AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Frozen CLIP Priors for Robust Self-Supervised Poisson Inverse Problems

Laura C. Diaz-Delgado, Emmanuel Martinez, Henry Arguello

ECCV 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add EI regularization to GR2R loss (ablation)Frozen CLIP unrolled solver · Poisson demosaicing BSDS500 (gamma=0.01)PSNR (dB): 27.45 -> 30.53Improved
add GR2R re-corruption loss to measurement consistency (ablation)Frozen CLIP unrolled solver · Poisson demosaicing BSDS500 (gamma=0.01)PSNR (dB): 21.42 -> 27.45Improved
use GR2R+EI self loss instead of EI only (ablation)Frozen CLIP unrolled solver · Poisson demosaicing BSDS500 (gamma=0.01)PSNR (dB): 28.41 -> 30.53Improved
use self loss instead of REI (ablation)Frozen CLIP unrolled solver · Poisson demosaicing BSDS500 (gamma=0.01)PSNR (dB): 30.31 -> 30.53Improved
use frozen pretrained CLIP encoder instead of DnCNN backbone (ablation)Unrolled solver with L_self · Poisson demosaicing BSDS500 (gamma=0.01)PSNR (dB): 29.90 -> 30.53Improved
use frozen CLIP instead of DRUNet backbone (ablation)Unrolled solver with L_self · Poisson demosaicing BSDS500 (gamma=0.01)PSNR (dB): 29.82 -> 30.53Improved
add pretraining to DnCNN backbone (ablation)DnCNN + L_self · Poisson demosaicing BSDS500 (gamma=0.01)PSNR (dB): 29.90 -> 29.73Hurt
add pretraining to DRUNet backbone (ablation)DRUNet + L_self · Poisson demosaicing BSDS500 (gamma=0.01)PSNR (dB): 29.82 -> 30.00Improved
use pretrained CLIP decoder rather than untrained CLIP with supervised loss (ablation)Frozen CLIP · Poisson demosaicing BSDS500 (gamma=0.01)PSNR (dB): 21.91 -> 30.75Improved
use supervised loss instead of self-supervised lossFrozen CLIP solver · Poisson demosaicing BSDS500 (gamma=0.01)PSNR (dB): 30.53 -> 30.75Improved
replace GSPnP with Ours (Self) at severe noiseGSPnP · Poisson demosaicing BSDS500 (gamma=0.05)PSNR (dB): 26.50 -> 26.98Improved
replace RAM with Ours (Self) at mild noiseRAM · Poisson demosaicing BSDS500 (gamma=0.01)PSNR (dB): 30.46 -> 30.53Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy