AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Unleashing the Potential of the Semantic Latent Space in Diffusion Models for Image Dehazing

Zizheng Yang, Hu Yu, Bing Li, Jinghao Zhang, Jie Huang, Feng Zhao

ECCV 2024 · Image generation › Autoregressive and latent generation · approach: Latent diffusion with learned tokenizers · 16 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 CIM (h-space content integration at t1) to a baseline (ablation)DiffLI2D · SOTS indoorPSNR: 36.65 -> 38.44Improved
add HAE (h-space haze guidance at t2) to a baseline (ablation)DiffLI2D · SOTS indoorPSNR: 36.65 -> 38.21Improved
use both CIM and HAE (ablation)DiffLI2D · SOTS indoorPSNR: 38.44 -> 40.33Improved
use diffusion h-space features instead of encoder features (Layer-E) (ablation)DiffLI2D · SOTS indoorPSNR: 36.52 -> 40.33Improved
use diffusion h-space features instead of decoder features (Layer-D) (ablation)DiffLI2D · SOTS indoorPSNR: 39.10 -> 40.33Improved
use h-space features of a diffusion model instead of VGG16 features (ablation)DiffLI2D · SOTS indoorPSNR: 27.83 -> 40.33Improved
use h-space features instead of ResNet50 features (ablation)DiffLI2D · SOTS indoorPSNR: 25.49 -> 40.33Improved
set t2 around 500 instead of 100 or 600 (ablation)DiffLI2D · SOTS indoorPSNR: +1.99dB vs t2=100; +2.07dB vs t2=600Improved
use very large time-steps (t1 or t2 = 1000) (ablation)DiffLI2D · SOTS indoorPSNRHurt
set t2 to 800 instead of 600 for low-light enhancement (ablation)DiffLI2D · LOLv1PSNR: 23.30 -> 21.48Hurt
apply DiffLI2D to low-light enhancementDiffLI2D · LOLv1PSNR: 20.61 -> 23.30 vs RestormerImproved
DiffLI2D vs Dehamer on NH-HAZEDiffLI2D · NH-HAZEPSNR: 20.29 vs 20.66Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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