publications

2025

1. InSPE: Rapid Evaluation of Heterogeneous Multi-Modal Infrastructure Sensor Placement

   Submitted to International Conference on Computer Vision (ICCV), Mar 2025

   Zhaoliang Zheng*, Yun Zhang*, Zonglin Meng, Johnson Liu, Xin Xia, Jiaqi Ma

   Abs

   This paper introduces InSPE, a framework for evaluating heterogeneous multi-modal infrastructure sensor placement by integrating metrics like sensor coverage, occlusion, and information gain, supported by a new dataset and benchmarking experiments to optimize perception in intelligent intersections.

2. AgentAlign: Misalignment-Adapted Multi-Agent Perception for Resilient Inter-Agent Sensor Correlations

   Submitted to International Conference on Computer Vision (ICCV), Mar 2025

   Zonglin Meng, Yun Zhang, Zhaoliang Zheng, Seth Z. Zhao, Jiaqi Ma

   Abs

   This work presents AgentAlign, a real-world multi-agent perception framework that mitigates multi-modality misalignment in cooperative autonomous systems using cross-modality feature alignment and introduces the V2XSet-Noise dataset for robust evaluation.

3. RelMap: Enhancing Online Map Construction with Class-Aware Spatial Relation and Semantic Priors

   Submitted to International Conference on Computer Vision (ICCV), Mar 2025

   Tianhui Cai, Yun Zhang, Zewei Zhou, Zhiyu Huang, Jiaqi Ma

   Abs

   RelMap is an online HD map construction framework that enhances vectorized map generation using class-aware spatial relations and semantic priors, significantly improving accuracy and data efficiency on nuScenes and Argoverse 2 datasets.

4. V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Prediction

   Submitted to International Conference on Computer Vision (ICCV), Mar 2025

   Zewei Zhou, Hao Xiang, Zhaoliang Zheng, Seth Z. Zhao, Mingyue Lei, Yun Zhang, Tianhui Cai, Xinyi Liu, Johnson Liu, Maheswari Bajji, Xin Xia, Zhiyu Huang, Bolei Zhou, Jiaqi Ma

   Abs

   V2XPnP proposes a spatio-temporal fusion framework for multi-agent perception and prediction, leveraging a Transformer-based architecture and a novel sequential dataset to benchmark when, what, and how to fuse information in V2X scenarios.

5. V2X-ReaLO: An Open Online Framework and Dataset for Cooperative Perception in Reality

   Submitted to International Conference on Computer Vision (ICCV), Mar 2025

   Hao Xiang, Zhaoliang Zheng, Xin Xia, Seth Z. Zhao, Letian Gao, Zewei Zhou, Tianhui Cai, Yun Zhang, Jiaqi Ma

   Abs

   V2X-ReaLO is an open online cooperative perception framework that enables real-time V2X fusion in real-world urban environments, introducing a large-scale benchmark dataset and validating online intermediate fusion for practical deployment.