---
license: cc-by-nc-4.0
base_model: depth-anything/da3-giant
library_name: pytorch
tags:
  - 3d-gaussian-splatting
  - novel-view-synthesis
  - feed-forward
  - depth-anything-3
  - eccv-2026
---

# AirSplat: Alignment and Rating for Robust Feed-Forward 3D Gaussian Splatting

**ECCV 2026** · [Paper](https://arxiv.org/abs/2603.25129) · [Project page](https://kaist-viclab.github.io/airsplat-site/) · [Code](https://github.com/KAIST-VICLab/airsplat)

Minh-Quan Viet Bui\*, Jaeho Moon\*, Munchurl Kim — KAIST (\*equal contribution)

AirSplat adapts the Depth Anything 3 foundation model into a robust feed-forward 3D Gaussian Splatting model for novel-view synthesis, using **Self-Consistent Pose Alignment** (training-time feedback against pose–geometry misalignment) and **Rating-based Opacity Matching** (teacher-guided filtering of inconsistent primitives).

## Files

| file | size | contents |
|---|---|---|
| `airsplat-dl3dv.ckpt` | 5.6 GB (fp32) | full DA3-Giant backbone + AirSplat Gaussian heads, PyTorch `state_dict` (no optimizer state) |

The checkpoint is self-contained; the code never downloads the backbone separately.

## Usage

```bash
git clone https://github.com/KAIST-VICLab/airsplat && cd airsplat
pip install -r requirements.txt   # see README for the PyTorch/CUDA step
wget -P pretrained_weights https://huggingface.co/quan5609/AirSplat/resolve/main/airsplat-dl3dv.ckpt
CKPT=pretrained_weights/airsplat-dl3dv.ckpt ./eval_dl3dv_24v.sh
```

## License

**CC BY-NC 4.0 — non-commercial use only.** These weights are a derivative of the
[DA3-Giant](https://huggingface.co/depth-anything/da3-giant) weights (Copyright 2025 The Depth Anything 3 Team, CC BY-NC 4.0) and embed that backbone. The AirSplat source code is MIT-licensed separately.

## Citation

```bibtex
@inproceedings{bui2026airsplatalignmentratingrobust,
    title={AirSplat: Alignment and Rating for Robust Feed-Forward 3D Gaussian Splatting},
    author={Minh-Quan Viet Bui and Jaeho Moon and Munchurl Kim},
    booktitle={ECCV},
    year={2026}
}
```