Research map / Image generation / Image restoration
Zero-Reference Joint Low-Light Enhancement and Deblurring via Visual Autoregressive Modeling with VLM-Derived Modulation
Wei Dong, Han Zhou, Junwei Lin, Jun Chen
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 |
|---|---|---|---|
| unsupervised VAR-LIDE instead of cascaded LLIE+deblurring pipelines | joint low-light enhancement and deblurring · LOLBlur | PSNR: 18.16 (best cascade) -> 23.39 | Improved |
| VAR-LIDE vs unsupervised joint methods | VAR-LIDE · LOLBlur | PSNR: 20.22 (FourierDiff) -> 23.39 | Improved |
| unsupervised VAR-LIDE vs supervised joint methods | VAR-LIDE · LOLBlur | PSNR: 23.39 vs 26.14 (DarkIR-L), 26.42 (LIEDNet-L) | Hurt |
| VAR-LIDE perceptual quality vs supervised methods | VAR-LIDE · LOLBlur | NIQE: 5.15 (DarkIR-L) -> 4.80 | Improved |
| VAR-LIDE cross-dataset generalization vs unsupervised baselines | VAR-LIDE · Real-LOLBlur | MUSIQ: 32.01 (FourierDiff) -> 47.53 | Improved |
| VAR-LIDE vs supervised methods on real data | VAR-LIDE · Real-LOLBlur | NIQE: 5.16 vs 4.90 (DarkIR-L), 4.92 (JUDE) | Mixed |
| replace fixed-iteration Zero-DCE conditioning with VLM-adaptive curve truncation (VICM) (ablation) | VARSR backbone · LOLBlur qualitative | visual quality | Improved |
| add SF-RoPE and VGPM on top of VICM with vanilla RoPE (ablation) | VAR-LIDE · LOLBlur qualitative | visual quality | Improved |
Closest papers by meaning
- Zero-Reference Low-Light Enhancement via Physical Quadruple Priors (CVPR 2024 · similarity 0.88)
- Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring (CVPR 2024 · similarity 0.87)
- Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios (ICLR 2025 · similarity 0.86)
- VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebook (AAAI 2024 · similarity 0.86)
- AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement (AAAI 2025 · similarity 0.86)
- Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement (NeurIPS 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.
