A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Filters
Boundary Artifact Reduction in View Synthesis of 3D Video: From Perspective of Texture-Depth Alignment
2011
IEEE transactions on broadcasting
Preserved Fulltext
His research interests include 3D video processing, video quality assessment, and video coding. ...
Experiments on view synthesis with original and compressed texture/depth data consistently demonstrate the superior performance of the proposed method as compared with other relevant boundary artifact ...
They are grateful to the three anonymous reviewers for their valuable comments and suggestions, which improved quality of the paper. ...
doi:10.1109/tbc.2011.2120730
fatcat:3e3b3vovwnatlipgpzqv4y3rti
Performance comparison of objective metrics on free-viewpoint videos with different depth coding algorithms
2018
Applications of Digital Image Processing XLI
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
(DIBR), but the quality assessment of DIBR-synthesized view is very challenging owing to its new types of distortions induced by inaccurate depth map which the conventional 2D quality metrics may fail ...
In this paper, we test the performance of existing objective metrics on free-viewpoint video with different depth coding algorithms. ...
The distortion in DIBR-synthesized views mainly originate from the pristine texture/depth image and the DIBR process as well. ...
doi:10.1117/12.2321270
fatcat:cpdv6ulr6fgnrmni52udobugqa
A Benchmark of DIBR Synthesized View Quality Assessment Metrics on a New Database for Immersive Media Applications
2019
IEEE transactions on multimedia
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
The quality of synthesized views was assessed subjectively by 41 observers and objectively using 14 state-of-the-art objective metrics. ...
However, new challenges have also been brought in assessing the quality of DIBR-synthesized views since this process induces some new types of distortions, which are inherently different from the distortion ...
Zhu [45] and L. Li [60] for sharing their code or executable files. ...
doi:10.1109/tmm.2018.2875307
fatcat:azi4onnfuzc33k7rp655kx7l3y
A study of depth/texture bit-rate allocation in multi-view video plus depth compression
2013
Annales des télécommunications
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Multi-view Video plus Depth (MVD) data offer a reliable representation of three dimensional (3D) scenes for 3D Video applications. ...
Consisting of texture and depth video sequences, the question of the relationship between these two types of data regarding bitrate allocation often raises. ...
Fig. 2 gives selected snapshots of the resulting synthesized views when using H.264-decompressed data with various texture/depth ratios. ...
doi:10.1007/s12243-013-0363-x
fatcat:njijyhg2qzbbrkiezjkt7ie3ia
Evaluating virtual image quality using the side-views information fusion and depth maps
2018
Information Fusion
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The algorithm blends two quality metrics, one estimating the texture distortion in the synthesized texture image induced by compression, transmission, 3D warping, or other causes and the second one determining ...
The proposed Synthesized Image Quality Metric (SIQM) is tested on the challenging MCL-3D and SIAT-3D datasets. ...
Two viewpoints of each sequence are compressed with 3DV-ATM v10.0 with 14 different texture/depth quantization combinations. ...
doi:10.1016/j.inffus.2017.11.007
fatcat:odfiz3d2u5d3vi3kurjs4qa4sy
Scalable Bit Allocation Between Texture and Depth Views for 3-D Video Streaming Over Heterogeneous Networks
2015
IEEE transactions on circuits and systems for video technology (Print)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
In the multi-view video plus depth (MVD) coding format, both texture and depth views are jointly compressed to represent the three-dimensional (3D) video content. ...
of Quantization Parameters (QPs) for texture and depth views to maximize the synthesized view quality subject to a fixed total bit rate. ...
Shahram Shirani and the anonymous reviewers for their valuable comments and suggestions. ...
doi:10.1109/tcsvt.2014.2334011
fatcat:zcoekvvumbat5ho4ql7zxxfnbm
Using region-of-interest for quality evaluation of DIBR-based view synthesis methods
2016
2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
One of the most commonly used techniques for aiding with the compression and creation of 3D content is known as view synthesis. ...
As 3D media became more and more popular over the last years, new technologies are needed in the transmission, compression and creation of 3D content. ...
[24] studied the assessment of 3-D encoded video, the authors also considered the synthesized view quality. Bosc et al. ...
doi:10.1109/qomex.2016.7498950
dblp:conf/qomex/PuricaVPD16
fatcat:zhpc3cjpt5gjbhmuuw6tmxf67i
Latent Factor Modeling of Perceived Quality for Stereoscopic 3D Video Recommendation
2021
2021 International Conference on 3D Immersion (IC3D)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
It is also quite apparent how the related technologies have significantly improved over the years, resulting in better and better 3D visuals. ...
However, at the time of this paper, it is still the sad truth that even those movies with The scientific efforts leading to the results reported in this paper were ...
