53 citations · 123 across the 18 of their papers we have counts for
17 papers · 1 filter
Overview of Variable Rate Coding in JPEG AI
Panqi Jia, Fabian Brand, Dequan Yu +3
Empirical evidence has demonstrated that learning-based image compression can outperform classical compression frameworks. This has led to the ongoing standardization of learned-ba…
Spatially-Adaptive Learning-Based Image Compression with Hierarchical Multi-Scale Latent Spaces
Fabian Brand, Alexander Kopte, Kristian Fischer +1
Adaptive block partitioning is responsible for large gains in current image and video compression systems. This method is able to compress large stationary image areas with only a…
Conditional Residual Coding: A Remedy for Bottleneck Problems in Conditional Inter Frame Coding
Fabian Brand, Jürgen Seiler, André Kaup
Conditional coding is a new video coding paradigm enabled by neural-network-based compression. It can be shown that conditional coding is in theory better than the traditional resi…
Processing Energy Modeling for Neural Network Based Image Compression
Christian Herglotz, Fabian Brand, Andy Regensky +2
Nowadays, the compression performance of neural-networkbased image compression algorithms outperforms state-of-the-art compression approaches such as JPEG or HEIC-based image compr…
Learned Wavelet Video Coding using Motion Compensated Temporal Filtering
Anna Meyer, Fabian Brand, André Kaup
We present an end-to-end trainable wavelet video coder based on motion-compensated temporal filtering (MCTF). Thereby, we introduce a different coding scheme for learned video comp…
Multiscale Augmented Normalizing Flows for Image Compression
Marc Windsheimer, Fabian Brand, André Kaup
Most learning-based image compression methods lack efficiency for high image quality due to their non-invertible design. The decoding function of the frequently applied compressive…
The Bjøntegaard Bible -- Why your Way of Comparing Video Codecs May Be Wrong
Christian Herglotz, Hannah Och, Anna Meyer +8
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…
Saliency-Driven Hierarchical Learned Image Coding for Machines
Kristian Fischer, Fabian Brand, Christian Blum +1
We propose to employ a saliency-driven hierarchical neural image compression network for a machine-to-machine communication scenario following the compress-then-analyze paradigm. B…
Learning Frequency-Specific Quantization Scaling in VVC for Standard-Compliant Task-driven Image Coding
Kristian Fischer, Fabian Brand, Christian Herglotz +1
Today, visual data is often analyzed by a neural network without any human being involved, which demands for specialized codecs. For standard-compliant codec adaptations towards ce…
Domain Adaptation for Unknown Image Distortions in Instance Segmentation
Maximiliane Gruber, Fabian Brand, Alina Mosebach +2
Data-driven techniques for machine vision heavily depend on the training data to sufficiently resemble the data occurring during test and application. However, in practice unknown…
Video Coding for Machines with Feature-Based Rate-Distortion Optimization
Kristian Fischer, Fabian Brand, Christian Herglotz +1
Common state-of-the-art video codecs are optimized to deliver a low bitrate by providing a certain quality for the final human observer, which is achieved by rate-distortion optimi…
A Novel End-To-End Network for Reconstruction of Non-Regularly Sampled Image Data Using Locally Fully Connected Layers
Simon Grosche, Fabian Brand, André Kaup
Quarter sampling and three-quarter sampling are novel sensor concepts that enable the acquisition of higher resolution images without increasing the number of pixels. This is achie…
Enhanced Image Reconstruction From Quarter Sampling Measurements Using An Adapted Very Deep Super Resolution Network
Simon Grosche, Kristian Fischer, Fabian Brand +2
Quarter sampling is a novel sensor concept that enables the acquisition of higher resolution images without increasing the number of pixels. This is achieved by covering three quar…
A Low-Parametric Model for Bit-Rate Estimation of VVC Residual Coding
Fabian Brand, Christian Herglotz, André Kaup
There are many tasks within video compression which require fast bit rate estimation. As an example, rate-control algorithms are only feasible because it is possible to estimate th…
Learning True Rate-Distortion-Optimization for End-To-End Image Compression
Fabian Brand, Kristian Fischer, Alexander Kopte +1
Even though rate-distortion optimization is a crucial part of traditional image and video compression, not many approaches exist which transfer this concept to end-to-end-trained i…
Generalized Difference Coder: A Novel Conditional Autoencoder Structure for Video Compression
Fabian Brand, Jürgen Seiler, André Kaup
Motion compensated inter prediction is a common component of all video coders. The concept was established in traditional hybrid coding and successfully transferred to learning-bas…
Boosting Neural Image Compression for Machines Using Latent Space Masking
Kristian Fischer, Fabian Brand, André Kaup
Today, many image coding scenarios do not have a human as final intended user, but rather a machine fulfilling computer vision tasks on the decoded image. Thereby, the primary goal…