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 …
Recent advancements in learning algorithms for point clouds: An updated overview
Recent advancements in self-driving cars, robotics, and remote sensing have widened the
range of applications for 3D Point Cloud (PC) data. This data format poses several new …
range of applications for 3D Point Cloud (PC) data. This data format poses several new …
Tri-perspective view for vision-based 3d semantic occupancy prediction
Modern methods for vision-centric autonomous driving perception widely adopt the bird's-
eye-view (BEV) representation to describe a 3D scene. Despite its better efficiency than …
eye-view (BEV) representation to describe a 3D scene. Despite its better efficiency than …
Surroundocc: Multi-camera 3d occupancy prediction for autonomous driving
Abstract 3D scene understanding plays a vital role in vision-based autonomous driving.
While most existing methods focus on 3D object detection, they have difficulty describing …
While most existing methods focus on 3D object detection, they have difficulty describing …
Bevfusion: Multi-task multi-sensor fusion with unified bird's-eye view representation
Multi-sensor fusion is essential for an accurate and reliable autonomous driving system.
Recent approaches are based on point-level fusion: augmenting the LiDAR point cloud with …
Recent approaches are based on point-level fusion: augmenting the LiDAR point cloud with …
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 …
Robo3d: Towards robust and reliable 3d perception against corruptions
The robustness of 3D perception systems under natural corruptions from environments and
sensors is pivotal for safety-critical applications. Existing large-scale 3D perception datasets …
sensors is pivotal for safety-critical applications. Existing large-scale 3D perception datasets …
Point Transformer V3: Simpler Faster Stronger
This paper is not motivated to seek innovation within the attention mechanism. Instead it
focuses on overcoming the existing trade-offs between accuracy and efficiency within the …
focuses on overcoming the existing trade-offs between accuracy and efficiency within the …
Clip2scene: Towards label-efficient 3d scene understanding by clip
Abstract Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D
zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP …
zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP …