gy65896/Neptune-X
[NeurIPS 2025 Spotlight] Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection
This project helps maritime professionals, like those in navigation safety or surveillance, improve the accuracy of detecting objects in diverse marine environments. It takes various inputs, such as conditional text or images, and generates realistic synthetic maritime scenes. These generated scenes are then used to train and enhance existing object detection systems, which output more reliable identifications of vessels, buoys, and other maritime objects.
Use this if you need high-quality synthetic maritime data to train or improve object detection models, especially when real-world annotated data is scarce or lacks diversity.
Not ideal if you are looking for a ready-to-use, off-the-shelf maritime object detection application rather than a tool for generating training data.
Stars
38
Forks
3
Language
Python
License
—
Category
Last pushed
Jan 15, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/gy65896/Neptune-X"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
soran-ghaderi/torchebm
🍓 Build and train energy-based and diffusion models in PyTorch ⚡.
spqb/adabmDCApy
Pytorch implementation of adabmDCA
opendilab/GenerativeRL
Python library for solving reinforcement learning (RL) problems using generative models (e.g....
AstraZeneca/DiffAbXL
The official implementation of DiffAbXL benchmarked in the paper "Exploring Log-Likelihood...
G-U-N/UniRL
a unified reinforcement learning toolbox for joint RL on language models and diffusion models