PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation
文献类型:会议论文
作者 | Gao, Naiyu3,4; He, Fei3,4; Jia, Jian3,4; Shan, Yanhu1; Zhang, Haoyang1; Zhao, Xin3,4; Huang, Kaiqi2,3,4 |
出版日期 | 2022 |
会议日期 | 2022 |
会议地点 | New Orleans |
国家 | US |
英文摘要 | 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. |
会议录 | IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
语种 | 英语 |
源URL | [http://ir.ia.ac.cn/handle/173211/48739] |
专题 | 智能系统与工程 |
通讯作者 | Zhao, Xin |
作者单位 | 1.Horizon Robotics, Inc. 2.CAS Center for Excellence in Brain Science and Intelligence Technology 3.School of Artificial Intelligence, University of Chinese Academy of Sciences 4.CRISE, Institute of Automation, Chinese Academy of Sciences |
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]. 见:. New Orleans. 2022. |
入库方式: OAI收割
来源:自动化研究所
其他版本
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。