Search Results for author:
Found 157 papers, 12 papers with code
Predicting the Energy Demand of a Hardware Video Decoder with Unknown Design Using Software Profiling
By using multiple video codecs for model training, we can predict the complexity of a HW decoder with an error of less than 8% and a minimum error of 4. 54% without using the corresponding HW decoder for training.
Analysis of Neural Video Compression Networks for 360-Degree Video Coding
As such, the state-of-the-art H. 266/VVC video coding standard integrates dedicated tools for 360-degree video, and considerable efforts have been put into designing 360-degree projection formats with improved compression efficiency.
A Comprehensive Review of Software and Hardware Energy Efficiency of Video Decoders
We find that AV1 is a sweet spot for optimized software decoder implementations with an additional energy demand of 16. 55% and bitrate savings of -43. 95% compared to VP9.
SLIC: A Learned Image Codec Using Structure and Color
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.
Encoding Time and Energy Model for SVT-AV1 based on Video Complexity
We propose an encoding time and energy model for SVT-AV1 based on empirical relations between the encoding time and video parameters as well as encoder configurations.
Enhanced Color Palette Modeling for Lossless Screen Content Compression
Compared to VVC and HEVC, the proposed method needs roughly 0. 44 and 0. 17 bits per pixel less on average for 24-bit screen content images, respectively.
Quantized Decoder in Learned Image Compression for Deterministic Reconstruction
Learned image compression has a problem of non-bit-exact reconstruction due to different calculations of floating point arithmetic on different devices.
Geometry-Corrected Geodesic Motion Modeling with Per-Frame Camera Motion for 360-Degree Video Compression
The large amounts of data associated with 360-degree video require highly effective compression techniques for efficient storage and distribution.
Color Agnostic Cross-Spectral Disparity Estimation
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.
A Guided Upsampling Network for Short Wave Infrared Images Using Graph Regularization
Thus, in this paper an upsampling method for SWIR images guided by a visible image is presented.
Extended Signaling Methods for Reduced Video Decoder Power Consumption Using Green Metadata
In this paper, we discuss one aspect of the latest MPEG standard edition on energy-efficient media consumption, also known as Green Metadata (ISO/IEC 232001-11), which is the interactive signaling for remote decoder-power reduction for peer-to-peer video conferencing.
Improving HEVC Encoding of Rendered Video Data Using True Motion Information
This paper shows that motion vectors representing the true motion of an object in a scene can be exploited to improve the encoding process of computer generated video sequences.
On Versatile Video Coding at UHD with Machine-Learning-Based Super-Resolution
Coding 4K data has become of vital interest in recent years, since the amount of 4K data is significantly increasing.
Video Decoding Energy Estimation Using Processor Events
In this paper, we show that processor events like instruction counts or cache misses can be used to accurately estimate the processing energy of software video decoders.
Conditional Residual Coding: A Remedy for Bottleneck Problems in Conditional Inter Frame Coding
Conditional coding is a new video coding paradigm enabled by neural-network-based compression.
Component-wise Power Estimation of Electrical Devices Using Thermal Imaging
This paper presents a novel method to estimate the power consumption of distinct active components on an electronic carrier board by using thermal imaging.
Power Modeling for Virtual Reality Video Playback Applications
This paper proposes a method to evaluate and model the power consumption of modern virtual reality playback and streaming applications on smartphones.
Power-Efficient Video Streaming on Mobile Devices Using Optimal Spatial Scaling
This paper derives optimal spatial scaling and rate control parameters for power-efficient wireless video streaming on portable devices.
Spatially-Adaptive Learning-Based Image Compression with Hierarchical Multi-Scale Latent Spaces
Current state-of-the-art neural-network-based image compression systems however use only one scale to transmit the latent space.
Encoder Complexity Control in SVT-AV1 by Speed-Adaptive Preset Switching
Current developments in video encoding technology lead to continuously improving compression performance but at the expense of increasingly higher computational demands.
Processing Energy Modeling for Neural Network Based Image Compression
Nowadays, the compression performance of neural-networkbased image compression algorithms outperforms state-of-the-art compression approaches such as JPEG or HEIC-based image compression.
