PulseAugur
EN
LIVE 15:43:11

New datasets aim to advance AI-assisted CAD program generation

Researchers have introduced two new datasets aimed at advancing AI-assisted Computer-Aided Design (CAD). CADBench offers a unified benchmark with 18,000 samples across six families, five input modalities, and six metrics to evaluate AI systems for CAD program generation. FllumaOne, a code-native dataset, provides 100,000 samples with executable Python programs and validated feature histories, supporting various CAD reconstruction tasks. Both datasets aim to standardize evaluation and drive progress in the field of editable 3D reconstruction. AI

IMPACT These datasets will enable more rigorous evaluation and development of AI models for 3D reconstruction and design.

RANK_REASON Two new research papers introducing datasets for AI-assisted CAD.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New datasets aim to advance AI-assisted CAD program generation

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Anna C. Doris, Jacob Thomas Sony, Ghadi Nehme, Era Syla, Amin Heyrani Nobari, Faez Ahmed ·

    CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation

    arXiv:2605.10873v2 Announce Type: replace-cross Abstract: Recovering editable CAD programs from images or 3D observations is central to AI-assisted design, but progress is difficult to measure because existing evaluations are fragmented across datasets, modalities, and metrics. W…

  2. arXiv cs.AI TIER_1 English(EN) · Jizong Zhan ·

    FllumaOne: A Code-Native Multimodal CAD Dataset with Executable Programs and Kernel-Validated Feature Histories

    arXiv:2606.17696v1 Announce Type: new Abstract: Parametric computer-aided design records both final geometry and the ordered construction history that determines how a part can be edited. Datasets for editable CAD research should therefore expose modeling operations, parameters, …