Research map / Detection and segmentation / CNN features
Deep Fourier Up-Sampling
man zhou, Hu Yu, Jie Huang, Feng Zhao, Jinwei Gu, Chen Change Loy, Deyu Meng, Chongyi Li
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 FourierUp-Padding instead of the original up-sampling | PReNet · Rain200H | PSNR: 29.041 -> 29.871 | Improved |
| Add FourierUp-Padding instead of the original up-sampling | PReNet · Rain200L | PSNR: 37.802 -> 39.971 | Improved |
| Use FourierUp-AreaUp rather than FourierUp-Padding (ablation) | LPNet · Rain200H | PSNR: 23.295 -> 22.163 | Hurt |
| Use FourierUp-Padding rather than FourierUp-AreaUp (ablation) | LPNet · Rain200L | PSNR: 32.681 -> 32.835 | Improved |
| Add FourierUp-Padding rather than parameter-matched spatial up-sampling | AODNet · RESIDE | PSNR: 18.91 -> 19.35 | Improved |
| Add FourierUp-Padding rather than parameter-matched spatial up-sampling | MSBDN · RESIDE | PSNR: 33.90 -> 34.35 | Improved |
| Add FourierUp-Padding rather than parameter-matched spatial up-sampling | Faster RCNN · PASCAL VOC 2007 test | mAP: 79.10 -> 79.15 | Improved |
| Add FourierUp-Padding rather than parameter-matched spatial up-sampling | U-Net · Synapse | DSC: 76.94 -> 77.37 | Improved |
| Add FourierUp-Padding rather than parameter-matched spatial up-sampling | PANNET · GaoFen2 | PSNR: 43.897 -> 46.145 | Improved |
| Use FourierUp-Padding rather than FourierUp-AreaUp (ablation) | PANNET · WorldView-II | PSNR: 41.167 -> 41.288 | Improved |
Closest papers by meaning
- Beyond Spatial Domain: Cross-domain Promoted Fourier Convolution Helps Single Image Dehazing (AAAI 2025 · similarity 0.87)
- FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining (ICML 2025 · similarity 0.85)
- Improving the Learning Capability of Small-size Image Restoration Network by Deep Fourier Shifting (NeurIPS 2024 · similarity 0.84)
- Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring (CVPR 2024 · similarity 0.84)
- Generalizable Fourier Augmentation for Unsupervised Video Object Segmentation (AAAI 2024 · similarity 0.83)
- Learning Spatially Collaged Fourier Bases for Implicit Neural Representation (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.
