30 datasets found

A dataset of 3D objects with varying sizes and orientations.

3D object recognition dataset

3D object recognition dataset

3D ShapeNets: A Deep Representation for Volumetric Shapes.

A public datasets adapted to the industrial context was developed in (Drost et al., 2017).

Semantic segmentation and 3D detection tasks on PartNet and ScanNet datasets

Shapellm: Universal 3D object understanding for embodied interaction

ULIP: Learning a unified representation of language, images, and point clouds for 3D understanding

Fine-grained RGB-D object datasets for 3D object recognition, consisting of 20 categories related to restaurants with a total of 100 instances, and 120 categories of shoe...

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.

Object recognition is arguably the most important problem at the heart of computer vision. Recently, Barbu et al. introduced a dataset called ObjectNet which includes objects in...

The ShapeNet part dataset contains 16,881 shapes from 16 classes and 50 parts in total.

A large-scale dataset of 3D objects for training next-generation image-text models.

The YCB-Video dataset contains 92 videos of 21 objects with varying textures and sizes under cluttered indoor environments.

LINEMOD dataset is a widely used instance-level 6D object pose estimation dataset which consists of 13 different objects with significant shape variation.

The dataset used in the PointCLIP paper is ModelNet10, ModelNet40, and ScanObjectNN. ModelNet10 consists of 4,899 synthetic meshed CAD models with 10 indoor categories, 3,991...

The ModelNet-40 dataset contains 2468 CAD models that correspond to 40 classes.

The PartNet dataset is a large-scale benchmark for 3D object recognition and retrieval. It consists of 527 objects composed of 2690 parts, which can be composited into a...

The authors created a custom dataset for their experiment, consisting of 33,000 images of 320 possible object-image combinations, with 10 possible shapes, 8 possible colors, 2...

The dataset used in the paper for point cloud registration.