Research map / Video / Video segmentation and tracking
EvLight++: Low-Light Video Enhancement With an Event Camera: A Large-Scale Real-World Dataset, Novel Method, and More
Kanghao Chen, Guoqiang Liang, Yunfan Lu, Hangyu Li, Lin Wang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add events to Base model (ablation) | Base · SDE-in | PSNR: 21.35 -> 21.58 | Improved |
| add regional feature selection with all-ones matrix (ablation) | Base · SDE-in | PSNR: 21.58 -> 21.86 | Improved |
| add SNR guidance to regional feature selection (ablation) | Base · SDE-in | PSNR: 21.86 -> 22.44 | Improved |
| add image-regional feature selection (IRFS) (ablation) | Base · SDE-in | PSNR: 21.58 -> 21.92 | Improved |
| add event-regional feature selection (ERFS) (ablation) | Base · SDE-in | PSNR: 21.58 -> 22.18 | Improved |
| combine IRFS and ERFS (ablation) | Base · SDE-in | PSNR: 21.58 -> 22.44 | Improved |
| add ConvGRU temporal enhancement (ablation) | EvLight · SDE-in | PSNR*: 24.81 -> 25.65 | Improved |
| add temporal loss (ablation) | EvLight++ w/ ConvGRU · SDE-in | PSNR: 22.53 -> 22.67 | Improved |
| add temporal loss (ablation) | EvLight++ w/ ConvGRU · SDE-in | SSIM: 0.7684 -> 0.7791 | Improved |
| EvLight++ vs EvLight | EvLight · SDE-in | PSNR*: 24.81 -> 25.83 | Improved |
| EvLight++ vs EvLight | EvLight · SDSD-out | PSNR*: 30.30 -> 30.59 | Improved |
| enhance low-light input with EvLight++ before SegFormer | SegFormer · SDE-out | mAcc: 31.02 -> 30.70 | Hurt |
Later papers that compared with this method
2 later accepted papers report EvLight++ as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- CompEvent: Complex-valued Event-RGB Fusion for Low-light Video Enhancement and Deblurring (AAAI 2026 · better on 2 of 2 shared results)
- Low-Light Image Enhancement Using Event-Based Illumination Estimation (ICCV 2025 · better on 6 of 6 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
- Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach (CVPR 2024 · similarity 0.94)
- Coherent Event Guided Low-Light Video Enhancement (ICCV 2023 · similarity 0.91)
- Event-guided Unified Framework for Low-light Video Enhancement, Frame Interpolation, and Deblurring (ICCV 2025 · similarity 0.90)
- Event-assisted Low-Light Video Object Segmentation (CVPR 2024 · similarity 0.88)
- LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising (CVPR 2024 · similarity 0.87)
- EvFocus: Learning to Reconstruct Sharp Images from Out-of-Focus Event Streams (ICML 2025 · similarity 0.86)
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.
