English
Related papers

Related papers: Unsupervised 3D Perception with 2D Vision-Language…

200 papers

A major bottleneck to scaling-up training of self-driving perception systems are the human annotations required for supervision. A promising alternative is to leverage "auto-labelling" offboard perception models that are trained to…

Computer Vision and Pattern Recognition · Computer Science 2023-11-03 Anqi Joyce Yang , Sergio Casas , Nikita Dvornik , Sean Segal , Yuwen Xiong , Jordan Sir Kwang Hu , Carter Fang , Raquel Urtasun

3D object detection plays an important role in autonomous driving and other robotics applications. However, these detectors usually require training on large amounts of annotated data that is expensive and time-consuming to collect.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-08 Jianren Wang , Haiming Gang , Siddharth Ancha , Yi-Ting Chen , David Held

Monocular 3D object detection has become a mainstream approach in automatic driving for its easy application. A prominent advantage is that it does not need LiDAR point clouds during the inference. However, most current methods still rely…

Computer Vision and Pattern Recognition · Computer Science 2023-03-16 Runzhou Tao , Wencheng Han , Zhongying Qiu , Cheng-zhong Xu , Jianbing Shen

Manually annotating 3D point clouds is laborious and costly, limiting the training data preparation for deep learning in real-world object detection. While a few previous studies tried to automatically generate 3D bounding boxes from weak…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Chang Liu , Xiaoyan Qian , Xiaojuan Qi , Edmund Y. Lam , Siew-Chong Tan , Ngai Wong

Both indoor and outdoor scene perceptions are essential for embodied intelligence. However, current sparse supervised 3D object detection methods focus solely on outdoor scenes without considering indoor settings. To this end, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2025-06-16 Yun Zhu , Le Hui , Hang Yang , Jianjun Qian , Jin Xie , Jian Yang

Recent self-training techniques have shown notable improvements in unsupervised domain adaptation for 3D object detection (3D UDA). These techniques typically select pseudo labels, i.e., 3D boxes, to supervise models for the target domain.…

Computer Vision and Pattern Recognition · Computer Science 2024-05-01 Zhanwei Zhang , Minghao Chen , Shuai Xiao , Liang Peng , Hengjia Li , Binbin Lin , Ping Li , Wenxiao Wang , Boxi Wu , Deng Cai

Conventional camera-based 3D object detectors in autonomous driving are limited to recognizing a predefined set of objects, which poses a safety risk when encountering novel or unseen objects in real-world scenarios. To address this…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Zhuolin He , Xinrun Li , Jiacheng Tang , Shoumeng Qiu , Wenfu Wang , Xiangyang Xue , Jian Pu

Point clouds provide a compact and efficient representation of 3D shapes. While deep neural networks have achieved impressive results on point cloud learning tasks, they require massive amounts of manually labeled data, which can be costly…

Computer Vision and Pattern Recognition · Computer Science 2020-10-20 Omid Poursaeed , Tianxing Jiang , Han Qiao , Nayun Xu , Vladimir G. Kim

This paper presents a semi-supervised learning framework for a customized semantic segmentation task using multiview image streams. A key challenge of the customized task lies in the limited accessibility of the labeled data due to the…

Computer Vision and Pattern Recognition · Computer Science 2018-12-06 Yuan Yao , Hyun Soo Park

Online Multi-Object Tracking (MOT) from videos is a challenging computer vision task which has been extensively studied for decades. Most of the existing MOT algorithms are based on the Tracking-by-Detection (TBD) paradigm combined with…

Computer Vision and Pattern Recognition · Computer Science 2019-04-10 Zhen He , Jian Li , Daxue Liu , Hangen He , David Barber

Poles and building edges are frequently observable objects on urban roads, conveying reliable hints for various computer vision tasks. To repetitively extract them as features and perform association between discrete LiDAR frames for…

Computer Vision and Pattern Recognition · Computer Science 2022-08-04 Xiangrui Zhao , Sheng Yang , Tianxin Huang , Jun Chen , Teng Ma , Mingyang Li , Yong Liu

Pre-trained on extensive and diverse multi-modal datasets, 2D foundation models excel at addressing 2D tasks with little or no downstream supervision, owing to their robust representations. The emergence of 2D-to-3D distillation frameworks…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Anas Mahmoud , Ali Harakeh , Steven Waslander

While modern visual recognition systems have made significant advancements, many continue to struggle with the open problem of learning from few exemplars. This paper focuses on the task of object detection in the setting where object…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Phi Vu Tran

Multimodal self-supervised learning is getting more and more attention as it allows not only to train large networks without human supervision but also to search and retrieve data across various modalities. In this context, this paper…

Detecting anomalous hazards in visual data, particularly in video streams, is a critical challenge in autonomous driving. Existing models often struggle with unpredictable, out-of-label hazards due to their reliance on predefined object…

Computer Vision and Pattern Recognition · Computer Science 2025-04-21 Shashank Shriram , Srinivasa Perisetla , Aryan Keskar , Harsha Krishnaswamy , Tonko Emil Westerhof Bossen , Andreas Møgelmose , Ross Greer

To fully understand the 3D context of a single image, a visual system must be able to segment both the visible and occluded regions of objects, while discerning their occlusion order. Ideally, the system should be able to handle any object…

Computer Vision and Pattern Recognition · Computer Science 2024-05-10 Jiayang Ao , Qiuhong Ke , Krista A. Ehinger

We unveil how generalizable AI can be used to improve multi-view 3D pedestrian detection in unlabeled target scenes. One way to increase generalization to new scenes is to automatically label target data, which can then be used for training…

Computer Vision and Pattern Recognition · Computer Science 2023-08-10 João Paulo Lima , Diego Thomas , Hideaki Uchiyama , Veronica Teichrieb

Understanding driving situations regardless the conditions of the traffic scene is a cornerstone on the path towards autonomous vehicles; however, despite common sensor setups already include complementary devices such as LiDAR or radar,…

Computer Vision and Pattern Recognition · Computer Science 2018-05-04 Jorge Beltran , Carlos Guindel , Francisco Miguel Moreno , Daniel Cruzado , Fernando Garcia , Arturo de la Escalera

Recent advancements in perception for autonomous driving are driven by deep learning. In order to achieve robust and accurate scene understanding, autonomous vehicles are usually equipped with different sensors (e.g. cameras, LiDARs,…

Low-latency intelligent systems are required for autonomous driving on non-uniform terrain in open-pit mines and developing countries. This work proposes a perception system for autonomous vehicles on unpaved roads and off-road…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Nelson Alves Ferreira Neto