High-precision lunar scene 3D data are essential for lunar exploration and the construction of scientific research stations. Currently, most existing data from orbital imagery offers resolutions up to 0.5–2 m, which is inadequate for tasks requiring centimeter-level precision. To overcome this, our research focuses on using in situ stereo vision systems for finer 3D reconstructions directly from the lunar surface. However, the scarcity and homogeneity of available lunar surface stereo datasets, combined with the Moon’s unique conditions—such as variable lighting from low albedo, sparse surface textures, and extensive shadow occlusions—pose significant challenges to the effectiveness of traditional stereo matching techniques. To address the dataset gap, we propose a method using Unreal Engine 4 (UE4) for high-fidelity physical simulation of lunar surface scenes, generating high-resolution images under realistic and challenging conditions. Additionally, we propose an optimized cost calculation method based on Census transform and color intensity fusion, along with a multi-level super-pixel disparity optimization, to improve matching accuracy under harsh lunar conditions. Experimental results demonstrate that the proposed method exhibits exceptional robustness and accuracy in our soon-to-be-released multi-scene lunar dataset, effectively addressing issues related to special lighting conditions, weak textures, and shadow occlusion, ultimately enhancing disparity estimation accuracy.

Point-like space target detection (PSTD) is a critical technology for space situation awareness. However, it grapples with challenges arising from intense noise, stray light, and stars resembling targets, making it difficult for existing methods to differentiate between point-like targets and stars. To address these issues, we propose a PSTD framework guided by local target continuity, global background volatility, and multi-star topological features. First, we tailor a background estimation approach to minimize noise and stray light while preserving target details. Then, we introduce a novel K-vector-based star angular distance (KV-SAD) voting strategy, which uses multi-star topological features to accurately identify key points. Finally, using these identified key points, we apply a fast linear attitude estimator (FLAE) to create a star template matrix and set up redundant windows for separating similarly shaped targets from stars. Extensive experiments across four space image sequences achieved an average AUC( P_d , τ) of 93.36%, which is 12.79% higher than the best baseline method, showing the best balance between detection rate and false alarm rate. This significant improvement underscores the strong generalization of our novel PSTD framework to diverse and challenging space scenarios.

Lunar in situ resource utilization is a core goal in lunar exploration, with accurate lunar rock pose estimation being essential. To address the challenges posed by the lack of texture features and extreme lighting conditions, this study proposes the Simulation-YOLO-Hourglass-Transformer (SYHT) method. The method enhances accuracy and robustness in complex lunar environments, demonstrating strong adaptability and excellent performance, particularly in conditions of extreme lighting and scarce texture. This approach provides valuable insights for object pose estimation in lunar exploration tasks and lays the foundation for lunar resource development. First, the YOLO-Hourglass-Transformer (YHT) network is used to extract keypoint information from each rock and generate the corresponding 3D pose. Then, a lunar surface imaging physics simulation model is employed to generate simulated lunar rock data for testing the method. The experimental results show that the SYHT method performs exceptionally well on simulated lunar rock data, achieving a mean per-joint position error (MPJPE) of 37.93 mm and a percentage of correct keypoints (PCK) of 99.94%, significantly outperforming existing methods. Finally, transfer learning experiments on real-world datasets validate its strong generalization capability, highlighting its effectiveness for lunar rock pose estimation in both simulated and real lunar environments.

3D point cloud understanding, e.g. out-of-distribution detection and recognition, remains a challenge, particularly in applications where safe and robust perception is critical. While recent 3D VLMs enable direct recognition via text prompts, their predictions are often unstable when the test distribution shifts or when only a handful of labeled samples are available. In this paper, we present GSP++, a graph-based inference framework that exploits the manifold structure of test-time point clouds to refine VLM scores without additional training. GSP++ constructs a graph over class prototypes, optional few-shot samples, and unlabeled test instances, and performs log-scaled score propagation to improve robustness across different dataset sizes while keeping computation efficient. The framework enables unified 3D OOD detection and classification. Moreover, we introduce a self-training strategy that selects high-confidence positive and negative samples and assigns them calibrated pseudo scores to further stabilize propagation. To enable practical deployment, we introduce dynamic graph construction and maintenance strategies that efficiently manage computation and memory, enabling scalable 3D understanding under both transductive and incremental inference. Extensive experiments on six datasets show that GSP++ not only reproduces and strengthens the full suite of OOD detection evaluations from GSP, a prior conference version, but also consistently improves zero-shot and few-shot 3D classification over strong VLM baselines. The code is available on https://github.com/handsome999KK/GSP.