Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cut-FUNQUE: An Objective Quality Model for Compressed Tone-Mapped High Dynamic Range Videos

Abhinau K. Venkataramanan, Cosmin Stejerean, Ioannis Katsavounidis, Hassene Tmar, Alan C. Bovik

TL;DR

Cut-FUNQUE tackles the challenge of predicting perceptual quality for tone-mapped and compressed HDR videos by introducing a perceptually uniform color encoding (PUColor), HDRMAX preprocessing, and a multi-scale, wavelet- and NSS-based feature framework. The method uses a bin-weighted, region-aware aggregation to capture diverse distortions across brightness, spatial texture, and temporal activity, culminating in 232 features fused across four scales. On the LIVE-TMHDR database, Cut-FUNQUE delivers state-of-the-art accuracy, achieving median PCC/SROCC around 0.78 and outperforming most baselines while being approximately 23× more computationally efficient than the best deep baselines like MSML. The results demonstrate practical utility for streaming systems that need fast and reliable HDR-to-SDR quality predictions, with potential future improvements in color- and contrast-sensitive descriptors and domain-specific neural approaches.

Abstract

High Dynamic Range (HDR) videos have enjoyed a surge in popularity in recent years due to their ability to represent a wider range of contrast and color than Standard Dynamic Range (SDR) videos. Although HDR video capture has seen increasing popularity because of recent flagship mobile phones such as Apple iPhones, Google Pixels, and Samsung Galaxy phones, a broad swath of consumers still utilize legacy SDR displays that are unable to display HDR videos. As result, HDR videos must be processed, i.e., tone-mapped, before streaming to a large section of SDR-capable video consumers. However, server-side tone-mapping involves automating decisions regarding the choices of tone-mapping operators (TMOs) and their parameters to yield high-fidelity outputs. Moreover, these choices must be balanced against the effects of lossy compression, which is ubiquitous in streaming scenarios. In this work, we develop a novel, efficient model of objective video quality named Cut-FUNQUE that is able to accurately predict the visual quality of tone-mapped and compressed HDR videos. Finally, we evaluate Cut-FUNQUE on a large-scale crowdsourced database of such videos and show that it achieves state-of-the-art accuracy.

Cut-FUNQUE: An Objective Quality Model for Compressed Tone-Mapped High Dynamic Range Videos

TL;DR

Cut-FUNQUE tackles the challenge of predicting perceptual quality for tone-mapped and compressed HDR videos by introducing a perceptually uniform color encoding (PUColor), HDRMAX preprocessing, and a multi-scale, wavelet- and NSS-based feature framework. The method uses a bin-weighted, region-aware aggregation to capture diverse distortions across brightness, spatial texture, and temporal activity, culminating in 232 features fused across four scales. On the LIVE-TMHDR database, Cut-FUNQUE delivers state-of-the-art accuracy, achieving median PCC/SROCC around 0.78 and outperforming most baselines while being approximately 23× more computationally efficient than the best deep baselines like MSML. The results demonstrate practical utility for streaming systems that need fast and reliable HDR-to-SDR quality predictions, with potential future improvements in color- and contrast-sensitive descriptors and domain-specific neural approaches.

Abstract

High Dynamic Range (HDR) videos have enjoyed a surge in popularity in recent years due to their ability to represent a wider range of contrast and color than Standard Dynamic Range (SDR) videos. Although HDR video capture has seen increasing popularity because of recent flagship mobile phones such as Apple iPhones, Google Pixels, and Samsung Galaxy phones, a broad swath of consumers still utilize legacy SDR displays that are unable to display HDR videos. As result, HDR videos must be processed, i.e., tone-mapped, before streaming to a large section of SDR-capable video consumers. However, server-side tone-mapping involves automating decisions regarding the choices of tone-mapping operators (TMOs) and their parameters to yield high-fidelity outputs. Moreover, these choices must be balanced against the effects of lossy compression, which is ubiquitous in streaming scenarios. In this work, we develop a novel, efficient model of objective video quality named Cut-FUNQUE that is able to accurately predict the visual quality of tone-mapped and compressed HDR videos. Finally, we evaluate Cut-FUNQUE on a large-scale crowdsourced database of such videos and show that it achieves state-of-the-art accuracy.
Paper Structure (14 sections, 54 equations, 3 figures, 4 tables)

This paper contains 14 sections, 54 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Cut-FUNQUE
  4. A Perceptually Uniform Encoding Function for Color
  5. HDRMAX Encoding
  6. Perceptually-Sensitized Wavelet Transform
  7. Wavelet-Domain Feature Extraction
  8. Natural Scene Statistics Features
  9. Binned Weighting to Isolate Frame Regions
  10. Evaluating Objective Quality Models
  11. The LIVE-TMHDR Database
  12. Evaluation Protocol
  13. Results of Quality Prediction on LIVE-TMHDR
  14. Conclusion

Figures (3)

  • Figure 1: An overview of the Cut-FUNQUE quality prediction model.
  • Figure 2: Numerical integrals of the threshold function and approximations using non-linear functions
  • Figure 3: A sample video frame and the soft-classification of $8\times8$ cuts into four bins based on luminance, spatial, and temporal complexity features.