no code implementations • 14 Dec 2023 • Frank Sippel, Nils Genser, Hannah Och, Jürgen Seiler, André Kaup
The theoretical examination of the novel color agnostic method is completed by an extensive evaluation compared to state of the art including self-recorded multispectral data and a reference implementation.
no code implementations • 14 Dec 2023 • Frank Sippel, Jürgen Seiler, André Kaup
Thus, in this paper an upsampling method for SWIR images guided by a visible image is presented.
no code implementations • 12 Sep 2023 • Marcel Trammer, Nils Genser, Jürgen Seiler
To this end, GIRRE increases the spatial resolution of the low-resolution IR image.
no code implementations • 24 Jul 2023 • Fabian Brand, Jürgen Seiler, André Kaup
Conditional coding is a new video coding paradigm enabled by neural-network-based compression.
1 code implementation • 27 Jun 2023 • Frank Sippel, Jürgen Seiler, André Kaup
Since only little cross spectral data is available for training, this neural network is highly regularized.
no code implementations • 24 Apr 2023 • Arya Rachman, Jürgen Seiler, André Kaup
The network is arranged in a Siamese-twin structure to constrain the network features learning to a mutually shared feature in both point cloud and camera (Lidar-camera constraint).
no code implementations • 3 Feb 2023 • Wolfgang Schnurrer, Thomas Richter, Jürgen Seiler, André Kaup
Factorized in the lifting structure, the wavelet transform can easily be extended by arbitrary compensation methods.
no code implementations • 2 Feb 2023 • Daniela Lanz, Jürgen Seiler, Karina Jaskolka, André Kaup
For the lossless compression of dynamic 3-D+t volumes as produced by medical devices like Computed Tomography, various coding schemes can be applied.
1 code implementation • 18 Jan 2023 • Frank Sippel, Jürgen Seiler, André Kaup
Two novel algorithms for two different applications are proposed to prove the diversity of applications that can be addressed by this novel database.
no code implementations • 12 Jan 2023 • Wolfgang Schnurrer, Markus Jonscher, Jürgen Seiler, Thomas Richter, Michel Bätz, André Kaup
To enlarge the test set for evaluation we further propose a method to generate arbitrarily shaped lost areas.
no code implementations • 11 Jan 2023 • Wolfgang Schnurrer, Jürgen Seiler, Michael Schöberl, André Kaup
Especially in lossless image coding the obtainable compression ratio strongly depends on the amount of noise included in the data as all noise has to be coded, too.
no code implementations • 11 Jan 2023 • Wolfgang Schnurrer, Tobias Tröger, Thomas Richter, Jürgen Seiler, André Kaup
Lossless image coding is a crucial task especially in the medical area, e. g., for volumes from Computed Tomography or Magnetic Resonance Tomography.
no code implementations • 11 Jan 2023 • Wolfgang Schnurrer, Jürgen Seiler, Eugen Wige, André Kaup
A huge advantage of the wavelet transform in image and video compression is its scalability.
no code implementations • 8 Dec 2022 • Wolfgang Schnurrer, Jürgen Seiler, André Kaup
This paper presents a new approach for improving the visual quality of the lowpass band of a compensated wavelet transform.
no code implementations • 8 Dec 2022 • Wolfgang Schnurrer, Thomas Richter, Jürgen Seiler, Christian Herglotz, André Kaup
We show that a 3-D mesh can obtain a higher quality of the lowpass band by 0. 28 dB with less than 40% of the model parameters of a comparable 2-D mesh.
no code implementations • 30 Nov 2022 • Andrea Eichenseer, Michel Bätz, Jürgen Seiler, André Kaup
Capturing large fields of view with only one camera is an important aspect in surveillance and automotive applications, but the wide-angle fisheye imagery thus obtained exhibits very special characteristics that may not be very well suited for typical image and video processing methods such as motion estimation.
no code implementations • 21 Nov 2022 • Andrea Eichenseer, Jürgen Seiler, Michel Bätz, André Kaup
Wide-angle video sequences obtained by fisheye cameras exhibit characteristics that may not very well comply with standard image and video processing techniques such as error concealment.
