# NURBS Splatting: A Unified Differentiable Rendering Framework for Vector Graphics

arXiv: https://arxiv.org/abs/2606.31764 · HTML: https://mlsanity.com/paper/2606.31764/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 54 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Builds on (most cited first, 26 of 26)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [CLIPstyler: Image Style Transfer with a Single Text Condition](https://mlsanity.com/paper/2112.00374/) (2021)
- [CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders](https://mlsanity.com/paper/2106.14843/) (2021)
- [VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models](https://mlsanity.com/paper/2211.11319/) (2022)
- [BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometry](https://mlsanity.com/paper/2401.15563/) (2024)
- [GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting](https://mlsanity.com/paper/2403.08551/) (2024)
- [Towards Layer-wise Image Vectorization](https://mlsanity.com/paper/2206.04655/) (2022)
- [SVGDreamer: Text Guided SVG Generation with Diffusion Model](https://mlsanity.com/paper/2312.16476/) (2023)
- [Word-As-Image for Semantic Typography](https://mlsanity.com/paper/2303.01818/) (2023)
- [DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models](https://mlsanity.com/paper/2306.14685/) (2023)
- [CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator](https://mlsanity.com/paper/2005.12500/) (2020)
- [DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality](https://mlsanity.com/paper/2303.14585/) (2023)
- [VecFusion: Vector Font Generation with Diffusion](https://mlsanity.com/paper/2312.10540/) (2023)
- [StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding](https://mlsanity.com/paper/2012.08687/) (2020)
- [Layered Image Vectorization via Semantic Simplification](https://mlsanity.com/paper/2406.05404/) (2024)
- [NURBS-Diff: A Differentiable Programming Module for NURBS](https://mlsanity.com/paper/2104.14547/) (2021)
- [Calliffusion: Chinese Calligraphy Generation and Style Transfer with Diffusion Modeling](https://mlsanity.com/paper/2305.19124/) (2023)
- [NeuroNURBS: Learning Efficient Surface Representations for 3D Solids](https://mlsanity.com/paper/2411.10848/) (2024)
- [Bezier Splatting for Fast and Differentiable Vector Graphics Rendering](https://mlsanity.com/paper/2503.16424/) (2025)
- [B'ezierGS: Dynamic Urban Scene Reconstruction with B'ezier Curve Gaussian Splatting](https://mlsanity.com/paper/2506.22099/) (2025)
- [Neural Image Abstraction Using Long Smoothing B-Splines](https://mlsanity.com/paper/2511.05360/) (2025)
- [Image-Space Collage and Packing with Differentiable Rendering](https://mlsanity.com/paper/2406.04008/) (2024)

## Abstract (arXiv)

Differentiable rendering of planar rational splines remains largely underexplored, despite their widespread use in vector graphics and design. Existing differentiable vector renderers primarily focus on B'ezier curves and rely on analytic rasterization, which can suffer from gradient instability and limited flexibility. We propose NURBS Splatting, a unified framework that represents planar rational curves as continuous Gaussian fields. By sampling Gaussians along the curve parameter domain and inside closed regions, rendering is reformulated as a smooth accumulation process with stable gradients. Our method naturally supports long splines, rational weights, non-uniform knots, and closed-region filling. We demonstrate its effectiveness in calligraphy reconstruction, vectorization frameworks, and long-spline image abstraction, showing improved stability and reconstruction quality over existing approaches.