Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction

TL;DR

This paper introduces a novel end-to-end framework for 3D parametric curve reconstruction from multi-view edge maps, utilizing a curve-aware Gaussian representation and adaptive topology optimization for improved accuracy and efficiency.

Contribution

It proposes a one-stage, differentiable approach that directly reconstructs 3D parametric curves, overcoming limitations of traditional two-stage methods.

Findings

Outperforms two-stage methods in accuracy and robustness.

Reduces parameter count and training time.

Achieves superior results on ABC dataset and real-world benchmarks.

Abstract

This paper presents an end-to-end framework for reconstructing 3D parametric curves directly from multi-view edge maps. Contrasting with existing two-stage methods that follow a sequential ``edge point cloud reconstruction and parametric curve fitting'' pipeline, our one-stage approach optimizes 3D parametric curves directly from 2D edge maps, eliminating error accumulation caused by the inherent optimization gap between disconnected stages. However, parametric curves inherently lack suitability for rendering-based multi-view optimization, necessitating a complementary representation that preserves their geometric properties while enabling differentiable rendering. We propose a novel bi-directional coupling mechanism between parametric curves and edge-oriented Gaussian components. This tight correspondence formulates a curve-aware Gaussian representation, \textbf{CurveGaussian}, that enables differentiable rendering of 3D curves, allowing direct optimization guided by multi-view evidence. Furthermore, we introduce a dynamically adaptive topology optimization framework during training to refine curve structures through linearization, merging, splitting, and pruning operations. Comprehensive evaluations on the ABC dataset and real-world benchmarks demonstrate our one-stage method's superiority over two-stage alternatives, particularly in producing cleaner and more robust reconstructions. Additionally, by directly optimizing parametric curves, our method significantly reduces the parameter count during training, achieving both higher efficiency and superior performance compared to existing approaches.