no code implementations • 5 Oct 2022 • Maximiliane Gruber, Fabian Brand, Alina Mosebach, Jürgen Seiler, André Kaup
However, in practice unknown distortion can lead to a domain gap between training and test data, impeding the performance of a machine vision system.
no code implementations • 28 Sep 2022 • Andreas Spruck, Maximilane Gruber, Anatol Maier, Denise Moussa, Jürgen Seiler, Christian Riess, André Kaup
The benefits of the proposed data generation pipeline, especially for machine learning scenarios with limited available training data, are demonstrated by an extensive experimental validation in the context of automatic license plate recognition.
no code implementations • 27 Sep 2022 • Andreas Spruck, Maximiliane Hawesch, Anatol Maier, Christian Riess, Jürgen Seiler, André Kaup
Applying the proposed method, improvements of up to 2. 79 percentage points in terms of Character Error Rate (CER), and up to 7. 88 percentage points in terms of Word Error Rate (WER) are achieved on the subset.
no code implementations • 27 Sep 2022 • Andreas Spruck, Jürgen Seiler, Michael Roll, Thomas Dudziak, Jürgen Eckstein, André Kaup
Due to their special characteristics, the images must be pre-processed to enable the use of a deep neural network.
no code implementations • 16 Sep 2022 • Frank Sippel, Jürgen Seiler, André Kaup
Therefore, multispectral cameras with wide-band filters are used, which are much cheaper and are often able to capture videos.
no code implementations • 16 Sep 2022 • Frank Sippel, Jürgen Seiler, Nils Genser, André Kaup
This novel estimation method is based on the guided filtering technique which preserves basic structures, while using spatial information to reduce the influence of noise.
no code implementations • 16 Sep 2022 • Frank Sippel, Jürgen Seiler, André Kaup
In many image processing tasks it occurs that pixels or blocks of pixels are missing or lost in only some channels.
no code implementations • 16 Sep 2022 • Frank Sippel, Jürgen Seiler, André Kaup
In this paper we introduce a novel fast binary search for optimal filter selection that guarantees a minimum distance metric between the different spectra to classify.
no code implementations • 15 Sep 2022 • Andreas Spruck, Markus Jonscher, Jürgen Seiler, André Kaup
This proposed extension solves the problem of changing content within the area considered by the 3D-FSE, which is caused by motion within the sequence.
no code implementations • 29 Jul 2022 • Denise Moussa, Anatol Maier, Andreas Spruck, Jürgen Seiler, Christian Riess
Forensic license plate recognition (FLPR) remains an open challenge in legal contexts such as criminal investigations, where unreadable license plates (LPs) need to be deciphered from highly compressed and/or low resolution footage, e. g., from surveillance cameras.
no code implementations • 20 Jul 2022 • Jürgen Seiler, Katrin Meisinger, André Kaup
Therefore the signal from the known samples is iteratively projected onto different basis functions in order to generate a model of the signal.
no code implementations • 20 Jul 2022 • Jürgen Seiler, Susanne Schöll, Wolfgang Schnurrer, André Kaup
A problem often arising in video communication is the reconstruction of missing or distorted areas in a video sequence.
no code implementations • 20 Jul 2022 • Jürgen Seiler, Thomas Richter, André Kaup
For this, the prediction is carried out in two steps.
no code implementations • 20 Jul 2022 • Jürgen Seiler, Haricharan Lakshman, André Kaup
Within the scope of this contribution we propose a novel efficient spatio-temporal prediction algorithm for video coding.
no code implementations • 14 Jul 2022 • Jürgen Seiler, André Kaup
This contribution introduces a novel signal extrapolation algorithm and its application to image error concealment.
no code implementations • 14 Jul 2022 • Jürgen Seiler, André Kaup
In the past years, video communication has found its application in an increasing number of environments.
no code implementations • 14 Jul 2022 • Jürgen Seiler, André Kaup
The proposed adaptive prior allows for a very high reconstruction quality, yielding gains of up to 0. 6 dB PSNR over the fixed prior, independently of the density of the available samples.
no code implementations • 8 Jul 2022 • Jürgen Seiler, André Kaup
The purpose of this contribution is to introduce a new method of signal prediction in video coding.
no code implementations • 8 Jul 2022 • Jürgen Seiler, Michael Schöberl, André Kaup
For this, Non-Local Means denoising is used which is extended by a spiral scan processing order and is improved by an adaptation step for taking the preliminary temporal extrapolation into account.
no code implementations • 8 Jul 2022 • Jürgen Seiler, André Kaup
To cope with this, error concealment can be applied on the distorted data at the receiver.
no code implementations • 4 Jul 2022 • Jürgen Seiler, André Kaup
The prediction step is a very important part of hybrid video codecs for effectively compressing video sequences.
no code implementations • 4 Jul 2022 • Jürgen Seiler, André Kaup
In this contribution, a novel spatio-temporal prediction algorithm for video coding is introduced.
no code implementations • 4 Jul 2022 • Jürgen Seiler, André Kaup
Since the basis functions are not orthogonal regarding the area of the known samples, the projection does not lead to the real portion a basis function has of the signal.
no code implementations • 1 Jul 2022 • Jürgen Seiler, André Kaup
The proposed framework allows for the application of existing image signal extrapolation algorithms without the need to modify them for a parallel processing.
no code implementations • 1 Jul 2022 • Jürgen Seiler, André Kaup
In this contribution an optimized processing order is proposed for Frequency Selective Extrapolation, a powerful signal extrapolation algorithm.
no code implementations • 1 Jul 2022 • Jürgen Seiler, André Kaup
Although wireless and IP-based access to video content gives a new degree of freedom to the viewers, the risk of severe block losses caused by transmission errors is always present.
no code implementations • 23 May 2022 • Ján Koloda, Jürgen Seiler, André Kaup
Digital images are commonly represented as regular 2D arrays, so pixels are organized in form of a matrix addressed by integers.
no code implementations • 23 May 2022 • Ján Koloda, Jürgen Seiler, Antonio M. Peinado, André Kaup
In this paper, we propose a novel scalable spatial error concealment algorithm that aims at obtaining high quality reconstructions with reduced computational burden.
no code implementations • 20 May 2022 • Ján Koloda, Jürgen Seiler, André Kaup
This paper presents a novel method for the reconstruction of images from samples located at non-integer positions, called mesh.
no code implementations • 16 May 2022 • Ján Koloda, Jürgen Seiler, André Kaup, Victoria Sánchez, Antonio M. Peinado
The purpose of signal extrapolation is to estimate unknown signal parts from known samples.
1 code implementation • 5 May 2022 • Simon Grosche, Andy Regensky, Alexander Sinn, Jürgen Seiler, André Kaup
Recently, non-regular three-quarter sampling has shown to deliver an increased image quality of image sensors by using differently oriented L-shaped pixels compared to the same number of square pixels.
no code implementations • 27 Apr 2022 • Jürgen Seiler, Markus Jonscher, Thomas Ussmueller, André Kaup
In this paper, we propose a novel image sensor layout which allows for the acquisition of images at a higher resolution and improved quality.
no code implementations • 27 Apr 2022 • Jürgen Seiler, Markus Jonscher, Michael Schöberl, André Kaup
Even though image signals are typically defined on a regular two-dimensional grid, there also exist many scenarios where this is not the case and the amplitude of the image signal only is available for a non-regular subset of pixel positions.
no code implementations • 27 Apr 2022 • Jürgen Seiler, André Kaup
The model generation is conducted by an enhanced version of Three-Dimensional Frequency Selective Extrapolation, an existing error concealment algorithm.
no code implementations • 27 Apr 2022 • Jürgen Seiler, André Kaup
Within the scope of this contribution, we introduce the complex-valued Frequency Selective Extrapolation for fast image and video signal extrapolation.
no code implementations • 27 Apr 2022 • Jürgen Seiler, André Kaup
Within the scope of this contribution, a novel efficient solution for Selective Extrapolation is presented for utilization with arbitrary basis functions.
no code implementations • 7 Apr 2022 • Markus Jonscher, Jürgen Seiler, Thomas Richter, Michel Bätz, André Kaup
Recently, it has been shown that by covering a low resolution sensor with a non-regular sampling mask and by using an efficient algorithm for image reconstruction, a high resolution image can be obtained.
