mlsanityData to 7 Oct 2026

Drawing-Recode: Annotation Grounding for Parametric CAD Code Generation from Raster 2D CAD Drawings

arXiv 2607.27558 ↗First posted 30 Jul 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Recovering Parametric CAD sequences from raster-format 2D Computer-Aided Design (CAD) drawings accumulated prior to digital transformation is important for part reproduction and manufacturing process automation. However, existing studies either process only vector drawings or are limited to specific domains, and fail to explicitly connect dimensional annotations to geometric information, limiting their use of dimensional information for 3D Parametric CAD sequences recovery. We propose Drawing-Recode, a framework that generates Parametric CAD sequences as CAD code from raster 2D CAD drawings. Drawing-Recode extracts geometric features via an image encoder and recognizes annotations through a separate text recognition module, then explicitly grounds annotations to geometric information using cross-attention and our proposed Annotation Grounding Loss (AGL). The resulting features are fed into a Large Language Model (LLM) to generate CAD code in the Structured Parametric CAD Code (SPCC) format. Experiments show that Drawing-Recode outperforms existing baselines and remains robust on scanned drawings resembling industrial conditions. We expect Drawing-Recode contributes to digitizing raster 2D CAD drawings in industrial settings and to part reproduction and manufacturing automation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 35 references that are in the map. First posted on arXiv 30 Jul 2026.

Builds on

21 of 35 references.

References · 21

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  6. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  7. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,033
  8. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  9. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 266
  10. 2024Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performancecited by 94
  11. 2022SVTR: Scene Text Recognition with a Single Visual Modelcited by 86
  12. 2025CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generationcited by 65
9 more
  1. 2024CAD-Recode: Reverse Engineering CAD Code from Point Cloudscited by 63
  2. 2025CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Rewardcited by 53
  3. 2025Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilitiescited by 43
  4. 2025Large Language Models for Computer-Aided Design: A Surveycited by 16
  5. 2024From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approachcited by 15
  6. 2025Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawingscited by 9
  7. 2026Towards High-Fidelity CAD Generation via LLM-Driven Program Generation and Text-Based B-Rep Primitive Groundingcited by 6
  8. 2021Photo2CAD: Automated 3D solid reconstruction from 2D drawings using OpenCVcited by 4
  9. 2026BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoningcited by 3

Built on by

Not cited yet.