Stefano Gasperini
Papers
2
Total Citations
7
H-Index
2
About
Stefano Gasperini is a rising researcher at the intersection of computer vision and robotics, with a primary focus on 3D scene understanding and object pose estimation. His work addresses a critical bottleneck in robotic manipulation: enabling machines to perceive and interact with objects they have never seen before. Gasperini’s major contribution is the development of **Zero123-6D**, a pioneering framework that leverages diffusion models for zero-shot novel view synthesis, applied specifically to RGB category-level 6D pose estimation. This approach allows a system to infer the full 3D position and orientation of an object from a single 2D image, without any prior training on that specific object instance. By harnessing the generative power of diffusion models, his method achieves remarkable flexibility and generalizability, overcoming the rigidity of traditional pose estimators. Although still early in his career, with his most-cited paper accumulating 7 citations to date, the conceptual leap of Zero123-6D has already captured attention for its potential to make robotic systems more adaptable in unstructured environments. Gasperini’s work is a promising step toward truly general-purpose robotic perception.
Research Focus
Key Achievements
Top Papers
- 1
- 2