Inverse Painting: Reconstructing The Painting Process

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Bowei, Wang, Yifan, Curless, Brian, Kemelmacher-Shlizerman, Ira, Seitz, Steven M.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910645974204416
author Chen, Bowei
Wang, Yifan
Curless, Brian
Kemelmacher-Shlizerman, Ira
Seitz, Steven M.
author_facet Chen, Bowei
Wang, Yifan
Curless, Brian
Kemelmacher-Shlizerman, Ira
Seitz, Steven M.
contents Given an input painting, we reconstruct a time-lapse video of how it may have been 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, showing plausible results for a wide range of artistic styles and genres.
format Preprint
id arxiv_https___arxiv_org_abs_2409_20556
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Inverse Painting: Reconstructing The Painting Process
Chen, Bowei
Wang, Yifan
Curless, Brian
Kemelmacher-Shlizerman, Ira
Seitz, Steven M.
Computer Vision and Pattern Recognition
Given an input painting, we reconstruct a time-lapse video of how it may have been 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, showing plausible results for a wide range of artistic styles and genres.
title Inverse Painting: Reconstructing The Painting Process
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.20556