AI Paper Atlas

Research map / Image generation / Image restoration

Image Restoration via Primal Dual Hybrid Gradient and Flow Generative Model

Ji Li, Chao Wang

AAAI 2026 · Image generation › Image restoration · approach: Diffusion-based universal restoration · 1 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
use l1 fidelity instead of squared l2 with PDHG (ablation)PDHG flow PnP · AFHQ-Cat impulse noise, denoisingPSNR: 25.81 -> 37.94Improved
use l1 fidelity instead of l2 under Poisson noise (ablation)PDHG flow PnP · AFHQ-Cat Poisson noise, denoisingPSNR: 34.82 -> 29.31Hurt
replace squared l2 fidelity (PnP-FBS) with PDHG and l1 fidelity for impulse noiseflow-based PnP · FFHQ salt-and-pepper denoisingPSNR: 26.27 -> 40.27Improved
replace squared l2 fidelity with l2-norm fidelity for Poisson noiseflow-based PnP · FFHQ Poisson super-resolutionPSNR: 23.51 -> 29.96Improved
use PDHG fidelity framework under Gaussian noiseflow-based PnP · CelebA Gaussian noisePSNR: 31.95 -> 31.40 (denoising)No clear effect
use PnP-FBS gradient step rather than exact proximal step (PnP-HQS)squared-l2 PnP methods · FFHQ Poisson deblurringPSNR: 23.25 -> 28.45Improved
use one denoiser sample instead of five and avoid sequential approximationPDHG flow PnP · time to deblur one imageseconds: 25 -> 13 (vs PnP-FBS)Improved

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