Perceptual representations of structural information in images: application to quality assessment of synthesized view in FTV scenario

Le Callet Patrick; Li Jing; Ling suiyi; Wang Junle

arxiv: 1907.03448 · v1 · pith:VU7JF2AWnew · submitted 2019-07-08 · 📡 eess.IV · cs.CV

Perceptual representations of structural information in images: application to quality assessment of synthesized view in FTV scenario

Ling suiyi , Li Jing , Le Callet Patrick , Wang Junle This is my paper

Pith reviewed 2026-05-25 01:09 UTC · model grok-4.3

classification 📡 eess.IV cs.CV

keywords image quality assessmentfree-viewpoint TVstructural informationbio-inspired metricsynthesized viewscontour descriptorsperceptual hierarchy

0 comments

The pith

A full-reference quality metric for free-viewpoint TV combines low-level contours, mid-level contour categories, and task-oriented non-natural structure descriptors to better capture non-uniform distortions in synthesized views.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes a bio-inspired image quality metric that draws on hierarchical structural representations from the human visual system to assess synthesized views in free-viewpoint TV. It extracts features at three levels: basic contour descriptors, contour category descriptors, and descriptors tuned to non-natural structures that arise in view synthesis. The approach targets structure-related distortions that differ from the uniform artifacts handled by conventional metrics. Experiments on relevant databases show the new metric produces higher correlation with human judgments than existing methods.

Core claim

Structural representations extracted from multiple levels of the human visual system hierarchy can be combined into a full-reference metric that quantifies the perceptual impact of structure-related distortions on synthesized views in the FTV scenario, with the resulting model outperforming state-of-the-art metrics.

What carries the argument

The three-layer bio-inspired metric formed by low-level contour descriptor, mid-level contour category descriptor, and task-oriented non-natural structure descriptor.

If this is right

The metric provides a more accurate automatic evaluation tool for synthesized views containing non-uniform structural artifacts.
It distinguishes natural contour properties from synthesis-induced non-natural structures.
The hierarchical decomposition allows separate analysis of distortion effects at different perceptual levels.
Experimental results indicate superior performance over current metrics on FTV-specific test material.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same layered descriptors might be tested on other view-synthesis pipelines to check whether the performance gain generalizes beyond the reported databases.
If the non-natural structure descriptor proves robust, it could be isolated and used as an auxiliary loss in view-synthesis training loops.
The approach suggests that quality metrics for immersive content may need explicit handling of task-oriented, scene-inconsistent structures rather than generic natural-image statistics.

Load-bearing premise

Multi-level structural representations from the human visual system can be directly translated into a quantitative measure of how structure-related distortions affect perceived quality in FTV synthesized views.

What would settle it

On standard FTV synthesized-view databases, the proposed metric shows no statistically significant improvement in correlation with subjective scores compared with the best existing full-reference metrics.

read the original abstract

As the immersive multimedia techniques like Free-viewpoint TV (FTV) develop at an astonishing rate, user's demand for high-quality immersive contents increases dramatically. Unlike traditional uniform artifacts, the distortions within immersive contents could be non-uniform structure-related and thus are challenging for commonly used quality metrics. Recent studies have demonstrated that the representation of visual features can be extracted from multiple levels of the hierarchy. Inspired by the hierarchical representation mechanism in the human visual system (HVS), in this paper, we explore to adopt structural representations to quantitatively measure the impact of such structure-related distortion on perceived quality in FTV scenario. More specifically, a bio-inspired full reference image quality metric is proposed based on 1) low-level contour descriptor; 2) mid-level contour category descriptor; and 3) task-oriented non-natural structure descriptor. The experimental results show that the proposed model outperforms significantly the state-of-the-art metrics.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper stacks three levels of contour and structure descriptors into a new FR-IQA metric aimed at non-uniform distortions in FTV synthesized views and reports stronger correlation than prior metrics.

