{"slug": "code-native-generation-of-highly-programmable-3d-assets-2026", "title": "Code-native generation of highly programmable 3D assets (2026)", "summary": "Nova3D, a system that generates 3D assets as executable Blender source code, produces a valid artifact for all 54 items in its Nova3D-Bench benchmark, with every asset exposing named parts in a parent-child assembly tree, satisfying 51 of 52 prompt-stated numeric and count constraints (best baseline: 11/52), and articulating 59 joints across 12 assets at 98.3% geometric validity, outperforming eleven baselines in four families.", "body_md": "# Computer Science > Graphics\n\n[Submitted on 22 Jul 2026]\n\n# Title:Nova3D: Code-Native Generation of Programmable 3D Assets\n\n[View PDF](/pdf/2607.22738)\n\n[HTML (experimental)](https://arxiv.org/html/2607.22738v1)\n\nAbstract:Current 3D generative models mostly produce a final surface: a visually strong but largely opaque mesh. Interactive 3D worlds need more than a surface. They need named parts, an assembly hierarchy, measurable constraints, local edit handles, and joints for articulation. We present Nova3D, a system that generates 3D assets as executable Blender source code; the compiled mesh, a binary glTF (GLB), is treated as the artifact, not the asset. Because the output is a program, semantic handles exist at generation time rather than being recovered afterward by segmentation or rigging. We evaluate on Nova3D-Bench, a frozen, spec-grounded benchmark of 54 items across six domains and three difficulty levels with text and image inputs, against eleven baselines in four families (mesh-native, part-structured, code-native, and CAD) plus a same-LLM ablation. Nova3D produces an executable program and a valid artifact for 54/54 items. Every asset exposes named parts organized in a parent-child assembly tree; no mesh-native, CAD, or segmentation baseline exposes either. It satisfies 51/52 prompt-stated numeric and count constraints (best baseline: 11/52), passes 14/18 blinded local edits with locality preserved in 18/18, and articulates 59 joints across 12 assets at 98.3% geometric validity, where every baseline exposes zero native joints. Its geometry is competitive: it wins the structured domains in a pairwise shape-quality tournament and is second only to the strongest mesh-native model, while conceding texture realism to baked-PBR systems. The central result is representational: code-native generation turns a generated 3D object from an opaque surface into a programmable asset that downstream systems can inspect, measure, edit, and animate.\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/code-native-generation-of-highly-programmable-3d-assets-2026", "canonical_source": "https://arxiv.org/abs/2607.22738", "published_at": "2026-08-18 14:54:44+00:00", "updated_at": "2026-08-18 15:12:36.755583+00:00", "lang": "en", "topics": ["generative-ai", "artificial-intelligence", "computer-vision"], "entities": ["Nova3D", "Nova3D-Bench", "Blender"], "alternates": {"html": "https://wpnews.pro/news/code-native-generation-of-highly-programmable-3d-assets-2026", "markdown": "https://wpnews.pro/news/code-native-generation-of-highly-programmable-3d-assets-2026.md", "text": "https://wpnews.pro/news/code-native-generation-of-highly-programmable-3d-assets-2026.txt", "jsonld": "https://wpnews.pro/news/code-native-generation-of-highly-programmable-3d-assets-2026.jsonld"}}