Cross Spectral Image Reconstruction Using a Deep Guided Neural Network
Since only little cross spectral data is available for training, this neural network is highly regularized.
Improving Spherical Image Resampling through Viewport-Adaptivity
The conversion between different spherical image and video projection formats requires highly accurate resampling techniques in order to minimize the inevitable loss of information.
Motion Plane Adaptive Motion Modeling for Spherical Video Coding in H.266/VVC
Motion compensation is one of the key technologies enabling the high compression efficiency of modern video coding standards.
Video Decoding Energy Reduction Using Temporal-Domain Filtering
In this paper, we study decoding energy reduction opportunities using temporal-domain filtering and subsampling methods.
Learned Wavelet Video Coding using Motion Compensated Temporal Filtering
In our experiments, we compare our MCTF-based approach to learning-based conditional coders and traditional hybrid video coding.
Power Reduction Opportunities on End-User Devices in Quality-Steady Video Streaming
We find that based on the power consumption of the streaming sessions from the crowdsourcing dataset, devices could save more than 55% of power if all participants adhere to low-power settings.
Image Segmentation For Improved Lossless Screen Content Compression
For SCIs with natural regions, the proposed method achieves a bit-rate reduction of up to 11. 6% and 1. 52% with respect to HEVC and the previous version of the SCF.
Multiscale Augmented Normalizing Flows for Image Compression
Most learning-based image compression methods lack efficiency for high image quality due to their non-invertible design.
Improved Screen Content Coding in VVC Using Soft Context Formation
Screen content images typically contain a mix of natural and synthetic image parts.
The Bjøntegaard Bible -- Why your Way of Comparing Video Codecs May Be Wrong
Using additional supporting points inbetween standard points defined by parameters such as the quantization parameter, we assess the interpolation error of the Bj{\o}ntegaard-Delta (BD) calculus and its impact on the final BD value.
End-to-End Lidar-Camera Self-Calibration for Autonomous Vehicles
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).
A novel Cross-Component Context Model for End-to-End Wavelet Image Coding
In this paper, we explore a promising alternative approach for neural compression, with an autoencoder whose latent space represents a nonlinear wavelet decomposition.
Multispectral Image Compression Based on HEVC Using Pel-Recursive Inter-Band Prediction
In this paper, we propose a cross-spectral compression scheme for efficiently coding multispectral data based on HEVC.
Temporal Scalability of Dynamic Volume Data Using Mesh Compensated Wavelet Lifting
We propose an approach based on compensated wavelet lifting for obtaining a scalable representation of dynamic CT and MR volumes with very high quality.
Motion Estimation for Fisheye Video With an Application to Temporal Resolution Enhancement
Simulations and experiments are conducted on synthetic as well as real-world fisheye video sequences that are part of a data set created in the context of this paper.
Saliency-Driven Hierarchical Learned Image Coding for Machines
Areas without saliency are transmitted in latent spaces of lower spatial resolution in order to reduce the bitrate.
Scalable Lossless Coding of Dynamic Medical CT Data Using Motion Compensated Wavelet Lifting with Denoised Prediction and Update
To improve the visual quality of the lowpass subband, motion compensation can be incorporated into the lifting structure, but leads to inferior compression results at the same time.
Graph-Based Compensated Wavelet Lifting for Scalable Lossless Coding of Dynamic Medical Data
This work focuses on coding these adjacency matrices to make the graph-based motion compensation feasible for data compression.
Analysis of mesh-based motion compensation in wavelet lifting of dynamical 3-D+t CT data
Factorized in the lifting structure, the wavelet transform can easily be extended by arbitrary compensation methods.
Optimizing Rate-Distortion Performance of Motion Compensated Wavelet Lifting with Denoised Prediction and Update
Additionally, the similarity of the temporal base layer to the input sequence is preserved by the use of motion compensated temporal filtering.
Content Adaptive Wavelet Lifting for Scalable Lossless Video Coding
Wavelet-based video coding decomposes an input sequence into a lowpass and a highpass subband by filtering along the temporal axis.
