Artisan: multi-agent pipeline generates physically grounded articulated 3D assets
nanyang-technological-university-singapore · hf · 2026-10-12
Overview
Researchers from NTU and partners present Artisan, targeting physically grounded articulated 3D asset generation — shifting from reproducing how objects look to capturing how they move and function. Extending Articraft, it adds a multi-agent pipeline with physical simulation feedback, enabling collision-free motion, stability under gravity, and accurate mass and material properties beyond geometry and appearance.
Benchmark
A unified benchmark spans spatial fidelity, physical plausibility, downstream task performance, and overall quality: 100 reference assets from ArtVIP and LightWheel, 50 stability prompts, and 50 ABO objects with reference masses.
Results
Across evaluations of 10+ representative models, Artisan achieves competitive spatial fidelity while attaining the lowest collision rates and highest stability rates.
More from Embodied
- RealHorse app quantifies horse lameness from smartphone video, dubbed 'Horse Tinder' — RexDouglass · 2026-10-12
- Yeah Hand: open-source humanoid robotic hand kits start at just $217 — CyberRobooo · 2026-10-12
- Fly-by-Code: coding agents program a tiltrotor drone with an arm, sim-to-real — furongh · 2026-10-12
- StreamRender-H3 renders interactive game worlds in real time with a 2-step diffusion model at 24 FPS — songhan_mit · 2026-10-12
- DexForce's UNITAS: a 1.7B 3D-native world action model tops LIBERO at 99.8%, beats 8B rivals — 机器之心 · 2026-10-12
- SuperNav: agentic navigation with pretrained multimodal models, no fine-tuning — rsasaki0109 · 2026-10-12