Handling Motion Blur in Multi-Frame Super-Resolution

Ziyang Ma, Renjie Liao, Xin Tao, Li Xu, Jiaya Jia, Enhua Wu

CVPR 2015

doi:10.1109/CVPR.2015.7299159 /cvpr/2015/ma2015cvpr-handling/

Abstract

Ubiquitous motion blur easily fails multi-frame super-resolution (MFSR). Our method proposed in this paper tackles this issue by optimally searching least blurred pixels in MFSR. An EM framework is proposed to guide residual blur estimation and high-resolution image reconstruction. To suppress noise, we employ a family of sparse penalties as natural image priors, along with an effective solver. Theoretical analysis is performed on how and when our method works. The relationship between estimation errors of motion blur and the quality of input images is discussed. Our method produces sharp and higher-resolution results given input of challenging low-resolution noisy and blurred sequences.

PDF CVPR Semantic Scholar

Cite

Text

Ma et al. "Handling Motion Blur in Multi-Frame Super-Resolution." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7299159

Markdown

[Ma et al. "Handling Motion Blur in Multi-Frame Super-Resolution." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/ma2015cvpr-handling/) doi:10.1109/CVPR.2015.7299159

BibTeX

@inproceedings{ma2015cvpr-handling,
  title     = {{Handling Motion Blur in Multi-Frame Super-Resolution}},
  author    = {Ma, Ziyang and Liao, Renjie and Tao, Xin and Xu, Li and Jia, Jiaya and Wu, Enhua},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2015},
  doi       = {10.1109/CVPR.2015.7299159},
  url       = {https://mlanthology.org/cvpr/2015/ma2015cvpr-handling/}
}