We present a simple yet effective fully convolutional one-stage 3D object detector for LiDAR
point clouds of autonomous driving scenes, termed FCOS-LiDAR. Unlike the dominant …

It is difficult to precisely annotate object instances and their semantics in 3D space, and as
such, synthetic data are extensively used for these tasks, eg, category-level 6D object pose …

The success of the transformer architecture in natural language processing has recently
triggered attention in the computer vision field. The transformer has been used as a …

Establishment of point correspondence between camera and object coordinate systems is a
promising way to solve 6D object poses. However, surrogate objectives of correspondence …

Bird's eye view (BEV) is widely adopted by most of the current point cloud detectors due to
the applicability of well-explored 2D detection techniques. However, existing methods obtain …

Semantic analyses of object point clouds are largely driven by releasing of benchmarking
datasets, including synthetic ones whose instances are sampled from object CAD models …

Convolutional neural networks (CNNs) have been extensively used in a number of
applications and have shown to be quite effective. As the depth and width of the network …

Recently, 3D object detection based on multi-modal sensor fusion has been increasingly
adopted in automated driving and robotics. For example, the semantic information provided …

Urban mobility is undergoing a paradigm shift due to increasing concerns about road safety,
environmental impact, and traffic efficiency. Addressing these challenges, this thesis fosters …

Our model mainly consists of two modules: CNN backbone and transformer encoder-
decoder. We test with SparseConv [6] and PointPillars [7] with SECOND [14] as feature …