HandMade: Spatial Prompting for Generative 3D Creation with Part-Labeled VR Sketches
This work addresses the problem of specifying spatial intent in 3D generation for users who need precise control over object layout and part relationships.
HandMade introduces a workflow combining VR 3D sketching with language for open-domain 3D generation, using part-labeled sketches as spatial prompts. It outperforms text-only and sketch-based baselines in preserving user-authored spatial scaffolds across 20 examples.
Text-to-3D generation lowers the barrier to 3D content creation, but text alone is a weak interface for specifying spatial intent: where parts should be placed, how they relate, and how an object should be organized in 3D. We present HandMade, a workflow that combines VR 3D sketching and language for open-domain 3D asset generation. HandMade treats coarse, part-labeled 3D sketches not as incomplete geometry to reconstruct directly, but as spatial prompts for existing generative models. It converts segmented VR strokes into multi-view part guidance and structured prompts, allowing users to specify object layout and part relationships through 3D sketching while using language for identity, material, style, and local details. A technical evaluation shows that HandMade better preserves user-authored spatial scaffolds than text-only and sketch-based baselines on 20 varied examples. A user study with eight participants characterizes how users make use of 3D sketching for spatial layout and language for identity, materials, and details across initial authoring and subsequent revision. HandMade contributes an interaction paradigm and interface-to-generation pipeline for spatially guided 3D creation.