Related papers: LinK: Linear Kernel for LiDAR-based 3D Perception

Autonomous systems need to process large-scale, sparse, and irregular point clouds with limited compute resources. Consequently, it is essential to develop LiDAR perception methods that are both efficient and effective. Although naively…

Feature extraction and matching are the basic parts of many robotic vision tasks, such as 2D or 3D object detection, recognition, and registration. As is known, 2D feature extraction and matching have already achieved great success.…

Recent advance in 2D CNNs has revealed that large kernels are important. However, when directly applying large convolutional kernels in 3D CNNs, severe difficulties are met, where those successful module designs in 2D become surprisingly…

Large kernel convolutions offer a scalable alternative to vision transformers for high-resolution 3D volumetric analysis, yet naively increasing kernel size often leads to optimization instability. Motivated by the spatial bias inherent in…

Recently, some large kernel convnets strike back with appealing performance and efficiency. However, given the square complexity of convolution, scaling up kernels can bring about an enormous amount of parameters and the proliferated…

Most scanning LiDAR sensors generate a sequence of point clouds in real-time. While conventional 3D object detectors use a set of unordered LiDAR points acquired over a fixed time interval, recent studies have revealed that substantial…

The multi-line LiDAR is widely used in autonomous vehicles, so point cloud-based 3D detectors are essential for autonomous driving. Extracting rich multi-scale features is crucial for point cloud-based 3D detectors in autonomous driving due…

We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few large convolutional kernels instead of a stack of small…

State-of-the-art methods for driving-scene LiDAR-based perception (including point cloud semantic segmentation, panoptic segmentation and 3D detection, \etc) often project the point clouds to 2D space and then process them via 2D…

3D action recognition was shown to benefit from a covariance representation of the input data (joint 3D positions). A kernel machine feed with such feature is an effective paradigm for 3D action recognition, yielding state-of-the-art…

3D object detection is vital for many robotics applications. For tasks where a 2D perspective range image exists, we propose to learn a 3D representation directly from this range image view. To this end, we designed a 2D convolutional…

A unified neural network structure is presented for joint 3D object detection and point cloud segmentation in this paper. We leverage rich supervision from both detection and segmentation labels rather than using just one of them. In…

Visual Attention Networks (VAN) with Large Kernel Attention (LKA) modules have been shown to provide remarkable performance, that surpasses Vision Transformers (ViTs), on a range of vision-based tasks. However, the depth-wise convolutional…

State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. Although this corporation shows the competitiveness in the point cloud, it…

LiDAR-based 3D object detection, semantic segmentation, and panoptic segmentation are usually implemented in specialized networks with distinctive architectures that are difficult to adapt to each other. This paper presents LidarMultiNet, a…

Although Faster R-CNN and its variants have shown promising performance in object detection, they only exploit simple first-order representation of object proposals for final classification and regression. Recent classification methods…

Metric and kernel learning are important in several machine learning applications. However, most existing metric learning algorithms are limited to learning metrics over low-dimensional data, while existing kernel learning algorithms are…

3D object detection from a single image without LiDAR is a challenging task due to the lack of accurate depth information. Conventional 2D convolutions are unsuitable for this task because they fail to capture local object and its scale…

Medical image segmentation has seen significant improvements with transformer models, which excel in grasping far-reaching contexts and global contextual information. However, the increasing computational demands of these models,…

Understanding the computations of convolutional neural networks requires effective visualization of their kernels. While maximal activation methods have proven successful in highlighting the preferred features of 2D convolutional kernels,…