Add model card for Depth Any Panoramas

README.md

@@ -0,0 +1,98 @@
+---
+pipeline_tag: depth-estimation
+license: apache-2.0
+---
+
+<h1 align="center">
+Depth Any Panoramas:<br>
+A Foundation Model for Panoramic Depth Estimation
+</h1>
+
+<p align="center">
+  <a href="https://linxin0.github.io"><b>Xin Lin</b></a> ·
+  <a href="#"><b>Meixi Song</b></a> ·
+  <a href="#"><b>Dizhe Zhang</b></a> ·
+  <a href="#"><b>Wenxuan Lu</b></a> ·
+  <a href="https://haodong2000.github.io"><b>Haodong Li</b></a>
+  <br>
+  <a href="#"><b>Bo Du</b></a> ·
+  <a href="#"><b>Ming-Hsuan Yang</b></a> ·
+  <a href="#"><b>Truong Nguyen</b></a> ·
+  <a href="http://luqi.info"><b>Lu Qi</b></a>
+</p>
+
+
+<p align="center">
+  <a href='https://huggingface.co/papers/2512.16913'><img src='https://img.shields.io/badge/Hugging%20Face-Paper-red?logo=huggingface&logoColor=white' alt='Hugging Face Paper'></a>
+  <a href='https://insta360-research-team.github.io/DAP_website/'><img src='https://img.shields.io/badge/Project_Page-Website-green?logo=insta360&logoColor=white' alt='Project Page'></a>
+  <a href='https://github.com/Insta360-Research-Team/DAP'><img src='https://img.shields.io/badge/GitHub-Code-blue?logo=github&logoColor=white' alt='GitHub'></a>
+  <a href='https://huggingface.co/spaces/Insta360-Research/DAP'><img src='https://img.shields.io/badge/🚀%20Hugging%20Face-Demo-orange'></a>
+</p>
+
+![teaser](https://huggingface.co/Insta360-Research/DAP/resolve/main/assets/depth_teaser2_00.png)
+
+This repository presents **Depth Any Panoramas (DAP)**, a panoramic metric depth foundation model that generalizes across diverse scene distances. It explores a data-in-the-loop paradigm for both data construction and framework design, combining public datasets, high-quality synthetic data, and real panoramic images. The model adopts DINOv3-Large as its backbone and introduces innovations such as a plug-and-play range mask head, sharpness-centric optimization, and geometry-centric optimization to enhance robustness and ensure geometric consistency across views. Experiments demonstrate strong performance and zero-shot generalization, providing robust and stable metric predictions in diverse real-world scenes.
+
+More details can be found in the [paper](https://huggingface.co/papers/2512.16913) and on the [project page](https://insta360-research-team.github.io/DAP_website/).
+
+## 🔨 Installation
+
+Clone the repo first:
+
+```Bash
+git clone https://github.com/Insta360-Research-Team/DAP
+cd DAP
+```
+
+(Optional) Create a fresh conda env:
+
+```Bash
+conda create -n dap python=3.12
+conda activate dap
+```
+
+Install necessary packages (torch > 2):
+
+```Bash
+# pytorch (select correct CUDA version, we test our code on torch==2.7.1 and torchvision==0.22.1)
+pip install torch==2.7.1 torchvision==0.22.1
+
+# other dependencies
+pip install -r requirements.txt
+```
+
+## 🤝 Pre-trained model
+
+Please download the pretrained model from this Hugging Face repository: [Insta360-Research/DAP-weights](https://huggingface.co/Insta360-Research/DAP-weights).
+
+## 📒 Inference
+
+```Bash
+python test/infer.py 
+```
+
+## 🚀 Evaluation
+
+```Bash
+python test/eval.py 
+```
+
+## 🤝 Acknowledgement
+
+We appreciate the open source of the following projects:
+
+* [PanDA](https://caozidong.github.io/PanDA_Depth/)
+* [Depth-Anything-V2](https://github.com/DepthAnything/Depth-Anything-V2)
+
+## Citation
+
+If you find our work useful, please cite our paper:
+
+```bibtex
+@article{lin2025dap,
+          title={Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation},
+          author={Lin, Xin and Song, Meixi and Zhang, Dizhe and Lu, Wenxuan and Li, Haodong and Du, Bo and Yang, Ming-Hsuan and Nguyen, Truong and Qi, Lu},
+          journal={arXiv},
+          year={2025}
+        }
+```