MoonAnything: A Vision Benchmark with Large-Scale Lunar Supervised Data

• URL: http://arxiv.org/abs/2604.00682v1
• Date: Wed, 01 Apr 2026 09:39:15 GMT
• Title: MoonAnything: A Vision Benchmark with Large-Scale Lunar Supervised Data
• Abstract summary: Existing lunar datasets lack either geometric ground truth, photometric realism, illumination diversity, or large-scale coverage.<n>We introduce MoonAnything, a unified benchmark built on real lunar topography with physically-based rendering.<n>We establish baselines using state-of-the-art methods and release the complete dataset along with generation tools to support community extension.
• Score: 0.13999481573773068
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate perception of lunar surfaces is critical for modern lunar exploration missions. However, developing robust learning-based perception systems is hindered by the lack of datasets that provide both geometric and photometric supervision. Existing lunar datasets typically lack either geometric ground truth, photometric realism, illumination diversity, or large-scale coverage. In this paper, we introduce MoonAnything, a unified benchmark built on real lunar topography with physically-based rendering, providing the first comprehensive geometric and photometric supervision under diverse illumination with large scale. The benchmark comprises two complementary sub-datasets : i) LunarGeo provides stereo images with corresponding dense depth maps and camera calibration enabling 3D reconstruction and pose estimation; ii) LunarPhoto provides photorealistic images using a spatially-varying BRDF model, along with multi-illumination renderings under real solar configurations, enabling reflectance estimation and illumination-robust perception. Together, these datasets offer over 130K samples with comprehensive supervision. Beyond lunar applications, MoonAnything offers a unique setting and challenging testbed for algorithms under low-textured, high-contrast conditions and applies to other airless celestial bodies and could generalize beyond. We establish baselines using state-of-the-art methods and release the complete dataset along with generation tools to support community extension: https://github.com/clementinegrethen/MoonAnything.

