Li Xiangtian

Li Xiangtian

he/him

Researcher focusing on Large Language Model Post-training, Reinforcement Learning, Multi-agent Systems, and Multimodal AI. Previously worked on Embodied AI.

Text-to-Scene Generation

发布时间：

Overview

Text2Scene is a system that generates 3D scenes from natural language descriptions, enabling users to create 3D environments through text input. This project was part of my work on embodied AI and scene understanding.

Key Features

  • Natural Language Understanding: Parsing and understanding scene descriptions
  • 3D Scene Generation: Creating 3D scenes from text descriptions
  • Object Placement: Intelligent placement and arrangement of objects
  • Scene Composition: Generating coherent and realistic 3D scenes

Technologies

  • Natural Language Processing
  • 3D Scene Generation
  • Computer Graphics
  • Python, 3D Libraries