DriveFlow: Rectified Flow Adaptation for Robust 3D Object Detection in Autonomous Driving
By: Hongbin Lin , Yiming Yang , Chaoda Zheng and more
Potential Business Impact:
Makes self-driving cars see better in new places.
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.
Similar Papers
Balanced conic rectified flow
CV and Pattern Recognition
Makes AI create better pictures with less data.
GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer
CV and Pattern Recognition
Makes 3D objects look like real things from pictures.
DoGFlow: Self-Supervised LiDAR Scene Flow via Cross-Modal Doppler Guidance
CV and Pattern Recognition
Helps cars see moving objects without human help.