Panoramic Panoptic Segmentation: Towards Complete Surrounding Understanding via Unsupervised Contrastive Learning
This addresses the need for holistic scene perception in safety-critical environments like real-world traffic, though it is incremental as it adapts existing methods to a new domain.
The paper tackles the problem of panoramic panoptic segmentation for complete surrounding understanding in intelligent vehicles, achieving over 5% improvement in PQ on the WildPPS dataset using an unsupervised contrastive learning framework.
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.