# Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Model

arXiv: https://arxiv.org/abs/2406.17998 · HTML: https://mlsanity.com/paper/2406.17998/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 65 of its 83 references that are in the map.
- First posted on arXiv 26 Jun 2024.

## Builds on (most cited first, 30 of 65)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [All are Worth Words: A ViT Backbone for Diffusion Models](https://mlsanity.com/paper/2209.12152/) (2022)

## Built on by (most cited first, 30 of 37)

- [TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis](https://mlsanity.com/paper/2506.20380/) (2025)
- [AeroGen: Enhancing Remote Sensing Object Detection with Diffusion-Driven Data Generation](https://mlsanity.com/paper/2411.15497/) (2024)
- [WildSAT: Learning Satellite Image Representations from Wildlife Observations](https://mlsanity.com/paper/2412.14428/) (2024)
- [ATRNet-STAR: A Large Dataset and Benchmark Towards Remote Sensing Object Recognition in the Wild](https://mlsanity.com/paper/2501.13354/) (2025)
- [The Change You Want To Detect: Semantic Change Detection In Earth Observation With Hybrid Data Generation](https://mlsanity.com/paper/2503.15683/) (2025)
- [Open-CD: A Comprehensive Toolbox for Change Detection](https://mlsanity.com/paper/2407.15317/) (2024)
- [ChangeDiff: A Multi-Temporal Change Detection Data Generator with Flexible Text Prompts via Diffusion Model](https://mlsanity.com/paper/2412.15541/) (2024)
- [Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?](https://mlsanity.com/paper/2503.07890/) (2025)
- [Visual Instruction Pretraining for Domain-Specific Foundation Models](https://mlsanity.com/paper/2509.17562/) (2025)
- [ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG](https://mlsanity.com/paper/2411.07688/) (2024)
- [Referring Change Detection in Remote Sensing Imagery](https://mlsanity.com/paper/2512.11719/) (2025)
- [ViewDelta: Scaling Scene Change Detection through Text-Conditioning](https://mlsanity.com/paper/2412.07612/) (2024)
- [Exploring Foundation Models in Remote Sensing Image Change Detection: A Comprehensive Survey](https://mlsanity.com/paper/2410.07824/) (2024)
- [From Pixels to Prose: Advancing Multi-Modal Language Models for Remote Sensing](https://mlsanity.com/paper/2411.05826/) (2024)
- [SMART-Ship: A Comprehensive Synchronized Multi-modal Aligned Remote Sensing Targets Dataset and Benchmark for Berthed Ships Analysis](https://mlsanity.com/paper/2508.02384/) (2025)
- [FUSAR-KLIP: Towards Multimodal Foundation Models for Remote Sensing](https://mlsanity.com/paper/2509.23927/) (2025)
- [Survey of Multimodal Geospatial Foundation Models: Techniques, Applications, and Challenges](https://mlsanity.com/paper/2510.22964/) (2025)
- [COP-GEN-Beta: Unified Generative Modelling of COPernicus Imagery Thumbnails](https://mlsanity.com/paper/2504.08548/) (2025)
- [ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Sensing](https://mlsanity.com/paper/2507.04678/) (2025)
- [UniRoute: Unified Routing Mixture-of-Experts for Modality-Adaptive Remote Sensing Change Detection](https://mlsanity.com/paper/2601.14797/) (2026)
- [RSEdit: Text-Guided Image Editing for Remote Sensing](https://mlsanity.com/paper/2603.13708/) (2026)
- [HuiYanEarth-SAR: A Foundation Model for High-Fidelity and Low-Cost Global Remote Sensing Imagery Generation](https://mlsanity.com/paper/2604.11444/) (2026)
- [LaVIDE: Language-Prompted Satellite Change Detection via Map-Image Alignment](https://mlsanity.com/paper/2411.19758/) (2024)
- [SChanger: Change Detection from a Semantic Change and Spatial Consistency Perspective](https://mlsanity.com/paper/2503.20734/) (2025)
- [Semantic Change Detection of Roads and Bridges: A Fine-grained Dataset and Multimodal Frequency-driven Detector](https://mlsanity.com/paper/2505.13212/) (2025)
- [Remote Sensing Change Detection via Weak Temporal Supervision](https://mlsanity.com/paper/2601.02126/) (2026)
- [COP-GEN: Latent Diffusion Transformer for Copernicus Earth Observation Data](https://mlsanity.com/paper/2603.03239/) (2026)
- [MetaEarth-MM: Unified Multimodal Remote Sensing Image Generation with Scene-centered Joint Modeling](https://mlsanity.com/paper/2605.20090/) (2026)
- [OSMGen: Highly Controllable Satellite Image Synthesis using OpenStreetMap Data](https://mlsanity.com/paper/2511.00345/) (2025)
- [Morphing Through Time: Diffusion-Based Bridging of Temporal Gaps for Robust Alignment in Change Detection](https://mlsanity.com/paper/2511.07976/) (2025)

## Abstract (arXiv)

Our understanding of the temporal dynamics of the Earth's surface has been advanced by deep vision models, which often require lots of labeled multi-temporal images for training. However, collecting, preprocessing, and annotating multi-temporal remote sensing images at scale is non-trivial since it is expensive and knowledge-intensive. In this paper, we present change data generators based on generative models, which are cheap and automatic, alleviating these data problems. Our main idea is to simulate a stochastic change process over time. We describe the stochastic change process as a probabilistic graphical model (GPCM), which factorizes the complex simulation problem into two more tractable sub-problems, i.e., change event simulation and semantic change synthesis. To solve these two problems, we present Changen2, a GPCM with a resolution-scalable diffusion transformer which can generate time series of images and their semantic and change labels from labeled or unlabeled single-temporal images. Changen2 is a generative change foundation model that can be trained at scale via self-supervision, and can produce change supervisory signals from unlabeled single-temporal images. Unlike existing foundation models, Changen2 synthesizes change data to train task-specific foundation models for change detection. The resulting model possesses inherent zero-shot change detection capabilities and excellent transferability. Experiments suggest Changen2 has superior spatiotemporal scalability, e.g., Changen2 model trained on 2562 pixel single-temporal images can yield time series of any length and resolutions of 1,0242 pixels. Changen2 pre-trained models exhibit superior zero-shot performance (narrowing the performance gap to 3% on LEVIR-CD and approximately 10% on both S2Looking and SECOND, compared to fully supervised counterparts) and transferability across multiple types of change tasks.