Inverse Painting: Reconstructing The Painting Process

Bowei Chen, Yifan Wang, Brian Curless, Ira Kemelmacher-Shlizerman, Steven M. Seitz
9/30/2024
cs.CV

No official code found. Best implementation: ArmastusChen/inverse_painting (198 stars, last commit 2024-12-13).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

ArmastusChen/inverse_paintingCommunity66%

Inverse Painting: Reconstructing The Painting Process (SIGGRAPH ASIA 2024)

19813CSS, HTMLSep 27, 20241 years ago

Similar Papers

ProcessPainter: Learn Painting Process from Sequence Data

88% match1 repo982024

Loomis Painter: Reconstructing the Painting Process

86% match1 repo552025

PaintScene4D: Consistent 4D Scene Generation from Text Prompts

84% match2024

AnimatePainter: A Self-Supervised Rendering Framework for Reconstructing Painting Process

83% match2025

Opt-In Art: Learning Art Styles Only from Few Examples

83% match2024

LoopAnimate: Loopable Salient Object Animation

82% match2024

Cite this paper

@article{chen2024inverse,
  title  = {Inverse Painting: Reconstructing The Painting Process},
  author = {Bowei Chen and Yifan Wang and Brian Curless and Ira Kemelmacher-Shlizerman and Steven M. Seitz},
  year   = {2024},
  eprint = {2409.20556},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.20556v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2409.20556.svg)](https://codeofpaper.com/paper/2409.20556)

Discussion