Marco Cagnazzo | Associate Professor

@conference{	11577_3469276,

title = {Depth Patch Selection for Decoder-Side Depth Estimation in MPEG Immersive Video},

author = { Marta Milovanovic and Félix Henry and Marco Cagnazzo},

year  = {2022},

date = {2022-01-01},

booktitle = {Picture Coding Symposium},

pages = {343--347},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469277,

title = {Towards zero-latency video transmission through frame extrapolation},

author = { Melan Vijayaratnam and Marco Cagnazzo and Giuseppe Valenzise and Anthony Trioux and Michel Kieffer},

year  = {2022},

date = {2022-01-01},

booktitle = {IEEE International Conference on Image Processing},

pages = {2122--2126},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469278,

title = {Vers une transmission vidéo sans latence par l'extrapolation d'images},

author = { Melan Vijaratnam and Marco Cagnazzo and Giuseppe Valenzise and Anthony Trioux and Michel Kieffer},

year  = {2022},

date = {2022-01-01},

booktitle = {XXVIIIème Colloque Francophone de Traitement du Signal et des Images},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469283,

title = {A Multi-View Stereoscopic Video Database With Green Screen (MTF) For Video Transition Quality-of-Experience Assessment},

author = { Nour Hobloss and Lu Zhang and Marco Cagnazzo},

year  = {2021},

date = {2021-01-01},

booktitle = {2021 13th International Conference on Quality of Multimedia Experience (QoMEX)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469285,

title = {DR2S: Deep Regression with Region Selection for Camera Quality Evaluation},

author = { Marcelin Tworski and Stéphane Lathuilière and Salim Belkarfa and Attilio Fiandrotti and Marco Cagnazzo},

year  = {2021},

date = {2021-01-01},

booktitle = {2020 25th International Conference on Pattern Recognition (ICPR)},

pages = {6173--6180},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469282,

title = {A Perceptual Study of the Decoding Process of the SoftCast Wireless Video Broadcast Scheme},

author = { Anthony Trioux and Giuseppe Valenzise and Marco Cagnazzo and Michel Kieffer and François-Xavier Coudoux and Patrick Corlay and Mohamed Gharbi},

year  = {2021},

date = {2021-01-01},

booktitle = {2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469284,

title = {Patch decoder-side depth estimation in MPEG immersive video},

author = { Marta Milovanovic and Joël Jung and Marco Cagnazzo},

year  = {2021},

date = {2021-01-01},

booktitle = {2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469351,

title = {Subjective and Objective Quality Assessment of the SoftCast Video Transmission Scheme},

author = { A. Trioux and G. Valenzise and M. Cagnazzo and M. Kieffer and F. -X. Coudoux and P. Corlay and M. Gharbi},

doi = {10.1109/VCIP49819.2020.9301778},

isbn = {978-1-7281-8068-7},

year  = {2020},

date = {2020-01-01},

booktitle = {2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020},

pages = {96--99},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {SoftCast-based linear video coding and transmission (LVCT) schemes have been proposed as a promising alternative to traditional video coding and transmission schemes in wireless environments. Currently, the performance of LVCT schemes is evaluated by means of traditional objective scores such as PSNR or SSIM. Nevertheless, since the compression is performed in a very different way from traditional coding schemes such as HEVC, visual artifacts are also quite different and deserve to be subjectively assessed. In this paper, we propose a subjective quality assessment of SoftCast, pioneer and standard of the LVCT schemes. This study aims to better understand the trade-offs between the LVCT parameters that can be tuned to improve the quality. These parameters, including different GoP-sizes, Compression Ratios (CR) and Channel Signal-to-Noise Ratio (CSNR), are used to generate a dataset of 85 videos. A Double Stimulus Impairment Scale (DSIS) test is performed on the received videos to assess the perceived quality. Results show that the key characteristic of SoftCast, the linear relation between CSNR and PSNR, is also observed with the Mean-Opinion Scores (MOS), except at high CSNR where the quality saturates. In addition, Bjontegaard model is used to quantify the trade-offs between CR, GoP-size and CSNR, depending on the intended application. Finally, the performance of objective metrics compared to the obtained MOS is evaluated. Results show that Multi-Scale SSIM (MS-SSIM), SSIM and Video Multimethod Assessment Fusion (VMAF) metrics offer the best correlation with the MOS values.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469353,

