2 citations · 3 across the 5 of their papers we have counts for
6 papers · 1 filter
Towards Complementary Keypoint Detection via Mixture of Detectors
Xiaoyong Lu, Guobao Xiao, Dong Liang +1
Keypoint detection plays a central role in geometric vision pipelines. Existing detectors exhibit complementary strengths across different scene structures and keypoint budgets, an…
SceneGlue: Scene-Aware Transformer for Feature Matching without Scene-Level Annotation
Songlin Du, Xiaoyong Lu, Yaping Yan +3
Local feature matching plays a critical role in understanding the correspondence between cross-view images. However, traditional methods are constrained by the inherent local natur…
JamMa: Ultra-lightweight Local Feature Matching with Joint Mamba
Xiaoyong Lu, Songlin Du
Existing state-of-the-art feature matchers capture long-range dependencies with Transformers but are hindered by high spatial complexity, leading to demanding training and highlate…
Raising the Ceiling: Conflict-Free Local Feature Matching with Dynamic View Switching
Xiaoyong Lu, Songlin Du
Current feature matching methods prioritize improving modeling capabilities to better align outputs with ground-truth matches, which are the theoretical upper bound on matching res…
Scene-Aware Feature Matching
Xiaoyong Lu, Yaping Yan, Tong Wei +1
Current feature matching methods focus on point-level matching, pursuing better representation learning of individual features, but lacking further understanding of the scene. This…
ParaFormer: Parallel Attention Transformer for Efficient Feature Matching
Xiaoyong Lu, Yaping Yan, Bin Kang +1
Heavy computation is a bottleneck limiting deep-learningbased feature matching algorithms to be applied in many realtime applications. However, existing lightweight networks optimi…