2023/04/25 · We propose a coupled compression generation network (CCGN) that reconstructs the image content and detailed textures separately and fuses them.

Therefore, we propose a coupled compression generation network (CCGN) that reconstructs the image content and detailed textures separately and fuses them ...

We propose a remote-sensing image compression framework at extremely low bitrates based on a coupled compression generation network (CCGN). To comprehensively.

NASA/ADS · A Coupled Compression Generation Network for Remote-Sensing Images at Extremely Low Bitrates.

2024/07/03 · Studies from Shenyang Aerospace University Have Provided New Data on Technology (A Coupled Compression Generation Network for Remote-sensing ...

A novel network called CompressNet is proposed which augments a Stacked Autoencoder with a Switch Prediction Network (SAE-SPN) which helps in the ...

2024/09/03 · MAGC employs a two-stage pipeline to compress and decompress RS images at extremely low bitrates. The first stage maps an image into a latent ...

Deep neural networks based on hyper-encoders play a critical role in estimating prior distributions in remote sensing image compression issues.

2024/07/17 · Most of these methods focus on enhancing the coding capability of the compression network and improving entropy model prediction accuracy.

However, few studies have been conducted on extremely low-bit compression for the remote sensing field. We find that a single GAN tends to generate visually ...