Compression of Dynamic Medical CT Data Using Motion Compensated Wavelet Lifting with Denoised Update
For the lossless compression of dynamic 3-D+t volumes as produced by medical devices like Computed Tomography, various coding schemes can be applied.
Joint Geometry and Attribute Upsampling of Point Clouds Using Frequency-Selective Models with Overlapped Support
The attribute model is evaluated for the upsampled geometry positions.
Learning Frequency-Specific Quantization Scaling in VVC for Standard-Compliant Task-driven Image Coding
This is a well-known method for the human visual system, where scaling lists are derived from psycho-visual models.
Synthetic Hyperspectral Array Video Database with Applications to Cross-Spectral Reconstruction and Hyperspectral Video Coding
Two novel algorithms for two different applications are proposed to prove the diversity of applications that can be addressed by this novel database.
Improving mesh-based motion compensation by using edge adaptive graph-based compensated wavelet lifting for medical data sets
Medical applications like Computed Tomography (CT) or Magnetic Resonance Tomography (MRT) often require an efficient scalable representation of their huge output volumes in the further processing chain of medical routine.
Graph-based compensated wavelet lifting for 3-D+t medical CT data
An efficient scalable data representation is an important task especially in the medical area, e. g. for volumes from Computed Tomography (CT) or Magnetic Resonance Tomography (MRT), when a downscaled version of the original signal is needed.
Centroid adapted frequency selective extrapolation for reconstruction of lost image areas
To enlarge the test set for evaluation we further propose a method to generate arbitrarily shaped lost areas.
On the influence of clipping in lossless predictive and wavelet coding of noisy images
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.
Efficient lossless coding of highpass bands from block-based motion compensated wavelet lifting using JPEG 2000
Lossless image coding is a crucial task especially in the medical area, e. g., for volumes from Computed Tomography or Magnetic Resonance Tomography.
Analysis of displacement compensation methods for wavelet lifting of medical 3-D thorax CT volume data
A huge advantage of the wavelet transform in image and video compression is its scalability.
A Bit Stream Feature-Based Energy Estimator for HEVC Software Encoding
To this end, this paper presents an energy estimator that uses a subset of bit stream features to accurately estimate the energy consumption of the HEVC software encoding process.
3-D mesh compensated wavelet lifting for 3-D+t medical CT data
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.
Improving block-based compensated wavelet lifting by reconstructing unconnected pixels
This paper presents a new approach for improving the visual quality of the lowpass band of a compensated wavelet transform.
Device Interoperability for Learned Image Compression with Weights and Activations Quantization
Learning-based image compression has improved to a level where it can outperform traditional image codecs such as HEVC and VVC in terms of coding performance.
Optimization of Probability Distributions for Residual Coding of Screen Content
For each pixel to be encoded, a probability distribution is estimated based on the neighboring pattern and the occurrence of that pattern in the already encoded image.
Motion estimation for fisheye video sequences combining perspective projection with camera calibration information
Fisheye cameras prove a convenient means in surveillance and automotive applications as they provide a very wide field of view for capturing their surroundings.
Disparity estimation for fisheye images with an application to intermediate view synthesis
A straightforward approach to disparity estimation is block matching, which performs well with perspective data.
Coding of distortion-corrected fisheye video sequences using H.265/HEVC
Both methods make use of the latest video coding standard H. 265/HEVC and are compared with regard to objective as well as subjective video quality.
A data set providing synthetic and real-world fisheye video sequences
In video surveillance as well as automotive applications, so-called fisheye cameras are often employed to capture a very wide angle of view.
A hybrid motion estimation technique for fisheye video sequences based on equisolid re-projection
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.
Temporal error concealment for fisheye video sequences based on equisolid re-projection
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.
Jointly Resampling and Reconstructing Corrupted Images for Image Classification using Frequency-Selective Mesh-to-Grid Resampling
Mostly, the visual data is transmitted from the application side to a central server where the interpretation is conducted.
Frame Rate Up-Conversion Using Key Point Agnostic Frequency-Selective Mesh-to-Grid Resampling
High frame rates are desired in many fields of application.
