Research map / Image generation / Super-resolution
Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images
Jinjin Gu, Haoming Cai, Chenyu Dong, Ruofan Zhang, Yulun Zhang, Wenming Yang, Chun Yuan
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 the SRPO network from one layer to three layers (ablation) | SRPO · Unreal Engine 4 test scenes | edge sharpness (qualitative) | Improved |
| deepen the SRPO network from three to seven layers (ablation) | SRPO · Unreal Engine 4 test scenes | edge sharpness (qualitative) | No clear effect |
| deepen the network to 30 layers (ablation) | SRPO · Unreal Engine 4 test scenes | edge sharpness (qualitative) | Improved |
| apply 8-bit static quantization | ESPCN and eSR-CNN · Unreal Engine 4 test scenes | visual quality (qualitative) | Hurt |
| apply 8-bit static quantization | SRPO · Unreal Engine 4 test scenes | visual quality (qualitative) | No clear effect |
| predict offsets on rasterized images instead of pixels on anti-aliased images (SRPO vs eSR-CNN) | SRPO · Unreal Engine 4 test scenes (x2) | LPIPS: 0.1547 -> 0.1501 | Improved |
| use SRPO instead of AMD FSR | SRPO · Unreal Engine 4 test scenes (x2) | PSNR: 27.56 -> 26.97 | Hurt |
Closest papers by meaning
- Achieving Lightweight Super-Resolution for Real-Time Computer Graphics (AAAI 2025 · similarity 0.89)
- Image Processing GNN: Breaking Rigidity in Super-Resolution (CVPR 2024 · similarity 0.86)
- Towards Real-World Burst Image Super-Resolution: Benchmark and Method (ICCV 2023 · similarity 0.86)
- Efficient Video Super-Resolution for Real-time Rendering with Decoupled G-buffer Guidance (CVPR 2025 · similarity 0.86)
- Neural Super-Resolution for Real-time Rendering with Radiance Demodulation (CVPR 2024 · similarity 0.85)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · 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.
