Research map / Image generation / Text-to-image diffusion
ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Senisng
Zhenghui Zhao, Chen Wu, Xiangyong Cao, Di Wang, Hongruixuan Chen, Datao Tang, Liangpei Zhang, Zhuo Zheng
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 Composed Bridge Initialization (start from composed pre-event state instead of noise) (ablation) | ChangeBridge UNet (SD1.5) · WHU-CD instance layout | FID: 76.81 -> 56.24 | Improved |
| add Asynchronous Drift Diffusion on top of CompBridge (ablation) | ChangeBridge UNet (SD1.5) · WHU-CD instance layout | FID: FID 56.24 -> 57.06; IS +0.18; IoU 71.87 -> 72.48 | Mixed |
| add Drift-Aware Denoising (ablation) | ChangeBridge UNet (SD1.5) · WHU-CD instance layout | FID: 57.06 -> 45.47 | Improved |
| use DiT backbone instead of UNet | ChangeBridge · S2Looking instance layout | FID: 72.56 -> 56.42 | Improved |
| ChangeBridge versus Instruct-Imagen on coordinate text | ChangeBridge DiT · LEVIR-CC | FID: 48.17 -> 31.45 | Improved |
| ChangeBridge versus Changen2 on semantic mask | ChangeBridge DiT · SECOND | mIoU %: 73.20 -> 74.26 | Improved |
| add 1x synthetic data to real data for binary change detection (ablation) | BiT · S2Looking | IoU %: 46.94 -> 48.11 | Improved |
| add 2x synthetic data for binary change detection (ablation) | BiT · WHU-CD | IoU %: 72.39 -> 74.65 | Improved |
| increase synthetic data from 1x to 2x for semantic change detection (ablation) | MambaSCD · SECOND | mIoU %: 74.02 -> 73.57 | Hurt |
| increase synthetic data from 2x to 3x (ablation) | BiT / RSICCformer · WHU-CD and LEVIR-CC | IoU % / CIDEr-D: WHU 74.65 -> 73.40; CIDEr-D 145.09 -> 142.31 | Hurt |
| add synthetic data for change captioning (ablation) | RSICCformer · LEVIR-CC | CIDEr-D: 134.12 -> 145.09 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ChangeDiff — ChangeDiff: A Multi-Temporal Change Detection Data Generator with Flexible Text Prompts via Diffusion Model (AAAI 2025) · better on 1 of 1 shared result
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
- Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model (CVPR 2024 · similarity 0.86)
- DiffusionSat: A Generative Foundation Model for Satellite Imagery (ICLR 2024 · similarity 0.85)
- Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model (NeurIPS 2024 · similarity 0.85)
- MMM-RS: A Multi-modal, Multi-GSD, Multi-scene Remote Sensing Dataset and Benchmark for Text-to-Image Generation (NeurIPS 2024 · similarity 0.84)
- SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening (NeurIPS 2024 · similarity 0.84)
- STDD: Spatio-Temporal Dual Diffusion for Video Generation (CVPR 2025 · similarity 0.84)
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.
