Semantic Segmentation of Panoramic Images Using a Synthetic Dataset
Panoramic images have advantages in information capacity and scene stability due to their large field of view (FoV). In this paper, we propose a method to synthesize a new dataset of panoramic image. We managed to stitch the images taken from different directions into panoramic images, together with their labeled images, to yield the panoramic semantic segmentation dataset denominated as SYNTHIA-PANO. For the purpose of finding out the effect of using panoramic images as training dataset, we designed and performed a comprehensive set of experiments. Experimental results show that using panoramic images as training data is beneficial to the segmentation result. In addition, it has been shown that by using panoramic images with a 180 degree FoV as training data the model has better performance. Furthermore, the model trained with panoramic images also has a better capacity to resist the image distortion.
Code (1)
Tasks
SegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Multi-source Domain Adaptation for Panoramic Semantic Segmentation
Unsupervised domain adaptation methods for panoramic semantic segmentation utilize real pinhole images or low-cost synthetic panoramic images to transfer segmentation models to real panoramic images. However, these metho…
Domain AdaptationSegmentationSemantic SegmentationUnsupervised Domain AdaptationBehind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation
In this paper, we address panoramic semantic segmentation which is under-explored due to two critical challenges: (1) image distortions and object deformations on panoramas; (2) lack of semantic annotations in the 360{\d…
Domain AdaptationPseudo LabelSegmentationSemantic Segmentation+1Semantics Distortion and Style Matter: Towards Source-free UDA for Panoramic Segmentation
This paper addresses an interesting yet challenging problem-- source-free unsupervised domain adaptation (SFUDA) for pinhole-to-panoramic semantic segmentation--given only a pinhole image-trained model (i.e. source) …
Domain AdaptationERPSemantic SegmentationTransfer Learning+1Semantics, Distortion, and Style Matter: Towards Source-free UDA for Panoramic Segmentation
This paper addresses an interesting yet challenging problem -- source-free unsupervised domain adaptation (SFUDA) for pinhole-to-panoramic semantic segmentation -- given only a pinhole image-trained model (i.e., source) …
Domain AdaptationERPSemantic SegmentationTransfer Learning+1DensePASS: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation with Attention-Augmented Context Exchange
Intelligent vehicles clearly benefit from the expanded Field of View (FoV) of the 360-degree sensors, but the vast majority of available semantic segmentation training images are captured with pinhole cameras. In this wo…
Domain AdaptationSegmentationSemantic SegmentationUnsupervised Domain Adaptation