|
Download README.md from kulits/BrickFlow: direct link, hf CLI and curl.
- Browser
- Download file 2.4 kB
-
https://huggingface.co/kulits/BrickFlow/resolve/refs%2Fpr%2F1/README.md
- Command line
-
hf download hf://kulits/BrickFlow@refs/pr/1/README.md
-
curl -L -o README.md https://huggingface.co/kulits/BrickFlow/resolve/refs%2Fpr%2F1/README.md
2.4 kB
| datasets: | |
| - kulits/BrickFlow | |
| license: mit | |
| pipeline_tag: image-to-3d | |
| tags: | |
| - lego | |
| - ldraw | |
| - brick-assembly | |
| - 3d | |
| - flow-matching | |
| <div align="center"> | |
| # BrickFlow: Connectivity-Guided Brick Reconstruction | |
| [Peter Kulits](https://kulits.github.io/) and [Cordelia Schmid](https://cordeliaschmid.github.io/) | |
| NeurIPS 2026 | |
| [\[Paper\]](https://huggingface.co/papers/2611.17321) | [\[Project Page\]](https://kulits.github.io/BrickFlow/) | |
| </div> | |
| The weights of BrickFlow's denoisers. See [kulits/BrickFlow](https://huggingface.co/datasets/kulits/BrickFlow) for the | |
| dataset. The [`brickflow`](https://github.com/kulits/BrickFlow) package is on GitHub and has more instructions. | |
| ## Weights | |
| | file | model | size | | |
| | --- | --- | --- | | |
| | `weights/pt-s.pt` | PT-S: pretrained on `train/pt` (width 384, depth 12) | 127 MiB | | |
| | `weights/pt-b.pt` | PT-B: pretrained on `train/pt` (width 768, depth 12) | 503 MiB | | |
| | `weights/pt-l.pt` | PT-L: pretrained on `train/pt` (width 1024, depth 24) | 1.72 GiB | | |
| | `weights/ic-s.pt` | IC-S: image-conditioned, finetuned from PT-S on `train/ic` | 206 MiB | | |
| | `weights/ic-b.pt` | IC-B: image-conditioned, finetuned from PT-B on `train/ic` | 811 MiB | | |
| | `weights/ic-l.pt` | IC-L: image-conditioned, finetuned from PT-L on `train/ic` | 2.48 GiB | | |
| Each file is `torch.save(dict(model=state_dict))` of a `brickflow.model.Denoiser`, the post-hoc EMA of the training | |
| snapshots. IC models read DINOv3 features | |
| ([facebook/dinov3-vitl16-pretrain-lvd1689m](https://huggingface.co/facebook/dinov3-vitl16-pretrain-lvd1689m)) and use | |
| the PT model of the same size to finish sampling. | |
| ## Download | |
| `brickflow` fetches the weights by name into `brickflow/` in BrickNet's data directory (`$BRICKNET_DATA`, else the | |
| platform user-data directory), at the same paths as here: | |
| ```bash | |
| pip install brick-flow | |
| python -m brickflow fetch # assets, val/procbrick, and weights/pt-l | |
| python -m brickflow fetch weights/pt-s weights/ic-s | |
| python -m brickflow sample weights/pt-l.pt val/procbrick --samples 100 --guidance --out pt-l | |
| ``` | |
| ## License | |
| The weights are under the MIT license. | |
| ## Citation | |
| ```bibtex | |
| @InProceedings{kulits2026brickflow, | |
| author = {Kulits, Peter and Schmid, Cordelia}, | |
| title = {BrickFlow: Connectivity-Guided Brick Reconstruction}, | |
| booktitle = {Advances in Neural Information Processing Systems}, | |
| year = {2026} | |
| } | |
| ``` |