CoDiff: Conditional Diffusion Model for Collaborative 3D Object Detection

TL;DR

CoDiff introduces a diffusion model-based framework for collaborative 3D object detection that effectively denoises noisy multi-agent features, improving detection accuracy and robustness in autonomous driving scenarios.

Contribution

This work is the first to apply diffusion models to multi-agent collaborative perception, enhancing feature fusion robustness against pose estimation errors and delays.

Findings

Outperforms existing methods in collaborative detection accuracy

Demonstrates robustness under high-level pose and delay noise

Effective in both simulated and real-world datasets

Abstract

Collaborative 3D object detection holds significant importance in the field of autonomous driving, as it greatly enhances the perception capabilities of each individual agent by facilitating information exchange among multiple agents. However, in practice, due to pose estimation errors and time delays, the fusion of information across agents often results in feature representations with spatial and temporal noise, leading to detection errors. Diffusion models naturally have the ability to denoise noisy samples to the ideal data, which motivates us to explore the use of diffusion models to address the noise problem between multi-agent systems. In this work, we propose CoDiff, a novel robust collaborative perception framework that leverages the potential of diffusion models to generate more comprehensive and clearer feature representations. To the best of our knowledge, this is the first work to apply diffusion models to multi-agent collaborative perception. Specifically, we project high-dimensional feature map into the latent space of a powerful pre-trained autoencoder. Within this space, individual agent information serves as a condition to guide the diffusion model's sampling. This process denoises coarse feature maps and progressively refines the fused features. Experimental study on both simulated and real-world datasets demonstrates that the proposed framework CoDiff consistently outperforms existing relevant methods in terms of the collaborative object detection performance, and exhibits highly desired robustness when the pose and delay information of agents is with high-level noise. The code is released at https://github.com/HuangZhe885/CoDiff