Deep Image Compression with Latent Optimization and Piece-wise Quantization Approximation

Wu, Yuyang; Qi, Zhiyang; Zheng, Huiming; Tao, Lvfang; Gao, Wei

doi:10.1109/cvprw53098.2021.00219

Cited by 8 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) In terms of quantization: since discretization is nondifferentiable, this is a difficult and challenging problem for deep learning based gradient backpropagation algorithms [5]. Many methods [5,18,19] have been proposed to solve these problems. Uniform noise [5] is added to the training process to simulate the quantization process.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Global Priors With Anchored-Stripe Attention and Multiscale Convolution for Remote Sensing Image Compression

Zhang,

Hu,

Pan

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Compressing remote sensing images with high spatial and spectral resolution plays an important role in subsequent image processing and information acquisition. Accurate data modeling can help the entropy model to better estimate the entropy value. For better image recovery, it is necessary to make full use of the prior information contained in the latent information. To achieve global association and hierarchical modeling of latent elements, this paper proposes adding additional global anchored-stripe self-attention capturing global, local and interchannel dependencies. To enhance the feature extraction capabilities of the encoder and decoder, the multiscale attention module of depthwise convolution is used to increase the receptive field and nonlinear conversion process, ensuring that the network can retain more useful information. We evaluate the compression performance of the proposed method in terms of rate-distortion curves and running speed. Through comparative experiments on DOTA, LoveDA and UC-Merced datasets, it is that the proposed method has a faster running speed than the context model. It outperforms some traditional compression methods such as BPG, WebP, JPEG2000, and state-of-the-art deep learning-based methods in terms of PSNR and MS-SSIM. In terms of perceptual quality, adding perceptual loss reduces the smooth image blurring due to MSE loss, and the proposed method has better image perceptual quality under the approximate BPP.

show abstract

mentioning

confidence: 99%

“…The quantization is replaced by a smoothing approximation and a scaling method [20] to obtain different rates. A nonlinear segmentation function [19] is used to approximate the quantization process.…”

mentioning

confidence: 99%

Global Priors With Anchored-Stripe Attention and Multiscale Convolution for Remote Sensing Image Compression

Zhang,

Hu,

Pan

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…After that, the process of object tracking 54,55 is adopted to continuously estimate the state of the object in subsequent video sequences based on the given position and size of the object in the initial frame. Moreover, AI-enabled computer vision technology [56][57][58][59][60] is evolving rapidly, which can solve more complicated problems and serve as an aid to intelligent communications.…”

mentioning

confidence: 99%

Intelligent metasurface system for automatic tracking of moving targets and wireless communications based on computer vision

Zhang

et al. 2023

Nat Commun

View full text Add to dashboard Cite

The fifth-generation (5G) wireless communication has an urgent need for target tracking. Digital programmable metasurface (DPM) may offer an intelligent and efficient solution owing to its powerful and flexible controls of electromagnetic waves and advantages of lower cost, less complexity and smaller size than the traditional antenna array. Here, we report an intelligent metasurface system to perform target tracking and wireless communications, in which computer vision integrated with a convolutional neural network (CNN) is used to automatically detect the locations of moving targets, and the dual-polarized DPM integrated with a pre-trained artificial neural network (ANN) serves to realize the smart beam tracking and wireless communications. Three groups of experiments are conducted for demonstrating the intelligent system: detection and identification of moving targets, detection of radio-frequency signals, and real-time wireless communications. The proposed method sets the stage for an integrated implementation of target identification, radio environment tracking, and wireless communications. This strategy opens up an avenue for intelligent wireless networks and self-adaptive systems.

show abstract

MPEG AI-Based 3D Graphics Coding Standard

Li,

Gao,

Gao

2024

Point Cloud Compression

View full text Add to dashboard Cite

Deep Image Compression with Latent Optimization and Piece-wise Quantization Approximation

Cited by 8 publications

References 9 publications

Global Priors With Anchored-Stripe Attention and Multiscale Convolution for Remote Sensing Image Compression

Global Priors With Anchored-Stripe Attention and Multiscale Convolution for Remote Sensing Image Compression

Intelligent metasurface system for automatic tracking of moving targets and wireless communications based on computer vision

MPEG AI-Based 3D Graphics Coding Standard

Contact Info

Product

Resources

About