Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets
This addresses the scalability challenge in physics-based world simulators for robotic manipulation and simulation training, though it appears incremental as an enhancement to existing 3D generation methods.
The paper tackles the problem of scalable creation of simulation-ready 3D assets for embodied AI training by introducing Seed3D 1.0, a foundation model that generates assets from single images with accurate geometry, textures, and materials, enabling direct integration into physics engines.
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