Research map / Image generation / Image restoration
Inheriting Bayer’s Legacy: Joint Remosaicing and Denoising for Quad Bayer Image Sensor
Haijin Zeng, Kai Feng, Jiezhang Cao, Shaoguang Huang, Yongqiang Zhao, Hiep Quang Luong, Jan Aelterman, Wilfried R. Philips
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 |
|---|---|---|---|
| fine-tune on hard cases (ablation) | DN-RM pipeline · MIPI average | PSNR: 35.26 -> 35.94 | Improved |
| fine-tune on hard cases (ablation) | RM-DN pipeline · MIPI average | PSNR: 35.59 -> 36.06 | Improved |
| fine-tune on hard cases (ablation) | DN-RM pipeline · MIPI 42dB | PSNR: 31.91 -> 31.98 | No clear effect |
| remosaic first then denoise instead of denoise first (ablation) | DJRD variants · MIPI average | PSNR: 35.26 -> 35.59 | Improved |
| use dual-head joint pipeline instead of sequential RM-DN, with hard fine-tuning (ablation) | DJRD · MIPI average | PSNR: 36.06 -> 36.40 | Improved |
| use dual-head joint pipeline instead of sequential DN-RM, with hard fine-tuning (ablation) | DJRD · MIPI average | PSNR: 35.94 -> 36.40 | Improved |
| use dual-head joint pipeline instead of RM-DN (ablation) | DJRD · MIPI 0dB | SSIM: 0.9652 -> 0.9662 | Improved |
| use DJRD instead of SAGAN | DJRD · MIPI average | PSNR: 31.81 -> 36.40 | Improved |
| use DJRD instead of PIPNet | DJRD · Urban100 | PSNR: 26.67 -> 31.02 | Improved |
Closest papers by meaning
- Quad Bayer Joint Demosaicing and Denoising Based on Dual Encoder Network with Joint Residual Learning (AAAI 2024 · similarity 0.89)
- MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging (NeurIPS 2024 · similarity 0.83)
- Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing (CVPR 2025 · similarity 0.83)
- Quad-Pixel Image Defocus Deblurring: A New Benchmark and Model (CVPR 2025 · similarity 0.82)
- Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios (ICLR 2025 · similarity 0.82)
- Real-World Mobile Image Denoising Dataset with Efficient Baselines (CVPR 2024 · similarity 0.81)
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.
