Draw2Cut: Direct On-Material Annotations for CNC Milling

TL;DR

Draw2Cut introduces a sketch-based workflow that lets users annotate wood directly with color pens to define blueprints and toolpaths, thereby bypassing traditional CAD in CNC milling. The system relies on registration between physical space and a virtual model, interpreted via a three-color drawing language, and provides cut previews before fabrication. Technical evaluation shows sub-millimeter alignment accuracy within the work area, and demonstrations showcase joinery, customization, and kerf-based engraving, plus a user workshop and discussions of limitations. The approach promises to lower barriers to personal fabrication, boost creativity, and broaden accessibility in subtractive woodworking, with open-source tooling for broader adoption.

Abstract

Creating custom artifacts with computer numerical control (CNC) milling machines typically requires mastery of complex computer-aided design (CAD) software. To eliminate this user barrier, we introduced Draw2Cut, a novel system that allows users to design and fabricate artifacts by sketching directly on physical materials. Draw2Cut employs a custom-drawing language to convert user-drawn lines, symbols, and colors into toolpaths, thereby enabling users to express their creative intent intuitively. The key features include real-time alignment between material and virtual toolpaths, a preview interface for validation, and an open-source platform for customization. Through technical evaluations and user studies, we demonstrate that Draw2Cut lowers the entry barrier for personal fabrication, enabling novices to create customized artifacts with precision and ease. Our findings highlight the potential of the system to enhance creativity, engagement, and accessibility in CNC-based woodworking.

Figures (15)

• Figure 1: Design space for exploring the interaction methods, including four aspects: (a) possible input, (b) necessary output, (c) procedure of how the drawing language is developed, and (d) application scope.
• Figure 2: Various tools, including (a) several sizes of wood and three erasable color pens. If the user is dissatisfied with their drawing (b), they may erase it (c) and redraw it (d).
• Figure 3: Concept of drawing language illustrating how various colors and symbols can be utilized to accurately communicate cut intent and the method. Left panel: Top view of symbols describing the cut type and cut direction. Right panel: Side view of the difference in output between using the red pen and the green pen.
• Figure 4: Visualization interface for users to specify the cut depth (the orange box on the right) and smooth size (the blue box) for each item, providing users with three types of visualizations: reconstructed mesh based on the collected point cloud data (interface on the left-bottom), the target mesh that shows the result, and an animation that explains the cut procedure.
• Figure 5: Technical processes for data collection, virtual space construction, image interpretation, and trajectory planning.