Edify 3D: Scalable High-Quality 3D Asset Generation

2024/11/11 by NVIDIA, :, Bala, Maciej +43 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Graphics (cs.GR)

paper · pdf · doi:10.48550/arxiv.2411.07135

openalex publication_date 2024/11/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We introduce Edify 3D, an advanced solution designed for high-quality 3D asset generation. Our method first synthesizes RGB and surface normal images of the described object at multiple viewpoints using a diffusion model. The multi-view observations are then used to reconstruct the shape, texture, and PBR materials of the object. Our method can generate high-quality 3D assets with detailed geometry, clean shape topologies, high-resolution textures, and materials within 2 minutes of runtime.

Cited by

• Voxify3D: Pixel Art Meets Volumetric Rendering

Related

• GraphicsDreamer: Image to 3D Generation with Physical Consistency
• Elevating 3D Models: High-Quality Texture and Geometry Refinement from a Low-Quality Model
• Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials
• An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion
• Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details