Video Panoptic Segmentation
This work addresses the problem of consistent visual recognition in videos for applications like autonomous driving and video analysis, though it is incremental as it extends an existing image task to video.
The paper introduces video panoptic segmentation, a new task that unifies semantic and instance segmentation across video frames, and presents two datasets (VIPER and Cityscapes-VPS) and a network (VPSNet) with a new metric (VPQ), achieving state-of-the-art results in image PQ on Cityscapes and VPQ on the new datasets.
Panoptic segmentation has become a new standard of visual recognition task by unifying previous semantic segmentation and instance segmentation tasks in concert. In this paper, we propose and explore a new video extension of this task, called video panoptic segmentation. The task requires generating consistent panoptic segmentation as well as an association of instance ids across video frames. To invigorate research on this new task, we present two types of video panoptic datasets. The first is a re-organization of the synthetic VIPER dataset into the video panoptic format to exploit its large-scale pixel annotations. The second is a temporal extension on the Cityscapes val. set, by providing new video panoptic annotations (Cityscapes-VPS). Moreover, we propose a novel video panoptic segmentation network (VPSNet) which jointly predicts object classes, bounding boxes, masks, instance id tracking, and semantic segmentation in video frames. To provide appropriate metrics for this task, we propose a video panoptic quality (VPQ) metric and evaluate our method and several other baselines. Experimental results demonstrate the effectiveness of the presented two datasets. We achieve state-of-the-art results in image PQ on Cityscapes and also in VPQ on Cityscapes-VPS and VIPER datasets. The datasets and code are made publicly available.