三維資產更可編輯

Papers arxiv:2608.

26238 Copy markdown Procedura: Agentic 3D Modeling with Procedural Control Published on Aug 26 · Submitted by Youtian Lin on Aug 28 · Nanjing University Upvote 10 +2 Authors: Youtian Lin ,Yikang Yang ,Zhanpeng Hu ,Mengqi Zhou ,Feihu Zhang ,Xun Cao ,Jiaheng Liu ,Yao Yao Abstract Procedura is a 3D modeling agent that generates editable, part-structured procedural assemblies with sharp geometry and validated articulation from text prompts.

Generated by thinkingmachines/Inkling-Small Native 3D generators now recover impressive mesh geometry from a single image.However, a dense mesh stays soft where a machined object should be sharp, it carries no part decomposition, and it exposes no parameter a user could edit.

To address this, we explore the paradigm of 3D shape as code, leveraging and scaling the coding ability of an LLM for 3D modeling.

We introduce Procedura, a novel 3D modeling agent framework that writes an object as a procedural assembly, a parametric program whose named parts are joined by typed, machine-checkable mates.

From a text prompt, the agent plans the object as an assembly graph and writes the program part by part, solving each placement from the mated frames rather than guessing it, and admitting a part only once compile, mate, and connectivity checks pass.

A decoupled vision critic then refines the assembly one diagnosed fix at a time.Moreover, the same graph carries per-part materials and a simulator-validated articulation.We evaluate on P3D-Bench under its assembly judge, and with the same judge on MechBench-36, our hard-surface benchmark.

On both, Procedura outperforms state-of-the-art native 3D generators and every prior 3D-code agent on judged quality, produces the sharpest edges of any method we evaluate, and is the only one whose output is an editable, part-structured program.

View arXiv page View PDF Project page GitHub 96 Add to collection Community LoYoT Paper author Paper submitter 2 days ago Procedura turns a text prompt into an editable parametric 3D program, with optional per-part materials and articulation.

Reply librarian-bot 1 day ago This is an automated message from the Librarian Bot.I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API Nova3D: Code-Native Generation of Programmable 3D Assets (2026) SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation (2026) aDSL: Agentic 3D Creation via Joint Agent-Program Design (2026) PhysX-CoT: Structured Physical Reasoning from a Single Image to Simulation-Ready 3D Assets (2026) NeoWorld-Pro: Programming Interactive Scenes from Monocular Images for Embodied Simulation (2026) ArtiMo: Agent-Driven Articulated Mesh Animation (2026) ArtLang: Structured Language-to-Kinematics Grounding for Articulated 3D Actuation (2026) Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend Reply EditPreview Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images Comment · Sign up or log in to comment Upvote 10 Get this paper in your agent: hf papers read 2608.26238 Don't have the latest CLI?curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0 No model linking this paper Cite arxiv.org/abs/2608.

26238 in a model README.md to link it from this page.Datasets citing this paper 1 Spaces citing this paper 0 No Space linking this paper Cite arxiv.org/abs/2608.26238 in a Space README.md to link it from this page.Collections including this paper 1