Research map / Image generation / Super-resolution
AdderSR: Towards Energy Efficient Image Super-Resolution
Check 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 |
|---|---|---|---|
| Replace intermediate EDSR convolutions with adder layers | EDSR · Set5, Set14, B100, Urban100, ×2/×3/×4 | PSNR: The average PSNR gap between AdderSR models and baselines using convolutions over the four datasets is about 0.17 dB. | Hurt |
| Replace intermediate EDSR convolutions with adder layers | EDSR · 1280 × 720 image, ×2 | energy consumption: about 2.5× | Helped |
| Add self-shortcuts to adder layers (ablation) | Adder VDSR · Set5, Set14, B100, Urban100 | PSNR: about 1.67 dB | Helped |
| Add learnable power activation (ablation) | Adder VDSR · Set5, Set14, B100, Urban100 | PSNR: about 0.24 dB | Helped |
| Add both self-shortcuts and learnable power activation (ablation) | Adder VDSR · Set5, Set14, B100, Urban100 | PSNR: 1.91 dB | Helped |
| Add learnable power activation while omitting self-shortcuts (ablation) | Adder VDSR · Set5, Set14, B100, Urban100 | PSNR: 35.11 -> 35.44; 31.40 -> 31.62; 30.63 -> 30.78; 27.77 -> 27.96 | Helped |
| Add self-shortcuts while omitting power activation (ablation) | Adder VDSR · Set5, Set14, B100, Urban100 | PSNR: 35.11 -> 37.10; 31.40 -> 32.77; 30.63 -> 31.69; 27.77 -> 30.05 | Helped |
Closest papers by meaning
- Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary (CVPR 2024 · similarity 0.86)
- Efficient Look-Up Table from Expanded Convolutional Network for Accelerating Image Super-resolution (AAAI 2024 · similarity 0.86)
- Image Processing GNN: Breaking Rigidity in Super-Resolution (CVPR 2024 · similarity 0.85)
- Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-Resolution (AAAI 2025 · similarity 0.85)
- Effective Diffusion Transformer Architecture for Image Super-Resolution (AAAI 2025 · similarity 0.85)
- Exploring the Low-Pass Filtering Behavior in Image Super-Resolution (ICML 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.