UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation
This addresses the costly and impractical need for CAD models in robotics for novel object pose estimation, though it builds incrementally on prior diffusion and 3DGS methods.
The paper tackles the problem of estimating 6D object poses without CAD models by proposing UnPose, a framework that uses uncertainty-guided diffusion priors and 3D Gaussian Splatting to achieve zero-shot pose estimation and reconstruction from single or multi-view images, significantly outperforming existing methods in accuracy and quality.
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 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, 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 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.