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
Visual JND: A Perceptual Measurement in Video Coding
2019
IEEE Access
Preserved Fulltext
Next, we introduce the applications of JND models in the perceptual quality evaluation and video compression coding, especially in applying machine-learning techniques to JND prediction. ...
INDEX TERMS Just noticeable difference (JND), human visual system (HVS), machine learning, perceptual measurement, video coding. ...
In psychology, the concept of just noticeable difference (JND) was presented. JND determines how accurate human sense are. ...
doi:10.1109/access.2019.2901342
fatcat:y3o67i3h75cq5nd3gaa7orsynq
Deep Local and Global Spatiotemporal Feature Aggregation for Blind Video Quality Assessment
[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.
Then, the feature aggregation is conducted by the regression model to predict the perceptual video quality. ...
In recent years, deep learning has achieved promising success for multimedia quality assessment, especially for image quality assessment (IQA). ...
[8] , the algorithm for video quality assessment via analysis of spatial and spatiotemporal slices (ViS3) [3] , the just noticeable difference-based video quality (JVQ) index [9] , etc. ...
arXiv:2009.03411v1
fatcat:3qxvr5izm5cdzl6qgcnbg727iq
A Survey on Perceptually Optimized Video Coding
[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
Secondly, recent advances on visual factors, computational perceptual models and quality assessment models are presented. ...
However, the data amount of videos increases exponentially, which requires high efficiency video compression for storage and network transmission. ...
[46] proposed learning-based Just-Noticeable-Quantization-Distortion (JNQD) models, LR-JNQD and CNN-JNQD, for perceptual video coding, which were able to adjust JND levels according to quantization ...
arXiv:2112.12284v2
fatcat:epphkkngbbdpreaxqkekssufli
2020 Index IEEE Transactions on Broadcasting Vol. 66
2020
IEEE transactions on broadcasting
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.
Zhang, L., Wu, Y., and Li, W., Using NOMA for Enabling Broadcast/Unicast Convergence in 5G Networks; TBC June 2020 503-514 ...
., and Zhao, W., Future 5G mmWave TV Service With Fast List Decoding of Polar Codes; TBC June 2020 525-533 Hou, J., Wang, W., Zhang, Y., and Liu, X Iradier, E., Montalban, J., Fanari, L., Angueira, P., ...
., +, TBC June 2020 579-588 Visual databases Just Noticeable Difference Level Prediction for Perceptual Image Compression. ...
doi:10.1109/tbc.2021.3055975
fatcat:4tbvfkcodrgxbput2p7rpem2na
A Framework to Map VMAF with the Probability of Just Noticeable Difference between Video Encoding Recipes
[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
Just Noticeable Difference (JND) model developed based on Human Vision System (HVS) through subjective studies is valuable for many multimedia use cases. ...
Nevertheless, recent state-of-the-art deep learning based JND prediction model relies on large-scale JND ground truth that is expensive and time consuming to collect. ...
Specifically, large-scale JND datasets are necessary for deep learning-based method for SUR prediction [8] - [10] . (2) these SUR/JND models are not codec agnostic. ...
arXiv:2205.07565v2
fatcat:tabc6ccgvnbylm6vabq2q56vbm
Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling
[article]
2024
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 2023; 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:
2023 pre-print arXiv:2211.06797v2 fatcat:jxxcxdyiyfezpigrsnod4ai4a4Other Versions
We then propose an SMR prediction model based on the correlation between deep feature differences and SMR. ...
To overcome these limitations, this paper introduces Satisfied Machine Ratio (SMR), a metric that statistically evaluates the perceptual quality of compressed images and videos for machines by aggregating ...
ACKNOWLEDGMENTS This work was supported in part by the National Natural Science Foundation of China under grant 62072008 and U20A20184, and the High Performance Computing Platform of Peking University, ...
arXiv:2211.06797v3
fatcat:cxwvppubfvfozmjkhu6oknen54
DVC-P: Deep Video Compression with Perceptual Optimizations
[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
Recent years have witnessed the significant development of learning-based video compression methods, which aim at optimizing objective or perceptual quality and bit rates. ...
Our proposed DVC-P is based on Deep Video Compression (DVC) network, but improves it with perceptual optimizations. ...
[7] presented an adversarial learned video compression model based on a 3D autoencoder, which tends to eliminate blurred results under extreme video compression. ...
arXiv:2109.10849v2
fatcat:yybw353jm5cxhet3kgjczuxddy
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
2018
2018 IEEE/CVF Conference on 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 2019; you can also visit the original URL.
The file type is application/pdf.
Acknowledgements This research was supported, in part, by grants from Berkeley Deep Drive, NSF IIS-1633310, and hardware donations by NVIDIA. ...
