ESDiff performs few-shot color image inpainting by training a score-based diffusion model on channel-perturbed patches and iteratively applying inverse perturbation, low-rank, and data-consistency steps.
Learning invariant representation for unsupervised image restoration,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ESDiff: Encoding Strategy-inspired Diffusion Model with Few-shot Learning for Color Image Inpainting
ESDiff performs few-shot color image inpainting by training a score-based diffusion model on channel-perturbed patches and iteratively applying inverse perturbation, low-rank, and data-consistency steps.