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

Mengya Liu, Siyuan Li, Ajad Chhatkuli, Prune Truong, Luc Van Gool, Federico Tombari; Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), 2025, pp. 6457-6467

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's 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.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2025_CVPR, author = {Liu, Mengya and Li, Siyuan and Chhatkuli, Ajad and Truong, Prune and Van Gool, Luc and Tombari, Federico}, title = {One2Any: One-Reference 6D Pose Estimation for Any Object}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)}, month = {June}, year = {2025}, pages = {6457-6467} }