Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Jaerin, Lee, Kanggeon, Lee, Kyoung Mu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911673900597248
author Lee, Jaerin
Lee, Kanggeon
Lee, Kyoung Mu
author_facet Lee, Jaerin
Lee, Kanggeon
Lee, Kyoung Mu
contents Differentiable vector graphics have enabled powerful gradient-based optimization of vector primitives directly from raster images. However, existing frameworks formulate this as a flat optimization problem, forcing hundreds to thousands of randomly initialized curves to blindly compete for pixel-level error reduction. This disordered optimization leads to topology collapse, where macroscopic structures are distorted by internal high-frequency noise, resulting in a redundant and uneditable "polygon soup" that limits practical editability. To address this limitation, we propose Vector Scaffolding, a novel hierarchical optimization framework that shifts from flat pixel-matching to structured topological construction tailored for vector graphics. By identifying a key cause of topology collapse as the mathematical imbalance between area and boundary gradients, we introduce Interior Gradient Aggregation to stabilize the learning dynamics of multi-scale curve mixtures. Upon this stabilized landscape, we employ Progressive Stratification and Rapid Inflation Scheduling to progressively densify vector primitives with extremely high learning rates ($\times 50$). Experiments demonstrate that our approach accelerates optimization by $2.5\times$ while simultaneously improving PSNR by up to 1.4 dB over the previous state of the art.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11913
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization
Lee, Jaerin
Lee, Kanggeon
Lee, Kyoung Mu
Computer Vision and Pattern Recognition
Differentiable vector graphics have enabled powerful gradient-based optimization of vector primitives directly from raster images. However, existing frameworks formulate this as a flat optimization problem, forcing hundreds to thousands of randomly initialized curves to blindly compete for pixel-level error reduction. This disordered optimization leads to topology collapse, where macroscopic structures are distorted by internal high-frequency noise, resulting in a redundant and uneditable "polygon soup" that limits practical editability. To address this limitation, we propose Vector Scaffolding, a novel hierarchical optimization framework that shifts from flat pixel-matching to structured topological construction tailored for vector graphics. By identifying a key cause of topology collapse as the mathematical imbalance between area and boundary gradients, we introduce Interior Gradient Aggregation to stabilize the learning dynamics of multi-scale curve mixtures. Upon this stabilized landscape, we employ Progressive Stratification and Rapid Inflation Scheduling to progressively densify vector primitives with extremely high learning rates ($\times 50$). Experiments demonstrate that our approach accelerates optimization by $2.5\times$ while simultaneously improving PSNR by up to 1.4 dB over the previous state of the art.
title Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.11913