HunyuanWorld-Mirror is a versatile feed-forward model for comprehensive 3D geometric prediction. It integrates diverse geometric priors (camera poses, calibrated intrinsics, depth maps) and simultaneously generates various 3D representations (point clouds, multi-view depths, camera parameters, surface normals, 3D Gaussians) in a single forward pass.
☯️ HunyuanWorld-Mirror Introduction
Architecture
HunyuanWorld-Mirror consists of two key components:
(1) Multi-Modal Prior Prompting: A mechanism that embeds diverse prior modalities, including calibrated intrinsics, camera pose, and depth, into the feed-forward model. Given any subset of the available priors, we utilize several lightweight encoding layers to convert each modality into structured tokens.
(2) Universal Geometric Prediction: A unified architecture capable of handling the full spectrum of 3D reconstruction tasks from camera and depth estimation to point map regression, surface normal estimation, and novel view synthesis.
🔗 BibTeX
If you find HunyuanWorld-Mirror useful for your research and applications, please cite using this BibTeX:
@article{liu2025worldmirror,
title={WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting},
author={Liu, Yifan and Min, Zhiyuan and Wang, Zhenwei and Wu, Junta and Wang, Tengfei and Yuan, Yixuan and Luo, Yawei and Guo, Chunchao},
journal={arXiv preprint arXiv:2510.10726},
year={2025}
}
Acknowledgements
We sincerely thank the authors and contributors of VGGT, Fast3R, CUT3R, and DUSt3R for their outstanding open-source work and pioneering research.
- Downloads last month
- 2,412