no code implementations • 7 Apr 2022 • Markus Jonscher, Jürgen Seiler, Michel Bätz, Thomas Richter, Wolfgang Schnurrer, André Kaup
Recently, it has been shown that a high resolution image can be obtained without the usage of a high resolution sensor.
no code implementations • 7 Apr 2022 • Markus Jonscher, Jürgen Seiler, Thomas Richter, André Kaup
Recently, it has been shown that it is possible to obtain a high resolution image by covering a low resolution sensor with a non-regular sampling mask.
no code implementations • 7 Apr 2022 • Markus Jonscher, Jürgen Seiler, André Kaup
The reconstruction of clipped speech signals is an important task in audio signal processing to achieve an enhanced audio quality for further processing.
no code implementations • 7 Apr 2022 • Markus Jonscher, Karina Jaskolka, Jürgen Seiler, André Kaup
In this paper, a new recursive multi-frame reconstruction approach is proposed in order to further increase the reconstruction quality.
no code implementations • 7 Apr 2022 • Markus Jonscher, Jürgen Seiler, André Kaup
Hence, a new texture-dependent approach for frequency selective reconstruction is introduced that distributes the number of iterations depending on the texture of the regions to be reconstructed.
no code implementations • 7 Apr 2022 • Markus Jonscher, Jürgen Seiler, Daniela Lanz, Michael Schöberl, Michel Bätz, André Kaup
The main benefit of the proposed dynamic readout is that for each frame, different sampling points are available which is advantageous since this information can significantly enhance the reconstruction quality of the proposed reconstruction algorithm.
no code implementations • 17 Mar 2022 • Simon Grosche, Jürgen Seiler, André Kaup
Altogether, we are able to significantly increase the reconstruction quality by + 1. 01 dB compared to the state-of-the-art recursive reconstruction method using a fixed mask.
no code implementations • 3 Mar 2022 • Christian Herglotz, Jürgen Seiler, André Kaup, Arne Hendricks, Marc Reichenbach, Dietmar Fey
In recent years, due to a higher demand for portable devices, which provide restricted amounts of processing capacity and battery power, the need for energy and time efficient hard- and software solutions has increased.
no code implementations • 1 Mar 2022 • Simon Grosche, Kristian Fischer, Fabian Brand, Jürgen Seiler, André Kaup
Quarter sampling is a novel sensor concept that enables the acquisition of higher resolution images without increasing the number of pixels.
no code implementations • 1 Mar 2022 • Simon Grosche, Jürgen Seiler, André Kaup
Non-regular sampling can reduce aliasing at the expense of noise.
no code implementations • 1 Mar 2022 • Simon Grosche, Jürgen Seiler, André Kaup
Even though image signals are typically acquired on a regular two dimensional grid, there exist many scenarios where non-regular sampling is possible.
1 code implementation • 28 Feb 2022 • Andy Regensky, Simon Grosche, Jürgen Seiler, André Kaup
Frequency Selective Reconstruction (FSR) is a state-of-the-art algorithm for solving diverse image reconstruction tasks, where a subset of pixel values in the image is missing.
no code implementations • 15 Dec 2021 • Fabian Brand, Jürgen Seiler, André Kaup
Motion compensated inter prediction is a common component of all video coders.
no code implementations • CVPR 2023 • Simon Grosche, Andy Regensky, Jürgen Seiler, André Kaup
Next, we investigate the reconstruction quality using tetromino pixels for the first time in literature.
no code implementations • 22 May 2016 • Huynh Van Luong, Jürgen Seiler, André Kaup, Søren Forchhammer
This two-level optimization leads the proposed reconstruction algorithm with multiple SI using adaptive weights (RAMSIA) to robustly exploit the multiple SIs with different qualities.
no code implementations • 26 Feb 2015 • Lan Shi, Christopher Soell, Andreas Baenisch, Robert Weigel, Jürgen Seiler, Thomas Ussmueller
As an example, an image restoration algorithm for reducing image noise is applied as image pre-processing in the analog domain.