| --- |
| license: cc-by-nc-4.0 |
| library_name: pytorch |
| pipeline_tag: image-to-3d |
| tags: |
| - 3d-reconstruction |
| - panoramic |
| - depth-estimation |
| - camera-pose-estimation |
| - point-cloud |
| - indoor-scenes |
| - feed-forward |
| gated: true |
| extra_gated_heading: "Request access to Argus" |
| extra_gated_description: "Argus is released for non-commercial research and educational use only. We review access requests and may take 2-3 business days to respond." |
| extra_gated_prompt: "By requesting access you agree to use Argus and the associated weights for non-commercial purposes only, in accordance with the CC BY-NC 4.0 license." |
| extra_gated_fields: |
| Full name: text |
| Affiliation / Organization: text |
| Country: country |
| Intended use: |
| type: select |
| options: |
| - Academic research |
| - Education |
| - Personal / non-commercial project |
| - label: Other |
| value: other |
| Brief description of intended use: text |
| I confirm I will use Argus for non-commercial purposes only: checkbox |
| I agree to cite the Argus paper in any resulting work: checkbox |
| extra_gated_button_content: "Agree and request access" |
| --- |
| |
| <div align="center"> |
|
|
| <img src="https://raw.githubusercontent.com/realsee-developer/Argus/main/assets/argus_logo.png" width="200"> |
|
|
| <h3>Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes</h3> |
|
|
| <h4>ECCV 2026</h4> |
|
|
| <a href="https://argus-paper.realsee.ai" target="_blank"><img src="https://img.shields.io/badge/Project_Page-green" alt="Project Page"></a> |
| <a href="https://arxiv.org/abs/2606.30047" target="_blank"><img src="https://img.shields.io/badge/arXiv-2606.30047-b31b1b" alt="arXiv"></a> |
| <a href="https://huggingface.co/RealseeTechnology/argus-realsee3d" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-yellow" alt="HuggingFace Model"></a> |
| <a href="https://huggingface.co/spaces/RealseeDeveloper/Argus" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Demo-blue" alt="HuggingFace Demo"></a> |
| <a href="https://github.com/realsee-developer/RealSee3D" target="_blank"><img src="https://img.shields.io/badge/RealSee3D-Dataset-orange" alt="RealSee3D Dataset"></a> |
|
|
|
|
| <p><b><a href="https://www.realsee.ai">Realsee</a></b></p> |
| </div> |
|
|
| Argus is a feed-forward network for **metric panoramic 3D reconstruction** of indoor |
| scenes. Given sparse, unordered panoramic captures, it jointly predicts camera pose, |
| metric depth, and point cloud reconstruction in a shared metric world frame. |
|
|
| This repository hosts the pretrained Argus weights (`argus_realsee3d.pt`). |
|
|
| - **Paper:** [Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes](https://arxiv.org/abs/2606.30047) (arXiv:2606.30047) |
| - **Project page:** https://argus-paper.realsee.ai/ |
| - **Code & usage:** https://github.com/realsee-developer/Argus |
| - **Realsee3D dataset:** https://dataset.realsee.ai/ |
| - **Authors:** Xi Li, Linyuan Li, Yan Wu, Tong Rao, Kai Zhang, Xinchen Hui, Cihui Pan |
| - **License:** CC BY-NC 4.0 |
|
|
| ## Overview |
|
|
| Metric feed-forward 3D reconstruction for panoramic data has remained under-explored |
| due to the lack of large-scale panoramic RGB-D training data. This work introduces: |
|
|
| - **Realsee3D** — a hybrid dataset of 10K indoor scenes (1K real, 9K synthetic) with |
| 299K panoramic viewpoints and precise metric annotations. |
| - **Argus** — a feed-forward network trained on Realsee3D for metric panoramic 3D |
| reconstruction. |
|
|
| In the sparse unordered capture setting of Realsee3D, a poorly chosen coordinate anchor |
| can cause global pose drift. Argus addresses this with a **learned covisibility module** |
| that selects the geometrically optimal reference view to anchor the metric world frame. |
| To improve multi-task learning, the bidirectional pixel-to-world mapping is decomposed |
| into interpretable sub-steps with per-step supervision and cross-coordinate joint |
| constraints, reinforcing geometric consistency across prediction branches. |
|
|
| On the Realsee3D benchmark, Argus achieves state-of-the-art metric performance in |
| **camera pose estimation**, **depth estimation**, and **point cloud reconstruction**. |
|
|
| ## Files |
|
|
| | File | Description | |
| | --- | --- | |
| | `argus_realsee3d.pt` | Pretrained Argus model weights (PyTorch checkpoint) | |
|
|
| ## Usage |
|
|
| For the model architecture, inference pipeline, and example code, see the official |
| repository: https://github.com/realsee-developer/Argus |
|
|
| ## Citation |
|
|
| If you use Argus or the Realsee3D dataset, please cite: |
|
|
| ```bibtex |
| @misc{li2026argusmetricpanoramic3d, |
| title={Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes}, |
| author={Xi Li and Linyuan Li and Yan Wu and Tong Rao and Kai Zhang and Xinchen Hui and Cihui Pan}, |
| year={2026}, |
| eprint={2606.30047}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.CV}, |
| url={https://arxiv.org/abs/2606.30047}, |
| } |
| ``` |
|
|
