# Any2Any: Unified Arbitrary Modality Translation for Remote Sensing

arXiv: https://arxiv.org/abs/2603.04114 · HTML: https://mlsanity.com/paper/2603.04114/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 26 of 26)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [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)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models](https://mlsanity.com/paper/2205.07680/) (2022)
- [SpaceNet: A Remote Sensing Dataset and Challenge Series](https://mlsanity.com/paper/1807.01232/) (2018)
- [SEN12MS -- A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusion](https://mlsanity.com/paper/1906.07789/) (2019)
- [Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model](https://mlsanity.com/paper/2501.00895/) (2025)
- [SpaceNet 6: Multi-Sensor All Weather Mapping Dataset](https://mlsanity.com/paper/2004.06500/) (2020)
- [The SEN1-2 Dataset for Deep Learning in SAR-Optical Data Fusion](https://mlsanity.com/paper/1807.01569/) (2018)
- [LBM: Latent Bridge Matching for Fast Image-to-Image Translation](https://mlsanity.com/paper/2503.07535/) (2025)
- [The QXS-SAROPT Dataset for Deep Learning in SAR-Optical Data Fusion](https://mlsanity.com/paper/2103.08259/) (2021)
- [DiffI2I: Efficient Diffusion Model for Image-to-Image Translation](https://mlsanity.com/paper/2308.13767/) (2023)
- [Residual Diffusion Bridge Model for Image Restoration](https://mlsanity.com/paper/2510.23116/) (2025)
- [A Diffusion Model Translator for Efficient Image-to-Image Translation](https://mlsanity.com/paper/2502.00307/) (2025)
- [UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes](https://mlsanity.com/paper/2511.23332/) (2025)
- [MMM-RS: A Multi-modal, Multi-GSD, Multi-scene Remote Sensing Dataset and Benchmark for Text-to-Image Generation](https://mlsanity.com/paper/2410.22362/) (2024)
- [SARMAE: Masked Autoencoder for SAR Representation Learning](https://mlsanity.com/paper/2512.16635/) (2025)
- [Cooperative Colorization: Exploring Latent Cross-Domain Priors for NIR Image Spectrum Translation](https://mlsanity.com/paper/2308.03348/) (2023)
- [Image-to-Image Translation with Diffusion Transformers and CLIP-Based Image Conditioning](https://mlsanity.com/paper/2505.16001/) (2025)
- [Deterministic Image-to-Image Translation via Denoising Brownian Bridge Models with Dual Approximators](https://mlsanity.com/paper/2512.23463/) (2025)
- [Subjective Camera 1.0: Bridging Human Cognition and Visual Reconstruction through Sequence-Aware Sketch-Guided Diffusion](https://mlsanity.com/paper/2506.23711/) (2025)
- [CSHNet: A Novel Information Asymmetric Image Translation Method](https://mlsanity.com/paper/2501.10197/) (2025)
- [Degradation-Aware Metric Prompting for Hyperspectral Image Restoration](https://mlsanity.com/paper/2512.20251/) (2025)

## Built on by (most cited first, 4 of 4)

- [CoRE-UIR: Prior-guided common and residual experts for efficient all-in-one remote sensing image restoration](https://mlsanity.com/paper/2607.27898/) (2026)
- [UniTriGen: Unified Triplet Generation of Aligned Visible-Infrared-Label for Few-Shot RGB-T Semantic Segmentation](https://mlsanity.com/paper/2605.14626/) (2026)
- [Learning the Target Priors Before Image Translation: A Decoupled Training Paradigm for Cross-Modal Image Translation in Remote Sensing](https://mlsanity.com/paper/2608.28517/) (2026)
- [OmniRSI: Taming Latent Diffusion for Unified Multimodal Remote Sensing Image Generation](https://mlsanity.com/paper/2610.15414/) (2026)

## Abstract (arXiv)

Multi-modal remote sensing imagery provides complementary observations of the same geographic scene, yet such observations are frequently incomplete in practice. Existing cross-modal translation methods treat each modality pair as an independent task, resulting in quadratic complexity and limited generalization to unseen modality combinations. We formulate Any-to-Any translation as inference over a shared latent representation of the scene, where different modalities correspond to partial observations of the same underlying semantics. Based on this formulation, we propose Any2Any, a unified latent diffusion framework that projects heterogeneous inputs into a geometrically aligned latent space. Such structure performs anchored latent regression with a shared backbone, decoupling modality-specific representation learning from semantic mapping. Moreover, lightweight target-specific residual adapters are used to correct systematic latent mismatches without increasing inference complexity. To support learning under sparse but connected supervision, we introduce RST-1M, the first million-scale remote sensing dataset with paired observations across five sensing modalities, providing supervision anchors for any-to-any translation. Experiments across 14 translation tasks show that Any2Any consistently outperforms pairwise translation methods and exhibits strong zero-shot generalization to unseen modality pairs. Code and models are available at https://github.com/MiliLab/Any2Any.