☆ 4.7 Article

Discrete Wavelet Transform-Based Gaussian Mixture Model for Remote Sensing Image Compression

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Artificial Intelligence

Multi-stage image denoising with the wavelet transform

Chunwei Tian et al.

Summary: This paper proposes a multi-stage image denoising CNN with wavelet transform, using dynamic convolution, wavelet transform and enhancement, and residual block to improve denoising performance. Experimental results show that the proposed method outperforms popular denoising methods.

PATTERN RECOGNITION (2023)

Add to Collection

Article Engineering, Electrical & Electronic

Learned image compression with generalized octave convolution and cross-resolution parameter estimation

Haisheng Fu et al.

Summary: Image compression approaches based on deep learning have outperformed existing compression standards by utilizing context-adaptive entropy model and multi-resolution framework. The proposed method achieves better rate-distortion performance and faster decoding speed through factorization of latent representations and cross-resolution parameter estimation.

SIGNAL PROCESSING (2023)

Add to Collection

Article Engineering, Electrical & Electronic

Remote sensing image compression with long-range convolution and improved non-local attention model

Shao Xiang et al.

Summary: The author proposes a long-range convolution compression network (LR-CompNet) for remote sensing image compression. To capture long-range context information, a long-range convolution is first introduced, and a lightweight compression model is designed. An improved non-local attention model is also proposed to reduce computation complexity. Experimental results show that the proposed compression network achieves improved rate-distortion performance and significantly reduces time complexity compared to other methods.

SIGNAL PROCESSING (2023)

Add to Collection

Article Engineering, Electrical & Electronic

Causal Contextual Prediction for Learned Image Compression

Zongyu Guo et al.

Summary: In recent years, there has been impressive progress in the field of learned image compression. However, existing entropy models lack the ability to capture global spatial correlations among latent representations and cross-channel relationships. This paper proposes the concept of separate entropy coding, which leverages a serial decoding process for causal contextual entropy prediction. It also introduces a group-separated attention module to build more powerful transform networks. Experimental results show that the proposed image compression model outperforms standard codecs in terms of both PSNR and MS-SSIM.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Multi-scale spatial-spectral attention network for multispectral image compression based on variational autoencoder

Fanqiang Kong et al.

Summary: This paper proposes a Multi-Scale SpatialSpectral Attention Network (MSSSA-Net) based on variational autoencoder (VAE) for multispectral image compression. The network incorporates a neuroscience-based non-local attention module and a multi-scale spectral attention block to capture both spatial features and spectral correlation at different scales. Experimental results show that the MSSSA-Net outperforms classical algorithms and recent learnt models.

SIGNAL PROCESSING (2022)

Add to Collection

Article Environmental Sciences

Learned Hyperspectral Compression Using a Student's T Hyperprior

Yuanyuan Guo et al.

Summary: A trainable network architecture for hyperspectral compression tasks is proposed in this paper, considering the anisotropic characteristic of hyperspectral images and embedding an accurate entropy model using non-Gaussian prior knowledge and nonlinear transform. The proposed method shows superior rate-distortion performance by designing spatial-spectral blocks and a Student's T hyperprior to enhance entropy model flexibility.

REMOTE SENSING (2021)

Add to Collection

Article Geography, Physical

Symmetrical lattice generative adversarial network for remote sensing images compression

Shihui Zhao et al.

Summary: In this paper, a new symmetrical lattice generating adversarial network (SLGAN) for remote sensing images (RSIs) compression is proposed. SLGAN utilizes symmetric structure, cooperative learning algorithm, and enhanced Laplacian of gaussian loss to outperform other existing state-of-the-art methods. Experimental results on GF2 satellite's panchromatic images demonstrate the superior performance of SLGAN.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Checkerboard Context Model for Efficient Learned Image Compression

Dailan He et al.

Summary: The autoregressive context model proves effective in learned image compression, but the strict decoding process hinders parallelization. To address this issue, a parallelizable checkerboard context model is proposed, significantly improving computational efficiency by reorganizing the decoding order and achieving almost the same rate-distortion performance. This marks the first exploration in parallelization-friendly spatial context models for learned image compression.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Article Computer Science, Information Systems

Learned Multi-Resolution Variable-Rate Image Compression With Octave-Based Residual Blocks

Mohammad Akbari et al.

Summary: This paper proposes a new variable-rate image compression framework with the use of generalized octave convolutions and transposed convolutions. Experimental results show that the framework outperforms standard codecs in multi-rate learning.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

End-to-End Learnt Image Compression via Non-Local Attention Optimization and Improved Context Modeling

Tong Chen et al.

Summary: This research introduces an end-to-end learnt lossy image compression method that significantly improves compression efficiency through deep neural network structure and non-local attention optimization. The proposed model outperforms existing compression methods and supports reproducible research with publicly accessible materials.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

Add to Collection

Article Computer Science, Information Systems

iWave: CNN-Based Wavelet-Like Transform for Image Compression

Haichuan Ma et al.

IEEE TRANSACTIONS ON MULTIMEDIA (2020)

Add to Collection

Article Geochemistry & Geophysics

Effects of Compression on Remote Sensing Image Classification Based on Fractal Analysis

Zhenzhong Chen et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2019)

Add to Collection

Article Environmental Sciences

Hyperspectral Image Compression Using Vector Quantization, PCA and JPEG2000

Daniel Bascones et al.

REMOTE SENSING (2018)

Add to Collection

Article Geochemistry & Geophysics

Fast and Lightweight Rate Control for Onboard Predictive Coding of Hyperspectral Images

Diego Valsesia et al.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2017)

Add to Collection

Article Geochemistry & Geophysics

Spatial-Spectral Classification of Hyperspectral Images Using Discriminative Dictionary Designed by Learning Vector Quantization

Zhaowen Wang et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2014)

Add to Collection

Article Computer Science, Information Systems

Lossy-to-lossless 3D image coding through prior coefficient lookup tables

Frances Auli-Llinas et al.

INFORMATION SCIENCES (2013)

Add to Collection

Article Environmental Sciences

Performance impact of parameter tuning on the CCSDS-123 lossless multi- and hyperspectral image compression standard

Estanislau Auge et al.

JOURNAL OF APPLIED REMOTE SENSING (2013)

Add to Collection

Article Engineering, Electrical & Electronic

Objective assessment of the WebP image coding algorithm

Giaime Ginesu et al.

SIGNAL PROCESSING-IMAGE COMMUNICATION (2012)

Add to Collection

Article Remote Sensing

Effects of lossy compression on remote sensing image classification of forest areas

A. Zabala et al.

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION (2011)

Add to Collection

Article Remote Sensing

Effects of JPEG compression on image classification

WL Lau et al.

INTERNATIONAL JOURNAL OF REMOTE SENSING (2003)

Add to Collection

Article Geochemistry & Geophysics

Compression of multispectral images by three-dimensional SPIHT algorithm

PL Dragotti et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2000)

Add to Collection

© Peeref 2019-2024. All rights reserved.