Shap-E is a conditional generative model for 3D assets launched by OpenAI. Unlike recent work on 3D generative models, Shap-E directly generates parameters of implicit functions that can be rendered into textured meshes and neural radiation fields. The development team trains Shap-E in two phases: first, an encoder is trained that deterministically maps 3D assets to the parameters of the implicit function; second, a conditional diffusion model is trained on the output of the encoder. When trained on large datasets of paired 3D and text data, the resulting model is capable of generating complex and diverse…

#Text #model #ShapE

Leave a Comment

Your email address will not be published. Required fields are marked *