Jiahao Pang

Papers

Total Citations

H-Index

About

Jiahao Pang is a leading researcher in 3D computer vision and scene understanding, with a focus on point cloud processing and dynamic scene analysis. His most notable contribution is the development of **FESTA (Flow Estimation via Spatial-Temporal Attention)**, a groundbreaking framework for estimating scene flow directly from 3D point clouds. This work addresses a critical challenge in autonomous driving, robot navigation, and AR/VR by enabling precise motion estimation in dynamic 3D environments without relying on dense RGB video frames. The FESTA paper has garnered over 45 citations, reflecting its significant impact on the field. By leveraging spatial-temporal attention mechanisms, Pang’s approach achieves state-of-the-art accuracy in capturing the complex dynamics of real-world scenes, such as moving vehicles and pedestrians. His research bridges the gap between traditional 2D flow estimation and modern 3D sensing technologies, paving the way for more robust and efficient perception systems. Pang’s work is widely recognized for its practical applications in safety-critical domains, making him a key figure in advancing 3D scene flow estimation and its integration into next-generation autonomous systems.