Panoramic Panoptic Segmentation: Towards Complete Surrounding Understanding via Unsupervised Contrastive Learning

TL;DR

This paper introduces panoramic panoptic segmentation for complete scene understanding, proposes a domain transfer framework for training on standard images, and presents a new dataset, WildPPS, to advance surrounding perception in autonomous systems.

Contribution

The paper presents a novel panoramic panoptic segmentation framework with unsupervised contrastive learning and domain transfer, along with the first panoramic dataset WildPPS.

Findings

Achieved over 5% improvement in PQ on WildPPS dataset

Demonstrated effectiveness of the PRF framework in cross-domain scenarios

Provided a new dataset to facilitate research in panoramic scene understanding

Abstract

In this work, we introduce panoramic panoptic segmentation as the most holistic scene understanding both in terms of field of view and image level understanding for standard camera based input. A complete surrounding understanding provides a maximum of information to the agent, which is essential for any intelligent vehicle in order to make informed decisions in a safety-critical dynamic environment such as real-world traffic. In order to overcome the lack of annotated panoramic images, we propose a framework which allows model training on standard pinhole images and transfers the learned features to a different domain. Using our proposed method, we manage to achieve significant improvements of over 5% measured in PQ over non-adapted models on our Wild Panoramic Panoptic Segmentation (WildPPS) dataset. We show that our proposed Panoramic Robust Feature (PRF) framework is not only suitable to improve performance on panoramic images but can be beneficial whenever model training and deployment are executed on data taken from different distributions. As an additional contribution, we publish WildPPS: The first panoramic panoptic image dataset to foster progress in surrounding perception.