Modeling of Energy Consumption and Streaming Video QoE using a Crowdsourcing Dataset
In this paper, we perform a first analysis of both end-user power efficiency and Quality of Experience of a video streaming service.
Domain Adaptation for Unknown Image Distortions in Instance Segmentation
However, in practice unknown distortion can lead to a domain gap between training and test data, impeding the performance of a machine vision system.
Sweet Streams are Made of This: The System Engineer's View on Energy Efficiency in Video Communications
We discuss all relevant energy sinks, highlight dependencies with quality-of-service variables as well as video properties, review energy consumption models for different devices from the literature, and aggregate these existing models into a global model for the overall energy consumption of a generic online video service.
Increasing the Accuracy of a Neural Network Using Frequency Selective Mesh-to-Grid Resampling
Using an extensive experimental evaluation we show that depending on the network architecture and classification task the application of FSMR during training aids the learning process.
Synthesizing Annotated Image and Video Data Using a Rendering-Based Pipeline for Improved License Plate Recognition
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.
3D Rendering Framework for Data Augmentation in Optical Character Recognition
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.
Quality Assurance of Weld Seams Using Laser Triangulation Imaging and Deep Neural Networks
Due to their special characteristics, the images must be pre-processed to enable the use of a deep neural network.
Extending Video Decoding Energy Models for 360° and HDR Video Formats in HEVC
We show that bit streams of the 360{\deg}, HDR, and fisheye video format can be estimated with a mean estimation error lower than 3. 88% if the setups have the same coding bit depth.
Matched Quality Evaluation of Temporally Downsampled Videos with Non-Integer Factors
Recent research has shown that temporal downsampling of high-frame-rate sequences can be exploited to improve the rate-distortion performance in video coding.
Advanced Design Space Exploration for Joint Energy and Quality Optimization for VVC
In recent studies, it could be shown that the energy demand of Versatile Video Coding (VVC) decoders can be twice as high as comparable High Efficiency Video Coding (HEVC) decoders.
Decoding Energy Modeling For Versatile Video Coding
In previous research, it was shown that the software decoding energy demand of High Efficiency Video Coding (HEVC) can be reduced by 15$\%$ by using a decoding-energy-rate-distortion optimization algorithm.
A Comparative Analysis of the Time and Energy Demand of Versatile Video Coding and High Efficiency Video Coding Reference Decoders
The evaluation shows that the energy demand of the VTM decoder is increased significantly compared to HM and that the increase depends on the coding configuration.
Spatio-spectral Image Reconstruction Using Non-local Filtering
In many image processing tasks it occurs that pixels or blocks of pixels are missing or lost in only some channels.
Optimal Filter Selection for Multispectral Object Classification Using Fast Binary Search
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.
Hyperspectral Image Reconstruction from Multispectral Images Using Non-Local Filtering
Therefore, multispectral cameras with wide-band filters are used, which are much cheaper and are often able to capture videos.
Structure-Preserving Spectral Reflectance Estimation using Guided Filtering
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.
Motion-Adapted Three-Dimensional Frequency Selective Extrapolation
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.
Spatio-temporal prediction in video coding by non-local means refined motion compensation
For this, the prediction is carried out in two steps.
Orthogonality Deficiency Compensation for Improved Frequency Selective Image Extrapolation
Therefore the signal from the known samples is iteratively projected onto different basis functions in order to generate a model of the signal.
Spatio-temporal prediction in video coding by best approximation
Within the scope of this contribution we propose a novel efficient spatio-temporal prediction algorithm for video coding.
Optimized processing order for 3D hole filling in video sequences using frequency selective extrapolation
A problem often arising in video communication is the reconstruction of missing or distorted areas in a video sequence.
Multiple Selection Extrapolation for Improved Spatial Error Concealment
This contribution introduces a novel signal extrapolation algorithm and its application to image error concealment.
Adaptive joint spatio-temporal error concealment for video communication
In the past years, video communication has found its application in an increasing number of environments.
Adaptive frequency prior for frequency selective reconstruction of images from non-regular subsampling
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.
