Three-Dimensional Reconstruction From a Single Satellite Image via Iterative RGB-D Completion
Open Access
- 23 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 14820-14833
Abstract
Reconstructing 3D scenes from a single satellite image remains challenging because reliable metric depth is unavailable and many regions are occluded, which limits the geometric observability and appearance evidence required for faithful reconstruction. To address these issues, we propose SSRecon, a diffusion-driven framework for single-image satellite 3D reconstruction via iterative RGB-D completion. SSRecon fits the RPC model to a pinhole approximation, estimates depth with a language-conditioned diffusion model, and performs RGB and depth inpainting using Stable Diffusion and a step-segmented gradient-guidance scheme, respectively. The input image together with the estimated depth forms the first RGB-D frame to initialize a 3D Gaussian Splatting representation, which is then refined by repeatedly rendering novel views, completing missing regions, and updating the scene representation. Experiments on DFC2019 and SpaceNet4 show that SSRecon improves perceptual realism and cross-view consistency across diverse target poses without auxiliary semantics or height inputs. In the pure single-image setting, SSRecon increases CLIP-Score by 0.65 on DFC2019 and 0.76 on SpaceNet4 over the strongest baseline, with consistent gains in CLIP-IQA quality and sharpness.Keywords
Funding Information
- National Natural Science Foundation of China (42530106)
- National Natural Science Foundation of China (42571507)
- State Key Laboratory of Micro-Spacecraft Rapid Design and Intelligent Cluster (MS01240125)
This publication has 40 references indexed in Scilit:
- Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting2025
- Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion2024
- Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models2024
- Consistent View Synthesis with Pose-Guided Diffusion Models2023
- RGBD2: Generative Scene Synthesis via Incremental View Inpainting Using RGBD Diffusion Models2023
- NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors2023
- CompletionFormer: Depth Completion with Convolutions and Vision Transformers2023
- A general deep learning based framework for 3D reconstruction from multi-view stereo satellite imagesISPRS Journal of Photogrammetry and Remote Sensing, 2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Indoor Segmentation and Support Inference from RGBD Images2012