EarthBridge-Preview

EarthBridge: A Solution for the 4th Multi-modal Aerial View Image Challenge (MAVIC-T) — Translation Track

Chen, Zhenyuan, Guanyuan Shen, and Feng Zhang. "EarthBridge: A Solution for 4th Multi-Modal Aerial View Image Challenge Translation Track." Accepted to the 22nd IEEE CVPR Workshop on Perception Beyond the Visible Spectrum (PBVS 2026). Preprint: arXiv, March 6, 2026. https://doi.org/10.48550/arXiv.2603.06753

This repository is a preview release of the EarthBridge codebase, containing the DBIM and CUT baselines used in our competition solution, along with their related training, inference, and evaluation code.

Flagship Experiments

This preview release includes only the flagship experiment configurations where each method achieved its best results among our experiments. Due to time limitations, comprehensive baselines, hyperparameter tuning, and scaling studies are not included — these are left for community exploration.

Baselines Included

Installation

1. Install from requirements.txt (recommended)

conda create -n rsgen python=3.12
conda activate rsgen
# we are using PyTorch 2.8.0 torchaudio 2.8.0 torchvision 0.23.0 from https://download.pytorch.org/whl/cu126
# other version mostly would work as long installed follow https://pytorch.org/get-started/previous-versions/
pip install torch==2.8.0+cu126 torchaudio==2.8.0+cu126 torchvision==0.23.0+cu126 --index-url https://download.pytorch.org/whl/cu126
# install other packages
pip install -r requirements.txt
pip install swanlab

2. Install from environment.yaml

conda env create -f environment.yaml
conda activate rsgen

Path configuration (optional)

If you clone the repo to a custom location, set PROJECT_ROOT to your project directory. Scripts will then resolve paths relative to it.

# Option 1: Source paths.env (auto-detects project root from file location)
source paths.env

# Option 2: Set manually before running scripts
export PROJECT_ROOT=/path/to/EarthBridge-Preview

Project structure

Pre-trained models (MaRS-Base)

Some scripts use pre-trained MaRS encoders for representation alignment or validation-set creation. Please pre-download them from HuggingFace/BiliSakura to your local models/ folder:

# From project root
mkdir -p models/BiliSakura
huggingface-cli download BiliSakura/MaRS-Base-RGB --local-dir models/BiliSakura/MaRS-Base-RGB
huggingface-cli download BiliSakura/MaRS-Base-SAR --local-dir models/BiliSakura/MaRS-Base-SAR

Experiment tracking with SwanLab

Training scripts support SwanLab for experiment tracking. Install with pip install swanlab.

SwanLab logs

Public resources

Enable SwanLab — Add --log_with swanlab to any training command:

--log_with swanlab

Log location — SwanLab logs are stored under ./ckpt/swanlog.

Quick Start

See docs/quick_start.md for detailed training, inference, and evaluation instructions.

Documentation

• Dataset setup
• Quick start guide
• Model parameters
• Pre-trained models

Credits

Library credits

diffusers.

Reference papers

Diffusion Bridge Implicit Models (DBIM, 2025)

Contrastive Unpaired Translation (CUT, ECCV 2020)