7 datasets found

Text2Shape is a dataset of 8,447 table instances and 6,591 chair instances from the ShapeNet dataset, along with 75,344 natural language descriptions.

Text-to-3D generation has shown promising results, yet common challenges such as the Multi-face Janus problem and extended generation time for high-quality assets. In this...

The dataset used in the paper for testing the HeadSculpt model, which consists of 3D head avatars generated from textual prompts.

The dataset used in the paper for training and testing the HeadSculpt model, which consists of 3D head avatars generated from textual prompts.

Text-to-3D generation using 2D visual prompts

CG3D: Compositional Generation for Text-to-3D via Gaussian Splatting

The Objaverse dataset contains around 800k 3D objects. After adopting simple filter leveraging CLIP [27] to remove the objects whose rendered images are not relevant to its...