Knowledge Commons of Institute of Automation,CAS
PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation | |
Gao, Naiyu1,2; He, Fei1,2; Jia, Jian1,2; Shan, Yanhu4; Zhang, Haoyang4; Zhao, Xin1,2; Huang, Kaiqi1,2,3 | |
2022 | |
会议名称 | IEEE Conference on Computer Vision and Pattern Recognition |
会议录名称 | IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
会议日期 | 2022 |
会议地点 | New Orleans |
会议举办国 | US |
摘要 | This paper presents a unified framework for depth-aware panoptic segmentation (DPS), which aims to reconstruct 3D scene with instance-level semantics from one single image. Prior works address this problem by simply adding a dense depth regression head to panoptic segmentation (PS) networks, resulting in two independent task branches. This neglects the mutually-beneficial relations between these two tasks, thus failing to exploit handy instance-level semantic cues to boost depth accuracy while also producing suboptimal depth maps. To overcome these limitations, we propose a unified framework for the DPS task by applying a dynamic convolution technique to both the PS and depth prediction tasks. Specifically, instead of predicting depth for all pixels at a time, we generate instance-specific kernels to predict depth and segmentation masks for each instance. Moreover, leveraging the instance-wise depth estimation scheme, we add additional instance-level depth cues to assist with supervising the depth learning via a new depth loss. Extensive experiments on Cityscapes-DPS and SemKITTI-DPS show the effectiveness and promise of our method. We hope our unified solution to DPS can lead a new paradigm in this area. |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48739 |
专题 | 复杂系统认知与决策实验室_智能系统与工程 |
通讯作者 | Zhao, Xin |
作者单位 | 1.CRISE, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.CAS Center for Excellence in Brain Science and Intelligence Technology 4.Horizon Robotics, Inc. |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Gao, Naiyu,He, Fei,Jia, Jian,et al. PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation[C],2022. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
PanopticDepth-CVPR20(4698KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论