Artur Jesslen
Papers
1
Total Citations
1
H-Index
1
About
Artur Jesslen is a rising researcher in computer vision and robotics, whose work tackles the fundamental challenge of enabling machines to perceive and interact with 3D objects in the real world. His primary research focus lies in unsupervised and category-level 3D pose estimation—a critical capability for embodied agents and generative 3D modeling. In his most notable work, "Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos" (2024), Jesslen introduces a groundbreaking approach that eliminates the traditional reliance on massive human annotations or CAD models. Instead, his method leverages object-centric videos to learn pose estimation directly from unlabeled data, significantly reducing the barriers to deploying robots in unstructured environments. This innovation has already garnered attention in the field, with its potential to democratize 3D perception for autonomous systems. Jesslen’s contributions are particularly impactful for robotics and augmented reality, where scalable, annotation-free pose estimation is essential. As an early-career researcher, his work signals a promising trajectory toward more autonomous, data-efficient machine perception systems.
Research Focus
Key Achievements
Top Papers
- 1