We manipulate images and videos in order to generate new ones with different properties. We are interested in methods that maintain realistic appearance of the generated image (or video).
Relevant papers
- R. Mechrez, I. Talmi, F. Shama, L. Zelnik-Manor, Maintaining Natural Image Statistics with the Contextual Loss, arXiv preprint arXiv:1803.04626, 13 Mar 2018. To appear in ACCV’2018. (arxiv , Project page)
- R. Mechrez, I. Talmi, L. Zelnik-Manor, The Contextual Loss for Image Transformation with Non-Aligned Data, arXiv preprint arXiv:1803.02077, 6 Mar 2018. Oral presentation at ECCV’2018. (arxiv , Project page)
- T. Tlusty, T. Michaeli, T. Dekel, L. Zelnik-Manor, Modifying Non-Local Variations Across Multiple Views, CVPR’2018. (arxiv, Project page)
- R. Mechrez, E. Shechtman, L. Zelnik-Manor, Saliency Driven Image Manipulation, WACV’2018. (pdf, arxiv, Project page)
- R. Mechrez, E. Shechtman, L. Zelnik-Manor, Photorealistic Style Transfer with Screened Poisson Equation, BMVC’2017. ( arxiv, Project page)
- D. Rudoy and L. Zelnik-Manor, Video Inlays: A System for User-Friendly Matchmove, VRST’2013. (pdf, Project page)