# Vision-based Lifting of 2D Object Detections for Automated Driving

Source: [Vision-based Lifting of 2D Object Detections for Automated Driving](<https://www.sota2.com/research/paper/68fa796e1e209131cea7d96a>)

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

Data updated: 2025-10-27T06:55:51.510Z

Authors: Hendrik K\\"onigshof, Kun Li, Christoph Stiller

Published: 2025-06-13T14:40:12.000Z

## Abstract

Image-based 3D object detection is an inevitable part of autonomous driving because cheap onboard cameras are already available in most modern cars. Because of the accurate depth information, currently, most state-of-the-art 3D object detectors heavily rely on LiDAR data. In this paper, we propose a pipeline which lifts the results of existing vision-based 2D algorithms to 3D detections using only cameras as a cost-effective alternative to LiDAR. In contrast to existing approaches, we focus not only on cars but on all types of road users. To the best of our knowledge, we are the first using a 2D CNN to process the point cloud for each 2D detection to keep the computational effort as low as possible. Our evaluation on the challenging KITTI 3D object detection benchmark shows results comparable to state-of-the-art image-based approaches while having a runtime of only a third.

## 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/2506.11839>)

[PDF](<https://arxiv.org/pdf/2506.11839.pdf>)
