UniVector: Unified Vector Extraction via Instance-Geometry Interaction

• URL: http://arxiv.org/abs/2510.13234v1
• Date: Wed, 15 Oct 2025 07:39:25 GMT
• Title: UniVector: Unified Vector Extraction via Instance-Geometry Interaction
• Abstract summary: Uni is a unified VE framework that leverages instancegeometry interaction to extract multiple vector types within a single model.<n>Uni 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.
• Score: 28.129438331953452
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Vector Map as Language: Toward Unified Remote Sensing Vector Mapping [52.15388144187478]
  We propose Vector Map as Language (VecLang), a unified paradigm that reformulates multiclass vector mapping as structured text generation.<n>VecLang encodes the common elements of different geospatial entities into a GeoJSON-like vector language.<n>We show that VecLang handles both single-class and multiclass vector mapping while achieving strong cross-dataset and open-vocabulary generalization.
  arXiv  Detail & Related papers  (2026-06-09T11:02:51Z)
• See More, Match Better: Multi-Source Feature Fusion for Two-View Correspondence Learning [52.52121389921707]
  Two-view correspondence learning aims to distinguish true correspondences (inliers) from false ones (outliers) in image pairs.<n>Existing methods mainly rely on coordinate-based geometric consistency.<n>We propose TriMatch, a multi-source feature fusion framework for two-view correspondence learning.
  arXiv  Detail & Related papers  (2026-06-08T09:33:01Z)
• SCAPO: Self-Supervised Category-Level Articulated Pose Estimation from a Single 3D Observation [54.98864436812187]
  We propose a self-supervised framework that estimates canonical geometry, rigid part segmentation, and joint pivots, axes, and articulation states from a single RGB-D observation.<n> Experiments on synthetic and real articulated-object datasets show that our SCAPO recovers consistent part structure and accurate articulation parameters and outperforms all self-supervised baselines.
  arXiv  Detail & Related papers  (2026-06-01T09:04:49Z)
• Vector Linking via Cross-Model Local Isometric Consistency [11.584547136733889]
  We study Vector Linking: given two embedding clouds produced by different black-box encoders over partially overlapping datasets, recover cross-model object correspondences using only vectors.<n>We propose an iterative, reference-based geometric embedding hashing that recovers vector links from a tiny seed set of paired anchors.<n> Experiments across multiple benchmarks and embedding model pairs demonstrate accurate and robust linking under varying overlap, seed budgets, and out-of-domain anchors.
  arXiv  Detail & Related papers  (2026-05-29T10:12:52Z)
• Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds [49.95082206008502]
  Alignment across Trees is a method that constructs and aligns tree-like hierarchical features for both image and text modalities.<n>We introduce a semantic-aware visual feature extraction framework that applies a cross-attention mechanism to visual class tokens from intermediate Transformer layers.
  arXiv  Detail & Related papers  (2025-10-31T11:32:15Z)
• SegVec3D: A Method for Vector Embedding of 3D Objects Oriented Towards Robot manipulation [4.19191792860075]
  SegVec3D is a novel framework for 3D point cloud instance segmentation.<n>It integrates attention mechanisms, embedding learning, and cross-modal alignment.
  arXiv  Detail & Related papers  (2025-07-13T02:54:55Z)
• Learning Geometric Invariant Features for Classification of Vector Polygons with Graph Message-passing Neural Network [3.804240190982697]
  We propose a simple graph message-passing framework, PolyMP, to learn more expressive and robust latent representations of polygons.<n>This framework hierarchically captures self-looped graph information and learns geometric-invariant features for polygon shape classification.<n>Our findings indicate that PolyMP and PolyMP-DSC effectively capture expressive geometric features that remain invariant under common transformations.
  arXiv  Detail & Related papers  (2024-07-05T08:19:36Z)
• Correspondence Free Multivector Cloud Registration using Conformal Geometric Algebra [6.929025509877642]
  We present a novel theoretical approach to address the problem of correspondence free multivector cloud registration in conformal geometric algebra. We show that such formalism is able to: $(i)$ perform the registration without directly accessing the input multivectors. In this way, we can explicitly avoid solving the correspondences in the registration process.
  arXiv  Detail & Related papers  (2024-06-17T16:50:04Z)
• An Intrinsic Vector Heat Network [64.55434397799728]
  This paper introduces a novel neural network architecture for learning tangent vector fields embedded in 3D. We introduce a trainable vector heat diffusion module to spatially propagate vector-valued feature data across the surface. We also demonstrate the effectiveness of our method on the useful industrial application of quadrilateral mesh generation.
  arXiv  Detail & Related papers  (2024-06-14T00:40:31Z)
• AdaContour: Adaptive Contour Descriptor with Hierarchical Representation [52.381359663689004]
  Existing angle-based contour descriptors suffer from lossy representation for non-star shapes. AdaCon is able to represent shapes more accurately robustly than other descriptors.
  arXiv  Detail & Related papers  (2024-04-12T07:30:24Z)
• HiT: Building Mapping with Hierarchical Transformers [43.31497052507252]
  We propose a simple and novel building mapping method with Hierarchical Transformers, called HiT. HiT builds on a two-stage detection architecture by adding a polygon head parallel to classification and bounding box regression heads. Our method achieves a new state-of-the-art in terms of instance segmentation and polygonal metrics compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-18T10:24:25Z)
• VariGrad: A Novel Feature Vector Architecture for Geometric Deep Learning on Unregistered Data [3.4447129363520337]
  We present a novel geometric deep learning layer that leverages the varifold gradient to compute feature vector representations of 3D geometric data. Our model's use of parameterization independent varifold representations of geometric data allows our model to be both trained and tested on data independent of the given sampling or parameterization.
  arXiv  Detail & Related papers  (2023-07-07T12:37:37Z)
• Recurrent Generic Contour-based Instance Segmentation with Progressive Learning [111.31166268300817]
  We propose a novel deep network architecture, i.e., PolySnake, for generic contour-based instance segmentation. Motivated by the classic Snake algorithm, the proposed PolySnake achieves superior and robust segmentation performance.
  arXiv  Detail & Related papers  (2023-01-21T05:34:29Z)
• Segmenting Moving Objects via an Object-Centric Layered Representation [100.26138772664811]
  We introduce an object-centric segmentation model with a depth-ordered layer representation. We introduce a scalable pipeline for generating synthetic training data with multiple objects. We evaluate the model on standard video segmentation benchmarks.
  arXiv  Detail & Related papers  (2022-07-05T17:59:43Z)
• NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go [109.88509362837475]
  We present NeuroMorph, a new neural network architecture that takes as input two 3D shapes. NeuroMorph produces smooth and point-to-point correspondences between them. It works well for a large variety of input shapes, including non-isometric pairs from different object categories.
  arXiv  Detail & Related papers  (2021-06-17T12:25:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.