---
pipeline_tag: depth-estimation
library_name: torch
license: mit
---

# TAPIP3D: Tracking Any Point in Persistent 3D Geometry

This repository contains the TAPIP3D model as presented in [TAPIP3D: Tracking Any Point in Persistent 3D Geometry](https://huggingface.co/papers/2504.14717).

[Project Page](https://tapip3d.github.io)

Code: https://github.com/zbww/tapip3d

**Overview**

TAPIP3D is a method for long-term feed-forward 3D point tracking in monocular RGB and RGB-D video sequences. It introduces a 3D feature cloud representation that lifts image features into a persistent world coordinate space, canceling out camera motion and enabling accurate trajectory estimation across frames.

## Demo Usage

We provide a simple demo script `inference.py`, along with sample input data located in the `demo_inputs/` directory. The script accepts as input either an `.mp4` video file or an `.npz` file. If providing an `.npz` file, it should follow the following format:

- `video`: array of shape (T, H, W, 3), dtype: uint8
- `depths` (optional): array of shape (T, H, W), dtype: float32
- `intrinsics` (optional): array of shape (T, 3, 3), dtype: float32
- `extrinsics` (optional): array of shape (T, 4, 4), dtype: float32

For demonstration purposes, the script uses a 32x32 grid of points at the first frame as queries.

### Inference with Monocular Video

By providing a video as `--input_path`, the script first runs [MegaSAM](https://github.com/mega-sam/mega-sam) with [MoGe](https://wangrc.site/MoGePage/) to estimate depth maps and camera parameters. Subsequently, the model will process these inputs within the global frame.

To run inference:

```bash
python inference.py --input_path demo_inputs/sheep.mp4 --checkpoint checkpoints/tapip3d_final.pth --resolution_factor 2
```

An npz file will be saved to `outputs/inference/`. To visualize the results:

```bash
python visualize.py <result_npz_path>
```

### Inference with Known Depths and Camera Parameters

If an `.npz` file containing all four keys (`rgb`, `depths`, `intrinsics`, `extrinsics`) is provided, the model will operate in an aligned global frame, generating point trajectories in world coordinates.

## Citation

If you find this project useful, please consider citing:

```
@article{tapip3d,
  title={TAPIP3D: Tracking Any Point in Persistent 3D Geometry},
  author={Zhang, Bowei and Ke, Lei and Harley, Adam W and Fragkiadaki, Katerina},
  journal={arXiv preprint arXiv:2504.14717},
  year={2025}
}
```