Boosting Instance Awareness via Cross-View Correlation with 4D Radar and Camera for 3D Object Detection

TL;DR

SIFormer is a transformer-based method that enhances 3D object detection by integrating 4D radar and camera data, addressing radar sparsity and improving instance awareness for autonomous driving.

Contribution

It introduces a cross-view activation mechanism and a transformer-based fusion module to effectively combine radar and camera information for better 3D detection.

Findings

Achieves state-of-the-art results on multiple datasets

Effectively suppresses background noise during view transformation

Enhances instance awareness by integrating 2D cues into BEV space

Abstract

4D millimeter-wave radar has emerged as a promising sensing modality for autonomous driving due to its robustness and affordability. However, its sparse and weak geometric cues make reliable instance activation difficult, limiting the effectiveness of existing radar-camera fusion paradigms. BEV-level fusion offers global scene understanding but suffers from weak instance focus, while perspective-level fusion captures instance details but lacks holistic context. To address these limitations, we propose SIFormer, a scene-instance aware transformer for 3D object detection using 4D radar and camera. SIFormer first suppresses background noise during view transformation through segmentation- and depth-guided localization. It then introduces a cross-view activation mechanism that injects 2D instance cues into BEV space, enabling reliable instance awareness under weak radar geometry. Finally, a transformer-based fusion module aggregates complementary image semantics and radar geometry for robust perception. As a result, with the aim of enhancing instance awareness, SIFormer bridges the gap between the two paradigms, combining their complementary strengths to address inherent sparse nature of radar and improve detection accuracy. Experiments demonstrate that SIFormer achieves state-of-the-art performance on View-of-Delft, TJ4DRadSet and NuScenes datasets. Source code is available at github.com/shawnnnkb/SIFormer.