metadata
license: mit
pipeline_tag: image-to-3d
tags:
- 3d
- gaussian-splatting
- novel-view-synthesis
- information-bottleneck
datasets:
- lhmd/re10k_torch
- lhmd/acid_torch
ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS
Weijie Wang 路 Donny Y. Chen 路 Zeyu Zhang 路 Duochao Shi 路 Akide Liu 路 Bohan Zhuang
NeurIPS 2025
Paper | Project Page | Code | Models
ZPressor is an architecture-agnostic module that compresses multi-view inputs for scalable feed-forward 3DGS.
Citation
If you find our work useful for your research, please consider citing us:
@article{wang2025zpressor,
title={ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS},
author={Wang, Weijie and Chen, Donny Y. and Zhang, Zeyu and Shi, Duochao and Liu, Akide and Zhuang, Bohan},
journal={arXiv preprint arXiv:2505.23734},
year={2025}
}
Contact
If you have any questions, please contact at wangweijie@zju.edu.cn.
Acknowledgements
This project is developed with several fantastic repos: pixelSplat, MVSplat and DepthSplat. We thank the original authors for their excellent work.