paper-with-me

Papers

Deformable 3D Convolution for Video Super-Resolution

2020-04-06 · Xinyi Ying, Longguang Wang, Yingqian Wang, Weidong Sheng, Wei An, Yulan Guo

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.

📄 PDF Abstract BibTeX arXiv:2004.02803

Code (1)

XinyiYing/D3Dnet 공식 구현 pytorch

Tasks

Motion CompensationSuper-ResolutionVideo Super-Resolution

Methods 이 논문이 사용한 방법론

Deformable Convolution Deformable convolutions add 2D offsets to the regular grid sampling locations in the standard convolution. It enables free…
3D Convolution A 3D Convolution is a type of convolution where the kernel slides in 3 dimensions as opposed to 2 dimensions with 2D…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Deformable Kernel Convolutional Network for Video Extreme Super-Resolution

2020-10-01 · Xuan Xu, Xin Xiong, Jinge Wang, Xin Li

Video super-resolution, which attempts to reconstruct high-resolution video frames from their corresponding low-resolution versions, has received increasingly more attention in recent years. Most existing approaches opt …

Super-ResolutionVideo Super-Resolution

Understanding Deformable Alignment in Video Super-Resolution

2020-09-15 · Kelvin C. K. Chan, Xintao Wang, Ke Yu, Chao Dong 외

Deformable convolution, originally proposed for the adaptation to geometric variations of objects, has recently shown compelling performance in aligning multiple frames and is increasingly adopted for video super-resolut…

DiversityOptical Flow EstimationSuper-ResolutionVideo Super-Resolution

Temporal Modulation Network for Controllable Space-Time Video Super-Resolution

2021-04-21 · CVPR 2021 1 · Gang Xu, Jun Xu, Zhen Li, Liang Wang 외

Space-time video super-resolution (STVSR) aims to increase the spatial and temporal resolutions of low-resolution and low-frame-rate videos. Recently, deformable convolution based methods have achieved promising STVSR pe…

Space-time Video Super-resolutionSuper-ResolutionVideo Super-Resolution

EDVR: Video Restoration with Enhanced Deformable Convolutional Networks

2019-05-07 · Xintao Wang, Kelvin C. K. Chan, Ke Yu, Chao Dong 외

Video restoration tasks, including super-resolution, deblurring, etc, are drawing increasing attention in the computer vision community. A challenging benchmark named REDS is released in the NTIRE19 Challenge. This new b…

DeblurringSuper-ResolutionVideo EnhancementVideo Restoration+1

Deformable Non-local Network for Video Super-Resolution

2019-09-24 · Hua Wang, Dewei Su, Chuangchuang Liu, Longcun Jin 외

The video super-resolution (VSR) task aims to restore a high-resolution (HR) video frame by using its corresponding low-resolution (LR) frame and multiple neighboring frames. At present, many deep learning-based VSR meth…

Optical Flow EstimationSuper-ResolutionVideo Super-Resolution