Pith. sign in

REVIEW 4 cited by

Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometry

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.03417 v1 pith:QRL3ZZRR submitted 2024-10-04 cs.CV

Tianrun Chen , Chunan Yu , Yuanqi Hu , Jing Li , Tao Xu , Runlong Cao , Lanyun Zhu , Ying Zang
show 3 more authors
Yong Zhang Zejian Li Linyun Sun
This is my paper · ORCID
classification cs.CV
keywords modelsconditionedgenerationimageimg2cadmodeldatasetfirst
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In this paper, we propose Img2CAD, the first approach to our knowledge that uses 2D image inputs to generate CAD models with editable parameters. Unlike existing AI methods for 3D model generation using text or image inputs often rely on mesh-based representations, which are incompatible with CAD tools and lack editability and fine control, Img2CAD enables seamless integration between AI-based 3D reconstruction and CAD software. We have identified an innovative intermediate representation called Structured Visual Geometry (SVG), characterized by vectorized wireframes extracted from objects. This representation significantly enhances the performance of generating conditioned CAD models. Additionally, we introduce two new datasets to further support research in this area: ABC-mono, the largest known dataset comprising over 200,000 3D CAD models with rendered images, and KOCAD, the first dataset featuring real-world captured objects alongside their ground truth CAD models, supporting further research in conditioned CAD model generation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. HoLa: B-Rep Generation using a Holistic Latent Representation

    cs.GR 2025-04 conditional novelty 7.0 of 10

    HoLa stores a full B-Rep in surface-only latent vectors, recovers curves from surface pairs via a neural intersection module, and generates valid CAD models from multiple conditions with 82 percent validity.

  2. Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Drawing2CAD generates parametric CAD operation sequences from SVG engineering drawings, outperforming a raster-input baseline and a DeepCAD-vector baseline on accuracy and validity.

  3. CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation

    cs.CV 2025-04 conditional novelty 6.0 of 10

    CMT is a cascade masked autoregressive model that generates B-Rep CAD models from multimodal inputs, paired with the new mmABC dataset of 1.35M annotated CAD models.

  4. Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilities

    cs.AI 2025-05 conditional novelty 5.0 of 10

    Fine-tuning pretrained LLMs to emit CadQuery code directly from text outperforms the Text2CAD command-sequence baseline on geometric metrics, with the best open-source 3B model achieving the reported gains.

Pith tools