mlsanityData to 14 Oct 2026

SparseAlign: A Fully Sparse Framework for Cooperative Object Detection

arXiv 2503.12982 ↗First posted 17 Mar 2025cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Cooperative perception can increase the view field and decrease the occlusion of an ego vehicle, hence improving the perception performance and safety of autonomous driving. Despite the success of previous works on cooperative object detection, they mostly operate on dense Bird's Eye View (BEV) feature maps, which are computationally demanding and can hardly be extended to long-range detection problems. More efficient fully sparse frameworks are rarely explored. In this work, we design a fully sparse framework, SparseAlign, with three key features: an enhanced sparse 3D backbone, a query-based temporal context learning module, and a robust detection head specially tailored for sparse features. Extensive experimental results on both OPV2V and DairV2X datasets show that our framework, despite its sparsity, outperforms the state of the art with less communication bandwidth requirements. In addition, experiments on the OPV2Vt and DairV2Xt datasets for time-aligned cooperative object detection also show a significant performance gain compared to the baseline works.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 37 of its 45 references that are in the map. First posted on arXiv 17 Mar 2025.

Builds on

37 of 45 references.

References · 37

  1. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  2. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  3. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  4. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  5. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  6. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  7. 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
  8. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 315
  9. 2021OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communicationcited by 304
  10. 2020V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Predictioncited by 292
  11. 2022DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detectioncited by 273
  12. 2022Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Mapscited by 255
25 more
  1. 2022CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformerscited by 227
  2. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 222
  3. 2019F-Cooper: Feature based Cooperative Perception for Autonomous Vehicle Edge Computing System Using 3D Point Cloudscited by 171
  4. 2019Cooper: Cooperative Perception for Connected Autonomous Vehicles based on 3D Point Cloudscited by 165
  5. 2023V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perceptioncited by 155
  6. 2022Robust Collaborative 3D Object Detection in Presence of Pose Errorscited by 129
  7. 2023V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecastingcited by 114
  8. 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
  9. 2022COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehiclescited by 95
  10. 2022Latency-Aware Collaborative Perceptioncited by 86
  11. 2022Fully Sparse 3D Object Detectioncited by 84
  12. 2020SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognitioncited by 66
  13. 2022Learning for Vehicle-to-Vehicle Cooperative Perception under Lossy Communicationcited by 47
  14. 2021Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous Drivingcited by 45
  15. 2024RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perceptioncited by 38
  16. 2023DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detectioncited by 34
  17. 2024Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehiclescited by 33
  18. 2023Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detectioncited by 31
  19. 2023QUEST: Query Stream for Practical Cooperative Perceptioncited by 23
  20. 2022CASSPR: Cross Attention Single Scan Place Recognitioncited by 22
  21. 2024HoloVIC: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperativecited by 14
  22. 2023Generating Evidential BEV Maps in Continuous Driving Spacecited by 10
  23. 2022Leveraging Dynamic Objects for Relative Localization Correction in a Connected Autonomous Vehicle Networkcited by 8
  24. 2023V2X-AHD:Vehicle-to-Everything Cooperation Perception via Asymmetric Heterogenous Distillation Networkcited by 2
  25. 2024StreamLTS: Query-based Temporal-Spatial LiDAR Fusion for Cooperative Object Detectioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 11.

15 papers.

Sort:

By area:

  1. 2025SparseCoop: Cooperative Perception with Kinematic-Grounded Queriescited by 4
  2. 2025SafeCoop: Unravelling Full Stack Safety in Agentic Collaborative Drivingcited by 2
  3. 2025FocalComm: Hard Instance-Aware Multi-Agent Perceptioncited by 2
  4. 2025Background Fades, Foreground Leads: Curriculum-Guided Background Pruning for Efficient Foreground-Centric Collaborative Perceptioncited by 1
  5. 2026Long-SCOPE: Fully Sparse Long-Range Cooperative 3D Perceptioncited by 1
  6. 2026BOLT: Online Lightweight Adaptation for Preparation-Free Heterogeneous Cooperative Perceptioncited by 1
  7. 2026Node Learning: A Framework for Adaptive, Decentralised and Collaborative Network Edge AIcited by 0
  8. 2026CoLC: Communication-Efficient Collaborative Perception with LiDAR Completioncited by 0
  9. 2026When the City Teaches the Car: Label-Free 3D Perception from Infrastructurecited by 0
  10. 2026UECP: Uncertainty-Enhanced Collaborative Perceptioncited by 0
  11. 2026SimBEV2X: A Large-Scale Dataset and Data Generation Tool for Multi-Task Vehicle-to-Everything Cooperative Perceptioncited by 0
  12. 2026CoAnchor: Robust Collaborative Perception under Spatio-Temporal Misalignment via Object-Level Anchorscited by 0
3 more
  1. 2026VIPS: Vehicle-Infrastructure Cooperative Planning Benchmark via Pseudo-Simulationcited by 0
  2. 2026CoVLM-Bench: A Real-World Benchmark for Cooperative Driving Question Answering and Planningcited by 0
  3. 2026Embodied Semantic Communication for Collective Autonomous Agents: A Tutorial on Representation, Wireless Delivery, and Closed-Loop Coordinationcited by 0