Accurate 3D reconstruction of lunar surfaces is essential for space exploration. However, existing stereo vision reconstruction methods struggle in this context due to the Moon's lack of texture, difficult lighting variations, and atypical orbital trajectories. State-of-the-art deep learning models, trained on human-scale datasets, have rarely been tested on planetary imagery and cannot be transferred directly to lunar conditions. To address this issue, we introduce LunarStereo, the first open dataset of photorealistic stereo image pairs of the Moon, simulated using ray tracing based on high-resolution topography and reflectance models. It covers diverse altitudes, lighting conditions, and viewing angles around the lunar South Pole, offering physically grounded supervision for 3D reconstruction tasks. Based on this dataset, we adapt the MASt3R model to the lunar domain through fine-tuning on LunarStereo. We validate our approach through extensive qualitative and quantitative experiments on both synthetic and real lunar data, evaluating 3D surface reconstruction and relative pose estimation. Extensive experiments on synthetic and real lunar data validate the approach, demonstrating significant improvements over zero-shot baselines and paving the way for robust cross-scale generalization in extraterrestrial environments.
Adapting a Foundation Model for Lunar Surface Height Estimation
University of Technology of Troyes（特鲁瓦技术大学）；Hochschule Darmstadt（达姆施塔特应用科学大学）；European Space Agency（欧洲空间局）；Technische Hochschule Würzburg-Schweinfurt（维尔茨堡-施韦因富特应用科学大学）
Sub-metre Lunar DEM Generation and Validation from Chandrayaan-2 OHRC Multi-View Imagery Using an Open-Source Pipeline
School of Computer Science and Engineering Manipal University（曼海姆大学计算机科学与工程学院）；Space Applications Centre (SAC) Indian Space Research Organisation (ISRO)（空间应用中心（SAC）印度空间研究组织（ISRO））；Intelligent Robotics Group NASA Ames Research Center（智能机器人小组美国国家航空航天局阿姆斯研究中心）
We propose a novel idea for depth estimation from multi-view image-pose pairs, where the model has capability to leverage information from previous latent-space encodings of the scene. This model uses pairs of images and poses, which are passed through an encoder--decoder model for disparity estimation. The novelty lies in soft-constraining the bottleneck layer by a nonparametric Gaussian process prior. We propose a pose-kernel structure that encourages similar poses to have resembling latent spaces. The flexibility of the Gaussian process (GP) prior provides adapting memory for fusing informa…
LuSNAR:A Lunar Segmentation, Navigation and Reconstruction Dataset based on Muti-sensor for Autonomous Exploration
University of Chinese Academy of Sciences（中国科学院大学）；Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences（中国科学院空间应用工程与技术中心）
Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）
Onboard localization capabilities for planetary rovers to date have used relative navigation, by integrating combinations of wheel odometry, visual odometry, and inertial measurements during each drive to track position relative to the start of each drive. At the end of each drive, a ground-in-the-loop (GITL) interaction is used to get a position update from human operators in a more global reference frame, by matching images or local maps from onboard the rover to orbital reconnaissance images or maps of a large region around the rover's current position. Autonomous rover drives are limited i…
Nanjing University of Science and Technology（南京理工大学）；University of Trento（特伦托大学）；Huawei Technologies Ireland（华为技术爱尔兰公司）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
In this work, we tackle the problem of online adaptation for stereo depth estimation, that consists in continuously adapting a deep network to a target video recordedin an environment different from that of the source training set. To address this problem, we propose a novel Online Meta-Learning model with Adaption (OMLA). Our proposal is based on two main contributions. First, to reducethe domain-shift between source and target feature distributions we introduce an online feature alignment procedurederived from Batch Normalization. Second, we devise a meta-learning approach that exploits feat…
Advancing Applications of Satellite Photogrammetry: Novel Approaches for Built-up Area Modeling and Natural Environment Monitoring using Stereo/Multi-view Satellite Image-derived 3D Data
