Search papers, labs, and topics across Lattice.
We introduce Artisan, a multi-agent generation pipeline that integrates physical simulation feedback to produce articulated 3D assets with physically grounded motion and functional attributes beyond mere appearance. This system addresses the critical gap in current 3D generation by enabling collision-free movement, gravitational stability, and accurate physical properties, moving beyond static geometry. Artisan achieves competitive spatial fidelity while significantly reducing collision rates and improving stability compared to existing methods, establishing a new benchmark for physically plausible and functionally usable 3D assets.
Existing 3D asset generators can now produce objects that not only look good but also move and function realistically, passing physics tests for stability and collision-free articulation.
In this paper, we study physically grounded articulated 3D asset generation---moving the goal from reproducing how objects look to capturing how they move and function. Inspired by the literature on procedural and agentic generation, we present Artisan, a system that extends the latest method Articraft by introducing a multi-agent pipeline with physical simulation feedback, enabling comprehensive attributes beyond geometry, appearance, and physically plausible articulation, such as collision-free motion, stability under gravity, and accurate mass and material properties. Furthermore, we construct a unified benchmark spanning four key aspects: spatial fidelity, physical plausibility, downstream task performance, and overall quality. The benchmark encompasses 100 reference assets from ArtVIP and LightWheel, 50 stability prompts, and 50 ABO objects with reference masses, with protocols evaluating various metrics. Through extensive evaluation of more than 10 representative models, Artisan achieves competitive spatial fidelity while attaining the lowest collision rates and highest stability rates among the evaluated methods. Together, our system and benchmark establish insights for advancing 3D generation towards physically plausible, functionally usable assets.
