Yuliang Sun
Papers
1
Total Citations
29
H-Index
1
About
Yuliang Sun is a researcher specializing in 3D computer vision and deep learning, with a particular focus on point cloud analysis for indoor scene understanding. His most notable contribution is the development of PGCNet (Patch Graph Convolutional Network), a pioneering architecture that enhances point cloud segmentation by leveraging local geometric structures through graph convolutions. This work, published in 2020 and cited 29 times, addresses the critical challenge of accurately parsing complex indoor environments—a key enabler for applications in robotics, augmented reality, and autonomous navigation. Sun’s approach innovatively combines patch-based feature extraction with graph neural networks, improving segmentation robustness against noise and irregular point distributions. His research has been recognized for advancing the efficiency and accuracy of 3D scene parsing, laying groundwork for subsequent studies in spatial deep learning. By bridging graph theory and point cloud processing, Sun’s contributions offer practical solutions for real-world spatial intelligence, making his work a valuable reference for students and researchers exploring geometric deep learning and its applications in perception systems.
Research Focus
Key Achievements
Top Papers
- 1