Younghwa Jung
Papers
2
Total Citations
9
H-Index
2
About
Younghwa Jung is a researcher at the forefront of autonomous systems, specializing in 3D LiDAR perception, point cloud processing, and deep learning for robotics. Her work addresses critical challenges in self-driving vehicles and autonomous robots, particularly the trade-off between sensor cost, size, and resolution. In her highly cited 2022 paper, "Fast Point Clouds Upsampling with Uncertainty Quantification for Autonomous Vehicles" (6 citations), she pioneered a method to enhance low-resolution LiDAR data, enabling compact sensors to generate dense, accurate point clouds while quantifying prediction uncertainty—a vital step for safety-critical applications. Building on this, her 2023 work "LoRCoN-LO: Long-term Recurrent Convolutional Network-based LiDAR Odometry" (3 citations) introduced an innovative deep learning architecture that fuses convolutional and recurrent neural networks to simultaneously capture spatial features and temporal dynamics, significantly improving odometry estimation for long-duration autonomous navigation. Through these contributions, Jung is advancing the practicality and reliability of autonomous perception systems, making high-performance LiDAR processing accessible for cost-sensitive platforms. Her research continues to shape the future of robust, real-time 3D scene understanding in autonomous vehicles and robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2