collaborators

7 papers

cs.CV2025

UniGaussian: Driving Scene Reconstruction from Multiple Camera Models via Unified Gaussian Representations

Yuan Ren, Guile Wu, Runhao Li +5

Urban scene reconstruction is crucial for real-world autonomous driving simulators. Although existing methods have achieved photorealistic reconstruction, they mostly focus on pinh…

cs.RO2025

UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation

Zhaodong Jiang, Ashish Sinha, Tongtong Cao +3

Estimating the 6D pose of novel objects is a fundamental yet challenging problem in robotics, often relying on access to object CAD models. However, acquiring such models can be co…

cs.CV2025

3DArticCyclists: Generating Synthetic Articulated 8D Pose-Controllable Cyclist Data for Computer Vision Applications

Eduardo R. Corral-Soto, Yang Liu, Tongtong Cao +2

In Autonomous Driving (AD) Perception, cyclists are considered safety-critical scene objects. Commonly used publicly-available AD datasets typically contain large amounts of car an…

cs.CV2025

HIPPo: Harnessing Image-to-3D Priors for Model-free Zero-shot 6D Pose Estimation

Yibo Liu, Zhaodong Jiang, Binbin Xu +7

This work focuses on model-free zero-shot 6D object pose estimation for robotics applications. While existing methods can estimate the precise 6D pose of objects, they heavily rely…

cs.CV2025

Learning Effective NeRFs and SDFs Representations with 3D Generative Adversarial Networks for 3D Object Generation

Zheyuan Yang, Yibo Liu, Guile Wu +4

We present a solution for 3D object generation of ICCV 2023 OmniObject3D Challenge. In recent years, 3D object generation has made great process and achieved promising results, but…

cs.CV2024

AutoSplat: Constrained Gaussian Splatting for Autonomous Driving Scene Reconstruction

Mustafa Khan, Hamidreza Fazlali, Dhruv Sharma +4

Realistic scene reconstruction and view synthesis are essential for advancing autonomous driving systems by simulating safety-critical scenarios. 3D Gaussian Splatting excels in re…