title = {Towards practical hologram streaming using progressive coding},

author = { A. El Rhammad and P. Gioia and A. Gilles and M. Cagnazzo},

doi = {10.1117/12.2529202},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of SPIE - The International Society for Optical Engineering},

volume = {11137},

publisher = {SPIE},

abstract = {Digital holography is an emerging technology for 3D visualization which is expected to dethrone conventional stereoscopic devices in the future. Aside from their specific signal properties, high quality holograms with broad viewing angles contain massive amount of data. For a reasonable transmission time, efficient scalable compression schemes are needed to bridge the gap between the overwhelming volume of data and the limited bandwidth of the communication channels. The viewpoint scalability is a powerful property since it allows to encode and transmit only the information corresponding to the observer's view. However, this approach imposes an online encoding at the server which may increase the latency of the transmission chain. To overcome this hurdle, we propose a scalable compression framework based on Gabor-wavelets decomposition, where the whole hologram is encoded offline. First, the observer plane is divided into spatial blocks. Then, the Gabor atoms are assigned to these blocks by exploiting the duality between Gabor wavelets and light rays. The atoms of each block are then classified into different layers according to their importance for the reconstruction and encoded in packets. At the decoder side, the atoms' packets are progressively decoded based on the viewer's position. Then, the corresponding sub-hologram is generated using a GPU implementation. Results show that our approach enables a practical progressive streaming of digital holograms with a low latency.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469357,

title = {Scalable Coding Framework for a View-Dependent Streaming of Digital Holograms},

author = { A. E. Rhammad and P. Gioia and A. Gilles and M. Cagnazzo},

doi = {10.1109/ICIP.2019.8802950},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings - International Conference on Image Processing, ICIP},

volume = {2019-},

pages = {146--150},

publisher = {IEEE Computer Society},

abstract = {Unlike conventional images and videos, digital holograms contain large amounts of data with very low redundancy. Consequently, current communication networks may be not able to meet the bandwidth requirements for hologram transmission in reasonable time. To enable practical streaming of holographic contents, we propose a progressive coding method that combines quality scalability with viewpoint scalability. From a Gabor wavelets decomposition of the hologram, the server starts by selecting the coefficients corresponding to the user's viewpoint. Then, the selected coefficients are encoded progressively according to their importance for the reconstructed view. Experimental results reveal that our approach outperforms conventional scalable codecs and enables the streaming of holographic data with a better quality of experience.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469356,

title = {A Hybrid Approach to Wide Baseline View Synthesis with Convolutional Neural Networks},

author = { N. Hobloss and A. Purica and A. Fiandrotti and M. Cagnazzo and R. Cozot and W. Hamidouche},

doi = {10.1109/IC3D48390.2019.8976000},

isbn = {978-1-7281-5189-2},

year  = {2019},

date = {2019-01-01},

booktitle = {2019 International Conference on 3D Immersion, IC3D 2019 - Proceedings},

volume = {2019-},

pages = {1--7},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {Convolutional Neural Networks (CNN) have been recently employed for implementing complete end-to-end view synthesis architectures, from reference view warping to target view blending while dealing with occlusions as well. However, the convolutional sizes filters must increase with the distance between reference views, making all-convolutional approaches prohibitively complex for wide baseline setups. In this work we propose a hybrid approach to view synthesis where we first warp the reference views resolving the occlusions, and then we train a simpler convolutional architecture for blending the preprocessed views. By warping the reference views, we reduce the equivalent distance between reference views, allowing the use of smaller convolutional filters and thus lower network complexity. We experimentally show that our method performs favorably against both traditional and convolutional synthesis methods while retaining lower complexity with respect to the latter.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469355,

title = {Enhancing HEVC Spatial Prediction by Context-based Learning},

author = { L. Wang and A. Fiandrotti and A. Purica and G. Valenzise and M. Cagnazzo},

doi = {10.1109/ICASSP.2019.8683624},

year  = {2019},

date = {2019-01-01},

booktitle = {ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings},

volume = {2019-},

pages = {4035--4039},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {Deep generative models have been recently employed to compress images, image residuals or to predict image regions. Based on the observation that state-of-the-art spatial prediction is highly optimized from a rate-distortion point of view, in this work we study how learning-based approaches might be used to further enhance this prediction. To this end, we propose an encoder-decoder convolutional network able to reduce the energy of the residuals of HEVC intra prediction, by leveraging the available context of previously decoded neigh-boring blocks. The proposed context-based prediction enhancement (CBPE) scheme enables to reduce the mean square error of HEVC prediction by 25% on average, without any additional signalling cost in the bitstream.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469354,

title = {Exploiting View synthesis for super-multiview video compression},

author = { P. Nikitin and J. Jung and M. Cagnazzo and A. Fiandrotti},

doi = {10.1145/3349801.3349820},

isbn = {9781450371896},

year  = {2019},

date = {2019-01-01},

booktitle = {ACM International Conference Proceeding Series},

pages = {1--6},

publisher = {Association for Computing Machinery},

abstract = {Super-multiview video consists in a 2D arrangement of cameras acquiring the same scene and it is a well-suited format for immersive and free navigation video services. However, the large number of acquired viewpoints calls for extremely effective compression tools. View synthesis allows to reconstruct a viewpoint using nearby cameras texture and depth information. In this work we explore the potential of recent advances in view synthesis algorithms to enhance the compression performances of super-multiview video. Towards this end we consider five methods that replace one viewpoint with a synthesized view, possibly enhanced with some side information. Our experiments suggest that, if the geometry information (i.e. depth map) is reliable, these methods have the potential to improve rate-distortion performance with respect to traditional approaches, at least for some specific content and configuration. Moreover, our results shed some light about how to further improve compression performance by integrating new view-synthesis prediction tools within a 3D video encoder.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469350,

title = {Cockpit Video Coding with Temporal Prediction},

author = { I. Mitrica and A. Fiandrotti and M. Cagnazzo and E. Mercier and C. Ruellan},

doi = {10.1109/EUVIP47703.2019.8946234},

year  = {2019},

date = {2019-01-01},

booktitle = {EUVIP},

volume = {2019-October},

pages = {28--33},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469352,

title = {Compression Improvement via Reference Organization for 2D-multiview Content},

author = { P. Nikitin and M. Cagnazzo and J. Jung},

doi = {10.1109/ICASSP.2019.8682999},

year  = {2019},

date = {2019-01-01},

booktitle = {ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings},

volume = {2019-},

pages = {1612--1616},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {One of the most challenging goals of future immersive services is to enable the observation of a scene from any viewpoint, thus making free-navigation possible under certain constraints. In order to provide such kind of services with smooth navigation, a huge amount of views should be available on the client's device. In particular, it is important for the case of 2D-multiview content, where cameras are positioned on a 2D grid in order to provide both horizontal and vertical parallax. This kind of content requires a large coding rate; therefore improving the compression performance of video encoders is especially relevant in this case. This paper studies how the encoder configuration affects the compression, by taking into account the spatial position of each camera. Four parameters are addressed in this work: coding order of the views, the number of reference lists, the number of reference pictures, and the ordering of pictures in the reference lists. An average of 12.0% bitrate saving is achieved for medium bitrate and 11.1% for low bitrate compared to the state of the art techniques.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3472323,

title = {Precoding Matrix Design in Linear Video Coding},

author = { S. Zheng and M. Cagnazzo and M. Kieffer},

doi = {10.1109/ICASSP.2018.8461287},

isbn = {978-1-5386-4658-8},

year  = {2018},

date = {2018-01-01},

booktitle = {ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings},

volume = {2018-},

pages = {1198--1202},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {Linear video coding (LVC) is a promising alternative to classical video coding when video has to be transmitted to wireless receivers experiencing different and time-varying channel conditions. This paper addresses the LVC channel precoding and decoding matrix design when the transmission channel consists of several sub-channels, each with its own power constraint. Such constraints may be found, e.g., in multi-antenna, DSL, or powerline transmission systems. In a previous paper, it has been shown that this matrix design problem may be addressed by an adaptation to LVC of a multi-level water-filling solution proposed for MIMO channels. Here, two suboptimal low-complexity multi-level water-filling techniques are proposed, with different trade-offs between complexity and efficiency. Extensive simulations show that the suboptimal solutions perform very close to the optimal one, with a sensibly reduced complexity.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469360,

