SGV3D: Toward Scenario Generalization for Vision-Based Roadside 3D Object Detection

Roadside perception can significantly enhance the safety of autonomous vehicles by extending their perceptual capabilities beyond the visual range and addressing occluded regions. However, current state-of-the-art vision-based roadside detection methods exhibit high accuracy on labeled scenes but perform poorly on new scenes. This limitation arises because roadside cameras remain stationary after installation and can only gather data from a single scene, leading the algorithm to overfit these roadside backgrounds and camera positions. To tackle this issue, we propose an innovative <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b>cenario <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">G</b>eneralization Framework for <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">V</b>ision-based Roadside <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3D</b> Object Detection, called <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SGV3D</b>. Specifically, we utilize a Background-suppressed Module (BSM) to reduce background overfitting in vision-centric pipelines by diminishing background features during the 2D to bird’s-eye-view projection. Furthermore, by introducing the Semi-supervised Data Generation Pipeline (SSDG) that employs unlabeled images from new scenes, we generate diverse foreground instances with varying camera poses, mitigating the risk of overfitting to specific camera positions. Experiments conducted on two large-scale roadside benchmarks demonstrate that SGV3D, with only a minimal increase in latency, effectively improves the scenario generalization capabilities of vision-based roadside 3D object detectors. The code is available here (https://github.com/yanglei18/SGV3D).