About me

I am a 4th-year Ph.D. student at Southeast University (SEU), advised by Prof. Songlin Du. Before joining SEU, I completed my undergraduate education at Nanjing University of Science and Technology (NJUST) under the supervision of Prof. Xuefeng Jiang. My research interests lie in 3D vision from multi-view and lightweight networks. I am currently seeking internship opportunities in computer vision, 3D vision, and spatial intelligence.

News

• [May, 2026] ProMa is accepted at TMM.
• [Nov, 2025] JamMa got 200+ ⭐ in github.
• [Sep, 2025] RCM+ is accepted at TPAMI.
• [Mar, 2025] JamMa is accepted at CVPR 2025.

Publications

Towards Free-form Local Feature Matching
Xiaoyong Lu, Songlin Du, Yaping Yan, Xiaobo Lu, Takeshi Ikenaga
TPAMI 2025
[Paper]

JamMa: Ultra-lightweight Local Feature Matching with Joint Mamba
Xiaoyong Lu, Songlin Du
CVPR 2025
[Project page] [Paper]

Progressive Matchability Guided Hybrid Interaction for Latency-balanced Local Feature Matching
Xiaoyong Lu, Songlin Du, Guobao Xiao, Guanghui Wen
TMM 2026
[coming soon]

Raising the Ceiling: Conflict-Free Local Feature Matching with Dynamic View Switching
Xiaoyong Lu, Songlin Du
ECCV 2024
[Code] [Paper]

Scene-Aware Feature Matching
Xiaoyong Lu, Yaping Yan, Tong Wei, Songlin Du
ICCV 2023
[Paper]

ParaFormer: Parallel Attention Transformer for Efficient Feature Matching
Xiaoyong Lu, Yaping Yan, Bin Kang, Songlin Du
AAAI 2023 Oral
[Paper]

Parallel Consensus Transformer for Local Feature Matching
Xiaoyong Lu, Yuhan Chen, Bin Kang, Songlin Du
Pattern Recogn. 2025
[Paper]

NCTR: Neighborhood Consensus Transformer for Feature Matching
Xiaoyong Lu, Songlin Du
ICIP 2022 Oral
[Code] [Paper]

SceneGlue: Scene-Aware Transformer for Feature Matching without Scene-Level Annotation
Songlin Du, Xiaoyong Lu, Yaping Yan, Guobao Xiao, Xiaobo Lu, Takeshi Ikenaga
TCSVT 2026
[Paper]

SemMatcher: Semantic-aware feature matching with neighborhood consensus
Qimin Jiang, Xiaoyong Lu, Dong Liang, Songlin Du
J. Vis. Commun. Image Represent. 2025
[Paper]

Service

• Reviewer of CVPR, ICCV, NeurIPS, ECCV, AAAI, BMVC, TIP, TCSVT.