Optical image sequences of spacecraft acquired by space-based monocular cameras are typically imaged through exposure bracketing. The spacecraft feature deformable alignment network for multi-exposure image fusion (SFDA-MEF) aims to synthesize a High Dynamic Range (HDR) spacecraft image from a set of Low Dynamic Range (LDR) images with varying exposures. The HDR image contains details of the observed target in LDR images captured within a specific luminance range. The relative attitude of the spacecraft in the camera coordinate system undergoes continuous changes during the orbital rendezvous, which leads to a large proportion of moving pixels between adjacent frames. Concurrently, subsequent tasks of the In-Orbit Servicing (IOS) system, such as attitude estimation, are highly sensitive to variations in multi-view geometric relationships, which means that the fusion result should preserve the shape of the spacecraft with minimal distortion. However, traditional methods and unsupervised deep-learning methods always exhibit inherent limitations in dealing with complex overlapping regions. In addition, supervised methods are not suitable when ground truth data are scarce. Therefore, we propose an unsupervised learning framework for the multi-exposure fusion of optical spacecraft image sequences. We introduce a deformable convolution in the feature deformable alignment module and construct an alignment loss function to preserve its shape with minimal distortion. We also design a feature point extraction loss function to render our output more conducive to subsequent IOS tasks. Finally, we present a multi-exposure spacecraft image dataset. Subjective and objective experimental results validate the effectiveness of SFDA-MEF, especially in retaining the shape of the spacecraft.
In this paper, a novel optimization framework based on 3D Gaussian splatting (3DGS) for high-fidelity 3D reconstruction of space targets under exposure bracketing conditions is studied. In the considered scenario, multi-view optical imagery captures space targets under complex and dynamic illumination, where severe inter-frame brightness variations degrade reconstruction quality by introducing photometric inconsistencies and blurring fine geometric details. Unlike existing methods, we explicitly address these challenges by integrating exposure-aware adaptive refinement and edge-preserving regularization into the 3DGS pipeline. Specifically, we propose an exposure bracketing-oriented bounding box (OBB) regional densification strategy to dynamically identify and refine under-reconstructed regions. In addition, we introduce a Sobel edge regularization mechanism to guide the learning of sharp geometric features and improve texture fidelity. To validate the framework, experiments are conducted on both a custom OBR-ST dataset and the public SHIRT dataset, demonstrating that our method significantly outperforms state-of-the-art techniques in geometric accuracy and visual quality under exposure-bracketing scenarios. The results highlight the effectiveness of our approach in enabling robust in-orbit perception for space applications.
Attitude estimation of noncooperative spacecraft based on monocular camera is a crucial technique in on-orbit servicing missions. Most of the existing methods rely on the known 3D model of the target, or require a large number of observation images with ground truth labels, which are not applicable to unseen spacecraft lacking such prior knowledge. In this paper, we present a two-stage framework for semantic feature extraction of spacecraft typical components and on-orbit attitude estimation of unseen targets to solve the above problem, which inverts the three-dimensional attitude information from the two-dimensional axes of spacecraft typical components in the sequential observation images. Firstly, a spacecraft semantic feature extraction network (SSF-Net) is designed, which can learn the common semantic features of typical components in different spacecraft, thereby achieving good generalization for unseen targets and extracting their axes features. Then, we introduce homographic adaptation, the geometric constraint of semantic features, and dynamic constraint in sequential images to optimize false positives or missed detections of the extracted features under extreme observation perspectives. Finally, the axis reconstruction algorithm based on the RANdom Sample Consensus (RANSAC) is proposed to estimate the attitude of unseen on-orbit spacecraft. Simulation results confirm that the proposed method can effectively extract semantic features, with average pixel and angular errors of 6.93 pixels and 1.86 degrees respectively, and estimate the attitude of unseen spacecraft with typical component structures accurately, achieving the average estimation error of 3.25 degrees. Experiments also exhibit significant advantages compared to classical methods and excellent robustness under worse observing conditions.