DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation

Published in 14th European Conference on Computer Vision (ECCV), 2016

Recommended citation: Ganin, Yaroslav & Kononenko, Daniil & Sungatullina, Diana & Lempitsky, Victor. (2016). DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation. 9906. 311-326. 10.1007/978-3-319-46475-6_20.

[PDF] [Project Page]


In this work, we consider the task of generating highlyrealistic images of a given face with a redirected gaze. We treat this problem as a specific instance of conditional image generation and suggest a new deep architecture that can handle this task very well as revealed by numerical comparison with prior art and a user study. Our deep architecture performs coarse-to-fine warping with an additional intensity correction of individual pixels. All these operations are performed in a feed-forward manner, and the parameters associated with different operations are learned jointly in the end-to-end fashion. After learning, the resulting neural network can synthesize images with manipulated gaze, while the redirection angle can be selected arbitrarily from a certain range and provided as an input to the network