AI Paper Atlas

Research map / Image generation / Image restoration

Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging

Zongliang Wu, Ruiying Lu, Ying Fu, Xin Yuan

ECCV 2024 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 27 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 the LDM-generated prior (diffusion) to the unfolding network (ablation)Ours-3stg · KAIST 10 scenesPSNR (dB): 37.61 -> 38.40Improved
feed clean HSI plus measurement (accurate guidance) to the latent encoder (ablation)Ours-3stg · KAIST 10 scenesPSNR (dB): 37.63 -> 38.40Improved
add gradient-correction GAP projection (ablation)Ours-3stg · KAIST 10 scenesPSNR (dB): 38.01 -> 38.40Improved
add spatial flow to the Trident Transformer (ablation)Ours-3stg · KAIST 10 scenesPSNR (dB): 37.66 -> 38.40Improved
add cross prior flow (cross-attention) instead of MLP layers (ablation)Ours-3stg · KAIST 10 scenesPSNR (dB): 37.89 -> 38.40Improved
use ACS-MHSA instead of basic MHSA in cross spectral flow (ablation)Ours-3stg · KAIST 10 scenesPSNR (dB) / FLOPs (G): 38.31 -> 38.40 PSNR; 36.80 -> 33.80 FLOPsImproved
increase latent prior length N from 16 to 256 (ablation)Ours-3stg · KAIST 10 scenesPSNR (dB): 38.40 -> 38.41 (FLOPs 33.80 -> 36.99)No clear effect
decrease latent prior length N from 16 to 4 (ablation)Ours-3stg · KAIST 10 scenesPSNR (dB): 38.40 -> 37.99Hurt
use proposed 9-stage model instead of RDLUF-MixS2-9stgdeep unfolding CASSI · KAIST 10 scenesFLOPs (G): 231.09 -> 88.68 (PSNR 39.57 -> 40.09)Improved
use proposed 9-stage model with diffusion instead of PADUT-12stgdeep unfolding CASSI · KAIST 10 scenesInference time (ms): 749.94 -> 1096.58Hurt

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