Spatio-temporal error concealment in video by denoised temporal extrapolation refinement
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.
Spatio-temporal prediction in video coding by spatially refined motion compensation
The purpose of this contribution is to introduce a new method of signal prediction in video coding.
Content-Adaptive Motion Compensated Frequency Selective Extrapolation for Error Concealment in Video Communication
To cope with this, error concealment can be applied on the distorted data at the receiver.
Modeling the HEVC Encoding Energy Using the Encoder Processing Time
The global significance of energy consumption of video communication renders research on the energy need of video coding an important task.
Multiple Selection Approximation for Improved Spatio-Temporal Prediction in Video Coding
In this contribution, a novel spatio-temporal prediction algorithm for video coding is introduced.
Fast orthogonality deficiency compensation for improved frequency selective image extrapolation
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.
Reusing the H.264/AVC deblocking filter for efficient spatio-temporal prediction in video coding
The prediction step is a very important part of hybrid video codecs for effectively compressing video sequences.
Distributed Parallel Image Signal Extrapolation Framework using Message Passing Interface
The proposed framework allows for the application of existing image signal extrapolation algorithms without the need to modify them for a parallel processing.
Motion Compensated Frequency Selective Extrapolation for Error Concealment in Video Coding
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.
Optimized and Parallelized Processing Order for Improved Frequency Selective Signal Extrapolation
In this contribution an optimized processing order is proposed for Frequency Selective Extrapolation, a powerful signal extrapolation algorithm.
Optimized Decoding-Energy-Aware Encoding in Practical VVC Implementations
We show that encoding using our proposed coding tool profiles, the decoding energy efficiency is improved by over 25% with a bit rate increase of less than 5% with respect to standard encoding.
Rate-Distortion Optimal Transform Coefficient Selection for Unoccupied Regions in Video-Based Point Cloud Compression
These savings are more than twice as high as savings obtained using competing methods from literature.
Denoising-based image reconstruction from pixels located at non-integer positions
Digital images are commonly represented as regular 2D arrays, so pixels are organized in form of a matrix addressed by integers.
Scalable Kernel-Based Minimum Mean Square Error Estimator for Accelerated Image Error Concealment
In this paper, we propose a novel scalable spatial error concealment algorithm that aims at obtaining high quality reconstructions with reduced computational burden.
Reliability-based Mesh-to-Grid Image Reconstruction
This paper presents a novel method for the reconstruction of images from samples located at non-integer positions, called mesh.
Frequency selective extrapolation with residual filtering for image error concealment
The purpose of signal extrapolation is to estimate unknown signal parts from known samples.
Evaluation of Video Coding for Machines without Ground Truth
To mitigate this problem, we propose an evaluation method based on pseudo ground-truth data from the field of semantic segmentation to the evaluation of video coding for machines.
Robust Deep Neural Object Detection and Segmentation for Automotive Driving Scenario with Compressed Image Data
Deep neural object detection or segmentation networks are commonly trained with pristine, uncompressed data.
Analysis of Neural Image Compression Networks for Machine-to-Machine Communication
Video and image coding for machines (VCM) is an emerging field that aims to develop compression methods resulting in optimal bitstreams when the decoded frames are analyzed by a neural network.
Fast Reconstruction of Three-Quarter Sampling Measurements Using Recurrent Local Joint Sparse Deconvolution and Extrapolation
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.
Frequency-Selective Geometry Upsampling of Point Clouds
The demand for high-resolution point clouds has increased throughout the last years.
Resampling Images to a Regular Grid from a Non-Regular Subset of Pixel Positions Using Frequency Selective Reconstruction
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.
Increasing Imaging Resolution by Non-Regular Sampling and Joint Sparse Deconvolution and Extrapolation
In this paper, we propose a novel image sensor layout which allows for the acquisition of images at a higher resolution and improved quality.
Motion Compensated Three-Dimensional Frequency Selective Extrapolation for Improved Error Concealment in Video Communication
The model generation is conducted by an enhanced version of Three-Dimensional Frequency Selective Extrapolation, an existing error concealment algorithm.
