Research map / Image generation / Image restoration
Guided Deep Decoder: Unsupervised Image Pair Fusion
Tatsumi Uezato, Danfeng Hong, Naoto Yokoya, Wei He
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 GDD's guided multi-scale attention gates instead of plain DIP with guidance input | DIP · CAVE HS super-resolution | RMSE: 3.1589 -> 2.0213 | Improved |
| use GDD instead of DIP | DIP · CAVE HS super-resolution | SA: 7.6734 -> 5.5740 | Improved |
| use GDD instead of DIP | DIP · CAVE HS super-resolution | SSIM: 0.9621 -> 0.9869 | Improved |
| use unsupervised GDD instead of supervised MHF | MHF · CAVE HS super-resolution | RMSE: 2.0827 -> 2.0213 | Improved |
| use unsupervised GDD instead of supervised MHF | MHF · CAVE HS super-resolution | SSIM: 0.9874 -> 0.9869 | No clear effect |
| use GDD instead of DIP | DIP · WorldView-2 pansharpening (synthetic) | Q8: 0.9171 -> 0.9469 | Improved |
| use GDD instead of DIP | DIP · WorldView-2 pansharpening (synthetic) | ERGAS: 3.5274 -> 2.6879 | Improved |
| use GDD instead of DIP | DIP · WorldView-2 pansharpening (synthetic) | SA: 4.6514 -> 4.0254 | Improved |
| use GDD instead of supervised PNN+ | PNN+ · WorldView-2 pansharpening (synthetic) | Q8: 0.9231 -> 0.9469 | Improved |
| use GDD instead of DIP | DIP · WorldView-2 pansharpening (real) | QNR: 0.9446 -> 0.9517 | Improved |
| use GDD instead of DIP | DIP · WorldView-2 pansharpening (real) | D_lambda: 0.0188 -> 0.0202 | Hurt |
| use GDD instead of PNN+ | PNN+ · WorldView-2 pansharpening (real) | D_s: 0.0264 -> 0.0288 | Hurt |
Closest papers by meaning
- LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Images (TPAMI 2023 · similarity 0.86)
- An Efficient Image Fusion Network Exploiting Unifying Language and Mask Guidance (TPAMI 2025 · similarity 0.86)
- A General Image Fusion Approach Exploiting Gradient Transfer Learning and Fusion Rule Unfolding (TPAMI 2026 · similarity 0.86)
- Joint Image Filtering with Deep Convolutional Networks (TPAMI 2019 · similarity 0.85)
- PanAdapter: Two-Stage Fine-Tuning with Spatial-Spectral Priors Injecting for Pansharpening (AAAI 2025 · similarity 0.83)
- Unsupervised Pan-Sharpening via Mutually Guided Detail Restoration (AAAI 2024 · 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.
