Search Results for author:
Found 14 papers, 3 papers with code
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.
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.
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.
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.
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.
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.
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.
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.
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).
Saliency-Driven Versatile Video Coding for Neural Object Detection
Saliency-driven image and video coding for humans has gained importance in the recent past.
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.
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.
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.