title = {View-dependent compression of digital hologram based on matching pursuit},

author = { A. El Rhammad and P. Gioia and A. Gilles and M. Cagnazzo and B. Pesquet-Popescu},

doi = {10.1117/12.2315233},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of SPIE - The International Society for Optical Engineering},

volume = {10679},

publisher = {SPIE},

abstract = {In this paper we investigate the suitability of Gabor Wavelets for an adaptive partial reconstruction of holograms based on the viewer position. Matching Pursuit is used for a sparse light rays decomposition of holographic patterns. At the decoding stage, sub-holograms are generated by selecting the diffracted rays corresponding to a specific area of visualization. The use of sub-holograms has been suggested in the literature as an alternative to full compression, by degrading a hologram with respect to the directional degrees of freedom. We present our approach in a complete framework for color digital holograms compression and explain, in details, how it can be efficiently exploited in the context of holographic Head-Mounted Displays. Among other aspects, encoding, adaptive reconstruction and selective degradation are studied.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469358,

title = {Quality assessment of deep-learning-based image compression},

author = { G. Valenzise and A. Purica and V. Hulusic and M. Cagnazzo},

doi = {10.1109/MMSP.2018.8547064},

isbn = {978-1-5386-6070-6},

year  = {2018},

date = {2018-01-01},

booktitle = {2018 IEEE 20th International Workshop on Multimedia Signal Processing, MMSP 2018},

pages = {1--6},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {Image compression standards rely on predictive coding, transform coding, quantization and entropy coding, in order to achieve high compression performance. Very recently, deep generative models have been used to optimize or replace some of these operations, with very promising results. However, so far no systematic and independent study of the coding performance of these algorithms has been carried out. In this paper, for the first time, we conduct a subjective evaluation of two recent deep-learning-based image compression algorithms, comparing them to JPEG 2000 and to the recent BPG image codec based on HEVC Intra. We found that compression approaches based on deep auto-encoders can achieve coding performance higher than JPEG 2000, and sometimes as good as BPG. We also show experimentally that the PSNR metric is to be avoided when evaluating the visual quality of deep-learning-based methods, as their artifacts have different characteristics from those of DCT or wavelet-based codecs. In particular, images compressed at low bitrate appear more natural than JPEG 2000 coded pictures, according to a no-reference naturalness measure. Our study indicates that deep generative models are likely to bring huge innovation into the video coding arena in the coming years.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3214371,

title = {Depth map coding with elastic contours and 3D surface prediction},

author = { Marco Calemme and Pietro Zanuttigh and Simone Milani and Marco Cagnazzo and Beatrice Pesquet Popescu},

doi = {10.1109/ICIP.2016.7532529},

isbn = {978-1-4673-9961-6},

year  = {2016},

date = {2016-01-01},

booktitle = {Proceedings of IEEE International Conference on Image Processing (ICIP)},

pages = {1106--1110},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469675,

title = {Compressed digital holography: From micro towards macro},

author = { C. Schretter and S. Bettens and D. Blinder and B. Pesquet-Popescu and M. Cagnazzo and F. Dufaux and P. Schelkens},

doi = {10.1117/12.2238761},

year  = {2016},

date = {2016-01-01},

booktitle = {Proceedings of SPIE - The International Society for Optical Engineering},

volume = {9971},

publisher = {SPIE},

abstract = {The age of computational imaging is merging the physical hardware-driven approach of photonics with advanced signal processing methods from software-driven computer engineering and applied mathematics. The compressed sensing theory in particular established a practical framework for reconstructing the scene content using few linear combinations of complex measurements and a sparse prior for regularizing the solution. Compressed sensing found direct applications in digital holography for microscopy. Indeed, the wave propagation phenomenon in free space mixes in a natural way the spatial distribution of point sources from the 3-dimensional scene. As the 3-dimensional scene is mapped to a 2-dimensional hologram, the hologram samples form a compressed representation of the scene as well. This overview paper discusses contributions in the field of compressed digital holography at the micro scale. Then, an outreach on future extensions towards the real-size macro scale is discussed. Thanks to advances in sensor technologies, increasing computing power and the recent improvements in sparse digital signal processing, holographic modalities are on the verge of practical high-quality visualization at a macroscopic scale where much higher resolution holograms must be acquired and processed on the computer.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469364,

