Sotabase

Career

· PhD Student, UC Berkeley2024–

Publications (18)

DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignment
European Conference on Computer Vision · 2024
36
cited
DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes
Computer Vision and Pattern Recognition · 2024
30
cited
Interactive Multi-Scale Fusion of 2D and 3D Features for Multi-Object Vehicle Tracking
IEEE transactions on intelligent transportation systems (Print) · 2023
27
cited
PNAS-MOT: Multi-Modal Object Tracking With Pareto Neural Architecture Search
IEEE Robotics and Automation Letters · 2024
18
cited
DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds
IEEE International Conference on Computer Vision · 2023
17
cited
Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation
European Conference on Computer Vision · 2024
17
cited
Q-SLAM: Quadric Representations for Monocular SLAM
Conference on Robot Learning · 2024
14
cited
COMPGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians
Computer Vision and Pattern Recognition · 2024
9
cited
Joint Pedestrian Trajectory Prediction through Posterior Sampling
IEEE/RJS International Conference on Intelligent RObots and Systems · 2024
9
cited
X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenarios
International Conference on Learning Representations · 2024
8
cited
Certifiable Out-of-Distribution Generalization
AAAI Conference on Artificial Intelligence · 2023
7
cited
Interactive Multi-scale Fusion of 2D and 3D Features for Multi-object Tracking
arXiv.org · 2022
7
cited
R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation
arXiv.org · 2025
6
cited
A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision
arXiv.org · 2024
3
cited
BEV-GS: Feed-forward Gaussian Splatting in Bird's-Eye-View for Road Reconstruction
arXiv.org · 2025
2
cited
S2GO: Streaming Sparse Gaussian Occupancy Prediction
arXiv.org · 2025
1
cited
VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing
arXiv.org · 2025
1
cited
DIAL-GS: Dynamic Instance Aware Reconstruction for Label-free Street Scenes with 4D Gaussian Splatting
arXiv.org · 2025
Sotabase
Chensheng Peng | Researcher Profile | Sotabase | Sotabase