# Controlling Your Image via Simplified Vector Graphics

Source: [Controlling Your Image via Simplified Vector Graphics](<https://www.sota2.com/research/paper/6993f64c9ebc499c97409cf0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-18T05:00:15.522Z

Authors: Lanqing Guo, Xi Liu, Yufei Wang, Zhihao Li, Siyu Huang

Published: 2026-02-16T03:56:42.000Z

## Abstract

Recent advances in image generation have achieved remarkable visual quality, while a fundamental challenge remains: Can image generation be controlled at the element level, enabling intuitive modifications such as adjusting shapes, altering colors, or adding and removing objects? In this work, we address this challenge by introducing layer-wise controllable generation through simplified vector graphics (VGs). Our approach first efficiently parses images into hierarchical VG representations that are semantic-aligned and structurally coherent. Building on this representation, we design a novel image synthesis framework guided by VGs, allowing users to freely modify elements and seamlessly translate these edits into photorealistic outputs. By leveraging the structural and semantic features of VGs in conjunction with noise prediction, our method provides precise control over geometry, color, and object semantics. Extensive experiments demonstrate the effectiveness of our approach in diverse applications, including image editing, object-level manipulation, and fine-grained content creation, establishing a new paradigm for controllable image generation. Project page: https://guolanqing.github.io/Vec2Pix/

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Controllable Image Generation on 5,000-image Reconstruction (evaluation)](<https://www.sota2.com/research/sota/controllable-image-generation-on-5-000-image-reconstruction-evaluation.md>): Controllable Image Generation; 5,000-image Reconstruction (evaluation); FID: 15.52.

- [Controllable Image Generation on Editing 5,000-image](<https://www.sota2.com/research/sota/controllable-image-generation-on-editing-5-000-image.md>): Controllable Image Generation; Editing 5,000-image (evaluation); FID: 17.84.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.14443>)

[PDF](<https://arxiv.org/pdf/2602.14443.pdf>)