Autonomous driving system: A comprehensive survey
Automation is increasingly at the forefront of transportation research, with the potential to
bring fully autonomous vehicles to our roads in the coming years. This comprehensive …
bring fully autonomous vehicles to our roads in the coming years. This comprehensive …
Delving into the devils of bird's-eye-view perception: A review, evaluation and recipe
Learning powerful representations in bird's-eye-view (BEV) for perception tasks is trending
and drawing extensive attention both from industry and academia. Conventional …
and drawing extensive attention both from industry and academia. Conventional …
Voxformer: Sparse voxel transformer for camera-based 3d semantic scene completion
Humans can easily imagine the complete 3D geometry of occluded objects and scenes. This
appealing ability is vital for recognition and understanding. To enable such capability in AI …
appealing ability is vital for recognition and understanding. To enable such capability in AI …
Ulip: Learning a unified representation of language, images, and point clouds for 3d understanding
The recognition capabilities of current state-of-the-art 3D models are limited by datasets with
a small number of annotated data and a pre-defined set of categories. In its 2D counterpart …
a small number of annotated data and a pre-defined set of categories. In its 2D counterpart …
Pointnext: Revisiting pointnet++ with improved training and scaling strategies
PointNet++ is one of the most influential neural architectures for point cloud understanding.
Although the accuracy of PointNet++ has been largely surpassed by recent networks such …
Although the accuracy of PointNet++ has been largely surpassed by recent networks such …
Point transformer v2: Grouped vector attention and partition-based pooling
As a pioneering work exploring transformer architecture for 3D point cloud understanding,
Point Transformer achieves impressive results on multiple highly competitive benchmarks. In …
Point Transformer achieves impressive results on multiple highly competitive benchmarks. In …
Rethinking range view representation for lidar segmentation
LiDAR segmentation is crucial for autonomous driving perception. Recent trends favor point-
or voxel-based methods as they often yield better performance than the traditional range …
or voxel-based methods as they often yield better performance than the traditional range …
Spherical transformer for lidar-based 3d recognition
LiDAR-based 3D point cloud recognition has benefited various applications. Without
specially considering the LiDAR point distribution, most current methods suffer from …
specially considering the LiDAR point distribution, most current methods suffer from …
Stratified transformer for 3d point cloud segmentation
Abstract 3D point cloud segmentation has made tremendous progress in recent years. Most
current methods focus on aggregating local features, but fail to directly model long-range …
current methods focus on aggregating local features, but fail to directly model long-range …
Virtual sparse convolution for multimodal 3d object detection
Abstract Recently, virtual/pseudo-point-based 3D object detection that seamlessly fuses
RGB images and LiDAR data by depth completion has gained great attention. However …
RGB images and LiDAR data by depth completion has gained great attention. However …