Problem
Research questions and friction points this paper is trying to address.
Poisson noise
self-supervised learning
inverse problems
photon-limited settings
data consistency
Frozen CLIP Priors for Robust Self-Supervised Poisson Inverse Problems
🤖 AI Summary
本文提出一种基于冻结CLIP先验的自监督方法，通过解耦数据一致性更新和轻量级解码器实现Poisson逆问题的鲁棒求解。
📝 Abstract
Self-supervised learning for imaging inverse problems is increasingly important in photon-limited settings, where acquiring clean ground truth is impractical and reconstruction must remain stable under dataset and acquisition shifts. This challenge is amplified under Poisson noise, whose signal-dependent statistics interact with sampling operators (e.g., CFA mosaicing). Meanwhile, foundation vision encoders trained at web scale offer distortion-invariant, content-related representations that generalize well across domains, suggesting a promising route to build priors that transfer beyond the training distribution without expensive fine-tuning. This paper proposes an ADMM-inspired unrolled plug-and-play solver for Poisson inverse problems that decouples a closed-form data-consistency update from a parameter-efficient prior. The prior is implemented as a lightweight decoder operating on frozen CLIP RN50 dense multi-scale features, adapting foundation representations with less trainable parameters. For self-supervision, the method integrates GR2R measurement-domain re-corruption with an Equivariant Imaging regularizer via virtual acquisitions. Experiments on Poisson CFA demosaicing and deblurring show competitive quality, improved robustness under shifts, and self-supervised performance approaching supervised training.
Innovation
Methods, ideas, or system contributions that make the work stand out.
ADMM-inspired unrolled plug-and-play solver
frozen CLIP RN50 dense multi-scale features
self-supervised learning
Poisson inverse problems
GR2R measurement-domain re-corruption
🔎 Similar Papers
No similar papers found.
