Boosting Flow-based Generative Super-Resolution Models via Learned Prior
Flow-based super-resolution (SR) models have demonstrated astonishing capabilities in generating high-quality images. However, these methods encounter several challenges during image generation, such as grid artifacts, exploding inverses, and suboptimal results due to a fixed sampling temperature. To overcome these issues, this work introduces a conditional learned prior to the inference phase of a flow-based SR model. This prior is a latent code predicted by our proposed latent module conditioned on the low-resolution image, which is then transformed by the flow model into an SR image. Our framework is designed to seamlessly integrate with any contemporary flow-based SR model without modifying its architecture or pre-trained weights. We evaluate the effectiveness of our proposed framework through extensive experiments and ablation analyses. The proposed framework successfully addresses all the inherent issues in flow-based SR models and enhances their performance in various SR scenarios. Our code is available at: https://github.com/liyuantsao/FlowSR-LP
PDF AbstractCode
DIV2K
Set14
Set5
Results from the Paper
Ranked #3 on
Image Super-Resolution
on DIV2K val - 4x upscaling
(using extra training data)
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
|---|---|---|---|---|---|---|---|
| Image Super-Resolution | DIV2K val - 4x upscaling | LINF-LP | PSNR | 28.00 | # 7 | ||
| SSIM | 0.78 | # 9 | |||||
| LPIPS | 0.105 | # 3 | |||||
| LRPSNR | 47.3 | # 6 | |||||
| Image Super-Resolution | DIV2K val - 4x upscaling | SRFlow-LP | PSNR | 27.51 | # 10 | ||
| SSIM | 0.78 | # 9 | |||||
| LPIPS | 0.109 | # 4 | |||||
| LRPSNR | 51.51 | # 2 |
