This paper introduces a state-of-the-art method for line art vectorization using 2D Gaussian splatting and Bézier splines, achieving high-quality vector outputs with compatibility for user input and video applications.
# 2D Gaussian Splatting for Bézier Spline Line Art Vectorization
Source: [https://studios.disneyresearch.com/2026/07/16/2d-gaussian-splatting-for-bezier-spline-line-art-vectorization/](https://studios.disneyresearch.com/2026/07/16/2d-gaussian-splatting-for-bezier-spline-line-art-vectorization/)
### In this work, we leverage several recent advances in the field to introduce a new state\-of\-the\-art method for line art vectorization\.
**July 16, 2026**
**SIGGRAPH \(2026\)**
#### Authors
Tianhao Chen \(DisneyResearch\|Studios/ETH Zurich\)
Clara Fernandez \(DisneyResearch\|Studios\)
Marteinn Oskarsson \(Walt Disney Animation Studios\)
Chuck Tappan \(Walt Disney Animation Studios\)
Olga Sorkine\-Hornung \(ETH Zurich\)
Markus Gross \(DisneyResearch\|Studios/ETH Zurich\)
Christopher Schroers \(DisneyResearch\|Studios\)
Abdelaziz Djelouah \(DisneyResearch\|Studios\)
#### 2D Gaussian Splatting for Bézier Spline Line Art Vectorization
Vectorization of line art and sketches is an important problem in computer graphics and remains an active area of research\. In this paper, we leverage several recent advances in the field to introduce a new state\-of\-the\-art method for line art vectorization\. First, we show that it is possible to go beyond heuristics to extract a meaningful set of strokes from a raster image\. We leverage both depth prediction and semantic feature extraction models to propose a more principled approach to split the skeleton graph of the sketch into subgraphs to initialize a set of strokes, producing results that better align with artistic intent\. Second, we model strokes as Bézier curves with both geometric and appearance components, and employ 2D Gaussian splatting for fast, di erentiable rendering\. This formulation enables e cient tting of strokes to the input while jointly optimizing control points and brush texture\.We further demonstrate promising results on video by incorporating temporal tracking and adaptive keyframe introduction\. Our evaluation shows that we achieve state\-of\-the\-art results for image reconstruction, while being fast and producing strokes of high quality\. More importantly, the tting is highly compatible with user input, through the correction of the splines and the selection of optimization parameters\.
### Copyright Notice
The documents contained in these directories are included by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non\-commercial basis\. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically\. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author’s copyright\. These works may not be reposted without the explicit permission of the copyright holder\.
##### Research at Disney
##### Legal
##### MORE
The author describes building an interactive painting tool that uses edge information from an image to guide 2D Gaussian splats as brush strokes, avoiding slow gradient descent methods and producing painting-like results.
ZipSplat is a token-based feed-forward 3D Gaussian Splatting model that uses k-means clustering to decouple Gaussian placement from the pixel grid, achieving ~6x fewer Gaussians while setting new state-of-the-art results on DL3DV and RealEstate10K without requiring ground-truth poses or intrinsics.
Researchers propose Gaussian Point Splatting, a stochastic rendering method using pixel-sized opaque points and 64-bit GPU atomics that scales to hundreds of millions of Gaussians in real time. The method, accepted at SIGGRAPH 2026, employs hierarchical culling and parallel programming primitives to achieve even workload distribution with only minor noise differences compared to original Gaussian splatting.
GlobalSplat introduces an efficient feed-forward framework for 3D Gaussian splatting that achieves compact and consistent scene reconstruction using global scene tokens, reducing computational overhead and inference time to under 78ms. The method uses a coarse-to-fine training approach to prevent representation bloat while maintaining competitive novel-view synthesis performance with significantly fewer Gaussians (16K) compared to dense baselines.