CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation

2025-04-27

AI Summary

This work addresses the topological inconsistency and geometric distortion arising from decoupled vertex-edge-face modeling in existing 3D wireframe generation methods. We propose the first framework that unifies geometric and topological structure into a continuous, fixed-length latent representation (CLR) for 3D curve wireframes. Our approach integrates neural parametric curve representation with an attention-enhanced variational autoencoder, coupled with flow matching for efficient and expressive latent-space modeling. The framework supports both unconditional generation and conditional generation guided by point clouds or images. Extensive experiments demonstrate state-of-the-art performance in reconstruction accuracy, shape novelty, and structural diversity. It robustly handles complex geometries and irregular topologies—enabling applications in CAD design, geometry reconstruction, and controllable 3D content synthesis.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

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.

Problem

• Integrates geometry and topology for 3D wireframe generation
• Encodes curves and connectivity into continuous latent space
• Improves accuracy and diversity in shape generation

Innovation

• Unified Continuous Latent Representation for 3D wireframes
• Attention-driven VAE encodes Neural Parametric Curves
• Flow matching model maps noise to latents