Xu Pan

Xu Pan

CV, DL, 3D Recon, GenAI in Wuhan, China, he/him

About

Master's student in LIESMARS, Wuhan University

Projects

2023
基于尺度先验学习的宽基线影像匹配研究
  • 通过CNN多尺度特征提取与注意力机制检测影像对重叠区域,获取尺度先验指导下游宽基线影像匹配
  • 创造性地将重叠估计问题转化为目标检测问题
2022

Intelligent Interpretation of Remote Sensing Images

2022

Global Natural Disaster Assessment System

2021
基于深度学习的三维重建与分层视觉定位
  • 基于前沿深度学习算法,从图像序列进行三维场景重建,并实现由粗到细的分层视觉定位
  • 负责整体框架的搭建以及算法改进与整合

Writing

2024
CoSAM: Segment Anything Co-Visible for Robust Feature Matching, The IEEE/CVF Conference on Computer Vision and Pattern Recognition (Submitted)

We introduce CoSAM, a novel matching framework designed to predict precise correspondences in uncontrolled environments. Unlike existing methods that rely on pixel-level correlation volumes spanning the entire image, we redefine the matching problem between image pairs as a co-visible region segmentation task within unified images. Our approach establishes binocular correspondences using a monocular vision foundational model. We derive hierarchical anchor points from learnable queries within a scale-aware transformer to guide pixel-wise co-visible region segmentation, enabling high-fidelity correspondences via the integration of diverse matching plugins. The prompt-based segmentation paradigm distinguishes our method from traditional semantic segmentation, which focuses on region-based class identification. This innovative paradigm effectively addresses the challenges posed by vast solution search spaces and complex one-to-many correspondence relationships, particularly in the presence of variations in viewpoints and scales. Experimental results in challenging scenarios demonstrate that CoSAM excels in both efficiency and effectiveness in feature matching and various downstream tasks.

2024
Scale-aware Co-visible Region Detection for Hierarchical Correspondence Establishment, ISPRS Journal of Photogrammetry and Remote Sensing (Submitted)

Establishing reliable point correspondences between images with significant scale differences is a persistent challenge in photogrammetry and remote sensing. The scale differences often cause semantic ambiguities and positional shifts in the estimated correspondences. Limited by the direct point correspondence framework, existing methods struggle to address the scale issue at the local feature level. To overcome this, we address the scale difference issue by detecting co-visible regions between image pairs and propose \textbf{SCoDe} (\textbf{S}cale-aware \textbf{Co}-visible region \textbf{De}tector) that identifies and aligns co-visible regions for highly robust hierarchical point correspondence matching. Specifically, SCoDe employs a novel Scale Head Attention mechanism to map and correlate features across multiple scale subspaces, and leverages a learnable query to gather information from extracted scale-aware features of both images for co-visible region detection. In this way, correspondences can be hierarchically determined from region-level to point-level with semantic and location uncertainty eliminated. Extensive experiments conducted on three challenging datasets demonstrate the clear superiority of SCoDe over state-of-the-art methods, improving point matching precision by 9.04\%. SCoDe also exhibits a notable advantage when dealing with images that have large scale differences.

Awards

2022
中国软件杯大学生软件设计大赛全国二等奖 from 工业和信息化部,教育部,江苏省人民政府
2021
全国大学生算法设计与编程挑战赛铜奖 from 中国未来研究会大数据与数学模型专业委员会
2021
Third Prize of Asia and Pacific Mathematical Contest in Modeling from Beijing Society of Image and Graphics
2021
全国大学生数学建模竞赛湖北赛区一等奖 from 中国工业与应用数学学会
2020
第26届湖北省翻译大赛决赛二等奖 from 湖北省翻译工作者协会,湖北省外事翻译中心

Volunteering

2023 — 2024
Chairman at the 22nd LIESMARS Graduate Student Union
Wuhan, China
2022 — 2024
Director at GeoScience Café Operation Center
Wuhan, China
2023 — 2023
Volunteer at the 21st China Ocean Color Conference
Wuhan, China
2023 — 2023
Volunteer at 2023 International Graduate Workshop on Geo-Informatics
Wuhan, China
2022 — 2022
Volunteer at 2022 International Graduate Workshop on Geo-Informatics
Hong Kong SAR, China
2021
全国计算机等级考试:网络工程师四级 from 教育部考试中心
2021
全国计算机等级考试:网络技术三级 from 教育部考试中心
2020
全国计算机等级考试:数据库技术三级 from 教育部考试中心

Contact

Website
GitHub
LinkedIn