I am a Ph.D. candidate in the Department of Computer Science at the National University of Singapore, under Prof. Wei Tsang Ooi. I am also closely with Dr. Benoit Cottereau from CNRS, Dr. Lai Xing Ng from A*STAR, and Prof. Ziwei Liu from Nanyang Technological University, Singapore.
My research pursues to build 3D perception and generation models that are robust, scalable, and generalizable across domains and scenarios, while requiring minimum human annotations.
I have been fortunate to have research attachments and internships at NVIDIA Research, OpenMMLab, MMLab@NTU, Motional, and ByteDance AI Lab.
I was the recipient of the National Scholarship (Ministry of Education, 2019) and Research Achievement Award (NUS Computing, 2023).
🦁 I am a member of AnySyn3D. We are open to discussions and collaborations in 3D scene perception and generation. Feel free to drop me an email if you find our research backgrounds a potential match.
* indicates equal contributions
OpenESS: Event-Based Semantic Scene Understanding with Open Vocabularies |
Multi-Space Alignments Towards Universal LiDAR Segmentation |
Unified 3D and 4D Panoptic Segmentation via Dynamic Shifting Networks |
RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions |
Segment Any Point Cloud Sequences by Distilling Vision Foundation Models |
Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective |
Towards Label-Free Scene Understanding by Vision Foundation Models |
Robo3D: Towards Robust and Reliable 3D Perception against Corruptions |
Rethinking Range View Representation for LiDAR Segmentation |
UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase |
LaserMix for Semi-Supervised LiDAR Semantic Segmentation |
CLIP2Scene: Towards Label-Efficient 3D Scene Understanding by CLIP |
ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation |
Benchmarking 3D Robustness to Common Corruptions and Sensor Failure |
The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition
Technical Report, 2024
|
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
Technical Report, 2023
|
Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving
arXiv, 2024
|
LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving
arXiv, 2024
|
Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding
arXiv, 2024
|
Optimizing LiDAR Placements for Robust Driving Perception in Adverse Conditions
arXiv, 2024
|
Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
arXiv, 2024
|
Hierarchical Instance Feature Aggregation and Contrast for 3D Object Detection from Point Cloud Sequences
arXiv, 2024
|
Benchmarking and Analyzing Bird's Eye View Perception Robustness to Corruptions
arXiv, 2023
|
FRNet: Frustum-Range Networks for Scalable LiDAR SemanticSegmentation
arXiv, 2023
|
Learning to Adapt SAM for Segmenting Cross-Domain Point Clouds
arXiv, 2023
|
PointCloud-C: Benchmarking and Analyzing Point Cloud Perception Robustness under Corruptions
arXiv, 2022
|
Free Lunch for Co-Saliency Detection: Context Adjustment
arXiv, 2021
|
NVIDIA Research |
OpenMMLab |
Motional |
ByteDance AI Lab |