12 datasets found

The DeepCAD dataset, which consists of 34910 training models and 3087 test models.

The dataset used in the Point2Cyl paper, which consists of 4316 training models and 1242 test models from the Fusion Gallery and DeepCAD datasets.

A dataset of volumetric point clouds for training an autoencoder for point clouds, consisting of four types of point clouds: encapsulated spheres, encapsulated cuboids,...

The GarageWorld dataset comprises eight large-scale garages, featuring six underground garages, one outdoor parking lot, and one multi-floor indoor garage.

The Habitat dataset is a large-scale indoor simulator dataset containing 145 semantically-annotated indoor scenes.

The ProlificDreamer dataset is a dataset of 3D models generated using the ProlificDreamer model.

A 3D warehouse dataset used to create the dataset mentioned in the paper.

The dataset used for training and testing the N-Cloth model, which consists of SMPL human body data with 2779 different postures in a fixed body shape.

The dataset used for training and testing the N-Cloth model, which consists of 90 action sequences of non-SMPL human bodies.

The dataset used for training and testing the N-Cloth model, which consists of 800 bunny models with different positions, rotations, and scales.

The Replica dataset contains 18 various highly photo-realistic indoor environments. It provides dense-mesh, high-resolution RGBD images and a large range of instance annotations...

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...