Ir para o conteúdo
ModelListadosExterno
Baixar

Depth Head Kitti

Monocular depth estimation head trained on KITTI (RMSE: 2.79). Part of A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens (CVPR 2026 Highlight).

Fontehuggingface.co/Amazon-FAR/depth-head-kitti/tree/87e1f23886fbe152cdddfc77bae21287e8dc6693
TipoOtherVersãoPytorch modelCnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
784 KB
Versão
vPytorch model
Atualizado
20 de out. de 2026
Fonte
Hugging Face

Descrição da fonte

Depth Head — KITTI

Monocular depth estimation head trained on KITTI (RMSE: 2.79). Part of A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens (CVPR 2026 Highlight).

Usage

Requires a frozen DINOv3 ViT-B backbone. See the DeltaTok GitHub repository for training and evaluation code.

Acknowledgements

Citation

@inproceedings{kerssies2026deltatok,
  title     = {A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens},
  author    = {Kerssies, Tommie and Berton, Gabriele and He, Ju and Yu, Qihang and Ma, Wufei and de Geus, Daan and Dubbelman, Gijs and Chen, Liang-Chieh},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year      = {2026}
}

Fontes

1 fonte
Hugging FacePrimárioVersão 87e1f23886fbe152cdddfc77bae21287e8dc6693
huggingface.co/Amazon-FAR/depth-head-kitti/tree/87e1f23886fbe152cdddfc77bae21287e8dc6693

Verificado 20 de out.

Artefatos de modelo

1 artefato

pytorch_model.bin

bin · 784 KB · SHA-256 a05336ed06c2…2b5b · Hugging Face

Download file

Trechos de fonte

2 trechos
Readme3 de ago.huggingface.co/Amazon-FAR/depth-head-kitti

--- datasets: - kitti library_name: pytorch license: apache-2.0 pipeline_tag: depth-estimation tags: - deltatok - cvpr2026-highlight --- # Depth Head — KITTI Monocular depth estimation head trained on KITTI (RMSE: 2.79). Part of [A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens](https://huggingface.co/papers/2604.04913) (CVPR 2026 Highlight). ## Usage Requires a frozen [DINOv3](https://github.com/facebookresearch/dinov3) ViT-B backbone. See the [DeltaTok GitHub repository](https://github.com/amazon-far/deltatok) for training and evaluation code. ## Acknowledgements - [DINOv3](https://github.com/facebookresearch/dinov3) - [KITTI](https://www.cvlibs.net/datasets/kitti/) ## Citation ```bibtex @inproceedings{kerssies2026deltatok, title = {A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens}, author = {Kerssies, Tommie and Berton, Gabriele and He, Ju and Yu, Qihang and Ma, Wufei and de Geus, Daan and Dubbelman, Gijs and Chen, Liang-Chieh}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026} } ```

Note3 de ago.huggingface.co/Amazon-FAR/depth-head-kitti

Source context: 0 downloads · 1 likes · Pipeline depth-estimation · Library pytorch · Repo Amazon-FAR/depth-head-kitti