Research Area:  Machine Learning

Abstract:

Spaceborne LiDAR systems are crucial for Earth observation but face hardware constraints, thus limiting resolution and data processing. We propose integrating compressed sensing and diffusion generative models to reconstruct high-resolution satellite LiDAR data within the Hyperheight Data Cube (HHDC) framework. Using a randomized illumination pattern in the imaging model, we achieve efficient sampling and compression, reducing the onboard computational load and optimizing data transmission. Diffusion models then reconstruct detailed HHDCs from sparse samples on Earth. To ensure reliability despite lossy compression, we analyze distortion metrics for derived products like Digital Terrain and Canopy Height Models and evaluate the 3D reconstruction accuracy in waveform space. We identify image quality assessment metrics—ADD_GSIM, DSS, HaarPSI, PSIM, SSIM4, CVSSI, MCSD, and MDSI—that strongly correlate with subjective quality in reconstructed forest landscapes. This work advances high-resolution Earth observation by combining efficient data handling with insights into LiDAR imaging fidelity.

Keywords:  
canopy height model (CHM)
compressive sampling
digital terrain model (DTM)
light detection and ranging (LiDAR)
machine learning (ML)
image quality assessment (IQA)
hyperheight data cube (HHDC)

Author(s) Name:  Andres Ramirez-Jaime,Gonzalo R. Arce ,Nestor Porras-Diaz ,Oleg Ieremeiev ,Andrii Rubel ,Vladimir Lukin ,Mateusz Kopytek,Piotr Lech ,Jaros?aw Fastowicz and Krzysztof Okarma

Publisher name:  MDPI

DOI:  10.3390/rs17071215

Volume Information:  Volume 17 ,(2025)

Paper Link:   https://www.mdpi.com/2072-4292/17/7/1215