LGM
L
LGM
Overview :
LGM is a novel framework for generating high-resolution 3D models from textual prompts or single-view images. Its key insights include: (1) 3D Representation: We propose a multi-view Gaussian feature as an efficient yet powerful representation that can be fused for differentiable rendering. (2) 3D Backbone: We present an asymmetric U-Net as a high-throughput backbone operation for multi-view images, which can be utilized to generate from text or single-view image inputs using multi-view diffusion models. Extensive experiments demonstrate the high fidelity and efficiency of our method. Notably, we achieve high-resolution 3D content generation while maintaining fast rendering speed for 3D objects, even when training resolution is increased to 512x512.
Target Users :
["3D Content Creation","3D Object Design","Virtual World Development"]
Total Visits: 951
Top Region: US(100.00%)
Website Views : 73.4K
Use Cases
Generate a 3D model of a 'chair' described in text
Generate a 3D model of a 'car' from photographs
Generate a 3D model of a room from images taken from multiple angles
Features
Generate 3D models from text prompts
Generate 3D models from single-view images
Achieve high-resolution (512x512) 3D content generation
Differentiable rendering
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase