مقاله deepwarp یکی از مقالات منتشر شده در سال ۲۰۱۶ میباشد. ایده اصلی شناسایی ناحیه مربوط به چشم و سپس شناسایی ویژگی های مربوط به جهات آن در راستای اعمال جهت و زاویه به آن هاست.
توضیحات مقاله در ادامه آورده شده است:
The proposed system takes an input eye region, feature points (anchors) as well as a correction angle and sends them to the multi-scale neural network predicting a flow field. The flow field is then applied to the input image to produce an image of a redirected eye. Finally, the output is enhanced by processing with the lightness correction neural network.
- ۲۴٫۰۲٫۱۷: Check out an article (in Russian) about the technology! It comes with a Telegram bot.
- ۱۱٫۰۳٫۱۷: New! An article (in English) on the Verge.
- ۱۱٫۰۳٫۱۷: New! The online demo should be working on iOS and in the Safari browser.
In this work, we consider the task of generating highly-realistic 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.
Deep Learning network to change the gaze of the person