Image Coding for Machines based on Non-Uniform Importance Allocation
In the Internet era, the explosive growth of media data processing poses significant
challenges for the research of Image Coding for Machines (ICM) in improving the efficiency …
challenges for the research of Image Coding for Machines (ICM) in improving the efficiency …
Scalable compression for machine and human vision tasks via multi-branch shared module
The existing image compression methods are mainly aimed at human perception tasks
instead of machine vision tasks. Rich features learned by the shallow and deep layers of pre …
instead of machine vision tasks. Rich features learned by the shallow and deep layers of pre …
Learned image compression via multiscale prior for machine recognition
Y Shi, L Shen, Q Wang - Journal of Electronic Imaging, 2023 - spiedigitallibrary.org
The conventional image compression framework is pixel fidelity-driven, which can generate
compressed images with considerable visual quality even at low bit rates. However, these …
compressed images with considerable visual quality even at low bit rates. However, these …
End-to-End Image Compression Through Machine Semantics
J Liu, C Zhang, W Ji - International Forum on Digital TV and Wireless …, 2023 - Springer
With the increasing demand for AI automated analysis, machine semantics have replaced
signals as a new focus in visual information compression. In this paper, we propose a novel …
signals as a new focus in visual information compression. In this paper, we propose a novel …
Visual Analysis Motivated Super-Resolution Model for Image Reconstruction
H Wang, J Xue, M Yang, Y Zhang - 2022 IEEE International …, 2022 - ieeexplore.ieee.org
This paper presents a concise end-to-end visual analysis motivated super-resolution model
VASR for image reconstruction. Compatible with the existing machine vision feature coding …
VASR for image reconstruction. Compatible with the existing machine vision feature coding …
An End-to-End Mutual Enhancement Network Toward Image Compression and Semantic Segmentation
Image compression is to compress image data without compromising human vision feeling.
However, the information loss through the image compression process may influence the …
However, the information loss through the image compression process may influence the …