read the letter

The main thing here is a concrete attempt to build an image quality metric that respects the non-uniform, structure-heavy distortions typical of free-viewpoint synthesis rather than treating artifacts as spatially uniform. It does this by pulling low-level contour features, mid-level category descriptors, and a higher task-oriented term for non-natural structures, all framed as a bio-inspired hierarchy. That framing is reasonable given how synthesized views break standard metrics, and the choice to focus on FTV is a clear application target where existing tools are known to fall short. The abstract states the model beats current methods on their tests, which at least shows they ran a comparison rather than stopping at theory. What is actually new is the specific three-layer construction tuned to this scenario; the individual ideas (contour descriptors, hierarchical features) are not novel on their own. Soft spots are the lack of any visible implementation details, dataset sizes, or statistical tests in the provided text, so the outperformance claim remains an assertion until the methods and numbers are examined. The direct mapping from HVS levels to metric components is plausible but could easily become brittle if the descriptors are not stable across different synthesis algorithms. This is the kind of work that belongs in a specialized IQA or immersive media venue. A reader already working on quality metrics for 3D or view synthesis would get value from the construction and the reported gains, even if they later modify the descriptors. It is coherent enough on its own terms to deserve a serious referee rather than a desk reject; the central empirical claim can be checked once the full experiments are in front of someone. I would send it out for review but would flag the need for clearer ablation and cross-dataset checks in the first round.

Referee Report

0 major / 2 minor

Summary. The manuscript proposes a bio-inspired full-reference image quality metric (FR-IQA) for synthesized views in Free-viewpoint TV (FTV). It constructs the metric from three hierarchical structural descriptors drawn from the human visual system: a low-level contour descriptor, a mid-level contour category descriptor, and a task-oriented non-natural structure descriptor. The central claim is that this model significantly outperforms existing state-of-the-art metrics on structure-related, non-uniform distortions typical of FTV content.

Significance. If the reported outperformance is reproducible and statistically robust, the work would be a useful incremental contribution to perceptual IQA for immersive media, where conventional metrics often fail on non-uniform structural artifacts. The hierarchical, multi-level construction is a reasonable extension of prior bio-inspired IQA approaches and supplies a concrete, falsifiable prediction about which descriptor levels matter most for FTV distortions.

minor comments (2)

[Abstract] Abstract: the claim of 'significant outperformance' is stated without reference to the specific datasets, number of test images, or statistical tests used; while these details presumably appear in the experimental section, a brief indication in the abstract would improve readability.
The manuscript should clarify whether the three descriptors are combined with learned weights or fixed combination rules, as this affects reproducibility.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive assessment of our manuscript and the recommendation for minor revision. The evaluation correctly identifies the hierarchical bio-inspired construction and its relevance to non-uniform structural distortions in FTV synthesized views.

Circularity Check

0 steps flagged

No significant circularity; derivation is empirical and self-contained

full rationale

The paper proposes a hierarchical bio-inspired FR-IQA metric using low-level contour descriptor, mid-level contour category descriptor, and task-oriented non-natural structure descriptor, inspired by HVS representations. No equations, fitting procedures, or derivation chain are visible in the abstract that reduce any prediction or result to inputs by construction. The central claim is an empirical assertion of outperformance on FTV distortions, which is a standard experimental result not forced by self-definition, self-citation, or renaming. No load-bearing self-citations or ansatzes are referenced. This matches the default expectation of no circularity.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Review based on abstract only; no equations or detailed methods available to enumerate free parameters or axioms.

axioms (1)

domain assumption Hierarchical representation mechanism in the human visual system can be modeled using contour descriptors at low, mid, and task-oriented levels for quality assessment.
Stated as inspiration in the abstract.

pith-pipeline@v0.9.0 · 5695 in / 1164 out tokens · 18097 ms · 2026-05-25T01:09:16.245098+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

37 extracted references · 37 canonical work pages · 1 internal anchor

[1]

INTRODUCTION With the rise of 3D displays, head-mounted displays and other advanced display techniques, immersive media applications such as FTV , 3DTV , Virtual Reality (VR) and LightField (LF) have become a hot topic for media ecosystems. The development of immersive media largely relies on the usage of computer vision/image processing techniques to gen...

work page internal anchor Pith review Pith/arXiv arXiv 1907
[2]

RELA TED WORK In order to better evaluate the quality of synthesized views in the case of FTV , some metrics are proposed. The very ﬁrst metric VSQA [6] was proposed using three visibility maps which characterize complexity in terms of textures, diversity of gradient orientations and presence of high contrast. The 3DswIM was introduced by Battisti et al. ...

work page
[3]

