arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.19944eess.IVcs.CV
收藏

Seed3D 1.0:从图像到高保真仿真就绪3D资产

Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets

ByteDance(字节跳动)
Jiashi Feng, Xiu Li, Jing Lin, Jiahang Liu, Gaohong Liu, Weiqiang Lou, Su Ma, Guang Shi, Qinlong Wang, Jun Wang, Zhongcong Xu, Xuanyu Yi, Zihao Yu, Jianfeng Zha… 展开作者

Jiashi Feng, Xiu Li, Jing Lin, Jiahang Liu, Gaohong Liu, Weiqiang Lou, Su Ma, Guang Shi, Qinlong Wang, Jun Wang, Zhongcong Xu, Xuanyu Yi, Zihao Yu, Jianfeng Zhang, Yifan Zhu, Rui Chen, Jinxin Chi, Zixian Du, Li Han, Lixin Huang, Kaihua Jiang, Yuhan Li, Guan Luo, Shuguang Wang, Qianyi Wu, Fan Yang, Junyang Zhang, Xuanmeng Zhang

AI总结:

Seed3D 1.0是一个从单张图像生成仿真就绪3D资产的基础模型,解决了世界模拟器中物理准确性与可扩展性的矛盾,可直接用于机器人操作和仿真训练。

摘要:

开发具身AI智能体需要可扩展的训练环境,这些环境需在内容多样性与物理准确性之间取得平衡。世界模拟器提供了此类环境,但面临明显的局限性:基于视频的方法能生成多样化的内容,但缺乏用于交互式学习的实时物理反馈;而基于物理的引擎能提供精确的动力学,但受限于昂贵的人工资产创建带来的可扩展性问题。我们提出了Seed3D 1.0,一个从单张图像生成仿真就绪3D资产的基础模型,在保持物理严谨性的同时解决了可扩展性挑战。与现有的3D生成模型不同,我们的系统生成的资产具有准确的几何形状、对齐良好的纹理和逼真的基于物理的材质。这些资产可以以最小的配置直接集成到物理引擎中,从而能够部署到机器人操作和仿真训练中。除了单个物体,该系统还通过将物体组装成连贯的环境,扩展到完整的场景生成。通过实现可扩展的仿真就绪内容创建,Seed3D 1.0为推进基于物理的世界模拟器奠定了基础。Seed3D 1.0现已在https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?modelId=doubao-seed3d-1-0-250928&tab=Gen3D上提供。

英文摘要:

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

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