Estimating the confidence of disparity maps inferred by a stereo algorithm has become a very relevant task in the years, due to the increasing number of applications leveraging such cue. Although self-supervised learning has recently spread across many computer vision tasks, it has been barely considered in the field of confidence estimation. In this paper, we propose a flexible and lightweight solution enabling self-adapting confidence estimation agnostic to the stereo algorithm or network. Our approach relies on the minimum information available in any stereo setup (i.e., the input stereo pa…
Self-supervised learning of depth has been a highly studied topic of research as it alleviates the requirement of having ground truth annotations for predicting depth. Depth is learnt as an intermediate solution to the task of view synthesis, utilising warped photometric consistency. Although it gives good results when trained using stereo data, the predicted depth is still sensitive to noise, illumination changes and specular reflections. Also, occlusion can be tackled better by learning depth from a single camera. We propose ADAA, utilising depth augmentation as depth supervision for learnin…
DEM Refinement and Validation on the Lunar Surface Using Shape-from-Shading with Chandrayaan-2 OHRC Imagery
School of Computer Science and Engineering, Manipal University（曼海姆大学计算机科学与工程学院）；Space Applications Centre (SAC), Indian Space Research Organisation (ISRO)（印度空间研究组织空间应用中心）
University of Bologna（博洛尼亚大学）；Google Zurich（谷歌苏黎世）
Depth estimation from stereo images is carried out with unmatched results by convolutional neural networks trained end-to-end to regress dense disparities. Like for most tasks, this is possible if large amounts of labelled samples are available for training, possibly covering the whole data distribution encountered at deployment time. Being such an assumption systematically unmet in real applications, the capacity of adapting to any unseen setting becomes of paramount importance. Purposely, we propose a continual adaptation paradigm for deep stereo networks designed to deal with challenging an…
Reconstructing 3D geometry from satellite imagery is an important topic of research. However, disparities exist between how this 3D reconstruction problem is handled in the remote sensing context and how multi-view reconstruction pipelines have been developed in the computer vision community. In this paper, we explore whether state-of-the-art reconstruction pipelines from the vision community can be applied to the satellite imagery. Along the way, we address several challenges adapting vision-based structure from motion and multi-view stereo methods. We show that vision pipelines can offer com…
Depth-Aware Rover: A Study of Edge AI and Monocular Vision for Real-World Implementation
Space Applications Centre（空间应用中心）；Institute of Advanced Indian Space Research（印度高级空间研究机构）；Indian Space Research Organization（印度空间研究组织）；Technology and Research（技术与研究）
LunarDepthNet: Generation of Digital Elevation Models using Deep Learning and Monocular Satellite Images
School of Computer Science and Engineering（计算机科学与工程学院）；Space Applications Centre (SAC)（空间应用中心）；Indian Space Research Organisation (ISRO)（印度空间研究组织）；Department of IoT and Intelligent Systems（物联网与智能系统系）；Department of Computer and Communication Engineering（计算机与通信工程系）
SomBench: Benchmark Dataset for Advancing Machine Learning in Lunar Science
The University of Alabama in Huntsville（阿拉巴马大学亨茨维尔分校）；IBM Research（IBM研究院）；Science and Technology Institute, Universities Space Research Association (USRA)（大学空间研究协会科学技术研究所）；NASA Goddard Space Flight Center（美国国家航空航天局戈达德太空飞行中心）；SETI Institute（搜寻地外文明研究所）；NASA Ames Research Center（美国国家航空航天局艾姆斯研究中心）；University of Maryland, Baltimore County (UMBC)（马里兰大学巴尔的摩县分校）；Howard University（霍华德大学）
Deep S2P: Integrating Learning Based Stereo Matching Into the Satellite Stereo Pipeline
IIE, Facultad de Ingeniería, Universidad de la República（拉普拉塔大学工程学院）；AMIAD, Pôle Recherche（AMIAD研究机构）；Université Paris-Saclay, ENS Paris-Saclay, CNRS, Centre Borelli（巴黎-萨克雷大学、巴黎-萨克雷高等学院、国家科学研究中心、Borelli中心）；Institut Universitaire de France（法国国家科学研究中心）
GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Model
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Intelligent Science and Technology Academy of CASIC（中国航天科工集团智能科技研究院）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；Department of Automation, Tsinghua University（清华大学自动化系）
SonarSweep: Fusing Sonar and Vision for Robust 3D Reconstruction via Plane Sweeping
Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Chinese University of Hong Kong, Hong Kong（香港中文大学）；Department of Automation, Harbin Institute of Technology（哈尔滨工业大学自动化系）
Cross-Domain Foundation Model Adaptation: Pioneering Computer Vision Models for Geophysical Data Analysis
School of Earth and Space Sciences, University of Science and Technology of China（中国科学技术大学地球和空间科学学院）；Microsoft Applied Sciences Group（微软应用科学组）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）
