Research map / Image generation / Super-resolution
PC-SRGAN: Physically Consistent Super-Resolution Generative Adversarial Network for General Transient Simulations
Md Rakibul Hasan, Pouria Behnoudfar, Daniel MacKinlay, Thomas Poulet
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 physics-based inner and boundary losses | SRGAN · Allen-Cahn 8x Periodic | PSNR: 32.4400 -> 37.2748 | Improved |
| add physics-based losses | SRGAN · Eriksson-Johnson 8x Dirichlet | PSNR: 41.6019 -> 49.3625 | Improved |
| add physics-based losses | SRGAN · Allen-Cahn 8x Neumann | PSNR: 33.1739 -> 38.1240 | Improved |
| add physics-based losses | SRGAN · Allen-Cahn 4x Periodic | PSNR: 30.7071 -> 33.1279 | Improved |
| add physics-based losses to ESRGAN generator | ESRGAN · Allen-Cahn 8x Periodic | PSNR: 27.3812 -> 44.2954 | Improved |
| use BDF time integrator instead of Crank-Nicolson (ablation) | PC-SRGAN · Allen-Cahn 8x Periodic | PSNR: 35.0870 -> 37.2748 | Improved |
| use BDF time integrator instead of Explicit Euler (ablation) | PC-SRGAN · Allen-Cahn 8x Periodic | PSNR: 33.9045 -> 37.2748 | Improved |
| add physics-inner loss (ablation) | PC-SRGAN · Allen-Cahn 8x Periodic | PSNR: 34.6566 -> 37.2748 | Improved |
| add physics-boundary loss (ablation) | PC-SRGAN · Allen-Cahn 8x Periodic | PSNR: 36.7473 -> 37.2748 | Mixed |
| add pixel loss (ablation) | PC-SRGAN · Allen-Cahn 8x Periodic | SSIM: 0.9653 -> 0.9652 | Mixed |
| add content (VGG) loss (ablation) | PC-SRGAN · Allen-Cahn 8x Periodic | PSNR: 35.9596 -> 37.2748 | Improved |
| add adversarial loss (ablation) | PC-SRGAN · Allen-Cahn 8x Periodic | PSNR: 35.6935 -> 37.2748 | Improved |
Closest papers by meaning
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (CVPR 2017 · similarity 0.90)
- SRFeat: Single Image Super-Resolution with Feature Discrimination (ECCV 2018 · similarity 0.88)
- Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions (ICLR 2023 · similarity 0.87)
- Uncertainty-Aware GAN for Single Image Super Resolution (AAAI 2024 · similarity 0.87)
- RG-GAN: Dynamic Regenerative Pruning for Data-Efficient Generative Adversarial Networks (AAAI 2024 · similarity 0.86)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 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.
