#Google SR3

Google has recently introduced new AI-based image upscaling technology that enhances the quality of low-resolution images. In a post on Google’s AI blog titled "High Fidelity Image Generation Using Diffusion Model," the researchers from Brain Team unveiled two diffusion models to generate high-fidelity images. The two models are Super-Resolution via Repeated Refinements (SR3) and Cascaded Diffusion Models (CDM). First is the SR3, which is a super-resolution diffusion model that takes as input a low-resolution image, and builds a corresponding high-resolution image from pure noise. However, with large-scale training, SR3 achieves strong benchmark results on the super-resolution task for face and natural images when scaling to resolutions 4x–8x that of the input low-resolution image. Meanwhile, after seeing the effectiveness of SR3, Google used these SR3 models for class-conditional image generation. "Since ImageNet is a difficult, high-entropy dataset, we built CDM as a cascade of multiple diffusion models," Google said in the blog. Furthermore, this cascade approach involves chaining together multiple generative models over several spatial resolutions: one diffusion model that generates data at a low resolution, followed by a sequence of SR3 super-resolution diffusion models that gradually increase the resolution of the generated image to the highest resolution. Read more in our articles including "Google intros new AI photo upscaling tech" and "KiQ intros cheaper UNLI data, physical SIM".