Research map / Vision-language and multimodal / Cross-modal learning
AnyMod-LLVE: Low-Light Video Enhancement with Modality-Agnostic Inference
Hangfeng Liang, Yutao Hu, Yanhan Hu, Xiaohan Wu, Wenqi Shao, Ying Fu
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 multimodal pretraining (100% vs 0%) (ablation) | AMNet · DID (RGB-only) | PSNR: 29.78 -> 31.57 | Improved |
| add multimodal pretraining (100% vs 0%) (ablation) | AMNet · SDSD-Indoor (RGB-only) | PSNR: 27.96 -> 29.03 | Improved |
| add multimodal pretraining (100% vs 0%) (ablation) | AMNet · SDSD-Outdoor (RGB-only) | PSNR: 26.07 -> 26.37 | Improved |
| scale pretraining data 0% to 100% (ablation) | AMNet · DID | L2(Event): 0.328 -> 0.289 | Improved |
| add IADS and FBS together to baseline translator (ablation) | AMNet · DID (RGB-only) | PSNR: 29.85 -> 31.57 | Improved |
| add IADS alone (ablation) | AMNet · DID (RGB-only) | PSNR: 29.85 -> 30.30 | Improved |
| add FBS alone (ablation) | AMNet · DID (RGB-only) | PSNR: 29.85 -> 30.95 | Improved |
| add IADS to FBS (ablation) | AMNet · SDSD-Indoor (RGB-only) | PSNR: 29.20 -> 29.03 | Hurt |
| add IADS alone (ablation) | AMNet · SDSD-Outdoor (RGB-only) | SSIM: 0.81 -> 0.84 | Improved |
| use RGB-only AMNet instead of STCD | STCD · DID | PSNR: 30.10 -> 31.57 | Improved |
| use RGB-only AMNet instead of EvLight++ which uses events | EvLight++ · SDE-Indoor | PSNR: 22.67 -> 23.04 | Improved |
| add event stream at inference | AMNet · SDE-Indoor | PSNR: 23.04 -> 23.22 | Improved |
Closest papers by meaning
- Event-Guided Consistent Video Enhancement with Modality-Adaptive Diffusion Pipeline (NeurIPS 2025 · similarity 0.91)
- Low-Light Video Enhancement with Synthetic Event Guidance (AAAI 2023 · similarity 0.89)
- Context-Aware Multimodal Pretraining (CVPR 2025 · similarity 0.86)
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.85)
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.85)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.85)
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.
