Compression of high dynamic range video using the HEVC and H.264/AVC standards

Banitalebi-Dehkordi, Amin; Azimi, Maryam; Pourazad, Mahsa T.; Nasiopoulos, Panos

doi:10.1109/qshine.2014.6928652

Cited by 31 publications

(15 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The paper concludes that for specific bitrates, subjective evaluation results suggest that HDR video generated by the perceptual quantization scheme were rated higher than the videos reconstructed using the inverse tone-mapping scheme. Similar evaluations on HDR video content have been conducted by Dehkrodi et al [6], Dong et al [11], Rerabek et al [38], Hanhart et al [16], Narwaria et al [35].…”

Section: Evaluation Of Hdr Video Compression Methodssupporting

confidence: 52%

“…Subsequently, the participant had to view each of the seven decoded HDRVs including the hidden reference and perform a qualitative assessment as to how much the decoded HDRVs resembled the ground truth HDRV in the center. Based on their judgement, the participants positioned the corresponding thumbnails to one of the blank positions on the right labeled [1][2][3][4][5][6][7] where 1 being an HDRV with least distortion compared to the reference and 7 being the HDRV with most visible distortions. …”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Objective and subjective evaluation of High Dynamic Range video compression

Mukherjee

Debattista

Bashford-Rogers

et al. 2016

Signal Processing: Image Communication

View full text Add to dashboard Cite

Copyright and reuse:The Warwick Research Archive Portal (WRAP) makes this work by researchers of the University of Warwick available open access under the following conditions. Copyright © and all moral rights to the version of the paper presented here belong to the individual author(s) and/or other copyright owners. To the extent reasonable and practicable the material made available in WRAP has been checked for eligibility before being made available.Copies of full items can be used for personal research or study, educational, or not-for-profit purposes without prior permission or charge. Provided that the authors, title and full bibliographic details are credited, a hyperlink and/or URL is given for the original metadata page and the content is not changed in any way. A note on versions:The version presented here may differ from the published version or, version of record, if you wish to cite this item you are advised to consult the publisher's version. Please see the 'permanent WRAP URL' above for details on accessing the published version and note that access may require a subscription. AbstractA number of High Dynamic Range (HDR) video compression algorithms proposed to date have either been developed in isolation or only-partially compared with each other. Previous evaluations were conducted using quality assessment error metrics, which for the most part were developed for qualitative assessment of Low Dynamic Range (LDR) videos. This paper presents a comprehensive objective and subjective evaluation conducted with six published HDR video compression algorithms. The objective evaluation was undertaken on a large set of 39 HDR video sequences using seven numerical error metrics namely: PSNR, logPSNR, puPSNR, puSSIM, Weber MSE, HDR-VDP and HDR-VQM. The subjective evaluation involved six short-listed sequences and two ranking-based subjective experiments with hidden reference at two different output bitrates with 32 participants each, who were tasked to rank distorted HDR video footage compared to an uncompressed version of the same footage. Results suggest a strong correlation between the objective and subjective evaluation. Also, non-backward compatible compression algorithms appear to perform better at lower output bit rates than backward compatible algorithms across the settings used in this evaluation.

show abstract

Section: Evaluation Of Hdr Video Compression Methodssupporting

confidence: 52%

Section: Methodsmentioning

confidence: 99%

Objective and subjective evaluation of High Dynamic Range video compression

Mukherjee

Debattista

Bashford-Rogers

et al. 2016

Signal Processing: Image Communication

View full text Add to dashboard Cite

show abstract

“…The measures have been evaluated and averaged over the saturated pixels only. Test data are 10 HDR video sequences from two different sources [10,3]. The blind video consistency has been performed on gamma corrected HDR images.…”

Section: Hdr Reconstructionmentioning

confidence: 99%

Single-Frame Regularization for Temporally Stable CNNs

Eilertsen

Mantiuk

Unger

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) can model complicated non-linear relations between images. However, they are notoriously sensitive to small changes in the input. Most CNNs trained to describe image-to-image mappings generate temporally unstable results when applied to video sequences, leading to flickering artifacts and other inconsistencies over time. In order to use CNNs for video material, previous methods have relied on estimating dense frame-to-frame motion information (optical flow) in the training and/or the inference phase, or by exploring recurrent learning structures. We take a different approach to the problem, posing temporal stability as a regularization of the cost function. The regularization is formulated to account for different types of motion that can occur between frames, so that temporally stable CNNs can be trained without the need for video material or expensive motion estimation. The training can be performed as a fine-tuning operation, without architectural modifications of the CNN. Our evaluation shows that the training strategy leads to large improvements in temporal smoothness. Moreover, for small datasets the regularization can help in boosting the generalization performance to a much larger extent than what is possible with naïve augmentation strategies.

show abstract

“…Combined with the recent increase in HDR image data, e.g. due to a number of publicly available HDR video datasets [23,40,95,136], deep learning for HDR imaging is now an interesting topic to be explored. There are only very few examples of deep learning for HDR imaging published before the year 2017, including estimation of reflectance maps from images [213].…”

Section: Deep Learning For Hdr Imagingmentioning

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

Compression of high dynamic range video using the HEVC and H.264/AVC standards

Cited by 31 publications

References 16 publications

Objective and subjective evaluation of High Dynamic Range video compression

Objective and subjective evaluation of High Dynamic Range video compression

Single-Frame Regularization for Temporally Stable CNNs

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

Contact Info

Product

Resources

About