Logo

Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting

Duochao Shi* . Weijie Wang*Donny Y. ChenZeyu ZhangJia-Wang BianBohan ZhuangChunhua Shen

Paper | Project Page | Code

Logo

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

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 [email protected]

Acknowledgements

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

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support