SceneGen: Learning to Generate Realistic Traffic Scenes

TL;DR

SceneGen is a neural autoregressive model that generates realistic traffic scenes from high-definition maps and ego-vehicle states, improving fidelity for training self-driving systems.

Contribution

It introduces a rule-free, neural approach to synthesize diverse and realistic traffic scenes, surpassing heuristic-based methods.

Findings

Faithfully models real traffic scene distributions

Enhances training of perception models for real-world generalization

Outperforms heuristic-based scene generation methods

Abstract

We consider the problem of generating realistic traffic scenes automatically. Existing methods typically insert actors into the scene according to a set of hand-crafted heuristics and are limited in their ability to model the true complexity and diversity of real traffic scenes, thus inducing a content gap between synthesized traffic scenes versus real ones. As a result, existing simulators lack the fidelity necessary to train and test self-driving vehicles. To address this limitation, we present SceneGen, a neural autoregressive model of traffic scenes that eschews the need for rules and heuristics. In particular, given the ego-vehicle state and a high definition map of surrounding area, SceneGen inserts actors of various classes into the scene and synthesizes their sizes, orientations, and velocities. We demonstrate on two large-scale datasets SceneGen's ability to faithfully model distributions of real traffic scenes. Moreover, we show that SceneGen coupled with sensor simulation can be used to train perception models that generalize to the real world.