A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
An extended hybrid image compression based on soft-to-hard quantification
2020
IEEE Access
Preserved Fulltext
The residual of the input image and the reconstructed image is encoded by the BPG codec as the enhancement layer. ...
including BPG in SSIM metric across a wide range of bit rates, when the images are coded in the RGB444 domain. ...
[4] combine deep learning and traditional standard coding to form a hybrid image coding framework for improving the compression performance. ...
doi:10.1109/access.2020.2994393
fatcat:3njlexiuzfbjxgsfjlrgmj7upi
Learned Block-based Hybrid Image Compression
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To tackle the above challenges, this paper provides a learned block-based hybrid image compression (LBHIC) framework. ...
learned image compression methods. ...
Traditional image codecs, such as JPEG [1] , BPG [2] , and VVC (intra) [3] , adopt a hybrid coding framework consisting of prediction, transformation, quantization, and entropy coding. ...
arXiv:2012.09550v4
fatcat:jjhcjhfo6zgcha3m626djuwude
Semantically Video Coding: Instill Static-Dynamic Clues into Structured Bitstream for AI Tasks
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Specifically, we introduce optical flow to encode continuous motion information and reduce cross-frame redundancy via a predictive coding architecture, then the optical flow and residual information are ...
Semantically Structured Image Coding (SSIC) framework makes the first attempt to enable decoding-free or partial-decoding image intelligent task analysis via a Semantically Structured Bitstream (SSB). ...
On the other hand, based on the learning-based coding schemes, Chen et al. [51] propose a learning based facial image compression (LFIC) framework with a novel regionally adaptive pooling (RAP) module ...
arXiv:2201.10162v2
fatcat:erjq25be3bbgzkled3bf2s34fi
Learning for Video Compression
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Although entropy coding and complex configurations are not employed in this paper, we still demonstrate superior performance compared with MPEG-2 and achieve comparable results with H.264 codec. ...
One key challenge to learning-based video compression is that motion predictive coding, a very effective tool for video compression, can hardly be trained into a neural network. ...
A. Codec-based Improvements Lossy image/video codecs, such as JPEG and High Efficiency Video Coding (HEVC) [12] , give a profound impact on image/video compression. ...
arXiv:1804.09869v1
fatcat:txjul47xdzfu5byqdopsbdfesm
Neural Data-Dependent Transform for Learned Image Compression
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
It is equivalent to a continuous online mode decision, like coding modes in the traditional codecs, to improve the coding efficiency based on the individual input image. ...
To explore this potential in the learned codec, we make the first attempt to build a neural data-dependent transform and introduce a continuous online mode decision mechanism to jointly optimize the coding ...
Key ideas with related formulations of image compression. (a) Previous learned image compression. (b) Hybrid coding framework. ...
arXiv:2203.04963v2
fatcat:u5csafeh2fb37i7xrg75wtcklu
Learning to Compress Videos without Computing Motion
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2009.14110v1 fatcat:v76vlyfp4zakrhazxyw2odgkqeOther Versions
In this paper, we propose a new deep learning video compression architecture that does not require motion estimation, which is the most expensive element of modern hybrid video compression codecs like ...
The DCU removes the need for motion estimation found in hybrid codecs, and is less expensive. ...
proposed an end-to-end video compression model (DVC) [21] which replaces each component of the traditional hybrid video codec with a deep learning model, which are jointly trained as a global hybrid ...
arXiv:2009.14110v2
fatcat:hm4qdgnz4fehvghdyyabcahf5e
A New Image Codec Paradigm for Human and Machine Uses
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Finally, the residual map between the original image and the predicted one is compressed with a lossy codec, used for high-quality image reconstruction. ...
To this end, a new image codec paradigm for both human and machine uses is proposed in this work. ...
Compared with the image codecs optimized for humans, image description coding for machines can support a variety of machine tasks with small bitstream. ...
arXiv:2112.10071v1
fatcat:ok7wsc2nnzbb5brlbymkfvgrfa
CNN-Optimized Image Compression with Uncertainty based Resource Allocation
2018
Computer Vision and Pattern Recognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Our approach is a hybrid image coder based on CNN-optimized in-loop filter and mode coding, with uncertainty based resource allocation for compressing the task images. ...
In this paper, we provide the description of our approach designed for participating the CVPR 2018 Challenge on Learned Image Compression (CLIC). ...
