Research map / Image generation / Super-resolution
CUF: Continuous Upsampling Filters
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 CUF instead of Sub-pixel conv. | EDSR-baseline · DIV2K val, seen scales (2×–4×) | PSNR: 34.69 -> 34.70; 30.94 -> 30.99; 28.97 -> 29.01 | Helped |
| use CUF instead of MetaSR | EDSR-baseline · DIV2K val, unseen scales (6×–30×) | PSNR: 26.61 -> 26.76; 23.55 -> 23.73; 22.03 -> 22.20 | Helped |
| replace Fourier positional encoding with DCT (ablation) | ABPN-CUF · Urban100 | PSNR: 30.45 -> 30.44; 26.85 -> 26.86; 25.00 -> 25.00 | No clear effect |
| condition the hyper-network on kernel indices instead of representing them as output neurons (ablation) | CUF · RDN and SwinIR; ABPN and EDSR | PSNR | Mixed |
Closest papers by meaning
- Kernel Aware Resampler (CVPR 2023 · similarity 0.88)
- Correction Filter for Single Image Super-Resolution: Robustifying Off-the-Shelf Deep Super-Resolvers (CVPR 2020 · similarity 0.88)
- UltraPixel: Advancing Ultra High-Resolution Image Synthesis to New Peaks (NeurIPS 2024 · similarity 0.86)
- ResDiff: Combining CNN and Diffusion Model for Image Super-resolution (AAAI 2024 · similarity 0.86)
- Arbitrary-Scale Video Super-resolution Guided by Dynamic Context (AAAI 2024 · similarity 0.85)
- Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder (CVPR 2024 · 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.