#24 · Primary category： 3D Generation & Asset Creation
OpenLRM
An open-source impl. of Large Reconstruction Models
Project last updated：05/06/24
GitHub Stars
1.2K
Forks
80
Contributors
3
License
Apache-2.0
Why we included this project
A single image, or a few views, is enough for OpenLRM to output a triplane NeRF and mesh in one pass. It's the open-source companion to the LRM paper, so you get both pretrained weights and the training code to retrain on your own object data. That makes it a practical shortcut for 3D asset pipelines, game asset prep, and AR/VR work, compared with photogrammetry-style reconstruction. The codebase has been refactored for extensibility, and a Hugging Face demo lets you test it before integrating. Just be aware the released weights are under a non-commercial license, so verify that.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
modly
Desktop app to generate 3D models from images or prompt using local AI — runs entirely on your GPU
LichtFeld-Studio
Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.
map-anything
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
ComfyUI-3D-Pack
An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)
dust3d
Dust3D is a cross-platform 3D modeling software that makes it easy to create low poly 3D models for video games, 3D printing, and more.