Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution
Explore this paper's citation graph
Summary
This work proposes a bidirectional recurrent convolutional network for efficient multi-frame SR, different from vanilla RNNs, which has a low computational complexity and runs orders of magnitude faster than other multi- frame methods.
- Type
- article
- Published
- 2015-12-07
- Cited by
- 272
- References
- 47
- OpenAlex
- https://openalex.org/W2184360182
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:56486313
Keywords
Computer science, Recurrent neural network, Frame (networking), Dependency (UML), Convolutional neural network
References
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
- Learning Spatiotemporal Features with 3D Convolutional Networks
- Rectified Linear Units Improve Restricted Boltzmann Machines
- Image Super-Resolution Using Deep Convolutional Networks
- Handling motion blur in multi-frame super-resolution
- Single image super-resolution from transformed self-exemplars
- Long-term recurrent convolutional networks for visual recognition and description
- Space-time super-resolution from a single video
- Image Transformation Based on Learning Dictionaries across Image Spaces
- On Bayesian Adaptive Video Super Resolution
- A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
- Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding
- Long Short-Term Memory
- Super-resolution image reconstruction: a technical overview
- Fast image/video upsampling
- Improving resolution by image registration
- Natural Image Denoising with Convolutional Networks
- Joint MAP registration and high-resolution image estimation using a sequence of undersampled images
- Learning long-term dependencies with gradient descent is difficult
- Super-Resolution Without Explicit Subpixel Motion Estimation
Cited by
- Deep fully-connected networks for video compressive sensing
- FAST: Free Adaptive Super-Resolution via Transfer for Compressed Videos
- FOCUS: Robust Visual Codes for Everyone
- Deep Learning Convolutional Networks for Multiphoton Microscopy Vasculature Segmentation
- DeepBinaryMask: Learning a Binary Mask for Video Compressive Sensing
- Deep RNNs for video denoising
- Instance-Aware Image and Sentence Matching with Selective Multimodal LSTM
- Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation
- Deep Video Deblurring
- Video Superresolution via Motion Compensation and Deep Residual Learning
- Local Patch Classification Based Framework for Single Image Super-Resolution
- Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks
- Video Super-Resolution via Bidirectional Recurrent Convolutional Networks
- See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-identification
- Filtered Mapping-Based Method for Compressed Web Image Super-Resolution
- Super-Resolution via Deep Learning
- Interactive reconstruction of Monte Carlo image sequences using a recurrent denoising autoencoder
- cvpaper.challenge in 2016: Futuristic Computer Vision through 1, 600 Papers Survey
- Deep Video Deblurring for Hand-Held Cameras
- Deep learning for pixel-level image fusion: Recent advances and future prospects
Related papers
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
- Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
- Video Super-Resolution With Convolutional Neural Networks
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks
- Video Super-Resolution via Deep Draft-Ensemble Learning
- Deep Residual Learning for Image Recognition
- Image Super-Resolution Using Deep Convolutional Networks