Aug 19, 2018 · Kai Xu (徐凯) is a Professor at the School of Computer Science, National University of Defense Technology (NUDT). He is also an Adjunct Professor of Simon Fraser University. He earned his Ph.D in computer science in 2011 from NUDT.

Xuening Zhu, Renjiao Yi, Xin Wen, Chenyang Zhu, Kai Xu*, "Relighting Scenes with Object Insertions in Neural Radiance Fields", IEEE Transactions on Circuits and Systems for Video Technology. 2025. (Xuening and Renjiao are joint first authors)

Xu, H. Li, H. Zhang, D. Cohen-Or, Y. Xiong, and Z.-Q. Cheng, \Style-Content Separation by Anisotropic Part Scales," ACM Trans. on Graphics (SIGGRAPH Asia 2010), Vol. 29, No. 5, 2010.

If you are interested, please send email to: kevin.kai.xu [at] gmail.com Research Interests: Geometry Processing, Geometric Modeling, Data-Driven Shape Analysis and Modeling, 3D Vision, Autonomous 3D Sensing, Robot Perception, etc.

11. Intelligent 3D Sensing and Modeling, USTC Summer School 2015 on "Advances in Computer Graphics", University of Science and Technology of China, Qingdao, China, July 29, 2015. 10. Robot-Operated Indoor Scene Reconstruction, SDU Summer School on Visual Computing, Shandong University, Qingdao, China, July 23, 2014. 9. Data-Driven Shape Modeling and Processing, Chinese Conference on Image and ...

Kevin (Kai) Xu's Homepage. Home; Research; Publications; Group; ... Fenggen Yu 1, Kun Liu 1, Yan Zhang 1, Chenyang Zhu 2, Kai Xu 2 1 Nanjing University, 2 National University of Defense Technology (Fenggen and Kun are joint first authors; Kai is corresponding author.) CVPR 2019.

(Kai Xu is the corresponding author.) ACM Transactions on Graphics (SIGGRAPH 2021), 40(4). We introduce ROSEFusion, a depth-only online dense reconstruction which is stable and robust to highly fast camera motion.

Visual comparison of shape composition results with ComplementMe [Sung et al. 2017] and Fit-and-Diverse [Xu et al. 2012]. Visual examples of challenging compositions achieved by SCORES over six object categories.

(* Kai Xu is the corresponding author) ACM Transactions on Graphics (SIGGRAPH 2018), 37(4) Autonomous scene scanning and reconstruction on a real office scene using our object-aware guidance approach.

We approach the problem of high-DOF reaching-and-grasping via learning joint planning of grasp and motion with deep reinforcement learning. To resolve the sample efficiency issue in learning the high-dimensional and complex control of dexterous grasping, we propose an effective representation of grasping state characterizing the spatial interaction between the …