hustvl / GKT
Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer
☆235Updated 2 years ago
Alternatives and similar repositories for GKT:
Users that are interested in GKT are comparing it to the libraries listed below
- [ICLR2024] TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning☆180Updated 7 months ago
- [ECCV 2024] Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction☆138Updated 6 months ago
- ☆218Updated last year
- Code for Paper, MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries. https://tsinghua-mars-lab.github.io/mutr3d/☆189Updated 2 years ago
- Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection☆251Updated 2 years ago
- Source code of PivotNet (ICCV2023, PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction)☆110Updated last year
- [AAAI 2023] PolarFormer: Multi-camera 3D Object Detection with Polar Transformers☆168Updated 2 years ago
- An official code release of our CVPR'23 paper, BEVHeight☆215Updated 7 months ago
- Official code for "Structured Bird’s-Eye-View Traffic Scene Understanding from Onboard Images" (ICCV 2021)☆204Updated 2 years ago
- Official PyTorch implementation for paper`Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection' accepted by CVPR …☆160Updated 10 months ago
- Official code for BEVStereo☆266Updated 2 years ago
- The official repository for BEVerse☆406Updated 2 years ago
- EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object Detection☆269Updated last year
- A general map auto annotation framework based on MapTR, with high flexibility in terms of spatial scale and element type☆232Updated last year
- Code for paper "MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping", ECCV 2024 (Oral)☆199Updated 7 months ago
- [AAAI2024] Far3D: Expanding the Horizon for Surround-view 3D Object Detection☆165Updated last year
- [IROS 2024 Oral Presentation] WidthFormer: Toward Efficient Transformer-based BEV View Transformation☆140Updated 9 months ago
- 3D occupancy☆378Updated 2 years ago
- Implemented BEVFormer support for BEV segmentation☆114Updated last year
- ☆107Updated 2 years ago
- ☆195Updated last year
- ☆227Updated last year
- Official implementation of our RAL'24 paper: Multi-Camera Unified Pre-training for Autonomous Driving☆221Updated last year
- [ICLR 2024] Map Learning with Lane Segment for Autonomous Driving☆297Updated 8 months ago
- Awesome papers about Multi-Camera Semantic Occupancy Prediction, such as TPVFormer, OccFormer, Occ3D, OpenOccupancy☆231Updated last year
- An intuitive approach for 3D Occupancy Detection☆129Updated last year
- [ICCV2023] Official Implementation of "UniTR: A Unified and Efficient Multi-Modal Transformer for Bird’s-Eye-View Representation"☆308Updated 6 months ago
- Online HD Map Construction CVPR2023☆252Updated last year
- [CVPR'21] Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation☆148Updated 3 years ago
- ☆92Updated last year