Research map / Image generation / Image restoration
ReCoNet: Recurrent Correction Network for Fast and Efficient Multi-Modality Image Fusion
Zhanbo Huang, Jinyuan Liu, Xin Fan, Risheng Liu, Wei Zhong, Zhongxuan Luo
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 |
|---|---|---|---|
| add the micro registration module to the fusion network | ReCoNet · Computational efficiency (GPU) | Model size (M params): 0.007 -> 0.209 | Hurt |
| add the micro registration module to the fusion network | ReCoNet · Computational efficiency (GPU) | Runtime (s): 0.024 -> 0.052 | Hurt |
| add the micro registration module to the fusion network | ReCoNet · Computational efficiency (GPU) | FLOPs (G): 1.162 -> 12.54 | Hurt |
| increase recurrent attention iterations (ablation) | ReCoNet · Infrared-visible fusion | visual quality | Improved |
| add the deformable alignment (micro registration) module (ablation) | ReCoNet · Misaligned TNO/RoadScene | visual artifacts | Improved |
| use ReCoNet against DenseFuse, PMGI, DIDFuse, U2Fusion under added transforms | ReCoNet · Misaligned TNO/RoadScene | CC | Improved |
Closest papers by meaning
- Rectification Reimagined: A Unified Mamba Model for Image Correction and Rectangling with Prompts (AAAI 2026 · similarity 0.86)
- ERDN: Equivalent Receptive Field Deformable Network for Video Deblurring (ECCV 2022 · similarity 0.85)
- AMDANet: Attention-Driven Multi-Perspective Discrepancy Alignment for RGB-Infrared Image Fusion and Segmentation (ICCV 2025 · similarity 0.85)
- Efficient Rectified Flow for Image Fusion (NeurIPS 2025 · similarity 0.85)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.85)
- RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers (ICML 2025 · 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.