THE PROPOSED METRIC In this section, we propose a full-reference image quality met- ric based on hierarchical structure representation. The pro- posed framework consists of (1) a pre-processing step for structural information extraction, (2) a hierarchical feature extraction for low, mid and high-level perceptual information extraction, and (3) a pooling ...

work page
[4]

Images from this database were obtained from three multi-view video plus depth sequences: ‘Book Arrival’, ‘Lovebird1’ and ‘Newspa- per’

EXPERIMENTAL RESULTS The performance of the proposed model is evaluated on the IRCCyN/IVC DIBR images database [30]. Images from this database were obtained from three multi-view video plus depth sequences: ‘Book Arrival’, ‘Lovebird1’ and ‘Newspa- per’. Seven DIBR algorithms processed the three sequences to generate four new virtual views for each of them...

work page
[5]

Inspired by the hierarchical framework of visual perception, in this paper, a 3-level structure representation based model is proposed

CONCLUSION Local, non-uniform structure-related distortions within im- mersive multimedia are challenging for traditional quality metrics. Inspired by the hierarchical framework of visual perception, in this paper, a 3-level structure representation based model is proposed. This model quantiﬁes the structure- related distortion by checking 1) how local co...

work page
[6]

The role of structure and textural information in image utility and quality assessment tasks,

Suiyi Ling, Patrick Le Callet, and Zitong Yu, “The role of structure and textural information in image utility and quality assessment tasks,” Electronic Imaging, vol. 2018, no. 14, pp. 1–13, 2018

work page 2018
[7]

Contributions of low-and high-level properties to neural processing of visual scenes in the human brain,

Iris IA Groen, Edward H Silson, and Chris I Baker, “Contributions of low-and high-level properties to neural processing of visual scenes in the human brain,” Phil. Trans. R. Soc. B , vol. 372, no. 1714, pp. 20160102, 2017

work page 2017
[8]

Low-level properties of natural images predict topographic patterns of neural response in the ventral visual pathway,

Timothy J Andrews, David M Watson, Grace E Rice, and Tom Hartley, “Low-level properties of natural images predict topographic patterns of neural response in the ventral visual pathway,” Journal of Vision, vol. 15, no. 7, pp. 3–3, 2015

work page 2015
[9]

Understanding mid-level representations in visual processing,

Jonathan W Peirce, “Understanding mid-level representations in visual processing,” Journal of Vision, vol. 15, no. 7, pp. 5–5, 2015

work page 2015
[10]

When crowding of crowding leads to uncrowding,

Mauro Manassi, Bilge Sayim, and Michael H Herzog, “When crowding of crowding leads to uncrowding,” Journal of Vision, vol. 13, no. 13, pp. 10–10, 2013

work page 2013
[11]

Objective view synthesis quality assessment,

Pierre-Henri Conze, Philippe Robert, and Luce Morin, “Objective view synthesis quality assessment,” in IS&T/SPIE Electronic Imaging. Inter- national Society for Optics and Photonics, 2012, pp. 82881M–82881M

work page 2012
[12]

Objective image quality assessment of 3d synthesized views,

Federica Battisti, Emilie Bosc, Marco Carli, Patrick Le Callet, and Si- mone Perugia, “Objective image quality assessment of 3d synthesized views,” Signal Processing: Image Communication , vol. 30, pp. 78–88, 2015

work page 2015
[13]

Dibr synthesized image quality assessment based on morphological wavelets,

Dragana Sandi ´c-Stankovi´c, Dragan Kukolj, and Patrick Le Callet, “Dibr synthesized image quality assessment based on morphological wavelets,” in Quality of Multimedia Experience (QoMEX), 2015 Sev- enth International Workshop on. IEEE, 2015, pp. 1–6

work page 2015
[14]

Dibr synthesized image quality assessment based on morphologi- cal pyramids,

Dragana Sandic-Stankovic, Dragan Kukolj, and Patrick Le Callet, “Dibr synthesized image quality assessment based on morphologi- cal pyramids,” in 2015 3DTV-Conference: The True Vision-Capture, Transmission and Display of 3D Video (3DTV-CON) . IEEE, 2015, pp. 1–4

work page 2015
[15]

Dibr-synthesized image quality assessment based on morphological multi-scale approach,

