Research map / Image generation / Image restoration
SLCFormer: Spectral-Local Context Transformer with Physics-Grounded Flare Synthesis for Nighttime Flare Removal
Xiyu Zhu, Wei Wang, Xin Yuan, Xiao 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 FFEM (ablation) | SLCFormer · Flare7K++ real | PSNR: 27.888 -> 28.092 | Improved |
| add DESM (ablation) | SLCFormer · Flare7K++ real | PSNR: 27.804 -> 28.092 | Improved |
| add both FFEM and DESM (ablation) | SLCFormer · Flare7K++ real | PSNR: 27.633 -> 28.092 | Improved |
| add FFEM (ablation) | SLCFormer · Flare7K++ real | LPIPS: 0.0408 -> 0.0400 | Improved |
| add DESM (ablation) | SLCFormer · Flare7K++ real | LPIPS: 0.0430 -> 0.0400 | Improved |
| add high-frequency loss (ablation) | SLCFormer · Flare7K++ real | PSNR: 27.824 -> 28.092 | Improved |
| add high-frequency loss (ablation) | SLCFormer · Flare7K++ real | LPIPS: 0.0431 -> 0.0400 | Improved |
| add high-frequency loss (ablation) | SLCFormer · Flare7K++ real | S-PSNR: 22.986 -> 23.287 | Improved |
| SLCFormer vs SGSFT | SLCFormer · Flare7K++ real | PSNR: 28.077 -> 28.092 | No clear effect |
| SLCFormer vs SGSFT | SLCFormer · Flare7K++ real | S-PSNR: 23.305 -> 23.287 | Hurt |
| SLCFormer vs SGSFT | SLCFormer · Flare7K++ synthetic | S-PSNR: 24.914 -> 24.578 | Hurt |
| SLCFormer vs Flare-Free | SLCFormer · Flare7K++ synthetic | G-PSNR: 24.879 -> 24.792 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 2 of 2 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
- Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond (TPAMI 2024 · similarity 0.93)
- FlareReal: A Real-Captured Paired Dataset for Nighttime Lens Flare Removal (NeurIPS 2026 · similarity 0.92)
- Disentangle Nighttime Lens Flares: Self-supervised Generation-based Lens Flare Removal (AAAI 2025 · similarity 0.92)
- 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 0.89)
- FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views (CVPR 2025 · similarity 0.83)
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.
