Research map / 3D vision / NeRF and radiance fields
Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs
Ming Qian, Jincheng Xiong, Gui-Song Xia, Nan Xue
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add illumination injection from sky histogram (ablation) | Sat2Density baseline · CVACT (Aligned) | RMSE: 48.40 -> 41.62 | Improved |
| add non-sky opacity supervision alone (ablation) | Sat2Density baseline · CVACT (Aligned) | PSNR: 14.67 -> 14.63 | Hurt |
| add non-sky opacity supervision on top of illumination injection (ablation) | Sat2Density · CVACT (Aligned) | RMSE: 41.62 -> 40.71 | Improved |
| concatenate rendered depth with initial panorama as RenderNet input (ablation) | Sat2Density · CVACT (Aligned) | RMSE: 40.71 -> 39.76 | Improved |
| use Sat2Density with random illumination histogram vs Shi et al. | Sat2Density · CVACT (Aligned) | RMSE: 48.50 -> 47.13 | Improved |
| use Sat2Density instead of Shi et al. on CVUSA | Sat2Density · CVUSA | SSIM: 0.3451 -> 0.3301 | Hurt |
Closest papers by meaning
- Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image (ICLR 2026 · similarity 0.86)
- Geometry-Aware Satellite-to-Ground Image Synthesis for Urban Areas (CVPR 2020 · similarity 0.86)
- AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis (CVPR 2025 · similarity 0.85)
- SGFormer: Satellite-Ground Fusion for 3D Semantic Scene Completion (CVPR 2025 · similarity 0.84)
- Satellite to GroundScape - Large-scale Consistent Ground View Generation from Satellite Views (CVPR 2025 · similarity 0.83)
- SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation (CVPR 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
