README.md

---
license: mit
pipeline_tag: image-to-3d
---

# Quantized Visual Geometry Grounded Transformer

[![arXiv](https://img.shields.io/badge/QuantVGGT-2509.21302-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2509.21302)
[![GitHub](https://img.shields.io/badge/GitHub-Code-blue?style=flat-square&logo=github)](https://github.com/wlfeng0509/QuantVGGT)

This repository contains the weights and calibration data for **QuantVGGT**, presented in the paper [Quantized Visual Geometry Grounded Transformer](https://arxiv.org/abs/2509.21302).

QuantVGGT is the first quantization framework specifically designed for Visual Geometry Grounded Transformers (VGGTs). It addresses unique challenges in compressing billion-scale 3D reconstruction models, such as heavy-tailed activation distributions and multi-view calibration instability.

## Installation

To get started, clone the official repository and install the dependencies:

```bash
git clone https://github.com/wlfeng0509/QuantVGGT.git
cd QuantVGGT
pip install -r requirements.txt
pip install -r requirements_demo.txt
```

## Quick Start

You can use the provided scripts for inference and calibration. For example, to generate filtered Co3D calibration data:

```bash
python Quant_VGGT/vggt/evaluation/make_calibation.py \
    --model_path VGGT-1B/model_tracker_fixed_e20.pt \
    --co3d_dir co3d_datasets/ \
    --co3d_anno_dir co3d_v2_annotations/ \
    --seed 0 \
    --cache_path all_calib_data.pt \
    --save_path calib_data.pt \
    --class_mode all \
    --kmeans_n 6 \
    --kmeans_m 7
```

To quantize, calibrate, and evaluate on Co3D:

```bash
python Quant_VGGT/vggt/evaluation/run_co3d.py \
    --model_path Quant_VGGT/VGGT-1B/model_tracker_fixed_e20.pt \
    --co3d_dir co3d_datasets/ \
    --co3d_anno_dir co3d_v2_annotations/ \
    --dtype quarot_w4a4 \
    --seed 0 \
    --lac \
    --lwc \
    --cache_path calib_data.pt \
    --class_mode all \
    --exp_name a44_uqant \
    --resume_qs
```

## Citation

If you find QuantVGGT useful for your work, please cite the following paper:

```bibtex
@article{feng2025quantized,
  title={Quantized Visual Geometry Grounded Transformer},
  author={Feng, Weilun and Qin, Haotong and Wu, Mingqiang and Yang, Chuanguang and Li, Yuqi and Li, Xiangqi and An, Zhulin and Huang, Libo and Zhang, Yulun and Magno, Michele and others},
  journal={arXiv preprint arXiv:2509.21302},
  year={2025}
}
```