Chong Xia

Papers

Total Citations

H-Index

About

Chong Xia is a rising researcher in computer vision and robotics, whose work focuses on bridging the gap between offline 3D scene understanding and real-time, interactive perception. His key research areas include online 3D scene perception, embodied AI, and memory-augmented deep learning. Xia’s most notable contribution is the introduction of **Memory-based Adapters for Online 3D Scene Perception**, a framework that enables models to process streaming RGB-D video inputs—rather than relying on pre-reconstructed 3D geometry—making it directly applicable to robotic systems. This work, published in 2024, has already garnered 6 citations, signaling its timely impact on the field. By integrating lightweight, memory-efficient adapters into existing architectures, Xia addresses a critical bottleneck in deploying 3D perception models on resource-constrained platforms. His research is paving the way for more adaptive and autonomous robots that can understand and navigate dynamic environments in real time. As an early-career scientist, Chong Xia is establishing himself as a key voice in the next generation of embodied vision research.