9 datasets found

A custom dataset of prompts, reference images, and associated camera poses Pi, selected to showcase parallax and disocclusion in the 3D scene.

The dataset used in the paper for training and testing the DreamWaltz framework for generating and animating complex 3D avatars from text guidance and parametric human body prior.

Realistic 3D human generation from text prompts is a de-

Magic3D: High-resolution text-to-3D content creation.

Prolific-Dreamer: High-fidelity and diverse text-to-3D generation with variational score distillation.

The dataset used in the paper for 3D scene generation from text descriptions.

The dataset used in the TextMesh paper, containing 35 text prompts for 3D mesh generation.

The dataset used in the paper SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity

Text-to-3D generation has emerged as an important application that enables non-experts to easily create 3D contents. The conventional approaches for text-to-3D train a...