Duochao Shi* . Weijie Wang* · Donny Y. Chen · Zeyu Zhang · Jia-Wang Bian · Bohan Zhuang · Chunhua Shen
Paper | Project Page | Models
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.
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.- Release Code.
- Release Model Checkpoints.
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}
}
If you have any questions, please create an issue on this repository or contact at dcshi@zju.edu.cn
This project is developed with several fantastic repos: VGGT, MVSplat and DepthSplat. We thank the original authors for their excellent work.