Proceedings ArticleDOI
Regularization function for video super-resolution using auxiliary high resolution still images
Seyedreza Najafi,Shahram Shirani +1 more
- pp 1713-1717
Reads0
Chats0
TLDR
This paper uses high-resolution still images to form a regularization function and use it for the de-blurring stage of the super-resolution process, and shows that performance of the proposed algorithm is superior in terms of recovering high-frequency details of the original video and edge reconstruction.Abstract:
In this paper video super-resolution using sequences generated by dual-mode cameras is studied Dual-mode cameras are capable to shoot high-resolution still images at a low rate while taking low-resolution video from the scene An algorithm for video super-resolution is proposed which uses high-resolution still images generated by the dual-mode cameras for super-resolution process We use high-resolution still images to form a regularization function and use it for the de-blurring stage of the super-resolution process The simulation results show that performance of the proposed algorithm is superior in terms of recovering high-frequency details of the original video and edge reconstructionread more
Citations
More filters
Patent
Content display on moving vehicles
TL;DR: In this paper, a system for displaying content on a vehicle with at least one display device coupled to a frame member and extending to the right or left of the license plate receiving area of the vehicle is described.
Proceedings ArticleDOI
Multi-view video super-resolution for hybrid cameras using modified NLM and adaptive thresholding
TL;DR: Through a combination of techniques including adaptive thresholds and specialized candidate pixel selection schemes, the proposed method reconstructs a high fidelity video stream with considerably improved performance.
Proceedings ArticleDOI
A new approach in single Image Super Resolution
Saeideh Sarmadi,Zari Shamsa +1 more
TL;DR: This paper proposes a new super resolution algorithm based on single low resolution image, which consists of three phases up-sampling, deblurring and denoising.
Journal ArticleDOI
Video Super-resolution using Edge-based Optical Flow and Intensity Prediction
Jen-Wen Wang,Ching-Te Chiu +1 more
TL;DR: This paper proposes an edge-based motion and intensity prediction scheme to reduce the computation cost while maintain good enough quality simultaneously and reveals that the proposed scheme can successfully keep the super-resolved sequence quality and get about 4x speed up in computation time.
Journal ArticleDOI
Super resolution for multiview mixed resolution images in transform-domain with optimal weight
TL;DR: A novel Super Resolution (SR) scheme is presented, which not only borrows the high frequency content from neighboring full resolution frame, but also makes use of all high resolution (HR) warped images to enhance low resolution (LR) view image.
References
More filters
Proceedings ArticleDOI
A non-local algorithm for image denoising
TL;DR: A new measure, the method noise, is proposed, to evaluate and compare the performance of digital image denoising methods, and a new algorithm, the nonlocal means (NL-means), based on a nonlocal averaging of all pixels in the image is proposed.
Journal ArticleDOI
Fast and robust multiframe super resolution
TL;DR: This paper proposes an alternate approach using L/sub 1/ norm minimization and robust regularization based on a bilateral prior to deal with different data and noise models and demonstrates its superiority to other super-resolution methods.
Journal ArticleDOI
A new diamond search algorithm for fast block-matching motion estimation
Shan Zhu,Kai-Kuang Ma +1 more
TL;DR: Experimental results show that the proposed diamond search (DS) algorithm is better than the four-step search (4SS) and block-based gradient descent search (BBGDS), in terms of mean-square error performance and required number of search points.
Journal ArticleDOI
Generalizing the Nonlocal-Means to Super-Resolution Reconstruction
TL;DR: This paper shows how this denoising method is generalized to become a relatively simple super-resolution algorithm with no explicit motion estimation, and results show that the proposed method is very successful in providing super- resolution on general sequences.