Zobrazeno 1 - 10
of 55
pro vyhledávání: '"Fischer, Kristian"'
Coding 4K data has become of vital interest in recent years, since the amount of 4K data is significantly increasing. We propose a coding chain with spatial down- and upscaling that combines the next-generation VVC codec with machine learning based s
Externí odkaz:
http://arxiv.org/abs/2308.06570
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 few symbols, while maintaining a high level of quality in more detaile
Externí odkaz:
http://arxiv.org/abs/2307.06102
Autor:
Herglotz, Christian, Och, Hannah, Meyer, Anna, Ramasubbu, Geetha, Eichermüller, Lena, Kränzler, Matthias, Brand, Fabian, Fischer, Kristian, Nguyen, Dat Thanh, Regensky, Andy, Kaup, André
In this paper, we provide an in-depth assessment on the Bj{\o}ntegaard 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. These metr
Externí odkaz:
http://arxiv.org/abs/2304.12852
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. By that, different areas of the image are coded at different qualities
Externí odkaz:
http://arxiv.org/abs/2302.13581
Publikováno v:
ICIP2022
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 certain information sinks, HEVC or VVC provide the possibility of freque
Externí odkaz:
http://arxiv.org/abs/2301.08533
Publikováno v:
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022
In the emerging field of video coding for machines, video datasets with pristine video quality and high-quality annotations are required for a comprehensive evaluation. However, existing video datasets with detailed annotations are severely limited i
Externí odkaz:
http://arxiv.org/abs/2205.06519
Publikováno v:
IEEE International Conference on Image Processing (ICIP) 2021
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. Several approaches already exist improving classic hybri
Externí odkaz:
http://arxiv.org/abs/2205.06511
Publikováno v:
IEEE International Symposium on Circuits and Systems (ISCAS) 2021
Deep neural object detection or segmentation networks are commonly trained with pristine, uncompressed data. However, in practical applications the input images are usually deteriorated by compression that is applied to efficiently transmit the data.
Externí odkaz:
http://arxiv.org/abs/2205.06501
Publikováno v:
IEEE ICASSP 2021
Saliency-driven image and video coding for humans has gained importance in the recent past. In this paper, we propose such a saliency-driven coding framework for the video coding for machines task using the latest video coding standard Versatile Vide
Externí odkaz:
http://arxiv.org/abs/2203.05944