---
license: other
license_name: polyform-noncommercial-1.0.0
license_link: LICENSE
tags:
- 3d-gaussian-splatting
- novel-view-synthesis
- feed-forward
- neural-rendering
pipeline_tag: image-to-3d
---

# GlobalSplat — pretrained weights

Feed-forward, generalizable 3D Gaussian Splatting via global scene tokens
(*align first, decode later*). These are the released **RealEstate10K**
checkpoints for the GlobalSplat paper.

- Project page: https://r-itk.github.io/globalsplat/
- Paper: https://arxiv.org/abs/2604.15284

## Checkpoints

| File | Variant | #Gaussians | RE10K 24-view PSNR / SSIM / LPIPS |
|---|---|---|---|
| `globalsplat-re10k-2k.ckpt` | 2K (M_max=2) | 2K | 26.84 / 0.838 / 0.199 |
| `globalsplat-re10k-16k.ckpt` | 16K (paper default) | 16K | 28.53 / 0.883 / 0.140 |
| `globalsplat-re10k-16k-noopacity.ckpt` | 16K (current code, no opacity loss) | 16K | 28.95 / 0.891 / 0.124 |
| `globalsplat-re10k-32k.ckpt` | 32K | 32K | 29.48 / 0.901 / 0.123 |

The `-noopacity` 16K (trained with the released code, decoder opacity regularizer
disabled) outperforms the paper default at every context count:
12v 29.10 / 24v 28.95 / 36v 28.76 PSNR.

All files are weights-only checkpoints (`state_dict` + Lightning version; the
frozen VGG perceptual net and optimizer state are stripped).

## Usage

With the [GlobalSplat](https://r-itk.github.io/globalsplat/) code:

```bash
# 16K paper default
python -m globalsplat.main +experiment=re10k_16k dataset=re10k_eval_ctx24 \
    mode=test checkpointing.load=globalsplat-re10k-16k.ckpt
# 2K (sets M_max=2) and 32K
python -m globalsplat.main +experiment=re10k_2k  ... checkpointing.load=globalsplat-re10k-2k.ckpt
python -m globalsplat.main +experiment=re10k_32k ... checkpointing.load=globalsplat-re10k-32k.ckpt
```

## License

**PolyForm Noncommercial 1.0.0** with additional terms (see `LICENSE` and
`ADDITIONAL_TERMS.md`): noncommercial research / academic / personal use only;
commercial use requires a separate written license; military and surveillance
use are prohibited. Source-available, **not** an OSI open-source license.

## Citation

```bibtex
@article{itkin2026globalsplat,
  title={GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens},
  author={Itkin, Roni and Issachar, Noam and Keypur, Yehonatan and Chen, Xingyu and Chen, Anpei and Benaim, Sagie},
  journal={arXiv preprint arXiv:2604.15284},
  year={2026}
}
```