HyperCon: Image-To-Video Model Transfer for Video-To-Video Translation Tasks
@article{Szeto2019HyperConIM, title={HyperCon: Image-To-Video Model Transfer for Video-To-Video Translation Tasks}, author={Ryan Szeto and Mostafa El-Khamy and Jungwon Lee and Jason J. Corso}, journal={ArXiv}, year={2019}, volume={abs/1912.04950} }
Video-to-video translation for super-resolution, inpainting, style transfer, etc. is more difficult than corresponding image-to-image translation tasks due to the temporal consistency problem that, if left unaddressed, results in distracting flickering effects. Although video models designed from scratch produce temporally consistent results, training them to match the vast visual knowledge captured by image models requires an intractable number of videos. To combine the benefits of image and… Expand
Figures and Tables from this paper
References
SHOWING 1-10 OF 54 REFERENCES
Deep Video Inpainting
- Computer Science
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2019
- 37
- Highly Influential
- PDF
Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation
- Computer Science
- ACM Multimedia
- 2019
- 7
- PDF
Copy-and-Paste Networks for Deep Video Inpainting
- Computer Science
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- 2019
- 15
- Highly Influential
- PDF
Frame-Recurrent Video Super-Resolution
- Computer Science, Mathematics
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- 2018
- 157
- PDF