Wenbo Ji
Papers
1
Total Citations
1
H-Index
1
About
Wenbo Ji is a rising researcher at the forefront of 3D computer vision and robotics, with a focus on zero-shot perception and instance segmentation. His most notable contribution, "RE0: Recognize Everything with 3D Zero-Shot Instance Segmentation" (2025), tackles a critical bottleneck in robotics: the scarcity of high-quality 3D training data. By ingeniously leveraging vision foundation models (VFMs) from the 2D domain, Ji’s work enables general-purpose 3D segmentation without task-specific training, effectively bridging the gap between 2D and 3D recognition. This approach empowers robots to identify and segment arbitrary objects in real-world environments, a breakthrough for autonomous manipulation and navigation. Though early in his career, Ji’s work has already garnered attention for its practical impact, with the RE0 paper accumulating citations that underscore its relevance. His research sits at the intersection of computer vision, machine learning, and embodied AI, promising to make robotic perception more adaptable and data-efficient. As a young innovator, Wenbo Ji is poised to shape the next generation of intelligent systems that can truly “recognize everything” in the 3D world.
Research Focus
Key Achievements
Top Papers
- 1RE0: Recognize Everything with 3D Zero-Shot Instance Segmentation1 citations · 2025