# HeightFormer: A Semantic Alignment Monocular 3D Object Detection Method from Roadside Perspective

Source: [HeightFormer: A Semantic Alignment Monocular 3D Object Detection Method from Roadside Perspective](<https://www.sota2.com/research/paper/68fa75531e209131cea67327>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:32:00.805Z

Authors: Pei Liu, Zihao Zhang, Haipeng Liu, Nanfang Zheng, Meixin Zhu, Ziyuan Pu (4) \_\_INSTITUTION\_6\_\_ Intelligent Transportation Thrust, Systems Hub, The Hong Kong University of Science, Technology, (2) School of Cyber Science, Engineering, Southeast University, (3) Li Auto Inc, (4) School of Transportation, Southeast University)

Published: 2024-10-10T09:37:33.000Z

## Abstract

The on-board 3D object detection technology has received extensive attention as a critical technology for autonomous driving, while few studies have focused on applying roadside sensors in 3D traffic object detection. Existing studies achieve the projection of 2D image features to 3D features through height estimation based on the frustum. However, they did not consider the height alignment and the extraction efficiency of bird's-eye-view features. We propose a novel 3D object detection framework integrating Spatial Former and Voxel Pooling Former to enhance 2D-to-3D projection based on height estimation. Extensive experiments were conducted using the Rope3D and DAIR-V2X-I dataset, and the results demonstrated the outperformance of the proposed algorithm in the detection of both vehicles and cyclists. These results indicate that the algorithm is robust and generalized under various detection scenarios. Improving the accuracy of 3D object detection on the roadside is conducive to building a safe and trustworthy intelligent transportation system of vehicle-road coordination and promoting the large-scale application of autonomous driving. The code and pre-trained models will be released on https://anonymous.4open.science/r/HeightFormer.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2410.07758>)

[PDF](<https://arxiv.org/pdf/2410.07758.pdf>)