README.md

---
tags:
  - computer-vision
  - 4d-reconstruction
  - monocular-video
  - dynamic-scene-reconstruction
  - pytorch
library_name: pytorch
---

# MoRe Pretrained Weights

This repository is an **unofficial mirror** of the pretrained weights released for
[MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer](https://github.com/HellexF/MoRe).
The checkpoints are intended to be used with the official MoRe codebase for model inference.

## Source and provenance

The files in this repository were copied, without modification, from the
[Google Drive folder published by the MoRe authors](https://drive.google.com/drive/folders/1T5CBo4bqJAaR0IBU-v8fde87FkqdDpUe).

This mirror is provided only as an alternative download location. It is not affiliated with,
endorsed by, or maintained by the original MoRe authors. Please refer to the
[official repository](https://github.com/HellexF/MoRe), the
[project page](https://hellexf.github.io/MoRe/), and the
[paper](https://arxiv.org/abs/2603.05078) for authoritative documentation, licensing,
usage terms, and updates.

## Files

| File | Description | Size | SHA-256 |
| --- | --- | ---: | --- |
| `more_full.pt` | Full-attention MoRe checkpoint | 5,677,547,294 bytes | `8ac67b4870da62052a7529d9c71db200d943f9b061f71459c721665ca97454d0` |
| `more_stream.pt` | Streaming/grouped-causal-attention MoRe checkpoint | 5,677,555,805 bytes | `7db3af5ec6b2a977e2fe24aa7789a713d26c607214fad1bfb1e70054bc358dac` |

## Usage

Clone and install the official MoRe repository:

```bash
git clone https://github.com/HellexF/MoRe
cd MoRe

conda create -n more python=3.10 -y
conda activate more
conda install pytorch=2.9.0 torchvision=0.24.0 cudatoolkit=11.8 -c pytorch
conda install cudatoolkit-dev=11.8 -c conda-forge
pip install -r requirements.txt
```

Download the mirrored checkpoints into the directory expected by MoRe:

```bash
hf download haikuoxin/more --local-dir pretrained
```

Run inference with the full-attention checkpoint:

```bash
python inference.py \
    --config_path training/config/omniworld_full.yaml \
    --ckpt_path pretrained/more_full.pt \
    --image_path ./data/example_video \
    --output_dir ./results/full_res \
    --conf_thres 50.0 \
    --predict_motion
```

For streaming inference with `more_stream.pt`, follow the official repository's
MagiAttention installation and streaming configuration instructions.

## About MoRe

MoRe is a feed-forward 4D reconstruction transformer for recovering dynamic 3D scenes
from monocular videos. The official project describes two core components:
motion–structure disentanglement and grouped causal attention.

## Citation

If you use these weights, please cite the original MoRe work:

```bibtex
@inproceedings{fang2026moremotionawarefeedforward4d,
  title     = {MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer},
  author    = {Juntong Fang and Zequn Chen and Weiqi Zhang and Donglin Di and
               Xuancheng Zhang and Chengmin Yang and Yu-Shen Liu},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2026}
}
```