Improving Bird's Eye View Semantic Segmentation by Task Decomposition
Semantic segmentation in bird's eye view (BEV) plays a crucial role in autonomous driving.
Previous methods usually follow an end-to-end pipeline directly predicting the BEV …
Previous methods usually follow an end-to-end pipeline directly predicting the BEV …
BEVSOC: Self-supervised contrastive learning for calibration-free bev 3d object detection
3-D object detection based on multiview cameras and bird's-eye view (BEV) representation
is a key task for autonomous driving, as it enables the perception systems to understand the …
is a key task for autonomous driving, as it enables the perception systems to understand the …
OctOcc: High-Resolution 3D Occupancy Prediction with Octree
W Ouyang, X Song, B Feng, Z Xu - … of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
3D semantic occupancy has garnered considerable attention due to its abundant structural
information encompassing the entire scene in autonomous driving. However, existing 3D …
information encompassing the entire scene in autonomous driving. However, existing 3D …
Bird's-Eye View Semantic Segmentation for Autonomous Driving through the Large Kernel Attention Encoder and Bilinear-Attention Transform Module
K Li, X Wu, W Zhang, W Yu - World Electric Vehicle Journal, 2023 - mdpi.com
Building an autonomous driving system requires a detailed and unified semantic
representation from multiple cameras. The bird's eye view (BEV) has demonstrated …
representation from multiple cameras. The bird's eye view (BEV) has demonstrated …