Video Panoptic Segmentation
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9856-9865
Abstract
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.Keywords
All Related Versions
This publication has 34 references indexed in Scilit:
- SegFlow: Joint Learning for Video Object Segmentation and Optical Flow2017
- Playing for Benchmarks2017
- The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes2017
- Mask R-CNN2017
- One-Shot Video Object Segmentation2017
- FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks2017
- Learning Video Object Segmentation from Static Images2017
- Deep Feature Flow for Video Recognition2017
- Deep Residual Learning for Image Recognition2016
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016