/CollaborativePerception_paper

A paper list about collaborative perception.

Awesome-Collaborative-Perception-Papers

collaborative perception, v2x-communication aided autonomous driving

Dataset

  1. [ISPRS 2021] Comap: a Synthetic Dataset for Collective Multi-Agent Perception of Autonomous Driving.[paper] [data]
  2. [RAL 2022] V2X-Sim: A Virtual Collaborative Perception Dataset for Autonomous Driving. [paper] [code]
  3. [ICRA 2022] OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication. [paper] [code]
  4. [CVPR 2022] DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection. [website] [code]

Collaboration framework

  1. [ICRA 2020] Who2com: Collaborative Perception via Learnable Handshake Communication. [paper] [code]
  2. [CVPR 2020] When2com: Multi-Agent Perception via Communication Graph Grouping.[paper] [code]
  3. [ECCV 2020] V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction. [paper]
  4. [MobiCom 2021] EMP: Edge-assisted Multi-vehicle Perception. [paper] [code]
  5. [NeurIPS 2021] Learning distilled collaboration graph for multi-agent perception. [paper] [code]
  6. [CVPR 2022] COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehicles. [paper] [code]
  7. [ECCV 2022] V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer.[paper] [code]
  8. [arxiv] Model-Agnostic Multi-Agent Perception Framework. [paper]
  9. [arxiv] CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers. [paper]

Robustness to localization error

  1. [CoRL 2020] Learning to Communicate and Correct Pose Errors. [paper]
  2. [IROS 2021] Overcoming Obstructions via Bandwidth-Limited Multi-Agent Spatial Handshaking.[paper]
  3. [RAL 2022] Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous Driving. [paper] [code]
  4. [ECCV 2022] V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer. [paper] [code]