ChenhongyiYang / WidthFormerLinks
[IROS 2024 Oral Presentation] WidthFormer: Toward Efficient Transformer-based BEV View Transformation
☆147Updated 3 months ago
Alternatives and similar repositories for WidthFormer
Users that are interested in WidthFormer are comparing it to the libraries listed below
Sorting:
- [AAAI2024] Far3D: Expanding the Horizon for Surround-view 3D Object Detection☆175Updated last year
- [ECCV 2024] HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras☆56Updated 11 months ago
- ☆41Updated last year
- [CVPR 2024] Learning Occupancy for Monocular 3D Object Detection☆129Updated last year
- Code for "Object as Query: Lifting any 2D Object Detector to 3D Detection"☆101Updated last year
- StreamPETR with 3dppe Extension☆51Updated last year
- An official code release of our CVPR'23 paper, BEVHeight☆219Updated 11 months ago
- [ICLR2024] TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning☆189Updated 2 weeks ago
- [AAAI 2023] PolarFormer: Multi-camera 3D Object Detection with Polar Transformers☆172Updated 2 years ago
- Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer☆239Updated 2 years ago
- Target Inner-Geometry Learning for BEV 3D Object Detection☆89Updated 2 years ago
- DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation (ICCV 2023)☆104Updated last year
- Source code of PivotNet (ICCV2023, PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction)☆116Updated last year
- Official code for MatrixVT on BEVDepth.☆46Updated 2 years ago
- ☆53Updated 10 months ago
- (CVPR2023) CAPE: Camera View Position Embedding for Multi-View 3D Object Detection☆108Updated 2 years ago
- ☆63Updated last year
- [ECCV 2024] Ray Denoising (RayDN): Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection☆108Updated 9 months ago
- POWERBEV, a novel and elegant vision-based end-to-end framework that only consists of 2D convolutional layers to perform perception and f…☆93Updated last year
- Official implementation of our RAL'24 paper: Multi-Camera Unified Pre-training for Autonomous Driving☆228Updated last year
- Code for Paper, MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries. https://tsinghua-mars-lab.github.io/mutr3d/☆195Updated 2 years ago
- Official PyTorch implementation for paper`Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection' accepted by CVPR …☆168Updated 2 weeks ago
- This is the implementation of the paper "SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection" (I…☆77Updated last year
- Papers on occupation, including monocular and multi-view in autonomous driving scenarios☆40Updated last year
- [ECCV 2024] Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction☆143Updated 10 months ago
- ☆21Updated 8 months ago
- [ICLR 2023] BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection☆126Updated 2 years ago
- [NeurIPS 2023] Query-based Temporal Fusion with Explicit Motion for 3D Object Detection☆78Updated last year
- [ECCV 2024] The official implementation of DualBEV☆61Updated last year
- ☆32Updated last year