CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation
This provides an efficient solution for CAD design, geometric reconstruction, and 3D content creation, though it appears incremental as it builds on existing generative approaches.
The paper tackles 3D curve-based wireframe generation by introducing CLR-Wire, a framework that integrates geometry and topology into a continuous latent representation, resulting in substantial improvements in accuracy, novelty, and diversity compared to state-of-the-art methods.
We introduce CLR-Wire, a novel framework for 3D curve-based wireframe generation that integrates geometry and topology into a unified Continuous Latent Representation. Unlike conventional methods that decouple vertices, edges, and faces, CLR-Wire encodes curves as Neural Parametric Curves along with their topological connectivity into a continuous and fixed-length latent space using an attention-driven variational autoencoder (VAE). This unified approach facilitates joint learning and generation of both geometry and topology. To generate wireframes, we employ a flow matching model to progressively map Gaussian noise to these latents, which are subsequently decoded into complete 3D wireframes. Our method provides fine-grained modeling of complex shapes and irregular topologies, and supports both unconditional generation and generation conditioned on point cloud or image inputs. Experimental results demonstrate that, compared with state-of-the-art generative approaches, our method achieves substantial improvements in accuracy, novelty, and diversity, offering an efficient and comprehensive solution for CAD design, geometric reconstruction, and 3D content creation.