IEEE Transactions on Industrial Informatics · 2025 · 17 citations · 22 references
ComputingComputer ScienceComputer GraphicsComputer VisionComputer-aided Design3D ReconstructionGeometry ProcessingShape RepresentationSurface ReconstructionBenchmark DatasetsComputer-aided Design ModelsEditable ParametersIntermediate Representation Design
In this article, we propose Img2CAD, the first approach to our knowledge that uses 2-D image inputs to generate computer-aided design (CAD) models with editable parameters. Unlike existing artificial intelligence (AI) methods for 3-D 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 3-D reconstruction and CAD software. We have identified an innovative intermediate representation called structured visual geometry, characterized by vectorized wireframes extracted from objects. This representation significantly enhances the performance of generating conditioned CAD models. In addition, we introduce two new datasets to further support research in this area: <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a big cad model dataset (ABC)-mono</b>, the largest known dataset comprising over 200 000 3-D CAD models with rendered images, and <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">KOCAD</b>, the first dataset featuring real-world captured objects alongside their ground truth CAD models, supporting further research in conditioned CAD model generation.
22
Diffusion Probabilistic Models for 3D Point Cloud Generation
Shitong Luo, Wei Hu · 2021 · 566 citations
Stacked Hourglass Network for Robust Facial Landmark Localisation
Jing Yang, Qingshan Liu, Kaihua Zhang · 2017 · 292 citations
Wonder3D: Single Image to 3D Using Cross-Domain Diffusion
Xiaoxiao Long, Yuan–Chen Guo, Cheng Lin et al. · 2024 · 284 citations
Holistically-Attracted Wireframe Parsing