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

Source: [EarthBridge: A Solution for 4th Multi-modal Aerial View Image Challenge Translation Track](<https://www.sota2.com/research/paper/69afa5812d603e6de3e43a3d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-02T05:00:04.464Z

Authors: Zhenyuan Chen, Guanyuan Shen, Feng Zhang

Published: 2026-03-06T12:28:46.000Z

## Abstract

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 \\textbf{EarthBridge}, a high-fidelity translation framework developed for the 4th Multi-modal Aerial View Image Challenge -- Translation (MAVIC-T). We explore two distinct methodologies: \\textbf{Diffusion Bridge Implicit Models (DBIM)}, which we generalize using non-Markovian bridge processes for high-quality deterministic sampling, and \\textbf{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 (SAR$\\rightarrow$EO, SAR$\\rightarrow$RGB, SAR$\\rightarrow$IR, RGB$\\rightarrow$IR), 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image-to-Image translation on MAVIC-T (challenge evaluation)](<https://www.sota2.com/research/sota/image-to-image-translation-on-mavic-t-challenge-evaluation.md>): Image-to-Image Translation; MAVIC-T (challenge evaluation); SAR→EO Score: 27.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.06753>)

[PDF](<https://arxiv.org/pdf/2603.06753.pdf>)
