R$^3$D: Regional-guided Residual Radar Diffusion

TL;DR

R3D introduces a regional-guided residual diffusion approach to enhance radar point clouds, focusing on high-frequency details and adaptive guidance to improve perception accuracy in autonomous systems.

Contribution

The paper presents a novel regional-guided residual diffusion framework that efficiently enhances radar data by focusing on residual details and adaptive regional guidance, addressing limitations of previous methods.

Findings

Outperforms state-of-the-art radar enhancement methods

Effectively captures high-frequency details in radar data

Reduces learning complexity through residual diffusion modeling

Abstract

Millimeter-wave radar enables robust environment perception in autonomous systems under adverse conditions yet suffers from sparse, noisy point clouds with low angular resolution. Existing diffusion-based radar enhancement methods either incur high learning complexity by modeling full LiDAR distributions or fail to prioritize critical structures due to uniform regional processing. To address these issues, we propose R3D, a regional-guided residual radar diffusion framework that integrates residual diffusion modeling-focusing on the concentrated LiDAR-radar residual encoding complementary high-frequency details to reduce learning difficulty-and sigma-adaptive regional guidance-leveraging radar-specific signal properties to generate attention maps and applying lightweight guidance only in low-noise stages to avoid gradient imbalance while refining key regions. Extensive experiments on the ColoRadar dataset demonstrate that R3D outperforms state-of-the-art methods, providing a practical solution for radar perception enhancement. Our anonymous code and pretrained models are released here: https://anonymous.4open.science/r/r3d-F836