Related papers: Fast Point Transformer
The continual improvement of 3D sensors has driven the development of algorithms to perform point cloud analysis. In fact, techniques for point cloud classification and segmentation have in recent years achieved incredible performance…
The remarkable breakthroughs in point cloud representation learning have boosted their usage in real-world applications such as self-driving cars and virtual reality. However, these applications usually have an urgent requirement for not…
Along with increasingly popular virtual reality applications, the three-dimensional (3D) point cloud has become a fundamental data structure to characterize 3D objects and surroundings. To process 3D point clouds efficiently, a suitable…
LiDAR has become one of the primary 3D object detection sensors in autonomous driving. However, LiDAR's diverging point pattern with increasing distance results in a non-uniform sampled point cloud ill-suited to discretized volumetric…
Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention, but ignore their content and fail to establish relationships…
Most existing 3D instance segmentation methods are derived from 3D semantic segmentation models. However, these indirect approaches suffer from certain limitations. They fail to fully leverage global and local semantic information for…
While Transformers have achieved impressive success in natural language processing and computer vision, their performance on 3D point clouds is relatively poor. This is mainly due to the limitation of Transformers: a demanding need for…
Many point-based semantic segmentation methods have been designed for indoor scenarios, but they struggle if they are applied to point clouds that are captured by a LiDAR sensor in an outdoor environment. In order to make these methods more…
This paper presents a learning-based, lossless compression method for static point cloud geometry, based on context-adaptive arithmetic coding. Unlike most existing methods working in the octree domain, our encoder operates in a hybrid…
Feedforward fully convolutional neural networks currently dominate in semantic segmentation of 3D point clouds. Despite their great success, they suffer from the loss of local information at low-level layers, posing significant challenges…
Exploring contextual information in the local region is important for shape understanding and analysis. Existing studies often employ hand-crafted or explicit ways to encode contextual information of local regions. However, it is hard to…
The integration of point and voxel representations is becoming more common in LiDAR-based 3D object detection. However, this combination often struggles with capturing semantic information effectively. Moreover, relying solely on point…
While the Transformer architecture has become ubiquitous in the machine learning field, its adaptation to 3D shape recognition is non-trivial. Due to its quadratic computational complexity, the self-attention operator quickly becomes…
Remarkable performance from Transformer networks in Natural Language Processing promote the development of these models in dealing with computer vision tasks such as image recognition and segmentation. In this paper, we introduce a novel…
3D point cloud-based place recognition is highly demanded by autonomous driving in GPS-challenged environments and serves as an essential component (i.e. loop-closure detection) in lidar-based SLAM systems. This paper proposes a novel…
Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments. Most state-of-art approaches rely on relatively dense…
Conventional methods of 3D object generative modeling learn volumetric predictions using deep networks with 3D convolutional operations, which are direct analogies to classical 2D ones. However, these methods are computationally wasteful in…
For current object detectors, the scale of the receptive field of feature extraction operators usually increases layer by layer. Those operators are called scale-oriented operators in this paper, such as the convolution layer in CNN, and…
Existing networks directly learn feature representations on 3D point clouds for shape analysis. We argue that 3D point clouds are highly redundant and hold irregular (permutation-invariant) structure, which makes it difficult to achieve…
Autonomous vehicles operate in highly dynamic environments necessitating an accurate assessment of which aspects of a scene are moving and where they are moving to. A popular approach to 3D motion estimation, termed scene flow, is to employ…