I'm a 4th-year Ph.D. student in the Department of EECS at UC Berkeley and a member of BAIR, advised by Prof. Angjoo Kanazawa.
Previously, I had the pleasure to be a research assistant in the Vision & Graphics Lab at USC ICT for 2 years, collaborating with Prof. Hao Li. I obtained my B.Sc. degree in Physics and Mathematics and M.Sc. degree in Computer Science at Tsinghua University, where I worked closely with Prof. Shi-Min Hu and Prof. Song-Hai Zhang. I've been interned at NVIDIA, Google Research, Facebook Reality Labs, and Bytedance AI Lab.
My current research interests lie in the intersection field of Computer Vision and Computer Graphics, especially on the tasks of generation and reconstruction in the 3D world via information from 2D images.
![]() |
gsplat: Efficient Gaussian Splatting CUDA Backend |
![]() |
NeRF-XL: Scaling NeRFs with Multiple GPUs European Conference on Computer Vision (ECCV, 2024) |
![]() |
NerfAcc: A General NeRF Acceleration Toolbox International Conference on Computer Vision (ICCV, 2023) |
![]() |
Nerfstudio: A collaboration friendly studio for NeRFs. ACM Siggraph 2023 |
|
Monocular Dynamic View Synthesis: A Reality Check Conference on Neural Information Processing Systems (NeurIPS, 2022) |
TAVA: Template-free Animatable Volumetric Actors European Conference on Computer Vision (ECCV, 2022) |
PlenOctrees for Real-time Rendering of Neural Radiance Fields International Conference on Computer Vision (ICCV, 2021) [Oral] |
![]() |
AI Choreographer: Music Conditioned 3D Dance Generation with AIST++ International Conference on Computer Vision (ICCV, 2021) |
![]() |
Monocular Real-Time Volumetric Performance Capture European Conference on Computer Vision (ECCV, 2020) |
![]() |
Volumetric Human Teleportation Siggraph Real-Time Live 2020 [Jury's Choice Award (Best Show Award)] |
Learning Formation of Physically-Based Face Attributes IEEE Conference on Computer Vision and Pattern Recognition (CVPR, 2020) |
Deep Portrait Image Completion and Extrapolation IEEE Transactions on Image Processing (TIP) |
Pose2Seg: Detection Free Human Instance Segmentation IEEE Conference on Computer Vision and Pattern Recognition (CVPR, 2019) |
Example-Guided Style-Consistent Image Synthesis from Semantic Labeling IEEE Conference on Computer Vision and Pattern Recognition (CVPR, 2019) |
Detecting and Removing Visual Distractors for Video Aesthetic Enhancement IEEE Transactions on Multimedia (TMM, 2018) |