Chenyangguang Zhang

Papers

Total Citations

H-Index

About

Chenyangguang Zhang is a rising researcher in computer vision and 3D scene understanding, with a focus on bridging semantic and functional reasoning in indoor environments. His most-cited work, "Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces" (2025, 8 citations), pioneers the task of predicting functional 3D scene graphs from posed RGB-D images. Unlike conventional approaches that model only spatial object relationships, Zhang’s framework captures objects, interactive elements, and their functional connections—enabling machines to understand not just where things are, but how they can be used. This open-vocabulary capability allows generalization to unseen objects and actions, marking a significant step toward embodied AI and human-robot interaction. By grounding functional semantics in 3D space, his work has immediate implications for assistive robotics, smart homes, and augmented reality. Though early in his career, Zhang’s contributions are already shaping how researchers think about scene graphs—moving from static spatial layouts to dynamic, interaction-aware representations. His research sits at the intersection of 3D vision, scene graph generation, and functional reasoning, promising to redefine how intelligent systems perceive and act within real-world spaces.