Skip to content
ModelListedExternal
Download

ChronoDepth v1

This model represents the official checkpoint of the paper titled "Learning Temporally Consistent Video Depth from Video Diffusion Priors".

Sourcehuggingface.co/jhshao/ChronoDepth-v1/tree/8ed51301cb97ec7a61a94a1bff1f7a107f73e9e8
KindUNetBase modelstabilityai/stable-video-diffusion-img2vid-xtVersionFP16Bgrade

Model source

Kind
UNet
File size
2.84 GB
Base model
stabilityai/stable-video-diffusion-img2vid-xt
Version
vFP16
Updated
Nov 1, 2026
Downloads
78
Source
Hugging Face

Source description

ChronoDepth: Learning Temporally Consistent Video Depth from Video Diffusion Priors

This model represents the official checkpoint of the paper titled "Learning Temporally Consistent Video Depth from Video Diffusion Priors".

Website PaperGitHub

Jiahao Shao*, Yuanbo Yang*, Hongyu Zhou, Youmin Zhang, Yujun Shen, Vitor Guizilini, Yue Wang, Matteo Poggi, Yiyi Liao†

🎓 Citation

Please cite our paper if you find this repository useful:

@misc{shao2024learningtemporallyconsistentvideo,
      title={Learning Temporally Consistent Video Depth from Video Diffusion Priors}, 
      author={Jiahao Shao and Yuanbo Yang and Hongyu Zhou and Youmin Zhang and Yujun Shen and Vitor Guizilini and Yue Wang and Matteo Poggi and Yiyi Liao},
      year={2024},
      eprint={2406.01493},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2406.01493}, 
}

Sources

1 source
Hugging FacePrimaryVersion 8ed51301cb97ec7a61a94a1bff1f7a107f73e9e8
huggingface.co/jhshao/ChronoDepth-v1/tree/8ed51301cb97ec7a61a94a1bff1f7a107f73e9e8

Verified Nov 1

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

1 artifact

diffusion_pytorch_model.safetensors

safetensors · FP16 (unverified) · 2.84 GB · SHA-256 9b5db40028bf…b469 · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 17huggingface.co/jhshao/ChronoDepth-v1

--- license: mit library_name: diffusers pipeline_tag: depth-estimation tags: - video depth estimation base_model: - stabilityai/stable-video-diffusion-img2vid-xt --- # ChronoDepth: Learning Temporally Consistent Video Depth from Video Diffusion Priors This model represents the official checkpoint of the paper titled "Learning Temporally Consistent Video Depth from Video Diffusion Priors". [![Website](https://img.shields.io/website?url=https%3A%2F%2Fjhaoshao.github.io%2FChronoDepth%2F&up_message=ChronoDepth&up_color=blue&style=flat&logo=timescale&logoColor=%23FFDC0F)](https://xdimlab.github.io/ChronoDepth/) [![Paper](https://img.shields.io/badge/arXiv-PDF-b31b1b)](https://arxiv.org/abs/2406.01493)[![GitHub](https://img.shields.io/github/stars/jhaoshao/ChronoDepth?style=default&label=GitHub%20★&logo=github)](https://github.com/jhaoshao/ChronoDepth) [Jiahao Shao*](https://jiahao-shao1.github.io/), Yuanbo Yang*, Hongyu Zhou, [Youmin Zhang](https://youmi-zym.github.io/), [Yujun Shen](https://shenyujun.github.io/), [Vitor Guizilini](https://vitorguizilini.github.io/), [Yue Wang](https://yuewang.xyz/), [Matteo Poggi](https://mattpoggi.github.io/), [Yiyi Liao†](https://yiyiliao.github.io/ ) ## 🎓 Citation Please cite our paper if you find this repository useful: ```bibtex @misc{shao2024learningtemporallyconsistentvideo, title={Learning Temporally Consistent Video Depth from Video Diffusion Priors}, author={Jiahao Shao and Yuanbo Yang and Hongyu Zhou and Youmin Zhang and Yujun Shen and Vitor Guizilini and Yue Wang and Matteo Poggi and Yiyi Liao}, year={2024}, eprint={2406.01493}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2406.01493}, } ```

NoteNov 1huggingface.co/jhshao/ChronoDepth-v1

Source context: 78 downloads · 1 likes · Pipeline depth-estimation · Library diffusers · Repo jhshao/ChronoDepth-v1

NoteAug 17huggingface.co/jhshao/ChronoDepth-v1

Source context: 20 downloads · 1 likes · Pipeline depth-estimation · Library diffusers · Repo jhshao/ChronoDepth-v1