期刊
IEEE ROBOTICS AND AUTOMATION LETTERS
卷 7, 期 4, 页码 9302-9309出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2022.3189425
关键词
Deep learning for visual perception; object detection; segmentation and categorization; semantic scene understanding
类别
资金
- European Union's Horizon 2020 Research and Innovation Program [871449-OpenDR]
This paper presents a proposal-free framework for solving the problem of amodal panoptic segmentation. The framework incorporates multiple techniques, including amodal instance regression, feature aggregation, and occlusion reasoning, and sets a new state-of-the-art on two benchmark datasets.
Amodal panoptic segmentation aims to connect the perception of the world to its cognitive understanding. It entails simultaneously predicting the semantic labels of visible scene regions and the entire shape of traffic participant instances, including regions that may be occluded. In this work, we formulate a proposal-free framework that tackles this task as a multi-label and multi-class problem by first assigning the amodal masks to different layers according to their relative occlusion order and then employing amodal instance regression on each layer independently while learning background semantics. We propose the PAPS architecture that incorporates a shared backbone and an asymmetrical dual-decoder consisting of several modules to facilitate within-scale and cross-scale feature aggregations, bilateral feature propagation between decoders, and integration of global instance-level and local pixel-level occlusion reasoning. Further, we propose the amodal mask refiner that resolves the ambiguity in complex occlusion scenarios by explicitly leveraging the embedding of unoccluded instance masks. Extensive evaluation on the BDD100K-APS and KITTI-360-APS datasets demonstrate that our approach set the new state-of-the-art on both benchmarks.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据