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

• URL: http://arxiv.org/abs/2608.05539v1
• Date: Thu, 06 Aug 2026 02:36:22 GMT
• Title: OmniMech: All-in-one Multimodal Mechanical Benchmark for 3D Reconstruction
• Abstract summary: We introduce OmniMech, the first million-scale benchmark for evaluating vision-language models on CAD generation from industrial data.<n> OmniMech contains more than 251,000 fully dimensioned and toleranced 2D orthographic drawings, paired with native CAD models.<n>We will release the benchmark data, evaluation code, and tool interfaces to support future research.
• Score: 15.427717696810456
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generation [17.467056775887944]
  MUSE is a Text-to-CAD benchmark focused on complex, editable boundary representation assemblies.<n>MUSE evaluates generated models through a three-stage protocol: code check, geometric check, and design-intent alignment.<n> Experiments on closed-source and open-source LLMs reveal a clear failure cascade from executable code to valid geometry.
  arXiv  Detail & Related papers  (2026-05-27T15:01:59Z)
• CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation [3.6136995620089145]
  We introduce CADBench, a unified benchmark for multimodal CAD program generation.<n>CADBench contains 18,000 evaluation samples spanning six benchmark families.<n>We benchmark eleven CAD-specialized and general-purpose vision-language systems, generating more than 1.4 million CAD programs.
  arXiv  Detail & Related papers  (2026-05-11T17:25:47Z)
• BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CAD [14.284307846349774]
  We present BenchCAD, a unified benchmark for industrial CAD reasoning.<n> BenchCAD contains 17,900 execution-verified CadQuery programs across 106 industrial part families.<n>It evaluates models through visual question answering, code question answering, image-to-code generation, and instruction-guided code editing.
  arXiv  Detail & Related papers  (2026-05-11T17:13:36Z)
• Zero-to-CAD: Agentic Synthesis of Interpretable CAD Programs at Million-Scale Without Real Data [8.896486786253766]
  We introduce Zero-to-CAD, a scalable framework for executable CAD construction sequences.<n>We frame synthesis as an agentic search problem: by embedding a large language model within a feedback-driven CAD environment, our system iteratively generates, executes, and validates code.<n>This agentic approach enables the synthesis of approximately one million executable, readable, editable CAD sequences.
  arXiv  Detail & Related papers  (2026-04-27T13:46:41Z)
• DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces [67.45867367326105]
  We propose DreamCAD, a multi-modal generative framework that directly produces editable BReps from point-level supervision.<n>DreamCAD represents each BRep as a set of parametric patches and uses a differentiable tessellation method to generate meshes.<n>DreamCAD achieves state-of-the-art performance on ABC and averse benchmarks across text, image, and point modalities.
  arXiv  Detail & Related papers  (2026-03-05T19:04:07Z)
• From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation [47.67703214044401]
  We propose CAD-RL, a multimodal Chain-of-Thought guided reinforcement learning framework for CAD modeling code generation.<n>Our method combines Cold Start with goal-driven reinforcement learning post training using three task-specific rewards.<n>Experiments demonstrate that CAD-RL achieves significant improvements in reasoning quality, output precision, and code executability.
  arXiv  Detail & Related papers  (2025-08-13T18:30:49Z)
• RAG-6DPose: Retrieval-Augmented 6D Pose Estimation via Leveraging CAD as Knowledge Base [112.72361202480154]
  We present RAG-6DPose, a retrieval-augmented approach that leverages 3D CAD models as a knowledge base.<n> Experimental results on standard benchmarks and real-world robotic tasks demonstrate the effectiveness and robustness of our approach.
  arXiv  Detail & Related papers  (2025-06-23T17:19:41Z)
• E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models [78.1674905950243]
  We present the first comprehensive benchmark for 3D geometric foundation models (GFMs)<n>GFMs directly predict dense 3D representations in a single feed-forward pass, eliminating the need for slow or unavailable precomputed camera parameters.<n>We evaluate 16 state-of-the-art GFMs, revealing their strengths and limitations across tasks and domains.<n>All code, evaluation scripts, and processed data will be publicly released to accelerate research in 3D spatial intelligence.
  arXiv  Detail & Related papers  (2025-06-02T17:53:09Z)
• CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning [31.342222156939403]
  We introduce CReFT-CAD, a two-stage fine-tuning paradigm that first employs a curriculum-driven reinforcement learning stage with difficulty-aware rewards to build reasoning ability steadily.<n>We release TriView2CAD, the first large-scale, open-source benchmark for orthographic projection reasoning.
  arXiv  Detail & Related papers  (2025-05-31T13:52:56Z)
• CADReview: Automatically Reviewing CAD Programs with Error Detection and Correction [11.33947758511237]
  We introduce the CAD review task to automatically detect and correct potential errors.<n>In this paper, we propose the CAD program repairer (ReCAD) framework to effectively detect program errors.<n>We create a dataset, CADReview, consisting of over 20K program-image pairs, with diverse errors for the CAD review task.
  arXiv  Detail & Related papers  (2025-05-28T12:41:00Z)
• CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images [69.7768227804928]
  CADCrafter is an image-to-parametric CAD model generation framework that trains solely on synthetic textureless CAD data.<n>We introduce a geometry encoder to accurately capture diverse geometric features.<n>Our approach can robustly handle real unconstrained CAD images, and even generalize to unseen general objects.
  arXiv  Detail & Related papers  (2025-04-07T06:01:35Z)
• PHT-CAD: Efficient CAD Parametric Primitive Analysis with Progressive Hierarchical Tuning [52.681829043446044]
  ParaCAD comprises over 10 million annotated drawings for training and 3,000 real-world industrial drawings with complex topological structures and physical constraints for test.<n> PHT-CAD is a novel 2D PPA framework that harnesses the modality alignment and reasoning capabilities of Vision-Language Models.
  arXiv  Detail & Related papers  (2025-03-23T17:24:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.