Chongdi Wang

Papers

Total Citations

H-Index

About

Chongdi Wang is a rising researcher in computer vision and robotics, whose work centers on advancing dense 3D scene reconstruction and neural implicit representations for large-scale environments. His most-cited paper, "Incremental Joint Learning of Depth, Pose, and Implicit Scene Representation on Monocular Camera in Large-Scale Scenes" (2025, 5 citations), tackles a critical limitation of existing methods—their confinement to small, room-sized spaces. Wang’s key contribution lies in developing a unified framework that jointly learns depth, camera pose, and implicit scene representations from monocular video, enabling photo-realistic view synthesis and robust navigation across expansive, real-world scenes. This approach is particularly impactful for applications in virtual and augmented reality (VR/AR) and autonomous robotics, where scalability and incremental learning are essential. By addressing the gap between small-scale benchmarks and large-scale deployment, Wang’s work provides a practical foundation for robots to understand and interact with their surroundings in real time. His research reflects a growing trend toward end-to-end, self-supervised systems that reduce reliance on expensive sensors, making advanced spatial intelligence more accessible. As an early-career researcher, Wang’s innovative integration of depth, pose, and scene representation signals a promising trajectory in the field of embodied AI.