Seonglae Chooutput is
When compared to Point-E, an explicit generative model over point clouds, Shap-E converges faster and reaches comparable or better sample quality despite modeling a higher-dimensional, multi-representation output space.
release model weights, inference code, and samples
Shap-E: Generating Conditional 3D Implicit Functions
We present Shap-E, a conditional generative model for 3D assets. Unlike recent work on 3D generative models which produce a single output representation, Shap-E directly generates the parameters...
https://arxiv.org/abs/2305.02463
