joint Up-sampling High Dynamic Range Images with a Guidance Image

Deep Tone Mapping Operator for High Dynamic Range Images

Optical-Flow Based Nonlinear Weighted Prediction for SDR and Backward Compatible HDR Video Coding

Contact Info

Product

Resources

About