Yang Fu 付旸

Yang is currently a Ph.D student in Electrical and Computer Engineering (ECE) at University of California San Diego (UCSD), advised by Prof. Xiaolong Wang. He has received Qualcomm Innovation Fellowship (2023). Before that, he obtained his M.S. in ECE at UIUC in 2020 under the supervision of Prof. Thomas S. Huang (1936-2020) and Prof. Humphrey Shi.

News

• [2024.09] SpatialRGPT: Grounded Spatial Reasoning in Vision Language Model is accepted to NeurIPS 2024.

• [2024.03] A Construct-Optimize Approach to Sparse View Synthesis without Camera Pose is accepted to SIGGRAPH 2024.

• [2024.02] Three papers(CF3DGS, HOIDiffusion and WILD RGBD) are accepted to CVPR 2024.
• [2024.01] 3D Reconstruction with Generalizable Neural Fields using Scene Prior is accepted to ICLR 2024.
• [2023.09] I start my internship at NVIDIA Learning and Perception Research Group advised by Sifei Liu.
• [2023.07] I’m selected to be a recipient of Qualcomm Innovation Fellowship 2023.
• [2023.05] MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Poses is accepted to ICML 2023.
• [2023.01] Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild is accepted to ICLR 2023.

• [2022.09] Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset is accepted to NeurIPS 2022.

• [2022.06] DexMV: Imitation Learning for Dexterous Manipulation from Human Videos is accepted to ECCV 2022.

• [2022.06] Check out our Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset which introduces an in-the-wild object-centric RGBD dataset with 5000+ videos over 1700+ objects. We peform semi-supervised 6D object pose estimation on it without human annotations.