---
license: cc-by-nc-sa-4.0
base_model:
- facebook/VGGT-1B
tags:
- multimodal
- thermal
- rgb
- 3d-reconstruction
---

# SEAR: Simple and Efficient Adaptation of Visual Geometric Transformers for RGB+Thermal 3D Reconstruction

This project aims to estimate camera poses of RGB and Thermal images together

* [Arxiv paper](https://arxiv.org/abs/2603.18774).
* [Code repo](https://github.com/Schindler-EPFL-Lab/SEAR)

![](https://raw.githubusercontent.com/Schindler-EPFL-Lab/SEAR/main/images/sink.gif)
![](https://raw.githubusercontent.com/Schindler-EPFL-Lab/SEAR/main/images/laptop.gif)
![](https://raw.githubusercontent.com/Schindler-EPFL-Lab/SEAR/main/images/reflect-robot.gif)
![](https://raw.githubusercontent.com/Schindler-EPFL-Lab/SEAR/main/images/drone-bathroom.gif)


This repo provides the checkpoints of the model.