Improve model card: Add pipeline tag, paper, project page, and code links

README.md

@@ -1,3 +1,52 @@
----
-license: cc-by-nc-4.0
----
+---
+license: cc-by-nc-4.0
+pipeline_tag: image-to-3d
+---
+
+# TUN3D: Towards Real-World Scene Understanding from Unposed Images
+
+This repository contains an implementation of TUN3D, a method for real-world indoor scene understanding from multi-view images.
+
+*   **Paper:** [TUN3D: Towards Real-World Scene Understanding from Unposed Images](https://huggingface.co/papers/2509.21388)
+*   **Project Page:** https://bulatko.github.io/tun3d/
+*   **Code:** https://github.com/col14m/TUN3D
+
+<div align="center">
+  <video src="https://github.com/user-attachments/assets/8644a6d7-3a4e-4b1b-b58e-023276ea12ee"> </video>
+  <p><i>TUN3D works with GT point clouds, posed images (with known camera poses), or fully unposed image sets (without poses or depths).</i></p>
+</div>
+
+## Abstract
+Layout estimation and 3D object detection are two fundamental tasks in indoor scene understanding. When combined, they enable the creation of a compact yet semantically rich spatial representation of a scene. Existing approaches typically rely on point cloud input, which poses a major limitation since most consumer cameras lack depth sensors and visual-only data remains far more common. We address this issue with TUN3D, the first method that tackles joint layout estimation and 3D object detection in real scans, given multi-view images as input, and does not require ground-truth camera poses or depth supervision. Our approach builds on a lightweight sparse-convolutional backbone and employs two dedicated heads: one for 3D object detection and one for layout estimation, leveraging a novel and effective parametric wall representation. Extensive experiments show that TUN3D achieves state-of-the-art performance across three challenging scene understanding benchmarks: (i) using ground-truth point clouds, (ii) using posed images, and (iii) using unposed images. While performing on par with specialized 3D object detection methods, TUN3D significantly advances layout estimation, setting a new benchmark in holistic indoor scene understanding.
+
+## Installation and Usage
+The repository is divided into two modules: `Reconstruction` and `Recognition`. Each module requires a separate installation of dependencies. Please refer to the [GitHub repository](https://github.com/col14m/TUN3D) for detailed installation instructions, data preprocessing steps, and guidance on running the model.
+
+## Predictions example
+
+#### ScanNet
+
+<p float="left">
+  <img src="https://github.com/col14m/TUN3D/raw/main/recognition/imgs/predictions_scannet.png" width="900"  height="396" />
+</p>
+
+#### S3DIS
+<p float="left">
+  <img src="https://github.com/col14m/TUN3D/raw/main/recognition/imgs/predictions_s3dis.png" width="900"  height="396" />
+</p>
+
+## Citation
+
+If you find this work useful for your research, please cite our paper:
+
+```bibtex
+@misc{konushin2025tun3drealworldsceneunderstanding,
+      title={TUN3D: Towards Real-World Scene Understanding from Unposed Images}, 
+      author={Anton Konushin and Nikita Drozdov and Bulat Gabdullin and Alexey Zakharov and Anna Vorontsova and Danila Rukhovich and Maksim Kolodiazhnyi},
+      year={2025},
+      eprint={2509.21388},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2509.21388}, 
+}
+```