arXiv subjects

Ferdinand Jost

Publications and source records attributed to Ferdinand Jost.

4 recordsLinked to original sources

arXiv2026

Optimizing Multiple Feature Types for Image Inpainting in the Linear and Nonlinear Setting

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 decisively on the stored data. So far, these data consist almost exclusively of pixel locations along with their grayscale or color values. In the present paper, we present a general theory and a practical framework that allows to incorporate arbitrary features which can be described by linear or nonlinear equations. This includes e.g. derivatives of arbitrary order or local integrals. Our features can be combined with linear or nonlinear inpainting operators. Moreover, we present an algorithm that automatically optimizes the location and the type of the selected feature. The approach of allowing different types of optimized features turns inpainting-based compression into a more general, versatile and powerful paradigm. Our experiments report a consistent quality gain when increasing the number of feature types from 1 to 5. With the same amount of stored data, the average peak signal-to-noise improvement is 2.76 dB for harmonic (homogeneous diffusion) inpainting, and 1.82 dB for edge-enhancing diffusion inpainting.

eess.IV↗

arXiv2022

Optimising Different Feature Types for Inpainting-based Image Representations

Inpainting-based image compression is a promising alternative to classical transform-based lossy codecs. Typically it stores a carefully selected subset of all pixel locations and their colour values. In the decoding phase the missing information is reconstructed by an inpainting process such as homogeneous diffusion inpainting. Optimising the stored data is the key for achieving good performance. A few heuristic approaches also advocate alternative feature types such as derivative data and construct dedicated inpainting concepts. However, one still lacks a general approach that allows to optimise and inpaint the data simultaneously w.r.t. a collection of different feature types, their locations, and their values. Our paper closes this gap. We introduce a generalised inpainting process that can handle arbitrary features which can be expressed as linear equality constraints. This includes e.g. colour values and derivatives of any order. We propose a fully automatic algorithm that aims at finding the optimal features from a given collection as well as their locations and their function values within a specified total feature density. Its performance is demonstrated with a novel set of features that also includes local averages. Our experiments show that it clearly outperforms the popular inpainting with optimised colour data with the same density.

eess.IV↗

arXiv2020

Compressing Piecewise Smooth Images with the Mumford-Shah Cartoon Model

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 explicitly stored segmentations excel in this task since they preserve discontinuities between smooth regions. However, current approaches rely on ad hoc segmentations that lack a clean interpretation in terms of energy minimisation. As a remedy, we derive a generic region merging algorithm from the Mumford-Shah cartoon model. It adapts the segmentation to arbitrary reconstruction operators for the segment content. In spite of its conceptual simplicity, our framework can outperform previous segment-based compression methods as well as BPG by up to 3 dB.

eess.IV↗

arXiv2020

Compressing Flow Fields with Edge-aware Homogeneous Diffusion Inpainting

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 in this area so far. Our paper addresses this problem by proposing the first lossy diffusion-based codec for this purpose. It keeps only a few flow vectors on a coarse grid. Additionally stored edge locations ensure the accurate representation of discontinuities. In the decoding step, the missing information is recovered by homogeneous diffusion inpainting that incorporates the stored edges as reflecting boundary conditions. In spite of the simple nature of this codec, our experiments show that it achieves remarkable quality for compression ratios up to 800 : 1.

eess.IV↗