Yu Zhang
AboutThoughtsNotes
notes/slam/papers/f-features/f2-learned-descriptors

F2 Learned Descriptors

  • K2E-B-F2-1ALIKED A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation

    Paper note on ALIKED, an efficient keypoint and descriptor extraction network using sparse deformable descriptor heads (IEEE TIM 2023)

  • K2E-B-F2-2LightGlue Local Feature Matching at Light Speed

    Paper note on LightGlue, an adaptive deep network for efficient sparse local feature matching (ICCV 2023)

  • K2E-B-F2-3BootsTAP Bootstrapped Training for Tracking-Any-Point

    Paper note on BootsTAP, a self-supervised student-teacher method for improving point tracking on real-world videos (ACCV 2024)

© 2026 Yu Zhang