Back to Basics: Let Denoising Generative Models Denoise
By: Tianhong Li, Kaiming He
Potential Business Impact:
Makes AI create clearer pictures by predicting them directly.
Today's denoising diffusion models do not "denoise" in the classical sense, i.e., they do not directly predict clean images. Rather, the neural networks predict noise or a noised quantity. In this paper, we suggest that predicting clean data and predicting noised quantities are fundamentally different. According to the manifold assumption, natural data should lie on a low-dimensional manifold, whereas noised quantities do not. With this assumption, we advocate for models that directly predict clean data, which allows apparently under-capacity networks to operate effectively in very high-dimensional spaces. We show that simple, large-patch Transformers on pixels can be strong generative models: using no tokenizer, no pre-training, and no extra loss. Our approach is conceptually nothing more than "$\textbf{Just image Transformers}$", or $\textbf{JiT}$, as we call it. We report competitive results using JiT with large patch sizes of 16 and 32 on ImageNet at resolutions of 256 and 512, where predicting high-dimensional noised quantities can fail catastrophically. With our networks mapping back to the basics of the manifold, our research goes back to basics and pursues a self-contained paradigm for Transformer-based diffusion on raw natural data.
Similar Papers
PixelDiT: Pixel Diffusion Transformers for Image Generation
CV and Pattern Recognition
Makes AI create clearer, more detailed pictures.
2-Shots in the Dark: Low-Light Denoising with Minimal Data Acquisition
CV and Pattern Recognition
Makes dark photos clear with just one picture.
Diffusion models under low-noise regime
CV and Pattern Recognition
Helps AI make better pictures by learning from less data.