12 datasets found

ShapeNet Parts is a dataset for part segmentation of 3D shapes.

Tags2Parts dataset for 3D shape co-segmentation

Unsupervised co-segmentation of 3D shapes using a branched autoencoder network

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 dataset used in the paper is a Shapes3D dataset, which contains 3D shapes with varying sizes and colors.

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.

A dataset of 3D shapes, consisting of 30,000 images of 6,196 objects.

Shapenet is a large-scale synthesis 3D object dataset, where we follow [9] to use the official test splits of chair, car, and motorbike categories for evaluation since they...

The dataset used in the paper for text-driven photorealistic 3D style transfer.

ModelNet is a large-scale 3D object recognition dataset containing 30,000 models from 50 categories.

The dataset used in the paper is ShapeNetPart, a synthetic dataset for 3D object part segmentation. It contains 16,881 models from 16 categories.

Point cloud registration is a crucial problem in computer vision and robotics. Existing methods either rely on matching local geometric features, which are sensitive to the pose...