基于BEV特征表达的自动驾驶视觉感知
关注
分享
扫一扫
文章平均质量分 90
主要关注前视图图像到BEV的特征转换方法
byzy
不定期分享最新论文或基础知识，欢迎关注。
展开
-
【论文笔记】Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting
【论文笔记】Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting原创 2025-05-05 21:23:05 · 1162 阅读 · 0 评论 -
【论文笔记】GaussianBeV: 3D Gaussian Representation meets Perception Models for BeV Segmentation
【论文笔记】GaussianBeV: 3D Gaussian Representation meets Perception Models for BeV Segmentation原创 2025-03-07 16:36:57 · 1118 阅读 · 0 评论 -
【论文笔记】DualBEV: CNN is All You Need in View Transformation
DualBEV: CNN is All You Need in View Transformation原创 2024-05-11 15:38:34 · 1099 阅读 · 0 评论 -
【论文笔记】EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object Detection
【论文笔记】EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object Detection原创 2024-05-11 15:37:50 · 1915 阅读 · 1 评论 -
【论文笔记】HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras
【论文笔记】HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras原创 2024-05-11 15:36:32 · 819 阅读 · 0 评论 -
BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection 论文笔记
BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection 论文笔记原创 2022-08-10 20:18:12 · 1341 阅读 · 0 评论 -
Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer（GKT）论文
Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer 论文笔记原创 2022-08-09 23:25:06 · 1472 阅读 · 0 评论 -
M²BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Bird’s-Eye View Representation
M²BEV: Multi-Camera Joint 3D Detection andSegmentation with Unified Bird’s-Eye ViewRepresentation 论文笔记原创 2022-08-09 14:41:58 · 1204 阅读 · 0 评论 -
BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection 论文笔记
BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection 论文笔记原创 2022-08-08 17:12:41 · 3350 阅读 · 2 评论 -
Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformati
Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation 论文笔记原创 2022-08-07 21:42:37 · 996 阅读 · 0 评论 -
BEVFormer: Learning Bird’s-Eye-View Representation from Multi-Camera Images via Spatiotemporal Trans
BEVFormer: Learning Bird’s-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers论文笔记原创 2022-07-03 14:09:35 · 1858 阅读 · 0 评论 -
PolarFormer: Multi-camera 3D Object Detection with Polar Transformers 论文笔记
PolarFormer: Multi-camera 3D Object Detection with Polar Transformers 论文笔记原创 2022-08-03 11:08:00 · 1014 阅读 · 0 评论 -
BEVDet:High-Performance Multi-Camera 3D Object Detection in Bird-Eye-View 论文笔记
BEVDet:High-Performance Multi-Camera 3D Object Detection in Bird-Eye-View 论文笔记原创 2022-08-04 17:15:21 · 2265 阅读 · 1 评论 -
Translating Images into Maps 论文笔记
Translating Images into Maps 论文笔记原创 2022-08-05 14:50:04 · 1755 阅读 · 12 评论 -
Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D（LSS）
Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D 论文笔记原创 2022-08-03 21:49:31 · 3470 阅读 · 0 评论 -
PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark 论文笔记
PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark 论文笔记原创 2022-08-07 12:15:15 · 2163 阅读 · 7 评论