DiffGF is a non-reference diffusion-based restoration method trained on a new Antarctic SLCANT dataset that fills gaps in Landsat 7 SLC-off imagery and supports downstream tasks like crevasse segmentation.
Diffusion Models Beat GANs on Image Synthesis,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Non-Reference Diffusion-Based Restoration Framework for Landsat 7 ETM+ SLC-off Imagery in Antarctica
DiffGF is a non-reference diffusion-based restoration method trained on a new Antarctic SLCANT dataset that fills gaps in Landsat 7 SLC-off imagery and supports downstream tasks like crevasse segmentation.