Panoramic image enables deeper understanding and more holistic perception of 360∘ surrounding environment, which can naturally encode enriched scene context information compared to standard perspective image. Previous work has made lots of effort to solve the scene understanding task in a bottom-up form, thus each sub-task is processed separately and few correlations are explored in this procedure. In this paper, we propose a novel method using depth prior for holistic indoor scene understanding which recovers the objects' shapes, oriented bounding boxes and the 3D room layout simultaneously from a single panorama. In order to fully utilize the rich context information, we design a transformer-based context module to predict the representation and relationship among each component of the scene. In addition, we introduce a real-world dataset for scene understanding, including photo-realistic panoramas, high-fidelity depth images, accurately annotated room layouts, and oriented object bounding boxes and shapes. Experiments on the synthetic and real-world datasets demonstrate that our method outperforms previous panoramic scene understanding methods in terms of both layout estimation and 3D object detection.
@article{arxiv.2305.12497,
title = {PanoContext-Former: Panoramic Total Scene Understanding with a Transformer},
author = {Yuan Dong and Chuan Fang and Liefeng Bo and Zilong Dong and Ping Tan},
journal= {arXiv preprint arXiv:2305.12497},
year = {2023}
}