AI Paper Atlas

Research map / Video / Video segmentation and tracking

Low-Light Image Enhancement Using Event-Based Illumination Estimation

Lei Sun, Yuhan Bao, Jiajun Zhai, Jingyun Liang, Yulun Zhang, Kaiwei Wang, Danda Pani Paudel, Luc Van Gool

ICCV 2025 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 17 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 temporal-mapping events as input (ablation)Retinex LLIE pipeline · LOL-v1PSNR: 16.98 -> 26.96Improved
add the T2I module (ablation)event LLIE pipeline · LOL-v1PSNR: 26.96 -> 27.25Improved
add low-light degradation model (LLDM) to denoiser training (ablation)T2I module · LOL-v1PSNR: 27.25 -> 27.83Improved
add LLDM when cross-attention fusion is used (ablation)full model · LOL-v1PSNR: 28.45 -> 28.60Improved
add illumination via simple add fusion in reflectance enhancement (ablation)event LLIE with LLDM · LOL-v1PSNR: 27.83 -> 28.13Improved
use cross-modal attention instead of add fusion (ablation)IRE module · LOL-v1PSNR: 28.13 -> 28.60Improved
use cross-modal attention instead of concatenation fusion (ablation)IRE module · LOL-v1PSNR: 28.01 -> 28.60Improved
use cross-modal attention instead of multiply fusion (ablation)IRE module · LOL-v1PSNR: 27.98 -> 28.60Improved
use temporal-mapping events for illumination instead of image-only RetinexRetinexformer vs ours · LOL-v1PSNR: 25.16 -> 28.60Improved
use temporal-mapping events instead of motion eventsEvLight vs ours · SDSD-inPSNR: 28.52 -> 33.65Improved
use temporal-mapping events instead of motion eventsEvLight vs ours · Real-world dataset (60 scenes, exposure-fusion reference)PIQE: 20.45 -> 9.41Improved
add motion events to image-only LLIE (EvLight vs best image-only)EvLight · LOL/SDSDSSIM: 0.017Mixed

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