Our Image Compression Approach
Hybrid block-based image codec In the proposed approach, we develop our codec based on the JEM platform, i.e., Joint Exploration Model (JEM) 7.1 [1], which is the codec ...
dblp:conf/cvpr/ChenLLLPSWZZL18
fatcat:erxqlkw7fbbzbantydyck4ntim
Codec-Simulation Network for Joint Optimization of Video Coding With Pre- and Post-Processing
2021
IEEE Open Journal of Circuits and Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
When we use down-sampling and up-sampling as examples of pre-and post-processing of a video codec, the joint optimization of these two processing modules in a video coding system can result in 46.88% and ...
55.15% BD-rate reduction based on PSNR and SSIM compared with that without joint optimization. ...
A ResNet-based convolutional neural network with input of side information is developed as a simulator of traditional hybrid video codec. ...
doi:10.1109/ojcas.2021.3124243
fatcat:wjvtcsbqirctfl5aem6okhjfuq
Dynamically Expanded CNN Array for Video Coding
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Recently, there has been an interest in finding ways to apply techniques form the fast-progressing field of machine learning to further improve video coding. ...
The novelty of our approach is to train multiple different sets of network parameters, with each set corresponding to a specific, short segment of video. ...
Instead of using ML to form a hybrid video coding framework, some works propose an end-to-end framework for video compression, the performance of which can be on par with the commercial codecs. ...
arXiv:1905.04326v1
fatcat:suskad2bpze77gbeulb7hapsuq
Neural Inter-Frame Compression for Video Coding
2019
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
While there are many deep learning based approaches for single image compression, the field of end-to-end learned video coding has remained much less explored. ...
Therefore, in this work we present an inter-frame compression approach for neural video coding that can seamlessly build up on different existing neural image codecs. ...
They also rely on a hand-crafted block based hybrid structure [19] combining inter with intra frame predictions. ...
doi:10.1109/iccv.2019.00652
dblp:conf/iccv/DjelouahCSS19
fatcat:36gzffkhozcajadlx3spjg4x7q
CAESR: Conditional Autoencoder and Super-Resolution for Learned Spatial Scalability
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
2021
2021 International Conference on Visual Communications and Image Processing (VCIP)
unpublished
doi:10.1109/vcip53242.2021.9675351 fatcat:ruvcbtnuwza5vknqbqxbzp2c2u
doi:10.1109/vcip53242.2021.9675351 fatcat:ruvcbtnuwza5vknqbqxbzp2c2u
Our approach relies on conditional coding that learns the optimal mixture of the source and the upscaled BL image, enabling better performance than residual coding. ...
In this paper, we present CAESR, an hybrid learning-based coding approach for spatial scalability based on the versatile video coding (VVC) standard. ...
In this paper, we present CAESR, an hybrid layered approach that uses a downscaled representation of the input image, encoded using versatile video coding (VVC) as a BL codec and a deep conditional autoencoder ...
arXiv:2202.00416v1
fatcat:5ilwqyfulrbfvaavf3e7e2y3ja
Inpainting-based Video Compression in FullHD
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Compression methods based on inpainting are an evolving alternative to classical transform-based codecs for still images. ...
To compress residuals, we introduce a new highly efficient block-based variant of pseudodifferential inpainting. ...
With the residual we can correct remaining errors.
Fig. 2 : 2 Intermediate results for inter coding at a compression rate of roughly 100:1. The colour coding of the BOFF is adapted from [4] . ...
arXiv:2008.10273v3
fatcat:5ilqwsyghjal5n5mtcgfxlh67u
Learning End-to-End Lossy Image Compression: A Benchmark
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2002.03711v2 fatcat:uqqykyjd5bbz7dqvdxs3qvh4deOther Versions
With this survey, the main challenges of image compression methods are revealed, along with opportunities to address the related issues with recent advanced learning methods. ...
In this paper, we first conduct a comprehensive literature survey of learned image compression methods. ...
CONCLUSION In this paper, we conduct a systematic benchmark on existing methods for learned image compression. ...
arXiv:2002.03711v4
fatcat:47d2ybnvmbhvtjp3lxqkkvxjq4
Large-Scale Crowdsourcing Subjective Quality Evaluation of Learning-Based Image Coding
2021
2021 International Conference on Visual Communications and Image Processing (VCIP)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Moreover, one hybrid codec combining the Versatile Video Coding (VVC Intra) standard [14] with learning-based tools was proposed. ...
residual codec at an enhancement layer. ...
doi:10.1109/vcip53242.2021.9675314
fatcat:zicb4r7zyfgwhktskcokkitveu
« Previous
Showing results 1 — 15 out of 657 results