A Non-Reference Diffusion-Based Restoration Framework for Landsat 7 ETM+ SLC-off Imagery in Antarctica

2026-05-20

AI Summary

This study addresses the challenge of repairing Landsat 7 ETM+ SLC-off imagery, which suffers from approximately 22% missing pixels due to the Scan Line Corrector failure. Conventional reference-based inpainting methods are ineffective in Antarctica owing to rapid surface changes that invalidate temporal assumptions. To overcome this, the authors propose DiffGF, the first reference-free, two-stage diffusion-based framework specifically designed for Antarctic SLC-off images: it first performs generative inpainting in a latent space and then refines the results in pixel space. The work introduces SLCANT, the first Antarctica-specific dataset for training and evaluating SLC-off restoration models. Comprehensive evaluations—quantitative, qualitative, and through downstream ice crevasse segmentation tasks—demonstrate DiffGF’s high-fidelity reconstruction capability, effectively unlocking the scientific potential of historical Landsat 7 data over Antarctica.

Abstract

Acquiring usable optical imagery in Antarctica is inherently challenging due to prolonged polar nights and frequent cloud cover. Landsat provides the longest and most continuous optical observations and constitutes one of the most important remote sensing data sources for Antarctic studies. However, the scan-line corrector (SLC) failure in 2003 resulted in approximately 22% missing pixels in Landsat 7 ETM+ SLC-off imagery, severely limiting its usability. Unlike many non-polar environments, Antarctic surfaces undergo rapid and substantial changes, which makes it difficult to obtain reliable reference imagery and reduces the applicability of conventional reference-based gap-filling methods. To address this challenge, we propose DiffGF, a non-reference diffusion-based framework for restoring Landsat 7 SLC-off imagery without requiring any external reference data. DiffGF adopts a two-stage design consisting of a latent-space diffusion process and a pixel-space refinement. A dedicated Antarctic dataset, SLCANT, is constructed for training and evaluation. Quantitative and qualitative results demonstrate that DiffGF restores Antarctic SLC-off imagery with high fidelity. Its practical value is further examined through a downstream crevasse segmentation application. The results suggest that DiffGF provides a useful approach for exploiting Landsat 7 SLC-off archives in Antarctica, enabling the extraction of valuable information from historical records and supporting related Antarctic studies.

Problem

• Landsat 7
• SLC-off
• Antarctica
• gap-filling
• missing pixels

Innovation

• diffusion model
• non-reference restoration
• Landsat 7 SLC-off
• Antarctic remote sensing
• gap-filling