mlsanityData to 7 Oct 2026

EarthBridge: A Solution for 4th Multi-modal Aerial View Image Challenge Translation Track

arXiv 2603.06753 ↗First posted 6 Mar 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Cross-modal image-to-image translation among Electro-Optical (EO), Infrared (IR), and Synthetic Aperture Radar (SAR) sensors is essential for comprehensive multi-modal aerial-view analysis. However, translating between these modalities is notoriously difficult due to their distinct electromagnetic signatures and geometric characteristics. This paper presents EarthBridge, a high-fidelity translation framework developed for the 4th Multi-modal Aerial View Image Challenge -- Translation (MAVIC-T). We explore two distinct methodologies: Diffusion Bridge Implicit Models (DBIM), which we generalize using non-Markovian bridge processes for high-quality deterministic sampling, and Contrastive Unpaired Translation (CUT), which utilizes contrastive learning for structural consistency. Our EarthBridge framework employs a channel-concatenated UNet denoiser trained with Karras-weighted bridge scalings and a specialized "booting noise" initialization to handle the inherent ambiguity in cross-modal mappings. We evaluate these methods across all four challenge tasks (SARrightarrowEO, SARrightarrowRGB, SARrightarrowIR, RGBrightarrowIR), achieving superior spatial detail and spectral accuracy. Our solution achieved a composite score of 0.38, securing the second position on the MAVIC-T leaderboard. Code is available at https://github.com/Bili-Sakura/EarthBridge-Preview.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 55 references that are in the map. First posted on arXiv 6 Mar 2026.

Builds on

26 of 55 references.

References · 26

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  7. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  8. 2016Least Squares Generative Adversarial Networkscited by 1,000
  9. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 666
  10. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
  11. 2023Zero-shot Image-to-Image Translationcited by 503
  12. 2022BBDM: Image-to-image Translation with Brownian Bridge Diffusion Modelscited by 222
14 more
  1. 2022Dual Diffusion Implicit Bridges for Image-to-Image Translationcited by 212
  2. 2023Denoising Diffusion Bridge Modelscited by 171
  3. 2023Prodigy: An Expeditiously Adaptive Parameter-Free Learnercited by 129
  4. 2022Let us Build Bridges: Understanding and Extending Diffusion Generative Modelscited by 102
  5. 2023Non-Denoising Forward-Time Diffusionscited by 75
  6. 2023Direct Diffusion Bridge using Data Consistency for Inverse Problemscited by 65
  7. 2021Simulating Diffusion Bridges with Score Matchingcited by 51
  8. 2024Diffusion Bridge Implicit Modelscited by 47
  9. 2025LBM: Latent Bridge Matching for Fast Image-to-Image Translationcited by 36
  10. 2024Consistency Diffusion Bridge Modelscited by 22
  11. 2020Classification of Large-Scale High-Resolution SAR Images with Deep Transfer Learningcited by 12
  12. 2025Deterministic Image-to-Image Translation via Denoising Brownian Bridge Models with Dual Approximatorscited by 5
  13. 2026Adaptive Domain Shift in Diffusion Models for Cross-Modality Image Translationcited by 3
  14. 2025CSHNet: A Novel Information Asymmetric Image Translation Methodcited by 2

Built on by

Not cited yet.