Inverse Painting: Reconstructing The Painting Process
DescriptionGiven an input painting, we reconstruct a time-lapse video of how it may be painted. We formulate this as an autoregressive image generation problem, in which an initially blank "canvas'' is iteratively updated. The model learns from real artists by training on many painting videos.
Our approach incorporates text and region understanding to define a set of painting "instructions'' and updates the canvas with a novel diffusion-based renderer. The method extrapolates beyond the limited, acrylic style paintings on which it has been trained to show plausible results for a wide range of artistic styles and genres.
Our approach incorporates text and region understanding to define a set of painting "instructions'' and updates the canvas with a novel diffusion-based renderer. The method extrapolates beyond the limited, acrylic style paintings on which it has been trained to show plausible results for a wide range of artistic styles and genres.
Event Type
Technical Papers
TimeTuesday, 3 December 20243:19pm - 3:31pm JST
LocationHall B7 (1), B Block, Level 7
