# UniTS: Unified Spatio-Temporal Generative Model for Remote Sensing

arXiv: https://arxiv.org/abs/2512.04461 · HTML: https://mlsanity.com/paper/2512.04461/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 37 of its 46 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 30 of 37)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Building Normalizing Flows with Stochastic Interpolants](https://mlsanity.com/paper/2209.15571/) (2022)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [VRT: A Video Restoration Transformer](https://mlsanity.com/paper/2201.12288/) (2022)
- [SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery](https://mlsanity.com/paper/2312.10115/) (2023)
- [PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning](https://mlsanity.com/paper/2103.09504/) (2021)
- [History-Guided Video Diffusion](https://mlsanity.com/paper/2502.06764/) (2025)
- [Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks](https://mlsanity.com/paper/2107.07933/) (2021)
- [Long-Context Autoregressive Video Modeling with Next-Frame Prediction](https://mlsanity.com/paper/2503.19325/) (2025)
- [Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2403.05419/) (2024)
- [DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation](https://mlsanity.com/paper/2203.12560/) (2022)
- [AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities](https://mlsanity.com/paper/2412.14123/) (2024)
- [Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention](https://mlsanity.com/paper/1911.07757/) (2019)
- [Progressive Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2410.08151/) (2024)
- [The Multi-Temporal Urban Development SpaceNet Dataset](https://mlsanity.com/paper/2102.04420/) (2021)
- [SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration](https://mlsanity.com/paper/2501.01320/) (2025)
- [ViTs for SITS: Vision Transformers for Satellite Image Time Series](https://mlsanity.com/paper/2301.04944/) (2023)
- [LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior](https://mlsanity.com/paper/2410.21264/) (2024)
- [Joint Spatio-Temporal Modeling for the Semantic Change Detection in Remote Sensing Images](https://mlsanity.com/paper/2212.05245/) (2022)
- [EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a guided video prediction task](https://mlsanity.com/paper/2104.10066/) (2021)
- [SEN12MS-CR-TS: A Remote Sensing Data Set for Multi-modal Multi-temporal Cloud Removal](https://mlsanity.com/paper/2201.09613/) (2022)
- [UnCRtainTS: Uncertainty Quantification for Cloud Removal in Optical Satellite Time Series](https://mlsanity.com/paper/2304.05464/) (2023)
- [VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step](https://mlsanity.com/paper/2504.01956/) (2025)

## Built on by (most cited first, 2 of 2)

- [EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting](https://mlsanity.com/paper/2606.27277/) (2026)
- [GeoCR: Learning a Generalist Cloud Removal Prior from Heterogeneous Observations](https://mlsanity.com/paper/2609.32510/) (2026)

## Abstract (arXiv)

One of the primary objectives of satellite remote sensing is to capture the complex dynamics of the Earth environment, which encompasses tasks such as reconstructing continuous cloud-free image sequences, detecting land cover changes, and forecasting future surface evolution. However, existing methods typically require specialized models tailored to different tasks, and lack a general framework that can address these multi-level tasks from a unified perspective. In this paper, we propose a Unified Spatio-Temporal Generative Model (UniTS), which integrates several long-separated core tasks, including time series reconstruction, time series cloud removal, time series semantic change detection, and time series forecasting. Based on the flow matching generative paradigm, UniTS constructs a deterministic evolution path from noise to targets under the guidance of task-specific conditions, achieving unified modeling of spatiotemporal representations for multi-level tasks. The UniTS architecture consists of a diffusion transformer with spatiotemporal blocks, where we design an Adaptive Condition Injector (ACor) to enhance the model's conditional perception of multimodal inputs, enabling high-quality controllable generation. Additionally, we design a Spatiotemporal-aware Modulator (STM) to improve the ability of spatiotemporal blocks to capture complex spatiotemporal dependencies. It substantially outperforms existing specialized models, particularly under challenging conditions such as severe cloud contamination, modality absence, and forecasting complex phenological variations.