Illumination-Prior-Based High-Resolution DEM Reconstruction from Single-View Lunar Image Constrained with Initial DEM

Abstract. The lunar south pole is characterized by complex illumination conditions, extensive shadowed regions, and rugged topography, which make high-resolution terrain reconstruction from single-view imagery particularly challenging. To address this problem, this paper proposes an Illumination-Prior-Based DEM Reconstruction framework (IPDR) for single-view lunar terrain reconstruction under initial DEM constraints. The proposed method jointly exploits monocular image features, geometric prior information from the initial DEM, and illumination guidance derived from solar geometry. Experimental results on representative lunar south polar regions show that the proposed method achieves more stable and geometrically consistent reconstruction results than the compared methods. Large-area and local comparisons demonstrate improved terrain continuity and local morphological recovery, while ablation experiments verify the complementary roles of the initial DEM and the illumination prior. Additional experiments under different solar azimuth conditions and on ShadowCam imagery further show that the proposed framework maintains good robustness and adaptability. These results demonstrate the effectiveness of the proposed method for high-resolution lunar south polar terrain reconstruction from single-view imagery under initial DEM constraints.

Authors

Institutions

Publication Details

Journal
˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences
Published
2026-07-23
DOI
https://doi.org/10.5194/isprs-archives-xlix-b2-2026-523-2026
Primary Topic
Planetary Science and Exploration
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Illumination-Prior-Based High-Resolution DEM Reconstruction from Single-View Lunar Image Constrained with Initial DEM

Rong Huang, Xiaohua Tong, Siyi Qiu, Yusheng Xu et al.
˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences
Planetary Science and Exploration
article

Illumination-Prior-Based High-Resolution DEM Reconstruction from Single-View Lunar Image Constrained with Initial DEM

Rong Huang, Xiaohua Tong, Siyi Qiu, Yusheng Xu, Zhen Ye
article en

Abstract

Abstract. The lunar south pole is characterized by complex illumination conditions, extensive shadowed regions, and rugged topography, which make high-resolution terrain reconstruction from single-view imagery particularly challenging. To address this problem, this paper proposes an Illumination-Prior-Based DEM Reconstruction framework (IPDR) for single-view lunar terrain reconstruction under initial DEM constraints. The proposed method jointly exploits monocular image features, geometric prior information from the initial DEM, and illumination guidance derived from solar geometry. Experimental results on representative lunar south polar regions show that the proposed method achieves more stable and geometrically consistent reconstruction results than the compared methods. Large-area and local comparisons demonstrate improved terrain continuity and local morphological recovery, while ablation experiments verify the complementary roles of the initial DEM and the illumination prior. Additional experiments under different solar azimuth conditions and on ShadowCam imagery further show that the proposed framework maintains good robustness and adaptability. These results demonstrate the effectiveness of the proposed method for high-resolution lunar south polar terrain reconstruction from single-view imagery under initial DEM constraints.

˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciencesVol. XLIX-B2-2026
Tongji University (CN)
National Natural Science Foundation of China
Sustainable cities and communities
Openalex Percentile: Top 9%
Planetary Science and Exploration
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.