Shap-E: Generating Conditional 3D Implicit Functions

<p>Interesting work titled "Shap-E: Generating Conditional 3D Implicit Functions" from OpenAI. Shap-E is a generative model for creating 3D objects.</p>
<p>The model is trained in two stages: first, the encoder is trained, and then the diffusion model is trained on the outputs of the encoder. Training on a large dataset with 3D and text data allows for the creation of complex and diverse 3D objects in seconds. Compared to Point-E, an explicit generative model based on point clouds, Shap-E converges faster and achieves comparable or better quality.</p>
<p>Paper: <a href="https://arxiv.org/abs/2305.02463">https://arxiv.org/abs/2305.02463</a><br>Github: <a href="https://github.com/openai/shap-e">https://github.com/openai/shap-e</a><br>Demo: <a href="https://huggingface.co/spaces/hysts/Shap-E">https://huggingface.co/spaces/hysts/Shap-E</a></p>;
<p>#ai #gpt #llm #3d #openai #text23D</p>