Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.13234 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914094041268224 |
|---|---|
| author | Yan, Yinglong Yue, Jun Xia, Shaobo Sun, Hanmeng Ying, Tianxu Wu, Chengcheng Lan, Sifan He, Min Ghamisi, Pedram Fang, Leyuan |
| author_facet | Yan, Yinglong Yue, Jun Xia, Shaobo Sun, Hanmeng Ying, Tianxu Wu, Chengcheng Lan, Sifan He, Min Ghamisi, Pedram Fang, Leyuan |
| contents | Vector extraction retrieves structured vector geometry from raster images, offering high-fidelity representation and broad applicability. Existing methods, however, are usually tailored to a single vector type (e.g., polygons, polylines, line segments), requiring separate models for different structures. This stems from treating instance attributes (category, structure) and geometric attributes (point coordinates, connections) independently, limiting the ability to capture complex structures. Inspired by the human brain's simultaneous use of semantic and spatial interactions in visual perception, we propose UniVector, a unified VE framework that leverages instance-geometry interaction to extract multiple vector types within a single model. UniVector encodes vectors as structured queries containing both instance- and geometry-level information, and iteratively updates them through an interaction module for cross-level context exchange. A dynamic shape constraint further refines global structures and key points. To benchmark multi-structure scenarios, we introduce the Multi-Vector dataset with diverse polygons, polylines, and line segments. Experiments show UniVector sets a new state of the art on both single- and multi-structure VE tasks. Code and dataset will be released at https://github.com/yyyyll0ss/UniVector. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_13234 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UniVector: Unified Vector Extraction via Instance-Geometry Interaction Yan, Yinglong Yue, Jun Xia, Shaobo Sun, Hanmeng Ying, Tianxu Wu, Chengcheng Lan, Sifan He, Min Ghamisi, Pedram Fang, Leyuan Computer Vision and Pattern Recognition Vector extraction retrieves structured vector geometry from raster images, offering high-fidelity representation and broad applicability. Existing methods, however, are usually tailored to a single vector type (e.g., polygons, polylines, line segments), requiring separate models for different structures. This stems from treating instance attributes (category, structure) and geometric attributes (point coordinates, connections) independently, limiting the ability to capture complex structures. Inspired by the human brain's simultaneous use of semantic and spatial interactions in visual perception, we propose UniVector, a unified VE framework that leverages instance-geometry interaction to extract multiple vector types within a single model. UniVector encodes vectors as structured queries containing both instance- and geometry-level information, and iteratively updates them through an interaction module for cross-level context exchange. A dynamic shape constraint further refines global structures and key points. To benchmark multi-structure scenarios, we introduce the Multi-Vector dataset with diverse polygons, polylines, and line segments. Experiments show UniVector sets a new state of the art on both single- and multi-structure VE tasks. Code and dataset will be released at https://github.com/yyyyll0ss/UniVector. |
| title | UniVector: Unified Vector Extraction via Instance-Geometry Interaction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.13234 |