Nathan Tseng
Papers
2
Total Citations
25
H-Index
2
About
Nathan Tseng is a rising researcher at the forefront of autonomous perception and 3D scene understanding, with a primary focus on sensor fusion for self-driving and robotics applications. His most impactful work introduces **CLONeR**, a pioneering framework that fuses camera and LiDAR data to enhance neural radiance fields (NeRFs) for large-scale, unbounded outdoor environments. Tseng’s key contribution lies in integrating occupancy grid representations into the NeRF pipeline, effectively overcoming the notorious failure of standard NeRFs under sparse-view, far-field conditions. This innovation enables robust novel view synthesis and dense scene property estimation where prior methods falter. With his flagship 2023 paper already garnering **23 citations** in a short span, Tseng’s work is rapidly influencing the fields of autonomous navigation and 3D reconstruction. By bridging the gap between traditional geometric mapping and modern neural rendering, he is helping to build more reliable, real-world perception systems. His research is particularly notable for its practical impact on self-driving technology, offering a scalable solution for understanding complex, unbounded scenes from limited sensor data.
Research Focus
Key Achievements
Top Papers
- 1
- 2