8000 GitHub - aim-uofa/PM-Loss: Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

aim-uofa/PM-Loss

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 

Repository files navigation

Logo

Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting

Duochao Shi* . Weijie Wang* · Donny Y. Chen · Zeyu Zhang · Jia-Wang Bian · Bohan Zhuang · Chunhua Shen

Logo

We introduce PM-Loss, a novel regularization loss based on a learned point map for feed-forward 3DGS, leading to smoother 3D geometry and better rendering.

Method

Logo

Overview of our PM-Loss. The process begins by estimating a dense point map of the scene using a pre-trained model. This estimated point map then serves as direct 3D supervision for training a feed-forward 3D Gaussian Splatting model. Crucially, unlike conventional methods relying predominantly on 2D supervision, our approach leverages explicit 3D geometric cues, leading to enhanced 3D shape fidelity.

TODOs

  • Release Code.
  • Release Model Checkpoints.

Citation

If you find our work useful for your research, please consider citing us:

@article{shi2025pmloss,
  title={Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting},
  author={Shi, Duochao and Wang, Weijie and Chen, Donny Y. and Zhang, Zeyu and Bian, Jiawang and Zhuang, Bohan and Shen, Chunhua},
  journal={arXiv preprint arXiv:2506.05327},
  year={2025}
}

Contact

If you have any questions, please create an issue on this repository or contact at dcshi@zju.edu.cn

Acknowledgements

This project is developed with several fantastic repos: VGGT, MVSplat and DepthSplat. We thank the original authors for their excellent work.

About

Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0