Research map / Image generation / Super-resolution
Omni Aggregation Networks for Lightweight Image Super-Resolution
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 |
|---|---|---|---|
| Add channel self-attention to the spatial-only model (ablation) | Omni-SR · Urban100 ×4 | PSNR: 26.51 -> 26.64 | Helped |
| Add spatial self-attention to the channel-only model (ablation) | Omni-SR · Urban100 ×4 | PSNR: 26.45 -> 26.64 | Helped |
| Use covariance-based channel self-attention instead of SE channel attention (ablation) | Omni-SR · Urban100 ×4 | PSNR: 26.50 -> 26.64 | Helped |
| Use the proposed spatial and channel self-attention instead of CBAM attention (ablation) | Omni-SR · Urban100 ×4 | PSNR: 26.53 -> 26.64 | Helped |
| Combine local, meso, and global-scale interactions in OSAG (ablation) | Omni-SR · Urban100 ×4 | PSNR | Helped |
| Increase the number of OSAG groups from K=1 (ablation) | Omni-SR · Urban100 ×4 | PSNR | Helped |
| Train with DF2K rather than DIV2K only | Omni-SR · Urban100 ×4 | PSNR: 26.64 -> 26.95 | Helped |
Closest papers by meaning
- OSFFNet: Omni-Stage Feature Fusion Network for Lightweight Image Super-Resolution (AAAI 2024 · similarity 0.87)
- CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution (CVPR 2025 · similarity 0.84)
- Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors (AAAI 2025 · similarity 0.84)
- Occlusion-Embedded Hybrid Transformer for Light Field Super-Resolution (AAAI 2025 · similarity 0.84)
- Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-Resolution (AAAI 2025 · similarity 0.83)
- Lightweight Image Super-Resolution via Flexible Meta Pruning (ICML 2024 · similarity 0.82)
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.