Research map / Image generation / Super-resolution
Benchmarking Ultra-High-Definition Image Super-Resolution
Kaihao Zhang, Dongxu Li, Wenhan Luo, Wenqi Ren, Björn Stenger, Wei Liu, Hongdong Li, Ming-Hsuan Yang
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 |
|---|---|---|---|
| increase upscaling factor from 2x to 16x | MANet · UHDSR4K | PSNR: 43.742 -> 23.523 | Hurt |
| increase upscaling factor from 2x to 16x | MANet · UHDSR8K | PSNR: 57.371 -> 32.463 | Hurt |
| add Gaussian noise to the 3x downsampling | MANet · UHDSR4K | PSNR: 35.842 -> 31.589 | Hurt |
| add blur before the 3x downsampling | MANet · UHDSR4K | PSNR: 35.842 -> 35.240 | Hurt |
| add Gaussian noise to the 3x downsampling | MANet · UHDSR8K | PSNR: 52.544 -> 37.893 | Hurt |
| add blur before the 3x downsampling | MANet · UHDSR8K | PSNR: 52.544 -> 48.862 | Hurt |
| use 8K instead of 4K images at the same 2x factor | MANet · UHDSR 2x | PSNR: 43.742 -> 57.371 | Improved |
| use mesh attention on RDB features (MANet vs RDN) at 2x | MANet vs RDN · UHDSR4K 2x | PSNR: 43.642 -> 43.742 | Improved |
| use mesh attention on RDB features (MANet vs RDN) at 4x | MANet vs RDN · UHDSR4K 4x | PSNR: 32.532 -> 32.218 | Hurt |
| use mesh attention (MANet vs RDN) at 16x | MANet vs RDN · UHDSR8K 16x | PSNR: 32.491 -> 32.463 | Hurt |
| use mesh attention (MANet vs RDN) at 4x | MANet vs RDN · UHDSR8K 4x | PSNR: 50.604 -> 50.686 | Improved |
Closest papers by meaning
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.87)
- Toward Real-World Single Image Super-Resolution: A New Benchmark and a New Model (ICCV 2019 · similarity 0.87)
- Rethinking Image Super Resolution from Training Data Perspectives (ECCV 2024 · similarity 0.87)
- JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video (AAAI 2020 · similarity 0.86)
- ARM: Any-Time Super-Resolution Method (ECCV 2022 · similarity 0.86)
- Block-Based Multi-Scale Image Rescaling (AAAI 2025 · similarity 0.86)
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.
