Research map / Image generation / Super-resolution
Binarized Neural Network for Single Image Super Resolution
Jingwei Xin, Nannan Wang, Xinrui Jiang, Jie Li, Heng Huang, Xinbo Gao
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 |
|---|---|---|---|
| add bit accumulation mechanism (BAM) instead of ABC | SRResNet · Set5 x4 | PSNR (dB): 30.78 -> 31.24 | Improved |
| add BAM instead of DoReFa | SRResNet · Urban100 x4 | PSNR (dB): 24.45 -> 24.95 | Improved |
| add BAM instead of ABC | VDSR · Set5 x4 | PSNR (dB): 29.59 -> 30.31 | Improved |
| add BAM instead of BNN | VDSR · Set5 x4 | PSNR (dB): 29.02 -> 30.31 | Improved |
| use the BSRN lightweight architecture instead of SRResNet with BAM | BAM · Set5 x4 | PSNR (dB): 31.24 -> 31.35 | Improved |
| add linear combination coefficients in weight quantization (ablation) | BSRN · Set5 x4 | PSNR (dB): 31.25 -> 31.35 | Improved |
| add bit accumulation in weight quantization (ablation) | BSRN · Set5 x4 | PSNR (dB): 31.14 -> 31.35 | Improved |
| add linear combination coefficients in activation quantization (ablation) | BSRN · Set5 x4 | PSNR (dB): 31.22 -> 31.35 | Improved |
| add bit accumulation in activation quantization (ablation) | BSRN · Set5 x4 | PSNR (dB): 30.92 -> 31.35 | Improved |
| use BAM with binary filters instead of Ma et al. quantization | SRResNet · Set5 x4 | PSNR (dB): 30.34 -> 31.57 | Improved |
Closest papers by meaning
- Training Binary Neural Network without Batch Normalization for Image Super-Resolution (AAAI 2021 · similarity 0.92)
- Flexible Residual Binarization for Image Super-Resolution (ICML 2024 · similarity 0.90)
- Binarized Diffusion Model for Image Super-Resolution (NeurIPS 2024 · similarity 0.88)
- 2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution (NeurIPS 2024 · similarity 0.88)
- AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution (CVPR 2024 · similarity 0.87)
- BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution (ICML 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.
