---
title: stereo-splat
canonical_url: "https://www.modelscope.cn/models/facebook/stereo-splat"
md_url: "https://www.modelscope.cn/models/facebook/stereo-splat.md"
repository: facebook/stereo-splat
last_updated: 2026-11-12
license: cc-by-nc-4.0
pipeline_tag: image-to-3D
tasks:
  - image-to-3D
parameters: 5.1M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 5
stars: 0
tags:
  - gaussian-splatting
  - novel-view-synthesis
  - stereo
  - depth-estimation
  - 3d-reconstruction
---

# stereo-splat

> stereo-splat - facebook 在 ModelScope 开源的模型。Model weights for StereoSplat: Metric-Scale Novel View Synthesis via Stereo-Grounded Gaussian Splatting (NeurIPS 2026).

facebook/stereo-splat 是 ModelScope 魔搭社区上的 5.1M 参数image-to-3D模型，采用 cc-by-nc-4.0 许可。

- **Repository**: facebook/stereo-splat
- **License**: cc-by-nc-4.0
- **Tasks**: image-to-3D
- **Parameters**: 5.1M
- **Tags**: gaussian-splatting, novel-view-synthesis, stereo, depth-estimation, 3d-reconstruction
- **Downloads**: 5
- **Stars**: 0
- **Last updated**: 2026-11-12

Source: https://www.modelscope.cn/models/facebook/stereo-splat

---

# StereoSplat

Model weights for **StereoSplat: Metric-Scale Novel View Synthesis via Stereo-Grounded Gaussian
Splatting** (NeurIPS 2026).

[Paper](https://arxiv.org/abs/2610.35902) |
[Project Page](https://vladimiryugay.github.io/stereosplat/) |
[Code](https://github.com/facebookresearch/stereo-splat)

StereoSplat predicts metric-scale 3D Gaussians from calibrated stereo pairs in a single
feed-forward pass, and renders novel views and depth.

## Files

| File | Content | SHA-256 |
|---|---|---|
| `stereosplat_v1.safetensors` | Weights; the model config is in the file metadata | `e84556050f65b28367a6bab67606d742db7b4881aa202582d687ad560260184f` |
| `stereosplat_v1.json` | Same config as plain JSON | `8c8c57468beafb55fabbea5cd2a72efff9b994a986839f891b27033a8fdff1cb` |

## FoundationStereo dependency

StereoSplat uses a frozen [FoundationStereo](https://github.com/NVlabs/FoundationStereo) backbone,
which is not included here and is subject to NVIDIA's license. Get it separately:

```
git clone https://github.com/NVlabs/FoundationStereo third_party/FoundationStereo
git -C third_party/FoundationStereo checkout 6e8806816b533e4d13ddbb95ffa907b797060a62
```

Download the ViT-S model `11-33-40` from the FoundationStereo README and place it as:

```
checkpoints/foundation_stereo/11-33-40/
  cfg.yaml
  model_best_bp2.pth   # sha256 8d7850b9dc68d1366722a02a39745704b1db41471211be6abd93ef463727e6be
```

## Usage

Install the code following the [GitHub repository](https://github.com/facebookresearch/stereo-splat),
then:

```
hf download facebook/stereo-splat stereosplat_v1.safetensors --local-dir checkpoints

python scripts/demo.py \
    --left path/to/left.png --right path/to/right.png \
    --intrinsics FX FY CX CY --baseline 0.25 \
    --checkpoint checkpoints/stereosplat_v1.safetensors \
    --fs-checkpoint-dir checkpoints/foundation_stereo/11-33-40 \
    --output-dir outputs/demo
```

The demo writes the Gaussians (`.ply`, standard 3DGS layout), the input-view depth, and rendered
RGB and depth for novel cameras. Rendering needs a CUDA GPU.

In Python:

```python
from huggingface_hub import hf_hub_download
from stereosplat.models.build import build_model, load_checkpoint, read_checkpoint

path = hf_hub_download("facebook/stereo-splat", "stereosplat_v1.safetensors")
config = dict(read_checkpoint(path)["config"], fs_checkpoint_path="checkpoints/foundation_stereo/11-33-40")
model = build_model(config)   # loads FoundationStereo
load_checkpoint(model, path)  # loads StereoSplat
model = model.cuda().eval()
```

## Results

Novel view synthesis at 320 x 640 with [MAC-VO](https://github.com/MAC-VO/MAC-VO) poses (paper
protocol: 3 consecutive stereo pairs, first and last as input, middle rendered).

| Benchmark | PSNR | SSIM | LPIPS | AbsRel | delta1 (%) |
|---|---|---|---|---|---|
| Infinigen | 29.41 | 0.954 | 0.116 | 0.033 | 98.56 |
| TartanAir v2 | 26.25 | 0.944 | 0.101 | 0.058 | 94.95 |
| KITTI (zero-shot) | 25.20 | 0.941 | 0.101 | 0.044 | 95.98 |

Trained on TartanAir, Infinigen and [XRStereo](https://huggingface.co/datasets/facebook/xrstereo).

## License

[CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/), see [LICENSE](LICENSE).
Non-commercial use only. FoundationStereo is subject to NVIDIA's license.

## Citation

```bibtex
@inproceedings{yugay2026stereosplat,
  title     = {StereoSplat: Metric-Scale Novel View Synthesis via Stereo-Grounded Gaussian Splatting},
  author    = {Yugay, Vladimir and Rozumny, Denis and Gevers, Theo and Vansteenkiste, Elias and Oswald, Martin R. and Luvizon, Diogo C.},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2026}
}
```