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

arXiv: https://arxiv.org/abs/2312.15742 · HTML: https://mlsanity.com/paper/2312.15742/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 22 references that are in the map.
- First posted on arXiv 25 Dec 2023.

## Builds on (most cited first, 19 of 19)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer](https://mlsanity.com/paper/2203.10638/) (2022)
- [V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction](https://mlsanity.com/paper/2008.07519/) (2020)
- [Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps](https://mlsanity.com/paper/2209.12836/) (2022)
- [Learning Distilled Collaboration Graph for Multi-Agent Perception](https://mlsanity.com/paper/2111.00643/) (2021)
- [F-Cooper: Feature based Cooperative Perception for Autonomous Vehicle Edge Computing System Using 3D Point Clouds](https://mlsanity.com/paper/1909.06459/) (2019)
- [Cooper: Cooperative Perception for Connected Autonomous Vehicles based on 3D Point Clouds](https://mlsanity.com/paper/1905.05265/) (2019)
- [When2com: Multi-Agent Perception via Communication Graph Grouping](https://mlsanity.com/paper/2006.00176/) (2020)
- [Robust Collaborative 3D Object Detection in Presence of Pose Errors](https://mlsanity.com/paper/2211.07214/) (2022)
- [Who2com: Collaborative Perception via Learnable Handshake Communication](https://mlsanity.com/paper/2003.09575/) (2020)
- [Mix3D: Out-of-Context Data Augmentation for 3D Scenes](https://mlsanity.com/paper/2110.02210/) (2021)
- [V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting](https://mlsanity.com/paper/2305.05938/) (2023)
- [PointMixup: Augmentation for Point Clouds](https://mlsanity.com/paper/2008.06374/) (2020)
- [Bridging the Domain Gap for Multi-Agent Perception](https://mlsanity.com/paper/2210.08451/) (2022)
- [Regularization Strategy for Point Cloud via Rigidly Mixed Sample](https://mlsanity.com/paper/2102.01929/) (2021)
- [Model-Agnostic Multi-Agent Perception Framework](https://mlsanity.com/paper/2203.13168/) (2022)
- [A Survey on Deep Domain Adaptation for LiDAR Perception](https://mlsanity.com/paper/2106.02377/) (2021)
- [Instant Domain Augmentation for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2303.14378/) (2023)

## Built on by (most cited first, 30 of 34)

- [IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection](https://mlsanity.com/paper/2403.15241/) (2024)
- [SparseAlign: A Fully Sparse Framework for Cooperative Object Detection](https://mlsanity.com/paper/2503.12982/) (2025)
- [Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions](https://mlsanity.com/paper/2503.03262/) (2025)
- [A Survey on Intermediate Fusion Methods for Collaborative Perception Categorized by Real World Challenges](https://mlsanity.com/paper/2404.16139/) (2024)
- [FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Driving](https://mlsanity.com/paper/2408.06832/) (2024)
- [Research Challenges and Progress in the End-to-End V2X Cooperative Autonomous Driving Competition](https://mlsanity.com/paper/2507.21610/) (2025)
- [Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Cameras](https://mlsanity.com/paper/2502.19630/) (2025)
- [Collaborative Perception Datasets for Autonomous Driving: A Review](https://mlsanity.com/paper/2504.12696/) (2025)
- [UVCPNet: A UAV-Vehicle Collaborative Perception Network for 3D Object Detection](https://mlsanity.com/paper/2406.04647/) (2024)
- [RCDN: Towards Robust Camera-Insensitivity Collaborative Perception via Dynamic Feature-based 3D Neural Modeling](https://mlsanity.com/paper/2405.16868/) (2024)
- [RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception](https://mlsanity.com/paper/2407.10876/) (2024)
- [V2X-DG: Domain Generalization for Vehicle-to-Everything Cooperative Perception](https://mlsanity.com/paper/2503.15435/) (2025)
- [Systematic Literature Review on Vehicular Collaborative Perception -- A Computer Vision Perspective](https://mlsanity.com/paper/2504.04631/) (2025)
- [INSTINCT: Instance-Level Interaction Architecture for Query-Based Collaborative Perception](https://mlsanity.com/paper/2509.23700/) (2025)
- [Redundant Queries in DETR-Based 3D Detection Methods: Unnecessary and Prunable](https://mlsanity.com/paper/2412.02054/) (2024)
- [Unleashing the Temporal Potential of Stereo Event Cameras for Continuous-Time 3D Object Detection](https://mlsanity.com/paper/2508.02288/) (2025)
- [V2X-DGPE: Addressing Domain Gaps and Pose Errors for Robust Collaborative 3D Object Detection](https://mlsanity.com/paper/2501.02363/) (2025)
- [The Components of Collaborative Joint Perception and Prediction -- A Conceptual Framework](https://mlsanity.com/paper/2501.15860/) (2025)
- [LaGen: Towards Autoregressive LiDAR Scene Generation](https://mlsanity.com/paper/2511.21256/) (2025)
- [FocalComm: Hard Instance-Aware Multi-Agent Perception](https://mlsanity.com/paper/2512.13982/) (2025)
- [Faster-HEAL: An Efficient and Privacy-Preserving Collaborative Perception Framework for Heterogeneous Autonomous Vehicles](https://mlsanity.com/paper/2603.07314/) (2026)
- [CoDS: Enhancing Collaborative Perception in Heterogeneous Scenarios via Domain Separation](https://mlsanity.com/paper/2510.13432/) (2025)
- [C2E: Boosting Ego-Only 3D Object Detection via Multi-Teacher Contrastive Knowledge Distillation](https://mlsanity.com/paper/2607.01827/) (2026)
- [Dual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object Detection](https://mlsanity.com/paper/2503.08992/) (2025)
- [DATA: Domain-And-Time Alignment for High-Quality Feature Fusion in Collaborative Perception](https://mlsanity.com/paper/2507.18237/) (2025)
- [PointSlice: Accurate and Efficient Slice-Based Representation for 3D Object Detection from Point Clouds](https://mlsanity.com/paper/2509.01487/) (2025)
- [Move What Matters: Parameter-Efficient Domain Adaptation via Optimal Transport Flow for Collaborative Perception](https://mlsanity.com/paper/2602.11565/) (2026)
- [CATNet: Collaborative Alignment and Transformation Network for Cooperative Perception](https://mlsanity.com/paper/2603.05255/) (2026)
- [Rethinking Air-Ground Collaboration: A Progressive Cross-Task Benchmark and Socialized Learning Framework](https://mlsanity.com/paper/2606.18841/) (2026)
- [ViCo3D: Empowering LiDAR-based Collaborative 3D Object Detection with Vision Foundation Models](https://mlsanity.com/paper/2607.12959/) (2026)

## 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