Showing 2026Show all
3 papers · 1 filter
cs.CV2026
E-S2Feat:Semantic-Guided Spiking Local Feature Detection and Description for Event Cameras
Yang Yi, Juntao Hua, Jinpu Zhang +3
Benefiting from high temporal resolution and dynamic range, event-based local feature methods have attracted increasing attention. However, event sparsity, noise, and limited textu…
cs.CV2026
GESS: Multi-cue Guided Local Feature Learning via Geometric and Semantic Synergy
Yang Yi, Xieyuanli Chen, Jinpu Zhang +2
Robust local feature detection and description are foundational tasks in computer vision. Existing methods primarily rely on single appearance cues for modeling, leading to unstabl…
cs.CV2026
TAPFormer: Robust Arbitrary Point Tracking via Transient Asynchronous Fusion of Frames and Events
Jiaxiong Liu, Zhen Tan, Jinpu Zhang +4
Tracking any point (TAP) is a fundamental yet challenging task in computer vision, requiring high precision and long-term motion reasoning. Recent attempts to combine RGB frames an…