Shap-E：生成条件3D隐式函数

摘要

我们提出了Shap-E，这是一个用于3D资产的条件生成模型。与最近关于3D生成模型的工作不同，这些模型产生单个输出表示，Shap-E直接生成可以呈现为纹理网格和神经辐射场的隐式函数的参数。我们通过两个阶段来训练Shap-E：首先，我们训练一个编码器，将3D资产确定性地映射到隐式函数的参数；其次，我们在编码器的输出上训练一个条件扩散模型。当在大型配对的3D和文本数据集上进行训练时，我们得到的模型能够在几秒钟内生成复杂且多样化的3D资产。与Point-E相比，Point-E是一个基于点云的显式生成模型，Shap-E收敛更快，并且在建模更高维度、多表示输出空间的情况下，达到了可比较或更好的样本质量。我们在https://github.com/openai/shap-e发布了模型权重、推理代码和样本。

English

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 of implicit functions that can be rendered as both textured meshes and neural radiance fields. We train Shap-E in two stages: first, we train an encoder that deterministically maps 3D assets into the parameters of an implicit function; second, we train a conditional diffusion model on outputs of the encoder. When trained on a large dataset of paired 3D and text data, our resulting models are capable of generating complex and diverse 3D assets in a matter of seconds. 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. We release model weights, inference code, and samples at https://github.com/openai/shap-e.

Shap-E：生成条件3D隐式函数

Shap-E: Generating Conditional 3D Implicit Functions

摘要

Support