BTC-Net: Efficient Bit-Level Tensor Data Compression Network for Hyperspectral Image

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Now it is still a challenge to compress high-throughput hyperspectral tensor image data on lightweight air-carried/spaceborne remote sensing systems, primarily due to insufficient computational resources and limited transmission bandwidth. To address this challenge, we propose a bit-level tensor data compression network (BTC-Net) that provides higher compression performance by leveraging a data-driven lightweight quantized neural encoder with two-stage bit compression. The BTC-Net achieves semantic near-lossless high reconstruction quality at low compression bit rates thanks to its optimized decoder, which uses a channelwise attention-based enhancement module to recover hyperspectral tensor data. Experimental results on different hyperspectral datasets show that the BTC-Net could achieve an extremely low compression bit rate of fewer than 0.04 bits per pixel per band (bpppb) with the state-of-the-art (SOTA) reconstruction performances. The demo of BTC-Net will be publicly available online at: https://github.com/zx20173646/BTCNet .
Funding Information
  • National Natural Science Foundation of China (61971072, 62001063, U2133211)
  • Graduate research and innovation foundation of Chongqing, China (CYB22068)
  • Fundamental Research Funds for the Central Universities (2023CDJXY-037)

This publication has 61 references indexed in Scilit: