Research map / Video / Video segmentation and tracking
Low-Light Video Enhancement with Synthetic Event Guidance
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use synthetic event guidance with EIFT and EGDB | Low-light video enhancement · SDSD | PSNR: 24.92 -> 25.81 | Helped |
| Use synthetic event guidance with EIFT and EGDB | Low-light video enhancement · Vimeo90K | LPIPS: 0.059 -> 0.038 | Helped |
| Use the proposed method rather than SDSDNet | Low-light video enhancement · SDSD | FID: 0.368 -> 0.370 | Hurt |
| Use the proposed method rather than SMOID | Low-light video enhancement · SDSD | Warping Error: 2.62 -> 2.61 | Helped |
| Replace EIFT with a concatenation-based UNet (ablation) | Full model · SDSD | PSNR: 25.81 -> 25.54 | Hurt |
| Remove cross-channel transform from EIFT (ablation) | Full model · SDSD | PSNR: 25.81 -> 25.46 | Hurt |
| Remove element-wise product from EIFT (ablation) | Full model · SDSD | PSNR: 25.81 -> 25.52 | Hurt |
| Remove event-based map generation and image-feature masking (ablation) | Full model · SDSD | PSNR: 25.81 -> 25.49 | Hurt |
| Remove the EGDB global branch (ablation) | Full model · SDSD | PSNR: 25.81 -> 25.34 | Hurt |
| Remove the EGDB local branch (ablation) | Full model · SDSD | PSNR: 25.81 -> 25.42 | Hurt |
| Replace event guidance with PCD and omit events (ablation) | Full model · SDSD | PSNR: 25.81 -> 24.27 | Hurt |
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 0.89)
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.85)
- Event-assisted Low-Light Video Object Segmentation (CVPR 2024 · similarity 0.84)
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.84)
- Latency Correction for Event-guided Deblurring and Frame Interpolation (CVPR 2024 · similarity 0.84)
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.84)
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.