EdwardLeeLPZ / PowerBEV
POWERBEV, a novel and elegant vision-based end-to-end framework that only consists of 2D convolutional layers to perform perception and forecasting of multiple objects in BEVs.
☆86Updated 10 months ago
Alternatives and similar repositories for PowerBEV:
Users that are interested in PowerBEV are comparing it to the libraries listed below
- [CVPR 2024] Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications☆220Updated 9 months ago
- Source code of PivotNet (ICCV2023, PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction)☆109Updated 10 months ago
- [ECCV 2024] The official implementation of DualBEV☆49Updated 7 months ago
- [NeurIPS 2024] An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes☆95Updated 2 months ago
- ☆77Updated 2 months ago
- (ECCV2024)ADMap: Anti-disturbance framework for reconstructing online vectorized HD map☆73Updated 7 months ago
- Official implementation of PointBeV: A Sparse Approach to BeV Predictions☆108Updated 11 months ago
- [ICLR 2025] The official implementation of SSR☆75Updated last week
- [ECCV 2024] Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction☆137Updated 5 months ago
- Offical implementation of ICCV2023 paper 3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking.☆72Updated 10 months ago
- Official implementation for 'SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction' (CVPR 202…