Skip to content

Latest commit

 

History

History
88 lines (77 loc) · 9.69 KB

Multi-Cameras-Perception.md

File metadata and controls

88 lines (77 loc) · 9.69 KB
Raw

SOTA Techniques of Perception with Multiples Cameras

This repository provides an up-to-date list of techniques used for autolabeling project.

=============================

Table of contents

  1. DataSets and Benchmarks
    1.1 3D ObjectS Detection
    1.2 Lane Segmentation 1.3 Auxiliary Tasks
  2. 3D Obstacles Detection
    2.1 Bird's-Eye-View Based
    2.2 Multi-Modals Fusion
  3. Road Markers Detection
    3.1 Lanes Segmentation
    3.2 Lights and other Signs Detection
  4. Multi-objects Tracking
    4.1 Multi-objects Tracking

1. DataSets and Benchmarks

1.1 3D ObjectS Detection

1.2 Lane Segmentation

1.3 Auxiliary Tasks

  • Is Pseudo-Lidar needed for Monocular 3D Object detection? ; [Paper] [Project]
  • Categorical Depth Distribution Network for Monocular 3D Object Detection;[Paper] [Project]

2 3D Obstacles Detection

2.1 Bird's-Eye-View Based

  • 2022 BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection; [Paper]
  • 2022 VectorMapNet: End-to-end Vectorized HD Map Learning; [Paper]
  • 2022 Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer; [Paper] [Project]
  • 2022 BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving; [Paper] [Project]
  • 2022 CVPR Cross-view Transformers for real-time Map-view Semantic Segmentation; [Paper] [Project]
  • 2021 BEVDet: High-Performance Multi-Camera 3D Object Detection in Bird-Eye-View; [Paper] [Project]
  • 2022 BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection; [Paper] [Project]
  • 2022 BEVFormer: Learning Bird’s-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers; [Paper] [Project]
  • 2022 PETR: Position Embedding Transformation for Multi-View 3D Object Detection; [Paper] [Project]
  • 2022 PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images; [Paper] [Project]
  • 2022 M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Bird’s-Eye View Representation; [Paper] [Project]
  • 2020 ECCV Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D [Paper] [Project]
  • HFT: Lifting Perspective Representations via Hybrid Feature Transformation; [Paper] [Project]
  • 2021 FIERY: Future Instance Prediction in Bird’s-Eye View from Surround Monocular Cameras; [Paper] [Project]
  • 2022 PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark; [Paper] [Project] [Datasets]
  • 2022 BEVSegFormer: Bird’s Eye View Semantic Segmentation From Arbitrary Camera Rigs; [Paper]
  • HDMapNet: An Online HD Map Construction and Evaluation Framework; [Paper] [Project]
  • End-to-end Birds-eye-view Flow Estimation for Autonomous Driving; [Paper]
  • Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Images; [Project] [Code]
  • BEV-MODNet: Monocular Camera based Bird’s Eye View Moving Object Detection for Autonomous Driving; [Paper] [Project]
  • 2022 StretchBEV: Stretching Future Instance Prediction Spatially and Temporally; [Paper] [Project]
  • 2022 GitNet: Geometric Prior-based Transformation for Birds-Eye-View Segmentation ; [Paper]
  • Translating Images into Maps; [Paper]
  • Structured Bird’s-Eye-View Traffic Scene Understanding from Onboard Images; [Paper] [Project]
  • MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection; [Paper]
  • CVPR 2021 Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation; [Paper]
  • ICCV 2021 NEAT: Neural Attention Fields for End-to-End Autonomous Driving; [Paper] [Project]

2.2 Multi-Modals Fusion

  • 2022 MVFuseNet: Improving End-to-End Object Detection and Motion Forecasting through Multi-View Fusion of LiDAR Data; [Paper]
  • Exploiting Temporal Relations on Radar Perception for Autonomous Driving; [Paper]
  • 2022 BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird’s-Eye View Representation; [Paper] [Project]
  • 2022 BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework; [Paper] [Project]
  • 2022 Unifying Voxel-based Representation with Transformer for 3D Object Detection; [Paper] [Project]

3 Road Markers Detection

3.1 Lanes Segmentation

3.2 Lights and other Signs Detection

4 Multi-objects Tracking

4.1 Multi-objects Tracking

  • 2022 Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking with Transformer; [Paper] [Project]
  • 2022 Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving; [Paper]
  • 2022 3D Object Tracking with Transformer; [Paper] [Project]
  • 2022 TrackFormer: Multi-Object Tracking with Transformers; [Paper] [Project]
  • 2022 MOTR: End-to-End Multiple-Object Tracking with Transformer; [Paper] [Project]
  • 2022 TransTrack: Multiple Object Tracking with Transformer; [Paper] [Project]