Developed and published significant research results and technologies, including but not limited to: ScanNet, BundleFusion, SG-NN.
Research Experience
Led or participated in several research projects such as ScanNet (Richly-annotated 3D Reconstructions of Indoor Scenes), BundleFusion (Real-time Globally-Consistent 3D Reconstruction), and SG-NN (Self-Supervised 3D Scan Completion).
Background
Focused on attaining a 3D understanding of the world around us, including 3D reconstruction and semantic understanding from commodity RGB-D sensor data, leveraging generative 3D deep learning towards enabling understanding and interaction with 3D scenes for content creation and virtual or robotic agents.