DFPN: Deformable Frame Prediction Network

Abstract

Learned frame prediction is a current problem of interest in computer vision and video compression. Although several deep network architectures have been proposed for learned frame prediction, to the best of our knowledge, there is no work based on using deformable convolutions for frame prediction. To this effect, we propose a deformable frame prediction network (DFPN) for task oriented implicit motion modeling and next frame prediction. Experimental results demonstrate that the proposed DFPN model achieves state of the art results in next frame prediction. Our models and results are available at https://github.com/makinyilmaz/DFPN.

arXiv commentAccepted for publication in IEEE International Conference on Image Processing (ICIP) 2021

References in corpus (5)

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• A Review on Deep Learning Techniques for Video Prediction
• GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modeling
• Effect of Architectures and Training Methods on the Performance of Learned Video Frame Prediction

Cited by in corpus (1)

• A New Multi-Picture Architecture for Learned Video Deinterlacing and Demosaicing with Parallel Deformable Convolution and Self-Attention Blocks