Research map / Image generation / Image restoration
BlueNeg: A 35mm Negative Film Dataset for Restoring Channel-Heterogeneous Deterioration
Hanyuan Liu, Chengze Li, Minshan Xie, Zhenni Wang, Jiawen Liang, Chi-Sing Leung, Tien-Tsin Wong
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 supervised NAFNet on pseudo ground truth instead of using pretrained generic models | NAFNet · BlueNeg blue-corrupted test-split (30 photos), negative domain | PSNR: 28.62 vs 23.59 (BringOld) | Improved |
| train supervised Restormer on pseudo ground truth instead of using pretrained generic models | Restormer · BlueNeg blue-corrupted test-split (30 photos), printed domain | PSNR: 28.71 vs 25.72 (BringOld) | Improved |
| evaluate in negative domain vs printed domain for generic methods | DACLIP · BlueNeg blue-corrupted partition (pretrained generic models) | PSNR: 20.34 -> 24.80 | No clear effect |
| use global FID rather than patch-wise FID for ranking methods | generic restoration methods · BlueNeg blue-corrupted partition (pretrained generic models) | FID: 165.05 (PromptIR) vs 164.98 (DACLIP) vs 168.39 (DDNM) | Hurt |
Closest papers by meaning
- Bridging Degradation Discrimination and Generation for Universal Image Restoration (ICLR 2026 · similarity 0.88)
- Descanning: From Scanned to the Original Images with a Color Correction Diffusion Model (AAAI 2024 · similarity 0.87)
- Making Old Film Great Again: Degradation-aware State Space Model for Old Film Restoration (CVPR 2025 · similarity 0.86)
- Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration (ICLR 2025 · similarity 0.85)
- GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration (CVPR 2025 · similarity 0.84)
- Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration (AAAI 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.