title = {Improved integral images compression based on multi-view extraction},

author = { A. Dricot and J. Jung and M. Cagnazzo and B. Pesquet and F. Dufaux},

doi = {10.1117/12.2238707},

year  = {2016},

date = {2016-01-01},

booktitle = {Proceedings of SPIE - The International Society for Optical Engineering},

volume = {9971},

publisher = {SPIE},

abstract = {Integral imaging is a technology based on plenoptic photography that captures and samples the light-field of a scene through a micro-lens array. It provides views of the scene from several angles and therefore is foreseen as a key technology for future immersive video applications. However, integral images have a large resolution and a structure based on micro-images which is challenging to encode. A compression scheme for integral images based on view extraction has previously been proposed, with average BD-rate gains of 15.7% (up to 31.3%) reported over HEVC when using one single extracted view. As the efficiency of the scheme depends on a tradeoff between the bitrate required to encode the view and the quality of the image reconstructed from the view, it is proposed to increase the number of extracted views. Several configurations are tested with different positions and different number of extracted views. Compression efficiency is increased with average BD-rate gains of 22.2% (up to 31.1%) reported over the HEVC anchor, with a realistic runtime increase.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469514,

title = {Softcast with per-carrier power-constrained channels},

author = { S. Zheng and M. Antonini and M. Cagnazzo and L. Guerrieri and M. Kieffer and I. Nemoianu and R. Samy and B. Zhang},

doi = {10.1109/ICIP.2016.7532733},

year  = {2016},

date = {2016-01-01},

booktitle = {Proceedings - International Conference on Image Processing, ICIP},

volume = {2016-},

pages = {2122--2126},

publisher = {IEEE Computer Society},

abstract = {This paper considers the Softcast joint source-channel video coding scheme for data transmission over parallel channels with different power constraints and noise characteristics, typical in DSL or PLT channels. To minimize the mean square error at receiver, an optimal precoding matrix design problem has to be solved, which requires the solution of an inverse eigenvalue problem. Such solution is taken from the MIMO channel precoder design literature. Alternative suboptimal precoding matrices are also proposed and analyzed, showing the efficiency of the optimal precoding matrix within Softcast, which provides gains increasing with the encoded video quality.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469365,

title = {View synthesis based on temporal prediction via warped motion vector fields},

author = { A. I. Purica and M. Cagnazzo and B. Pesquet-Popescu and F. Dufaux and B. Ionesc},

doi = {10.1109/ICASSP.2016.7471856},

year  = {2016},

date = {2016-01-01},

booktitle = {ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings},

volume = {2016-},

pages = {1150--1154},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {The demand for 3D content has increased over the last years as 3D displays are now widespread. View synthesis methods, such as depth-image-based-rendering, provide an efficient tool in 3D content creation or transmission, and are integrated in coding solutions for multiview video content such as 3D-HEVC. In this paper, we propose a view synthesis method that takes advantage of temporal and inter-view correlations in multiview video sequences. We use warped motion vector fields computed in reference views to obtain temporal predictions of a frame in a synthesized view and blend them with depth-image-based-rendering synthesis. Our method is shown to bring gains of 0.42dB in average when tested on several multiview sequences.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469363,

title = {Contour-Based Depth Coding: A Subjective Quality Assessment Study},

author = { M. Calemme and M. Cagnazzo and B. Pesquet-Popescu},

doi = {10.1109/ISM.2015.34},

isbn = {978-1-5090-0379-2},

year  = {2016},

date = {2016-01-01},

booktitle = {Proceedings - 2015 IEEE International Symposium on Multimedia, ISM 2015},

