Open AccessPosted Content
Non-Local ConvLSTM for Video Compression Artifact Reduction
TLDR
Zhang et al. as mentioned in this paper proposed an end-to-end deep neural network called non-local ConvLSTM (NL-ConvLSTMs) that exploits multiple consecutive frames.Abstract:Â
Video compression artifact reduction aims to recover high-quality videos from low-quality compressed videos. Most existing approaches use a single neighboring frame or a pair of neighboring frames (preceding and/or following the target frame) for this task. Furthermore, as frames of high quality overall may contain low-quality patches, and high-quality patches may exist in frames of low quality overall, current methods focusing on nearby peak-quality frames (PQFs) may miss high-quality details in low-quality frames. To remedy these shortcomings, in this paper we propose a novel end-to-end deep neural network called non-local ConvLSTM (NL-ConvLSTM in short) that exploits multiple consecutive frames. An approximate non-local strategy is introduced in NL-ConvLSTM to capture global motion patterns and trace the spatiotemporal dependency in a video sequence. This approximate strategy makes the non-local module work in a fast and low space-cost way. Our method uses the preceding and following frames of the target frame to generate a residual, from which a higher quality frame is reconstructed. Experiments on two datasets show that NL-ConvLSTM outperforms the existing methods.read more
Citations
More filters
Posted Content
RegNet: Self-Regulated Network for Image Classification.
TL;DR: A regulator module is proposed as a memory mechanism to extract complementary features of the intermediate layers, which are further fed to the ResNet, and named the new regulated network as regulated residual network (RegNet).
Journal ArticleDOI
MV-GNN: Multi-View Graph Neural Network for Compression Artifacts Reduction
Xin He,Qiong Liu,You Yang +2 more
TL;DR: A GNN-based fusion mechanism is designed to fuse the cross-view information under the aggregation and update mechanism of GNN to reduce compression artifacts in multi-view compressed images and demonstrates that the experimental results demonstrate that the MV-GNN outperforms the state-of-the-art methods.
Journal ArticleDOI
NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results
Ren Yang,Radu Timofte,Mei Zheng,Qunliang Xing,Minglang Qiao,Mai Xu,Lai Jiang,Huaida Liu,Ying Chen,Youcheng Ben,Xiang Zhao,Chen Fu,Pei Cheng,Gang Yu,Junyi Li,Ren-Rong Wu,Zhilu Zhang,Wei Shang,Zhe Lv,Yunjin Chen,Mingcai Zhou,Dongwei Ren,Kai Zhang,Wangmeng Zuo,Pavel Ostyakov,V.Z. Dmitry,Shakarim Soltanayev,Chervontsev Sergey,Zhussip Magauiya,Xueyi Zou,Youliang Yan Pablo Navarrete Michelini,Yunhua Lu,Di Zhang,Shaoli Lin,S Y Gao,Biao Wu,Cheng-yong Zheng,Xiaofeng Zhang,Kaidi Lu,Ning Wei Wang,Thuong Nguyen Canh,T T C Bach,Qing Wang,Xiaopeng Sun,Haoyu Ma,Shijie Zhao,Junlin Li,Liangbin Xie,Shu Shi,Yujiu Yang,Xintao Wang,Jinjin Gu,Chao Dong,Xiaodi Shi,Chunmei Nian,Dong-Jin Jiang,Jucai Lin,Zhihuai Xie,Dengyan Luo,Li Peng,Sheng Chen,Xin Liu,Bo Liang,Hang Dong,Yuhao Huang,Kai Ge Chen,Xin-Xin Guo,Yujing Sun,Hu Wu,Pengxu Wei,Yulin Huang,Ik Hyun Lee,Sunder Ali Khowaja,Jiseok Yoon +73 more
TL;DR: This paper reviews the NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video and proposed the LDV 2.0 dataset, which includes theLDV dataset (240 videos) and 95 additional videos.
Proceedings ArticleDOI
DAVD-Net: Deep Audio-Aided Video Decompression of Talking Heads
TL;DR: This work presents a novel deep convolutional neural network method that can exploit the audio-video correlations to repair compression defects in the face region and improves reconstruction quality by embedding into the DCNN the encoder information of the video compression standards and introducing a constraining projection module in the network.
Journal ArticleDOI
A Robust Quality Enhancement Method Based on Joint Spatial-Temporal Priors for Video Coding
TL;DR: This article proposes a robust multi-frame guided attention network (MGANet) to reconstruct high-quality frames based on HEVC compressed videos and presents extensive experimental results to demonstrate the robustness of the method.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal ArticleDOI
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.
Proceedings ArticleDOI
Non-local Neural Networks
TL;DR: In this article, the non-local operation computes the response at a position as a weighted sum of the features at all positions, which can be used to capture long-range dependencies.
Journal ArticleDOI
Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering
TL;DR: An algorithm based on an enhanced sparse representation in transform domain based on a specially developed collaborative Wiener filtering achieves state-of-the-art denoising performance in terms of both peak signal-to-noise ratio and subjective visual quality.