taegyoun88/egoxtreme-test

---
language:
- en
license: cc-by-nc-4.0
size_categories:
- 100K<n<1M
task_categories:
- object-detection
pretty_name: EgoXtreme (Test Set)
---

# EgoXtreme: A Dataset for Robust Object Pose Estimation in Egocentric Views under Extreme Conditions

[](https://taegyoun88.github.io/EgoXtreme/)
[](https://github.com/taegyoun88/EgoXtreme)
[](https://arxiv.org/abs/2603.25135)
[](https://huggingface.co/datasets/taegyoun88/egoxtreme)

## 📖 Dataset Information
EgoXtreme is a novel large-scale dataset designed for robust egocentric 6D object pose estimation under extreme environmental conditions. It was captured at 30 fps using Aria glasses, providing high-resolution 1408 x 1408 raw fisheye RGB images.

The dataset features 15 participants performing diverse interactions with 13 different objects (including sports equipment, assembly blocks, and emergency supplies). It is divided into training (518.8 min), validation (80.7 min), and test (176 min) sets across three challenging scenarios: Industrial Maintenance, Sports, and Emergency Rescue.

> **Note on Train/Val Set:** For fair evaluation, the GT annotations for the test set are withheld. The train or validation images can be downloaded from our separate repository: [taegyoun88/egoxtreme](https://huggingface.co/datasets/taegyoun88/egoxtreme).

## 🚀 Sample Usage

The official [EgoXtreme GitHub repository](https://github.com/taegyoun88/EgoXtreme) provides tools for processing and visualizing the data.

### Undistortion
To generate undistorted RGB images and masks from the raw fisheye data:

```bash
# Process a specific scene
python tools/undistortion.py --data_dir ./data/test --scene_id 000000

# Process all scenes in the test set
python tools/undistortion.py --data_dir ./data/test --all
```

### Visualization
To visualize the Ground Truth pose on the images:

```bash
# Visualize specific scene (Add --undist for undistorted images, --im_id for single frame)
python tools/visualization.py --data_dir ./data/test --scene_id 000000 --models_dir ./models [--undist] [--im_id 0]
```

## 🎛️ Scenario Configurations
The detailed configurations of illumination and environmental conditions for each scenario are summarized below:
<table>
<thead>
<tr>
<th rowspan="2">Scenario</th>
<th rowspan="2">Standard<br><span style="font-size: 0.8em; font-weight: normal;">(normal, middle, high)</span></th>
<th colspan="5">Extreme</th>
<th rowspan="2">Smoke</th>
<th rowspan="2">Object</th>
</tr>
<tr style="font-size: 0.85em; font-weight: normal;">
<th>&nbsp;&nbsp;&nbsp;&nbsp;low&nbsp;&nbsp;&nbsp;&nbsp;</th>
<th>&nbsp;&nbsp;&nbsp;&nbsp;head&nbsp;&nbsp;&nbsp;&nbsp;</th>
<th>&nbsp;&nbsp;&nbsp;flash&nbsp;&nbsp;&nbsp;</th>
<th>&nbsp;&nbsp;warning&nbsp;&nbsp;</th>
<th style="border-right: 1px solid rgba(128, 128, 128, 0.2);">&nbsp;&nbsp;&nbsp;green&nbsp;&nbsp;&nbsp;</th>
</tr>
</thead>
<tbody style="text-align: center;">
<tr>
<td style="text-align: left;"><strong>Maintenance</strong></td>
<td>✔️</td>
<td>✔️</td>
<td>✔️</td>
<td>✔️</td>
<td></td>
<td></td>
<td>✔️</td>
<td>5</td>
</tr>
<tr>
<td style="text-align: left;"><strong>Sports</strong></td>
<td>✔️</td>
<td>✔️</td>
<td></td>
<td></td>
<td></td>
<td></td>
<td></td>
<td>5</td>
</tr>
<tr>
<td style="text-align: left;"><strong>Emergency</strong></td>
<td>✔️</td>
<td>✔️</td>
<td></td>
<td></td>
<td>✔️</td>
<td>✔️</td>
<td>✔️</td>
<td>3</td>
</tr>
</tbody>
</table>

Below is the mapping of Scene IDs to their corresponding scenarios across the dataset splits:
| Split | Scenario | Scene IDs |
| :--- | :--- | :--- |
| **Test** | Maintenance | `000000` - `000095` |
| | Sports | `000096` - `000179` |
| | Emergency | `000180` - `000191` |

For further fine-grained environmental attributes (e.g., specific light conditions and the presence of smoke) of each sequence, please refer to the sequence-level metadata JSON files.

## 📁 Dataset Structure & Format
All files (`*.json`) and 3d model information follow the **BOP format**.
Test targets for evaluation (`test_targets/`) and GT detections (`detections/`) are included.

The structure of the data hosted here is organized as follows:
```text
EgoXtreme-Test
├── test_targets/ # Target list for evaluation
├── detections/ # GT bounding boxes and masks
├── models/ # 3D CAD models (.ply) and info
├── test/
│ ├── 000000/ # Scene ID
│ │ ├── rgb/ # Raw fisheye RGB images
│ │ ├── mask/ # Full object masks
│ │ ├── scene_camera.json
│ │ └── scene_camera_undist.json
│ └── ...
├── camera.json
└── metadata_test.json # Sequence-level metadata (light, smoke, scenario)
```

## Citation

```bibtex
@inproceedings{egoxtreme2026,
title={EgoXtreme: A Dataset for Robust Object Pose Estimation in Egocentric Views under Extreme Conditions},
author={Yoon, Taegyoon and Han, Yegyu and Ji, Seojin and Park, Jaewoo and Kim, Sojeong and Kwon, Taein and Kim, Hyung-Sin},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2026}
}
```