Search Results for author:
Found 10 papers, 0 papers with code
CPSeg: Cluster-free Panoptic Segmentation of 3D LiDAR Point Clouds
A fast and accurate panoptic segmentation system for LiDAR point clouds is crucial for autonomous driving vehicles to understand the surrounding objects and scenes.
SMAC-Seg: LiDAR Panoptic Segmentation via Sparse Multi-directional Attention Clustering
Thus, we propose to use a novel centroid-aware repel loss as an additional term to effectively supervise the network to differentiate each object cluster with its neighbours.
GP-S3Net: Graph-based Panoptic Sparse Semantic Segmentation Network
GP-S3Net is a proposal-free approach in which no object proposals are needed to identify the objects in contrast to conventional two-stage panoptic systems, where a detection network is incorporated for capturing instance information.
Lite-HDSeg: LiDAR Semantic Segmentation Using Lite Harmonic Dense Convolutions
Autonomous driving vehicles and robotic systems rely on accurate perception of their surroundings.
S3Net: 3D LiDAR Sparse Semantic Segmentation Network
In literature, several approaches are introduced to attempt LiDAR semantic segmentation task, such as projection-based (range-view or birds-eye-view), and voxel-based approaches.
(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network
Autonomous robotic systems and self driving cars rely on accurate perception of their surroundings as the safety of the passengers and pedestrians is the top priority.
Ranked #3 on
3D Semantic Segmentation
on nuScenes
TORNADO-Net: mulTiview tOtal vaRiatioN semAntic segmentation with Diamond inceptiOn module
Semantic segmentation of point clouds is a key component of scene understanding for robotics and autonomous driving.
Ranked #15 on
3D Semantic Segmentation
on SemanticKITTI
Adaptive Binary-Ternary Quantization
Ternary quantization provides a more flexible model and outperforms binary quantization in terms of accuracy, however doubles the memory footprint and increases the computational cost.
Smart Ternary Quantization
Low bit quantization such as binary and ternary quantization is a common approach to alleviate this resource requirements.
Adaptive Hierarchical Down-Sampling for Point Cloud Classification
While several convolution-like operators have recently been proposed for extracting features out of point clouds, down-sampling an unordered point cloud in a deep neural network has not been rigorously studied.
