Research map / Image generation / Image restoration
NODiff: Neural Operator Diffusion for Multispectral Image Fusion
Junming Hou, Ran Ran, Sixing Chen, Zihao Chen, Xiaofeng Cong, Junling Li, Liang-Jian Deng
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 |
|---|---|---|---|
| use NODiff instead of ADWM | pansharpening · WV3 reduced resolution | PSNR (dB): 39.170 -> 39.314 | Improved |
| use NODiff instead of PanDiff (attention-based diffusion) | pansharpening · WV3 reduced resolution | PSNR (dB): 37.860 -> 39.314 | Improved |
| use NODiff instead of PanMamba | pansharpening · QB reduced resolution | PSNR (dB): 37.356 -> 38.700 | Improved |
| use NODiff instead of PanMamba | pansharpening · WV3 full resolution | HQNR: 0.952 -> 0.956 | Improved |
| add two-stage pretraining (Stage I texture priors) before fine-tuning (ablation) | NODiff · WV3 reduced resolution | PSNR (dB): 38.865 -> 39.314 | Improved |
| add conditional guidance adapter (CGA) (ablation) | NODiff · WV3 reduced resolution | PSNR (dB): 38.681 -> 39.314 | Improved |
| add time-aware LoRA (ablation) | NODiff · WV3 reduced resolution | PSNR (dB): 39.032 -> 39.314 | Improved |
| set spectral mode truncation to 12 rather than 8, 16 or 32 (ablation) | NODiff · WV3 reduced resolution | PSNR/SAM/ERGAS/Q8 | Improved |
| use 8 FNO layers instead of 12 (ablation) | NODiff · WV3 reduced resolution | PSNR (dB): 38.85 -> 39.31 | Improved |
| use 8 FNO layers instead of 4 (ablation) | NODiff · WV3 reduced resolution | PSNR (dB): 39.1 -> 39.31 | Improved |
Closest papers by meaning
- SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening (NeurIPS 2024 · similarity 0.90)
- Hyperspectral Pansharpening via Diffusion Models with Iteratively Zero-Shot Guidance (CVPR 2025 · similarity 0.88)
- Dual-Granularity Semantic Guided Sparse Routing Diffusion Model for General Pansharpening (CVPR 2025 · similarity 0.87)
- PanAdapter: Two-Stage Fine-Tuning with Spatial-Spectral Priors Injecting for Pansharpening (AAAI 2025 · similarity 0.86)
- DiffusionSat: A Generative Foundation Model for Satellite Imagery (ICLR 2024 · similarity 0.86)
- Binarized Neural Network for Multi-spectral Image Fusion (CVPR 2025 · similarity 0.85)
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.
