HunyuanWorld Mirror

--- license: other license_name: tencent-hunyuanworld-mirror-community license_link: https://github.com/Tencent-Hunyuan/HunyuanWorld-Mirror/blob/main/License.txt language: - en - zh tags: - hunyuan3d - worldmodel - 3d-reconstruction - 3d-generation - 3d - scene-generation - image-to-3D - video-to-3D pipeline_tag: image-to-3d extra_gated_eu_disallowed: true --- <p align="center"> <img src="assets/teaser.jpg" width="95%" alt="HunyuanWorld-Mirror Teaser"> </p> <p align="center"> <a href='https://3d-models.hunyuan.tencent.com/world/'><img src='https://img.shields.io/badge/Project-Page-green'></a> <a href='https://3d-models.hunyuan.tencent.com/world/worldMirror1_0/HYWorld_Mirror_Tech_Report.pdf'><img src='https://img.shields.io/badge/Technique-Report-red'></a> <a href='https://github.com/Tencent-Hunyuan/HunyuanWorld-Mirror'><img src='https://img.shields.io/badge/Github-Page-Green'></a> <a href='https://huggingface.co/spaces/tencent/HunyuanWorld-Mirror'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Demo-orange'></a> <a href=https://discord.gg/dNBrdrGGMa target="_blank"><img src= https://img.shields.io/badge/Discord-white.svg?logo=discord height=22px></a> <a href=https://x.com/TencentHunyuan target="_blank"><img src=https://img.shields.io/badge/Hunyuan-black.svg?logo=x height=22px></a> <p align="center"> 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....