André Kaup
YOU?
Author Swipe
View article: A High-Level Feature Model to Predict the Encoding Energy of a Hardware Video Encoder
A High-Level Feature Model to Predict the Encoding Energy of a Hardware Video Encoder Open
In today's society, live video streaming and user generated content streamed from battery powered devices are ubiquitous. Live streaming requires real-time video encoding, and hardware video encoders are well suited for such an encoding ta…
View article: Optimized Learned Image Compression for Facial Expression Recognition
Optimized Learned Image Compression for Facial Expression Recognition Open
Efficient data compression is crucial for the storage and transmission of visual data. However, in facial expression recognition (FER) tasks, lossy compression often leads to feature degradation and reduced accuracy. To address these chall…
View article: Compact Latent Representation for Image Compression (CLRIC)
Compact Latent Representation for Image Compression (CLRIC) Open
Current image compression models often require separate models for each quality level, making them resource-intensive in terms of both training and storage. To address these limitations, we propose an innovative approach that utilizes late…
View article: Overview of Variable Rate Coding in JPEG AI
Overview of Variable Rate Coding in JPEG AI Open
Empirical evidence has demonstrated that learning-based image compression can outperform classical compression frameworks. This has led to the ongoing standardization of learned-based image codecs, namely Joint Photographic Experts Group (…
View article: Improved Motion Plane Adaptive 360-Degree Video Compression Using Affine Motion Models
Improved Motion Plane Adaptive 360-Degree Video Compression Using Affine Motion Models Open
Efficient compression of 360-degree video content requires the application of advanced motion models for interframe prediction. The Motion Plane Adaptive (MPA) motion model projects the frames on multiple perspective planes in the 3D space…
View article: Inter-Camera Color Correction for Multispectral Imaging with Camera Arrays Using a Consensus Image
Inter-Camera Color Correction for Multispectral Imaging with Camera Arrays Using a Consensus Image Open
This paper introduces a novel method for inter-camera color calibration for multispectral imaging with camera arrays using a consensus image. Capturing images using multispectral camera arrays has gained importance in medical, agricultural…
View article: Variable Rate Learned Wavelet Video Coding using Temporal Layer Adaptivity
Variable Rate Learned Wavelet Video Coding using Temporal Layer Adaptivity Open
Learned wavelet video coders provide an explainable framework by performing discrete wavelet transforms in temporal, horizontal, and vertical dimensions. With a temporal transform based on motion-compensated temporal filtering (MCTF), spat…
View article: Conditional Optimal Filter Selection for Multispectral Object Classification
Conditional Optimal Filter Selection for Multispectral Object Classification Open
Capturing images using multispectral camera arrays has gained importance in medical, agricultural and environmental processes. However, using all available spectral bands is infeasible and produces much data, while only a fraction is neede…
View article: Modeling the Energy Consumption of the HEVC Software Encoding Process using Processor events
Modeling the Energy Consumption of the HEVC Software Encoding Process using Processor events Open
Developing energy-efficient video encoding algorithms is highly important due to the high processing complexities and, consequently, the high energy demand of the encoding process. To accomplish this, the energy consumption of the video en…
View article: Design Space Exploration at Frame-Level for Joint Decoding Energy and Quality Optimization in VVC
Design Space Exploration at Frame-Level for Joint Decoding Energy and Quality Optimization in VVC Open
In the pursuit of a reduced energy demand of VVC decoders, it was found that the coding tool configuration has a substantial influence on the bit rate efficiency and the decoding energy demand. The Advanced Design Space Exploration algorit…
View article: Fast Edge-Aware Occlusion Detection in the Context of Multispectral Camera Arrays
Fast Edge-Aware Occlusion Detection in the Context of Multispectral Camera Arrays Open
Multispectral imaging is very beneficial in diverse applications, like healthcare and agriculture, since it can capture absorption bands of molecules in different spectral areas. A promising approach for multispectral snapshot imaging are …
View article: End-to-end learned Lossy Dynamic Point Cloud Attribute Compression
End-to-end learned Lossy Dynamic Point Cloud Attribute Compression Open
Recent advancements in point cloud compression have primarily emphasized geometry compression while comparatively fewer efforts have been dedicated to attribute compression. This study introduces an end-to-end learned dynamic lossy attribu…
View article: High-Resolution Hyperspectral Video Imaging Using A Hexagonal Camera Array
High-Resolution Hyperspectral Video Imaging Using A Hexagonal Camera Array Open
Retrieving the reflectance spectrum from objects is an essential task for many classification and detection problems, since many materials and processes have a unique spectral behaviour. In many cases, it is highly desirable to capture hyp…
View article: SVT-AV1 Encoding Bitrate Estimation Using Motion Search Information
SVT-AV1 Encoding Bitrate Estimation Using Motion Search Information Open
Enabling high compression efficiency while keeping encoding energy consumption at a low level, requires prioritization of which videos need more sophisticated encoding techniques. However, the effects vary highly based on the content, and …
View article: A Study on the Effect of Color Spaces in Learned Image Compression
A Study on the Effect of Color Spaces in Learned Image Compression Open
