%0 Journal Article
%T CDNet&#65306;空间向量用于双视图对应学习的研究<br>CDNet: Using Spatial Vectors for Two-View Correspondence Learning Research
%A 李浩然
%J Computer Science and Application
%P 22-32
%@ 2161-881X
%D 2025
%I Hans Publishing
%R 10.12677/csa.2025.154074
%X 特征匹配是计算机视觉中的一项基本而重要的任务&#65292;目的是在给定的一对图像之间找到正确的对应关系(即内线)。严格地说&#65292;特征匹配通常包括四个步骤&#65292;即特征提取、特征描述、建立初始对应集和去除虚假对应(即离群值去除)。然而&#65292;现有的方法单纯考虑到了对应点之间的联系&#65292;而忽视了场景图片中可以获取的视觉信息。在本文中&#65292;我们提出了一种新型剪枝框架Context Depth Net (CDNet)来准确识别内线和恢复相机姿态。我们从对应点中提取方向信息作为提示方法指导剪枝操作&#65292;并利用向量场更好地挖掘对应之间的深层空间信息&#65292;最后设计一组融合模块来使空间信息更好融合。实验表明&#65292;所提出的CDNet在室内室外数据集上的测试结果优于先前提出的方法。<br>Feature matching is a fundamental and crucial task in computer vision, aiming to find the correct correspondences (<i>i.e.</i>, inliers) between a given pair of images. Strictly speaking, feature matching typically involves four steps: feature extraction, feature description, establishing an initial set of correspondences, and removing false correspondences (<i>i.e.</i>, outlier removal). However, existing methods only consider the connections between corresponding points while neglecting the visual information that can be obtained from scene images. In this paper, we propose a novel pruning framework called Context Depth Net (CDNet) to accurately identify inliers and recover camera poses. We extract directional information from corresponding points as a cue to guide the pruning process, and utilize vector fields to better mine the deep spatial information between correspondences. Finally, we design a set of fusion modules to better integrate the spatial information. Experiments show that the proposed CDNet performs better on indoor and outdoor datasets than previously proposed methods.
%K 向量场&#65292
%K 上下文&#65292
%K Transformer<br>Vector Field
%K Context
%K Transformer
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=110876