6 papers
MirrorSAM2: Segment Mirror in Videos with Depth Perception
Mingchen Xu, Yukun Lai, Ze Ji +1
This paper presents MirrorSAM2, the first framework that adapts Segment Anything Model 2 (SAM2) to the task of RGB-D video mirror segmentation. MirrorSAM2 addresses key challenges…
Skeletonization Quality Evaluation: Geometric Metrics for Point Cloud Analysis in Robotics
Qingmeng Wen, Yu-Kun Lai, Ze Ji +1
Skeletonization is a powerful tool for shape analysis, rooted in the inherent instinct to understand an object's morphology. It has found applications across various domains, inclu…
Fusion of Short-term and Long-term Attention for Video Mirror Detection
Mingchen Xu, Jing Wu, Yukun Lai +1
Techniques for detecting mirrors from static images have witnessed rapid growth in recent years. However, these methods detect mirrors from single input images. Detecting mirrors f…
Learning to bag with a simulation-free reinforcement learning framework for robots
Francisco Munguia-Galeano, Jihong Zhu, Juan David Hernández +1
Bagging is an essential skill that humans perform in their daily activities. However, deformable objects, such as bags, are complex for robots to manipulate. This paper presents an…
Deep Reinforcement Learning with Explicit Context Representation
Francisco Munguia-Galeano, Ah-Hwee Tan, Ze Ji
Reinforcement learning (RL) has shown an outstanding capability for solving complex computational problems. However, most RL algorithms lack an explicit method that would allow lea…
CasIL: Cognizing and Imitating Skills via a Dual Cognition-Action Architecture
Zixuan Chen, Ze Ji, Shuyang Liu +3
Enabling robots to effectively imitate expert skills in longhorizon tasks such as locomotion, manipulation, and more, poses a long-standing challenge. Existing imitation learning (…