README.md

---
library_name: diffusers
license: cc-by-nc-4.0
pipeline_tag: other
tags:
- 3d-scene-generation
- latent-diffusion
- autonomous-driving
- kitti-360
- primitives
- cvpr-2026
---

# PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban Scenes

<p align="center">
  <a href="https://huggingface.co/papers/2506.19117">📄 Paper</a> &nbsp;|&nbsp;
  <a href="https://raniatze.github.io/pritti/">🌐 Project Page</a> &nbsp;|&nbsp;
  <a href="https://github.com/autonomousvision/pritti">💻 Code</a>
</p>

<p align="center">
  <img src="https://huggingface.co/raniatze/pritti-checkpoints/resolve/main/teaser.png" alt="PrITTI teaser" width="95%">
</p>

This repository hosts the **pre-trained checkpoints** for **PrITTI** (CVPR 2026), a latent-diffusion framework for controllable and editable 3D semantic urban scene generation.

Existing approaches to 3D semantic urban scene generation predominantly rely on voxel-based representations. In contrast, PrITTI advocates for a primitive-based paradigm where urban scenes are represented using compact, semantically meaningful 3D elements that are easy to manipulate and compose. PrITTI achieves state-of-the-art 3D scene generation quality with lower memory requirements and faster inference than voxel-based methods.

## Released Checkpoints

The checkpoints below were trained on [KITTI-360](https://www.cvlibs.net/datasets/kitti-360/).

| File | Size | Description |
|------|------|-------------|
| `lvae.ckpt` | 1.1 GB | Layout Variational Autoencoder, trained for 300 epochs (`epoch=299, step=580200`). |
| `ldm_b/` | 773 MB | DiT-B Latent Diffusion Model in `diffusers`-pipeline format (`model_index.json` + `transformer/` + `decoder/` + `scheduler/`). |

## Quick Start

Full environment setup, preprocessing, training, inference, and evaluation instructions live in the [official GitHub repository](https://github.com/autonomousvision/pritti). The snippet below downloads both checkpoints into the locations the code expects:

```bash
# Make sure these are set (also documented in the main README)
export LVAE_TIMESTAMP="2025.06.03.17.23.30"
export LVAE_EPOCH="299"
export LVAE_STEP="580200"

# LVAE checkpoint
LVAE_DIR=$PRITTI_EXP_ROOT/exp/training_lvae_model/training_lvae_model/$LVAE_TIMESTAMP/checkpoints
mkdir -p $LVAE_DIR
huggingface-cli download raniatze/pritti-checkpoints lvae.ckpt --local-dir $LVAE_DIR
mv $LVAE_DIR/lvae.ckpt $LVAE_DIR/epoch=$LVAE_EPOCH-step=$LVAE_STEP.ckpt

# LDM (DiT-B) checkpoint
LDM_DIR=$PRITTI_EXP_ROOT/exp/training_dit_model/training_dit_b_model/training_dit_b_model/$LVAE_TIMESTAMP
mkdir -p $LDM_DIR
huggingface-cli download raniatze/pritti-checkpoints --include "ldm_b/*" --local-dir $LDM_DIR
mv $LDM_DIR/ldm_b $LDM_DIR/checkpoint
```

Once downloaded, follow the [Inference](https://github.com/autonomousvision/pritti#-inference) section of the main README to reconstruct and generate scenes.

## License

Released under **CC BY-NC 4.0** — free for academic and non-commercial research use. See [LICENSE](https://github.com/autonomousvision/pritti/blob/main/LICENSE) for full terms.

## Citation

If you find PrITTI useful, please cite:

```bibtex
@inproceedings{Tze2026PrITTI,
    author    = {Tze, Christina Ourania and Dauner, Daniel and Liao, Yiyi and Tsishkou, Dzmitry and Geiger, Andreas},
    title     = {PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Scenes},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    year      = {2026},
}
```