-
Multi-stage point completion network with critical set supervision
A multi-stage point completion network for 3D object reconstruction. -
Point Cloud Completion Via Skeleton-Detail Transformer
A point cloud completion network for 3D object reconstruction from a single image. -
PC2-PU: Patch Correlation and Point Correlation for Effective Point Cloud Ups...
Point cloud upsampling is to densify a sparse point set acquired from 3D sensors, providing a denser representation for the underlying surface. -
Oxford RobotCar
Oxford RobotCar dataset contains a large amount of data collected from one route through central Oxford, and covers various weather and traffic conditions. -
Completion3D benchmark
The Completion3D benchmark dataset, used for evaluating point cloud completion methods. -
PCN dataset
The dataset used for point cloud completion, including pairs of complete and partial point clouds. -
SampleNet: Differentiable Point Cloud Sampling
The dataset used in the paper for point cloud sampling and classification tasks. -
Argoverse 2
The Argoverse 2 motion forecasting dataset contains 250,000 driving scenarios, each 11 seconds long. These scenarios cover 6 geographical regions and represent 763 total hours... -
Microsoft Voxelized Upper Bodies (MVUB)
Point Cloud (PC) is a set of discrete 3D points that represent 3D scenes or objects. Typical PCs contain millions of points and each point is represented by spatial coordinates... -
DTU 3D Scan Dataset
DTU 3D Scan Dataset -
Object Re-Identification from Point Clouds
Object re-identification from point clouds -
Point Cloud Shape Completion Dataset
The dataset used in the paper is a dataset for training and testing the proposed RL-GAN-Net model. -
ESP-ZERO: UNSUPERVISED ENHANCEMENT OF ZERO-SHOT CLASSIFICATION FOR EXTREMELY ...
The proposed approach enhances the zero-shot classification capability on extremely sparse point clouds. -
3DeformRS: Certifying Spatial Deformations on Point Clouds
3D computer vision models are commonly used in security-critical applications such as autonomous driving and surgical robotics. Emerging concerns over the robustness of these... -
Eyecandies
The Eyecandies dataset is a novel synthetic dataset comprising ten different categories of candies rendered in a controlled environment. -
KITTI Vision Benchmark Suite
The KITTI Vision Benchmark Suite is a dataset used for object detection and tracking in autonomous vehicles. -
ScanObjectNN
Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen...
