Related papers: CycleBEV: Regularizing View Transformation Network…

Semantic segmentation stands as a pivotal research focus in computer vision. In the context of industrial image inspection, conventional semantic segmentation models fail to maintain the segmentation consistency of fixed components across…

Learning the dense bird's eye view (BEV) motion flow in a self-supervised manner is an emerging research for robotics and autonomous driving. Current self-supervised methods mainly rely on point correspondences between point clouds, which…

Recent deep learning models achieve impressive results on 3D scene analysis tasks by operating directly on unstructured point clouds. A lot of progress was made in the field of object classification and semantic segmentation. However, the…

3D visual perception tasks, including 3D detection and map segmentation based on multi-camera images, are essential for autonomous driving systems. In this work, we present a new framework termed BEVFormer, which learns unified BEV…

Infrastructure-based perception plays a crucial role in intelligent transportation systems, offering global situational awareness and enabling cooperative autonomy. However, existing camera-based detection models often underperform in such…

Depth estimation, visual odometry (VO), and bird's-eye-view (BEV) scene layout estimation present three critical tasks for driving scene perception, which is fundamental for motion planning and navigation in autonomous driving. Though they…

Bird's eye view (BEV)-based 3D perception plays a crucial role in autonomous driving applications. The rise of large language models has spurred interest in BEV-based captioning to understand object behavior in the surrounding environment.…

BEV-based 3D perception has emerged as a focal point of research in end-to-end autonomous driving. However, existing BEV approaches encounter significant challenges due to the large feature space, complicating efficient modeling and…

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…

Recent advancements in Bird's Eye View (BEV) fusion for map construction have demonstrated remarkable mapping of urban environments. However, their deep and bulky architecture incurs substantial amounts of backpropagation memory and…

Accurate object detection and prediction are critical to ensure the safety and efficiency of self-driving architectures. Predicting object trajectories and occupancy enables autonomous vehicles to anticipate movements and make decisions…

Generating annotations for bird's-eye-view (BEV) segmentation presents significant challenges due to the scenes' complexity and the high manual annotation cost. In this work, we address these challenges by leveraging the abundance of…

A fundamental bottleneck in Novel View Synthesis (NVS) for autonomous driving is the inherent supervision gap on novel trajectories: models are tasked with synthesizing unseen views during inference, yet lack ground truth images for these…

While bird's-eye-view (BEV) perception models can be useful for building high-definition maps (HD-Maps) with less human labor, their results are often unreliable and demonstrate noticeable inconsistencies in the predicted HD-Maps from…

Currently, detecting 3D objects in Bird's-Eye-View (BEV) is superior to other 3D detectors for autonomous driving and robotics. However, transforming image features into BEV necessitates special operators to conduct feature sampling. These…

Monocular visual-inertial odometry (VIO) is a critical problem in robotics and autonomous driving. Traditional methods solve this problem based on filtering or optimization. While being fully interpretable, they rely on manual interference…

Variational auto-encoders (VAEs) are a powerful approach to unsupervised learning. They enable scalable approximate posterior inference in latent-variable models using variational inference (VI). A VAE posits a variational family…

3D object detection based on LiDAR point clouds is a crucial module in autonomous driving particularly for long range sensing. Most of the research is focused on achieving higher accuracy and these models are not optimized for deployment on…

Vision Transformer (ViT) has shown its advantages over the convolutional neural network (CNN) with its ability to capture global long-range dependencies for visual representation learning. Besides ViT, contrastive learning is another…

Trajectory prediction is, naturally, a key task for vehicle autonomy. While the number of traffic rules is limited, the combinations and uncertainties associated with each agent's behaviour in real-world scenarios are nearly impossible to…