45 datasets found

The Through the Looking Glass dataset is a dataset for predicting 3D shapes of transparent shapes from a single image.

The TransProteus dataset is a synthetic dataset for predicting 3D shapes, masks, and properties of materials, liquids, and objects inside transparent containers.

The dataset used for training a Convolutional Neural Network to predict a grasp quality score over all grasp poses, given a depth image of an object.

The SHREC 19’ different connectivity data set contains shapes from different classes like humans.

The SHREC 16’ partiality data set contains shapes from different classes like dogs and humans.

The FAUST Synthetic data set contains 100 shapes which show 10 different people in 10 different poses.

The BuildingNet dataset is a large-scale 3D building model dataset. The dataset is used for 3D shape generation, completion, and reconstruction.

The dataset used in this paper is the 3D-Shapes dataset, a 3D shape classification dataset.

3D shapes are represented as point clouds, which are unordered sets of 3D points.

Pix3D dataset used for wild image reconstruction.

The dataset used in the paper is ShapeNet, a large-scale 3D shape dataset, and ModelNet40, a dataset for 3D object classification.

A dataset for 3D shape generation, using ShapeNet Core V2

A dataset for 3D shape generation, using the five shape categories selected from ShapeNet Core V1

The GET3D dataset is a dataset of 3D shapes, consisting of 3,000 models, each described by 2,048 points.

The LION dataset is a dataset of 3D shapes, consisting of 3,000 models, each described by 2,048 points.

The ShapeNet55 dataset was first created by PoinTr [40]. The training set contains 41,952 objects, while test set contains 10,518 objects.

The dataset used in the paper is ModelNet40 and ShapeNet55, which are 3D shape analysis datasets.

The ModelNet40 dataset is a collection of 3D models, each with multiple views and annotations.

The Dynamic FAUST dataset contains raw-scanned and registered meshes for 129 sequences of 10 humans with various motions.

3D shape datasets for active object recognition