Artifact-Free Decompression and Zooming of JPEG Compressed Images with Total Generalized Variation
We propose a new model for the improved reconstruction and zooming of JPEG (Joint Photographic Experts Group) images. In the reconstruction process, given a JPEG compressed image, our method first determines the set of possible source images and then specifically chooses one of these source images satisfying additional regularity properties. This is realized by employing the recently introduced Total Generalized Variation (TGV) as regularization term and solving a constrained minimization problem. Data fidelity is modeled by the composition of a color-subsampling and a discrete cosine transformation operator. Furthermore, extending the notion of data set by allowing unconstrained intervals, the method facilitates optional magnification of the original image. In order to obtain an optimal solution numerically, we propose a primal-dual algorithm. We have developed a parallel implementation of this algorithm for the CPU and the GPU, using OpenMP and Nvidia’s Cuda, respectively. Finally, experiments have been performed, confirming a good visual reconstruction quality as well as the suitability for real-time application.
KeywordsArtifact-free JPEG decompression Total generalized variation Image reconstruction Image zooming
Unable to display preview. Download preview PDF.
- 5.Kartalov, T., Ivanovski, Z.A., Panovski, L., Karam, L.J.: An adaptive POCS algorithm for compression artifacts removal. In: 9th International Symposium on Signal Processing and Its Applications, pp. 1–4 (2007)Google Scholar
- 10.Zhong, S.: Image coding with optimal reconstruction. In: International Conference on Image Processing, vol. 1, pp. 161–164 (1997)Google Scholar
- 17.Bredies, K.: Recovering PIECEWISE smooth multichannel images by minimization of convex functionals with total generalized variation penalty. SFB Report 2012-006, Institute of Mathematics and Scientific Computing, University of Graz (2012)Google Scholar
- 18.OpenMP Architecture Review Board: Openmp application program interface, version 3.1 (2011), http://www.openmp.org
- 19.NVIDIA: NVIDIA CUDA programming guide 2.0. NVIDIA Cooperation (2008)Google Scholar
- 20.Frigo, M., Johnson, S.G.: The design and implementation of FFTW3. Proceedings of the IEEE 93, 216–231 (2005); Special issue on Program Generation, Optimization, and Platform AdaptationGoogle Scholar
- 21.Dawgbyte77 (2005), http://www.flickr.com/photos/dawgbyte77/3052164481/
- 22.Kubina, J. (2008), http://flickr.com/photos/kubina/42275122