A Fast Algorithm for Selective Signal Extrapolation with Arbitrary Basis Functions
Within the scope of this contribution, a novel efficient solution for Selective Extrapolation is presented for utilization with arbitrary basis functions.
Complex-Valued Frequency Selective Extrapolation for Fast Image and Video Signal Extrapolation
Within the scope of this contribution, we introduce the complex-valued Frequency Selective Extrapolation for fast image and video signal extrapolation.
A Bitstream Feature Based Model for Video Decoding Energy Estimation
In this paper we show that a small amount of bit stream features can be used to accurately estimate the energy consumption of state-of-the-art software and hardware accelerated decoder implementations for four different video codecs.
Texture-Dependent Frequency Selective Reconstruction of Non-Regularly Sampled Images
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.
Dynamic Non-Regular Sampling Sensor Using Frequency Selective Reconstruction
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.
Recursive Frequency Selective Reconstruction of Non-Regularly Sampled Video Data
In this paper, a new recursive multi-frame reconstruction approach is proposed in order to further increase the reconstruction quality.
Reconstruction of images taken by a pair of non-regular sampling sensors using correlation based matching
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.
Reconstruction of Videos Taken by a Non-Regular Sampling Sensor
Recently, it has been shown that a high resolution image can be obtained without the usage of a high resolution sensor.
Reducing Randomness of Non-Regular Sampling Masks for Image Reconstruction
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.
Declipping of Speech Signals Using Frequency Selective Extrapolation
The reconstruction of clipped speech signals is an important task in audio signal processing to achieve an enhanced audio quality for further processing.
Automatic Registration of Images with Inconsistent Content Through Line-Support Region Segmentation and Geometrical Outlier Removal
This new approach is designed to address the problems associated with the registration of images with affine deformations and inconsistent content, such as remote sensing images with different spectral content or noise interference, or map images with inconsistent annotations.
RFVTM: A Recovery and Filtering Vertex Trichotomy Matching for Remote Sensing Image Registration
In this paper, a robust feature point matching algorithm called Recovery and Filtering Vertex Trichotomy Matching (RFVTM) is proposed to remove outliers and retain sufficient inliers for remote sensing images.
Frequency-Selective Mesh-to-Mesh Resampling for Color Upsampling of Point Clouds
Secondly, we propose to apply a novel Frequency-Selective Mesh-to-Mesh Resampling (FSMMR) technique for the interpolation of the points in 2D.
A Novel End-To-End Network for Reconstruction of Non-Regularly Sampled Image Data Using Locally Fully Connected Layers
Altogether, using a three-quarter sampling sensor with our novel neural network layout, the image quality in terms of PSNR for the Urban100 dataset can be increased by 2. 96 dB compared to the state-of-the-art approach.
Novel Consistency Check For Fast Recursive Reconstruction Of Non-Regularly Sampled Video Data
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.
Key Point Agnostic Frequency-Selective Mesh-to-Grid Image Resampling using Spectral Weighting
A state-of-the-art high quality model-based resampling technique is frequency-selective mesh-to-grid resampling which requires pre-estimation of key points.
On Intra Video Coding and In-loop Filtering for Neural Object Detection Networks
Classical video coding for satisfying humans as the final user is a widely investigated field of studies for visual content, and common video codecs are all optimized for the human visual system (HVS).
Video Coding for Machines with Feature-Based Rate-Distortion Optimization
In this paper, we propose a standard-compliant feature-based RDO (FRDO) that is designed to increase the coding performance, when the decoded frame is analyzed by a neural network in a video coding for machine scenario.
Saliency-Driven Versatile Video Coding for Neural Object Detection
Saliency-driven image and video coding for humans has gained importance in the recent past.
Estimation of Non-Functional Properties for Embedded Hardware with Application to Image Processing
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.
Modeling the Energy Consumption of HEVC Intra Decoding
Battery life is one of the major limitations to mobile device use, which makes research on energy efficient soft- and hardware an important task.
Joint Optimization of Rate, Distortion, and Decoding Energy for HEVC Intraframe Coding
This paper presents a novel algorithm that aims at minimizing the required decoding energy by exploiting a general energy model for HEVC-decoder solutions.
