Search papers, labs, and topics across Lattice.
This paper introduces a novel framework for estimating the pose of unknown spacecraft using a single image, which integrates 3D shape reconstruction with learned 2D-3D feature matching. The method employs a frozen DINOv3 vision transformer for feature extraction and a dynamic graph convolutional neural network for geometric feature computation, culminating in a dual-stream transformer matcher that enhances descriptor accuracy. Evaluation on the SPE3R dataset reveals that the approach achieves a mean pointing error of just 0.157 degrees, showcasing its robustness and generalization capabilities for autonomous space operations.
Achieving a mean pointing error of only 0.157 degrees, this method redefines single-shot pose estimation for unknown spacecraft using just a single image.
6-DoF pose estimation is a critical task in autonomous rendezvous and proximity operations. In the case of an unknown target, this task becomes challenging as it shall be paired with the reconstruction of the target shape model. In this article, we propose a novel framework for single-shot shape and pose estimation of unknown spacecraft objects. Given a single image, we first reconstruct a 3D shape model of the target, then estimate the relative six-degrees-of-freedom pose by learning dense 2D-3D correspondences. The image features are extracted using a frozen DINOv3 vision transformer, while the geometric features are computed from the reconstructed point cloud using a trainable dynamic graph convolutional neural network encoder. A dual-stream transformer matcher refines descriptors through alternating self- and cross-attention, producing soft correspondences that are passed to a Perspective-$n$-Point solver for pose recovery. We evaluate the method on the SPE3R dataset and consider FoundationPose as a representative baseline for current state-of-the-art capabilities. Results show reliable pose estimates achieving 0.157 degrees mean pointing error using only a single image and reconstructed geometry, demonstrating strong generalization to unseen spacecraft.
