collaborators

5 papers

cs.CV2026

UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception

Mohammad Mahdavian, Gordon Tan, Binbin Xu +3

We present UniScale, a unified, scale-aware multi-view 3D reconstruction framework for robotic applications that flexibly integrates geometric priors through a modular, semanticall…

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

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…