CATNet: Collaborative Alignment and Transformation Network for Cooperative Perception

2026-03-05

AI Summary

This work addresses the challenge of information fusion in multi-agent collaborative perception, where high temporal latency and multi-source noise severely degrade performance. To this end, the authors propose an adaptive compensation fusion framework comprising three key components: a spatiotemporal recurrent synchronization mechanism (STSync) for precise alignment of asynchronous data streams, a wavelet-enhanced dual-branch denoiser (WTDen) to effectively suppress multi-source noise, and an adaptive feature selection module (AdpSel) that dynamically preserves critical perceptual features. Extensive experiments demonstrate that the proposed method significantly outperforms existing approaches across multiple benchmark datasets, exhibiting superior robustness and adaptability in complex traffic scenarios.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Multiagent Systems: Coordination and Collaboration

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Cooperative perception significantly enhances scene understanding by integrating complementary information from diverse agents. However, existing research often overlooks critical challenges inherent in real-world multi-source data integration, specifically high temporal latency and multi-source noise. To address these practical limitations, we propose Collaborative Alignment and Transformation Network (CATNet), an adaptive compensation framework that resolves temporal latency and noise interference in multi-agent systems. Our key innovations can be summarized in three aspects. First, we introduce a Spatio-Temporal Recurrent Synchronization (STSync) that aligns asynchronous feature streams via adjacent-frame differential modeling, establishing a temporal-spatially unified representation space. Second, we design a Dual-Branch Wavelet Enhanced Denoiser (WTDen) that suppresses global noise and reconstructs localized feature distortions within aligned representations. Third, we construct an Adaptive Feature Selector (AdpSel) that dynamically focuses on critical perceptual features for robust fusion. Extensive experiments on multiple datasets demonstrate that CATNet consistently outperforms existing methods under complex traffic conditions, proving its superior robustness and adaptability.

Problem

• cooperative perception
• temporal latency
• multi-source noise
• asynchronous data
• feature fusion

Innovation

• Collaborative Perception
• Temporal Alignment
• Wavelet Denoising
• Adaptive Fusion
• Multi-agent Systems