Compressing Images with Diffusion- and Exemplar-Based Inpainting
Diffusion-based image compression methods can surpass state-of-the-art transform coders like JPEG 2000 for cartoon-like images. However, they are not well-suited for highly textured image content. Recently, advances in exemplar-based inpainting have made it possible to reconstruct images with non-local methods from sparse known data. In our work we compare the performance of such exemplar-based and diffusion-based inpainting algorithms, dependent on the type of image content. We use our insights to construct a hybrid compression codec that combines the strengths of both approaches. Experiments demonstrate that our novel method offers significant advantages over state-of-the-art diffusion-based methods on textured image data and can compete with transform coders.
KeywordsExemplar-based inpainting Diffusion-based inpainting Image compression Texture
Unable to display preview. Download preview PDF.
- 7.Efros, A.A., Leung, T.K.: Texture synthesis by non-parametric sampling. In: Proc. Seventh IEEE International Conference on Computer Vision, Corfu, vol. 2, pp. 1033–1038, September 1999Google Scholar
- 10.Gautier, J., Meur, O.L., Guillemot, C.: Efficient depth map compression based on lossless edge coding and diffusion. In: Proc. 29th Picture Coding Symposium, Krakow, Poland, pp. 81–84, May 2012Google Scholar
- 11.Hays, J., Efros, A.A.: Scene completion using millions of photographs. ACM Transactions on Graphics 26(3), 4 (2007)Google Scholar
- 13.Li, Y., Sjostrom, M., Jennehag, U., Olsson, R.: A scalable coding approach for high quality depth image compression. In: 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video, Zurich, Switzerland, pp. 1–4, October 2012Google Scholar
- 15.Mahoney, M.: Adaptive weighing of context models for lossless data compression. Tech. Rep. CS-2005-16, Florida Institute of Technology, Melbourne, Florida, December 2005Google Scholar
- 17.Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proc. Eigth International Conference on Computer Vision, Vancouver, Canada, pp. 416–423, July 2001Google Scholar
- 18.Pennebaker, W.B., Mitchell, J.L.: JPEG: Still Image Data Compression Standard. Springer, New York (1992)Google Scholar
- 20.Peter, P., Weickert, J.: Colour image compression with anisotropic diffusion. In: Proc. 21st IEEE International Conference on Image Processing, Paris, France, October 2014 (in press)Google Scholar
- 25.Taubman, D.S., Marcellin, M.W. (eds.): JPEG 2000: Image Compression Fundamentals, Standards and Practice. Kluwer, Boston (2002) Google Scholar
- 26.Weickert, J.: Theoretical foundations of anisotropic diffusion in image processing. Computing Supplement, vol. 11, pp. 221–236 (1996)Google Scholar