Xinhang Yang
Papers
1
Total Citations
8
H-Index
1
About
Xinhang Yang is a computer vision researcher whose work lies at the intersection of 3D reconstruction, real-time perception, and semantic scene understanding. Yang’s most cited contribution, “InstanceFusion: Real-time Instance-level 3D Reconstruction Using a Single RGBD Camera” (2020, 8 citations), introduces a robust system that fuses deep learning with traditional SLAM to detect, segment, and reconstruct individual objects in indoor environments in real time. This work addresses a critical challenge: moving beyond holistic scene reconstruction to produce semantically rich, instance-level 3D models—a capability essential for robotics, augmented reality, and autonomous navigation. By enabling a single handheld RGBD camera to generate visually compelling, object-aware reconstructions, Yang’s research bridges the gap between high-level semantic understanding and low-level geometric mapping. Though early in their career, Yang’s focus on real-time, instance-level 3D reconstruction signals a promising trajectory in making machines perceive and interact with the physical world as humans do—by recognizing and modeling distinct objects, not just surfaces.
Research Focus
Key Achievements
Top Papers
- 1