![[2602.13555] Privacy-Concealing Cooperative Perception for BEV Scene Segmentation](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.13555] Privacy-Concealing Cooperative Perception for BEV Scene Segmentation
Summary
The paper presents a Privacy-Concealing Cooperation (PCC) framework for Bird's Eye View (BEV) semantic segmentation, enhancing autonomous vehicle perception while protecting sensitive visual data from reconstruction.
Why It Matters
As autonomous driving technology advances, ensuring the privacy of shared visual data becomes critical. This research addresses privacy concerns in cooperative perception systems, offering a solution that balances performance and data security, which is vital for public acceptance and regulatory compliance.
Key Takeaways
- Introduces a PCC framework to enhance BEV semantic segmentation.
- Employs adversarial learning to protect visual data during sharing.
- Demonstrates minimal impact on segmentation performance while improving privacy.
- Provides a public source code for further research and development.
- Addresses critical privacy concerns in autonomous vehicle technology.
Computer Science > Computer Vision and Pattern Recognition arXiv:2602.13555 (cs) [Submitted on 14 Feb 2026] Title:Privacy-Concealing Cooperative Perception for BEV Scene Segmentation Authors:Song Wang, Lingling Li, Marcus Santos, Guanghui Wang View a PDF of the paper titled Privacy-Concealing Cooperative Perception for BEV Scene Segmentation, by Song Wang and 3 other authors View PDF HTML (experimental) Abstract:Cooperative perception systems for autonomous driving aim to overcome the limited perception range of a single vehicle by communicating with adjacent agents to share sensing information. While this improves perception performance, these systems also face a significant privacy-leakage issue, as sensitive visual content can potentially be reconstructed from the shared data. In this paper, we propose a novel Privacy-Concealing Cooperation (PCC) framework for Bird's Eye View (BEV) semantic segmentation. Based on commonly shared BEV features, we design a hiding network to prevent an image reconstruction network from recovering the input images from the shared features. An adversarial learning mechanism is employed to train the network, where the hiding network works to conceal the visual clues in the BEV features while the reconstruction network attempts to uncover these clues. To maintain segmentation performance, the perception network is integrated with the hiding network and optimized end-to-end. The experimental results demonstrate that the proposed PCC framework e...