Zongtan Li

Papers

Total Citations

H-Index

About

Zongtan Li is an emerging researcher in the field of computer vision and 3D representation learning, with a focus on advancing how machines perceive and interpret three-dimensional data. Their most notable contribution is the development of MD-Mamba, a novel feature extractor that leverages multi-view depth information to enhance 3D representation. This work, published in 2024, introduces a state-space model-based approach that efficiently captures spatial and depth cues from multiple perspectives, offering a promising alternative to traditional transformer-based architectures for 3D tasks. Although early in its citation trajectory—with 4 citations to date—MD-Mamba represents a significant step forward in scalable and effective 3D feature extraction, particularly for applications in autonomous navigation, robotics, and augmented reality. Li's research sits at the intersection of deep learning, geometric deep learning, and multi-modal perception, aiming to bridge the gap between 2D image data and 3D spatial understanding. As a researcher whose work is gaining traction, Zongtan Li is poised to make further impactful contributions to the rapidly evolving landscape of 3D computer vision.