Efficient regression priors for reducing image compression artifacts
Authors:
- Radu TimofteRadu Timofte
- Luc Van GoolLGLuc Van Gool
- 1 September 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1543-1547
Abstract
Lossy image compression allows for large storage savings but at the cost of reduced fidelity of the compressed images. There is a fair amount of literature aiming at restoration by suppressing the compression artifacts. Very recently a learned semi-local Gaussian Processes-based solution (SLGP) has been proposed with impressive results. However, when applied to top compression schemes such as JPEG 2000, the improvement is less significant. In our paper we propose an efficient novel artifact reduction algorithm based on the adjusted anchored neighborhood regression (A+), a method from image super-resolution literature. We double the relative gains in PSNR when compared with the state-of-the-art methods such as SLGP, while being order(s) of magnitude faster.Keywords
This publication has 8 references indexed in Scilit:
- Anchored Neighborhood Regression for Fast Example-Based Super-Resolution2013
- On Single Image Scale-Up Using Sparse-Representations2012
- Scale-space method of image ringing estimation2009
- Efficient quadtree based block-shift filtering for deblocking and deringingJournal of Visual Communication and Image Representation, 2009
- Fields of ExpertsInternational Journal of Computer Vision, 2009
- Pointwise Shape-Adaptive DCT for High-Quality Denoising and Deblocking of Grayscale and Color ImagesIEEE Transactions on Image Processing, 2007
- Vector-valued image regularization with PDEs: a common framework for different applicationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Projection-based spatially adaptive reconstruction of block-transform compressed imagesIEEE Transactions on Image Processing, 1995