Estimating the HEVC Decoding Energy Using the Decoder Processing Time
This paper presents a method to accurately estimate the required decoding energy for a given HEVC software decoding solution.
Multi-Objective Design Space Exploration for the Optimization of the HEVC Mode Decision Process
Finding the best possible encoding decisions for compressing a video sequence is a highly complex problem.
Decoding-Energy-Rate-Distortion Optimization for Video Coding
Finally, measurements of the software decoding process for HEVC-coded bit streams are performed.
Design Techniques for Incremental Non-Regular Image Sampling Patterns
Even though image signals are typically acquired on a regular two dimensional grid, there exist many scenarios where non-regular sampling is possible.
Modeling the Energy Consumption of the HEVC Decoding Process
To show the modeling capabilities in general, we test the estimation performance for different decoding software and hardware solutions, where we find that the proposed model outperforms the models from literature by reaching frame-wise mean estimation errors of less than 7% for software and less than 15% for hardware based systems.
Iterative Optimization of Quarter Sampling Masks for Non-Regular Sampling Sensors
Non-regular sampling can reduce aliasing at the expense of noise.
Enhanced Image Reconstruction From Quarter Sampling Measurements Using An Adapted Very Deep Super Resolution Network
Quarter sampling is a novel sensor concept that enables the acquisition of higher resolution images without increasing the number of pixels.
A Novel Viewport-Adaptive Motion Compensation Technique for Fisheye Video
However, the approach does not consider the large field of view of fisheye lenses that requires the consideration of different motion planes in 3D space.
Real-Time Frequency Selective Reconstruction through Register-Based Argmax Calculation
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.
Beyond Bjøntegaard: Limits of Video Compression Performance Comparisons
For 20 years, the gold standard to evaluate the performance of video codecs is to calculate average differences between ratedistortion curves, also called the "Bj{\o}ntegaard Delta".
A Low-Parametric Model for Bit-Rate Estimation of VVC Residual Coding
There are many tasks within video compression which require fast bit rate estimation.
Motion-Plane-Adaptive Inter Prediction in 360-Degree Video Coding
Based on the known projection format of the video, MPA allows to perform inter prediction on different motion planes in 3D space instead of having to work on the - in theory arbitrarily mapped - 2D image representation directly.
Learning True Rate-Distortion-Optimization for End-To-End Image Compression
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 image compression.
Boosting Neural Image Compression for Machines Using Latent Space Masking
Compared to the standard VVC, 41. 4% of bitrate are saved by this method for Mask R-CNN as analysis network on the uncompressed Cityscapes dataset.
Generalized Difference Coder: A Novel Conditional Autoencoder Structure for Video Compression
Motion compensated inter prediction is a common component of all video coders.
Energy Efficient Video Decoding for VVC Using a Greedy Strategy Based Design Space Exploration
IP traffic has increased significantly in recent years, and it is expected that this progress will continue.
Image Super-Resolution Using T-Tetromino Pixels
Next, we investigate the reconstruction quality using tetromino pixels for the first time in literature.
Toward Bridging the Simulated-to-Real Gap: Benchmarking Super-Resolution on Real Data
One interesting result is that top-performing methods on simulated data may be surpassed by others on real data.
Online Decomposition of Compressive Streaming Data Using $n$-$\ell_1$ Cluster-Weighted Minimization
The proposed decomposition solves an $n$-$\ell_1$ cluster-weighted minimization to decompose a sequence of frames (or vectors), into sparse and low-rank components, from compressive measurements.
Benchmarking Super-Resolution Algorithms on Real Data
Therefore, current studies are either evaluated 1) on simulated data or 2) on real data without a pixel-wise ground truth.
Distributed Coding of Multiview Sparse Sources with Joint Recovery
In support of applications involving multiview sources in distributed object recognition using lightweight cameras, we propose a new method for the distributed coding of sparse sources as visual descriptor histograms extracted from multiview images.
Sparse Signal Reconstruction with Multiple Side Information using Adaptive Weights for Multiview Sources
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.
