[2111.05826] Palette: Image-to-Image Diffusion Models

This paper develops a unified framework for image-to-image translation based on conditional diffusion models and evaluates this framework on four challenging image-to-image translation tasks, namely colorization, inpainting, uncropping, and JPEG restoration. Our simple implementation of image-to-image diffusion models outperforms strong GAN and regression baselines on all tasks, without task-specific hyper-parameter tuning, architecture customization, or any auxiliary loss or sophisticated new techniques needed. We uncover the impact of an L2 vs. L1 loss in the denoising diffusion objective on sample diversity, and demonstrate the importance of self-attention in the neural architecture through empirical studies. Importantly, we advocate a unified evaluation protocol based on ImageNet, with human evaluation and sample quality scores (FID, Inception Score, Classification Accuracy of a pre-trained ResNet-50, and Perceptual Distance against original images). We expect this standardized evaluation protocol to play a role in advancing image-to-image translation research. Finally, we show that a generalist, multi-task diffusion model performs as well or better than task-specific specialist counterparts. Check out this https URL for an overview of the results.

This paper develops a unified framework for image-to-image translation based on conditional diffusion models and evaluates this framework on four challenging image-to-image translation tasks, namely colorization, inpainting, uncropping, and JPEG restoration. Our simple implementation of image-to-image diffusion models outperforms strong GAN and regression baselines on all tasks, without task-specific hyper-parameter tuning, architecture customization, or any auxiliary loss or sophisticated new techniques needed. We uncover the impact of an L2 vs. L1 loss in the denoising diffusion objective on

related reading

• [2105.05233] Diffusion Models Beat GANs on Image Synthesisarxiv.org
• [2006.11239] Denoising Diffusion Probabilistic Modelsarxiv.org
• What are Diffusion Models? | Lil'Loglilianweng.github.io
• Scalable Diffusion Models with Transformersopenaccess.thecvf.com
• Fusing Diffusion Paths for Controlled Image Generationmultidiffusion.github.io
• Fast Training of Diffusion Models with Masked Transformers | PDFarxiv.org
• [2010.02502] Denoising Diffusion Implicit Modelsarxiv.org
• What are Diffusion Models?lilianweng.github.io
• [2404.02905] Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictionarxiv.org
• https://arxiv.org/pdf/2006.11239arxiv.org
• [2112.10752] High-Resolution Image Synthesis with Latent Diffusion Modelsarxiv.org
• Diffusion models from scratchchenyang.co