EUVIMEDEUVIMED entdecken
Crossref

MM‐CAD: A Multi‐Modal CAD Dataset and Benchmark for Cross‐Modal Geometric Learning

Anush Bharathi, Ananthakrishnan A, Ramanathan Muthuganapathy

Computer Graphics Forum · 13.08.2026

DOI: 10.1111/cgf.70523 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 13.08.2026. Verfasst von Anush Bharathi und 2 weiteren Autor:innen. Die Arbeit nennt 75 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Computer‐Aided Design (CAD) boosts modern manufacturing, yet design reuse remains constrained by the absence of large, openly available CAD repositories with rich multi‐modal annotations suitable for search/retrieval. Recent large‐scale efforts to annotate public datasets rely on hash‐based redundancy removal that leaves no semantic structure, and on captioning by Vision‐Language Models (VLMs) using rendered images alone, which struggles to capture geometric and procedural information. We introduce MM‐CAD, a multi‐modal CAD dataset designed to level‐up retrieval and retrieval‐augmented generation models for engineering geometry, comprising two complementary parts. MM‐CAD:A brings 33,816 unique CAD models from eleven widely used benchmark datasets under a common identifier scheme, with isometric renderings, point clouds, and humanly‐curated multi‐level text captions, and 4,376 real hand‐drawn user sketches among others. MM‐CAD:B curates 192,626 models from the 1M‐model ABC corpus through a seven‐stage pipeline centered on Manifold‐Aware Adaptive Sampling (MAAS), which organizes models into semantically coherent neighborhoods rather than merely removing duplicates, directly supplying the hard negatives that contrastive retrieval training requires. Every retained model is annotated through a metadata‐grounded pipeline that conditions caption generation on parsed construction sequences rather than rendered views alone, producing three‐level text descriptions, multi‐level contour sketches, a hierarchical application taxonomy, and photorealistic in‐context images that largely preserve source CAD geometry, a modality not previously available at this scale on CAD data. We further introduce a joint retrieval architecture that aligns sketch, text, image, B‐Rep, and point cloud encoders in a single latent space through Matryoshka‐nested contrastive objectives, establishing the first unified cross‐modal retrieval benchmark for large‐scale CAD.

Zitieren

APA

Bharathi, A., A, A., & Muthuganapathy, R. (2026). MM‐CAD: A Multi‐Modal CAD Dataset and Benchmark for Cross‐Modal Geometric Learning. Computer Graphics Forum. https://doi.org/10.1111/cgf.70523

Vancouver

Bharathi A, A A, Muthuganapathy R. MM‐CAD: A Multi‐Modal CAD Dataset and Benchmark for Cross‐Modal Geometric Learning. Computer Graphics Forum. 2026. doi:10.1111/cgf.70523

BibTeX
@article{Bharathi2026,
  author = {Bharathi, Anush and A, Ananthakrishnan and Muthuganapathy, Ramanathan},
  title = {MM‐CAD: A Multi‐Modal CAD Dataset and Benchmark for Cross‐Modal Geometric Learning},
  journal = {Computer Graphics Forum},
  year = {2026},
  doi = {10.1111/cgf.70523}
}
Kostenlos starten →