Full-Reference Objective Quality Assessment of Tone-Mapped Images

Hadizadeh, Hadi; Bajić, Ivan V.

doi:10.1109/tmm.2017.2740023

Cited by 40 publications

(18 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fig. 12 and Table V show that FRQM offers improved performance over all other tested metrics, demonstrated by higher correlation coefficients, fewer outliers and lower prediction errors 5 . This is achieved with relatively low complexity (30 times greater than PSNR).…”

Section: Frqmmentioning

confidence: 93%

“…The content of the database is characterised using two distinct methods: one involves computing the coverage of BVI-HFR over three low-level descriptors, while the other compares BVI-HFR to typical broadcast material from BBC Redux archives. bobblehead (1) books (2) bouncyball (3) catch (4) catch track (5) cyclist (6) flowers (7) golf side (8) guitar focus (9) hamster (10) joggers (11) lamppost (12) leaves wall (13) library (14) martial arts (15) plasma (16) pond (17) pour (18) sparkler (19) typing (20) water ripples (21) water splashing (22)…”

Section: Bvi-hfr Video Databasementioning

confidence: 99%

“…As the demand for higher quality and more engaging video experiences increases, the pressure to extend the video parameter space beyond current spatial and temporal resolutions, dynamic ranges and screen sizes becomes ever greater [1]. Most of the significant activity in recent years has been focused towards the implementation of high spatial resolution (4K/8K) [2,3], high dynamic range (HDR) [4,5] and immersive multi-view formats [6,7]. However the progress related to high frame rate formats has been comparatively slow, shown by the frame rates used in television and cinema having remained constant for many years -rarely exceeding 60 fps.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Study of High Frame Rate Video Formats

Mackin

Zhang

Bull

2019

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Section: Frqmmentioning

confidence: 93%

Section: Bvi-hfr Video Databasementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Study of High Frame Rate Video Formats

Mackin

Zhang

Bull

2019

IEEE Trans. Multimedia

View full text Add to dashboard Cite

“…From acquisition to display, several significant developments have been made in High Dynamic Range (HDR) imagery in the last couple of decades [3]. It has been successfully applied to several multimedia technologies, including video coding [4], inverse tone mapping [5], saliency detection [6], data hiding [7], and quality assessment [8], but also to fields such as automotive or spacecrafts imaging [9]. HDR enables to capture a wider dynamic range and color gamut, encapsulating a vast amount of information.…”

Section: Introductionmentioning

confidence: 99%

Learning-Based Tone Mapping Operator for Efficient Image Matching

Rana

Valenzise

Dufaux

2019

IEEE Trans. Multimedia

View full text Add to dashboard Cite

To cite this version:Aakanksha Rana, Giuseppe Valenzise, Frédéric Dufaux. Learning-based tone mapping operator for efficient image matching.Abstract-In this paper, we propose a new framework to optimally tone map the high dynamic range (HDR) content for image matching under drastic illumination variations. Since tone mapping operators (TMO) have traditionally been used for displaying HDR scenes, their design is suboptimal when used for computer vision tasks such as image matching. We address this sub-optimality by proposing a two-step framework, consisting of: a) a luminance-invariant guidance model based on a Support Vector Regressor (SVR) to optimally adapt the tone mapping function for image matching; and b) an energy maximization model to generate appropriate training samples for learning the SVR. At each step, we collectively address both stages of keypoint detection and descriptor extraction in the feature matching framework. By locally altering the intrinsic characteristics of the tone mapping function, the learned guidance model facilitates the extraction of local invariant features in the presence of illumination variations. We demonstrate that the proposed TMO significantly outperforms perceptually-driven state-of-the-art TMOs on a dataset of HDR scenes characterized by challenging lighting variations, such as day/night transitions.Index Terms-High dynamic range, tone mapping operator, image matching, stochastic gradient descent, machine learning.

show abstract

“…Such formats are becoming increasingly popular as they provide the potential to offer new sustainable multimedia services and experiences. There is significant research activity in all aspects of this technology [1][2][3][4][5][6][7][8][9][10][11][12], from content design to displays, new immersive audio-visual formats and quality assessment.…”

Section: Introductionmentioning

confidence: 99%

BVI-HD: A Video Quality Database for HEVC Compressed and Texture Synthesized Content

Zhang

Moss

Baddeley

et al. 2018

IEEE Trans. Multimedia

View full text Add to dashboard Cite

This paper introduces a new high definition video quality database, referred to as BVI-HD, which contains 32 reference and 384 distorted video sequences plus subjective scores. The reference material in this database was carefully selected to optimise the coverage range and distribution uniformity of five low level video features, while the included 12 distortions, using both original High Efficiency Video Coding (HEVC) and HEVC with synthesis mode (HEVC-SYNTH), represent state-ofthe-art approaches to compression. The range of quantisation parameters included in the database for HEVC compression was determined by a subjective study, the results of which indicate that a wider range of QP values should be used than the current recommendation. The subjective opinion scores for all 384 distorted videos were collected from a total of 86 subjects, using a double stimulus test methodology. Based on these results, we compare the subjective quality between HEVC and synthesised content, and evaluate the performance of nine state-of-the-art, full-reference objective quality metrics. This database has now been made available online, representing a valuable resource to those concerned with compression performance evaluation and objective video quality assessment.

show abstract

Full-Reference Objective Quality Assessment of Tone-Mapped Images

Cited by 40 publications

References 46 publications

A Study of High Frame Rate Video Formats

A Study of High Frame Rate Video Formats

Learning-Based Tone Mapping Operator for Efficient Image Matching

BVI-HD: A Video Quality Database for HEVC Compressed and Texture Synthesized Content

Contact Info

Product

Resources

About