Order Matters: 3D Shape Generation from Sequential VR Sketches

TL;DR

This paper presents VRSketch2Shape, a novel framework and dataset for generating 3D shapes from sequential VR sketches, emphasizing the importance of stroke order for improved shape reconstruction.

Contribution

It introduces an order-aware sketch encoder, a large dataset of synthetic and real sketches, and a pipeline for generating sequential VR sketches from arbitrary shapes.

Findings

Higher geometric fidelity than prior methods

Effective generalization from synthetic to real sketches

Robust performance on partial sketches

Abstract

VR sketching lets users explore and iterate on ideas directly in 3D, offering a faster and more intuitive alternative to conventional CAD tools. However, existing sketch-to-shape models ignore the temporal ordering of strokes, discarding crucial cues about structure and design intent. We introduce VRSketch2Shape, the first framework and multi-category dataset for generating 3D shapes from sequential VR sketches. Our contributions are threefold: (i) an automated pipeline that generates sequential VR sketches from arbitrary shapes, (ii) a dataset of over 20k synthetic and 900 hand-drawn sketch-shape pairs across four categories, and (iii) an order-aware sketch encoder coupled with a diffusion-based 3D generator. Our approach yields higher geometric fidelity than prior work, generalizes effectively from synthetic to real sketches with minimal supervision, and performs well even on partial sketches. All data and models will be released open-source at https://chenyizi086.github.io/VRSketch2Shape_website.