DFPN: Deformable Frame Prediction Network
This work addresses frame prediction for applications in video compression and computer vision, but it appears incremental as it introduces a new method based on deformable convolutions without a major paradigm shift.
The paper tackles the problem of learned frame prediction in computer vision and video compression by proposing a deformable frame prediction network (DFPN), achieving state-of-the-art results in next frame prediction.
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.