Seed3D 1.0：從圖像到高擬真度、可即時模擬的3D資產

摘要

開發具身智慧體需要能平衡內容多樣性與物理準確性的可擴展訓練環境。世界模擬器雖能提供此類環境，卻面臨明顯侷限：基於影片的方法能生成多樣內容，但缺乏即時物理回饋以支援互動式學習；而基於物理的引擎雖能提供精確動力學模擬，卻因需耗費大量人力創建資產而存在可擴展性限制。我們推出Seed3D 1.0基礎模型，可透過單張影像生成即用型3D模擬資產，在保持物理嚴謹性的同時解決可擴展性難題。有別於現有3D生成模型，本系統產出的資產具備精確幾何結構、完美貼合紋理及符合物理規律的真實材質。這些資產僅需極簡配置即可直接整合至物理引擎，適用於機器人操作與模擬訓練等場景。除單一物件生成外，系統更可透過物件組裝實現完整場景生成，構建連貫的環境體系。Seed3D 1.0藉由實現可擴展的即用型內容生成，為推進物理世界模擬器奠定基礎。現可於https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?modelId=doubao-seed3d-1-0-250928&tab=Gen3D 體驗使用。

English

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

Seed3D 1.0：從圖像到高擬真度、可即時模擬的3D資產

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

摘要

Support