Matthias NieBner

Papers

Total Citations

550

H-Index

About

Matthias Nießner is a leading figure in computer vision and graphics, renowned for his pioneering work in 3D scene understanding and reconstruction. His research centers on developing algorithms that enable machines to perceive, reconstruct, and interact with complex, real-world environments, with a strong emphasis on applications in augmented and virtual reality (AR/VR). A major contribution is his work on neural RGB-D surface reconstruction, which achieved high-quality, room-scale 3D models from commodity depth sensors—a paper that has garnered 277 citations and is foundational for AR/VR teleconferencing and robotics. He also advanced large-scale semantic scene reconstruction through incremental dense semantic stereo fusion (209 citations), enabling robots to both map and understand their surroundings. Notably, his work on RevealNet (64 citations) tackles the challenge of inferring occluded geometry behind objects in RGB-D scans, a critical capability for robotic manipulation. Nießner’s innovations have been widely adopted, influencing both academic research and industry practice, and he is recognized for bridging the gap between raw sensor data and actionable 3D scene understanding.