Add model card for Track4World

Hi! I'm Niels from the Hugging Face community science team. I've opened this PR to add a model card for Track4World to improve its discoverability and provide users with context and usage instructions.

This PR includes:
- Relevant metadata (license, pipeline tag, and tags).
- Links to the [Track4World paper](https://huggingface.co/papers/2603.02573), [GitHub repository](https://github.com/TencentARC/Track4World), and [project page](https://jiah-cloud.github.io/Track4World.github.io/).
- A brief introduction and framework overview.
- Installation steps and sample usage snippets derived from your GitHub README.

This will help the community better understand and interact with your work on the Hub.

README.md

@@ -0,0 +1,88 @@
+---
+license: other
+pipeline_tag: other
+tags:
+- 3d-tracking
+- video-understanding
+- 4d-reconstruction
+- computer-vision
+---
+
+# Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels
+
+Track4World is a feedforward model for efficient holistic 3D tracking of every pixel in a world-centric coordinate system from a monocular video. Built on a global 3D scene representation, Track4World applies a novel 3D correlation scheme to simultaneously estimate the pixel-wise 2D and 3D dense flow between arbitrary frame pairs.
+
+*   **Paper:** [Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels](https://huggingface.co/papers/2603.02573)
+*   **Project Page:** [jiah-cloud.github.io/Track4World](https://jiah-cloud.github.io/Track4World.github.io/)
+*   **Repository:** [GitHub Repository](https://github.com/TencentARC/Track4World)
+
+---
+
+### 🖼️ Framework
+
+Track4World estimates dense 3D scene flow of every pixel between arbitrary frame pairs from a monocular video in a global feedforward manner, enabling efficient and dense 3D tracking of every pixel in the world-centric coordinate system.
+
+---
+
+## ⚙️ Setup and Installation
+
+```bash
+# Clone the repository with submodules
+git clone --recursive https://github.com/TencentARC/Track4World.git
+cd Track4World
+
+# Create and activate environment
+conda create -n track4world python=3.11
+conda activate track4world
+
+# Install PyTorch
+pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --index-url https://download.pytorch.org/whl/cu121
+
+# Install dependencies
+pip install -r requirements.txt
+```
+
+Please refer to the [official GitHub README](https://github.com/TencentARC/Track4World) for detailed instructions on installing third-party modules and downloading weights.
+
+---
+
+## 🚀 Sample Usage
+
+You can perform tracking and reconstruction on the provided demo video using the following commands:
+
+### First Frame 3D Tracking (`3d_ff`)
+
+```bash
+python demo.py \
+    --mp4_path demo_data/cat.mp4 \
+    --mode 3d_ff \
+    --Ts -1 \
+    --save_base_dir results/cat
+```
+
+### Dense Tracking: Every Pixel, Every Frame (`3d_efep`)
+
+```bash
+python demo.py \
+    --mp4_path demo_data/cat.mp4 \
+    --coordinate world_depthanythingv3 \
+    --mode 3d_efep \
+    --Ts -1 \
+    --ckpt_init checkpoints/track4world_da3.pth \
+    --save_base_dir results/cat
+```
+
+---
+
+## Citation
+
+If you find Track4World useful for your research, please cite:
+
+```bibtex
+@article{lu2026track4world,
+  title   = {Track4World: Feedforward World-Centric Dense 3D Tracking of All Pixels},
+  author  = {Jiahao Lu and Jiayi Xu and Wenbo Hu and Ruijie Zhu and Chengfeng Zhao and Sai-Kit Yeung and Ying Shan and Yuan Liu},
+  journal = {arXiv preprint arXiv:2603.02573},
+  year    = {2026}
+}
+```