Research map / Image generation / Image restoration
sRGB Real Noise Synthesizing With Neighboring Correlation-Aware Noise Model
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 L_reg stabilization loss (ablation) | NeCA · SIDD camera IP | KL divergence: 0.108 -> 0.041 | Helped |
| add L_std2 noise-level loss (ablation) | NeCA · SIDD camera IP | KL divergence: 0.052 -> 0.041 | Helped |
| add adversarial loss on down-sampled noise (L_adv2; table column labeled L_adv1) (ablation) | NeCA · SIDD camera IP | KL divergence: 0.048 -> 0.041 | Helped |
| add neighboring correlation network applied to AWGN (NeCA-S) vs C2N | DnCNN denoiser · SIDD benchmark | PSNR: 33.76 -> 36.10 | Helped |
| use full NeCA-W (signal dependency + neighboring correlation) instead of NeCA-S (ablation) | DnCNN denoiser · SIDD benchmark | PSNR: 36.10 -> 36.82 | Helped |
| replace Flow-sRGB noise with NeCA-W noise for training denoiser | DnCNN denoiser · SIDD benchmark | PSNR: 34.74 -> 36.82 | Helped |
| replace NLF-ISP with NeCA | DnCNN denoiser · SIDD validation average | PSNR: 37.59 -> 37.58 | No clear effect |
| replace C2N with NeCA noise | noise synthesis · SIDD validation average | KL divergence: 0.2129 -> 0.0342 | Helped |
Closest papers by meaning
- Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning (CVPR 2026 · similarity 0.92)
- sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing Flows (ICLR 2024 · similarity 0.91)
- Realistic Noise Synthesis with Diffusion Models (AAAI 2025 · similarity 0.88)
- APR-RD: Complemental Two Steps for Self-Supervised Real Image Denoising (AAAI 2025 · similarity 0.88)
- Zero-Shot Blind-spot Image Denoising via Implicit Neural Sampling (CVPR 2025 · similarity 0.87)
- Noise Modeling in One Hour: Minimizing Preparation Efforts for Self-supervised Low-Light RAW Image Denoising (CVPR 2025 · similarity 0.87)
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.