Efficient Feature Aggregation and Scale-Aware Regression for Monocular 3D Object Detection

TL;DR

This paper introduces MonoASRH, a novel monocular 3D object detection framework that uses global feature aggregation and scale-aware regression to improve detection accuracy, especially for small and variably scaled objects.

Contribution

The paper proposes MonoASRH with EH-FAM and ASRH modules, enabling global semantic feature extraction and dynamic scale-aware 3D regression, advancing monocular 3D detection methods.

Findings

Achieves state-of-the-art results on KITTI and Waymo datasets.

Effectively detects small-scale and variably scaled objects.

Improves feature representation through global receptive fields.

Abstract

Monocular 3D object detection has attracted great attention due to simplicity and low cost. Existing methods typically follow conventional 2D detection paradigms, first locating object centers and then predicting 3D attributes via neighboring features. However, these methods predominantly rely on progressive cross-scale feature aggregation and focus solely on local information, which may result in a lack of global awareness and the omission of small-scale objects. In addition, due to large variation in object scales across different scenes and depths, inaccurate receptive fields often lead to background noise and degraded feature representation. To address these issues, we introduces MonoASRH, a novel monocular 3D detection framework composed of Efficient Hybrid Feature Aggregation Module (EH-FAM) and Adaptive Scale-Aware 3D Regression Head (ASRH). Specifically, EH-FAM employs multi-head attention with a global receptive field to extract semantic features for small-scale objects and leverages lightweight convolutional modules to efficiently aggregate visual features across different scales. The ASRH encodes 2D bounding box dimensions and then fuses scale features with the semantic features aggregated by EH-FAM through a scale-semantic feature fusion module. The scale-semantic feature fusion module guides ASRH in learning dynamic receptive field offsets, incorporating scale priors into 3D position prediction for better scale-awareness. Extensive experiments on the KITTI and Waymo datasets demonstrate that MonoASRH achieves state-of-the-art performance.