The LFOVIAS3DPh2 S3D video dataset has 12 reference sequences with a good variety of structure, texture, depth and temporal information. ...
doi:10.1109/ic3d53758.2021.9687271
fatcat:b6rkz2cwbjdajfg4sg7r42pzki
Bit-rate allocation between texture and depth: Influence of data sequence characteristics
2012
2012 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
This paper questions the existence of factors influencing the quality of the synthesized views, in the context of multi-view video plus depth coding (MVC). ...
The originality of this study lies in the investigation of direct relationships between the best bit-rate allocation, in terms of objective quality of synthesized views, and the sequence characteristics ...
by objective and subjective quality assessment methods. ...
doi:10.1109/3dtv.2012.6365458
dblp:conf/3dtv/BoscRPM12
fatcat:3zq2pfzj75hj3exq6jay2i2m74
Quality Assessment of 3D Synthesized Images via Measuring Local Feature Similarity and Global Sharpness
2019
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
INDEX TERMS Quality assessment, depth-image-based rendering, 3D synthesized image, view synthesis. ...
However, the DIBR algorithms will introduce geometric distortions that mainly distribute at the disoccluded regions in the synthesized views. ...
Six image distortions, including Gaussian blur, additive white noise, down-sampled blur, JPEG and JPEG-2000 (JP2K) compression and transmission error, are added on the texture/depth image before rendering ...
doi:10.1109/access.2019.2891070
fatcat:44p6c7ljgrdkflfnyuq74yljg4
DIBR-synthesized image quality assessment based on morphological multi-scale approach
2016
EURASIP Journal on Image and Video Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Such distortions are not handled efficiently by the common image quality assessment metrics which are primarily designed for other types of distortions. ...
The depth-image-based rendering (DIBR) algorithms used for 3D video applications introduce new types of artifacts mostly located around the disoccluded regions. ...
Authors' contributions DSS proposed the framework of this work, carried out the whole experiments, and drafted the manuscript. ...
doi:10.1186/s13640-016-0124-7
fatcat:2nsxye5tkjahrewy7fnyvqvbj4
Coding of mixed-resolution multiview video in 3D video application
2013
2013 IEEE International Conference on Image Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
The emerging MVC+D standard specifies the coding of Multiview Video plus Depth (MVD) data for enabling advanced 3D video applications. ...
The proposed scheme is compared against the original MVC+D scheme and an average of 4% delta bitrate reduction (dBR) in the coded views and 14.5% of dBR in the synthesized views are reported. ...
Subjective assessments confirmed that such coding scheme achieved a 20% bitrate reduction for stereoscopic image-pairs created from rendered views with no degradation in the perceived subjective quality ...
doi:10.1109/icip.2013.6738351
dblp:conf/icip/AflakiSJRHLG13
fatcat:63nsdixidrg4rj4uzlzf5ghc3m
Quality Assessment for DIBR-Synthesized Images with Local and Global Distortions
2020
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
VOLUME XX, 2017 9 Foundation under Grants ZR2017QF006, and by Key Laboratory of Intelligent Perception and Advanced Control of State Ethnic Affairs Commission under Grant MD-IPAC-2019102. ...
Six image distortions, including Gaussian blur, additive white noise, downsampled blur, JPEG and JP2K compression transmission error, and rendering distortion are added on the texture/depth image before ...
of synthesized video with synthesis distortions. ...
doi:10.1109/access.2020.2971995
fatcat:3hj3meij2bccbcghaha6gbbt5q
A ParaBoost Stereoscopic Image Quality Assessment (PBSIQA) System
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The developed quality metric can serve as an objective function to optimize the performance of a 3D content delivery system. ...
Extensive experimental results are conducted to compare the performance of the proposed PBSIQA system with those of existing stereo image quality assessment (SIQA) metrics. ...
Another interesting extension is to consider the quality assessment of 3D video. On one hand, we believe that the ParaBoost methodology can be extended to the case of 3D video in principle. ...
arXiv:1603.09469v1
fatcat:rd55vxkelvbrbjqyej27yawoie
Loss-Resilient Coding of Texture and Depth for Free-Viewpoint Video Conferencing
2014
IEEE transactions on multimedia
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
To maintain high quality of synthesized images, it is imperative to contain the adverse effects of network packet losses that may arise during texture and depth video transmission. ...
Finally, quantization parameter (QP) is adaptively selected per frame, optimally trading off source distortion due to compression with channel distortion due to potential packet losses. ...
poor view synthesis quality for this particular 3D video sequence. ...
doi:10.1109/tmm.2014.2299768
fatcat:mjezqtibwnfjdoopez7hm7xpla
« Previous
Showing results 1 — 15 out of 33 results