Scholar
Jiahui Lei
Google Scholar ID: rX6SwdIAAAAJ
UC Berkeley
Citations & Impact
Citations
514
H-index
10
i10-index
11
Publications
20
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- Published multiple papers including: MoMaps: Semantics-Aware Scene Motion Generation with Motion Maps, DIMO: Diverse 3D Motion Generation for Arbitrary Objects, MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds, HDGS: Textured 2D Gaussian Splatting for Enhanced Scene Rendering, GART: Gaussian Articulated Template Models, Track Everything Everywhere Fast and Robustly, DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting, NAP: Neural 3D Articulation Prior, Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance, EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision, CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphism, Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces, Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images.
Research Experience
- Post-doc researcher at UC Berkeley, working with Prof. Angjoo Kanazawa and Prof. Trevor Darrell. Conducted Ph.D. research at the University of Pennsylvania GRASP Lab under the guidance of Prof. Kostas Daniilidis. Worked as a student researcher at Google DeepMind.
Education
- Ph.D. (2020-2025) from the University of Pennsylvania GRASP Lab, advised by Prof. Kostas Daniilidis; Student researcher at Google DeepMind with Prof. Leo Guibas; Bachelor's degree (2016-2020) in Automation (Control Science) from Zhejiang University, ranked 1st/141 in the class of 2020.
Background
- Currently a post-doc researcher at UC Berkeley, working with Prof. Angjoo Kanazawa and Prof. Trevor Darrell. Focusing on 4D Vision for Robotics. Previously, worked on 4D as well as equivariant neural networks. Pursues inspiring, useful, and elegant research on hard problems.
Miscellany
- Open to collaborations and always looking for strong interns to work with.
Co-authors