Research map / Probabilistic and scientific modeling / Variational and generative sampling
Modelling complex vector drawings with stroke-clouds
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes generative models for highly complex vector drawings by representing them as unordered clouds of strokes rather than sequences, avoiding the auto-regressive modelling that fails to scale.
Problem
Generative modelling of complex vector drawings, which existing sequential auto-regressive approaches fail to scale to beyond simple drawings.
Approach
Defines generative models over vector drawings treated as stroke-clouds (sets of strokes) instead of ordered sequences, moving away from primarily sequential auto-regressive modelling to handle highly complex drawings.
Closest papers by meaning
- CoSE: Compositional Stroke Embeddings (NeurIPS 2020 · similarity 0.89)
- Cloud2Curve: Generation and Vectorization of Parametric Sketches (CVPR 2021 · similarity 0.89)
- SketchINR: A First Look into Sketches as Implicit Neural Representations (CVPR 2024 · similarity 0.87)
- Neural 3D Strokes: Creating Stylized 3D Scenes with Vectorized 3D Strokes (CVPR 2024 · similarity 0.87)
- SketchAgent: Language-Driven Sequential Sketch Generation (CVPR 2025 · similarity 0.86)
- DrawingsDreamer: A Unified Multi-View Engineering Drawings Generation Model (NeurIPS 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.