pages = {295--300},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {Multi-view video plus depth is emerging as the most flexible format for 3D video representation, as witnessed by the current standardization efforts by ISO and ITU. The depth information allows synthesizing virtual view points, and for its compression various techniques have been proposed. It is generally recognized that a high quality view rendering at the receiver side is possible only by preserving the contour information since distortions on edges during the encoding step would cause a sensible degradation on the synthesized view and on the 3D perception. As a consequence recent approaches include contour-based coding of depths. However, the impact of contour-preserving depth-coding on the perceived quality of synthesized images has not been conveniently studied. Therefore in this paper we make an investigation by means of a subjective study to better understand the limits and the potentialities of the different techniques. Our results show that the contour information is indeed relevant in the synthesis step: preserving the contours and coding coarsely the rest typically leads to images that users cannot tell apart from the reference ones, even at low bit rate. Moreover, our results show that objective metrics that are commonly used to evaluate synthesized images may have a low correlation coefficient with MOS rates and are in general not consistent across several techniques and contents.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469679,

title = {Convex optimization for frame-level rate allocation in MV-HEVC},

author = { A. Fiengo and G. Chierchia and M. Cagnazzo and B. Pesquet-Popescu},

doi = {10.1109/ICIP.2016.7532740},

year  = {2016},

date = {2016-01-01},

booktitle = {Proceedings - International Conference on Image Processing, ICIP},

volume = {2016-},

pages = {2157--2161},

publisher = {IEEE Computer Society},

abstract = {Optimal rate allocation is among the most challenging tasks to perform in the context of multi-view video coding, because of the dependency between frames induced by motion compensation and depth image-based rendering. In this paper, using a recursive rate-distortion model that explicitly takes into account these dependencies, we approach the frame-level rate allocation as a convex optimization problem. Within this framework, we provide an efficient algorithm for exactly solving the above problem with recent convex optimization tools. Experiments on standard sequences demonstrate the interest of considering the proposed rate allocation method and confirm that our approach ensures a better performance (in ratedistortion sense) than the standard MV-HEVC rate control.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469678,

title = {A distortion evaluation framework in 3D video view synthesis},

author = { A. I. Purica and M. Cagnazzo and B. Pesquet-Popescu and F. Dufaux and B. Ionescu},

doi = {10.1109/IC3D.2015.7391827},

isbn = {978-1-5090-1265-7},

year  = {2016},

date = {2016-01-01},

booktitle = {2015 International Conference on 3D Imaging, IC3D 2015 - Proceedings},

pages = {1--8},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {Demand for 3D content increased over the last years and more attention was dedicated to methods used in 3D content creation and transmission. View synthesis methods introduce localized artifacts when creating new virtual views. Evaluating these methods require therefore a different approach, in order to identify and emphasize synthesis artifact prone areas, while diminishing the impact, of other types of artifacts, such as those produced by quantization during the video coding. In this paper, we propose an artifact evaluation technique which was shown to provide a better differentiation of synthesis methods, while additional information can be extrapolated from the results about the spatial localization of typical synthesis artifacts and their impact on overall image quality.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469672,

title = {Key view selection in distributed multiview coding},

author = { T. Maugey and G. Petrazzuoli and P. Frossard and M. Cagnazzo and B. Pesquet-Popescu},

doi = {10.1109/VCIP.2014.7051612},

isbn = {978-1-4799-6139-9},

year  = {2015},

date = {2015-01-01},

booktitle = {2014 IEEE Visual Communications and Image Processing Conference, VCIP 2014},

pages = {486--487},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {Multiview image and video systems with large number of views lead to new problems in data representation, transmission and user interaction. In order to reduce the data volumes, most distributed multiview coding schemes exploit the inter-view redundancies at the decoder side, using view synthesis from key views. In the situation where many views are considered, the two following questions become fundamental: i) how many key views have to be chosen for keeping a good reconstruction quality with reasonable coding cost? ii) where to place them optimally in the multiview sequences? We propose in this paper an algorithm for selecting the key views in a distributed multiview coding scheme. Based on a novel metric for the correlation between the views, we formulate an optimization problem for the positioning of the key views such that both the distortion of the reconstruction and the coding rate cost are effectively minimized. We then propose a new optimization strategy based on shortest path algorithm that permits to determine both the optimal number of key views and their positions in the image set. We experimentally validate our solution in a practical distributed multiview coding system and we show that considering the 3D scene geometry in the key view positioning brings significant rate-distortion improvements compared to distance-based key view selection as it is commonly done in the literature.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}