Related papers

• AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World [75.54693105865003]
  We introduce AerialMetric, a benchmark dataset to evaluate and facilitate the adaptation of monocular metric depth estimation under UAV aerial viewpoints.<n>AerialMetric provides 52K real-world and 16K synthetic image-depth pairs with reliable metric ground truth.
  arXiv  Detail & Related papers  (2026-06-29T02:48:47Z)
• Do Image Editing Models Understand Lighting? [52.657799986035464]
  We introduce the 3D-anchored Light Probe (3DLP) benchmark, for which we have captured a new high-fidelity HDR dataset of real-world lighting changes.<n>The dataset consists of 1K image pairs of diverse indoor scenery in which light probes are physically turned on and off.<n>We evaluate a range of state-of-the-art image editing models by measuring how well their light probe edits align with reality.
  arXiv  Detail & Related papers  (2026-06-25T08:20:34Z)
• LunarDepthNet: Generation of Digital Elevation Models using Deep Learning and Monocular Satellite Images [0.40228234427513104]
  This study proposes a novel deep learning method that estimates and generates a surface elevation map directly from monocular images of the surface.<n>The dataset used comprises of the Chandrayaan-2 Terrain Mapping Camera (TMC) images with their corresponding Digital Terrain Models (DTMs)
  arXiv  Detail & Related papers  (2026-04-22T06:16:13Z)
• Lunar-G2R: Geometry-to-Reflectance Learning for High-Fidelity Lunar BRDF Estimation [0.11242503819703255]
  We propose a geometry-to-reflectance learning framework that predicts spatially varying BRDF parameters directly from a lunar digital elevation model (DEM)<n>Experiments on a geographically held-out region of the Tycho crater show that our approach reduces photometric error by 38 % compared to a state-of-the-art baseline.
  arXiv  Detail & Related papers  (2026-01-15T14:39:25Z)
• Depth Anything 3: Recovering the Visual Space from Any Views [64.12492264286522]
  We present Depth Anything 3 (DA3), a model that predicts spatially consistent geometry from an arbitrary number of visual inputs.<n>We establish a new visual geometry benchmark covering camera pose estimation, any-view geometry and visual rendering.<n>On this benchmark, DA3 sets a new state-of-the-art across all tasks, surpassing prior SOTA VGGT by an average of 44.3% in camera pose accuracy and 25.1% in geometric accuracy.
  arXiv  Detail & Related papers  (2025-11-13T18:59:53Z)
• OLATverse: A Large-scale Real-world Object Dataset with Precise Lighting Control [65.57356151743936]
  OLATverse is a large-scale dataset comprising around 9M images of 765 real-world objects.<n>Each object is captured using 35 DSLR cameras and 331 individually controlled light sources, enabling the simulation of diverse illumination conditions.<n>We construct an extensive evaluation set, establishing the first comprehensive real-world object-centric benchmark for inverse rendering and normal estimation.
  arXiv  Detail & Related papers  (2025-11-04T11:13:43Z)
• Adapting Stereo Vision From Objects To 3D Lunar Surface Reconstruction with the StereoLunar Dataset [0.12314765641075437]
  We introduce LunarStereo, the first open dataset of stereo image pairs of the Moon.<n>It covers diverse altitudes, lighting conditions, and viewing angles around the lunar South Pole.<n>We adapt the MASt3R model to the lunar domain through fine-tuning on LunarStereo.
  arXiv  Detail & Related papers  (2025-10-20T23:50:52Z)
• AI-Enabled Crater-Based Navigation for Lunar Mapping [12.60100558410094]
  Crater-Based Navigation (CBN) uses the ubiquitous impact craters of the Moon observed on images as natural landmarks to determine the six degrees of freedom pose of a spacecraft.<n> STELLA is the first end-to-end CBN pipeline for long-duration lunar mapping.<n>To rigorously test STELLA, we introduce CRESENT-365 - the first public dataset that emulates a year-long lunar mapping mission.
  arXiv  Detail & Related papers  (2025-09-25T05:09:41Z)
• FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views [100.45129752375658]
  We present FLARE, a feed-forward model designed to infer high-quality camera poses and 3D geometry from uncalibrated sparse-view images.<n>Our solution features a cascaded learning paradigm with camera pose serving as the critical bridge, recognizing its essential role in mapping 3D structures onto 2D image planes.
  arXiv  Detail & Related papers  (2025-02-17T18:54:05Z)
• LuSNAR:A Lunar Segmentation, Navigation and Reconstruction Dataset based on Muti-sensor for Autonomous Exploration [2.3011380360879237]
  Environmental perception and navigation algorithms are the foundation for lunar rovers. Most of the existing lunar datasets are targeted at a single task. We propose a multi-task, multi-scene, and multi-label lunar benchmark dataset LuSNAR.
  arXiv  Detail & Related papers  (2024-07-09T02:47:58Z)
• Icy Moon Surface Simulation and Stereo Depth Estimation for Sampling Autonomy [4.97538153735235]
  We propose a framework for versatile stereo dataset generation that spans the spectrum of bulk photometric properties. We also focus on a stereo-based visual perception system and evaluate both traditional and deep learning-based algorithms for depth estimation from stereo matching. Our framework can fit a wide range of hypotheses with respect to visual representations of icy moon terrains.
  arXiv  Detail & Related papers  (2024-01-23T00:06:19Z)
• Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Images [59.906948203578544]
  We introduce a novel learning-based method to reconstruct the high-quality geometry and complex, spatially-varying BRDF of an arbitrary object. We first estimate per-view depth maps using a deep multi-view stereo network. These depth maps are used to coarsely align the different views. We propose a novel multi-view reflectance estimation network architecture.
  arXiv  Detail & Related papers  (2020-03-27T21:28:54Z)
• Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materials [65.95928593628128]
  We present a method to capture both 3D shape and spatially varying reflectance with a multi-view photometric stereo technique. Our algorithm is suitable for perspective cameras and nearby point light sources.
  arXiv  Detail & Related papers  (2020-01-18T12:26:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.