activity
20242026
collaborators

6 papers

cs.CV2026

From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection

Yepeng Liu, Hao Li, Liwen Yang +8

Keypoint-based matching is a fundamental component of modern 3D vision systems, such as Structure-from-Motion (SfM) and SLAM. Most existing learning-based methods are trained on im…

cs.CV2025

RefDrone: A Challenging Benchmark for Referring Expression Comprehension in Drone Scenes

Zhichao Sun, Yepeng Liu, Zhiling Su +7

Drones have become prevalent robotic platforms with diverse applications, showing significant potential in Embodied Artificial Intelligence (Embodied AI). Referring Expression Comp…

cs.CV2025

MIFNet: Learning Modality-Invariant Features for Generalizable Multimodal Image Matching

Yepeng Liu, Zhichao Sun, Baosheng Yu +4

Many keypoint detection and description methods have been proposed for image matching or registration. While these methods demonstrate promising performance for single-modality ima…

cs.CV2025

LiftFeat: 3D Geometry-Aware Local Feature Matching

Yepeng Liu, Wenpeng Lai, Zhou Zhao +4

Robust and efficient local feature matching plays a crucial role in applications such as SLAM and visual localization for robotics. Despite great progress, it is still very challen…

cs.CV2024

Shape Transformation Driven by Active Contour for Class-Imbalanced Semi-Supervised Medical Image Segmentation

Yuliang Gu, Yepeng Liu, Zhichao Sun +3

Annotating 3D medical images demands expert knowledge and is time-consuming. As a result, semi-supervised learning (SSL) approaches have gained significant interest in 3D medical i…

cs.CV2024

Progressive Retinal Image Registration via Global and Local Deformable Transformations

Yepeng Liu, Baosheng Yu, Tian Chen +4

Retinal image registration plays an important role in the ophthalmological diagnosis process. Since there exist variances in viewing angles and anatomical structures across differe…