Video Super-Resolution Using Codebooks Derived From Key-Frames

Hung, Edson M.; Queiroz, Ricardo L. de; Brandi, Fernanda; Oliveira, Karen Fernandes de; Mukherjee, Debargha

doi:10.1109/tcsvt.2012.2201669

Cited by 38 publications

(54 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We would, however, like to add to the framework a motion estimation step as in [86], in order to take advantage of the already reconstructed frames and enforce temporal consistency.…”

Section: Weight Computation Methods To Provide Temporal Consistencymentioning

confidence: 99%

“…We then propose a new weight computation method for NE according to the principle described above, where the closest patches are found by motion estimation as in [86]. The motion estimation process is done for every overlapping patch: for a given LR input patch in a non-key frame x l i , we can then nd the two LR patches in the two neighbor key frames, pointed by the motion vectors …”

Section: Weight Computation Methods To Provide Temporal Consistencymentioning

confidence: 99%

“…The method is close to the SR algorithm of Hung et al proposed in [86]. In [86], for a given patch, the search for the closest patches is performed by restricting it to windows positioned on the key frames (the central positions are given by computed motion vectors): the two best matching patches are selected, one for each key frames, and combined according to distance-depending weights. Dierently than [86], we instead proposed with Proc.…”

Section: Analysis In the Coding Contextmentioning

confidence: 99%

“…In [86], for a given patch, the search for the closest patches is performed by restricting it to windows positioned on the key frames (the central positions are given by computed motion vectors): the two best matching patches are selected, one for each key frames, and combined according to distance-depending weights. Dierently than [86], we instead proposed with Proc. 3 to perform the neighbor search globally, by considering the dictionary formed by the two current key frames as a whole.…”

Section: Analysis In the Coding Contextmentioning

confidence: 99%

See 3 more Smart Citations

Image Quality Assessment by Upsampling Methods Based on Spatial Spectrum Extrapolation

Игнатьев¹,

Матвеев²,

Мурынин³

et al. 2017

HoBMSTU.SNS

View full text Add to dashboard Cite

“…We would, however, like to add to the framework a motion estimation step as in [86], in order to take advantage of the already reconstructed frames and enforce temporal consistency.…”

Section: Weight Computation Methods To Provide Temporal Consistencymentioning

confidence: 99%

Section: Weight Computation Methods To Provide Temporal Consistencymentioning

confidence: 99%

Section: Analysis In the Coding Contextmentioning

confidence: 99%

Section: Analysis In the Coding Contextmentioning

confidence: 99%

See 2 more Smart Citations

Image Quality Assessment by Upsampling Methods Based on Spatial Spectrum Extrapolation

Игнатьев¹,

Матвеев²,

Мурынин³

et al. 2017

HoBMSTU.SNS

View full text Add to dashboard Cite

“…[1] proposes a different framework of down-sampling based coding with super resolution technique, where a superresolution technique is employed to restore the downsampled frames to their original resolutions. [2] extends a multiresolution approach to example-based super-resolution and discuss codebook construction for video sequences. In [3], the authors apply the example-based SR algorithm to restore the down-sampled frames.…”

Section: Introductionmentioning

confidence: 99%

A Single Image Compression Framework Combined with Sparse Representation-Based Super-Resolution

He¹,

He²,

Huang³

et al. 2015

Proceedings of the 2015 International Conference on Electronic Science and Automation Control

View full text Add to dashboard Cite

Abstract-This paper addresses the problem of single image compression by using sparse representation-based superresolution modeling. The proposed single image compression framework (SICF) is mainly composed of two components, including image encoder and decoder. Given an image, the framework takes down-sampling processing. Then, the downsampling image is fed into JPEG and reconstructed by the sparse representation-based super-resolution, which is using the proposed targeted dictionary based on soft-decision adaptive interpolation (TD-SAI) and targeted residual dictionary (TRD). For further improving the quality of the final decoded image, the feedback is designed to obtain residual assistance image which can be compensated for the loss of high-frequency details in process of super-resolution reconstruction. Supported by the targeted dictionary, our method achieved an improvement in objective quality assessment and competitive performance in visual quality when comparing with other SR algorithms. More importantly, the proposed SICF achieved significant bit-rate saving under the same PSNR compared with JPEG standard. Extensive experiments manifest the viability and efficiency of the proposed image compression framework.

show abstract

Adaptive Video Super-Resolution Based on Superpixel-Guided Auto-Regressive Model

Zhu

Jiang

et al. 2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Video Super-Resolution Using Codebooks Derived From Key-Frames

Cited by 38 publications

References 34 publications

Image Quality Assessment by Upsampling Methods Based on Spatial Spectrum Extrapolation

Image Quality Assessment by Upsampling Methods Based on Spatial Spectrum Extrapolation

A Single Image Compression Framework Combined with Sparse Representation-Based Super-Resolution

Adaptive Video Super-Resolution Based on Superpixel-Guided Auto-Regressive Model

Contact Info

Product

Resources

About