GRCVMar 20, 2025

Bézier Splatting for Fast and Differentiable Vector Graphics Rendering

arXiv:2503.16424v31 citationsh-index: 2
Originality Highly original
AI Analysis

This addresses the bottleneck of costly optimization and poor rendering quality in image vectorization and synthesis, offering a significant speedup and better results for users in graphics and ML applications.

The paper tackles the problem of slow and low-quality differentiable vector graphics rendering by introducing Bézier Splatting, which achieves 30x faster forward and 150x faster backward rasterization for open curves compared to DiffVG while improving visual fidelity.

Differentiable vector graphics (VGs) are widely used in image vectorization and vector synthesis, while existing representations are costly to optimize and struggle to achieve high-quality rendering results for high-resolution images. This work introduces a new differentiable VG representation, dubbed Bézier Splatting, that enables fast yet high-fidelity VG rasterization. Bézier Splatting samples 2D Gaussians along Bézier curves, which naturally provide positional gradients at object boundaries. Thanks to the efficient splatting-based differentiable rasterizer, Bézier Splatting achieves 30x and 150x faster per forward and backward rasterization step for open curves compared to DiffVG. Additionally, we introduce an adaptive pruning and densification strategy that dynamically adjusts the spatial distribution of curves to escape local minima, further improving VG quality. Furthermore, our new VG representation supports conversion to standard XML-based SVG format, enhancing interoperability with existing VG tools and pipelines. Experimental results show that Bézier Splatting significantly outperforms existing methods with better visual fidelity and significant optimization speedup.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes