• Corpus ID: 56657918

3DSRnet: Video Super-resolution using 3D Convolutional Neural Networks

@article{Kim20183DSRnetVS,
  title={3DSRnet: Video Super-resolution using 3D Convolutional Neural Networks},
  author={Soo Ye Kim and Jeongyeon Lim and Taeyoung Na and Munchurl Kim},
  journal={ArXiv},
  year={2018},
  volume={abs/1812.09079}
}
In video super-resolution, the spatio-temporal coherence between, and among the frames must be exploited appropriately for accurate prediction of the high resolution frames. [...] Key Method Our 3DSRnet maintains the temporal depth of spatio-temporal feature maps to maximally capture the temporally nonlinear characteristics between low and high resolution frames, and adopts residual learning in conjunction with the sub-pixel outputs. It outperforms the most state-of-the-art method with average 0.45 and 0.36 dB…Expand
Video Super-Resolution Based on 3D-CNNS with Consideration of Scene Change
TLDR
This work proposes an effective 3D-CNN for video super-resolution that does not require motion alignment as preprocessing, maintains the temporal depth of spatio-temporal feature maps to maximally capture the temporally nonlinear characteristics between low and high resolution frames, and adopts residual learning in conjunction with the sub-pixel outputs.
Video Super-Resolution using Multi-scale Pyramid 3D Convolutional Networks
TLDR
The proposed MP3D model outperforms state-of-the-art video SR methods in terms of PSNR/SSIM values, visual quality and temporal consistency, respectively.
Wide Separate 3D Convolution for Video Super Resolution
  • Xiafei Yu, Jiying Zhao
  • Computer Science
    2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)
  • 2019
TLDR
An effective separate 3D Convolution Neural Network (CNN) with wide activation is proposed to overcome the drawback of utilizing motion estimation and compensation models and reduce the computation complexity compared to 3D CNN.
Wide Activated Separate 3D Convolution for Video Super-Resolution
TLDR
The proposed wide activated separate 3 dimensional (3D) Convolution Neural Network (CNN) for video super-resolution to overcome the drawback of utilizing motion compensation models and can capture temporal and spatial information of input frames simultaneously without additional motion evaluation and compensation model.
Revisiting Temporal Modeling for Video Super-resolution
TLDR
This work carefully study and compares three temporal modeling methods and proposes a novel Recurrent Residual Network (RRN) for efficient video super-resolution, where residual learning is utilized to stabilize the training of RNN and meanwhile to boost the super- resolution performance.
Video super resolution enhancement based on two-stage 3D convolution
  • Xu Wen, Meng Zhaohui
  • 2021 6th International Conference on Intelligent Computing and Signal Processing (ICSP)
  • 2021
In recent years, computer vision has penetrated into all aspects of social production and life, especially the results achieved in image and video super-resolution processing are even more amazing.
MultiBoot Vsr: Multi-Stage Multi-Reference Bootstrapping for Video Super-Resolution
  • R. Kalarot, F. Porikli
  • Computer Science
    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2019
TLDR
A scene and class agnostic, fully convolutional neural network model for 4× video super-resolution that recurrently applies this network to reconstruct high-resolution frames and then reuse them as additional reference frames after reshuffling them into multiple low-resolution images to bootstrap and enhance image quality progressively.
Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling
TLDR
A novel deep neural network with Dual Subnet and Multi-stage Communicated Upsampling (DSMC) for super-resolution of videos with large motion and a new module named U-shaped residual dense network with 3D convolution (U3D-RDN) for fine implicit motion estimation and motion compensation as well as coarse spatial feature extraction.
Learnable Sampling 3D Convolution for Video Enhancement and Action Recognition
TLDR
This paper introduces a new module to improve the capability of 3D convolution, namely, learnable sampling 3D Convolution (LS3D-Conv), which aims to sample locations on spatial feature maps across frames with learnable 2D offsets.
Video Super-Resolution With Temporal Group Attention
TLDR
This work proposes a novel method that can effectively incorporate temporal information in a hierarchical way and achieves favorable performance against state-of-the-art methods on several benchmark datasets.
...
1
2
...

References

SHOWING 1-10 OF 30 REFERENCES
Video Super-Resolution With Convolutional Neural Networks
TLDR
This paper proposes a CNN that is trained on both the spatial and the temporal dimensions of videos to enhance their spatial resolution and shows that by using images to pretrain the model, a relatively small video database is sufficient for the training of the model to achieve and improve upon the current state-of-the-art.
Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation
TLDR
A novel joint motion compensation and video super-resolution algorithm that is orders of magnitude more efficient than competing methods, relying on a fast multi-resolution spatial transformer module that is end-to-end trainable is proposed.
Learning Spatiotemporal Features with 3D Convolutional Networks
TLDR
The learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks.
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
TLDR
This paper presents the first convolutional neural network capable of real-time SR of 1080p videos on a single K2 GPU and introduces an efficient sub-pixel convolution layer which learns an array of upscaling filters to upscale the final LR feature maps into the HR output.
Robust Video Super-Resolution with Learned Temporal Dynamics
TLDR
This work proposes a temporal adaptive neural network that can adaptively determine the optimal scale of temporal dependency and reduces the complexity of motion between neighboring frames using a spatial alignment network which is much more robust and efficient than competing alignment methods.
Image Super-Resolution Using Deep Convolutional Networks
We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep
Video Super-Resolution via Deep Draft-Ensemble Learning
TLDR
This work proposes a new direction for fast video super-resolution via a SR draft ensemble, which is defined as the set of high-resolution patch candidates before final image deconvolution, and combines SR drafts through the nonlinear process in a deep convolutional neural network (CNN).
Large-Scale Video Classification with Convolutional Neural Networks
TLDR
This work studies multiple approaches for extending the connectivity of a CNN in time domain to take advantage of local spatio-temporal information and suggests a multiresolution, foveated architecture as a promising way of speeding up the training.
Large receptive field convolutional neural network for image super-resolution
TLDR
A novel, separable structure is introduced as a reliable support for robust convolution against artifacts as well as establishing the connection between traditional optimization-based schemes and neural network architectures.
Learning a Deep Convolutional Network for Image Super-Resolution
TLDR
This work proposes a deep learning method for single image super-resolution (SR) that directly learns an end-to-end mapping between the low/high-resolution images and shows that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network.
...
1
2
3
...