mlsanityData to 7 Oct 2026

DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection

arXiv 2312.15742 ↗First posted 25 Dec 2023cs.CV cs.AIcited by 34

Not on the map. Why?

Abstract (arXiv)

Vehicle-to-Everything (V2X) collaborative perception has recently gained significant attention due to its capability to enhance scene understanding by integrating information from various agents, e.g., vehicles, and infrastructure. However, current works often treat the information from each agent equally, ignoring the inherent domain gap caused by the utilization of different LiDAR sensors of each agent, thus leading to suboptimal performance. In this paper, we propose DI-V2X, that aims to learn Domain-Invariant representations through a new distillation framework to mitigate the domain discrepancy in the context of V2X 3D object detection. DI-V2X comprises three essential components: a domain-mixing instance augmentation (DMA) module, a progressive domain-invariant distillation (PDD) module, and a domain-adaptive fusion (DAF) module. Specifically, DMA builds a domain-mixing 3D instance bank for the teacher and student models during training, resulting in aligned data representation. Next, PDD encourages the student models from different domains to gradually learn a domain-invariant feature representation towards the teacher, where the overlapping regions between agents are employed as guidance to facilitate the distillation process. Furthermore, DAF closes the domain gap between the students by incorporating calibration-aware domain-adaptive attention. Extensive experiments on the challenging DAIR-V2X and V2XSet benchmark datasets demonstrate DI-V2X achieves remarkable performance, outperforming all the previous V2X models. Code is available at https://github.com/Serenos/DI-V2X

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 19 of its 22 references that are in the map. First posted on arXiv 25 Dec 2023.

Builds on

19 of 22 references.

References · 19

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  2. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  3. 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
  4. 2020V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Predictioncited by 292
  5. 2022Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Mapscited by 255
  6. 2021Learning Distilled Collaboration Graph for Multi-Agent Perceptioncited by 194
  7. 2019F-Cooper: Feature based Cooperative Perception for Autonomous Vehicle Edge Computing System Using 3D Point Cloudscited by 171
  8. 2019Cooper: Cooperative Perception for Connected Autonomous Vehicles based on 3D Point Cloudscited by 165
  9. 2020When2com: Multi-Agent Perception via Communication Graph Groupingcited by 157
  10. 2022Robust Collaborative 3D Object Detection in Presence of Pose Errorscited by 129
  11. 2020Who2com: Collaborative Perception via Learnable Handshake Communicationcited by 127
  12. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
7 more
  1. 2023V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecastingcited by 114
  2. 2020PointMixup: Augmentation for Point Cloudscited by 104
  3. 2022Bridging the Domain Gap for Multi-Agent Perceptioncited by 60
  4. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  5. 2022Model-Agnostic Multi-Agent Perception Frameworkcited by 51
  6. 2021A Survey on Deep Domain Adaptation for LiDAR Perceptioncited by 46
  7. 2023Instant Domain Augmentation for LiDAR Semantic Segmentationcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 17; 2026: 10.

34 papers.

Sort:

By area:

  1. 2024IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detectioncited by 57
  2. 2025SparseAlign: A Fully Sparse Framework for Cooperative Object Detectioncited by 15
  3. 2025Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directionscited by 14
  4. 2024A Survey on Intermediate Fusion Methods for Collaborative Perception Categorized by Real World Challengescited by 13
  5. 2024FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Drivingcited by 9
  6. 2025Research Challenges and Progress in the End-to-End V2X Cooperative Autonomous Driving Competitioncited by 9
  7. 2025Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Camerascited by 8
  8. 2025Collaborative Perception Datasets for Autonomous Driving: A Reviewcited by 8
  9. 2024UVCPNet: A UAV-Vehicle Collaborative Perception Network for 3D Object Detectioncited by 7
  10. 2024RCDN: Towards Robust Camera-Insensitivity Collaborative Perception via Dynamic Feature-based 3D Neural Modelingcited by 6
  11. 2024RepVF: A Unified Vector Fields Representation for Multi-task 3D Perceptioncited by 5
  12. 2025V2X-DG: Domain Generalization for Vehicle-to-Everything Cooperative Perceptioncited by 5
22 more
  1. 2025Systematic Literature Review on Vehicular Collaborative Perception -- A Computer Vision Perspectivecited by 5
  2. 2025INSTINCT: Instance-Level Interaction Architecture for Query-Based Collaborative Perceptioncited by 5
  3. 2024Redundant Queries in DETR-Based 3D Detection Methods: Unnecessary and Prunablecited by 4
  4. 2025V2X-DGPE: Addressing Domain Gaps and Pose Errors for Robust Collaborative 3D Object Detectioncited by 3
  5. 2025Unleashing the Temporal Potential of Stereo Event Cameras for Continuous-Time 3D Object Detectioncited by 3
  6. 2025The Components of Collaborative Joint Perception and Prediction -- A Conceptual Frameworkcited by 2
  7. 2025FocalComm: Hard Instance-Aware Multi-Agent Perceptioncited by 2
  8. 2026Faster-HEAL: An Efficient and Privacy-Preserving Collaborative Perception Framework for Heterogeneous Autonomous Vehiclescited by 2
  9. 2025CoDS: Enhancing Collaborative Perception in Heterogeneous Scenarios via Domain Separationcited by 1
  10. 2026C2E: Boosting Ego-Only 3D Object Detection via Multi-Teacher Contrastive Knowledge Distillationcited by 1
  11. 2025Dual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object Detectioncited by 0
  12. 2025DATA: Domain-And-Time Alignment for High-Quality Feature Fusion in Collaborative Perceptioncited by 0
  13. 2025PointSlice: Accurate and Efficient Slice-Based Representation for 3D Object Detection from Point Cloudscited by 0
  14. 2025LaGen: Towards Autoregressive LiDAR Scene Generationcited by 0
  15. 2026Move What Matters: Parameter-Efficient Domain Adaptation via Optimal Transport Flow for Collaborative Perceptioncited by 0
  16. 2026CATNet: Collaborative Alignment and Transformation Network for Cooperative Perceptioncited by 0
  17. 2026Rethinking Air-Ground Collaboration: A Progressive Cross-Task Benchmark and Socialized Learning Frameworkcited by 0
  18. 2026ViCo3D: Empowering LiDAR-based Collaborative 3D Object Detection with Vision Foundation Modelscited by 0
  19. 2026CoGoal3D: Collaborative 3D Object Detection with 3D-Aware Fusion and Refinementcited by 0
  20. 2026Towards Collaborative Joint Perception and Prediction: Framework, Baseline Evaluation, and Deployment Perspectivescited by 0
  21. 2026VIPS: Vehicle-Infrastructure Cooperative Planning Benchmark via Pseudo-Simulationcited by 0
  22. 2026PEARL: A Lightweight Prompt-based Feature Interpreter Framework for Real-Time, Anonymous, and Heterogeneous Collaborative Perceptioncited by 0