Unified and Efficient Point-Line Local Features

• URL: http://arxiv.org/abs/2608.19894v1
• Date: Thu, 20 Aug 2026 11:03:13 GMT
• Title: Unified and Efficient Point-Line Local Features
• Abstract summary: Multi-view computer vision pipelines typically rely on accurate sparse keypoints and robust descriptors.<n>Existing point-line approaches remain inefficient: they detect points and lines separately, use increasingly heavy networks, and depend on CPU-bounds that hinder real-time performance.<n>We introduce a Unified Efficient Points and Lines (UPAL) feature extractor that jointly extracts keypoints, line segments, and feature descriptors within a single lightweight architecture.<n>UPAL matches or exceeds state-of-the-art performance in both point and line applications while significantly reducing computational cost, achieving, for instance, a 4x speedup and 10x smaller memory
• Score: 49.49543960319266
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-view computer vision pipelines typically rely on accurate sparse keypoints and robust descriptors. While incorporating line features has shown clear benefits for matching and pose estimation, existing point-line approaches remain inefficient: they detect points and lines separately, use increasingly heavy networks, and depend on CPU-bound heuristics that hinder real-time performance. We introduce a Unified Efficient Points and Lines (UPAL) feature extractor that jointly extracts keypoints, line segments, and feature descriptors within a single lightweight architecture. A shared backbone provides common representations that feed different branches for point and line features. Line segments are recovered through an accelerated post-processing stage, an enhanced and highly efficient variant of the LSD algorithm. UPAL matches or exceeds state-ofthe-art performance in both point and line applications while significantly reducing computational cost, achieving, for instance, a 4x speedup and 10x smaller memory footprint over the ALIKED + DeepLSD pipeline. Code is publicly available at https://github.com/francois141/upal.

Related papers

• Co-PLNet: A Collaborative Point-Line Network for Prompt-Guided Wireframe Parsing [5.175452394220525]
  Existing methods predict lines and junctions separately and reconcile them post-hoc, causing mismatches and reduced robustness.<n>We present Co-PLNet, a point-line collaborative framework that exchanges spatial cues between the two tasks.<n>Experiments on Wireframe and YorkUrban show consistent improvements in accuracy and robustness, together with favorable real-time efficiency.
  arXiv  Detail & Related papers  (2026-01-26T08:16:02Z)
• Fast SAM2 with Text-Driven Token Pruning [52.8350457627401]
  Segment Anything Model 2 (SAM2), a vision computation model has significantly advanced in prompt-driven video object segmentation.<n>SAM2 pipelines propagate all visual tokens produced by the image encoder through downstream temporal reasoning modules, regardless of their relevance to the target object.<n>We introduce a text-guided token pruning framework that improves inference efficiency by selectively reducing token density prior to temporal propagation.
  arXiv  Detail & Related papers  (2025-12-24T18:59:05Z)
• LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching [70.96686341680648]
  LightGlueStick is a lightweight matcher for points and line segments.<n>We show that LightGlueStick establishes a new state-of-the-art across different benchmarks.
  arXiv  Detail & Related papers  (2025-10-18T10:20:14Z)
• Representing 3D sparse map points and lines for camera relocalization [1.2974519529978974]
  We show how a lightweight neural network can learn to represent both 3D point and line features. In tests, our method secures a significant lead, marking the most considerable enhancement over state-of-the-art learning-based methodologies.
  arXiv  Detail & Related papers  (2024-02-28T03:07:05Z)
• Dynamic Perceiver for Efficient Visual Recognition [87.08210214417309]
  We propose Dynamic Perceiver (Dyn-Perceiver) to decouple the feature extraction procedure and the early classification task. A feature branch serves to extract image features, while a classification branch processes a latent code assigned for classification tasks. Early exits are placed exclusively within the classification branch, thus eliminating the need for linear separability in low-level features.
  arXiv  Detail & Related papers  (2023-06-20T03:00:22Z)
• IDLS: Inverse Depth Line based Visual-Inertial SLAM [9.38589798999922]
  Inverse Depth Line SLAM (IDLS) is proposed to track the line features in SLAM in an accurate and efficient way. IDLS is extensively evaluated in multiple perceptually-challenging datasets.
  arXiv  Detail & Related papers  (2023-04-23T20:53:05Z)
• ELSD: Efficient Line Segment Detector and Descriptor [9.64386089593887]
  We present the novel Efficient Line Segment Detector and Descriptor (ELSD) to simultaneously detect line segments and extract their descriptors in an image. ELSD provides the essential line features to the higher-level tasks like SLAM and image matching in real time. In the experiments, the proposed ELSD achieves the state-of-the-art performance on the Wireframe dataset and YorkUrban dataset.
  arXiv  Detail & Related papers  (2021-04-29T08:53:03Z)
• SOLD2: Self-supervised Occlusion-aware Line Description and Detection [95.8719432775724]
  We introduce the first joint detection and description of line segments in a single deep network. Our method does not require any annotated line labels and can therefore generalize to any dataset. We evaluate our approach against previous line detection and description methods on several multi-view datasets.
  arXiv  Detail & Related papers  (2021-04-07T19:27:17Z)
• Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes [98.65457534223539]
  We propose a real-time high-performance DCNN-based method for robust semantic segmentation of urban street scenes. The proposed method achieves the accuracy of 73.6% and 68.0% mean Intersection over Union (mIoU) with the inference speed of 51.0 fps and 39.3 fps.
  arXiv  Detail & Related papers  (2020-03-11T08:45:53Z)

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.