In this work, we present a comparison between color spaces namely YUV, LAB, RGB and their effect on learned image compression. For this we use the structure and color based learned image codec (SLIC) from our prior work, which consists of …
View article: Towards Video Codec Performance Evaluation: A Rate-Energy-Distortion Perspective
Towards Video Codec Performance Evaluation: A Rate-Energy-Distortion Perspective Open
The Bj{\o}ntegaard Delta rate (BD-rate) objectively assesses the coding efficiency of video codecs using the rate-distortion (R-D) performance but overlooks encoding energy, which is crucial in practical applications, especially for those …
View article: Multispectral Snapshot Image Registration Using Learned Cross Spectral Disparity Estimation and a Deep Guided Occlusion Reconstruction Network
Multispectral Snapshot Image Registration Using Learned Cross Spectral Disparity Estimation and a Deep Guided Occlusion Reconstruction Network Open
Multispectral imaging aims at recording images in different spectral bands. This is extremely beneficial in diverse discrimination applications, for example in agriculture, recycling or healthcare. One approach for snapshot multispectral i…
View article: On Annotation-free Optimization of Video Coding for Machines
On Annotation-free Optimization of Video Coding for Machines Open
Today, image and video data is not only viewed by humans, but also automatically analyzed by computer vision algorithms. However, current coding standards are optimized for human perception. Emerging from this, research on video coding for…
View article: Efficient Learned Wavelet Image and Video Coding
Efficient Learned Wavelet Image and Video Coding Open
Learned wavelet image and video coding approaches provide an explainable framework with a latent space corresponding to a wavelet decomposition. The wavelet image coder iWave++ achieves state-of-the-art performance and has been employed fo…
View article: Bit Rate Matching Algorithm Optimization in JPEG-AI Verification Model
Bit Rate Matching Algorithm Optimization in JPEG-AI Verification Model Open
The research on neural network (NN) based image compression has shown superior performance compared to classical compression frameworks. Unlike the hand-engineered transforms in the classical frameworks, NN-based models learn the non-linea…
View article: Bit Distribution Study and Implementation of Spatial Quality Map in the JPEG-AI Standardization
Bit Distribution Study and Implementation of Spatial Quality Map in the JPEG-AI Standardization Open
Currently, there is a high demand for neural network-based image compression codecs. These codecs employ non-linear transforms to create compact bit representations and facilitate faster coding speeds on devices compared to the hand-crafte…
View article: Forensic analysis of AI-compression traces in spatial and frequency domain
Forensic analysis of AI-compression traces in spatial and frequency domain Open
The classical JPEG compression is a rich source of cues for forensic image analysis. However, this compression standard will in the near future be complemented by a new, highly efficient learning-based compression standard called JPEG-AI. …
View article: Energy Demand Prediction for Hardware Video Decoders Using Software Profiling
Energy Demand Prediction for Hardware Video Decoders Using Software Profiling Open
Energy efficiency for video communications is essential for mobile devices with a limited battery capacity. Therefore, hardware decoder implementations are commonly used to significantly reduce the energetic load of video playback. The ene…
View article: Analysis of Neural Video Compression Networks for 360-Degree Video Coding
Analysis of Neural Video Compression Networks for 360-Degree Video Coding Open
With the increasing efforts of bringing high-quality virtual reality technologies into the market, efficient 360-degree video compression gains in importance. As such, the state-of-the-art H.266/VVC video coding standard integrates dedicat…
View article: A Comprehensive Review of Software and Hardware Energy Efficiency of Video Decoders
A Comprehensive Review of Software and Hardware Energy Efficiency of Video Decoders Open
Energy and compression efficiency are two essential parts of modern video decoder implementations that have to be considered. This work comprehensively studies the following six video coding formats regarding compression and decoding energ…
View article: SLIC: A Learned Image Codec Using Structure and Color
SLIC: A Learned Image Codec Using Structure and Color Open
We propose the structure and color based learned image codec (SLIC) in which the task of compression is split into that of luminance and chrominance. The deep learning model is built with a novel multi-scale architecture for Y and UV chann…
View article: Encoding Time and Energy Model for SVT-AV1 based on Video Complexity
Encoding Time and Energy Model for SVT-AV1 based on Video Complexity Open
The share of online video traffic in global carbon dioxide emissions is growing steadily. To comply with the demand for video media, dedicated compression techniques are continuously optimized, but at the expense of increasingly higher com…
View article: Temporal Context Network for 3d Human Pose Estimation with Graph Attention
Temporal Context Network for 3d Human Pose Estimation with Graph Attention Open
View article: The Bjøntegaard Bible Why Your Way of Comparing Video Codecs May Be Wrong
The Bjøntegaard Bible Why Your Way of Comparing Video Codecs May Be Wrong Open
In this paper, we provide an in-depth assessment on the Bjøntegaard Delta. We construct a large data set of video compression performance comparisons using a diverse set of metrics including PSNR, VMAF, bitrate, and processing energies. Th…
View article: Enhanced Color Palette Modeling for Lossless Screen Content Compression
Enhanced Color Palette Modeling for Lossless Screen Content Compression Open
Soft context formation is a lossless image coding method for screen content. It encodes images pixel by pixel via arithmetic coding by collecting statistics for probability distribution estimation. Its main pipeline includes three stages, …