thu-ml/CRM
[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.
This tool transforms a single 2D image into a detailed 3D textured mesh model, ready for use in various applications. It takes a single image of an object, ideally with a grey background for best results, and rapidly produces a realistic 3D model in OBJ format, complete with texture. This is ideal for 3D artists, game developers, product designers, or anyone needing to quickly generate 3D assets from 2D images.
684 stars. No commits in the last 6 months.
Use this if you need to rapidly create a 3D textured model of an object from just one image.
Not ideal if you require extremely precise, high-fidelity 3D models from complex, multi-object scenes or need to work with images that are not easily isolated on a grey background.
Stars
684
Forks
55
Language
Python
License
MIT
Category
Last pushed
Nov 28, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/thu-ml/CRM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jayin92/Skyfall-GS
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Tencent-Hunyuan/Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D...
deepseek-ai/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...