3 papers
eess.IV2026
Optimizing Multiple Feature Types for Image Inpainting in the Linear and Nonlinear Setting
Vassillen Chizhov, Ferdinand Jost, Joachim Weickert
Inpainting-based compression stores a carefully optimized subset of the full image data and reconstructs the missing data by inpainting. The quality of these lossy codecs depends d…
eess.IV2020
Compressing Piecewise Smooth Images with the Mumford-Shah Cartoon Model
Ferdinand Jost, Pascal Peter, Joachim Weickert
Compressing piecewise smooth images is important for many data types such as depth maps in 3D videos or optic flow fields for motion compensation. Specialised codecs that rely on e…
eess.IV2019
Compressing Flow Fields with Edge-aware Homogeneous Diffusion Inpainting
Ferdinand Jost, Pascal Peter, Joachim Weickert
In spite of the fact that efficient compression methods for dense two-dimensional flow fields would be very useful for modern video codecs, hardly any research has been performed i…