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

• URL: http://arxiv.org/abs/2503.17029v1
• Date: Fri, 21 Mar 2025 10:39:04 GMT
• Title: AnimatePainter: A Self-Supervised Rendering Framework for Reconstructing Painting Process
• Authors: Junjie Hu, Shuyong Gao, Qianyu Guo, Yan Wang, Qishan Wang, Yuang Feng, Wenqiang Zhang,
• Abstract summary: We propose a self-supervised framework for generating drawing processes from any type of image.<n>Our approach reverses the drawing process by progressively removing strokes from a reference image, simulating a human-like creation sequence.<n>We model human drawings as "refinement" and "layering" processes and introduce depth fusion layers to enable video generation models to learn and replicate human drawing behavior.
• Score: 27.652358927257573
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Humans can intuitively decompose an image into a sequence of strokes to create a painting, yet existing methods for generating drawing processes are limited to specific data types and often rely on expensive human-annotated datasets. We propose a novel self-supervised framework for generating drawing processes from any type of image, treating the task as a video generation problem. Our approach reverses the drawing process by progressively removing strokes from a reference image, simulating a human-like creation sequence. Crucially, our method does not require costly datasets of real human drawing processes; instead, we leverage depth estimation and stroke rendering to construct a self-supervised dataset. We model human drawings as "refinement" and "layering" processes and introduce depth fusion layers to enable video generation models to learn and replicate human drawing behavior. Extensive experiments validate the effectiveness of our approach, demonstrating its ability to generate realistic drawings without the need for real drawing process data.

Related papers

• Learning to Synthesize Graphics Programs for Geometric Artworks [12.82009632507056]
  We present an approach that treats a set of drawing tools as executable programs. This method predicts a sequence of steps to achieve the final image. Experiments demonstrate that our program synthesizer, Art2Prog, can comprehensively understand complex input images.
  arXiv  Detail & Related papers  (2024-10-21T08:28:11Z)
• ProcessPainter: Learn Painting Process from Sequence Data [27.9875429986135]
  The painting process of artists is inherently stepwise and varies significantly among different painters and styles. Traditional stroke-based rendering methods break down images into sequences of brushstrokes, yet they fall short of replicating the authentic processes of artists. We introduce ProcessPainter, a text-to-video model that is initially pre-trained on synthetic data and subsequently fine-tuned with a select set of artists' painting sequences.
  arXiv  Detail & Related papers  (2024-06-10T07:18:41Z)
• SketchDreamer: Interactive Text-Augmented Creative Sketch Ideation [111.2195741547517]
  We present a method to generate controlled sketches using a text-conditioned diffusion model trained on pixel representations of images. Our objective is to empower non-professional users to create sketches and, through a series of optimisation processes, transform a narrative into a storyboard.
  arXiv  Detail & Related papers  (2023-08-27T19:44:44Z)
• Towards Interactive Image Inpainting via Sketch Refinement [13.34066589008464]
  We propose a two-stage image inpainting method termed SketchRefiner. In the first stage, we propose using a cross-correlation loss function to robustly calibrate and refine the user-provided sketches. In the second stage, we learn to extract informative features from the abstracted sketches in the feature space and modulate the inpainting process.
  arXiv  Detail & Related papers  (2023-06-01T07:15:54Z)
• I Know What You Draw: Learning Grasp Detection Conditioned on a Few Freehand Sketches [74.63313641583602]
  We propose a method to generate a potential grasp configuration relevant to the sketch-depicted objects. Our model is trained and tested in an end-to-end manner which is easy to be implemented in real-world applications.
  arXiv  Detail & Related papers  (2022-05-09T04:23:36Z)
• Quality Metric Guided Portrait Line Drawing Generation from Unpaired Training Data [88.78171717494688]
  We propose a novel method to automatically transform face photos to portrait drawings using unpaired training data. Our method can (1) learn to generate high quality portrait drawings in multiple styles using a single network and (2) generate portrait drawings in a "new style" unseen in the training data.
  arXiv  Detail & Related papers  (2022-02-08T06:49:57Z)
• DeepFacePencil: Creating Face Images from Freehand Sketches [77.00929179469559]
  Existing image-to-image translation methods require a large-scale dataset of paired sketches and images for supervision. We propose DeepFacePencil, an effective tool that is able to generate photo-realistic face images from hand-drawn sketches.
  arXiv  Detail & Related papers  (2020-08-31T03:35:21Z)
• Learning to Caricature via Semantic Shape Transform [95.25116681761142]
  We propose an algorithm based on a semantic shape transform to produce shape exaggerations. We show that the proposed framework is able to render visually pleasing shape exaggerations while maintaining their facial structures.
  arXiv  Detail & Related papers  (2020-08-12T03:41:49Z)
• Face Identity Disentanglement via Latent Space Mapping [47.27253184341152]
  We present a method that learns how to represent data in a disentangled way, with minimal supervision. Our key insight is to decouple the processes of disentanglement and synthesis, by employing a leading pre-trained unconditional image generator, such as StyleGAN. We show that our method successfully disentangles identity from other facial attributes, surpassing existing methods.
  arXiv  Detail & Related papers  (2020-05-15T18:24:49Z)
• SketchyCOCO: Image Generation from Freehand Scene Sketches [71.85577739612579]
  We introduce the first method for automatic image generation from scene-level freehand sketches. Key contribution is an attribute vector bridged Geneversarative Adrial Network called EdgeGAN. We have built a large-scale composite dataset called SketchyCOCO to support and evaluate the solution.
  arXiv  Detail & Related papers  (2020-03-05T14:54:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.