Dragana Sandi ´c-Stankovi´c, Dragan Kukolj, and Patrick Le Callet, “Dibr-synthesized image quality assessment based on morphological multi-scale approach,” EURASIP Journal on Image and Video Pro- cessing, vol. 2017, no. 1, pp. 4, 2016

work page 2017
[16]

Quality assessment for synthesized view based on variable-length context tree,

Patrick Le Callet Ling, Suiyi and Cheung Gene, “Quality assessment for synthesized view based on variable-length context tree,” in Multi- media Signal Processing (MMSP), 2017 IEEE 19th International Work- shop on. IEEE, 2017

work page 2017
[17]

Image quality assessment for dibr synthesized views using elastic metric,

Suiyi Ling and Patrick Le Callet, “Image quality assessment for dibr synthesized views using elastic metric,” in Proceedings of the 2017 ACM on Multimedia Conference. ACM, 2017, pp. 1157–1163

work page 2017
[18]

Quality as- sessment of dibr-synthesized images by measuring local geometric dis- tortions and global sharpness,

Leida Li, Yu Zhou, Ke Gu, Weisi Lin, and Shiqi Wang, “Quality as- sessment of dibr-synthesized images by measuring local geometric dis- tortions and global sharpness,” IEEE Transactions on Multimedia, vol. 20, no. 4, pp. 914–926, 2018

work page 2018
[19]

Niqsv: A no reference image quality assessment metric for 3d synthesized views,

Shishun Tian, Lu Zhang, Luce Morin, and Olivier Deforges, “Niqsv: A no reference image quality assessment metric for 3d synthesized views,” in Acoustics, Speech and Signal Processing (ICASSP), 2017 IEEE International Conference on. IEEE, 2017, pp. 1248–1252

work page 2017
[20]

Niqsv+: A no-reference synthesized view quality assessment metric,

Shishun Tian, Lu Zhang, Luce Morin, and Olivier D ´eforges, “Niqsv+: A no-reference synthesized view quality assessment metric,” IEEE Transactions on Image Processing, vol. 27, no. 4, pp. 1652–1664, 2018

work page 2018
[21]

Model-based referenceless quality metric of 3d synthe- sized images using local image description,

Ke Gu, Vinit Jakhetiya, Jun-Fei Qiao, Xiaoli Li, Weisi Lin, and Daniel Thalmann, “Model-based referenceless quality metric of 3d synthe- sized images using local image description,” IEEE Transactions on Image Processing, 2017

work page 2017
[22]

Effect of content features on short-term video qual- ity in the visual periphery,

Yashas Rai, Ahmed Aldahdooh, Suiyi Ling, Marcus Barkowsky, and Patrick Le Callet, “Effect of content features on short-term video qual- ity in the visual periphery,” in Multimedia Signal Processing (MMSP), 2016 IEEE 18th International Workshop on . IEEE, 2016, pp. 1–6

work page 2016
[23]

A fast approximation of the bilat- eral ﬁlter using a signal processing approach,

Sylvain Paris and Fr ´edo Durand, “A fast approximation of the bilat- eral ﬁlter using a signal processing approach,”International journal of computer vision, vol. 81, no. 1, pp. 24–52, 2009

work page 2009
[24]

Multiscale cate- gorical object recognition using contour fragments,

Jamie Shotton, Andrew Blake, and Roberto Cipolla, “Multiscale cate- gorical object recognition using contour fragments,”IEEE transactions on pattern analysis and machine intelligence , vol. 30, no. 7, pp. 1270– 1281, 2008

work page 2008
[25]

Image utility assessment and a relationship with image quality assessment,

David M Rouse, Romuald P ´epion, Sheila S Hemami, and Patrick Le Callet, “Image utility assessment and a relationship with image quality assessment,” in Human Vision and Electronic Imaging XIV . International Society for Optics and Photonics, 2009, vol. 7240, p. 724010

work page 2009
[26]

Encoding of conﬁgural regularity in the human visual system,

Jonas Kubilius, Johan Wagemans, and Hans P Op de Beeck, “Encoding of conﬁgural regularity in the human visual system,”Journal of Vision, vol. 14, no. 9, pp. 11–11, 2014

work page 2014
[27]

Image quality assessment for free viewpoint video based on mid-level contours feature,

