Presentation
Palette: Image-to-image Diffusion Models
SessionTechnical Papers
Event Type
Technical Paper
Research & Education
Virtual
Full Conference Supporter
Full Conference
Virtual Conference Supporter
Virtual Conference
Exhibitor Additional Full Conference
Exhibitor Full Conference
Time
Location
DescriptionWe’ve developed a simple and general framework for image-to-image translation based on iterative refinement, called Palette. We’ve trained and evaluated Palette on four challenging computer vision tasks, namely colorization, inpainting, uncropping, and JPEG restoration. Palette generates photorealistic results and outperforms strong task-specific GANs, without any task-specific customization or hyper-parameter tuning.
