Shengheng Deng

Papers

Total Citations

119

H-Index

About

Shengheng Deng is a leading researcher in computer vision and robotics, specializing in visual affordance understanding—the ability to infer how objects can be interacted with from visual cues. His most influential work, "3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding" (2021), has garnered 115 citations, establishing a foundational benchmark for categorizing, segmenting, and reasoning about affordances in 3D space. This contribution bridges the gap between 2D/2.5D studies and real-world robotic applications, enabling machines to grasp not just what objects are, but how they can be used. Deng’s research advances vision-guided robotics by providing critical tools for autonomous interaction with environments. His work is widely recognized for its practical impact, with the benchmark serving as a key resource for researchers developing intelligent robotic systems. Through his focus on 3D affordance reasoning, Deng is shaping the future of human-robot collaboration, making his contributions essential reading for students and engineers in embodied AI and visual perception.