Related papers: (AF)2-S3Net: Attentive Feature Fusion with Adaptiv…

Convolutional Neural Networks (CNN) are more suitable, indeed. However, fixed kernel sizes make traditional CNN too specific, neither flexible nor conducive to feature learning, thus impacting on the classification accuracy. The convolution…

Convolutional Neural Networks have become a cornerstone of medical image analysis due to their proficiency in learning hierarchical spatial features. However, this focus on a single domain is inefficient at capturing global, holistic…

Accurate detection of obstacles in 3D is an essential task for autonomous driving and intelligent transportation. In this work, we propose a general multimodal fusion framework FusionPainting to fuse the 2D RGB image and 3D point clouds at…

Semantic segmentation is a challenge in scene parsing. It requires both context information and rich spatial information. In this paper, we differentiate features for scene segmentation based on dedicated attention mechanisms (DF-DAM), and…

Precise and accurate predictions over boundary areas are essential for semantic segmentation. However, the commonly-used convolutional operators tend to smooth and blur local detail cues, making it difficult for deep models to generate…

Pedestrian detection plays an important role in many applications such as autonomous driving. We propose a method that explores semantic segmentation results as self-attention cues to significantly improve the pedestrian detection…

For real-time semantic segmentation, how to increase the speed while maintaining high resolution is a problem that has been discussed and solved. Backbone design and fusion design have always been two essential parts of real-time semantic…

Weakly supervised LiDAR semantic segmentation has made significant strides with limited labeled data. However, most existing methods focus on the network training under weak supervision, while efficient annotation strategies remain largely…

LiDAR panoptic segmentation facilitates an autonomous vehicle to comprehensively understand the surrounding objects and scenes and is required to run in real time. The recent proposal-free methods accelerate the algorithm, but their…

LiDAR semantic segmentation plays a pivotal role in 3D scene understanding for edge applications such as autonomous driving. However, significant challenges remain for real-world deployments, particularly for on-device post-deployment…

Decision making in automated driving is highly specific to the environment and thus semantic segmentation plays a key role in recognizing the objects in the environment around the car. Pixel level classification once considered a…

Despite significant progress in 3D object detection, point clouds remain challenging due to sparse data, incomplete structures, and limited semantic information. Capturing contextual relationships between distant objects presents additional…

Multimodal camera-LiDAR fusion technology has found extensive application in 3D object detection, demonstrating encouraging performance. However, existing methods exhibit significant performance degradation in challenging scenarios…

LiDAR-based 3D scene perception is a fundamental and important task for autonomous driving. Most state-of-the-art methods on LiDAR-based 3D recognition tasks focus on single frame 3D point cloud data, and the temporal information is ignored…

In recent years, with the development of computing resources and LiDAR, point cloud semantic segmentation has attracted many researchers. For the sparsity of point clouds, although there is already a way to deal with sparse convolution,…

Efficient RGB-D semantic segmentation has received considerable attention in mobile robots, which plays a vital role in analyzing and recognizing environmental information. According to previous studies, depth information can provide…

As the scene information, including objectness and scene type, are important for people with visual impairment, in this work we present a multi-task efficient perception system for the scene parsing and recognition tasks. Building on the…

This paper aims at high-accuracy 3D object detection in autonomous driving scenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR point cloud and RGB images as input and predicts oriented 3D…

LiDAR-based 3D object detection and semantic segmentation are critical tasks in 3D scene understanding. Traditional detection and segmentation methods supervise their models through bounding box labels and semantic mask labels. However,…

Large-scale LiDAR-based point cloud semantic segmentation is a critical task in autonomous driving perception. Almost all of the previous state-of-the-art LiDAR semantic segmentation methods are variants of sparse 3D convolution. Although…