A Novel Hybrid Kinect-Variety-Based High-Quality Multiview Rendering Scheme for Glass-Free 3D Displays

Sharma, Mansi; Chaudhury, Santanu; Lall, Brejesh

doi:10.1109/tcsvt.2016.2564798

Cited by 12 publications

(8 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, covering a range of bitrates assist in taking into account distortion considering the encoding of stereo LDR multiple exposure views and in conjunction regulate the reconstruction quality of fused HDR views. This is critical to achieve stereo personalization in 3D display applications with spontaneous realism and binocular 3D depth cues [19]- [21]. The results demonstrate that the required bitrate is much saved by the proposed scheme by efficiently exploiting the intraframe, inter-view and the inter-component redundancies in stereo multi-exposure LDR sequences.…”

Section: Discussionmentioning

confidence: 93%

“…In this work, we propose a new paradigm for coding multiexposure stereo images for 3D HDR display applications [19]- [21]. More specifically, we proposed a Tucker Decomposition based encoding model with 3D-HEVC that efficiently exploits the intra-frame, inter-view, inter-component redundancies and simultaneously takes the sparsity/low-rankness of latent multiexpsoure stereo images representation into consideration.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Unified Model for Multi-exposure Stereo Coding Based on Low Rank Tucker-ALS and 3D-HEVC

Sharma,

Wadaskar

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Display technology must offer high dynamic range (HDR) contrast-based depth induction and 3D personalization simultaneously. Efficient algorithms to compress HDR stereo data is critical. Direct capturing of HDR content is complicated due to the high expense and scarcity of HDR cameras. The HDR 3D images could be generated in low-cost by fusing low-dynamicrange (LDR) images acquired using a stereo camera with various exposure settings. In this paper, an efficient scheme for coding multi-exposure stereo images is proposed based on a tensor low-rank approximation scheme. The multi-exposure fusion can be realized to generate HDR stereo output at the decoder for increased realism and exaggerated binocular 3D depth cues.For exploiting spatial redundancy/sparsity in LDR stereo images, the stack of multi-exposure stereo images is decomposed into a set of projection matrices and a core tensor following an alternating least squares Tucker decomposition model. The compact, low-rank representation of the scene, thus, generated is further processed by 3D extension of High Efficiency Video Coding standard. The encoding with 3D-HEVC enhance the proposed scheme efficiency by exploiting intra-frame, inter-view and the inter-component redundancies in low-rank approximated representation. We consider constant luminance property of IPT and Y C b Cr color space to precisely approximate intensity prediction and perceptually minimize the encoding distortion. Besides, the proposed scheme gives flexibility to adjust the bitrate of tensor latent components by changing the rank of core tensor and its quantization. Extensive experiments on natural scenes demonstrate that the proposed scheme outperforms state-of-theart JPEG-XT and 3D-HEVC range coding standards.

show abstract

Section: Discussionmentioning

confidence: 93%

Section: Introductionmentioning

confidence: 99%

A Novel Unified Model for Multi-exposure Stereo Coding Based on Low Rank Tucker-ALS and 3D-HEVC

Sharma,

Wadaskar

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Glasses-free or naked-eye autostereoscopic displays have replaced stereoscopic displays which offer motion parallax for different viewing directions [ 4 ]. However, current naked-eye displays fall far short of truly recreating continuous motion parallax, greater depth-of-field, and a wider field-of-view for visual reality [ 5 , 6 , 7 , 8 ].…”

Section: Introductionmentioning

confidence: 99%

A Flexible Coding Scheme Based on Block Krylov Subspace Approximation for Light Field Displays with Stacked Multiplicative Layers

Ravishankar

Sharma

2021

Sensors

Self Cite

View full text Add to dashboard Cite

To create a realistic 3D perception on glasses-free displays, it is critical to support continuous motion parallax, greater depths of field, and wider fields of view. A new type of Layered or Tensor light field 3D display has attracted greater attention these days. Using only a few light-attenuating pixelized layers (e.g., LCD panels), it supports many views from different viewing directions that can be displayed simultaneously with a high resolution. This paper presents a novel flexible scheme for efficient layer-based representation and lossy compression of light fields on layered displays. The proposed scheme learns stacked multiplicative layers optimized using a convolutional neural network (CNN). The intrinsic redundancy in light field data is efficiently removed by analyzing the hidden low-rank structure of multiplicative layers on a Krylov subspace. Factorization derived from Block Krylov singular value decomposition (BK-SVD) exploits the spatial correlation in layer patterns for multiplicative layers with varying low ranks. Further, encoding with HEVC eliminates inter-frame and intra-frame redundancies in the low-rank approximated representation of layers and improves the compression efficiency. The scheme is flexible to realize multiple bitrates at the decoder by adjusting the ranks of BK-SVD representation and HEVC quantization. Thus, it would complement the generality and flexibility of a data-driven CNN-based method for coding with multiple bitrates within a single training framework for practical display applications. Extensive experiments demonstrate that the proposed coding scheme achieves substantial bitrate savings compared with pseudo-sequence-based light field compression approaches and state-of-the-art JPEG and HEVC coders.

show abstract

“…At the time of this paper, there is a notable growth in both the demand and the supply of novel 3D video contents, and the stereoscopic 3D (S3D) format is rapidly emerging in both cinematic and streaming use cases. There are three popular approaches to generate S3D videos: (i) Scene acquisition using a stereo camera, (ii) 2D-to-3D video conversion, which means the creation of left-and right-eye views from the original source video, and (iii) rendering, which is the process of synthesizing views by means of 3D reconstruction or employing global 3D models and computer vision techniques [1][2][3][4][5].…”

Section: Introductionmentioning

confidence: 99%

Latent Factor Modeling of Perceived Quality for Stereoscopic 3D Video Recommendation

Appina

Sharma

Kumar

et al. 2021

2021 International Conference on 3D Immersion (IC3D)

Self Cite

View full text Add to dashboard Cite

Throughout the recent decades, the movie industry has been continuously producing stereoscopic 3D contents on a wide scale of varying budget; while some of them are rather limited financially, others benefit from massive monetary reinforcements. 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 withThe scientific efforts leading to the results reported in this paper were

show abstract

A Novel Hybrid Kinect-Variety-Based High-Quality Multiview Rendering Scheme for Glass-Free 3D Displays

Cited by 12 publications

References 35 publications

A Novel Unified Model for Multi-exposure Stereo Coding Based on Low Rank Tucker-ALS and 3D-HEVC

A Novel Unified Model for Multi-exposure Stereo Coding Based on Low Rank Tucker-ALS and 3D-HEVC

A Flexible Coding Scheme Based on Block Krylov Subspace Approximation for Light Field Displays with Stacked Multiplicative Layers

Latent Factor Modeling of Perceived Quality for Stereoscopic 3D Video Recommendation

Contact Info

Product

Resources

About