English
Related papers

Related papers: OccAM's Laser: Occlusion-based Attribution Maps fo…

200 papers

Existing approaches for unsupervised point cloud pre-training are constrained to either scene-level or point/voxel-level instance discrimination. Scene-level methods tend to lose local details that are crucial for recognizing the road…

Computer Vision and Pattern Recognition · Computer Science 2022-09-05 Junbo Yin , Dingfu Zhou , Liangjun Zhang , Jin Fang , Cheng-Zhong Xu , Jianbing Shen , Wenguan Wang

Urban-oriented autonomous vehicles require a reliable perception technology to tackle the high amount of uncertainties. The recently introduced compact 3D LIDAR sensor offers a surround spatial information that can be exploited to enhance…

Computer Vision and Pattern Recognition · Computer Science 2018-04-24 Achim Kampker , Mohsen Sefati , Arya Abdul Rachman , Kai Kreisköther , Pascual Campoy

LiDAR datasets for autonomous driving exhibit biases in properties such as point cloud density, range, and object dimensions. As a result, object detection networks trained and evaluated in different environments often experience…

Computer Vision and Pattern Recognition · Computer Science 2024-04-19 Deepti Hegde , Suhas Lohit , Kuan-Chuan Peng , Michael J. Jones , Vishal M. Patel

In recent times, the scope of LIDAR (Light Detection and Ranging) sensor-based technology has spread across numerous fields. It is popularly used to map terrain and navigation information into reliable 3D point cloud data, potentially…

Computer Vision and Pattern Recognition · Computer Science 2021-06-15 Aakash Kumar , Jyoti Kini , Mubarak Shah , Ajmal Mian

Point cloud segmentation is a fundamental task in 3D scene understanding. Its progress is constrained by the high cost and time required for dense 3D annotations, making labeled samples difficult to obtain. Beyond annotation scarcity,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Thenukan Pathmanathan , Kanchan Keisham , Thangarajah Akilan

The goal of open-vocabulary detection is to identify novel objects based on arbitrary textual descriptions. In this paper, we address open-vocabulary 3D point-cloud detection by a dividing-and-conquering strategy, which involves: 1)…

Computer Vision and Pattern Recognition · Computer Science 2023-05-18 Yuheng Lu , Chenfeng Xu , Xiaobao Wei , Xiaodong Xie , Masayoshi Tomizuka , Kurt Keutzer , Shanghang Zhang

Recently, the advancement of deep learning in discriminative feature learning from 3D LiDAR data has led to rapid development in the field of autonomous driving. However, automated processing uneven, unstructured, noisy, and massive 3D…

Computer Vision and Pattern Recognition · Computer Science 2020-05-21 Ying Li , Lingfei Ma , Zilong Zhong , Fei Liu , Dongpu Cao , Jonathan Li , Michael A. Chapman

3D object detection from point clouds is crucial in safety-critical autonomous driving. Although many works have made great efforts and achieved significant progress on this task, most of them suffer from expensive annotation cost and poor…

Computer Vision and Pattern Recognition · Computer Science 2023-04-20 Qianjiang Hu , Daizong Liu , Wei Hu

The purpose of this work is to review the state-of-the-art LiDAR-based 3D object detection methods, datasets, and challenges. We describe novel data augmentation methods, sampling strategies, activation functions, attention mechanisms, and…

Computer Vision and Pattern Recognition · Computer Science 2022-04-04 Walter Zimmer , Emec Ercelik , Xingcheng Zhou , Xavier Jair Diaz Ortiz , Alois Knoll

While 2D object detection has improved significantly over the past, real world applications of computer vision often require an understanding of the 3D layout of a scene. Many recent approaches to 3D detection use LiDAR point clouds for…

Computer Vision and Pattern Recognition · Computer Science 2020-11-20 Jihao Andreas Lin , Jakob Brünker , Daniel Fährmann

3D LiDAR point cloud data is crucial for scene perception in computer vision, robotics, and autonomous driving. Geometric and semantic scene understanding, involving 3D point clouds, is essential for advancing autonomous driving…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Li Li

One key vertical application that will be enabled by 6G is the automation of the processes with the increased use of robots. As a result, sensing and localization of the surrounding environment becomes a crucial factor for these robots to…

Signal Processing · Electrical Eng. & Systems 2021-02-23 Madhushanka Padmal , Dileepa Marasinghe , Vijitha Isuru , Nalin Jayaweera , Samad Ali , Nandana Rajatheva

3D object detection aims to predict object centers, dimensions, and rotations from LiDAR point clouds. Despite its simplicity, LiDAR captures only the near side of objects, making center-based detectors prone to poor localization accuracy…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Ruixiao Zhang , Runwei Guan , Xiangyu Chen , Adam Prugel-Bennett , Xiaohao Cai

Point clouds and high-resolution 3D data have become increasingly important in various fields, including surveying, construction, and virtual reality. However, simply having this data is not enough; to extract useful information, semantic…

Computer Vision and Pattern Recognition · Computer Science 2024-02-12 Sophia Schwarz , Tanja Pilz , Olaf Wysocki , Ludwig Hoegner , Uwe Stilla

Existing point-cloud based 3D object detectors use convolution-like operators to process information in a local neighbourhood with fixed-weight kernels and aggregate global context hierarchically. However, non-local neural networks and…

Computer Vision and Pattern Recognition · Computer Science 2021-08-23 Prarthana Bhattacharyya , Chengjie Huang , Krzysztof Czarnecki

Attribution maps are one of the most established tools to explain the functioning of computer vision models. They assign importance scores to input features, indicating how relevant each feature is for the prediction of a deep neural…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Robin Hesse , Simone Schaub-Meyer , Stefan Roth

3D object detection is an essential task for computer vision applications in autonomous vehicles and robotics. However, models often struggle to quantify detection reliability, leading to poor performance on unfamiliar scenes. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Nikita Durasov , Rafid Mahmood , Jiwoong Choi , Marc T. Law , James Lucas , Pascal Fua , Jose M. Alvarez

We present a system for automatic converting of 2D mask object predictions and raw LiDAR point clouds into full 3D bounding boxes of objects. Because the LiDAR point clouds are partial, directly fitting bounding boxes to the point clouds is…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Robert McCraith , Eldar Insafutdinov , Lukas Neumann , Andrea Vedaldi

Autonomous vehicles need to have a semantic understanding of the three-dimensional world around them in order to reason about their environment. State of the art methods use deep neural networks to predict semantic classes for each point in…

Computer Vision and Pattern Recognition · Computer Science 2021-09-27 Larissa T. Triess , David Peter , Christoph B. Rist , J. Marius Zöllner

We develop new representations and algorithms for three-dimensional (3D) object detection and spatial layout prediction in cluttered indoor scenes. We first propose a clouds of oriented gradient (COG) descriptor that links the 2D appearance…

Computer Vision and Pattern Recognition · Computer Science 2019-06-12 Zhile Ren , Erik B. Sudderth