Suiyi Ling and Patrick Le Callet, “Image quality assessment for free viewpoint video based on mid-level contours feature,” in Multime- dia and Expo (ICME), 2017 IEEE International Conference on . IEEE, 2017, pp. 79–84

work page 2017
[28]

Quality as- sessment for view synthesis using low-level and mid-level structural representation,

Yu Zhou, Leida Li, Suiyi Ling, and Patrick Le Callet, “Quality as- sessment for view synthesis using low-level and mid-level structural representation,” Signal Processing: Image Communication , 2019

work page 2019
[29]

Image registration by template matching using normalized cross- correlation,

Jignesh N Sarvaiya, Suprava Patnaik, and Salman Bombaywala, “Image registration by template matching using normalized cross- correlation,” in Advances in Computing, Control, & Telecommunica- tion Technologies, 2009. ACT’09. International Conference on . IEEE, 2009, pp. 819–822

work page 2009
[30]

Sparse coding in the primate cortex,

Peter Foldiak, “Sparse coding in the primate cortex,” The handbook of brain theory and neural networks , 2003

work page 2003
[31]

From sparse coding signiﬁcance to perceptual quality: A new approach for image quality assessment,

Ayyoub Ahar, Adriaan Barri, and Peter Schelkens, “From sparse coding signiﬁcance to perceptual quality: A new approach for image quality assessment,” IEEE Transactions on Image Processing , vol. 27, no. 2, pp. 879–893, 2018

work page 2018
[32]

No-reference quality assessment for stitched panoramic images using convolutional sparse coding and compound feature selection,

Suiyi Ling, Gene Cheung, and Patrick Le Callet, “No-reference quality assessment for stitched panoramic images using convolutional sparse coding and compound feature selection,” in 2018 IEEE International Conference on Multimedia and Expo (ICME) . IEEE, 2018, pp. 1–6

work page 2018
[33]

How to learn the effect of non- uniform distortion on perceived visual quality? case study using convo- lutional sparse coding for quality assessment of synthesized views,

Suiyi Ling and Patrick Le Callet, “How to learn the effect of non- uniform distortion on perceived visual quality? case study using convo- lutional sparse coding for quality assessment of synthesized views,” in 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 2018, pp. 286–290

work page 2018
[34]

Fast convolutional sparse coding using matrix inversion lemma,

Michal ˇSorel and Filip ˇSroubek, “Fast convolutional sparse coding using matrix inversion lemma,” Digital Signal Processing, vol. 55, pp. 44–51, 2016

work page 2016
[35]

Towards a new quality metric for 3-d synthesized view assessment,

Emilie Bosc, Romuald Pepion, Patrick Le Callet, Martin Koppel, Patrick Ndjiki-Nya, Muriel Pressigout, and Luce Morin, “Towards a new quality metric for 3-d synthesized view assessment,”IEEE Journal of Selected Topics in Signal Processing , vol. 5, no. 7, pp. 1332–1343, 2011

work page 2011
[36]

Prediction of the inﬂuence of navigation scan-path on perceived quality of free- viewpoint videos,

Suiyi Ling, Jes ´us Guti´errez, Ke Gu, and Patrick Le Callet, “Prediction of the inﬂuence of navigation scan-path on perceived quality of free- viewpoint videos,” IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2019

work page 2019
[37]

Subjective and objective video quality assessment of 3D synthesized views with texture/depth compression distortion,

Xiangkai Liu, Yun Zhang, Sudeng Hu, Sam Kwong, C-C Jay Kuo, and Qiang Peng, “Subjective and objective video quality assessment of 3D synthesized views with texture/depth compression distortion,” IEEE Transactions on Image Processing , vol. 24, no. 12, pp. 4847–4861, Dec. 2015

work page 2015

[1] [1]

INTRODUCTION With the rise of 3D displays, head-mounted displays and other advanced display techniques, immersive media applications such as FTV , 3DTV , Virtual Reality (VR) and LightField (LF) have become a hot topic for media ecosystems. The development of immersive media largely relies on the usage of computer vision/image processing techniques to gen...

work page internal anchor Pith review Pith/arXiv arXiv 1907

[2] [2]

