What Does the Future Hold?
At Mirage, we’ve kept our platform at the edge of generative 3D starting with CLIP-Mesh by Nasir → GET3D by NVIDIA → Stable Dreamfusion by Google (implemented by ashawkey) → Point-E by OpenAI → Shap-E by OpenAI.
We’ve spent time optimizing these open-source repos to produce usable game assets in multiple formats (recently GLTF).
Today, we are open-sourcing Mirage3D. This repo is built upon the fantastic work of the folks mentioned above and is optimized to create GLB files easily.
GitHub — MirageML/Mirage3D: Open-Source Implementations of 3D Diffusion Models Optimized for GLB…
Open-Source Implementations of 3D Diffusion Models Optimized for GLB Output — GitHub — MirageML/Mirage3D: Open-Source…
Try out the repo yourself and consider contributing to help create a single source of truth for open-source generative 3D models, optimized to create usable 3D assets!
The Problem
Generative 3D is progressing slower than other modalities (audio, video, image, etc) due to the lack of 3D data online.
Unlike image models, it seems that closed-source models are going to have a significant quality improvement over open-source models.
Open-Source is Far Behind
There are a few notable open-source repositories that have been released recently.
Shap-E: Very efficient model from OpenAI that is able to generate meshes and NeRFs from text or image. Takes about 1 minute to generate.