We thank members of the Berkeley AI Research Lab and Adobe Research for helpful discussions. We thank Alan Bovik for his insightful comments. ...
We also collect judgments on a different perceptual test, just noticeable differences (JND). • We show that deep features, trained on supervised, self-supervised, and unsupervised objectives alike, Table ...
doi:10.1109/cvpr.2018.00068
dblp:conf/cvpr/ZhangIESW18
fatcat:chyjzhkx7zgynfa2trjtzqfwam
Group Perceptual Quality Optimization for Multi-Channel Image Encoding Systems based on Adaptive Hyper Networks
2021
IEEE Access
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.
The GQO framework employs adaptive hyper network to predict the relationships between encoding parameters, transmitting resources, and perceptual qualities, i.e., just taking the pristine image as input ...
Images and short videos that produced by social networks surge in recent years. Image/Video encoders, such as JPEG and H.264, are indispensably involved to reduce the transmitting bandwidth. ...
and perceptual quality for each image channel by compressing the source into different versions using various encoding parameters and calculating the IQA prediction score for each of the distorted version ...
doi:10.1109/access.2021.3068483
fatcat:d3jzcefg6zcklnwv5zh6qk5e3m
A Perceptual Quality Metric for Video Frame Interpolation
[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.
Some recent deep learning-based perceptual quality metrics are shown more consistent with human judgments, but their performance on videos is compromised since they do not consider temporal information ...
In this paper, we present a dedicated perceptual quality metric for measuring video frame interpolation results. ...
It is a relatively small dataset and hence not suitable for training deep learning models. ...
arXiv:2210.01879v1
fatcat:ovt3ypo5gzderg3sxuz5jncx7m
Texture Segmentation Based Video Compression Using Convolutional Neural Networks
2018
IS&T International Symposium on Electronic Imaging Science and Technology
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.
There has been a growing interest in using different approaches to improve the coding efficiency of modern video codec in recent years as demand for web-based video consumption increases. ...
In this paper, we propose a model-based approach that uses texture analysis/synthesis to reconstruct blocks in texture regions of a video to achieve potential coding gains using the AV1 codec developed ...
As a result, deep learning techniques can be developed to perform texture segmentation and classification for the proposed model-based video coding. ...
doi:10.2352/issn.2470-1173.2018.2.vipc-155
fatcat:4wo6mehm5fblbegff2xsvqvgxi
Deep Learning-Based Video Coding: A Review and A Case Study
[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 2020; you can also visit the original URL.
The file type is application/pdf.
For deep schemes, pixel probability modeling and auto-encoder are the two approaches, that can be viewed as predictive coding scheme and transform coding scheme, respectively. ...
However, deep learning-based video coding remains in its infancy. ...
Ma, Haichuan Ma, Rui Song, Yefei Wang, Ning Yan, Kun Yang, Qingyu Zhang, Zhenxin Zhang, and Haitao Yang. ...
arXiv:1904.12462v1
fatcat:cgcmwylwnvd67abpl6wders5hy
ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression
[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.
Other Versions
By building on top of an existing deep image compression model, we are able to demonstrate a bitrate reduction of as much as 31% over MSE optimization, given a specified perceptual quality (VMAF) level ...
Here, we describe a different "proximal" approach to optimize image analysis networks against quantitative perceptual models. ...
ACKNOWLEDGMENT The authors thank Johannes Ballé for providing the training images. ...
arXiv:1910.08845v2
fatcat:mgg2mruvpbfr3pjxoqdwtqnnne
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
[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 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We systematically evaluate deep features across different architectures and tasks and compare them with classic metrics. ...
Recently, the deep learning community has found that features of the VGG network trained on ImageNet classification has been remarkably useful as a training loss for image synthesis. ...
Acknowledgements This research was supported, in part, by grants from Berkeley Deep Drive, NSF IIS-1633310, and hardware donations by NVIDIA. ...
arXiv:1801.03924v2
fatcat:v3rqyohjazb7hjcf4qrrueslmq
JND-Based Perceptual Optimization For Learned Image Compression
[article]
2023
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 2023; you can also visit the original URL.
The file type is application/pdf.
Other Versions
However, few of them take the Just Noticeable Difference (JND) characteristic of the Human Visual System (HVS) into account and optimize learned image compression towards perceptual quality. ...
To address this issue, a JND-based perceptual quality loss is proposed. ...
Recently, several learningbased JND models [9, 10, 11, 12, 13] further improved the accuracy of JND prediction, which provided new techniques and perspectives of perceptual image/video compression. ...
arXiv:2302.13092v2
fatcat:3iaxjeklbnhb5i7elogjgwesju
« Previous
Showing results 1 — 15 out of 2,810 results