DriveFlow: Rectified Flow Adaptation for Robust 3D Object Detection in Autonomous Driving

TL;DR

DriveFlow is a novel method that enhances training data for 3D object detection in autonomous driving by adapting pre-trained text-to-image flow models, improving robustness against out-of-distribution scenarios.

Contribution

It introduces a rectified flow adaptation technique with frequency-based strategies to improve data augmentation for robust 3D detection without additional training.

Findings

Significant performance improvements across all categories in OOD scenarios.

Effective preservation of 3D object geometry during image editing.

Efficient data enhancement method validated by comprehensive experiments.

Abstract

In autonomous driving, vision-centric 3D object detection recognizes and localizes 3D objects from RGB images. However, due to high annotation costs and diverse outdoor scenes, training data often fails to cover all possible test scenarios, known as the out-of-distribution (OOD) issue. Training-free image editing offers a promising solution for improving model robustness by training data enhancement without any modifications to pre-trained diffusion models. Nevertheless, inversion-based methods often suffer from limited effectiveness and inherent inaccuracies, while recent rectified-flow-based approaches struggle to preserve objects with accurate 3D geometry. In this paper, we propose DriveFlow, a Rectified Flow Adaptation method for training data enhancement in autonomous driving based on pre-trained Text-to-Image flow models. Based on frequency decomposition, DriveFlow introduces two strategies to adapt noise-free editing paths derived from text-conditioned velocities. 1) High-Frequency Foreground Preservation: DriveFlow incorporates a high-frequency alignment loss for foreground to maintain precise 3D object geometry. 2) Dual-Frequency Background Optimization: DriveFlow also conducts dual-frequency optimization for background, balancing editing flexibility and semantic consistency. Comprehensive experiments validate the effectiveness and efficiency of DriveFlow, demonstrating comprehensive performance improvements on all categories across OOD scenarios. Code is available at https://github.com/Hongbin98/DriveFlow.