PaintCopilot: Modeling Painting as Autonomous Artistic Continuation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913148012855296 |
|---|---|
| author | Wen, Yunge Shen, Yuancheng Liang, Paul Pu |
| author_facet | Wen, Yunge Shen, Yuancheng Liang, Paul Pu |
| contents | We present PaintCopilot, a co-creative neural painting assistant that models painting as an open-ended autoregressive artistic behavior conditioned on evolving canvas states and prior brushstroke history, without requiring a target image. Unlike existing neural painting methods that frame painting as pixel reconstruction toward a predefined reference, PaintCopilot predicts future strokes directly from learned artistic dynamics, analogous to how large language models continue text sequences from prior context.
The framework proposes three complementary models: a ViT-based Target Predictor that infers artist intent from partial canvas observations, an autoregressive Next Stroke Predictor that generates temporally coherent brushstrokes via flow matching, and a VAE-based Region Sampler that synthesizes semantically localized stroke sequences on demand. Built on three differentiable brush representations (Hard Round, Brush Tip, and 2D Gaussian), the system supports four interactive workflows: Optimize History, Stroke Completion, Region Inpainting, and Dynamic Brush. Through case studies with professional artists, we demonstrate that PaintCopilot enables fluid co-creative painting workflows in which artists and AI continuously alternate control throughout the creative process. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_20941 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PaintCopilot: Modeling Painting as Autonomous Artistic Continuation Wen, Yunge Shen, Yuancheng Liang, Paul Pu Computer Vision and Pattern Recognition Graphics Human-Computer Interaction We present PaintCopilot, a co-creative neural painting assistant that models painting as an open-ended autoregressive artistic behavior conditioned on evolving canvas states and prior brushstroke history, without requiring a target image. Unlike existing neural painting methods that frame painting as pixel reconstruction toward a predefined reference, PaintCopilot predicts future strokes directly from learned artistic dynamics, analogous to how large language models continue text sequences from prior context. The framework proposes three complementary models: a ViT-based Target Predictor that infers artist intent from partial canvas observations, an autoregressive Next Stroke Predictor that generates temporally coherent brushstrokes via flow matching, and a VAE-based Region Sampler that synthesizes semantically localized stroke sequences on demand. Built on three differentiable brush representations (Hard Round, Brush Tip, and 2D Gaussian), the system supports four interactive workflows: Optimize History, Stroke Completion, Region Inpainting, and Dynamic Brush. Through case studies with professional artists, we demonstrate that PaintCopilot enables fluid co-creative painting workflows in which artists and AI continuously alternate control throughout the creative process. |
| title | PaintCopilot: Modeling Painting as Autonomous Artistic Continuation |
| topic | Computer Vision and Pattern Recognition Graphics Human-Computer Interaction |
| url | https://arxiv.org/abs/2605.20941 |