AI Paper Atlas

Research map / Image generation / Super-resolution

Seeing Through the Rain: Resolving High-Frequency Conflicts in Deraining and Super-Resolution via Diffusion Guidance

Wenjie Li, Jinglei Shi, Jin Han, Heng Guo, Zhanyu Ma

AAAI 2026 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 7 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 diffusion-learned latent priors (ablation)DHGM · RaindropPSNR: 25.41 -> 26.05Improved
learn priors with diffusion instead of CNN encoder (ablation)DHGM · RaindropPSNR: 25.63 -> 26.05Improved
estimate priors in 1D latent space instead of feature maps (ablation)DHGM diffusion · RaindropPSNR: 24.73 -> 26.05Improved
add guided filter (MR) (ablation)DHGM · RaindropPSNR: 26.48 -> 26.82Improved
add high-pass filter (TC) (ablation)DHGM · RaindropPSNR: 26.51 -> 26.82Improved
add both guided and high-pass filters (ablation)DHGM · RaindropPSNR: 26.11 -> 26.82Improved
add cross-attention for feature fusion (ablation)DHGM · RaindropPSNR: 26.73 -> 26.82Improved
joint DHGM vs cascading deraining and SRDHGM · RainDS-Syn-Rain (x2)PSNR: 27.23 -> 31.28Improved
joint DHGM vs best fine-tuned baselineDHGM · RainDS-Syn-Rain (x2)PSNR: 29.94 -> 31.28Improved
DHGM vs cascades on real raindrop setDHGM · Raindrop (x2)DISTS: 0.1378 vs 0.1385 (SR->Histoformer)Mixed

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