Research map / 3D vision / 3D generation
Geospecific View Generation - Geometry-Context Aware High-resolution Ground View Inference from Satellite Views
Ningli Xu, Rongjun Qin
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 geospecific prior (LoRA in cross-attention) to the diffusion model (ablation) | Ours · DFC 2019 Jacksonville | FID: 87.75 -> 66.06 | Improved |
| add geospecific prior (ablation) | Ours · DFC 2019 Jacksonville | building IoU (I_B): 0.359 -> 0.550 | Improved |
| condition on ground-view satellite texture instead of semantics (ablation) | Ours · DFC 2019 Jacksonville | FID: 89.60 -> 66.06 | Improved |
| replace semantics with satellite textures in PanoGAN | PanoGAN · DFC 2019 Jacksonville | FID: 98.81 -> 84.38 | Improved |
| replace semantics with satellite textures in CrossMLP | CrossMLP · DFC 2019 Jacksonville | FID / DreamSIM / LPIPS: FID 170.8 -> 86.65; LPIPS 0.509 -> 0.535 | Mixed |
| add geospecific prior | Ours · DFC 2019 Jacksonville | training convergence | Improved |
| diffusion model with texture condition versus GAN baselines on pixel metrics | Ours · DFC 2019 Jacksonville | PSNR: 21.02 (Sat2Ground) vs 19.95 | Hurt |
Closest papers by meaning
- Satellite to GroundScape - Large-scale Consistent Ground View Generation from Satellite Views (CVPR 2025 · similarity 0.88)
- GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual Grounding (CVPR 2026 · similarity 0.88)
- GeoCore-9B: Towards Geo-Aware Generative Foundation Models in Earth Observation (NeurIPS 2026 · similarity 0.87)
- Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control (ICLR 2025 · similarity 0.86)
- Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation (CVPR 2025 · similarity 0.86)
- SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation (CVPR 2024 · similarity 0.85)
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.
