3 papers
cs.RO2025
World-Coordinate Human Motion Retargeting via SAM 3D Body
Zhangzheng Tu, Kailun Su, Shaolong Zhu +1
Recovering world-coordinate human motion from monocular videos with humanoid robot retargeting is significant for embodied intelligence and robotics. To avoid complex SLAM pipeline…
cs.CV2025
MIFO: Learning and Synthesizing Multi-Instance from One Image
Kailun Su, Ziqi He, Xi Wang +1
This paper proposes a method for precise learning and synthesizing multi-instance semantics from a single image. The difficulty of this problem lies in the limited training data, a…
cs.RO2025
RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
Tianxing Chen, Zanxin Chen, Baijun Chen +23
Simulation-based data synthesis has emerged as a powerful paradigm for advancing real-world robotic manipulation. Yet existing datasets remain insufficient for robust bimanual mani…