Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908608844791808 |
|---|---|
| author | Feng, Jiashi Li, Xiu Lin, Jing Liu, Jiahang Liu, Gaohong Lou, Weiqiang Ma, Su Shi, Guang Wang, Qinlong Wang, Jun Xu, Zhongcong Yi, Xuanyu Yu, Zihao Zhang, Jianfeng Zhu, Yifan Chen, Rui Chi, Jinxin Du, Zixian Han, Li Huang, Lixin Jiang, Kaihua Li, Yuhan Luo, Guan Wang, Shuguang Wu, Qianyi Yang, Fan Zhang, Junyang Zhang, Xuanmeng |
| author_facet | Feng, Jiashi Li, Xiu Lin, Jing Liu, Jiahang Liu, Gaohong Lou, Weiqiang Ma, Su Shi, Guang Wang, Qinlong Wang, Jun Xu, Zhongcong Yi, Xuanyu Yu, Zihao Zhang, Jianfeng Zhu, Yifan Chen, Rui Chi, Jinxin Du, Zixian Han, Li Huang, Lixin Jiang, Kaihua Li, Yuhan Luo, Guan Wang, Shuguang Wu, Qianyi Yang, Fan Zhang, Junyang Zhang, Xuanmeng |
| contents | Developing embodied AI agents requires scalable training environments that balance content diversity with physics accuracy. World simulators provide such environments but face distinct limitations: video-based methods generate diverse content but lack real-time physics feedback for interactive learning, while physics-based engines provide accurate dynamics but face scalability limitations from costly manual asset creation. We present Seed3D 1.0, a foundation model that generates simulation-ready 3D assets from single images, addressing the scalability challenge while maintaining physics rigor. Unlike existing 3D generation models, our system produces assets with accurate geometry, well-aligned textures, and realistic physically-based materials. These assets can be directly integrated into physics engines with minimal configuration, enabling deployment in robotic manipulation and simulation training. Beyond individual objects, the system scales to complete scene generation through assembling objects into coherent environments. By enabling scalable simulation-ready content creation, Seed3D 1.0 provides a foundation for advancing physics-based world simulators. Seed3D 1.0 is now available on https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?modelId=doubao-seed3d-1-0-250928&tab=Gen3D |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_19944 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets Feng, Jiashi Li, Xiu Lin, Jing Liu, Jiahang Liu, Gaohong Lou, Weiqiang Ma, Su Shi, Guang Wang, Qinlong Wang, Jun Xu, Zhongcong Yi, Xuanyu Yu, Zihao Zhang, Jianfeng Zhu, Yifan Chen, Rui Chi, Jinxin Du, Zixian Han, Li Huang, Lixin Jiang, Kaihua Li, Yuhan Luo, Guan Wang, Shuguang Wu, Qianyi Yang, Fan Zhang, Junyang Zhang, Xuanmeng Image and Video Processing Computer Vision and Pattern Recognition Developing embodied AI agents requires scalable training environments that balance content diversity with physics accuracy. World simulators provide such environments but face distinct limitations: video-based methods generate diverse content but lack real-time physics feedback for interactive learning, while physics-based engines provide accurate dynamics but face scalability limitations from costly manual asset creation. We present Seed3D 1.0, a foundation model that generates simulation-ready 3D assets from single images, addressing the scalability challenge while maintaining physics rigor. Unlike existing 3D generation models, our system produces assets with accurate geometry, well-aligned textures, and realistic physically-based materials. These assets can be directly integrated into physics engines with minimal configuration, enabling deployment in robotic manipulation and simulation training. Beyond individual objects, the system scales to complete scene generation through assembling objects into coherent environments. By enabling scalable simulation-ready content creation, Seed3D 1.0 provides a foundation for advancing physics-based world simulators. Seed3D 1.0 is now available on https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?modelId=doubao-seed3d-1-0-250928&tab=Gen3D |
| title | Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.19944 |