alphaXiv

Explore

State of the Art

Sign In

Labs

Feedback

Browser Extension

We're hiring
PaperBlogResources

E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training

BibTex
Copy
@misc{zhaoThu Dec 11 2025 18:59:53 GMT+0000 (Coordinated Universal Time)erayzerselfsupervised3d,
      title={E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training},
      author={Qitao Zhao and Hao Tan and Qianqian Wang and Sai Bi and Kai Zhang and Kalyan Sunkavalli and Shubham Tulsiani and Hanwen Jiang},
      year={Thu Dec 11 2025 18:59:53 GMT+0000 (Coordinated Universal Time)},
      eprint={2512.10950},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2512.10950},
}
GitHub
E-RayZer
4
HTTPS
https://github.com/QitaoZhao/E-RayZer
SSH
git@github.com:QitaoZhao/E-RayZer.git
CLI
gh repo clone QitaoZhao/E-RayZer
Transform this paper into an audio lecture
Get an engaging lecture and Q&A format to quickly understand the paper in minutes, perfect for learning on the go.
Audio lecture
Q&A format