arplaboratory/ThermalGen

[NeurIPS 2025] Official repository for "ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation"

37
/ 100
Emerging

ThermalGen helps turn standard daytime camera footage into thermal infrared images. You provide regular RGB images or video from sources like drones or satellite cameras, and it generates realistic thermal versions, showing heat signatures as if captured by a thermal camera. This is useful for researchers or engineers working on tasks that benefit from thermal imaging but only have access to visible light cameras.

Use this if you need to simulate or analyze thermal properties of a scene or object, but you only have visible light (RGB) imagery available.

Not ideal if you require highly precise, calibrated temperature measurements, as this tool generates synthetic thermal images rather than actual sensor data.

thermal-imaging computer-vision drone-imagery remote-sensing image-synthesis
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 5 / 25

How are scores calculated?

Stars

41

Forks

2

Language

Python

License

MIT

Last pushed

Feb 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/arplaboratory/ThermalGen"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.