English
Related papers

Related papers: Efficient Multimodal 3D Object Detector via Instan…

200 papers

Multi-object tracking (MOT) has important applications in monitoring, logistics, and other fields. This paper develops a real-time multi-object tracking and prediction system in rugged environments. A 3D object detection algorithm based on…

Robotics · Computer Science 2023-08-24 Shixing Huang , Zhihao Wang , Junyuan Ouyang , Haoyao Chen

3D object detection has achieved significant performance in many fields, e.g., robotics system, autonomous driving, and augmented reality. However, most existing methods could cause catastrophic forgetting of old classes when performing on…

Computer Vision and Pattern Recognition · Computer Science 2023-08-25 Wenqi Liang , Gan Sun , Chenxi Liu , Jiahua Dong , Kangru Wang

Segmenting object instances is a key task in machine perception, with safety-critical applications in robotics and autonomous driving. We introduce a novel approach to instance segmentation that jointly leverages measurements from multiple…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Alex Zihao Zhu , Vincent Casser , Reza Mahjourian , Henrik Kretzschmar , Sören Pirk

LiDAR point clouds can effectively depict the motion and posture of objects in three-dimensional space. Many studies accomplish the 3D object detection by voxelizing point clouds. However, in autonomous driving scenarios, the sparsity and…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Yongxin Shao , Aihong Tan , Binrui Wang , Tianhong Yan , Zhetao Sun , Yiyang Zhang , Jiaxin Liu

Safety of the Intended Functionality (SOTIF) addresses sensor performance limitations and deep learning-based object detection insufficiencies to ensure the intended functionality of Automated Driving Systems (ADS). This paper presents a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Milin Patel , Rolf Jung

Recognizing objects in low-resolution images is a challenging task due to the lack of informative details. Recent studies have shown that knowledge distillation approaches can effectively transfer knowledge from a high-resolution teacher…

Computer Vision and Pattern Recognition · Computer Science 2024-09-05 Kangkai Zhang , Shiming Ge , Ruixin Shi , Dan Zeng

Augmenting LiDAR input with multiple previous frames provides richer semantic information and thus boosts performance in 3D object detection, However, crowded point clouds in multi-frames can hurt the precise position information due to the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-25 Yao Rong , Xiangyu Wei , Tianwei Lin , Yueyu Wang , Enkelejda Kasneci

Recent studies of multimodal industrial anomaly detection (IAD) based on 3D point clouds and RGB images have highlighted the importance of exploiting the redundancy and complementarity among modalities for accurate classification and…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Wenbo Sui , Daniel Lichau , Josselin Lefèvre , Harold Phelippeau

Bird's eye view (BEV) representation has emerged as a dominant solution for describing 3D space in autonomous driving scenarios. However, objects in the BEV representation typically exhibit small sizes, and the associated point cloud…

Computer Vision and Pattern Recognition · Computer Science 2024-03-25 Junbo Yin , Jianbing Shen , Runnan Chen , Wei Li , Ruigang Yang , Pascal Frossard , Wenguan Wang

Knowledge distillation (KD) is an effective method for compressing models in object detection tasks. Due to limited computational capability, UAV-based object detection (UAV-OD) widely adopt the KD technique to obtain lightweight detectors.…

Computer Vision and Pattern Recognition · Computer Science 2024-08-22 Liang Yao , Fan Liu , Chuanyi Zhang , Zhiquan Ou , Ting Wu

3D object detection based on LiDAR-camera fusion is becoming an emerging research theme for autonomous driving. However, it has been surprisingly difficult to effectively fuse both modalities without information loss and interference. To…

Computer Vision and Pattern Recognition · Computer Science 2020-12-09 Guojun Wang , Bin Tian , Yachen Zhang , Long Chen , Dongpu Cao , Jian Wu

Despite encouraging progress in 3D scene understanding, it remains challenging to develop an effective Large Multi-modal Model (LMM) that is capable of understanding and reasoning in complex 3D environments. Most previous methods typically…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Hanxun Yu , Wentong Li , Song Wang , Junbo Chen , Jianke Zhu

In real applications, new object classes often emerge after the detection model has been trained on a prepared dataset with fixed classes. Due to the storage burden and the privacy of old data, sometimes it is impractical to train the model…

Computer Vision and Pattern Recognition · Computer Science 2021-07-06 Dongbao Yang , Yu Zhou , Weiping Wang

Multimodal 3D object detection has garnered considerable interest in autonomous driving. However, multimodal detectors suffer from dimension mismatches that derive from fusing 3D points with 2D pixels coarsely, which leads to sub-optimal…

Computer Vision and Pattern Recognition · Computer Science 2025-01-09 Guoxin Zhang , Ziying Song , Lin Liu , Zhonghong Ou

The estimation of uncertainty in robotic vision, such as 3D object detection, is an essential component in developing safe autonomous systems aware of their own performance. However, the deployment of current uncertainty estimation methods…

Computer Vision and Pattern Recognition · Computer Science 2022-07-27 Matthew Pitropov , Chengjie Huang , Vahdat Abdelzad , Krzysztof Czarnecki , Steven Waslander

LiDAR and camera are two essential sensors for 3D object detection in autonomous driving. LiDAR provides accurate and reliable 3D geometry information while the camera provides rich texture with color. Despite the increasing popularity of…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Qi Jiang , Hao Sun , Xi Zhang

Contrastive image-to-LiDAR knowledge transfer, commonly used for learning 3D representations with synchronized images and point clouds, often faces a self-conflict dilemma. This issue arises as contrastive losses unintentionally dissociate…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Yifan Zhang , Junhui Hou

LiDAR-camera fusion methods have shown impressive performance in 3D object detection. Recent advanced multi-modal methods mainly perform global fusion, where image features and point cloud features are fused across the whole scene. Such…

Computer Vision and Pattern Recognition · Computer Science 2023-03-15 Xin Li , Tao Ma , Yuenan Hou , Botian Shi , Yuchen Yang , Youquan Liu , Xingjiao Wu , Qin Chen , Yikang Li , Yu Qiao , Liang He

3D object detection models that exploit both LiDAR and camera sensor features are top performers in large-scale autonomous driving benchmarks. A transformer is a popular network architecture used for this task, in which so-called object…

Computer Vision and Pattern Recognition · Computer Science 2024-10-28 Mathijs R. van Geerenstein , Felicia Ruppel , Klaus Dietmayer , Dariu M. Gavrila

3D object detection is an important task that has been widely applied in autonomous driving. To perform this task, a new trend is to fuse multi-modal inputs, i.e., LiDAR and camera. Under such a trend, recent methods fuse these two…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Yang Song , Lin Wang