Sketch2Arti: Sketch-based Articulation Modeling of CAD Objects

TL;DR

Sketch2Arti is a novel sketch-based system that automatically infers articulation and motion parameters for CAD objects from simple 2D sketches, enabling intuitive editing and animation.

Contribution

It introduces a category-agnostic approach for translating lightweight sketches into articulated 3D models, including internal structure completion for shell models.

Findings

Successfully generalizes to diverse object categories.

Enables iterative articulation modeling with fine-grained control.

Demonstrates effectiveness through experiments and user evaluations.

Abstract

Articulation modeling aims to infer movable parts and their motion parameters for a 3D object, enabling interactive animation, simulation, and shape editing. In this paper, we present Sketch2Arti, the first sketch-based articulation modeling system for CAD objects. Our key observation is that designers naturally communicate articulation intent through lightweight sketches (e.g., arrows and strokes) that indicate how parts should move, yet translating such sketches into articulated 3D models remains largely manual. Sketch2Arti bridges this gap by enabling users to specify articulation through simple 2D sketches drawn from a chosen viewpoint. Given a CAD model and user sketches, our approach automatically discovers the corresponding movable parts and predicts their motion parameters, allowing iterative modeling of multiple articulations on complex objects with fine-grained control. Importantly, Sketch2Arti is trained in a category-agnostic manner without requiring object category information, leading to strong generalization to diverse objects beyond existing articulation datasets. Moreover, for shell models lacking interior structures, Sketch2Arti supports controllable internal completion guided by user sketches, generating plausible internal components consistent with the existing geometry and predicted motion constraints. Comprehensive experiments and user evaluations demonstrate the effectiveness, controllability, and generalization of Sketch2Arti. The code, dataset, and the prototype system are at https://arlo-yang.github.io/Sketch2Arti.