Large Multi-View Gaussian Model

This tutorial provides a demo implementation of LGM. LGM, or Large Multi-View Gaussian Model, is an innovative framework for generating high-resolution 3D models from text prompts or single-view images. It was developed by researchers from Peking University, Nanyang Technological University's S-Lab, and the Shanghai Artificial Intelligence Laboratory in a paper... LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation The LGM framework, proposed in this paper, uses multi-view Gaussian features as 3D representations and an asymmetric U-Net as the backbone network to achieve high-fidelity and efficient 3D model generation. This method can generate 3D objects within 5 seconds and increases the training resolution to 512, thus achieving high-resolution 3D content generation.

Effect display

Run steps

1. After cloning the tutorial container and successfully starting it, follow the instructions in the figure below to enter the operation page:

2. Upload a picture/enter a prompt word/a combination of the two to generate a 3D display effect: