Learning to Look around Objects for Top-View Representations of Outdoor Scenes

TL;DR

This paper introduces a neural network approach to estimate occlusion-aware top-view scene layouts from a single RGB image of outdoor scenes, improving understanding of both visible and occluded areas without requiring extensive annotations.

Contribution

The method predicts occluded scene semantics and depths directly, enhancing top-view transformation and leveraging priors from map data without needing costly annotations.

Findings

Effective occlusion reasoning improves top-view scene understanding.

Model achieves accurate semantic and depth predictions in occluded regions.

Approach outperforms baseline methods on KITTI and Cityscapes datasets.

Abstract

Given a single RGB image of a complex outdoor road scene in the perspective view, we address the novel problem of estimating an occlusion-reasoned semantic scene layout in the top-view. This challenging problem not only requires an accurate understanding of both the 3D geometry and the semantics of the visible scene, but also of occluded areas. We propose a convolutional neural network that learns to predict occluded portions of the scene layout by looking around foreground objects like cars or pedestrians. But instead of hallucinating RGB values, we show that directly predicting the semantics and depths in the occluded areas enables a better transformation into the top-view. We further show that this initial top-view representation can be significantly enhanced by learning priors and rules about typical road layouts from simulated or, if available, map data. Crucially, training our model does not require costly or subjective human annotations for occluded areas or the top-view, but rather uses readily available annotations for standard semantic segmentation. We extensively evaluate and analyze our approach on the KITTI and Cityscapes data sets.