One2Any: One-Reference 6D Pose Estimation for Any Object

TL;DR

One2Any introduces a novel single-view RGB-D based method for 6D object pose estimation that generalizes to new objects without needing 3D models or multi-view data, achieving state-of-the-art results.

Contribution

It proposes a new encoding-decoding framework that estimates object pose from a single reference image, enabling scalable training and generalization to unseen objects.

Findings

Achieves state-of-the-art accuracy on benchmark datasets.

Generalizes well to novel objects without prior 3D models.

Operates efficiently with only a single reference image.

Abstract

6D object pose estimation remains challenging for many applications due to dependencies on complete 3D models, multi-view images, or training limited to specific object categories. These requirements make generalization to novel objects difficult for which neither 3D models nor multi-view images may be available. To address this, we propose a novel method One2Any that estimates the relative 6-degrees of freedom (DOF) object pose using only a single reference-single query RGB-D image, without prior knowledge of its 3D model, multi-view data, or category constraints. We treat object pose estimation as an encoding-decoding process, first, we obtain a comprehensive Reference Object Pose Embedding (ROPE) that encodes an object shape, orientation, and texture from a single reference view. Using this embedding, a U-Net-based pose decoding module produces Reference Object Coordinate (ROC) for new views, enabling fast and accurate pose estimation. This simple encoding-decoding framework allows our model to be trained on any pair-wise pose data, enabling large-scale training and demonstrating great scalability. Experiments on multiple benchmark datasets demonstrate that our model generalizes well to novel objects, achieving state-of-the-art accuracy and robustness even rivaling methods that require multi-view or CAD inputs, at a fraction of compute.