Scholar
Xin Kong
Google Scholar ID: eddJsWsAAAAJ
Ph.D. Student, Department of Computing, Imperial College London
Citations & Impact
Citations
1,255
H-index
13
i10-index
16
Publications
19
Co-authors
9
list available
Publications
Resume (English only)
Academic Achievements
- CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis
- EscherNet: A Generative Model for Scalable View Synthesis (CVPR 2024, Oral)
- vMAP: Vectorised Object Mapping for Neural Field SLAM (CVPR 2023)
- RINet: Efficient 3D Lidar-Based Place Recognition Using Rotation Invariant Neural Network (RA-L, ICRA 2022)
- SSC: Semantic Scan Context for Large-Scale Place Recognition (IROS 2021)
Background
- Research Interests: Computer vision and robotics. Currently working on 3D generative diffusion models, neural SLAM, scalable 3D scene representation, and also interested in bringing large visual/language priors into 3D vision and robotics to achieve high-level intelligence. Research objective is to build intelligent robots capable of continuously learning and perceiving the real world as humans do, which is hard but worthwhile.
Miscellany
- Contact: Email / Google Scholar / Github / LinkedIn / Twitter
