mlsanityData to 7 Oct 2026

OmniMech: All-in-one Multimodal Mechanical Benchmark for 3D Reconstruction

arXiv 2608.05539 ↗First posted 6 Aug 2026cs.CVcited by 0

On the map: Multimodal LLMs / vision-language models → Chart understanding and anomaly detection

Abstract (arXiv)

Recent vision-language models (VLMs) can generate executable CAD programs from images, but existing methods mainly target coarse, general-purpose 3D objects and rarely address the fine-grained geometry and millimeter-level tolerances required in industrial mechanical design. We introduce OmniMech, the first million-scale benchmark for evaluating VLMs on executable CAD generation from industrial manufacturing data. OmniMech contains more than 251,000 fully dimensioned and toleranced 2D orthographic drawings, paired with native CAD models, multi-view renderings, mesh, STEP and B-rep representations, and rich semantic annotations. The benchmark includes four tasks: (1) parametric CAD program synthesis from engineering drawings; (2) diagram-to-3D reasoning for geometrically and structurally consistent reconstruction; (3) annotation-grounded reasoning over dimensions, symbols, feature callouts, and manufacturing constraints; and (4) tool-augmented agentic reasoning using visualization, measurement, CAD execution, and verification tools. Experiments show that current VLMs and CAD-specialized models still struggle with executable program synthesis, fine-grained 3D reconstruction, and reliable enforcement of dimensions and tolerances. We will release the benchmark data, evaluation code, and tool interfaces to support future research.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 23 of its 35 references that are in the map. First posted on arXiv 6 Aug 2026.

Builds on

23 of 35 references.

References · 23

  1. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  2. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  3. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  4. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  5. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 679
  6. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  7. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  8. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  9. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 421
  10. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
  11. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  12. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 266
11 more
  1. 2025SAM 3D: 3Dfy Anything in Imagescited by 230
  2. 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Modelscited by 204
  3. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  4. 2023DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Priorcited by 157
  5. 2025Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Materialcited by 157
  6. 2025Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attentioncited by 103
  7. 2025CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generationcited by 39
  8. 2025ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understandingcited by 34
  9. 2025CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generationcited by 18
  10. 2024From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approachcited by 15
  11. 2026SldprtNet: A Large-Scale Multimodal Dataset for CAD Generation in Language-Driven 3D Designcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation
  2. 2026BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CAD
  3. 2026Foundation Models for Automatic CAD Generation
  4. 2024CadVLM: Bridging Language and Vision in the Generation of Parametric CAD Sketches
  5. 2024CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM
  6. 2026Zero-to-CAD: Agentic Synthesis of Interpretable CAD Programs at Million-Scale Without Real Data
  7. 2026MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generation
  8. 2025CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning