AI Paper Atlas

Research map / Video / Video segmentation and tracking

Coherent Event Guided Low-Light Video Enhancement

Jinxiu Liang, Yixin Yang, Boyu Li, Peiqi Duan, Yong Xu, Boxin Shi

ICCV 2023 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 47 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 event camera data as a guide to low-light video enhancement (ablation)hybrid event-frame enhancement network · Synthetic data with more severe noisePSNR: 22.86 -> 23.98Improved
add global feature alignment of event features to frames (ablation)hybrid event-frame enhancement network · Synthetic data with more severe noisePSNR: 23.41 -> 23.98Improved
add pixelwise motion aggregation of event and frame flows (ablation)hybrid event-frame enhancement network · Synthetic data with more severe noisePSNR: 22.89 -> 23.98Improved
add temporal coherence propagation with flow-guided integration (ablation)hybrid event-frame enhancement network · Synthetic data with more severe noisePSNR: 23.67 -> 23.98Improved
add exposure parameter estimation (ablation)hybrid event-frame enhancement network · Synthetic data with more severe noisePSNR: 19.83 -> 23.98Improved
train with the proposed noise simulation (Poisson shot noise, JPEG) (ablation)hybrid event-frame enhancement network · Synthetic data with more severe noiseSSIM: 0.7290 -> 0.8369Improved
use events plus frames instead of frames only video enhancement (StableLLVE)low-light video enhancement · Synthetic low-light video dataset of [63]PSNR: 21.79 -> 22.81Improved
reconstruct video from events only (E2VID, DVS-Dark)event-only baselines · Synthetic low-light video dataset of [63]PSNR: 11.63 vs 22.81 (hybrid)Hurt

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