Research map / Image generation / Text-to-image diffusion
Any2RSI: Controllable Remote Sensing Text-to-Image Generation via Any Control and Enriched Description
Xu Zhang, Jianzhong Huang, Lefei Zhang
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 VLM-enriched descriptions (EDG) (ablation) | Any2RSI · RSICD test | FID: 44.05 -> 41.14 | Improved |
| add EDG alone to baseline (ablation) | SD 1.5 baseline · RSICD test | FID: 58.95 -> 53.13 | Improved |
| add Prompt-Guided Optimization (PGO) alone (ablation) | SD 1.5 baseline · RSICD test | FID: 58.95 -> 54.67 | Improved |
| add CMMCA alone (ablation) | SD 1.5 baseline · RSICD test | FID: 58.95 -> 51.50 | Improved |
| add CMMCA on top of EDG+PGO (ablation) | Any2RSI · RSICD test | FID: 47.60 -> 41.14 | Improved |
| add PGO on top of EDG+CMMCA (ablation) | Any2RSI · RSICD test | FID: 45.52 -> 41.14 | Improved |
| add PGO to EDG (ablation) | Any2RSI · RSICD test | Inception Score: 15.87 -> 16.23 (EDG only vs EDG+PGO); EDG+CMMCA 16.67 -> full 16.86 | Mixed |
| use Qwen2.5-VL-7B instead of InternVL2.5-8B for descriptions (HED) (ablation) | Any2RSI EDG · RSICD test, HED | FID: 44.35 -> 44.15 | Improved |
| add any VLM-generated description vs none (ablation) | Any2RSI EDG · RSICD test, Canny/HED/Seg. | FID: Canny 45.52 -> 41.52 | Improved |
| use GPT-4o descriptions (ablation) | Any2RSI EDG · RSICD test, Canny | Inception Score: 16.67 -> 15.48 | Hurt |
| combine HED, Canny and segmentation controls vs single control (ablation) | Any2RSI · RSICD test | FID: 46.25 (Seg.) -> 41.14 (all three) | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- EasyControl — EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer (ICCV 2025) · better on 7 of 7 shared results
- ControlNet++ — ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback (ECCV 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MMM-RS: A Multi-modal, Multi-GSD, Multi-scene Remote Sensing Dataset and Benchmark for Text-to-Image Generation (NeurIPS 2024 · similarity 0.91)
- SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling (CVPR 2025 · similarity 0.87)
- GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution (NeurIPS 2025 · similarity 0.87)
- SynRS3D: A Synthetic Dataset for Global 3D Semantic Understanding from Monocular Remote Sensing Imagery (NeurIPS 2024 · similarity 0.86)
- SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing (AAAI 2024 · similarity 0.86)
- DiffusionSat: A Generative Foundation Model for Satellite Imagery (ICLR 2024 · similarity 0.86)
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.
