andvg3/LSDM
Dataset and Code for NeurIPS 2023 paper "Language-driven Scene Synthesis using Multi-conditional Diffusion Model."
This project helps 3D artists, interior designers, or researchers create realistic 3D scenes by synthesizing objects that interact naturally with human motions. You provide a description of human motion and contact points, and it generates appropriate 3D objects that fit the interaction. This is useful for rapidly populating virtual environments with interactive elements.
No commits in the last 6 months.
Use this if you need to generate 3D objects that realistically interact with human actions within a virtual scene, for animation, simulation, or design.
Not ideal if you're looking to generate entire scenes from scratch without specific human interaction as a primary driver, or if you need to design objects from scratch rather than placing existing 3D models.
Stars
48
Forks
2
Language
Python
License
MIT
Category
Last pushed
Aug 08, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/andvg3/LSDM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...