RELA TED WORK In order to better evaluate the quality of synthesized views in the case of FTV , some metrics are proposed. The very ﬁrst metric VSQA [6] was proposed using three visibility maps which characterize complexity in terms of textures, diversity of gradient orientations and presence of high contrast. The 3DswIM was introduced by Battisti et al. ...

work page

[3] [3]

THE PROPOSED METRIC In this section, we propose a full-reference image quality met- ric based on hierarchical structure representation. The pro- posed framework consists of (1) a pre-processing step for structural information extraction, (2) a hierarchical feature extraction for low, mid and high-level perceptual information extraction, and (3) a pooling ...

work page

[4] [4]

Images from this database were obtained from three multi-view video plus depth sequences: ‘Book Arrival’, ‘Lovebird1’ and ‘Newspa- per’

EXPERIMENTAL RESULTS The performance of the proposed model is evaluated on the IRCCyN/IVC DIBR images database [30]. Images from this database were obtained from three multi-view video plus depth sequences: ‘Book Arrival’, ‘Lovebird1’ and ‘Newspa- per’. Seven DIBR algorithms processed the three sequences to generate four new virtual views for each of them...

work page

[5] [5]

Inspired by the hierarchical framework of visual perception, in this paper, a 3-level structure representation based model is proposed

CONCLUSION Local, non-uniform structure-related distortions within im- mersive multimedia are challenging for traditional quality metrics. Inspired by the hierarchical framework of visual perception, in this paper, a 3-level structure representation based model is proposed. This model quantiﬁes the structure- related distortion by checking 1) how local co...

work page

[6] [6]

The role of structure and textural information in image utility and quality assessment tasks,

Suiyi Ling, Patrick Le Callet, and Zitong Yu, “The role of structure and textural information in image utility and quality assessment tasks,” Electronic Imaging, vol. 2018, no. 14, pp. 1–13, 2018

work page 2018

[7] [7]

Contributions of low-and high-level properties to neural processing of visual scenes in the human brain,

Iris IA Groen, Edward H Silson, and Chris I Baker, “Contributions of low-and high-level properties to neural processing of visual scenes in the human brain,” Phil. Trans. R. Soc. B , vol. 372, no. 1714, pp. 20160102, 2017

work page 2017

[8] [8]

Low-level properties of natural images predict topographic patterns of neural response in the ventral visual pathway,

Timothy J Andrews, David M Watson, Grace E Rice, and Tom Hartley, “Low-level properties of natural images predict topographic patterns of neural response in the ventral visual pathway,” Journal of Vision, vol. 15, no. 7, pp. 3–3, 2015

work page 2015

[9] [9]

Understanding mid-level representations in visual processing,

Jonathan W Peirce, “Understanding mid-level representations in visual processing,” Journal of Vision, vol. 15, no. 7, pp. 5–5, 2015

work page 2015

[10] [10]

When crowding of crowding leads to uncrowding,

Mauro Manassi, Bilge Sayim, and Michael H Herzog, “When crowding of crowding leads to uncrowding,” Journal of Vision, vol. 13, no. 13, pp. 10–10, 2013

work page 2013

[11] [11]

Objective view synthesis quality assessment,

Pierre-Henri Conze, Philippe Robert, and Luce Morin, “Objective view synthesis quality assessment,” in IS&T/SPIE Electronic Imaging. Inter- national Society for Optics and Photonics, 2012, pp. 82881M–82881M

work page 2012

[12] [12]

Objective image quality assessment of 3d synthesized views,

Federica Battisti, Emilie Bosc, Marco Carli, Patrick Le Callet, and Si- mone Perugia, “Objective image quality assessment of 3d synthesized views,” Signal Processing: Image Communication , vol. 30, pp. 78–88, 2015

work page 2015

[13] [13]

Dibr synthesized image quality assessment based on morphological wavelets,

Dragana Sandi ´c-Stankovi´c, Dragan Kukolj, and Patrick Le Callet, “Dibr synthesized image quality assessment based on morphological wavelets,” in Quality of Multimedia Experience (QoMEX), 2015 Sev- enth International Workshop on. IEEE, 2015, pp. 1–6

work page 2015

[14] [14]

Dibr synthesized image quality assessment based on morphologi- cal pyramids,

Dragana Sandic-Stankovic, Dragan Kukolj, and Patrick Le Callet, “Dibr synthesized image quality assessment based on morphologi- cal pyramids,” in 2015 3DTV-Conference: The True Vision-Capture, Transmission and Display of 3D Video (3DTV-CON) . IEEE, 2015, pp. 1–4

work page 2015

[15] [15]

Dibr-synthesized image quality assessment based on morphological multi-scale approach,

Dragana Sandi ´c-Stankovi´c, Dragan Kukolj, and Patrick Le Callet, “Dibr-synthesized image quality assessment based on morphological multi-scale approach,” EURASIP Journal on Image and Video Pro- cessing, vol. 2017, no. 1, pp. 4, 2016

work page 2017

[16] [16]

Quality assessment for synthesized view based on variable-length context tree,

Patrick Le Callet Ling, Suiyi and Cheung Gene, “Quality assessment for synthesized view based on variable-length context tree,” in Multi- media Signal Processing (MMSP), 2017 IEEE 19th International Work- shop on. IEEE, 2017

work page 2017

[17] [17]

Image quality assessment for dibr synthesized views using elastic metric,

Suiyi Ling and Patrick Le Callet, “Image quality assessment for dibr synthesized views using elastic metric,” in Proceedings of the 2017 ACM on Multimedia Conference. ACM, 2017, pp. 1157–1163

work page 2017

[18] [18]

Quality as- sessment of dibr-synthesized images by measuring local geometric dis- tortions and global sharpness,

Leida Li, Yu Zhou, Ke Gu, Weisi Lin, and Shiqi Wang, “Quality as- sessment of dibr-synthesized images by measuring local geometric dis- tortions and global sharpness,” IEEE Transactions on Multimedia, vol. 20, no. 4, pp. 914–926, 2018

work page 2018

[19] [19]

Niqsv: A no reference image quality assessment metric for 3d synthesized views,

Shishun Tian, Lu Zhang, Luce Morin, and Olivier Deforges, “Niqsv: A no reference image quality assessment metric for 3d synthesized views,” in Acoustics, Speech and Signal Processing (ICASSP), 2017 IEEE International Conference on. IEEE, 2017, pp. 1248–1252

work page 2017

[20] [20]

Niqsv+: A no-reference synthesized view quality assessment metric,

Shishun Tian, Lu Zhang, Luce Morin, and Olivier D ´eforges, “Niqsv+: A no-reference synthesized view quality assessment metric,” IEEE Transactions on Image Processing, vol. 27, no. 4, pp. 1652–1664, 2018

work page 2018

[21] [21]

Model-based referenceless quality metric of 3d synthe- sized images using local image description,

Ke Gu, Vinit Jakhetiya, Jun-Fei Qiao, Xiaoli Li, Weisi Lin, and Daniel Thalmann, “Model-based referenceless quality metric of 3d synthe- sized images using local image description,” IEEE Transactions on Image Processing, 2017

work page 2017

[22] [22]

Effect of content features on short-term video qual- ity in the visual periphery,

Yashas Rai, Ahmed Aldahdooh, Suiyi Ling, Marcus Barkowsky, and Patrick Le Callet, “Effect of content features on short-term video qual- ity in the visual periphery,” in Multimedia Signal Processing (MMSP), 2016 IEEE 18th International Workshop on . IEEE, 2016, pp. 1–6

work page 2016

[23] [23]

A fast approximation of the bilat- eral ﬁlter using a signal processing approach,

Sylvain Paris and Fr ´edo Durand, “A fast approximation of the bilat- eral ﬁlter using a signal processing approach,”International journal of computer vision, vol. 81, no. 1, pp. 24–52, 2009

work page 2009

[24] [24]

Multiscale cate- gorical object recognition using contour fragments,

Jamie Shotton, Andrew Blake, and Roberto Cipolla, “Multiscale cate- gorical object recognition using contour fragments,”IEEE transactions on pattern analysis and machine intelligence , vol. 30, no. 7, pp. 1270– 1281, 2008

work page 2008

[25] [25]

Image utility assessment and a relationship with image quality assessment,

David M Rouse, Romuald P ´epion, Sheila S Hemami, and Patrick Le Callet, “Image utility assessment and a relationship with image quality assessment,” in Human Vision and Electronic Imaging XIV . International Society for Optics and Photonics, 2009, vol. 7240, p. 724010

work page 2009

[26] [26]

