| --- |
| license: other |
| license_name: nvidia-license |
| license_link: LICENSE |
| pipeline_tag: image-to-3d |
| tags: |
| - 3d-reconstruction |
| - camera-pose-estimation |
| - multi-view |
| --- |
| |
| # Solv3R: 3D Looped Transformer as a Multi-view Solver |
|
|
| Pretrained weights of Solv3R ([paper](https://arxiv.org/abs/2611.02857), [project page](https://ubc-vision.github.io/solv3r/), |
| [code](https://github.com/ubc-vision/solv3r)). |
|
|
| ```python |
| from solv3r import Solv3R, cameras_from_pose_enc, list_images, load_images |
| |
| model = Solv3R.from_pretrained() # downloads solv3r.safetensors from this repo |
| images = load_images(list_images("path/to/images")) |
| ctx = model.encode(images) |
| z = model.solve(ctx, calls=16) |
| pred = model.decode(z, ctx) # depth, depth_conf, rays, world_points, pose_enc |
| c2w, K = cameras_from_pose_enc(pred["pose_enc"], (ctx.H, ctx.W)) |
| ``` |
|
|
| The weights are built on [DVLT](https://github.com/nv-tlabs/dvlt) and are released under the |
| [NVIDIA License](LICENSE) (non-commercial, research and evaluation use only). |
|
|
| ```bibtex |
| @article{kwak2026solv3r, |
| title = {Solv3R: 3D Looped Transformer as a Multi-view Solver}, |
| author = {Kwak, Jeong-gi and Tagliasacchi, Andrea and Kagami, Sho and Ono, Yuki and Yi, Kwang Moo}, |
| journal = {arXiv preprint arXiv:2611.02857}, |
| year = {2026} |
| } |
| ``` |
|
|
