Research map / Image generation / Image restoration
Flare7K: A Phenomenological Nighttime Flare Removal Dataset
Yuekun Dai, Chongyi Li, Shangchen Zhou, Ruicheng Feng, Chen Change Loy
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 |
|---|---|---|---|
| train U-Net on Flare7K instead of Wu et al. flare data | U-Net · Real-world nighttime flare test | PSNR: 24.61 -> 26.11 | Improved |
| train U-Net on Flare7K instead of Wu et al. flare data | U-Net · Synthetic nighttime flare test | PSNR: 27.88 -> 29.07 | Improved |
| train U-Net on Flare7K instead of Wu et al. flare data | U-Net · Real-world nighttime flare test | LPIPS: 0.060 -> 0.055 | Improved |
| use Uformer instead of U-Net backbone on Flare7K | Flare7K training · Real-world nighttime flare test | PSNR: 26.11 -> 26.98 | Improved |
| use Uformer instead of U-Net backbone on Flare7K | Flare7K training · Synthetic nighttime flare test | PSNR: 29.07 -> 30.47 | Improved |
| use nighttime dehazing (Zhang) or enhancement (Sharma) off-the-shelf instead of Flare7K-trained model | input images · Real-world nighttime flare test | PSNR: 22.56 -> 21.02 (Zhang), 20.49 (Sharma) | Hurt |
| use reduced-parameter MPRNet and Restormer | Flare7K benchmark · Real-world nighttime flare test | PSNR: 26.14 and 26.28 vs U-Net 26.11 | No clear effect |
Closest papers by meaning
- Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond (TPAMI 2024 · similarity 0.98)
- FlareReal: A Real-Captured Paired Dataset for Nighttime Lens Flare Removal (NeurIPS 2026 · similarity 0.93)
- Disentangle Nighttime Lens Flares: Self-supervised Generation-based Lens Flare Removal (AAAI 2025 · similarity 0.91)
- FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering (NeurIPS 2025 · similarity 0.91)
- Language-Guided One-Step Diffusion Model for Nighttime Flare Removal (CVPR 2026 · similarity 0.90)
- FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views (CVPR 2025 · similarity 0.82)
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.