Encoding of conﬁgural regularity in the human visual system,

Jonas Kubilius, Johan Wagemans, and Hans P Op de Beeck, “Encoding of conﬁgural regularity in the human visual system,”Journal of Vision, vol. 14, no. 9, pp. 11–11, 2014

work page 2014

[27] [27]

Image quality assessment for free viewpoint video based on mid-level contours feature,

Suiyi Ling and Patrick Le Callet, “Image quality assessment for free viewpoint video based on mid-level contours feature,” in Multime- dia and Expo (ICME), 2017 IEEE International Conference on . IEEE, 2017, pp. 79–84

work page 2017

[28] [28]

Quality as- sessment for view synthesis using low-level and mid-level structural representation,

Yu Zhou, Leida Li, Suiyi Ling, and Patrick Le Callet, “Quality as- sessment for view synthesis using low-level and mid-level structural representation,” Signal Processing: Image Communication , 2019

work page 2019

[29] [29]

Image registration by template matching using normalized cross- correlation,

Jignesh N Sarvaiya, Suprava Patnaik, and Salman Bombaywala, “Image registration by template matching using normalized cross- correlation,” in Advances in Computing, Control, & Telecommunica- tion Technologies, 2009. ACT’09. International Conference on . IEEE, 2009, pp. 819–822

work page 2009

[30] [30]

Sparse coding in the primate cortex,

Peter Foldiak, “Sparse coding in the primate cortex,” The handbook of brain theory and neural networks , 2003

work page 2003

[31] [31]

From sparse coding signiﬁcance to perceptual quality: A new approach for image quality assessment,

Ayyoub Ahar, Adriaan Barri, and Peter Schelkens, “From sparse coding signiﬁcance to perceptual quality: A new approach for image quality assessment,” IEEE Transactions on Image Processing , vol. 27, no. 2, pp. 879–893, 2018

work page 2018

[32] [32]

No-reference quality assessment for stitched panoramic images using convolutional sparse coding and compound feature selection,

Suiyi Ling, Gene Cheung, and Patrick Le Callet, “No-reference quality assessment for stitched panoramic images using convolutional sparse coding and compound feature selection,” in 2018 IEEE International Conference on Multimedia and Expo (ICME) . IEEE, 2018, pp. 1–6

work page 2018

[33] [33]

How to learn the effect of non- uniform distortion on perceived visual quality? case study using convo- lutional sparse coding for quality assessment of synthesized views,

Suiyi Ling and Patrick Le Callet, “How to learn the effect of non- uniform distortion on perceived visual quality? case study using convo- lutional sparse coding for quality assessment of synthesized views,” in 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 2018, pp. 286–290

work page 2018

[34] [34]

Fast convolutional sparse coding using matrix inversion lemma,

Michal ˇSorel and Filip ˇSroubek, “Fast convolutional sparse coding using matrix inversion lemma,” Digital Signal Processing, vol. 55, pp. 44–51, 2016

work page 2016

[35] [35]

Towards a new quality metric for 3-d synthesized view assessment,

Emilie Bosc, Romuald Pepion, Patrick Le Callet, Martin Koppel, Patrick Ndjiki-Nya, Muriel Pressigout, and Luce Morin, “Towards a new quality metric for 3-d synthesized view assessment,”IEEE Journal of Selected Topics in Signal Processing , vol. 5, no. 7, pp. 1332–1343, 2011

work page 2011

[36] [36]

Prediction of the inﬂuence of navigation scan-path on perceived quality of free- viewpoint videos,

Suiyi Ling, Jes ´us Guti´errez, Ke Gu, and Patrick Le Callet, “Prediction of the inﬂuence of navigation scan-path on perceived quality of free- viewpoint videos,” IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2019

work page 2019

[37] [37]

Subjective and objective video quality assessment of 3D synthesized views with texture/depth compression distortion,

Xiangkai Liu, Yun Zhang, Sudeng Hu, Sam Kwong, C-C Jay Kuo, and Qiang Peng, “Subjective and objective video quality assessment of 3D synthesized views with texture/depth compression distortion,” IEEE Transactions on Image Processing , vol. 24, no. 12, pp. 4847–4861, Dec. 2015

work page 2015