Hyperstroke: A Novel High-quality Stroke Representation for Assistive Artistic Drawing
This work addresses the challenge for artists by providing a more intuitive and user-friendly assistive drawing tool, though it appears incremental as it builds on existing methods with a new representation.
The paper tackles the problem of ineffective modeling of intricate stroke details and temporal aspects in assistive artistic drawing by introducing hyperstroke, a novel stroke representation that captures precise fine details like RGB appearance and alpha-channel opacity, resulting in a compact tokenized representation learned from real-life drawing videos.
Assistive drawing aims to facilitate the creative process by providing intelligent guidance to artists. Existing solutions often fail to effectively model intricate stroke details or adequately address the temporal aspects of drawing. We introduce hyperstroke, a novel stroke representation designed to capture precise fine stroke details, including RGB appearance and alpha-channel opacity. Using a Vector Quantization approach, hyperstroke learns compact tokenized representations of strokes from real-life drawing videos of artistic drawing. With hyperstroke, we propose to model assistive drawing via a transformer-based architecture, to enable intuitive and user-friendly drawing applications, which are experimented in our exploratory evaluation.