V2X-ViTv2: Improved Vision Transformers for Vehicle-to-Everything Cooperative Perception
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-01 · 47 (1) · 650-662
DOI: 10.1109/tpami.2024.3479222 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-01. Verfasst von Runsheng Xu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 51-mal zitiert (Crossref) und nennt 39 Literaturangaben.
Abstract (Originalsprache)
In this paper, we study the application of Vehicle-to-Everything (V2X) communication to improve the perception performance of autonomous vehicles. We present V2X-ViTs, a robust cooperative perception framework with V2X communication using novel vision Transformer models. First, we present V2X-ViTv1 containing holistic attention modules that can effectively fuse information across on-road agents (i.e., vehicles and infrastructure). Specifically, V2X-ViTv1 consists of alternating layers of heterogeneous multi-agent self-attention and multi-scale window self-attention, which captures inter-agent interaction and per-agent spatial relationships. These key modules are designed in a unified Transformer architecture to handle common V2X challenges, including asynchronous information sharing, pose errors, and heterogeneity of V2X components. Second, we propose an advanced architecture, V2X-ViTv2, that enjoys increased ability for multi-scale perception. We also propose advanced data augmentation techniques tailored for V2X applications to improve performance. We construct a large-scale V2X perception dataset using CARLA and OpenCDA to validate our approach. Extensive experimental results on both synthetic and real-world datasets show that V2X-ViTs achieve state-of-the-art performance for 3D object detection and are robust even under harsh, noisy environments.
Zitieren
APA
Xu, R., Chen, C. J., Tu, Z., & Yang, M. H. (2025). V2X-ViTv2: Improved Vision Transformers for Vehicle-to-Everything Cooperative Perception. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(1), 650-662. https://doi.org/10.1109/tpami.2024.3479222
Vancouver
Xu R, Chen CJ, Tu Z, Yang MH. V2X-ViTv2: Improved Vision Transformers for Vehicle-to-Everything Cooperative Perception. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(1):650-662. doi:10.1109/tpami.2024.3479222
BibTeX
@article{Xu2025,
author = {Xu, Runsheng and Chen, Chia-Ju and Tu, Zhengzhong and Yang, Ming-Hsuan},
title = {V2X-ViTv2: Improved Vision Transformers for Vehicle-to-Everything Cooperative Perception},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {1},
pages = {650--662},
doi = {10.1109/tpami.2024.3479222}
}
EUVIMED