DragTraffic: Interactive and Controllable Traffic Scene Generation for Autonomous Driving

TL;DR

DragTraffic is an interactive framework that uses conditional diffusion to generate diverse, realistic, and controllable traffic scenes for autonomous driving, aiding in system evaluation and training.

Contribution

It introduces a novel, controllable traffic scene generation method based on conditional diffusion with an adaptive architecture, enabling non-experts to create diverse scenarios.

Findings

Outperforms existing methods in realism and diversity

Enables high controllability through user customization

Demonstrates effectiveness on real-world datasets

Abstract

Evaluating and training autonomous driving systems require diverse and scalable corner cases. However, most existing scene generation methods lack controllability, accuracy, and versatility, resulting in unsatisfactory generation results. Inspired by DragGAN in image generation, we propose DragTraffic, a generalized, interactive, and controllable traffic scene generation framework based on conditional diffusion. DragTraffic enables non-experts to generate a variety of realistic driving scenarios for different types of traffic agents through an adaptive mixture expert architecture. We employ a regression model to provide a general initial solution and a refinement process based on the conditional diffusion model to ensure diversity. User-customized context is introduced through cross-attention to ensure high controllability. Experiments on a real-world driving dataset show that DragTraffic outperforms existing methods in terms of authenticity, diversity, and freedom. Demo videos and code are available at https://chantsss.github.io/Dragtraffic/.