Image Super-Resolution Via Iterative Refinement

🤖 Plain-English Summary

We present SR3, an approach to image Super-Resolution via Repeated Refinement. We evaluate SR3 on a 4× super-resolution task on ImageNet, where SR3 outperforms baselines in human evaluation and classification accuracy of a ResNet-50 classifier trained on high-resolution images.

🔑 Key Findings

• SR3 adapts denoising diffusion probabilistic models (Ho and colleagues
• 2015) to image-to-image translation, and performs super-resolution through a stochastic iterative denoising process.
• Output images are initialized with pure Gaussian noise and iteratively refined using a U-Net architecture that is trained on denoising at various noise levels, conditioned on a low-resolution input image.

🔗 Related Resources