Title: | Reduction of JPEG Artifacts using BSDEs |
Authors: | Borkowski, Dariusz Janczak-Borkowska, Katarzyna |
Citation: | WSCG 2021: full papers proceedings: 29. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 1-10. |
Issue Date: | 2021 |
Publisher: | Václav Skala - UNION Agency |
Document type: | conferenceObject konferenční příspěvek |
URI: | http://hdl.handle.net/11025/45004 |
ISBN: | 978-80-86943-34-3 |
ISSN: | 2464-4617 2464–4625(CD/DVD) |
Keywords: | rekonstrukce obrazu;artefakty JPEG;stochastické diferenciální rovnice;nelokální prostředky |
Keywords in different language: | image reconstruction;JPEG artifacts;stochastic differential equations;non local means |
Abstract in different language: | In this paper we propose a novel approach for reduction of JPEG artifacts using advanced techniques of stochasticcalculus. In order to solve this problem we use backward stochastic differential equations (in short BSDEs) andthe non local means method. In our algorithm we consider two processes. One of them has values in the imagedomain and determines pixels that will be involved in the reconstruction, the second one has values in the imagecodomain and gives weight to values of pixels. To calculate the weights, we use the idea of the patches similarityused in the non local means. Our experiments show that the new approach gives very good results and comparesfavourably with other methods. |
Rights: | © Václav Skala - UNION Agency |
Appears in Collections: | WSCG 2021: Full Papers Proceedings |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/45004
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.