.png){kind=icon}
返回
Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation
.png){kind=icon}
OA
AI
DOI：10.1109/TIP.2021.3049332.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
3D spatial information is known to be beneficial to the semantic segmentation task. Most existing methods take 3D spatial data as an additional input, leading to a two-stream segmentation network that processes RGB and 3D spatial information separately. This solution greatly increases the inference time and severely limits its scope for real-time applications. To solve this problem, we propose Spatial information guided Convolution (S-Conv), which allows efficient RGB feature and 3D spatial information integration. S-Conv is competent to infer the sampling offset of the convolution kernel guided by the 3D spatial information, helping the convolutional layer adjust the receptive field and adapt to geometric transformations. S-Conv also incorporates geometric information into the feature learning process by generating spatially adaptive convolutional weights. The capability of perceiving geometry is largely enhanced without much affecting the amount of parameters and computational cost. Based on S-Conv, we further design a semantic segmentation network, called Spatial information Guided convolutional Network (SGNet), resulting in real-time inference and state-of-the-art performance on NYUDv2 and SUNRGBD datasets.
Keyword:
Convolution
Three-dimensional displays
Semantics
Kernel
Geometry
Real-time systems
Image segmentation
Spatial information
receptive field
RGBD semantic segmentation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
分享收藏
Electrochemically assisted micro localized grafting of aptamers in a microchannel engraved in fluorinated thermoplastic polymer Dyneon THV.png)
RSC Advances
RSC AdvancesIF0
PREAI
分享收藏Preparation and microwave dielectric properties of BPO4 ceramics with ultra-low dielectric constant
PREAI
分享收藏
查看更多内容