Unified and Efficient Point-Line Local Features

2026-08-20

AI Summary

为提高多视图计算机视觉效率，提出UPAL特征提取器，统一提取关键点、线段和描述符，加速处理并减少计算成本。

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.

Problem

• multi-view computer vision
• sparse keypoints
• robust descriptors
• line features
• real-time performance

Innovation

• Unified Feature Extractor
• Lightweight Architecture
• Efficient Line Detection
• Shared Backbone
• Accelerated Post-Processing