Learning Structured Representations of 3D CAD Models
| dc.contributor.author | Fenggen Yu | |
| dc.date.accessioned | 2024-12-11T08:11:14Z | |
| dc.date.available | 2024-12-11T08:11:14Z | |
| dc.date.issued | 2024-05-21 | |
| dc.description.abstract | Computer-Aided-Design (CAD) models have become widespread in engineering and manufacturing, driving decision-making and product evolution related to 3D models. Understanding the structure of 3D CAD models is crucial for various applications, as it can significantly benefit 3D shape analysis, modeling, and manipulation. With the rapid advancements in AI-powered solutions across all relevant fields, several CAD datasets have emerged to support research in 3D geometric deep learning. However, learning the structure of 3D CAD models presents a challenging task. The primary reason is the significant structure variations among small, intricate parts and the limited availability of labeled datasets to support structure learning of 3D CAD models. This thesis proposes several methods to learn structured representations for 3D CAD models to address these challenges. Firstly, we introduce CAPRI-Net, a self-supervised neural network that learns compact 3D CAD models with adaptive primitive assembly. CAPRI-Net can be trained without ground-truth primitive assembly, and it can reconstruct an input shape by assembling quadric surface primitives via Constructive Solid Geometry (CSG) operations. In our subsequent work, D2CSG, we modify the architecture of CAPRI-Net by assembling the primitives in two dual and complementary network branches, with network weights dropout strategy, to reconstruct 3D CAD models with dedicated details and high genus. Compared to CAPRI-Net, D2CSG is provably general and can produce more compact CSG trees. We further introduce DPA-Net, inspired by the volume rendering algorithm in Neural Radiance Fields (NeRF). DPA-Net uses primitive assembly and differentiable rendering to reconstruct 3D CAD models with textures from sparse views. Finally, we introduce HAL3D, the first active learning tool for fine-grained 3D part labeling. HAL3D can take the output of previous methods as input and assign fine-grained semantic labels to part sets of 3D CAD models along a pre-defined hierarchy tree. We develop two novel features to reduce human efforts: hierarchical and symmetry-aware active labeling. Our human-in-the-loop approach achieves close to error-free fine-grained annotations on any test set with pre-defined hierarchical part labels, with 80% time-saving over manual effort. | |
| dc.identifier.uri | https://diglib.eg.org/handle/10.2312/3607089 | |
| dc.language.iso | en | |
| dc.publisher | Simon Fraser University | |
| dc.title | Learning Structured Representations of 3D CAD Models |