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

Zhaodong Jiang, Ashish Sinha, Tongtong Cao, Yuan Ren, Bingbing Liu, Binbin Xu

Keywords: 6D Pose Estimation, Diffusion Model, Object Reconstruction

TL;DR: A zero-shot, model-free 6D pose estimation and reconstruction framework that incrementally refines a 3D Gaussian Splatting model using diffusion priors and uncertainty-guided fusion from RGB-D inputs.

Abstract:

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 costly and impractical.
Recent approaches aim to bypass this requirement by leveraging strong priors from foundation models to reconstruct objects from single or multi-view images, but typically require additional training or produce hallucinated geometry.
To this end, we propose $\textit{UnPose}$, a novel framework for zero-shot, model-free 6D object pose estimation and reconstruction that exploits 3D priors and uncertainty estimates from a pre-trained diffusion model.
Specifically, starting from a single-view RGB-D frame, $\textit{UnPose}$ uses a multi-view diffusion model to estimate an initial 3D model using 3D Gaussian Splatting (3DGS) representation, along with pixel-wise epistemic uncertainty estimates.
As additional observations become available, we incrementally refine the 3DGS model by fusing new views guided by the diffusion model’s uncertainty,
thereby, continuously improving the pose estimation accuracy and 3D reconstruction quality.
To ensure global consistency, the diffusion prior-generated views and subsequent observations are further integrated in a pose graph and jointly optimized into a coherent 3DGS field.
Extensive experiments demonstrate that $\textit{UnPose}$ significantly outperforms existing approaches in both 6D pose estimation accuracy and 3D reconstruction quality.
We further showcase its practical applicability in real-world robotic manipulation tasks.

Submission Number: 785