Pith. sign in

REVIEW 9 cited by

CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM

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 2411.04954 v3 pith:5Y4ZUYRV submitted 2024-11-07 cs.CV

Jingwei Xu , Chenyu Wang , Zibo Zhao , Wen Liu , Yi Ma , Shenghua Gao This is my paper
classification cs.CV
keywords modelscad-mllmdatadesignmodelmultimodalqualitycommand
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper aims to design a unified Computer-Aided Design (CAD) generation system that can easily generate CAD models based on the user's inputs in the form of textual description, images, point clouds, or even a combination of them. Towards this goal, we introduce the CAD-MLLM, the first system capable of generating parametric CAD models conditioned on the multimodal input. Specifically, within the CAD-MLLM framework, we leverage the command sequences of CAD models and then employ advanced large language models (LLMs) to align the feature space across these diverse multi-modalities data and CAD models' vectorized representations. To facilitate the model training, we design a comprehensive data construction and annotation pipeline that equips each CAD model with corresponding multimodal data. Our resulting dataset, named Omni-CAD, is the first multimodal CAD dataset that contains textual description, multi-view images, points, and command sequence for each CAD model. It contains approximately 450K instances and their CAD construction sequences. To thoroughly evaluate the quality of our generated CAD models, we go beyond current evaluation metrics that focus on reconstruction quality by introducing additional metrics that assess topology quality and surface enclosure extent. Extensive experimental results demonstrate that CAD-MLLM significantly outperforms existing conditional generative methods and remains highly robust to noises and missing points. The project page and more visualizations can be found at: https://cad-mllm.github.io/

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

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

  1. CADENA: Stepwise CAD Reverse Engineering

    cs.CV 2026-08 conditional novelty 7.0 of 10

    A vision-language model that grows a CAD program step by step, rendering target and current build together after every operation, outperforms single-pass baselines on mechanical part reconstruction.

  2. BANG: Dividing 3D Assets via Generative Exploded Dynamics

    cs.GR 2025-07 conditional novelty 7.0 of 10

    A diffusion-based method that generates smooth exploded-view sequences of 3D objects, enabling part-level decomposition, control, and reassembly.

  3. AIMold: An Autonomous AI-based Pipeline for Complex Mold Design

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A new dataset and deep learning pipeline generate upper and lower molds, parting surfaces, and auxiliary components for complex injection-molded parts.

  4. ASSEMCAD: Production-Ready CAD Assembly Generation from Natural Language

    cs.AI 2026-07 conditional novelty 6.0 of 10

    AssemCAD generates production-oriented CAD assemblies from language via axiom-grounded specs, port-mate libraries, on-demand factories, and geometry-aware verification, beating code-only baselines on AssemBench.

  5. SOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction

    cs.CV 2026-07 conditional novelty 6.0 of 10

    SOV-CAD recovers CAD modeling sequences from orthographic images via Decision-Transformer offline RL conditioned on stepwise three-views plus sketch canvas and IoU-based rewards, beating holistic baselines with better...

  6. MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshes

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    MV-GEL uses a learned view selector and a fine-tuned vision-language segmentation model to localize text-described faces and edges on 3D meshes.

  7. BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning

    cs.LG 2026-02 conditional novelty 6.0 of 10

    BrepCoder trains one multimodal LLM to read B-rep CAD geometry and output CAD code, handling reverse engineering, completion, error correction, and CAD-QA.

  8. STEP-LLM: Generating CAD STEP Models from Natural Language with Large Language Models

    cs.AI 2026-01 conditional novelty 6.0 of 10

    STEP-LLM fine-tunes LLMs to emit complete STEP CAD files from natural-language captions, reporting lower median Chamfer distance than Text2CAD.

  9. BrepLLM: Enabling Large Language Models to Understand Boundary Representations

    cs.CV 2025-12 conditional novelty 6.0 of 10

    BrepLLM feeds boundary-representation CAD graphs directly into an LLM and reports state-of-the-art CAD captioning and generative classification over point-cloud 3D-LLM baselines.

Pith tools