Research map / Image generation / Super-resolution
Toward Accurate Post-Training Quantization for Image Super Resolution
Zhijun Tu, Jie Hu, Hanting Chen, Yunhe Wang
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 |
|---|---|---|---|
| Use DBDC and PaC for 4-bit PTQ instead of MinMax PTQ (ablation) | EDSR ×4 · Urban100 | PSNR (dB): 22.871 -> 25.556 | Improved |
| Add density-based dual clipping (ablation) | EDSR ×4, 4-bit MinMax PTQ · Urban100 | PSNR (dB): 22.871 -> 25.312 | Improved |
| Add pixel-aware calibration (ablation) | EDSR ×4, 4-bit MinMax PTQ · Urban100 | PSNR (dB): 22.871 -> 24.116 | Improved |
| Add PaC after DBDC (ablation) | EDSR ×4, 4-bit PTQ · Urban100 | PSNR (dB): 25.312 -> 25.556 | Improved |
| Add DBDC after PaC (ablation) | EDSR ×4, 4-bit PTQ · Urban100 | PSNR (dB): 24.116 -> 25.556 | Improved |
| Use the proposed PTQ method rather than the strongest listed baseline at each bit-width | EDSR ×4 · Urban100 | PSNR (dB): 26.560 -> 26.567; 25.890 -> 26.382; 22.871 -> 25.556 | Improved |
| Use the proposed PTQ method rather than the strongest listed baseline at each bit-width | SRResNet ×4 · Urban100 | PSNR (dB): 26.111 -> 26.191; 25.340 -> 26.011; 23.042 -> 25.133 | Improved |
Closest papers by meaning
- Outlier-Aware Post-Training Quantization for Image Super-Resolution (ICCV 2025 · similarity 0.93)
- 2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution (NeurIPS 2024 · similarity 0.91)
- Gradient Knows Best: Mixed-Precision Quantization via Gradient-Guided Bit Allocation for Super-Resolution (CVPR 2026 · similarity 0.91)
- PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution (CVPR 2025 · similarity 0.88)
- AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution (CVPR 2024 · similarity 0.88)
- Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues (AAAI 2025 · similarity 0.87)
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.
