ChenhongyiYang / WidthFormer
[IROS 2024 Oral Presentation] WidthFormer: Toward Efficient Transformer-based BEV View Transformation
☆124Updated 3 months ago
Related projects: ⓘ
- Source code of PivotNet (ICCV2023, PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction)☆96Updated 5 months ago
- [ECCV 2024] HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras☆42Updated last month
- [AAAI2024] Far3D: Expanding the Horizon for Surround-view 3D Object Detection☆135Updated 9 months ago
- [CVPR 2024] Learning Occupancy for Monocular 3D Object Detection☆101Updated last year
- Target Inner-Geometry Learning for BEV 3D Object Detection☆87Updated last year
- StreamPETR with 3dppe Extension☆47Updated 8 months ago
- [CVPR 2024] PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation☆132Updated last month
- Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer☆222Updated last year
- [AAAI 2023] PolarFormer: Multi-camera 3D Object Detection with Polar Transformers☆160Updated last year
- Papers on occupation, including monocular and multi-view in autonomous driving scenarios☆36Updated 4 months ago
- (CVPR2023) CAPE: Camera View Position Embedding for Multi-View 3D Object Detection☆101Updated last year
- Vision-based 3D occupancy prediction in autonomous driving: a review and outlook☆139Updated 2 months ago
- Code for paper "MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping", ECCV 2024 (Oral)☆147Updated 3 weeks ago
- Official implementation of our RAL'24 paper: Multi-Camera Unified Pre-training for Autonomous Driving☆202Updated 7 months ago
- ☆56Updated last year
- ☆77Updated this week
- [CVPR 2024] Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications☆189Updated 4 months ago
- ☆35Updated 3 weeks ago
- [ICLR2024] TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning☆158Updated 3 weeks ago
- Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection☆236Updated last year
- ☆28Updated 6 months ago
- An intuitive approach for 3D Occupancy Detection☆122Updated last year
- ☆52Updated 8 months 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…☆59Updated last year
- [NeurIPS 2023] Query-based Temporal Fusion with Explicit Motion for 3D Object Detection☆65Updated 2 months ago
- Code for "Object as Query: Lifting any 2D Object Detector to 3D Detection"☆83Updated last year
- [ICCV 2023] SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection☆187Updated last month
- An official code release of our CVPR'23 paper, BEVHeight☆193Updated last month
- This repository contains the PyTorch implementation of the CVPR'2024 paper (Highlight), IS-Fusion: Instance-Scene Collaborative Fusion fo…☆97Updated last month
- POWERBEV, a novel and elegant vision-based end-to-end framework that only consists of 2D convolutional layers to perform perception and f…☆82Updated 5 months ago