# AnchorFlow: Learning Anchor Placement for Faithful and Editable SVG Reconstruction

arXiv: https://arxiv.org/abs/2605.19551 · HTML: https://mlsanity.com/paper/2605.19551/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 19 May 2026.

## Builds on (most cited first, 22 of 22)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation](https://mlsanity.com/paper/2007.11301/) (2020)
- [Im2Vec: Synthesizing Vector Graphics without Vector Supervision](https://mlsanity.com/paper/2102.02798/) (2021)
- [VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models](https://mlsanity.com/paper/2211.11319/) (2022)
- [StarVector: Generating Scalable Vector Graphics Code from Images and Text](https://mlsanity.com/paper/2312.11556/) (2023)
- [A Learned Representation for Scalable Vector Graphics](https://mlsanity.com/paper/1904.02632/) (2019)
- [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)
- [IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers](https://mlsanity.com/paper/2304.14400/) (2023)
- [OmniSVG: A Unified Scalable Vector Graphics Generation Model](https://mlsanity.com/paper/2504.06263/) (2025)
- [Rendering-Aware Reinforcement Learning for Vector Graphics Generation](https://mlsanity.com/paper/2505.20793/) (2025)
- [Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models](https://mlsanity.com/paper/2411.16602/) (2024)
- [Deep Vectorization of Technical Drawings](https://mlsanity.com/paper/2003.05471/) (2020)
- [SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis](https://mlsanity.com/paper/2406.09794/) (2024)
- [Layered Image Vectorization via Semantic Simplification](https://mlsanity.com/paper/2406.05404/) (2024)
- [Cloud2Curve: Generation and Vectorization of Parametric Sketches](https://mlsanity.com/paper/2103.15536/) (2021)
- [SVGBuilder: Component-Based Colored SVG Generation with Text-Guided Autoregressive Transformers](https://mlsanity.com/paper/2412.10488/) (2024)
- [Segmentation-guided Layer-wise Image Vectorization with Gradient Fills](https://mlsanity.com/paper/2408.15741/) (2024)
- [Image Vectorization: a Review](https://mlsanity.com/paper/2306.06441/) (2023)
- [SAMVG: A Multi-stage Image Vectorization Model with the Segment-Anything Model](https://mlsanity.com/paper/2311.05276/) (2023)
- [VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models](https://mlsanity.com/paper/2603.24575/) (2026)
- [AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling](https://mlsanity.com/paper/2604.10940/) (2026)

## Built on by (most cited first, 1 of 1)

- [DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editable](https://mlsanity.com/paper/2608.00548/) (2026)

## Abstract (arXiv)

Raster-to-SVG reconstruction requires faithful geometry and a compact control structure for editing. A central challenge is deciding where to place anchors: raster appearance alone does not determine how a contour should be divided into B'ezier segments. We present AnchorFlow, which learns anchor placement from designer-authored SVGs to reconstruct accurate curves with sparse controls. Our key idea is a sparse anchor field that jointly encodes contour geometry and reference segment junctions, including those along smooth contours. An anchor decoder predicts explicit anchor proposals from features learned under field supervision. These proposals guide boundary-constrained fitting and local refinement to recover cubic B'ezier paths. On clean single-path inputs, AnchorFlow achieves 99.52% mean IoU while using 56.6% fewer anchors on average than AdaVec, with lower boundary error and closer agreement with source-SVG anchor layouts. Under boundary perturbations, it maintains high fidelity with limited anchor growth. Integrated into a component-based pipeline, the same path module also produces compact, faithful full-image reconstructions. On four local-editing tasks, our outputs require less median active time and fewer actions than AdaVec and LIVE while retaining high target-shape accuracy.