|
|
--- |
|
|
license: cc-by-nc-4.0 |
|
|
pipeline_tag: video-to-3d |
|
|
--- |
|
|
|
|
|
# Trace Anything: Representing Any Video in 4D via Trajectory Fields |
|
|
|
|
|
This repository contains the official implementation of the paper [Trace Anything: Representing Any Video in 4D via Trajectory Fields](https://huggingface.co/papers/2510.13802). |
|
|
|
|
|
Trace Anything proposes a novel approach to represent any video as a Trajectory Field, a dense mapping that assigns a continuous 3D trajectory function of time to each pixel in every frame. The model predicts the entire trajectory field in a single feed-forward pass, enabling applications like goal-conditioned manipulation, motion forecasting, and spatio-temporal fusion. |
|
|
|
|
|
Project Page: [https://trace-anything.github.io/](https://trace-anything.github.io/) |
|
|
Code: [https://github.com/ByteDance-Seed/TraceAnything](https://github.com/ByteDance-Seed/TraceAnything) |
|
|
|
|
|
## Overview |
|
|
<div align="center"> |
|
|
<img src="https://trace-anything.github.io/static/images/teaser.png" width="100%"/> |
|
|
</div> |
|
|
|
|
|
## Installation |
|
|
For detailed installation instructions, please refer to the [GitHub repository](https://github.com/ByteDance-Seed/TraceAnything#setup). |
|
|
|
|
|
## Sample Usage |
|
|
To run inference with the Trace Anything model, first, download the pretrained weights (see GitHub for details). Then, you can use the provided script as follows: |
|
|
|
|
|
```bash |
|
|
# Download the model weights to checkpoints/trace_anything.pt |
|
|
# Place your input video/image sequence in examples/input/<scene_name>/ |
|
|
|
|
|
python scripts/infer.py \ |
|
|
--input_dir examples/input \ |
|
|
--output_dir examples/output \ |
|
|
--ckpt checkpoints/trace_anything.pt |
|
|
``` |
|
|
Results, including 3D control points and confidence maps, will be saved to `<output_dir>/<scene>/output.pt`. |
|
|
|
|
|
## Interactive Visualization |
|
|
An interactive 3D viewer is available to explore the generated trajectory fields. Run it using: |
|
|
```bash |
|
|
python scripts/view.py --output examples/output/<scene>/output.pt |
|
|
``` |
|
|
For more options and remote usage, check the [GitHub repository](https://github.com/ByteDance-Seed/TraceAnything#interactive-visualization-%EF%B8%8F). |
|
|
|
|
|
## Citation |
|
|
If you find this work useful, please consider citing the paper: |
|
|
```bibtex |
|
|
@misc{liu2025traceanythingrepresentingvideo, |
|
|
title={Trace Anything: Representing Any Video in 4D via Trajectory Fields}, |
|
|
author={Xinhang Liu and Yuxi Xiao and Donny Y. Chen and Jiashi Feng and Yu-Wing Tai and Chi-Keung Tang and Bingyi Kang}, |
|
|
year={2025}, |
|
|
eprint={2510.13802}, |
|
|
archivePrefix={arXiv}, |
|
|
primaryClass={cs.CV}, |
|
|
url={https://arxiv.org/abs/2510.13802}, |
|
|
} |
|
|
``` |
