Shap-E

We generate a 3D SDF and a texture field via two latent codes. We utilize DMTet to extract a 3D surface mesh from the SDF and query the texture field at surface points to get colors. We train with adversarial losses defined on 2D images. In particular, we use a rasterization-based differentiable renderer to obtain RGB images and silhouettes. We utilize two 2D discriminators, each on RGB image, and silhouette, respectively, to classify whether the inputs are real or fake. The whole model is end-to-end trainable. As several industries are moving towards modeling massive 3D virtual worlds, the need for content creation tools that can scale in terms of the quantity, quality, and diversity of 3D content is becoming evident. In our work, we aim to train performant 3D generative models that synthesize textured meshes which can be directly consumed by 3D rendering engines, thus immediately usable in downstream applications.

Meshy is a 3D generative AI production suite. Use our AI texturing and AI modeling tools to accelerate 3D content creation. Our AI texturing tool allows artists to choose either text prompts or 2D concept art, as well as an untextured model as input. AI will do the automatic texturing for your model in less than 3 minutes. With our art-directable AI modeling tool, artists can easily craft 3D models from reference images or text prompts, without having to use 3D sculpting or scanning tools like ZBrush or RealityCapture, while still generating impressive, high-poly 3D models. Stop losing days for modeling and texturing. 3D can be done in minutes. Generate 3D directly from 2D. No need to be a professional prompter. Upload your model and write anything you can imagine with the model in the prompt box. You'll receive a textured model in only less than 3 minutes! Our goal is to automate the whole 3D production pipeline with generative AI.