English
Related papers

Related papers: Geometric-aware Pretraining for Vision-centric 3D …

200 papers

Self-supervised learning has made substantial strides in image processing, while visual pre-training for autonomous driving is still in its infancy. Existing methods often focus on learning geometric scene information while neglecting…

Computer Vision and Pattern Recognition · Computer Science 2024-11-20 Shaoqing Xu , Fang Li , Shengyin Jiang , Ziying Song , Li Liu , Zhi-xin Yang

Multi-view camera-based 3D detection is a challenging problem in computer vision. Recent works leverage a pretrained LiDAR detection model to transfer knowledge to a camera-based student network. However, we argue that there is a major…

Computer Vision and Pattern Recognition · Computer Science 2023-08-29 Jihao Liu , Tai Wang , Boxiao Liu , Qihang Zhang , Yu Liu , Hongsheng Li

Vision-centric Bird's Eye View (BEV) perception holds considerable promise for autonomous driving. Recent studies have prioritized efficiency or accuracy enhancements, yet the issue of domain shift has been overlooked, leading to…

Computer Vision and Pattern Recognition · Computer Science 2025-09-18 Rongyu Zhang , Jiaming Liu , Xiaoqi Li , Xiaowei Chi , Dan Wang , Li Du , Yuan Du , Shanghang Zhang

Bird's-Eye-View (BEV) representation has emerged as a mainstream paradigm for multi-view 3D object detection, demonstrating impressive perceptual capabilities. However, existing methods overlook the geometric quality of BEV representation,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Jinqing Zhang , Yanan Zhang , Yunlong Qi , Zehua Fu , Qingjie Liu , Yunhong Wang

Birds-eye-view (BEV) semantic segmentation is critical for autonomous driving for its powerful spatial representation ability. It is challenging to estimate the BEV semantic maps from monocular images due to the spatial gap, since it is…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Shi Gong , Xiaoqing Ye , Xiao Tan , Jingdong Wang , Errui Ding , Yu Zhou , Xiang Bai

LiDAR-based 3D detection has made great progress in recent years. However, the performance of 3D detectors is considerably limited when deployed in unseen environments, owing to the severe domain gap problem. Existing domain adaptive 3D…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Ziyu Li , Jingming Guo , Tongtong Cao , Liu Bingbing , Wankou Yang

Recent vision-only perception models for autonomous driving achieved promising results by encoding multi-view image features into Bird's-Eye-View (BEV) space. A critical step and the main bottleneck of these methods is transforming image…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Jiayu Yang , Enze Xie , Miaomiao Liu , Jose M. Alvarez

3D-aware visual pretraining has proven effective in improving the performance of downstream robotic manipulation tasks. However, existing methods are constrained to Euclidean embedding spaces, whose flat geometry limits their ability to…

Robotics · Computer Science 2026-03-13 Jin Yang , Ping Wei , Yixin Chen , Nanning Zheng

3D object detection using LiDAR data is an indispensable component for autonomous driving systems. Yet, only a few LiDAR-based 3D object detection methods leverage segmentation information to further guide the detection process. In this…

Computer Vision and Pattern Recognition · Computer Science 2022-03-07 Hamidreza Fazlali , Yixuan Xu , Yuan Ren , Bingbing Liu

Recent work on visual representation learning has shown to be efficient for robotic manipulation tasks. However, most existing works pretrained the visual backbone solely on 2D images or egocentric videos, ignoring the fact that robots…

Detecting objects in 3D space using multiple cameras, known as Multi-Camera 3D Object Detection (MC3D-Det), has gained prominence with the advent of bird's-eye view (BEV) approaches. However, these methods often struggle when faced with…

Computer Vision and Pattern Recognition · Computer Science 2023-12-27 Hao Lu , Yunpeng Zhang , Qing Lian , Dalong Du , Yingcong Chen

Multi-sensor fusion is crucial for accurate 3D object detection in autonomous driving, with cameras and LiDAR being the most commonly used sensors. However, existing methods perform sensor fusion in a single view by projecting features from…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Rohit Mohan , Daniele Cattaneo , Florian Drews , Abhinav Valada

Camera-based bird-eye-view (BEV) perception paradigm has made significant progress in the autonomous driving field. Under such a paradigm, accurate BEV representation construction relies on reliable depth estimation for multi-camera images.…

Computer Vision and Pattern Recognition · Computer Science 2023-12-14 Yang Jiao , Zequn Jie , Shaoxiang Chen , Lechao Cheng , Jingjing Chen , Lin Ma , Yu-Gang Jiang

Despite significant progress in Vision-Language Navigation (VLN), existing approaches still rely on dense RGB videos that produce excessive patch tokens and lack explicit spatial structure, resulting in substantial computational overhead…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Jiahao Yang , Zihan Wang , Xiangyang Li , Xing Zhu , Yujun Shen , Yinghao Xu , Shuqiang Jiang

Vision-centric bird-eye-view (BEV) perception has shown promising potential in autonomous driving. Recent works mainly focus on improving efficiency or accuracy but neglect the challenges when facing environment changing, resulting in…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Jiaming Liu , Rongyu Zhang , Xiaoqi Li , Xiaowei Chi , Zehui Chen , Ming Lu , Yandong Guo , Shanghang Zhang

This paper proposes 3DGeoDet, a novel geometry-aware 3D object detection approach that effectively handles single- and multi-view RGB images in indoor and outdoor environments, showcasing its general-purpose applicability. The key challenge…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Yi Zhang , Yi Wang , Yawen Cui , Lap-Pui Chau

This paper introduces VisionPAD, a novel self-supervised pre-training paradigm designed for vision-centric algorithms in autonomous driving. In contrast to previous approaches that employ neural rendering with explicit depth supervision,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Haiming Zhang , Wending Zhou , Yiyao Zhu , Xu Yan , Jiantao Gao , Dongfeng Bai , Yingjie Cai , Bingbing Liu , Shuguang Cui , Zhen Li

Most invariance-based self-supervised methods rely on single object-centric images (e.g., ImageNet images) for pretraining, learning features that invariant to geometric transformation. However, when images are not object-centric, the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-18 Taeho Kim , Jong-Min Lee

Existing LiDAR-based 3D object detection methods for autonomous driving scenarios mainly adopt the training-from-scratch paradigm. Unfortunately, this paradigm heavily relies on large-scale labeled data, whose collection can be expensive…

Computer Vision and Pattern Recognition · Computer Science 2024-01-23 Zhiwei Lin , Yongtao Wang , Shengxiang Qi , Nan Dong , Ming-Hsuan Yang

Accurate surround-view depth estimation provides a competitive alternative to laser-based sensors and is essential for 3D scene understanding in autonomous driving. While empirical studies have proposed various approaches that primarily…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Weimin Liu , Wenjun Wang , Joshua H. Meng
‹ Prev 1 2 3 10 Next ›