.png){kind=icon}
返回
Deformable 3D Convolution for Video Super-Resolution
.png){kind=icon}
OA
AI
DOI：10.1109/LSP.2020.3013518.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The spatio-temporal information among video sequences is significant for video super-resolution (SR). However, the spatio-temporal information cannot be fully used by existing video SR methods since spatial feature extraction and temporal motion compensation are usually performed sequentially. In this paper, we propose a deformable 3D convolution network (D3Dnet) to incorporate spatio-temporal information from both spatial and temporal dimensions for video SR. Specifically, we introduce deformable 3D convolution (D3D) to integrate deformable convolution with 3D convolution, obtaining both superior spatio-temporal modeling capability and motion-aware modeling flexibility. Extensive experiments have demonstrated the effectiveness of D3D in exploiting spatio-temporal information. Comparative results show that our network achieves state-of-the-art SR performance. Code is available at: https://github.com/XinyiYing/D3Dnet.
Keyword:
Convolution
Three-dimensional displays
Motion compensation
Feature extraction
Image resolution
Signal resolution
Solid modeling
Video super-resolution
deformable convolution
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:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
Ligand‐stereoselective allosteric activation of cold‐sensing TRPM8 channels by an H‐bonded homochiral menthol dimer with head‐to‐head or head‐to‐tail.png)
Chirality
ChiralityIF0
PREAI
分享收藏Learning Temporal Dynamics for Video Super-Resolution: A Deep Learning Approach学习视频超分辨率的时间动态: 一种深度学习方法
PREAI
分享收藏N-Doped Graphene-Supported PtRu Direct Methanol Fuel Cell Electrocatalysts氮掺杂石墨烯负载PtRu直接甲醇燃料电池电催化剂
OAAI
OAAI分享收藏Prevention Is Better than Cure: The Role of IPO Syndicates in Precluding Information Acquisition*OAAI
OAAI分享收藏YIELD RESPONSE OF TABLE AND OIL OLIVE VARIETIES TO DIFFERENT WATER USE LEVELS UNDER DRIP IRRIGATION
PREAI
分享收藏
查看更多内容