Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution

By Yan Huang, Wei Wang, Liang Wang. 2015

272 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, background): “Deep Convolutional and Recurrent Neural Networks has also been proposed and applied for activity recognition [34, 19].”
Progressive Fusion Video Super-Resolution Network via Exploiting Non-Local Spatio-Temporal Correlations (2019, methodology): “Time-based methods [11, 26, 31] consider frames as timeseries data, and send frames through the network one by”
Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation (2018, methodology): “[11] proposed BRCN using recurrent neural networks to model long-term contextual information of temporal sequences.”
Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction (2017, unknown): “In addition, previous work only modelled the recurrence of iteration or time [25] exclusively, whereas the proposed method jointly exploits both dimensions, yielding”
Deep Video Deblurring for Hand-Held Cameras (2017, methodology): “Super resolution networks have been applied to video sequences before [12, 16, 40], but these approaches”
See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-identification (2017, unknown): “And more importantly, deep neural networks have shown to be effective for person re-identification, and have achieved much better performance than traditional methods [1, 6, 9, 12, 13, 18, 25, 36, 38].”
Instance-Aware Image and Sentence Matching with Selective Multimodal LSTM (2016, methodology): “We will also consider to replace the used fully-connected RNN with a novel recurrent convolutional network [13] to better model the structural content in images as well as reduce the computational burden.”
Artificial intelligence in the creative industries: a review (2020, methodology): “Later work exploited temporal correlation via a motion compensation process before concatenating multiple warped frames into a 3D volume [95] using a recurrent architecture [90].”
Recurrent Back-Projection Network for Video Super-Resolution (2019, methodology): “In RNNs [30, 27, 13], it is not easy to jointly model subtle and significant changes (e.”
Interactive reconstruction of Monte Carlo image sequences using a recurrent denoising autoencoder (2017, methodology): “In the context of video super-resolution, good results have been demonstrated using recurrent neural networks (RNNs) [Huang et al. 2015] and sub-pixel CNNs [Shi et al.”
Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections (2016, methodology): “Other neural networks based methods such as multi-layer perceptron [1] and CNN [15] for image denoising, as well as DNN for image or video super-resolution [4, 30, 7, 14] and compression artifacts reduction [6] have been actively studied in these years.”
VRT: A Video Restoration Transformer (2022, methodology): “Existing video restoration methods can be mainly divided into two categories: sliding window-based methods [1], [2], [3], [4], [5], [6] and recurrent methods [7], [8], [9], [10], [11], [12], [13], [14], [15], [16].”
Multi-frame Quality Enhancement for Compressed Video (2018, background): “[17] developed a Bidirectional Recurrent Convolutional Network (BRCN), which improves the super-resolution performance over traditional single-frame approaches.”
Frame-Recurrent Video Super-Resolution (2018, methodology): “[16] use a bidirectional recurrent architecture for video super-resolution with shallow networks but do not use any explicit motion compensation in their model.”